Runaway CPU investigation for python3.13: busy poll at read_tsc

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer attributed a high-CPU/busy-poll signal to `python3.13`, but the evidence shows an application process: `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The excerpted strace is a 1-second supervisor loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD`, then `poll(..., 1000) = 0`. The sampled process is also `S (sleeping)` in `poll_schedule_timeout`, which does not identify a CPython runtime defect.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch. Prepare a no-patch diagnosis that the collected signal is not pull-request-ready for `python3.13`; it appears to be an application-level supervisor event loop or profiler misattribution, not a demonstrated interpreter bug.

## Patch Plan
Do not edit files in this pass. If later evidence proves a CPython defect, investigate the exact runtime path first, following CPython conventions from `README.rst` and the Developer Guide.

Relevant local conventions/helpers found:
`Modules/selectmodule.c` uses `_PyDeadline_Init`, `_PyDeadline_Get`, `_PyTime_AsMilliseconds`, `Py_BEGIN_ALLOW_THREADS`, and EINTR signal checks around `poll()`.
`Modules/posixmodule.c` uses Argument Clinic wrappers, `posix_error()`, `wait_helper()`, `Py_BEGIN_ALLOW_THREADS`, and `PyErr_CheckSignals()` around `wait4()`/`waitpid()`.
`Lib/subprocess.py` already handles `ECHILD` in process polling paths.

No prior Fixer patch for this issue was found in the workspace or Debian patch stack. Since this is a no-patch plan, there is no control-flow change to make; if a future patch is justified, avoid awkward `goto` where a bounded helper or existing EINTR loop pattern fits.

## Risks
A source patch based only on this evidence would likely change CPython behavior without a demonstrated failing CPython invariant. The `poll(..., 1000)` timeout and `wait4(..., WNOHANG)` pattern can be normal application scheduling behavior. The backtrace excerpt is weak: symbols are mostly unresolved and do not point to a specific CPython source bug.

## Validation
First try the project-level entrypoint from the workspace root: `./configure && make`. If it fails due to missing dependencies or generated files, record the exact command and failure reason.

For a bounded independent check of the collected signal, run a tiny straced Python loop after build, preferably with `./python`, that performs `os.waitpid(-1, os.WNOHANG)` with no children and `select.poll().poll(1000)` on an idle pipe. This can show the syscall pattern is easy to produce without proving an interpreter failure. If no source patch is made, no focused compile is needed beyond documenting the diagnosis and build availability.

## Patch Pass

Subject: Diagnose inferred python3.13 poll signal without source changes

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` evidence points to a Python-hosted `supervisord` process waking once per second, calling `wait4(..., WNOHANG)` with no children, and then sleeping in `poll(..., 1000)`. That is not enough evidence for an upstream CPython runtime patch.

## Evidence Confidence
inferred

## Issue Connection
The collected signal is a `python3.13` process reported as high CPU, with perf samples in `read_tsc`, strace showing repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`, and `/proc` showing the process sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the interpreter binary is hosting an application event loop from `/usr/bin/supervisord`, not that CPython’s `poll()` or `wait4()` wrappers are spinning incorrectly. Nearby CPython code already uses the expected local patterns: `_PyDeadline_Init()` / `_PyDeadline_Get()` around `poll()`, `Py_BEGIN_ALLOW_THREADS` around blocking syscalls, EINTR retry handling with `PyErr_CheckSignals()`, Argument Clinic wrappers, and existing `subprocess` handling for `ECHILD`.

The specific change made is no source change. I followed the saved plan and did not change course.

The expected effect is to avoid landing a speculative CPython patch from indirect profiler evidence. A stronger upstream report would need an application-independent reproducer or a trace showing a CPython invariant being violated.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional missing modules `_dbm`, `_gdbm`, and `_tkinter`; it also built `_ssl` but removed it because import failed with `undefined symbol: TLSv1_method`.

Attempted bounded syscall reproduction:

`timeout 5 strace -f -e trace=poll,wait4 ./python - <<'PY' ...`

This was blocked by the environment: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 6): Operation not permitted`. Because the independent trace could not run, I did not classify the issue as reproduced.

Checked contribution/style context in `README.rst`, which points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. Inspected `Modules/selectmodule.c`, `Modules/posixmodule.c`, and `Lib/subprocess.py` for local wait/poll helpers and conventions. Final `git status --short` is clean.

## Review Pass 1

RESULT: ok

No blocking findings.

The worktree is clean, `## Git Add Paths` is `None`, and the author correctly treats the evidence as `inferred` rather than landing a speculative CPython source patch. The diagnosis matches the evidence bundle: a Python-hosted `supervisord` process is sleeping in `poll_schedule_timeout` while periodically calling `wait4(..., WNOHANG)` and `poll(..., 1000)`.

The response includes the required evidence confidence section, avoids claiming local reproduction after `strace` was blocked by ptrace permissions, reports the project-level `./configure && make` validation result, and names relevant CPython conventions/helpers in the inspected wait/poll paths.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer attributed a high-CPU/busy-poll signal to `python3.13`, but the evidence shows an application process: `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The excerpted strace is a 1-second supervisor loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD`, then `poll(..., 1000) = 0`. The sampled process is also `S (sleeping)` in `poll_schedule_timeout`, which does not identify a CPython runtime defect.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch. Prepare a no-patch diagnosis that the collected signal is not pull-request-ready for `python3.13`; it appears to be an application-level supervisor event loop or profiler misattribution, not a demonstrated interpreter bug.

## Patch Plan
Do not edit files in this pass. If later evidence proves a CPython defect, investigate the exact runtime path first, following CPython conventions from `README.rst` and the Developer Guide.

Relevant local conventions/helpers found:
`Modules/selectmodule.c` uses `_PyDeadline_Init`, `_PyDeadline_Get`, `_PyTime_AsMilliseconds`, `Py_BEGIN_ALLOW_THREADS`, and EINTR signal checks around `poll()`.
`Modules/posixmodule.c` uses Argument Clinic wrappers, `posix_error()`, `wait_helper()`, `Py_BEGIN_ALLOW_THREADS`, and `PyErr_CheckSignals()` around `wait4()`/`waitpid()`.
`Lib/subprocess.py` already handles `ECHILD` in process polling paths.

No prior Fixer patch for this issue was found in the workspace or Debian patch stack. Since this is a no-patch plan, there is no control-flow change to make; if a future patch is justified, avoid awkward `goto` where a bounded helper or existing EINTR loop pattern fits.

## Risks
A source patch based only on this evidence would likely change CPython behavior without a demonstrated failing CPython invariant. The `poll(..., 1000)` timeout and `wait4(..., WNOHANG)` pattern can be normal application scheduling behavior. The backtrace excerpt is weak: symbols are mostly unresolved and do not point to a specific CPython source bug.

## Validation
First try the project-level entrypoint from the workspace root: `./configure && make`. If it fails due to missing dependencies or generated files, record the exact command and failure reason.

For a bounded independent check of the collected signal, run a tiny straced Python loop after build, preferably with `./python`, that performs `os.waitpid(-1, os.WNOHANG)` with no children and `select.poll().poll(1000)` on an idle pipe. This can show the syscall pattern is easy to produce without proving an interpreter failure. If no source patch is made, no focused compile is needed beyond documenting the diagnosis and build availability.

## Patch Pass

Subject: Diagnose inferred python3.13 poll signal without source changes

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` evidence points to a Python-hosted `supervisord` process waking once per second, calling `wait4(..., WNOHANG)` with no children, and then sleeping in `poll(..., 1000)`. That is not enough evidence for an upstream CPython runtime patch.

## Evidence Confidence
inferred

## Issue Connection
The collected signal is a `python3.13` process reported as high CPU, with perf samples in `read_tsc`, strace showing repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`, and `/proc` showing the process sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the interpreter binary is hosting an application event loop from `/usr/bin/supervisord`, not that CPython’s `poll()` or `wait4()` wrappers are spinning incorrectly. Nearby CPython code already uses the expected local patterns: `_PyDeadline_Init()` / `_PyDeadline_Get()` around `poll()`, `Py_BEGIN_ALLOW_THREADS` around blocking syscalls, EINTR retry handling with `PyErr_CheckSignals()`, Argument Clinic wrappers, and existing `subprocess` handling for `ECHILD`.

The specific change made is no source change. I followed the saved plan and did not change course.

The expected effect is to avoid landing a speculative CPython patch from indirect profiler evidence. A stronger upstream report would need an application-independent reproducer or a trace showing a CPython invariant being violated.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional missing modules `_dbm`, `_gdbm`, and `_tkinter`; it also built `_ssl` but removed it because import failed with `undefined symbol: TLSv1_method`.

Attempted bounded syscall reproduction:

`timeout 5 strace -f -e trace=poll,wait4 ./python - <<'PY' ...`

This was blocked by the environment: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 6): Operation not permitted`. Because the independent trace could not run, I did not classify the issue as reproduced.

Checked contribution/style context in `README.rst`, which points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. Inspected `Modules/selectmodule.c`, `Modules/posixmodule.c`, and `Lib/subprocess.py` for local wait/poll helpers and conventions. Final `git status --short` is clean.

## Review Pass 1

RESULT: ok

No blocking findings.

The worktree is clean, `## Git Add Paths` is `None`, and the author correctly treats the evidence as `inferred` rather than landing a speculative CPython source patch. The diagnosis matches the evidence bundle: a Python-hosted `supervisord` process is sleeping in `poll_schedule_timeout` while periodically calling `wait4(..., WNOHANG)` and `poll(..., 1000)`.

The response includes the required evidence confidence section, avoids claiming local reproduction after `strace` was blocked by ptrace permissions, reports the project-level `./configure && make` validation result, and names relevant CPython conventions/helpers in the inspected wait/poll paths.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `python3.13`, but the command line is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The strace excerpt shows a 1-second `poll()` timeout followed by `wait4(..., WNOHANG)` returning `ECHILD`, and the process state/wchan show it sleeping in `poll_schedule_timeout`, not spinning in a CPython runtime loop. The available evidence is profiler/trace evidence from an application entrypoint, not a demonstrated Python interpreter defect.

## Evidence Confidence
observed

## Proposed Subject
No source patch: diagnose as not currently actionable in upstream `python3.13` without additional application-level evidence.

## Patch Plan
Do not edit CPython in this pass. The observed loop appears to be supervisord’s event/reap cycle running under Python, not a CPython busy-poll bug.

Before any future source patch, collect evidence that isolates a Python-owned failure from the application:
- confirm the original `/usr/bin/supervisord` process still shows high CPU while blocking `poll(..., 1000)` calls are occurring;
- capture Python-level stack frames for supervisord, if possible, rather than only C frames around `_PyEval_EvalFrameDefault`;
- compare with a minimal Python `select.poll(..., 1000)` plus `os.wait4(-1, os.WNOHANG)` loop to verify whether the alleged signal is simply expected periodic wakeup behavior.

Contribution/style docs checked: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `Doc/README.rst` covers documentation style. Local subsystem scan found CPython wrappers/conventions such as `pycore_time.h` timeout conversion in `Modules/selectmodule.c`, `_del_safe.waitpid` in `Lib/subprocess.py`, and `PyMem_RawMalloc`/`pthread_attr_destroy` handling in `Python/thread_pthread.h`, but no relevant local helper for an upstream change because the evidence does not implicate those subsystems. No prior Fixer patch is present in the workspace, so there is nothing to replace. No awkward control flow such as `goto` should be introduced because no patch is planned.

## Risks
A CPython patch based on this evidence would likely optimize or alter normal application behavior and could regress correct `poll()`, `wait4()`, subprocess, or event-loop semantics. The profiler’s `read_tsc` and `_PyEval_EvalFrameDefault` samples are too indirect to identify a runtime bug.

## Validation
First try the project-level entrypoint from the workspace root before any narrower check: `./configure && make`.

If that fails due to missing dependencies or generated files, record the exact failure and then run the narrowest relevant clean-check command, likely a syntax/build smoke check only, because no source patch is planned.

Bounded independent reproduction attempt: run a small Python script that performs the same safe syscall shape, `wait4(-1, WNOHANG)` followed by `poll(..., 1000)`, under `strace -tt -e poll,wait4` for a few seconds. This should confirm whether the observed trace shape can occur without a CPython defect; it should not be claimed as reproducing the reported high CPU unless it actually shows high CPU.

## Patch Pass

Subject: Diagnose python3.13 busy-poll trace without source changes

## Commit Message
The likely root cause is not a CPython runtime loop. The collected `/proc` and strace evidence shows an application process, `supervisord`, running under Python and periodically calling `wait4(..., WNOHANG)` before blocking in `poll(..., 1000)` for about one second.

No source change is included. The evidence is profiler and syscall-trace based, and it does not isolate a Python-owned bug from the application event loop.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU signal for `python3.13`: perf samples included `read_tsc` and `_PyEval_EvalFrameDefault`, strace repeatedly showed `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)`, and `/proc` showed the sampled process named `supervisord` sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the trace reflects supervisord’s application-level event/reap loop, not a CPython busy-poll defect. CPython’s nearby poll path in `Modules/selectmodule.c` already uses `_PyDeadline_*` timeout handling and releases the GIL around `poll()`, and `Lib/subprocess.py` uses `_del_safe.waitpid` plus `_waitpid_lock` for nonblocking process reaping. The `pthread_attr_destroy` frame in the evidence is not enough to identify a thread-runtime defect.

I followed the saved plan’s no-patch direction. I changed the confidence from the plan’s `observed` to `inferred` because this authoring pass explicitly classifies profiler/strace-only evidence as indirect unless stronger evidence is gathered. The expected effect is that this proposal avoids an upstream CPython diff that would be speculative and gives maintainers a focused diagnosis for collecting application-level evidence instead.

Style and helper checks: `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `Doc/README.rst` documents documentation style. No relevant local helper was found for a source change because no CPython subsystem was proven faulty.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. The command exited successfully, but the build reported optional/environment module issues: `_ssl failed to import` with `undefined symbol: TLSv1_method`, missing `_dbm`, `_gdbm`, and `_tkinter`, and `Could not build the ssl module! Python requires a OpenSSL 1.1.1 or newer`.

Attempted bounded strace reproduction:
`/usr/bin/time -f 'cpu=%P user=%U sys=%S elapsed=%e' timeout 5 strace -qq -tt -e trace=poll,wait4 ./python ...`
Blocked by sandbox ptrace permissions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 7): Operation not permitted`.

Ran the same Python `wait4(WNOHANG)` plus `poll(1000)` smoke loop without strace. Result: `iterations=4`, `cpu=0% user=0.00 sys=0.00 elapsed=4.01`. This did not reproduce runaway CPU.

## Review Pass 1

RESULT: ok

No source changes are present: `git status --short` is clean, `git diff --stat` is empty, and a direct diff against the original snapshot only shows workspace metadata directories.

The patch output is a no-patch diagnosis, which is appropriate for the evidence level. It includes `## Evidence Confidence` with an allowed value (`inferred`), does not claim reproduction, does not invent a CPython failure, and explains why the perf/strace `/proc` signal points more plausibly at an application-level `supervisord` poll/reap loop than at an upstream interpreter defect.

Validation is acceptable for a no-patch report: the project-level `./configure && make` entrypoint was attempted and reported with the `_ssl`/optional-module build caveats, and the bounded strace reproduction attempt clearly records the ptrace permission blocker plus a non-strace smoke check result.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `python3.13`, but the command line is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The strace excerpt shows a 1-second `poll()` timeout followed by `wait4(..., WNOHANG)` returning `ECHILD`, and the process state/wchan show it sleeping in `poll_schedule_timeout`, not spinning in a CPython runtime loop. The available evidence is profiler/trace evidence from an application entrypoint, not a demonstrated Python interpreter defect.

## Evidence Confidence
observed

## Proposed Subject
No source patch: diagnose as not currently actionable in upstream `python3.13` without additional application-level evidence.

## Patch Plan
Do not edit CPython in this pass. The observed loop appears to be supervisord’s event/reap cycle running under Python, not a CPython busy-poll bug.

Before any future source patch, collect evidence that isolates a Python-owned failure from the application:
- confirm the original `/usr/bin/supervisord` process still shows high CPU while blocking `poll(..., 1000)` calls are occurring;
- capture Python-level stack frames for supervisord, if possible, rather than only C frames around `_PyEval_EvalFrameDefault`;
- compare with a minimal Python `select.poll(..., 1000)` plus `os.wait4(-1, os.WNOHANG)` loop to verify whether the alleged signal is simply expected periodic wakeup behavior.

Contribution/style docs checked: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `Doc/README.rst` covers documentation style. Local subsystem scan found CPython wrappers/conventions such as `pycore_time.h` timeout conversion in `Modules/selectmodule.c`, `_del_safe.waitpid` in `Lib/subprocess.py`, and `PyMem_RawMalloc`/`pthread_attr_destroy` handling in `Python/thread_pthread.h`, but no relevant local helper for an upstream change because the evidence does not implicate those subsystems. No prior Fixer patch is present in the workspace, so there is nothing to replace. No awkward control flow such as `goto` should be introduced because no patch is planned.

## Risks
A CPython patch based on this evidence would likely optimize or alter normal application behavior and could regress correct `poll()`, `wait4()`, subprocess, or event-loop semantics. The profiler’s `read_tsc` and `_PyEval_EvalFrameDefault` samples are too indirect to identify a runtime bug.

## Validation
First try the project-level entrypoint from the workspace root before any narrower check: `./configure && make`.

If that fails due to missing dependencies or generated files, record the exact failure and then run the narrowest relevant clean-check command, likely a syntax/build smoke check only, because no source patch is planned.

Bounded independent reproduction attempt: run a small Python script that performs the same safe syscall shape, `wait4(-1, WNOHANG)` followed by `poll(..., 1000)`, under `strace -tt -e poll,wait4` for a few seconds. This should confirm whether the observed trace shape can occur without a CPython defect; it should not be claimed as reproducing the reported high CPU unless it actually shows high CPU.

## Patch Pass

Subject: Diagnose python3.13 busy-poll trace without source changes

## Commit Message
The likely root cause is not a CPython runtime loop. The collected `/proc` and strace evidence shows an application process, `supervisord`, running under Python and periodically calling `wait4(..., WNOHANG)` before blocking in `poll(..., 1000)` for about one second.

No source change is included. The evidence is profiler and syscall-trace based, and it does not isolate a Python-owned bug from the application event loop.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU signal for `python3.13`: perf samples included `read_tsc` and `_PyEval_EvalFrameDefault`, strace repeatedly showed `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)`, and `/proc` showed the sampled process named `supervisord` sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the trace reflects supervisord’s application-level event/reap loop, not a CPython busy-poll defect. CPython’s nearby poll path in `Modules/selectmodule.c` already uses `_PyDeadline_*` timeout handling and releases the GIL around `poll()`, and `Lib/subprocess.py` uses `_del_safe.waitpid` plus `_waitpid_lock` for nonblocking process reaping. The `pthread_attr_destroy` frame in the evidence is not enough to identify a thread-runtime defect.

I followed the saved plan’s no-patch direction. I changed the confidence from the plan’s `observed` to `inferred` because this authoring pass explicitly classifies profiler/strace-only evidence as indirect unless stronger evidence is gathered. The expected effect is that this proposal avoids an upstream CPython diff that would be speculative and gives maintainers a focused diagnosis for collecting application-level evidence instead.

Style and helper checks: `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `Doc/README.rst` documents documentation style. No relevant local helper was found for a source change because no CPython subsystem was proven faulty.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. The command exited successfully, but the build reported optional/environment module issues: `_ssl failed to import` with `undefined symbol: TLSv1_method`, missing `_dbm`, `_gdbm`, and `_tkinter`, and `Could not build the ssl module! Python requires a OpenSSL 1.1.1 or newer`.

Attempted bounded strace reproduction:
`/usr/bin/time -f 'cpu=%P user=%U sys=%S elapsed=%e' timeout 5 strace -qq -tt -e trace=poll,wait4 ./python ...`
Blocked by sandbox ptrace permissions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 7): Operation not permitted`.

Ran the same Python `wait4(WNOHANG)` plus `poll(1000)` smoke loop without strace. Result: `iterations=4`, `cpu=0% user=0.00 sys=0.00 elapsed=4.01`. This did not reproduce runaway CPU.

## Review Pass 1

RESULT: ok

No source changes are present: `git status --short` is clean, `git diff --stat` is empty, and a direct diff against the original snapshot only shows workspace metadata directories.

The patch output is a no-patch diagnosis, which is appropriate for the evidence level. It includes `## Evidence Confidence` with an allowed value (`inferred`), does not claim reproduction, does not invent a CPython failure, and explains why the perf/strace `/proc` signal points more plausibly at an application-level `supervisord` poll/reap loop than at an upstream interpreter defect.

Validation is acceptable for a no-patch report: the project-level `./configure && make` entrypoint was attempted and reported with the `_ssl`/optional-module build caveats, and the bounded strace reproduction attempt clearly records the ptrace permission blocker plus a non-strace smoke check result.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `/usr/bin/python3.13`, but the captured command is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The available trace excerpt shows `supervisord` repeatedly doing `wait4(-1, ..., WNOHANG)` followed by `poll(..., 1000)` with one-second blocking timeouts. The raw artifact files named in `evidence.json` are not present, so there is no resolved Python-frame or CPython C-frame evidence tying this to a Python 3.13 runtime defect.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose the observed signal as an application-level `supervisord` event-loop/profile attribution issue unless a bounded reproduction produces CPython-specific evidence.

## Patch Plan
Do not edit CPython in this pass. The evidence points first at the script/application entrypoint, and the runtime backtrace is unresolved/noisy (`pthread_attr_destroy`, `_PyEval_EvalFrameDefault`, `PyMem_Realloc`) rather than a coherent CPython hot loop.

Contribution/style guidance found: `README.rst` points contributors to the CPython Developer Guide and gives the upstream build/test flow. Local conventions/helpers inspected include `Lib/subprocess.py`’s `_waitpid_lock`, `_try_wait()`, `_internal_poll()`, and `selectors.PollSelector.select()`, plus `_PyTime_ROUND_TIMEOUT` timeout conventions in `Include/internal/pycore_time.h`. No relevant local helper was found that would justify a CPython change for this evidence.

No prior Fixer patch is present in the workspace (`git status --short` is clean), so there is nothing to replace. I would also reject any speculative CPython workaround such as inserting sleeps, changing selector timeout rounding, or adding awkward control flow/goto-like early exits, because the trace already shows one-second blocking `poll()` calls rather than a tight CPython loop.

## Risks
A CPython source patch based only on this bundle would likely be a false attribution fix and could regress standard-library process waiting, selector semantics, or timeout precision. The evidence also includes contradictory signals: high aggregate CPU for two Python processes, but the sampled PID is sleeping in `poll_schedule_timeout`.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails due to missing build dependencies or generated files, record the exact failure and then use the narrowest reproducible check, likely syntax/compile checks for inspected Python files only.

For an independent bounded reproduction attempt, do not run the system `/etc/supervisor/supervisord.conf`. Instead, if `supervisord` is available, run it under `timeout` with a temporary minimal config and `strace -f -tt -e trace=poll,wait4` to see whether the same `wait4(WNOHANG)` plus one-second `poll()` pattern appears without implicating CPython internals. Do not claim `reproduced` unless that command actually demonstrates the collected failure signal.

## Patch Pass

Subject: Diagnose supervisor poll trace without CPython changes

## Commit Message
No source change is proposed. The collected evidence points at a `supervisord` process sleeping in an application event loop, not at a confirmed CPython runtime bug. `poll(1000)` is a one-second kernel wait, and the trace does not identify a CPython loop that can be safely patched upstream.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU signal for `/usr/bin/python3.13`, but the command line was `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The strace excerpt alternates `wait4(-1, ..., WNOHANG)` with `poll(..., 1000)` calls that time out after about one second, while `/proc` reports the sampled `supervisord` thread in sleeping state and waiting in `poll_schedule_timeout`.

The cautious inference is that this is a supervisor/application event-loop attribution, not a demonstrated CPython busy loop. The unresolved backtrace mentions CPython frames, but it does not identify a stable runtime code path to change. The saved plan was followed: no CPython source patch was left.

I checked CPython contribution/build guidance in `README.rst` and `Doc/README.rst`, and inspected nearby runtime helpers/conventions: `Lib/subprocess.py` uses `_waitpid_lock`, `_try_wait()`, and `_internal_poll()` for process waiting; `Lib/selectors.py` uses `PollSelector.select()` timeout rounding; `Include/internal/pycore_time.h` documents `_PyTime_ROUND_TIMEOUT`. No relevant local helper fits because there is no safe source change to make from this evidence. The expected effect is that this proposal avoids a speculative timing/process-waiting change and leaves a focused upstream report path: reproduce `supervisord` with resolved Python frames or show a CPython-owned tight loop before patching.

## Git Add Paths
None

## Validation
`./configure && make` from the workspace root completed with exit code 0. The build reported optional-module issues: `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` was built but removed because it failed to import with `undefined symbol: TLSv1_method`.

Focused smoke check after the build:

```sh
./python - <<'PY'
import os, selectors, subprocess, sys
print(sys.version.split()[0])
print(selectors.DefaultSelector.__name__)
print(hasattr(os, 'wait4'), hasattr(os, 'WNOHANG'))
PY
```

Output: `3.13.12`, `EpollSelector`, `True True`.

Independent reproduction was attempted by checking for the planned `supervisord` target, but it was blocked: `command -v supervisord` produced no path (`blocked: supervisord not found`). `strace` and Python were available, but I did not invent a synthetic reproducer or run the system supervisor config. Validation-only build outputs were cleaned with `make distclean`; the workspace is clean.

## Review Pass 1

RESULT: ok

No source diff is present, and the no-patch diagnosis matches the evidence level. The author did not claim reproduction, used `inferred` appropriately for indirect profiler/strace evidence, checked CPython guidance and relevant local helpers, attempted the project-level `./configure && make`, and reported the blocked `supervisord` reproduction attempt without inventing a synthetic failure.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `/usr/bin/python3.13`, but the captured command is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The available trace excerpt shows `supervisord` repeatedly doing `wait4(-1, ..., WNOHANG)` followed by `poll(..., 1000)` with one-second blocking timeouts. The raw artifact files named in `evidence.json` are not present, so there is no resolved Python-frame or CPython C-frame evidence tying this to a Python 3.13 runtime defect.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose the observed signal as an application-level `supervisord` event-loop/profile attribution issue unless a bounded reproduction produces CPython-specific evidence.

## Patch Plan
Do not edit CPython in this pass. The evidence points first at the script/application entrypoint, and the runtime backtrace is unresolved/noisy (`pthread_attr_destroy`, `_PyEval_EvalFrameDefault`, `PyMem_Realloc`) rather than a coherent CPython hot loop.

Contribution/style guidance found: `README.rst` points contributors to the CPython Developer Guide and gives the upstream build/test flow. Local conventions/helpers inspected include `Lib/subprocess.py`’s `_waitpid_lock`, `_try_wait()`, `_internal_poll()`, and `selectors.PollSelector.select()`, plus `_PyTime_ROUND_TIMEOUT` timeout conventions in `Include/internal/pycore_time.h`. No relevant local helper was found that would justify a CPython change for this evidence.

No prior Fixer patch is present in the workspace (`git status --short` is clean), so there is nothing to replace. I would also reject any speculative CPython workaround such as inserting sleeps, changing selector timeout rounding, or adding awkward control flow/goto-like early exits, because the trace already shows one-second blocking `poll()` calls rather than a tight CPython loop.

## Risks
A CPython source patch based only on this bundle would likely be a false attribution fix and could regress standard-library process waiting, selector semantics, or timeout precision. The evidence also includes contradictory signals: high aggregate CPU for two Python processes, but the sampled PID is sleeping in `poll_schedule_timeout`.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails due to missing build dependencies or generated files, record the exact failure and then use the narrowest reproducible check, likely syntax/compile checks for inspected Python files only.

For an independent bounded reproduction attempt, do not run the system `/etc/supervisor/supervisord.conf`. Instead, if `supervisord` is available, run it under `timeout` with a temporary minimal config and `strace -f -tt -e trace=poll,wait4` to see whether the same `wait4(WNOHANG)` plus one-second `poll()` pattern appears without implicating CPython internals. Do not claim `reproduced` unless that command actually demonstrates the collected failure signal.

## Patch Pass

Subject: Diagnose supervisor poll trace without CPython changes

## Commit Message
No source change is proposed. The collected evidence points at a `supervisord` process sleeping in an application event loop, not at a confirmed CPython runtime bug. `poll(1000)` is a one-second kernel wait, and the trace does not identify a CPython loop that can be safely patched upstream.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU signal for `/usr/bin/python3.13`, but the command line was `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The strace excerpt alternates `wait4(-1, ..., WNOHANG)` with `poll(..., 1000)` calls that time out after about one second, while `/proc` reports the sampled `supervisord` thread in sleeping state and waiting in `poll_schedule_timeout`.

The cautious inference is that this is a supervisor/application event-loop attribution, not a demonstrated CPython busy loop. The unresolved backtrace mentions CPython frames, but it does not identify a stable runtime code path to change. The saved plan was followed: no CPython source patch was left.

I checked CPython contribution/build guidance in `README.rst` and `Doc/README.rst`, and inspected nearby runtime helpers/conventions: `Lib/subprocess.py` uses `_waitpid_lock`, `_try_wait()`, and `_internal_poll()` for process waiting; `Lib/selectors.py` uses `PollSelector.select()` timeout rounding; `Include/internal/pycore_time.h` documents `_PyTime_ROUND_TIMEOUT`. No relevant local helper fits because there is no safe source change to make from this evidence. The expected effect is that this proposal avoids a speculative timing/process-waiting change and leaves a focused upstream report path: reproduce `supervisord` with resolved Python frames or show a CPython-owned tight loop before patching.

## Git Add Paths
None

## Validation
`./configure && make` from the workspace root completed with exit code 0. The build reported optional-module issues: `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` was built but removed because it failed to import with `undefined symbol: TLSv1_method`.

Focused smoke check after the build:

```sh
./python - <<'PY'
import os, selectors, subprocess, sys
print(sys.version.split()[0])
print(selectors.DefaultSelector.__name__)
print(hasattr(os, 'wait4'), hasattr(os, 'WNOHANG'))
PY
```

Output: `3.13.12`, `EpollSelector`, `True True`.

Independent reproduction was attempted by checking for the planned `supervisord` target, but it was blocked: `command -v supervisord` produced no path (`blocked: supervisord not found`). `strace` and Python were available, but I did not invent a synthetic reproducer or run the system supervisor config. Validation-only build outputs were cleaned with `make distclean`; the workspace is clean.

## Review Pass 1

RESULT: ok

No source diff is present, and the no-patch diagnosis matches the evidence level. The author did not claim reproduction, used `inferred` appropriately for indirect profiler/strace evidence, checked CPython guidance and relevant local helpers, attempted the project-level `./configure && make`, and reported the blocked `supervisord` reproduction attempt without inventing a synthetic failure.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer sampled `/usr/bin/python3.13` while it was running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The captured syscall sequence is `poll` with a 1000 ms timeout followed by `wait4(-1, ..., WNOHANG)` returning `ECHILD`, repeated once per second. That is application event-loop behavior, not yet evidence of a CPython runtime defect. The raw investigation directory referenced by the bundle is not present in this workspace, so I cannot inspect the full strace/backtrace beyond the bundle excerpts.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch in this pass: prepare a diagnosis/report that the evidence currently implicates the `supervisord` entrypoint behavior rather than `python3.13` internals.

## Patch Plan
Do not edit CPython unless additional evidence shows a runtime bug independent of `supervisord`.

Use the application entrypoint first: inspect the command-line evidence and syscall pattern as a Python-hosted `supervisord` loop. Treat runtime frames such as `_PyEval_EvalFrameDefault` and `PyMem_Realloc` as secondary until a Python-only reproducer shows pathological `select.poll()` or `os.waitpid()` behavior.

Local CPython conventions found: `README.rst` points contributors to the CPython Developer Guide and names `./configure`, `make`, and `make test` as the normal Unix workflow. In the touched runtime area, `Modules/selectmodule.c` uses Argument Clinic, `_PyTime_*` deadline helpers, `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, `PyErr_SetFromErrno()`, and `PyMem_*`; `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. No relevant local helper suggests a missing CPython wrapper for the observed 1-second blocking `poll`.

No prior Fixer source patch was found; the repo history only shows `Fixer baseline`, and no `fixer`/`89388` patch content appears in the workspace. There is therefore no prior patch to improve or replace.

## Risks
A CPython patch from this evidence would likely be speculative: the process is sleeping in `poll_schedule_timeout`, the observed poll timeout is one second, and the sampled executable is only the interpreter hosting `supervisord`.

Changing `select.poll()`, `selectors`, or waitpid handling without a CPython-level reproducer risks regressing valid event loops. No authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior should be patched from the current evidence.

## Validation
Before any future source edit, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails because Debian source dependencies or generated files are missing, record the exact failure and then run the narrowest relevant CPython check.

Bounded independent reproduction attempt: run a clean CPython script that performs the same shape of operations, `os.waitpid(-1, os.WNOHANG)` plus `select.poll().poll(1000)`, under `strace -tt -T`, and confirm whether it blocks for about one second rather than spinning. This can validate that the collected signal is compatible with normal runtime behavior, but it would not justify claiming the original `supervisord` issue was independently reproduced.

## Patch Pass

Subject: Diagnose supervisord poll trace without CPython patch

## Commit Message
No source change is included. The collected evidence points at a Python-hosted `supervisord` event loop that wakes once per second, not at a demonstrated CPython runtime defect. CPython’s `select.poll()` path already uses its local timeout helpers, releases the GIL around `poll(2)`, and retries only on `EINTR`.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a Fixer perf/strace investigation of `/usr/bin/python3.13` running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The process state was sleeping, `wchan` was `poll_schedule_timeout`, and the strace excerpt showed `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The cautious code-level inference is that the profiler attributed a Python application loop to the interpreter executable. This is not enough to justify a CPython source patch: the relevant CPython path in `Modules/selectmodule.c` already uses `_PyTime_*` deadline helpers, `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, and `PyErr_SetFromErrno()`, while `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. No relevant missing local helper or compatibility wrapper was found.

I followed `plan-output.txt` and did not change course. No patch was made because the independent smoke check showed the same `waitpid`/`poll(1000)` shape blocking for about one second, not spinning. The expected effect of this no-patch report is to avoid landing a speculative runtime change and to redirect follow-up investigation toward `supervisord` configuration or application-level event-loop behavior.

## Git Add Paths
None

## Validation
Ran the project-level entrypoint from the workspace root:

```sh
./configure && make
```

It completed with exit code 0. The build reported optional module issues: `_dbm`, `_gdbm`, and `_tkinter` were missing; `_ssl` built but failed to import due to `undefined symbol: TLSv1_method`.

Independent reproduction attempt with the built interpreter:

```sh
./python - <<'PY'
import os, select, time
r, w = os.pipe()
try:
    try:
        print('waitpid:', os.waitpid(-1, os.WNOHANG))
    except ChildProcessError as exc:
        print('waitpid:', type(exc).__name__)
    p = select.poll()
    p.register(r, select.POLLIN | select.POLLPRI | select.POLLHUP)
    start = time.monotonic()
    print('poll:', p.poll(1000), 'elapsed=%.3f' % (time.monotonic() - start))
finally:
    os.close(r)
    os.close(w)
PY
```

Result: `waitpid: ChildProcessError` and `poll: [] elapsed=1.001`, so it did not reproduce a busy loop.

Tried a syscall-level smoke trace:

```sh
strace -tt -T -e trace=poll,wait4 ./python ...
```

Blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran `make distclean` after validation; `git status --short` is clean.

## Review Pass 1

RESULT: ok

No source patch is present, and `git diff` is clean. The author correctly treated the perf/strace evidence as insufficient for a CPython runtime patch, used `## Evidence Confidence` with an allowed value (`inferred`), and avoided claiming local reproduction.

The no-patch diagnosis connects the evidence to the decision: the observed process was `supervisord`, `/proc` showed it sleeping in `poll_schedule_timeout`, and the strace excerpt showed one-second `poll()` timeouts rather than a tight busy loop. The validation section includes the project-level `./configure && make`, the optional module issues from that build, a bounded independent smoke check, and the ptrace blocker for `strace`.

I found no review blockers.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer sampled `/usr/bin/python3.13` while it was running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The captured syscall sequence is `poll` with a 1000 ms timeout followed by `wait4(-1, ..., WNOHANG)` returning `ECHILD`, repeated once per second. That is application event-loop behavior, not yet evidence of a CPython runtime defect. The raw investigation directory referenced by the bundle is not present in this workspace, so I cannot inspect the full strace/backtrace beyond the bundle excerpts.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch in this pass: prepare a diagnosis/report that the evidence currently implicates the `supervisord` entrypoint behavior rather than `python3.13` internals.

## Patch Plan
Do not edit CPython unless additional evidence shows a runtime bug independent of `supervisord`.

Use the application entrypoint first: inspect the command-line evidence and syscall pattern as a Python-hosted `supervisord` loop. Treat runtime frames such as `_PyEval_EvalFrameDefault` and `PyMem_Realloc` as secondary until a Python-only reproducer shows pathological `select.poll()` or `os.waitpid()` behavior.

Local CPython conventions found: `README.rst` points contributors to the CPython Developer Guide and names `./configure`, `make`, and `make test` as the normal Unix workflow. In the touched runtime area, `Modules/selectmodule.c` uses Argument Clinic, `_PyTime_*` deadline helpers, `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, `PyErr_SetFromErrno()`, and `PyMem_*`; `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. No relevant local helper suggests a missing CPython wrapper for the observed 1-second blocking `poll`.

No prior Fixer source patch was found; the repo history only shows `Fixer baseline`, and no `fixer`/`89388` patch content appears in the workspace. There is therefore no prior patch to improve or replace.

## Risks
A CPython patch from this evidence would likely be speculative: the process is sleeping in `poll_schedule_timeout`, the observed poll timeout is one second, and the sampled executable is only the interpreter hosting `supervisord`.

Changing `select.poll()`, `selectors`, or waitpid handling without a CPython-level reproducer risks regressing valid event loops. No authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior should be patched from the current evidence.

## Validation
Before any future source edit, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails because Debian source dependencies or generated files are missing, record the exact failure and then run the narrowest relevant CPython check.

Bounded independent reproduction attempt: run a clean CPython script that performs the same shape of operations, `os.waitpid(-1, os.WNOHANG)` plus `select.poll().poll(1000)`, under `strace -tt -T`, and confirm whether it blocks for about one second rather than spinning. This can validate that the collected signal is compatible with normal runtime behavior, but it would not justify claiming the original `supervisord` issue was independently reproduced.

## Patch Pass

Subject: Diagnose supervisord poll trace without CPython patch

## Commit Message
No source change is included. The collected evidence points at a Python-hosted `supervisord` event loop that wakes once per second, not at a demonstrated CPython runtime defect. CPython’s `select.poll()` path already uses its local timeout helpers, releases the GIL around `poll(2)`, and retries only on `EINTR`.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a Fixer perf/strace investigation of `/usr/bin/python3.13` running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The process state was sleeping, `wchan` was `poll_schedule_timeout`, and the strace excerpt showed `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The cautious code-level inference is that the profiler attributed a Python application loop to the interpreter executable. This is not enough to justify a CPython source patch: the relevant CPython path in `Modules/selectmodule.c` already uses `_PyTime_*` deadline helpers, `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, and `PyErr_SetFromErrno()`, while `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. No relevant missing local helper or compatibility wrapper was found.

I followed `plan-output.txt` and did not change course. No patch was made because the independent smoke check showed the same `waitpid`/`poll(1000)` shape blocking for about one second, not spinning. The expected effect of this no-patch report is to avoid landing a speculative runtime change and to redirect follow-up investigation toward `supervisord` configuration or application-level event-loop behavior.

## Git Add Paths
None

## Validation
Ran the project-level entrypoint from the workspace root:

```sh
./configure && make
```

It completed with exit code 0. The build reported optional module issues: `_dbm`, `_gdbm`, and `_tkinter` were missing; `_ssl` built but failed to import due to `undefined symbol: TLSv1_method`.

Independent reproduction attempt with the built interpreter:

```sh
./python - <<'PY'
import os, select, time
r, w = os.pipe()
try:
    try:
        print('waitpid:', os.waitpid(-1, os.WNOHANG))
    except ChildProcessError as exc:
        print('waitpid:', type(exc).__name__)
    p = select.poll()
    p.register(r, select.POLLIN | select.POLLPRI | select.POLLHUP)
    start = time.monotonic()
    print('poll:', p.poll(1000), 'elapsed=%.3f' % (time.monotonic() - start))
finally:
    os.close(r)
    os.close(w)
PY
```

Result: `waitpid: ChildProcessError` and `poll: [] elapsed=1.001`, so it did not reproduce a busy loop.

Tried a syscall-level smoke trace:

```sh
strace -tt -T -e trace=poll,wait4 ./python ...
```

Blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran `make distclean` after validation; `git status --short` is clean.

## Review Pass 1

RESULT: ok

No source patch is present, and `git diff` is clean. The author correctly treated the perf/strace evidence as insufficient for a CPython runtime patch, used `## Evidence Confidence` with an allowed value (`inferred`), and avoided claiming local reproduction.

The no-patch diagnosis connects the evidence to the decision: the observed process was `supervisord`, `/proc` showed it sleeping in `poll_schedule_timeout`, and the strace excerpt showed one-second `poll()` timeouts rather than a tight busy loop. The validation section includes the project-level `./configure && make`, the optional module issues from that build, a bounded independent smoke check, and the ptrace blocker for `strace`.

I found no review blockers.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` with high sampled CPU, but the concrete syscall trace shows `wait4(-1, ..., WNOHANG) = ECHILD` followed by `poll(..., 1000)` timeouts once per second. That pattern is `supervisord` event-loop behavior, not a demonstrated CPython runtime busy loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch for this pass: diagnose likely package attribution mismatch and reject a speculative Python runtime change.

## Patch Plan
- Do not edit CPython unless additional evidence ties the loop to interpreter code rather than the Python application entrypoint.
- Base the diagnosis on the script/application evidence first: the command line is `supervisord`, process state is sleeping, `wchan` is `poll_schedule_timeout`, and strace shows one-second blocking polls, not a tight zero-timeout poll loop.
- Treat the `pthread_attr_destroy` backtrace as non-actionable without symbols or a matching threaded runtime failure; the process evidence says one thread and the syscall trace points outside `Python/thread_pthread.h`.
- Note local conventions checked: CPython `README.rst` points contributors to the Developer Guide and standard `./configure`, `make`, `make test`; Debian `README.source` says quilt patches are used. Relevant local helpers in the inspected runtime area include `PyMem_RawMalloc`/`PyMem_RawFree`, `_PyTime_*`, `Py_BEGIN_ALLOW_THREADS`, `Py_END_ALLOW_THREADS`, and existing pthread status helpers, but no relevant helper-backed CPython change is justified.
- No prior Fixer patch was present in the workspace to improve or replace.
- If later evidence proves a CPython bug, prefer a small upstream-style change with existing helpers and bounded cleanup flow; do not introduce avoidable `goto` for this area.

## Risks
A source patch here would likely mask an application-level or monitoring-classification issue and could regress stable CPython process, signal, polling, or threading behavior without a confirmed runtime defect.

## Validation
Before any focused check after a real patch, try the project entrypoint from the workspace root: `./configure && make`. If it fails due to missing dependencies or generated files, record the exact failure and then use the narrowest reproducible compile/test.

For this no-patch diagnosis, add one bounded independent check after build only to test the implicated primitives, not to claim reproduction: run a short `python3.13` smoke under `timeout` that calls `os.waitpid(-1, os.WNOHANG)` and `select.poll().poll(1000)` and confirm it either returns `ECHILD` or blocks for about one second rather than spinning.

## Patch Pass



## Workflow Note

Codex stage timed out after 900 second(s).

Diff

--- a/Makefile.pre	1970-01-01 04:00:00.000000000 +0400
+++ b/Makefile.pre	2026-05-26 14:44:41.260504807 +0400
@@ -0,0 +1,3297 @@
+# Top-level Makefile for Python
+#
+# As distributed, this file is called Makefile.pre.in; it is processed
+# into the real Makefile by running the script ./configure, which
+# replaces things like @spam@ with values appropriate for your system.
+# This means that if you edit Makefile, your changes get lost the next
+# time you run the configure script.  Ideally, you can do:
+#
+#	./configure
+#	make
+#	make test
+#	make install
+#
+# If you have a previous version of Python installed that you don't
+# want to overwrite, you can use "make altinstall" instead of "make
+# install".  Refer to the "Installing" section in the README file for
+# additional details.
+#
+# See also the section "Build instructions" in the README file.
+
+# === Variables set by makesetup ===
+
+MODBUILT_NAMES=    _MODBUILT_NAMES_
+MODSHARED_NAMES=   _MODSHARED_NAMES_
+MODDISABLED_NAMES= _MODDISABLED_NAMES_
+MODOBJS=           _MODOBJS_
+MODLIBS=           _MODLIBS_
+
+# === Variables set by configure
+VERSION=	3.13
+srcdir=		.
+
+abs_srcdir=	b
+abs_builddir=	b
+
+
+CC=		gcc
+CXX=		g++
+LINKCC=		$(PURIFY) $(CC)
+AR=		ar
+READELF=	@READELF@
+SOABI=		cpython-313-x86_64-linux-gnu
+ABIFLAGS=	
+ABI_THREAD=	
+LDVERSION=	$(VERSION)$(ABIFLAGS)
+LIBPYTHON=
+GITVERSION=	git --git-dir $(srcdir)/.git rev-parse --short HEAD
+GITTAG=		git --git-dir $(srcdir)/.git describe --all --always --dirty
+GITBRANCH=	git --git-dir $(srcdir)/.git name-rev --name-only HEAD
+PGO_PROF_GEN_FLAG=-fprofile-generate
+PGO_PROF_USE_FLAG=-fprofile-use -fprofile-correction
+LLVM_PROF_MERGER=true
+LLVM_PROF_FILE=
+LLVM_PROF_ERR=no
+DTRACE=         
+DFLAGS=         
+DTRACE_HEADERS= 
+DTRACE_OBJS=    
+DSYMUTIL=       
+DSYMUTIL_PATH=  
+
+GNULD=		yes
+
+# Shell used by make (some versions default to the login shell, which is bad)
+SHELL=		/bin/sh -e
+
+# Use this to make a link between python$(VERSION) and python in $(BINDIR)
+LN=		ln
+
+# Portable install script (configure doesn't always guess right)
+INSTALL=	/usr/bin/install -c
+INSTALL_PROGRAM=${INSTALL}
+INSTALL_SCRIPT= ${INSTALL}
+INSTALL_DATA=	${INSTALL} -m 644
+# Shared libraries must be installed with executable mode on some systems;
+# rather than figuring out exactly which, we always give them executable mode.
+INSTALL_SHARED= ${INSTALL} -m 755
+
+MKDIR_P=	/usr/bin/mkdir -p
+
+MAKESETUP=      $(srcdir)/Modules/makesetup
+
+# Compiler options
+OPT=		-DNDEBUG -g -O3 -Wall
+BASECFLAGS=	 -fno-strict-overflow -Wsign-compare
+BASECPPFLAGS=	
+CONFIGURE_CFLAGS=	
+# CFLAGS_NODIST is used for building the interpreter and stdlib C extensions.
+# Use it when a compiler flag should _not_ be part of the distutils CFLAGS
+# once Python is installed (Issue #21121).
+CONFIGURE_CFLAGS_NODIST= -std=c11 -Wextra -Wno-unused-parameter -Wno-missing-field-initializers -Wstrict-prototypes -Werror=implicit-function-declaration -fvisibility=hidden
+# LDFLAGS_NODIST is used in the same manner as CFLAGS_NODIST.
+# Use it when a linker flag should _not_ be part of the distutils LDFLAGS
+# once Python is installed (bpo-35257)
+CONFIGURE_LDFLAGS_NODIST=
+# LDFLAGS_NOLTO is an extra flag to disable lto. It is used to speed up building
+# of _bootstrap_python and _freeze_module tools, which don't need LTO.
+CONFIGURE_LDFLAGS_NOLTO=
+CONFIGURE_CPPFLAGS=	
+CONFIGURE_LDFLAGS=	
+# Avoid assigning CFLAGS, LDFLAGS, etc. so users can use them on the
+# command line to append to these values without stomping the pre-set
+# values.
+PY_CFLAGS=	$(BASECFLAGS) $(OPT) $(CONFIGURE_CFLAGS) $(CFLAGS) $(EXTRA_CFLAGS)
+PY_CFLAGS_NODIST=$(CONFIGURE_CFLAGS_NODIST) $(CFLAGS_NODIST) -I$(srcdir)/Include/internal -I$(srcdir)/Include/internal/mimalloc
+# Both CPPFLAGS and LDFLAGS need to contain the shell's value for setup.py to
+# be able to build extension modules using the directories specified in the
+# environment variables
+PY_CPPFLAGS=	$(BASECPPFLAGS) -I. -I$(srcdir)/Include $(CONFIGURE_CPPFLAGS) $(CPPFLAGS)
+PY_LDFLAGS=	$(CONFIGURE_LDFLAGS) $(LDFLAGS)
+PY_LDFLAGS_NODIST=$(CONFIGURE_LDFLAGS_NODIST) $(LDFLAGS_NODIST)
+PY_LDFLAGS_NOLTO=$(PY_LDFLAGS) $(CONFIGURE_LDFLAGS_NOLTO) $(LDFLAGS_NODIST)
+NO_AS_NEEDED=	-Wl,--no-as-needed
+CCSHARED=	-fPIC
+# LINKFORSHARED are the flags passed to the $(CC) command that links
+# the python executable -- this is only needed for a few systems
+LINKFORSHARED=	-Xlinker -export-dynamic
+ARFLAGS=	rcs
+# Extra C flags added for building the interpreter object files.
+CFLAGSFORSHARED=
+# C flags used for building the interpreter object files
+PY_STDMODULE_CFLAGS= $(PY_CFLAGS) $(PY_CFLAGS_NODIST) $(PY_CPPFLAGS) $(CFLAGSFORSHARED)
+PY_BUILTIN_MODULE_CFLAGS= $(PY_STDMODULE_CFLAGS) -DPy_BUILD_CORE_BUILTIN
+PY_CORE_CFLAGS=	$(PY_STDMODULE_CFLAGS) -DPy_BUILD_CORE
+# Linker flags used for building the interpreter object files
+PY_CORE_LDFLAGS=$(PY_LDFLAGS) $(PY_LDFLAGS_NODIST)
+# Strict or non-strict aliasing flags used to compile dtoa.c, see above
+CFLAGS_ALIASING=
+
+
+# Machine-dependent subdirectories
+MACHDEP=	linux
+
+# Multiarch directory (may be empty)
+MULTIARCH=	x86_64-linux-gnu
+MULTIARCH_CPPFLAGS = -DMULTIARCH=\"x86_64-linux-gnu\"
+
+# Install prefix for architecture-independent files
+prefix=		/usr/local
+
+# Install prefix for architecture-dependent files
+exec_prefix=	${prefix}
+
+# Install prefix for data files
+datarootdir=    ${prefix}/share
+
+# Expanded directories
+BINDIR=		${exec_prefix}/bin
+LIBDIR=		${exec_prefix}/lib
+MANDIR=		${datarootdir}/man
+INCLUDEDIR=	${prefix}/include
+CONFINCLUDEDIR=	$(exec_prefix)/include
+PLATLIBDIR=	lib
+SCRIPTDIR=	$(prefix)/$(PLATLIBDIR)
+# executable name for shebangs
+EXENAME=	$(BINDIR)/python$(LDVERSION)$(EXE)
+# Variable used by ensurepip
+WHEEL_PKG_DIR=	
+
+# Detailed destination directories
+BINLIBDEST=	$(LIBDIR)/python$(VERSION)$(ABI_THREAD)
+LIBDEST=	$(SCRIPTDIR)/python$(VERSION)$(ABI_THREAD)
+INCLUDEPY=	$(INCLUDEDIR)/python$(LDVERSION)
+CONFINCLUDEPY=	$(CONFINCLUDEDIR)/python$(LDVERSION)
+
+# Symbols used for using shared libraries
+SHLIB_SUFFIX=	.so
+EXT_SUFFIX=	.cpython-313-x86_64-linux-gnu.so
+LDSHARED=	$(CC) -shared $(PY_LDFLAGS)
+BLDSHARED=	$(CC) -shared $(PY_CORE_LDFLAGS)
+LDCXXSHARED=	$(CXX) -shared $(PY_LDFLAGS)
+DESTSHARED=	$(LIBDEST)/lib-dynload
+
+# List of exported symbols for AIX
+EXPORTSYMS=	
+EXPORTSFROM=	
+
+# Executable suffix (.exe on Windows and Mac OS X)
+EXE=		
+BUILDEXE=	
+
+# Name of the patch file to apply for app store compliance
+APP_STORE_COMPLIANCE_PATCH=
+
+# Short name and location for Mac OS X Python framework
+UNIVERSALSDK=
+PYTHONFRAMEWORK=	
+PYTHONFRAMEWORKDIR=	no-framework
+PYTHONFRAMEWORKPREFIX=	
+PYTHONFRAMEWORKINSTALLDIR= 
+PYTHONFRAMEWORKINSTALLNAMEPREFIX= 
+RESSRCDIR= 
+# macOS deployment target selected during configure, to be checked
+# by distutils. The export statement is needed to ensure that the
+# deployment target is active during build.
+MACOSX_DEPLOYMENT_TARGET=
+#export MACOSX_DEPLOYMENT_TARGET
+
+# iOS Deployment target selected during configure. Unlike macOS, the iOS
+# deployment target is controlled using `-mios-version-min` arguments added to
+# CFLAGS and LDFLAGS by the configure script. This variable is not used during
+# the build, and is only listed here so it will be included in sysconfigdata.
+IPHONEOS_DEPLOYMENT_TARGET=
+
+# Option to install to strip binaries
+STRIPFLAG=-s
+
+# Flags to lipo to produce a 32-bit-only universal executable
+LIPO_32BIT_FLAGS=
+
+# Flags to lipo to produce an intel-64-only universal executable
+LIPO_INTEL64_FLAGS=
+
+# Environment to run shared python without installed libraries
+RUNSHARED=       
+
+# ensurepip options
+ENSUREPIP=      upgrade
+
+# Internal static libraries
+LIBMPDEC_A= Modules/_decimal/libmpdec/libmpdec.a
+LIBEXPAT_A= Modules/expat/libexpat.a
+LIBHACL_SHA2_A= Modules/_hacl/libHacl_Hash_SHA2.a
+
+# Module state, compiler flags and linker flags
+# Empty CFLAGS and LDFLAGS are omitted.
+# states:
+#   * yes: module is available
+#   * missing: build dependency is missing
+#   * disabled: module is disabled
+#   * n/a: module is not available on the current platform
+# MODULE_EGG_STATE=yes  # yes, missing, disabled, n/a
+# MODULE_EGG_CFLAGS=
+# MODULE_EGG_LDFLAGS=
+MODULE__IO_STATE=yes
+MODULE__IO_CFLAGS=-I$(srcdir)/Modules/_io
+MODULE_TIME_STATE=yes
+MODULE_TIME_LDFLAGS=
+MODULE_ARRAY_STATE=yes
+MODULE__ASYNCIO_STATE=yes
+MODULE__BISECT_STATE=yes
+MODULE__CONTEXTVARS_STATE=yes
+MODULE__CSV_STATE=yes
+MODULE__HEAPQ_STATE=yes
+MODULE__JSON_STATE=yes
+MODULE__LSPROF_STATE=yes
+MODULE__OPCODE_STATE=yes
+MODULE__PICKLE_STATE=yes
+MODULE__POSIXSUBPROCESS_STATE=yes
+MODULE__QUEUE_STATE=yes
+MODULE__RANDOM_STATE=yes
+MODULE_SELECT_STATE=yes
+MODULE__STRUCT_STATE=yes
+MODULE__TYPING_STATE=yes
+MODULE__INTERPRETERS_STATE=yes
+MODULE__INTERPCHANNELS_STATE=yes
+MODULE__INTERPQUEUES_STATE=yes
+MODULE__ZONEINFO_STATE=yes
+MODULE__MULTIPROCESSING_STATE=yes
+MODULE__MULTIPROCESSING_CFLAGS=-I$(srcdir)/Modules/_multiprocessing
+MODULE__POSIXSHMEM_STATE=yes
+MODULE__POSIXSHMEM_CFLAGS=-I$(srcdir)/Modules/_multiprocessing
+MODULE__POSIXSHMEM_LDFLAGS=
+MODULE__STATISTICS_STATE=yes
+MODULE__STATISTICS_LDFLAGS=-lm
+MODULE_CMATH_STATE=yes
+MODULE_CMATH_LDFLAGS=-lm
+MODULE_MATH_STATE=yes
+MODULE_MATH_LDFLAGS=-lm
+MODULE__DATETIME_STATE=yes
+MODULE__DATETIME_LDFLAGS= -lm
+MODULE_FCNTL_STATE=yes
+MODULE_FCNTL_LDFLAGS=
+MODULE_MMAP_STATE=yes
+MODULE__SOCKET_STATE=yes
+MODULE_GRP_STATE=yes
+MODULE_PWD_STATE=yes
+MODULE_RESOURCE_STATE=yes
+MODULE__SCPROXY_STATE=n/a
+MODULE_SYSLOG_STATE=yes
+MODULE_TERMIOS_STATE=yes
+MODULE_PYEXPAT_STATE=yes
+MODULE_PYEXPAT_CFLAGS=-I$(srcdir)/Modules/expat
+MODULE_PYEXPAT_LDFLAGS=-lm $(LIBEXPAT_A)
+MODULE__ELEMENTTREE_STATE=yes
+MODULE__ELEMENTTREE_CFLAGS=-I$(srcdir)/Modules/expat
+MODULE__CODECS_CN_STATE=yes
+MODULE__CODECS_HK_STATE=yes
+MODULE__CODECS_ISO2022_STATE=yes
+MODULE__CODECS_JP_STATE=yes
+MODULE__CODECS_KR_STATE=yes
+MODULE__CODECS_TW_STATE=yes
+MODULE__MULTIBYTECODEC_STATE=yes
+MODULE_UNICODEDATA_STATE=yes
+MODULE__MD5_STATE=yes
+MODULE__MD5_CFLAGS=-I$(srcdir)/Modules/_hacl/include -I$(srcdir)/Modules/_hacl/internal -D_BSD_SOURCE -D_DEFAULT_SOURCE
+MODULE__SHA1_STATE=yes
+MODULE__SHA1_CFLAGS=-I$(srcdir)/Modules/_hacl/include -I$(srcdir)/Modules/_hacl/internal -D_BSD_SOURCE -D_DEFAULT_SOURCE
+MODULE__SHA2_STATE=yes
+MODULE__SHA2_CFLAGS=-I$(srcdir)/Modules/_hacl/include -I$(srcdir)/Modules/_hacl/internal -D_BSD_SOURCE -D_DEFAULT_SOURCE
+MODULE__SHA3_STATE=yes
+MODULE__BLAKE2_STATE=yes
+MODULE__BLAKE2_CFLAGS=
+MODULE__BLAKE2_LDFLAGS=
+MODULE__CTYPES_STATE=yes
+MODULE__CTYPES_CFLAGS=-fno-strict-overflow 
+MODULE__CTYPES_LDFLAGS=-lffi -ldl
+MODULE__CURSES_STATE=yes
+MODULE__CURSES_CFLAGS=-D_DEFAULT_SOURCE 
+MODULE__CURSES_LDFLAGS=-lncursesw -ltinfo
+
+MODULE__CURSES_PANEL_STATE=yes
+MODULE__CURSES_PANEL_CFLAGS=-D_DEFAULT_SOURCE  -D_DEFAULT_SOURCE 
+MODULE__CURSES_PANEL_LDFLAGS=-lpanelw -lncursesw -ltinfo
+
+MODULE__DECIMAL_STATE=yes
+MODULE__DECIMAL_CFLAGS=-I$(srcdir)/Modules/_decimal/libmpdec -DCONFIG_64=1 -DANSI=1 -DHAVE_UINT128_T=1
+MODULE__DECIMAL_LDFLAGS=-lm $(LIBMPDEC_A)
+MODULE__DBM_STATE=missing
+MODULE__GDBM_STATE=missing
+MODULE_READLINE_STATE=yes
+MODULE_READLINE_CFLAGS=-D_DEFAULT_SOURCE 
+MODULE_READLINE_LDFLAGS=-lreadline
+MODULE__SQLITE3_STATE=yes
+MODULE__SQLITE3_CFLAGS= -I$(srcdir)/Modules/_sqlite
+MODULE__SQLITE3_LDFLAGS=-lsqlite3
+MODULE__TKINTER_STATE=missing
+MODULE__UUID_STATE=yes
+MODULE__UUID_CFLAGS=-I/usr/include/uuid
+MODULE__UUID_LDFLAGS=-luuid
+MODULE_ZLIB_STATE=yes
+MODULE_ZLIB_CFLAGS=
+MODULE_ZLIB_LDFLAGS=-lz
+MODULE_BINASCII_STATE=yes
+MODULE_BINASCII_CFLAGS=-DUSE_ZLIB_CRC32 
+MODULE_BINASCII_LDFLAGS=-lz
+MODULE__BZ2_STATE=yes
+MODULE__BZ2_CFLAGS=
+MODULE__BZ2_LDFLAGS=-lbz2
+MODULE__LZMA_STATE=yes
+MODULE__LZMA_CFLAGS=
+MODULE__LZMA_LDFLAGS=-llzma
+MODULE__SSL_STATE=yes
+MODULE__SSL_CFLAGS=
+MODULE__SSL_LDFLAGS=  -lssl -lcrypto
+MODULE__HASHLIB_STATE=yes
+MODULE__HASHLIB_CFLAGS=
+MODULE__HASHLIB_LDFLAGS=   -lcrypto
+MODULE__TESTCAPI_STATE=yes
+MODULE__TESTCAPI_LDFLAGS=
+MODULE__TESTCLINIC_STATE=yes
+MODULE__TESTCLINIC_LIMITED_STATE=yes
+MODULE__TESTLIMITEDCAPI_STATE=yes
+MODULE__TESTINTERNALCAPI_STATE=yes
+MODULE__TESTBUFFER_STATE=yes
+MODULE__TESTIMPORTMULTIPLE_STATE=yes
+MODULE__TESTMULTIPHASE_STATE=yes
+MODULE__TESTSINGLEPHASE_STATE=yes
+MODULE__TESTEXTERNALINSPECTION_STATE=yes
+MODULE_XXSUBTYPE_STATE=yes
+MODULE__XXTESTFUZZ_STATE=yes
+MODULE__CTYPES_TEST_STATE=yes
+MODULE__CTYPES_TEST_LDFLAGS=-lm
+MODULE_XXLIMITED_STATE=yes
+MODULE_XXLIMITED_35_STATE=yes
+
+
+# Default zoneinfo.TZPATH. Added here to expose it in sysconfig.get_config_var
+TZPATH=/usr/share/zoneinfo:/usr/lib/zoneinfo:/usr/share/lib/zoneinfo:/etc/zoneinfo
+
+# If to install mimalloc headers
+INSTALL_MIMALLOC=yes
+
+# Modes for directories, executables and data files created by the
+# install process.  Default to user-only-writable for all file types.
+DIRMODE=	755
+EXEMODE=	755
+FILEMODE=	644
+
+# configure script arguments
+CONFIG_ARGS=	
+
+
+# Subdirectories with code
+SRCDIRS= 	  Modules   Modules/_blake2   Modules/_ctypes   Modules/_decimal   Modules/_decimal/libmpdec   Modules/_hacl   Modules/_io   Modules/_multiprocessing   Modules/_sqlite   Modules/_sre   Modules/_testcapi   Modules/_testinternalcapi   Modules/_testlimitedcapi   Modules/_xxtestfuzz   Modules/cjkcodecs   Modules/expat   Objects   Objects/mimalloc   Objects/mimalloc/prim   Parser   Parser/tokenizer   Parser/lexer   Programs   Python   Python/frozen_modules
+
+# Other subdirectories
+SUBDIRSTOO=	Include Lib Misc
+
+# assets for Emscripten browser builds
+WASM_ASSETS_DIR=.$(prefix)
+WASM_STDLIB=$(WASM_ASSETS_DIR)/lib/python$(VERSION)/os.py
+
+# Files and directories to be distributed
+CONFIGFILES=	configure configure.ac acconfig.h pyconfig.h.in Makefile.pre.in
+DISTFILES=	README.rst ChangeLog $(CONFIGFILES)
+DISTDIRS=	$(SUBDIRS) $(SUBDIRSTOO) Ext-dummy
+DIST=		$(DISTFILES) $(DISTDIRS)
+
+
+LIBRARY=	libpython$(VERSION)$(ABIFLAGS).a
+LDLIBRARY=      libpython$(VERSION)$(ABIFLAGS).a
+BLDLIBRARY=     $(LDLIBRARY)
+PY3LIBRARY=     
+DLLLIBRARY=	
+LDLIBRARYDIR=   
+INSTSONAME=	$(LDLIBRARY)
+LIBRARY_DEPS=	$(LIBRARY) $(PY3LIBRARY) $(EXPORTSYMS)
+LINK_PYTHON_DEPS=$(LIBRARY_DEPS)
+PY_ENABLE_SHARED=	0
+STATIC_LIBPYTHON=	1
+
+
+LIBS=		-ldl 
+LIBM=		-lm
+LIBC=		
+SYSLIBS=	$(LIBM) $(LIBC)
+SHLIBS=		$(LIBS)
+
+DLINCLDIR=	.
+DYNLOADFILE=	dynload_shlib.o
+MACHDEP_OBJS=	
+LIBOBJDIR=	Python/
+LIBOBJS=	
+
+PYTHON=		python$(EXE)
+BUILDPYTHON=	python$(BUILDEXE)
+
+HOSTRUNNER= 
+
+PYTHON_FOR_REGEN?=python3.13
+UPDATE_FILE=$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/update_file.py
+PYTHON_FOR_BUILD=./$(BUILDPYTHON) -E
+# Single-platform builds depend on $(BUILDPYTHON). Cross builds use an
+# external "build Python" and have an empty PYTHON_FOR_BUILD_DEPS.
+PYTHON_FOR_BUILD_DEPS=$(BUILDPYTHON)
+
+# Single-platform builds use Programs/_freeze_module.c for bootstrapping and
+# ./_bootstrap_python Programs/_freeze_module.py for remaining modules
+# Cross builds use an external "build Python" for all modules.
+PYTHON_FOR_FREEZE=./_bootstrap_python
+FREEZE_MODULE_BOOTSTRAP=./Programs/_freeze_module
+FREEZE_MODULE_BOOTSTRAP_DEPS=Programs/_freeze_module
+FREEZE_MODULE=$(PYTHON_FOR_FREEZE) $(srcdir)/Programs/_freeze_module.py
+FREEZE_MODULE_DEPS=_bootstrap_python $(srcdir)/Programs/_freeze_module.py
+
+_PYTHON_HOST_PLATFORM=
+BUILD_GNU_TYPE=	x86_64-pc-linux-gnu
+HOST_GNU_TYPE=	x86_64-pc-linux-gnu
+
+# The task to run while instrumented when building the profile-opt target.
+# To speed up profile generation, we don't run the full unit test suite
+# by default. The default is "-m test --pgo". To run more tests, use
+# PROFILE_TASK="-m test --pgo-extended"
+PROFILE_TASK=	-m test --pgo --timeout=$(TESTTIMEOUT)
+
+# report files for gcov / lcov coverage report
+COVERAGE_INFO=	$(abs_builddir)/coverage.info
+COVERAGE_REPORT=$(abs_builddir)/lcov-report
+COVERAGE_LCOV_OPTIONS=--rc lcov_branch_coverage=1
+COVERAGE_REPORT_OPTIONS=--rc lcov_branch_coverage=1 --branch-coverage --title "CPython $(VERSION) LCOV report [commit $(shell $(GITVERSION))]"
+
+
+# === Definitions added by makesetup ===
+
+
+##########################################################################
+# Modules
+MODULE_OBJS=	\
+		Modules/config.o \
+		Modules/main.o \
+		Modules/gcmodule.o
+
+IO_H=		Modules/_io/_iomodule.h
+
+IO_OBJS=	\
+		Modules/_io/_iomodule.o \
+		Modules/_io/iobase.o \
+		Modules/_io/fileio.o \
+		Modules/_io/bufferedio.o \
+		Modules/_io/textio.o \
+		Modules/_io/bytesio.o \
+		Modules/_io/stringio.o
+
+
+##########################################################################
+# mimalloc
+
+MIMALLOC_HEADERS= \
+	$(srcdir)/Include/internal/pycore_mimalloc.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc/atomic.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc/internal.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc/prim.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc/track.h \
+	$(srcdir)/Include/internal/mimalloc/mimalloc/types.h
+
+
+##########################################################################
+# Parser
+
+PEGEN_OBJS=		\
+		Parser/pegen.o \
+		Parser/pegen_errors.o \
+		Parser/action_helpers.o \
+		Parser/parser.o \
+		Parser/string_parser.o \
+		Parser/peg_api.o
+
+TOKENIZER_OBJS=		\
+		Parser/lexer/buffer.o \
+		Parser/lexer/lexer.o \
+		Parser/lexer/state.o \
+		Parser/tokenizer/file_tokenizer.o \
+		Parser/tokenizer/readline_tokenizer.o \
+		Parser/tokenizer/string_tokenizer.o \
+		Parser/tokenizer/utf8_tokenizer.o \
+		Parser/tokenizer/helpers.o
+
+PEGEN_HEADERS= \
+		$(srcdir)/Include/internal/pycore_parser.h \
+		$(srcdir)/Parser/pegen.h \
+		$(srcdir)/Parser/string_parser.h
+
+TOKENIZER_HEADERS= \
+		Parser/lexer/buffer.h \
+		Parser/lexer/lexer.h \
+		Parser/lexer/state.h \
+		Parser/tokenizer/tokenizer.h \
+		Parser/tokenizer/helpers.h
+
+POBJS=		\
+		Parser/token.o \
+
+PARSER_OBJS=	$(POBJS) $(PEGEN_OBJS) $(TOKENIZER_OBJS) Parser/myreadline.o
+
+PARSER_HEADERS= \
+		$(PEGEN_HEADERS) \
+		$(TOKENIZER_HEADERS)
+
+##########################################################################
+# Python
+
+PYTHON_OBJS=	\
+		Python/_warnings.o \
+		Python/Python-ast.o \
+		Python/Python-tokenize.o \
+		Python/asdl.o \
+		Python/assemble.o \
+		Python/ast.o \
+		Python/ast_opt.o \
+		Python/ast_unparse.o \
+		Python/bltinmodule.o \
+		Python/brc.o \
+		Python/ceval.o \
+		Python/codecs.o \
+		Python/compile.o \
+		Python/context.o \
+		Python/critical_section.o \
+		Python/crossinterp.o \
+		Python/dynamic_annotations.o \
+		Python/errors.o \
+		Python/flowgraph.o \
+		Python/frame.o \
+		Python/frozenmain.o \
+		Python/future.o \
+		Python/gc.o \
+		Python/gc_free_threading.o \
+		Python/gc_gil.o \
+		Python/getargs.o \
+		Python/getcompiler.o \
+		Python/getcopyright.o \
+		Python/getplatform.o \
+		Python/getversion.o \
+		Python/ceval_gil.o \
+		Python/hamt.o \
+		Python/hashtable.o \
+		Python/import.o \
+		Python/importdl.o \
+		Python/initconfig.o \
+		Python/interpconfig.o \
+		Python/instrumentation.o \
+		Python/instruction_sequence.o \
+		Python/intrinsics.o \
+		Python/jit.o \
+		Python/legacy_tracing.o \
+		Python/lock.o \
+		Python/marshal.o \
+		Python/modsupport.o \
+		Python/mysnprintf.o \
+		Python/mystrtoul.o \
+		Python/object_stack.o \
+		Python/optimizer.o \
+		Python/optimizer_analysis.o \
+		Python/optimizer_symbols.o \
+		Python/parking_lot.o \
+		Python/pathconfig.o \
+		Python/preconfig.o \
+		Python/pyarena.o \
+		Python/pyctype.o \
+		Python/pyfpe.o \
+		Python/pyhash.o \
+		Python/pylifecycle.o \
+		Python/pymath.o \
+		Python/pystate.o \
+		Python/pythonrun.o \
+		Python/pytime.o \
+		Python/qsbr.o \
+		Python/bootstrap_hash.o \
+		Python/specialize.o \
+		Python/structmember.o \
+		Python/symtable.o \
+		Python/sysmodule.o \
+		Python/thread.o \
+		Python/traceback.o \
+		Python/tracemalloc.o \
+		Python/getopt.o \
+		Python/pystrcmp.o \
+		Python/pystrtod.o \
+		Python/pystrhex.o \
+		Python/dtoa.o \
+		Python/formatter_unicode.o \
+		Python/fileutils.o \
+		Python/suggestions.o \
+		Python/perf_trampoline.o \
+		Python/perf_jit_trampoline.o \
+		Python/$(DYNLOADFILE) \
+		$(LIBOBJS) \
+		$(MACHDEP_OBJS) \
+		$(DTRACE_OBJS) \
+		
+
+
+##########################################################################
+# Objects
+OBJECT_OBJS=	\
+		Objects/abstract.o \
+		Objects/boolobject.o \
+		Objects/bytes_methods.o \
+		Objects/bytearrayobject.o \
+		Objects/bytesobject.o \
+		Objects/call.o \
+		Objects/capsule.o \
+		Objects/cellobject.o \
+		Objects/classobject.o \
+		Objects/codeobject.o \
+		Objects/complexobject.o \
+		Objects/descrobject.o \
+		Objects/enumobject.o \
+		Objects/exceptions.o \
+		Objects/genericaliasobject.o \
+		Objects/genobject.o \
+		Objects/fileobject.o \
+		Objects/floatobject.o \
+		Objects/frameobject.o \
+		Objects/funcobject.o \
+		Objects/iterobject.o \
+		Objects/listobject.o \
+		Objects/longobject.o \
+		Objects/dictobject.o \
+		Objects/odictobject.o \
+		Objects/memoryobject.o \
+		Objects/methodobject.o \
+		Objects/moduleobject.o \
+		Objects/namespaceobject.o \
+		Objects/object.o \
+		Objects/obmalloc.o \
+		Objects/picklebufobject.o \
+		Objects/rangeobject.o \
+		Objects/setobject.o \
+		Objects/sliceobject.o \
+		Objects/structseq.o \
+		Objects/tupleobject.o \
+		Objects/typeobject.o \
+		Objects/typevarobject.o \
+		Objects/unicodeobject.o \
+		Objects/unicodectype.o \
+		Objects/unionobject.o \
+		Objects/weakrefobject.o \
+		Python/asm_trampoline.o
+
+##########################################################################
+# objects that get linked into the Python library
+LIBRARY_OBJS_OMIT_FROZEN=	\
+		Modules/getbuildinfo.o \
+		$(PARSER_OBJS) \
+		$(OBJECT_OBJS) \
+		$(PYTHON_OBJS) \
+		$(MODULE_OBJS) \
+		$(MODOBJS)
+
+LIBRARY_OBJS=	\
+		$(LIBRARY_OBJS_OMIT_FROZEN) \
+		Modules/getpath.o \
+		Python/frozen.o
+
+LINK_PYTHON_OBJS=$(LIBRARY_OBJS)
+
+##########################################################################
+# DTrace
+
+# On some systems, object files that reference DTrace probes need to be modified
+# in-place by dtrace(1).
+DTRACE_DEPS = \
+	Python/ceval.o Python/gc.o Python/import.o Python/sysmodule.o
+
+##########################################################################
+# decimal's libmpdec
+
+LIBMPDEC_OBJS= \
+		Modules/_decimal/libmpdec/basearith.o \
+		Modules/_decimal/libmpdec/constants.o \
+		Modules/_decimal/libmpdec/context.o \
+		Modules/_decimal/libmpdec/convolute.o \
+		Modules/_decimal/libmpdec/crt.o \
+		Modules/_decimal/libmpdec/difradix2.o \
+		Modules/_decimal/libmpdec/fnt.o \
+		Modules/_decimal/libmpdec/fourstep.o \
+		Modules/_decimal/libmpdec/io.o \
+		Modules/_decimal/libmpdec/mpalloc.o \
+		Modules/_decimal/libmpdec/mpdecimal.o \
+		Modules/_decimal/libmpdec/numbertheory.o \
+		Modules/_decimal/libmpdec/sixstep.o \
+		Modules/_decimal/libmpdec/transpose.o
+		# _decimal does not use signaling API
+		# Modules/_decimal/libmpdec/mpsignal.o
+
+LIBMPDEC_HEADERS= \
+		$(srcdir)/Modules/_decimal/libmpdec/basearith.h \
+		$(srcdir)/Modules/_decimal/libmpdec/bits.h \
+		$(srcdir)/Modules/_decimal/libmpdec/constants.h \
+		$(srcdir)/Modules/_decimal/libmpdec/convolute.h \
+		$(srcdir)/Modules/_decimal/libmpdec/crt.h \
+		$(srcdir)/Modules/_decimal/libmpdec/difradix2.h \
+		$(srcdir)/Modules/_decimal/libmpdec/fnt.h \
+		$(srcdir)/Modules/_decimal/libmpdec/fourstep.h \
+		$(srcdir)/Modules/_decimal/libmpdec/io.h \
+		$(srcdir)/Modules/_decimal/libmpdec/mpalloc.h \
+		$(srcdir)/Modules/_decimal/libmpdec/mpdecimal.h \
+		$(srcdir)/Modules/_decimal/libmpdec/numbertheory.h \
+		$(srcdir)/Modules/_decimal/libmpdec/sixstep.h \
+		$(srcdir)/Modules/_decimal/libmpdec/transpose.h \
+		$(srcdir)/Modules/_decimal/libmpdec/typearith.h \
+		$(srcdir)/Modules/_decimal/libmpdec/umodarith.h
+
+##########################################################################
+# pyexpat's expat library
+
+LIBEXPAT_OBJS= \
+		Modules/expat/xmlparse.o \
+		Modules/expat/xmlrole.o \
+		Modules/expat/xmltok.o
+
+LIBEXPAT_HEADERS= \
+		Modules/expat/ascii.h \
+		Modules/expat/asciitab.h \
+		Modules/expat/expat.h \
+		Modules/expat/expat_config.h \
+		Modules/expat/expat_external.h \
+		Modules/expat/iasciitab.h \
+		Modules/expat/internal.h \
+		Modules/expat/latin1tab.h \
+		Modules/expat/nametab.h \
+		Modules/expat/pyexpatns.h \
+		Modules/expat/siphash.h \
+		Modules/expat/utf8tab.h \
+		Modules/expat/xmlrole.h \
+		Modules/expat/xmltok.h \
+		Modules/expat/xmltok_impl.h \
+		Modules/expat/xmltok_impl.c \
+		Modules/expat/xmltok_ns.c
+
+##########################################################################
+# hashlib's HACL* library
+
+LIBHACL_SHA2_OBJS= \
+                Modules/_hacl/Hacl_Hash_SHA2.o
+
+LIBHACL_HEADERS= \
+                Modules/_hacl/include/krml/FStar_UInt128_Verified.h \
+                Modules/_hacl/include/krml/FStar_UInt_8_16_32_64.h \
+                Modules/_hacl/include/krml/fstar_uint128_struct_endianness.h \
+                Modules/_hacl/include/krml/internal/target.h \
+                Modules/_hacl/include/krml/lowstar_endianness.h \
+                Modules/_hacl/include/krml/types.h \
+		Modules/_hacl/Hacl_Streaming_Types.h \
+                Modules/_hacl/python_hacl_namespaces.h
+
+LIBHACL_SHA2_HEADERS= \
+                Modules/_hacl/Hacl_Hash_SHA2.h \
+                Modules/_hacl/internal/Hacl_Hash_SHA2.h \
+		$(LIBHACL_HEADERS)
+
+#########################################################################
+# Rules
+
+# Default target
+all:		build_all
+
+# First target in Makefile is implicit default. So .PHONY needs to come after
+# all.
+.PHONY: all
+
+# Provide quick help for common Makefile targets.
+.PHONY: help
+help:
+	@echo "Run 'make' to build the Python executable and extension modules"
+	@echo ""
+	@echo "or 'make <target>' where <target> is one of:"
+	@echo "  test         run the test suite"
+	@echo "  install      install built files"
+	@echo "  regen-all    regenerate a number of generated source files"
+	@echo "  clinic       run Argument Clinic over source files"
+	@echo ""
+	@echo "  clean        to remove build files"
+	@echo "  distclean    'clean' + remove other generated files (patch, exe, etc)"
+	@echo ""
+	@echo "  recheck      rerun configure with last cmdline options"
+	@echo "  reindent     reindent .py files in Lib directory"
+	@echo "  tags         build a tags file (useful for Emacs and other editors)"
+	@echo "  list-targets list all targets in the Makefile"
+
+# Display a full list of Makefile targets
+.PHONY: list-targets
+list-targets:
+	@grep -E '^[A-Za-z][-A-Za-z0-9]+:' Makefile | awk -F : '{print $$1}'
+
+.PHONY: build_all
+build_all:	check-clean-src check-app-store-compliance $(BUILDPYTHON) platform sharedmods \
+		gdbhooks Programs/_testembed scripts checksharedmods rundsymutil
+
+.PHONY: build_wasm
+build_wasm: check-clean-src $(BUILDPYTHON) platform sharedmods \
+		python-config checksharedmods
+
+# Check that the source is clean when building out of source.
+.PHONY: check-clean-src
+check-clean-src:
+	@if test -n "$(VPATH)" -a \( \
+	    -f "$(srcdir)/$(BUILDPYTHON)" \
+	    -o -f "$(srcdir)/Programs/python.o" \
+	    -o -f "$(srcdir)/Python/frozen_modules/importlib._bootstrap.h" \
+	\); then \
+		echo "Error: The source directory ($(srcdir)) is not clean" ; \
+		echo "Building Python out of the source tree (in $(abs_builddir)) requires a clean source tree ($(abs_srcdir))" ; \
+		echo "Build artifacts such as .o files, executables, and Python/frozen_modules/*.h must not exist within $(srcdir)." ; \
+		echo "Try to run:" ; \
+		echo "  (cd \"$(srcdir)\" && make clean || git clean -fdx -e Doc/venv)" ; \
+		exit 1; \
+	fi
+
+# Check that the app store compliance patch can be applied (if configured).
+# This is checked as a dry-run against the original library sources;
+# the patch will be actually applied during the install phase.
+.PHONY: check-app-store-compliance
+check-app-store-compliance:
+	@if [ "$(APP_STORE_COMPLIANCE_PATCH)" != "" ]; then \
+		patch --dry-run --quiet --force --strip 1 --directory "$(abs_srcdir)" --input "$(abs_srcdir)/$(APP_STORE_COMPLIANCE_PATCH)"; \
+		echo "App store compliance patch can be applied."; \
+	fi
+
+# Profile generation build must start from a clean tree.
+profile-clean-stamp:
+	$(MAKE) clean-profile
+	touch $@
+
+# Compile with profile generation enabled.
+profile-gen-stamp: profile-clean-stamp
+	@if [ $(LLVM_PROF_ERR) = yes ]; then \
+		echo "Error: Cannot perform PGO build because llvm-profdata was not found in PATH" ;\
+		echo "Please add it to PATH and run ./configure again" ;\
+		exit 1;\
+	fi
+	@echo "Building with support for profile generation:"
+	$(MAKE) all CFLAGS_NODIST="$(CFLAGS_NODIST) $(PGO_PROF_GEN_FLAG)" LDFLAGS_NODIST="$(LDFLAGS_NODIST) $(PGO_PROF_GEN_FLAG)" LIBS="$(LIBS)"
+	touch $@
+
+# Run task with profile generation build to create profile information.
+profile-run-stamp:
+	@echo "Running code to generate profile data (this can take a while):"
+	# First, we need to create a clean build with profile generation
+	# enabled.
+	$(MAKE) profile-gen-stamp
+	# Next, run the profile task to generate the profile information.
+	@ # FIXME: can't run for a cross build
+	task="$(PROFILE_TASK)"; \
+	case "$$task" in \
+	*-s\ *) \
+	  $(LLVM_PROF_FILE) $(RUNSHARED) ./$(BUILDPYTHON) $$task; \
+	  while [ -f $(abs_builddir)/build/pynexttest ]; do \
+	    $(LLVM_PROF_FILE) $(RUNSHARED) ./$(BUILDPYTHON) $$task; \
+	  done;; \
+	*) \
+	  $(LLVM_PROF_FILE) $(RUNSHARED) ./$(BUILDPYTHON) $$task; \
+	esac || true
+	$(LLVM_PROF_MERGER)
+	# Remove profile generation binary since we are done with it.
+	$(MAKE) clean-retain-profile
+	# This is an expensive target to build and it does not have proper
+	# makefile dependency information.  So, we create a "stamp" file
+	# to record its completion and avoid re-running it.
+	touch $@
+
+# Compile Python binary with profile guided optimization.
+# To force re-running of the profile task, remove the profile-run-stamp file.
+.PHONY: profile-opt
+profile-opt: profile-run-stamp
+	@echo "Rebuilding with profile guided optimizations:"
+	-rm -f profile-clean-stamp
+	$(MAKE) all CFLAGS_NODIST="$(CFLAGS_NODIST) $(PGO_PROF_USE_FLAG)" LDFLAGS_NODIST="$(LDFLAGS_NODIST)"
+
+# List of binaries that BOLT runs on.
+BOLT_BINARIES := $(BUILDPYTHON)
+
+BOLT_INSTRUMENT_FLAGS :=  -update-debug-sections -skip-funcs=_PyEval_EvalFrameDefault,sre_ucs1_match/1,sre_ucs2_match/1,sre_ucs4_match/1 
+BOLT_APPLY_FLAGS :=   -update-debug-sections -skip-funcs=_PyEval_EvalFrameDefault,sre_ucs1_match/1,sre_ucs2_match/1,sre_ucs4_match/1  -reorder-blocks=ext-tsp -reorder-functions=cdsort -split-functions -icf=1 -inline-all -split-eh -reorder-functions-use-hot-size -peepholes=none -jump-tables=aggressive -inline-ap -indirect-call-promotion=all -dyno-stats -use-gnu-stack -frame-opt=hot 
+
+.PHONY: clean-bolt
+clean-bolt:
+	# Profile data.
+	rm -f *.fdata
+	# Pristine binaries before BOLT optimization.
+	rm -f *.prebolt
+	# BOLT instrumented binaries.
+	rm -f *.bolt_inst
+
+profile-bolt-stamp: $(BUILDPYTHON)
+	# Ensure a pristine, pre-BOLT copy of the binary and no profile data from last run.
+	for bin in $(BOLT_BINARIES); do \
+	  prebolt="$${bin}.prebolt"; \
+	  if [ -e "$${prebolt}" ]; then \
+	    echo "Restoring pre-BOLT binary $${prebolt}"; \
+	    mv "$${bin}.prebolt" "$${bin}"; \
+	  fi; \
+	  cp "$${bin}" "$${prebolt}"; \
+	  rm -f $${bin}.bolt.*.fdata $${bin}.fdata; \
+	done
+	# Instrument each binary.
+	for bin in $(BOLT_BINARIES); do \
+	   "$${bin}" -instrument -instrumentation-file-append-pid -instrumentation-file=$(abspath $${bin}.bolt) -o $${bin}.bolt_inst $(BOLT_INSTRUMENT_FLAGS); \
+	  mv "$${bin}.bolt_inst" "$${bin}"; \
+	done
+	# Run instrumented binaries to collect data.
+	$(RUNSHARED) ./$(BUILDPYTHON) $(PROFILE_TASK)
+	# Merge all the data files together.
+	for bin in $(BOLT_BINARIES); do \
+	   $${bin}.*.fdata > "$${bin}.fdata"; \
+	  rm -f $${bin}.*.fdata; \
+	done
+	# Run bolt against the merged data to produce an optimized binary.
+	for bin in $(BOLT_BINARIES); do \
+	   "$${bin}.prebolt" -o "$${bin}.bolt" -data="$${bin}.fdata" $(BOLT_APPLY_FLAGS); \
+	  mv "$${bin}.bolt" "$${bin}"; \
+	done
+	touch $@
+
+.PHONY: bolt-opt
+bolt-opt:
+	$(MAKE) 
+	$(MAKE) profile-bolt-stamp
+
+# Compile and run with gcov
+.PHONY: coverage
+coverage:
+	@echo "Building with support for coverage checking:"
+	$(MAKE) clean
+	$(MAKE) all CFLAGS="$(CFLAGS) -O0 -pg --coverage" LDFLAGS="$(LDFLAGS) --coverage"
+
+.PHONY: coverage-lcov
+coverage-lcov:
+	@echo "Creating Coverage HTML report with LCOV:"
+	@rm -f $(COVERAGE_INFO)
+	@rm -rf $(COVERAGE_REPORT)
+	@lcov $(COVERAGE_LCOV_OPTIONS) --capture \
+	    --directory $(abs_builddir) \
+	    --base-directory $(realpath $(abs_builddir)) \
+	    --path $(realpath $(abs_srcdir)) \
+	    --output-file $(COVERAGE_INFO)
+	@ # remove 3rd party modules, system headers and internal files with
+	@ # debug, test or dummy functions.
+	@lcov $(COVERAGE_LCOV_OPTIONS) --remove $(COVERAGE_INFO) \
+	    '*/Modules/_blake2/impl/*' \
+	    '*/Modules/_ctypes/libffi*/*' \
+	    '*/Modules/_decimal/libmpdec/*' \
+	    '*/Modules/expat/*' \
+	    '*/Modules/xx*.c' \
+	    '*/Python/pyfpe.c' \
+	    '*/Python/pystrcmp.c' \
+	    '/usr/include/*' \
+	    '/usr/local/include/*' \
+	    '/usr/lib/gcc/*' \
+	    --output-file $(COVERAGE_INFO)
+	@genhtml $(COVERAGE_INFO) \
+	    --output-directory $(COVERAGE_REPORT) \
+	    $(COVERAGE_REPORT_OPTIONS)
+	@echo
+	@echo "lcov report at $(COVERAGE_REPORT)/index.html"
+	@echo
+
+# Force regeneration of parser and frozen modules
+.PHONY: coverage-report
+coverage-report: regen-token regen-frozen
+	@ # build with coverage info
+	$(MAKE) coverage
+	@ # run tests, ignore failures
+	$(TESTRUNNER) --fast-ci --timeout=$(TESTTIMEOUT) $(TESTOPTS) || true
+	@ # build lcov report
+	$(MAKE) coverage-lcov
+
+# Run "Argument Clinic" over all source files
+.PHONY: clinic
+clinic: check-clean-src $(srcdir)/Modules/_blake2/blake2s_impl.c
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/clinic/clinic.py --make --exclude Lib/test/clinic.test.c --srcdir $(srcdir)
+
+.PHONY: clinic-tests
+clinic-tests: check-clean-src $(srcdir)/Lib/test/clinic.test.c
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/clinic/clinic.py -f $(srcdir)/Lib/test/clinic.test.c
+
+# Build the interpreter
+$(BUILDPYTHON):	Programs/python.o $(LINK_PYTHON_DEPS)
+	$(LINKCC) $(PY_CORE_LDFLAGS) $(LINKFORSHARED) -o $@ Programs/python.o $(LINK_PYTHON_OBJS) $(LIBS) $(MODLIBS) $(SYSLIBS)
+
+platform: $(PYTHON_FOR_BUILD_DEPS) pybuilddir.txt
+	$(RUNSHARED) $(PYTHON_FOR_BUILD) -c 'import sys ; from sysconfig import get_platform ; print("%s-%d.%d" % (get_platform(), *sys.version_info[:2]))' >platform
+
+# Create build directory and generate the sysconfig build-time data there.
+# pybuilddir.txt contains the name of the build dir and is used for
+# sys.path fixup -- see Modules/getpath.c.
+# Since this step runs before shared modules are built, try to avoid bootstrap
+# problems by creating a dummy pybuilddir.txt just to allow interpreter
+# initialization to succeed.  It will be overwritten by generate-posix-vars
+# or removed in case of failure.
+pybuilddir.txt: $(PYTHON_FOR_BUILD_DEPS)
+	@echo "none" > ./pybuilddir.txt
+	$(RUNSHARED) $(PYTHON_FOR_BUILD) -S -m sysconfig --generate-posix-vars ;\
+	if test $$? -ne 0 ; then \
+		echo "generate-posix-vars failed" ; \
+		rm -f ./pybuilddir.txt ; \
+		exit 1 ; \
+	fi
+
+# blake2s is auto-generated from blake2b
+$(srcdir)/Modules/_blake2/blake2s_impl.c: $(srcdir)/Modules/_blake2/blake2b_impl.c $(srcdir)/Modules/_blake2/blake2b2s.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Modules/_blake2/blake2b2s.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/clinic/clinic.py -f $@
+
+# Build static library
+$(LIBRARY): $(LIBRARY_OBJS)
+	-rm -f $@
+	$(AR) $(ARFLAGS) $@ $(LIBRARY_OBJS)
+
+libpython$(LDVERSION).so: $(LIBRARY_OBJS) $(DTRACE_OBJS)
+	# AIX Linker don't support "-h" option
+	if test "$(MACHDEP)" != "aix"; then \
+		$(BLDSHARED) -Wl,-h$(INSTSONAME) -o $(INSTSONAME) $(LIBRARY_OBJS) $(MODLIBS) $(SHLIBS) $(LIBC) $(LIBM); \
+	else \
+		$(BLDSHARED) -o $@ $(LIBRARY_OBJS) $(MODLIBS) $(SHLIBS) $(LIBC) $(LIBM); \
+	fi
+	if test $(INSTSONAME) != $@; then \
+		$(LN) -f $(INSTSONAME) $@; \
+	fi
+
+libpython3.so:	libpython$(LDVERSION).so
+	$(BLDSHARED) $(NO_AS_NEEDED) -o $@ -Wl,-h$@ $^
+
+libpython$(LDVERSION).dylib: $(LIBRARY_OBJS)
+	 $(CC) -dynamiclib $(PY_CORE_LDFLAGS) -undefined dynamic_lookup -Wl,-install_name,$(prefix)/lib/libpython$(LDVERSION).dylib -Wl,-compatibility_version,$(VERSION) -Wl,-current_version,$(VERSION) -o $@ $(LIBRARY_OBJS) $(DTRACE_OBJS) $(SHLIBS) $(LIBC) $(LIBM); \
+
+
+libpython$(VERSION).sl: $(LIBRARY_OBJS)
+	$(LDSHARED) -o $@ $(LIBRARY_OBJS) $(MODLIBS) $(SHLIBS) $(LIBC) $(LIBM)
+
+# List of exported symbols for AIX
+Modules/python.exp: $(LIBRARY)
+	$(srcdir)/Modules/makexp_aix $@ "$(EXPORTSFROM)" $?
+
+# Copy up the gdb python hooks into a position where they can be automatically
+# loaded by gdb during Lib/test/test_gdb.py
+#
+# Distributors are likely to want to install this somewhere else e.g. relative
+# to the stripped DWARF data for the shared library.
+.PHONY: gdbhooks
+gdbhooks: $(BUILDPYTHON)-gdb.py
+
+SRC_GDB_HOOKS=$(srcdir)/Tools/gdb/libpython.py
+$(BUILDPYTHON)-gdb.py: $(SRC_GDB_HOOKS)
+	$(INSTALL_DATA) $(SRC_GDB_HOOKS) $(BUILDPYTHON)-gdb.py
+
+# This rule is here for OPENSTEP/Rhapsody/MacOSX. It builds a temporary
+# minimal framework (not including the Lib directory and such) in the current
+# directory.
+$(PYTHONFRAMEWORKDIR)/Versions/$(VERSION)/$(PYTHONFRAMEWORK): \
+		$(LIBRARY) \
+		$(RESSRCDIR)/Info.plist
+	$(INSTALL) -d -m $(DIRMODE) $(PYTHONFRAMEWORKDIR)/Versions/$(VERSION)
+	$(CC) -o $(LDLIBRARY) $(PY_CORE_LDFLAGS) -dynamiclib \
+		-all_load $(LIBRARY) \
+		-install_name $(DESTDIR)$(PYTHONFRAMEWORKINSTALLNAMEPREFIX)/$(PYTHONFRAMEWORK) \
+		-compatibility_version $(VERSION) \
+		-current_version $(VERSION) \
+		-framework CoreFoundation $(LIBS);
+	$(INSTALL) -d -m $(DIRMODE)  \
+		$(PYTHONFRAMEWORKDIR)/Versions/$(VERSION)/Resources/English.lproj
+	$(INSTALL_DATA) $(RESSRCDIR)/Info.plist \
+		$(PYTHONFRAMEWORKDIR)/Versions/$(VERSION)/Resources/Info.plist
+	$(LN) -fsn $(VERSION) $(PYTHONFRAMEWORKDIR)/Versions/Current
+	$(LN) -fsn Versions/Current/$(PYTHONFRAMEWORK) $(PYTHONFRAMEWORKDIR)/$(PYTHONFRAMEWORK)
+	$(LN) -fsn Versions/Current/Resources $(PYTHONFRAMEWORKDIR)/Resources
+
+# This rule is for iOS, which requires an annoyingly just slightly different
+# format for frameworks to macOS. It *doesn't* use a versioned framework, and
+# the Info.plist must be in the root of the framework.
+$(PYTHONFRAMEWORKDIR)/$(PYTHONFRAMEWORK): \
+		$(LIBRARY) \
+		$(RESSRCDIR)/Info.plist
+	$(INSTALL) -d -m $(DIRMODE) $(PYTHONFRAMEWORKDIR)
+	$(CC) -o $(LDLIBRARY) $(PY_CORE_LDFLAGS) -dynamiclib \
+		-all_load $(LIBRARY) \
+		-install_name $(PYTHONFRAMEWORKINSTALLNAMEPREFIX)/$(PYTHONFRAMEWORK) \
+		-compatibility_version $(VERSION) \
+		-current_version $(VERSION) \
+		-framework CoreFoundation $(LIBS);
+	$(INSTALL_DATA) $(RESSRCDIR)/Info.plist $(PYTHONFRAMEWORKDIR)/Info.plist
+
+# This rule builds the Cygwin Python DLL and import library if configured
+# for a shared core library; otherwise, this rule is a noop.
+$(DLLLIBRARY) libpython$(LDVERSION).dll.a: $(LIBRARY_OBJS)
+	if test -n "$(DLLLIBRARY)"; then \
+		$(LDSHARED) -Wl,--out-implib=$@ -o $(DLLLIBRARY) $^ \
+			$(LIBS) $(MODLIBS) $(SYSLIBS); \
+	else true; \
+	fi
+
+# wasm32-emscripten browser build
+# wasm assets directory is relative to current build dir, e.g. "./usr/local".
+# --preload-file turns a relative asset path into an absolute path.
+
+.PHONY: wasm_stdlib
+wasm_stdlib: $(WASM_STDLIB)
+$(WASM_STDLIB): $(srcdir)/Lib/*.py $(srcdir)/Lib/*/*.py \
+	    $(srcdir)/Tools/wasm/wasm_assets.py \
+	    Makefile pybuilddir.txt Modules/Setup.local
+	$(PYTHON_FOR_BUILD) $(srcdir)/Tools/wasm/wasm_assets.py \
+	    --buildroot . --prefix $(prefix)
+
+python.html: $(srcdir)/Tools/wasm/python.html python.worker.js
+	@cp $(srcdir)/Tools/wasm/python.html $@
+
+python.worker.js: $(srcdir)/Tools/wasm/python.worker.js
+	@cp $(srcdir)/Tools/wasm/python.worker.js $@
+
+############################################################################
+# Header files
+
+PYTHON_HEADERS= \
+		$(srcdir)/Include/Python.h \
+		$(srcdir)/Include/abstract.h \
+		$(srcdir)/Include/bltinmodule.h \
+		$(srcdir)/Include/boolobject.h \
+		$(srcdir)/Include/bytearrayobject.h \
+		$(srcdir)/Include/bytesobject.h \
+		$(srcdir)/Include/ceval.h \
+		$(srcdir)/Include/codecs.h \
+		$(srcdir)/Include/compile.h \
+		$(srcdir)/Include/complexobject.h \
+		$(srcdir)/Include/critical_section.h \
+		$(srcdir)/Include/descrobject.h \
+		$(srcdir)/Include/dictobject.h \
+		$(srcdir)/Include/dynamic_annotations.h \
+		$(srcdir)/Include/enumobject.h \
+		$(srcdir)/Include/errcode.h \
+		$(srcdir)/Include/exports.h \
+		$(srcdir)/Include/fileobject.h \
+		$(srcdir)/Include/fileutils.h \
+		$(srcdir)/Include/floatobject.h \
+		$(srcdir)/Include/frameobject.h \
+		$(srcdir)/Include/genericaliasobject.h \
+		$(srcdir)/Include/import.h \
+		$(srcdir)/Include/intrcheck.h \
+		$(srcdir)/Include/iterobject.h \
+		$(srcdir)/Include/listobject.h \
+		$(srcdir)/Include/lock.h \
+		$(srcdir)/Include/longobject.h \
+		$(srcdir)/Include/marshal.h \
+		$(srcdir)/Include/memoryobject.h \
+		$(srcdir)/Include/methodobject.h \
+		$(srcdir)/Include/modsupport.h \
+		$(srcdir)/Include/moduleobject.h \
+		$(srcdir)/Include/monitoring.h \
+		$(srcdir)/Include/object.h \
+		$(srcdir)/Include/objimpl.h \
+		$(srcdir)/Include/opcode.h \
+		$(srcdir)/Include/opcode_ids.h \
+		$(srcdir)/Include/osdefs.h \
+		$(srcdir)/Include/osmodule.h \
+		$(srcdir)/Include/patchlevel.h \
+		$(srcdir)/Include/pyatomic.h \
+		$(srcdir)/Include/pybuffer.h \
+		$(srcdir)/Include/pycapsule.h \
+		$(srcdir)/Include/pydtrace.h \
+		$(srcdir)/Include/pyerrors.h \
+		$(srcdir)/Include/pyexpat.h \
+		$(srcdir)/Include/pyframe.h \
+		$(srcdir)/Include/pyhash.h \
+		$(srcdir)/Include/pylifecycle.h \
+		$(srcdir)/Include/pymacconfig.h \
+		$(srcdir)/Include/pymacro.h \
+		$(srcdir)/Include/pymath.h \
+		$(srcdir)/Include/pymem.h \
+		$(srcdir)/Include/pyport.h \
+		$(srcdir)/Include/pystate.h \
+		$(srcdir)/Include/pystats.h \
+		$(srcdir)/Include/pystrcmp.h \
+		$(srcdir)/Include/pystrtod.h \
+		$(srcdir)/Include/pythonrun.h \
+		$(srcdir)/Include/pythread.h \
+		$(srcdir)/Include/pytypedefs.h \
+		$(srcdir)/Include/rangeobject.h \
+		$(srcdir)/Include/setobject.h \
+		$(srcdir)/Include/sliceobject.h \
+		$(srcdir)/Include/structmember.h \
+		$(srcdir)/Include/structseq.h \
+		$(srcdir)/Include/sysmodule.h \
+		$(srcdir)/Include/traceback.h \
+		$(srcdir)/Include/tupleobject.h \
+		$(srcdir)/Include/typeslots.h \
+		$(srcdir)/Include/unicodeobject.h \
+		$(srcdir)/Include/warnings.h \
+		$(srcdir)/Include/weakrefobject.h \
+		\
+		pyconfig.h \
+		$(PARSER_HEADERS) \
+		\
+		$(srcdir)/Include/cpython/abstract.h \
+		$(srcdir)/Include/cpython/bytearrayobject.h \
+		$(srcdir)/Include/cpython/bytesobject.h \
+		$(srcdir)/Include/cpython/cellobject.h \
+		$(srcdir)/Include/cpython/ceval.h \
+		$(srcdir)/Include/cpython/classobject.h \
+		$(srcdir)/Include/cpython/code.h \
+		$(srcdir)/Include/cpython/compile.h \
+		$(srcdir)/Include/cpython/complexobject.h \
+		$(srcdir)/Include/cpython/context.h \
+		$(srcdir)/Include/cpython/critical_section.h \
+		$(srcdir)/Include/cpython/descrobject.h \
+		$(srcdir)/Include/cpython/dictobject.h \
+		$(srcdir)/Include/cpython/fileobject.h \
+		$(srcdir)/Include/cpython/fileutils.h \
+		$(srcdir)/Include/cpython/floatobject.h \
+		$(srcdir)/Include/cpython/frameobject.h \
+		$(srcdir)/Include/cpython/funcobject.h \
+		$(srcdir)/Include/cpython/genobject.h \
+		$(srcdir)/Include/cpython/import.h \
+		$(srcdir)/Include/cpython/initconfig.h \
+		$(srcdir)/Include/cpython/listobject.h \
+		$(srcdir)/Include/cpython/lock.h \
+		$(srcdir)/Include/cpython/longintrepr.h \
+		$(srcdir)/Include/cpython/longobject.h \
+		$(srcdir)/Include/cpython/memoryobject.h \
+		$(srcdir)/Include/cpython/methodobject.h \
+		$(srcdir)/Include/cpython/modsupport.h \
+		$(srcdir)/Include/cpython/monitoring.h \
+		$(srcdir)/Include/cpython/object.h \
+		$(srcdir)/Include/cpython/objimpl.h \
+		$(srcdir)/Include/cpython/odictobject.h \
+		$(srcdir)/Include/cpython/picklebufobject.h \
+		$(srcdir)/Include/cpython/pthread_stubs.h \
+		$(srcdir)/Include/cpython/pyatomic.h \
+		$(srcdir)/Include/cpython/pyatomic_gcc.h \
+		$(srcdir)/Include/cpython/pyatomic_std.h \
+		$(srcdir)/Include/cpython/pyctype.h \
+		$(srcdir)/Include/cpython/pydebug.h \
+		$(srcdir)/Include/cpython/pyerrors.h \
+		$(srcdir)/Include/cpython/pyfpe.h \
+		$(srcdir)/Include/cpython/pyframe.h \
+		$(srcdir)/Include/cpython/pyhash.h \
+		$(srcdir)/Include/cpython/pylifecycle.h \
+		$(srcdir)/Include/cpython/pymem.h \
+		$(srcdir)/Include/cpython/pystate.h \
+		$(srcdir)/Include/cpython/pystats.h \
+		$(srcdir)/Include/cpython/pythonrun.h \
+		$(srcdir)/Include/cpython/pythread.h \
+		$(srcdir)/Include/cpython/setobject.h \
+		$(srcdir)/Include/cpython/sysmodule.h \
+		$(srcdir)/Include/cpython/traceback.h \
+		$(srcdir)/Include/cpython/tracemalloc.h \
+		$(srcdir)/Include/cpython/tupleobject.h \
+		$(srcdir)/Include/cpython/unicodeobject.h \
+		$(srcdir)/Include/cpython/warnings.h \
+		$(srcdir)/Include/cpython/weakrefobject.h \
+		\
+		$(MIMALLOC_HEADERS) \
+		\
+		$(srcdir)/Include/internal/pycore_abstract.h \
+		$(srcdir)/Include/internal/pycore_asdl.h \
+		$(srcdir)/Include/internal/pycore_ast.h \
+		$(srcdir)/Include/internal/pycore_ast_state.h \
+		$(srcdir)/Include/internal/pycore_atexit.h \
+		$(srcdir)/Include/internal/pycore_backoff.h \
+		$(srcdir)/Include/internal/pycore_bitutils.h \
+		$(srcdir)/Include/internal/pycore_blocks_output_buffer.h \
+		$(srcdir)/Include/internal/pycore_brc.h \
+		$(srcdir)/Include/internal/pycore_bytes_methods.h \
+		$(srcdir)/Include/internal/pycore_bytesobject.h \
+		$(srcdir)/Include/internal/pycore_call.h \
+		$(srcdir)/Include/internal/pycore_capsule.h \
+		$(srcdir)/Include/internal/pycore_cell.h \
+		$(srcdir)/Include/internal/pycore_ceval.h \
+		$(srcdir)/Include/internal/pycore_ceval_state.h \
+		$(srcdir)/Include/internal/pycore_code.h \
+		$(srcdir)/Include/internal/pycore_codecs.h \
+		$(srcdir)/Include/internal/pycore_compile.h \
+		$(srcdir)/Include/internal/pycore_complexobject.h \
+		$(srcdir)/Include/internal/pycore_condvar.h \
+		$(srcdir)/Include/internal/pycore_context.h \
+		$(srcdir)/Include/internal/pycore_critical_section.h \
+		$(srcdir)/Include/internal/pycore_crossinterp.h \
+		$(srcdir)/Include/internal/pycore_descrobject.h \
+		$(srcdir)/Include/internal/pycore_dict.h \
+		$(srcdir)/Include/internal/pycore_dict_state.h \
+		$(srcdir)/Include/internal/pycore_dtoa.h \
+		$(srcdir)/Include/internal/pycore_exceptions.h \
+		$(srcdir)/Include/internal/pycore_faulthandler.h \
+		$(srcdir)/Include/internal/pycore_fileutils.h \
+		$(srcdir)/Include/internal/pycore_floatobject.h \
+		$(srcdir)/Include/internal/pycore_flowgraph.h \
+		$(srcdir)/Include/internal/pycore_format.h \
+		$(srcdir)/Include/internal/pycore_frame.h \
+		$(srcdir)/Include/internal/pycore_freelist.h \
+		$(srcdir)/Include/internal/pycore_function.h \
+		$(srcdir)/Include/internal/pycore_gc.h \
+		$(srcdir)/Include/internal/pycore_genobject.h \
+		$(srcdir)/Include/internal/pycore_getopt.h \
+		$(srcdir)/Include/internal/pycore_gil.h \
+		$(srcdir)/Include/internal/pycore_global_objects.h \
+		$(srcdir)/Include/internal/pycore_global_objects_fini_generated.h \
+		$(srcdir)/Include/internal/pycore_global_strings.h \
+		$(srcdir)/Include/internal/pycore_hamt.h \
+		$(srcdir)/Include/internal/pycore_hashtable.h \
+		$(srcdir)/Include/internal/pycore_identifier.h \
+		$(srcdir)/Include/internal/pycore_import.h \
+		$(srcdir)/Include/internal/pycore_importdl.h \
+		$(srcdir)/Include/internal/pycore_initconfig.h \
+		$(srcdir)/Include/internal/pycore_instruments.h \
+		$(srcdir)/Include/internal/pycore_instruction_sequence.h \
+		$(srcdir)/Include/internal/pycore_interp.h \
+		$(srcdir)/Include/internal/pycore_intrinsics.h \
+		$(srcdir)/Include/internal/pycore_jit.h \
+		$(srcdir)/Include/internal/pycore_list.h \
+		$(srcdir)/Include/internal/pycore_llist.h \
+		$(srcdir)/Include/internal/pycore_lock.h \
+		$(srcdir)/Include/internal/pycore_long.h \
+		$(srcdir)/Include/internal/pycore_memoryobject.h \
+		$(srcdir)/Include/internal/pycore_mimalloc.h \
+		$(srcdir)/Include/internal/pycore_modsupport.h \
+		$(srcdir)/Include/internal/pycore_moduleobject.h \
+		$(srcdir)/Include/internal/pycore_namespace.h \
+		$(srcdir)/Include/internal/pycore_object.h \
+		$(srcdir)/Include/internal/pycore_object_alloc.h \
+		$(srcdir)/Include/internal/pycore_object_stack.h \
+		$(srcdir)/Include/internal/pycore_object_state.h \
+		$(srcdir)/Include/internal/pycore_obmalloc.h \
+		$(srcdir)/Include/internal/pycore_obmalloc_init.h \
+		$(srcdir)/Include/internal/pycore_opcode_metadata.h \
+		$(srcdir)/Include/internal/pycore_opcode_utils.h \
+		$(srcdir)/Include/internal/pycore_optimizer.h \
+		$(srcdir)/Include/internal/pycore_parking_lot.h \
+		$(srcdir)/Include/internal/pycore_parser.h \
+		$(srcdir)/Include/internal/pycore_pathconfig.h \
+		$(srcdir)/Include/internal/pycore_pyarena.h \
+		$(srcdir)/Include/internal/pycore_pyatomic_ft_wrappers.h \
+		$(srcdir)/Include/internal/pycore_pybuffer.h \
+		$(srcdir)/Include/internal/pycore_pyerrors.h \
+		$(srcdir)/Include/internal/pycore_pyhash.h \
+		$(srcdir)/Include/internal/pycore_pylifecycle.h \
+		$(srcdir)/Include/internal/pycore_pymath.h \
+		$(srcdir)/Include/internal/pycore_pymem.h \
+		$(srcdir)/Include/internal/pycore_pymem_init.h \
+		$(srcdir)/Include/internal/pycore_pystate.h \
+		$(srcdir)/Include/internal/pycore_pystats.h \
+		$(srcdir)/Include/internal/pycore_pythonrun.h \
+		$(srcdir)/Include/internal/pycore_pythread.h \
+		$(srcdir)/Include/internal/pycore_qsbr.h \
+		$(srcdir)/Include/internal/pycore_range.h \
+		$(srcdir)/Include/internal/pycore_runtime.h \
+		$(srcdir)/Include/internal/pycore_runtime_init.h \
+		$(srcdir)/Include/internal/pycore_runtime_init_generated.h \
+		$(srcdir)/Include/internal/pycore_semaphore.h \
+		$(srcdir)/Include/internal/pycore_setobject.h \
+		$(srcdir)/Include/internal/pycore_signal.h \
+		$(srcdir)/Include/internal/pycore_sliceobject.h \
+		$(srcdir)/Include/internal/pycore_strhex.h \
+		$(srcdir)/Include/internal/pycore_structseq.h \
+		$(srcdir)/Include/internal/pycore_symtable.h \
+		$(srcdir)/Include/internal/pycore_sysmodule.h \
+		$(srcdir)/Include/internal/pycore_stackref.h \
+		$(srcdir)/Include/internal/pycore_time.h \
+		$(srcdir)/Include/internal/pycore_token.h \
+		$(srcdir)/Include/internal/pycore_traceback.h \
+		$(srcdir)/Include/internal/pycore_tracemalloc.h \
+		$(srcdir)/Include/internal/pycore_tstate.h \
+		$(srcdir)/Include/internal/pycore_tuple.h \
+		$(srcdir)/Include/internal/pycore_typeobject.h \
+		$(srcdir)/Include/internal/pycore_typevarobject.h \
+		$(srcdir)/Include/internal/pycore_ucnhash.h \
+		$(srcdir)/Include/internal/pycore_unicodeobject.h \
+		$(srcdir)/Include/internal/pycore_unicodeobject_generated.h \
+		$(srcdir)/Include/internal/pycore_unionobject.h \
+		$(srcdir)/Include/internal/pycore_uop_ids.h \
+		$(srcdir)/Include/internal/pycore_uop_metadata.h \
+		$(srcdir)/Include/internal/pycore_warnings.h \
+		$(srcdir)/Include/internal/pycore_weakref.h \
+		$(DTRACE_HEADERS) \
+		 \
+		\
+		$(srcdir)/Python/stdlib_module_names.h
+
+##########################################################################
+# Build static libmpdec.a
+LIBMPDEC_CFLAGS=-I$(srcdir)/Modules/_decimal/libmpdec -DCONFIG_64=1 -DANSI=1 -DHAVE_UINT128_T=1 $(PY_STDMODULE_CFLAGS) $(CCSHARED)
+
+# "%.o: %c" is not portable
+Modules/_decimal/libmpdec/basearith.o: $(srcdir)/Modules/_decimal/libmpdec/basearith.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/basearith.c
+
+Modules/_decimal/libmpdec/constants.o: $(srcdir)/Modules/_decimal/libmpdec/constants.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/constants.c
+
+Modules/_decimal/libmpdec/context.o: $(srcdir)/Modules/_decimal/libmpdec/context.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/context.c
+
+Modules/_decimal/libmpdec/convolute.o: $(srcdir)/Modules/_decimal/libmpdec/convolute.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/convolute.c
+
+Modules/_decimal/libmpdec/crt.o: $(srcdir)/Modules/_decimal/libmpdec/crt.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/crt.c
+
+Modules/_decimal/libmpdec/difradix2.o: $(srcdir)/Modules/_decimal/libmpdec/difradix2.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/difradix2.c
+
+Modules/_decimal/libmpdec/fnt.o: $(srcdir)/Modules/_decimal/libmpdec/fnt.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/fnt.c
+
+Modules/_decimal/libmpdec/fourstep.o: $(srcdir)/Modules/_decimal/libmpdec/fourstep.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/fourstep.c
+
+Modules/_decimal/libmpdec/io.o: $(srcdir)/Modules/_decimal/libmpdec/io.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/io.c
+
+Modules/_decimal/libmpdec/mpalloc.o: $(srcdir)/Modules/_decimal/libmpdec/mpalloc.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/mpalloc.c
+
+Modules/_decimal/libmpdec/mpdecimal.o: $(srcdir)/Modules/_decimal/libmpdec/mpdecimal.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/mpdecimal.c
+
+Modules/_decimal/libmpdec/mpsignal.o: $(srcdir)/Modules/_decimal/libmpdec/mpsignal.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/mpsignal.c
+
+Modules/_decimal/libmpdec/numbertheory.o: $(srcdir)/Modules/_decimal/libmpdec/numbertheory.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/numbertheory.c
+
+Modules/_decimal/libmpdec/sixstep.o: $(srcdir)/Modules/_decimal/libmpdec/sixstep.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/sixstep.c
+
+Modules/_decimal/libmpdec/transpose.o: $(srcdir)/Modules/_decimal/libmpdec/transpose.c $(LIBMPDEC_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBMPDEC_CFLAGS) -o $@ $(srcdir)/Modules/_decimal/libmpdec/transpose.c
+
+$(LIBMPDEC_A): $(LIBMPDEC_OBJS)
+	-rm -f $@
+	$(AR) $(ARFLAGS) $@ $(LIBMPDEC_OBJS)
+
+##########################################################################
+# Build static libexpat.a
+LIBEXPAT_CFLAGS=-I$(srcdir)/Modules/expat $(PY_STDMODULE_CFLAGS) $(CCSHARED)
+
+Modules/expat/xmlparse.o: $(srcdir)/Modules/expat/xmlparse.c $(LIBEXPAT_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBEXPAT_CFLAGS) -o $@ $(srcdir)/Modules/expat/xmlparse.c
+
+Modules/expat/xmlrole.o: $(srcdir)/Modules/expat/xmlrole.c $(LIBEXPAT_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBEXPAT_CFLAGS) -o $@ $(srcdir)/Modules/expat/xmlrole.c
+
+Modules/expat/xmltok.o: $(srcdir)/Modules/expat/xmltok.c $(LIBEXPAT_HEADERS) $(PYTHON_HEADERS)
+	$(CC) -c $(LIBEXPAT_CFLAGS) -o $@ $(srcdir)/Modules/expat/xmltok.c
+
+$(LIBEXPAT_A): $(LIBEXPAT_OBJS)
+	-rm -f $@
+	$(AR) $(ARFLAGS) $@ $(LIBEXPAT_OBJS)
+
+##########################################################################
+# Build HACL* static libraries for hashlib: libHacl_Hash_SHA2.a
+LIBHACL_CFLAGS=-I$(srcdir)/Modules/_hacl/include -D_BSD_SOURCE -D_DEFAULT_SOURCE $(PY_STDMODULE_CFLAGS) $(CCSHARED)
+
+Modules/_hacl/Hacl_Hash_SHA2.o: $(srcdir)/Modules/_hacl/Hacl_Hash_SHA2.c $(LIBHACL_SHA2_HEADERS)
+	$(CC) -c $(LIBHACL_CFLAGS) -o $@ $(srcdir)/Modules/_hacl/Hacl_Hash_SHA2.c
+
+$(LIBHACL_SHA2_A): $(LIBHACL_SHA2_OBJS)
+	-rm -f $@
+	$(AR) $(ARFLAGS) $@ $(LIBHACL_SHA2_OBJS)
+
+# create relative links from build/lib.platform/egg.so to Modules/egg.so
+# pybuilddir.txt is created too late. We cannot use it in Makefile
+# targets. ln --relative is not portable.
+.PHONY: sharedmods
+sharedmods: $(SHAREDMODS) pybuilddir.txt
+	@target=`cat pybuilddir.txt`; \
+	$(MKDIR_P) $$target; \
+	for mod in X $(SHAREDMODS); do \
+		if test $$mod != X; then \
+			$(LN) -sf ../../$$mod $$target/`basename $$mod`; \
+		fi; \
+	done
+
+# dependency on BUILDPYTHON ensures that the target is run last
+.PHONY: checksharedmods
+checksharedmods: sharedmods $(PYTHON_FOR_BUILD_DEPS) $(BUILDPYTHON)
+	@$(RUNSHARED) $(PYTHON_FOR_BUILD) $(srcdir)/Tools/build/check_extension_modules.py
+
+.PHONY: rundsymutil
+rundsymutil: sharedmods $(PYTHON_FOR_BUILD_DEPS) $(BUILDPYTHON)
+	@if [ ! -z $(DSYMUTIL) ] ; then \
+		echo $(DSYMUTIL_PATH) $(BUILDPYTHON); \
+		$(DSYMUTIL_PATH) $(BUILDPYTHON); \
+		if test -f $(LDLIBRARY); then \
+			echo $(DSYMUTIL_PATH) $(LDLIBRARY); \
+			$(DSYMUTIL_PATH) $(LDLIBRARY); \
+		fi; \
+		for mod in X $(SHAREDMODS); do \
+			if test $$mod != X; then \
+				echo $(DSYMUTIL_PATH) $$mod; \
+				$(DSYMUTIL_PATH) $$mod; \
+			fi; \
+		done \
+	fi
+
+Modules/Setup.local:
+	@# Create empty Setup.local when file was deleted by user
+	echo "# Edit this file for local setup changes" > $@
+
+Modules/Setup.bootstrap: $(srcdir)/Modules/Setup.bootstrap.in config.status
+	./config.status $@
+
+Modules/Setup.stdlib: $(srcdir)/Modules/Setup.stdlib.in config.status
+	./config.status $@
+
+Makefile Modules/config.c: Makefile.pre \
+				$(srcdir)/Modules/config.c.in \
+				$(MAKESETUP) \
+				$(srcdir)/Modules/Setup \
+				Modules/Setup.local \
+				Modules/Setup.bootstrap \
+				Modules/Setup.stdlib
+	$(MAKESETUP) -c $(srcdir)/Modules/config.c.in \
+				-s Modules \
+				Modules/Setup.local \
+				Modules/Setup.stdlib \
+				Modules/Setup.bootstrap \
+				$(srcdir)/Modules/Setup
+	@mv config.c Modules
+	@echo "The Makefile was updated, you may need to re-run make."
+
+.PHONY: regen-test-frozenmain
+regen-test-frozenmain: $(BUILDPYTHON)
+	# Regenerate Programs/test_frozenmain.h
+	# from Programs/test_frozenmain.py
+	# using Programs/freeze_test_frozenmain.py
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Programs/freeze_test_frozenmain.py Programs/test_frozenmain.h
+
+.PHONY: regen-test-levenshtein
+regen-test-levenshtein:
+	# Regenerate Lib/test/levenshtein_examples.json
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_levenshtein_examples.py $(srcdir)/Lib/test/levenshtein_examples.json
+
+.PHONY: regen-re
+regen-re: $(BUILDPYTHON)
+	# Regenerate Lib/re/_casefix.py
+	# using Tools/build/generate_re_casefix.py
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/build/generate_re_casefix.py $(srcdir)/Lib/re/_casefix.py
+
+Programs/_testembed: Programs/_testembed.o $(LINK_PYTHON_DEPS)
+	$(LINKCC) $(PY_CORE_LDFLAGS) $(LINKFORSHARED) -o $@ Programs/_testembed.o $(LINK_PYTHON_OBJS) $(LIBS) $(MODLIBS) $(SYSLIBS)
+
+############################################################################
+# "Bootstrap Python" used to run Programs/_freeze_module.py
+
+BOOTSTRAP_HEADERS = \
+	Python/frozen_modules/importlib._bootstrap.h \
+	Python/frozen_modules/importlib._bootstrap_external.h \
+	Python/frozen_modules/zipimport.h
+
+Programs/_bootstrap_python.o: Programs/_bootstrap_python.c $(BOOTSTRAP_HEADERS) $(PYTHON_HEADERS)
+
+_bootstrap_python: $(LIBRARY_OBJS_OMIT_FROZEN) Programs/_bootstrap_python.o Modules/getpath.o Modules/Setup.local
+	$(LINKCC) $(PY_LDFLAGS_NOLTO) -o $@ $(LIBRARY_OBJS_OMIT_FROZEN) \
+		Programs/_bootstrap_python.o Modules/getpath.o $(LIBS) $(MODLIBS) $(SYSLIBS)
+
+
+############################################################################
+# frozen modules (including importlib)
+#
+# Freezing is a multi step process. It works differently for standard builds
+# and cross builds. Standard builds use Programs/_freeze_module and
+# _bootstrap_python for freezing, so users can build Python
+# without an existing Python installation. Cross builds cannot execute
+# compiled binaries and therefore rely on an external build Python
+# interpreter. The build interpreter must have same version and same bytecode
+# as the host (target) binary.
+#
+# Standard build process:
+# 1) compile minimal core objects for Py_Compile*() and PyMarshal_Write*().
+# 2) build Programs/_freeze_module binary.
+# 3) create frozen module headers for importlib and getpath.
+# 4) build _bootstrap_python binary.
+# 5) create remaining frozen module headers with
+#    ``./_bootstrap_python Programs/_freeze_module.py``. The pure Python
+#    script is used to test the cross compile code path.
+#
+# Cross compile process:
+# 1) create all frozen module headers with external build Python and
+#    Programs/_freeze_module.py script.
+#
+
+# FROZEN_FILES_* are auto-generated by Tools/build/freeze_modules.py.
+FROZEN_FILES_IN = \
+		Lib/importlib/_bootstrap.py \
+		Lib/importlib/_bootstrap_external.py \
+		Lib/zipimport.py \
+		Lib/abc.py \
+		Lib/codecs.py \
+		Lib/io.py \
+		Lib/_collections_abc.py \
+		Lib/_sitebuiltins.py \
+		Lib/genericpath.py \
+		Lib/ntpath.py \
+		Lib/posixpath.py \
+		Lib/os.py \
+		Lib/site.py \
+		Lib/stat.py \
+		Lib/importlib/util.py \
+		Lib/importlib/machinery.py \
+		Lib/runpy.py \
+		Lib/__hello__.py \
+		Lib/__phello__/__init__.py \
+		Lib/__phello__/ham/__init__.py \
+		Lib/__phello__/ham/eggs.py \
+		Lib/__phello__/spam.py \
+		Tools/freeze/flag.py
+# End FROZEN_FILES_IN
+FROZEN_FILES_OUT = \
+		Python/frozen_modules/importlib._bootstrap.h \
+		Python/frozen_modules/importlib._bootstrap_external.h \
+		Python/frozen_modules/zipimport.h \
+		Python/frozen_modules/abc.h \
+		Python/frozen_modules/codecs.h \
+		Python/frozen_modules/io.h \
+		Python/frozen_modules/_collections_abc.h \
+		Python/frozen_modules/_sitebuiltins.h \
+		Python/frozen_modules/genericpath.h \
+		Python/frozen_modules/ntpath.h \
+		Python/frozen_modules/posixpath.h \
+		Python/frozen_modules/os.h \
+		Python/frozen_modules/site.h \
+		Python/frozen_modules/stat.h \
+		Python/frozen_modules/importlib.util.h \
+		Python/frozen_modules/importlib.machinery.h \
+		Python/frozen_modules/runpy.h \
+		Python/frozen_modules/__hello__.h \
+		Python/frozen_modules/__phello__.h \
+		Python/frozen_modules/__phello__.ham.h \
+		Python/frozen_modules/__phello__.ham.eggs.h \
+		Python/frozen_modules/__phello__.spam.h \
+		Python/frozen_modules/frozen_only.h
+# End FROZEN_FILES_OUT
+
+Programs/_freeze_module.o: Programs/_freeze_module.c Makefile
+
+Modules/getpath_noop.o: $(srcdir)/Modules/getpath_noop.c Makefile
+
+Programs/_freeze_module: Programs/_freeze_module.o Modules/getpath_noop.o $(LIBRARY_OBJS_OMIT_FROZEN)
+	$(LINKCC) $(PY_CORE_LDFLAGS) -o $@ Programs/_freeze_module.o Modules/getpath_noop.o $(LIBRARY_OBJS_OMIT_FROZEN) $(LIBS) $(MODLIBS) $(SYSLIBS)
+
+# We manually freeze getpath.py rather than through freeze_modules
+Python/frozen_modules/getpath.h: Modules/getpath.py $(FREEZE_MODULE_BOOTSTRAP_DEPS)
+	$(FREEZE_MODULE_BOOTSTRAP) getpath $(srcdir)/Modules/getpath.py Python/frozen_modules/getpath.h
+
+# BEGIN: freezing modules
+
+Python/frozen_modules/importlib._bootstrap.h: Lib/importlib/_bootstrap.py $(FREEZE_MODULE_BOOTSTRAP_DEPS)
+	$(FREEZE_MODULE_BOOTSTRAP) importlib._bootstrap $(srcdir)/Lib/importlib/_bootstrap.py Python/frozen_modules/importlib._bootstrap.h
+
+Python/frozen_modules/importlib._bootstrap_external.h: Lib/importlib/_bootstrap_external.py $(FREEZE_MODULE_BOOTSTRAP_DEPS)
+	$(FREEZE_MODULE_BOOTSTRAP) importlib._bootstrap_external $(srcdir)/Lib/importlib/_bootstrap_external.py Python/frozen_modules/importlib._bootstrap_external.h
+
+Python/frozen_modules/zipimport.h: Lib/zipimport.py $(FREEZE_MODULE_BOOTSTRAP_DEPS)
+	$(FREEZE_MODULE_BOOTSTRAP) zipimport $(srcdir)/Lib/zipimport.py Python/frozen_modules/zipimport.h
+
+Python/frozen_modules/abc.h: Lib/abc.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) abc $(srcdir)/Lib/abc.py Python/frozen_modules/abc.h
+
+Python/frozen_modules/codecs.h: Lib/codecs.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) codecs $(srcdir)/Lib/codecs.py Python/frozen_modules/codecs.h
+
+Python/frozen_modules/io.h: Lib/io.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) io $(srcdir)/Lib/io.py Python/frozen_modules/io.h
+
+Python/frozen_modules/_collections_abc.h: Lib/_collections_abc.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) _collections_abc $(srcdir)/Lib/_collections_abc.py Python/frozen_modules/_collections_abc.h
+
+Python/frozen_modules/_sitebuiltins.h: Lib/_sitebuiltins.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) _sitebuiltins $(srcdir)/Lib/_sitebuiltins.py Python/frozen_modules/_sitebuiltins.h
+
+Python/frozen_modules/genericpath.h: Lib/genericpath.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) genericpath $(srcdir)/Lib/genericpath.py Python/frozen_modules/genericpath.h
+
+Python/frozen_modules/ntpath.h: Lib/ntpath.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) ntpath $(srcdir)/Lib/ntpath.py Python/frozen_modules/ntpath.h
+
+Python/frozen_modules/posixpath.h: Lib/posixpath.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) posixpath $(srcdir)/Lib/posixpath.py Python/frozen_modules/posixpath.h
+
+Python/frozen_modules/os.h: Lib/os.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) os $(srcdir)/Lib/os.py Python/frozen_modules/os.h
+
+Python/frozen_modules/site.h: Lib/site.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) site $(srcdir)/Lib/site.py Python/frozen_modules/site.h
+
+Python/frozen_modules/stat.h: Lib/stat.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) stat $(srcdir)/Lib/stat.py Python/frozen_modules/stat.h
+
+Python/frozen_modules/importlib.util.h: Lib/importlib/util.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) importlib.util $(srcdir)/Lib/importlib/util.py Python/frozen_modules/importlib.util.h
+
+Python/frozen_modules/importlib.machinery.h: Lib/importlib/machinery.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) importlib.machinery $(srcdir)/Lib/importlib/machinery.py Python/frozen_modules/importlib.machinery.h
+
+Python/frozen_modules/runpy.h: Lib/runpy.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) runpy $(srcdir)/Lib/runpy.py Python/frozen_modules/runpy.h
+
+Python/frozen_modules/__hello__.h: Lib/__hello__.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) __hello__ $(srcdir)/Lib/__hello__.py Python/frozen_modules/__hello__.h
+
+Python/frozen_modules/__phello__.h: Lib/__phello__/__init__.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) __phello__ $(srcdir)/Lib/__phello__/__init__.py Python/frozen_modules/__phello__.h
+
+Python/frozen_modules/__phello__.ham.h: Lib/__phello__/ham/__init__.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) __phello__.ham $(srcdir)/Lib/__phello__/ham/__init__.py Python/frozen_modules/__phello__.ham.h
+
+Python/frozen_modules/__phello__.ham.eggs.h: Lib/__phello__/ham/eggs.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) __phello__.ham.eggs $(srcdir)/Lib/__phello__/ham/eggs.py Python/frozen_modules/__phello__.ham.eggs.h
+
+Python/frozen_modules/__phello__.spam.h: Lib/__phello__/spam.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) __phello__.spam $(srcdir)/Lib/__phello__/spam.py Python/frozen_modules/__phello__.spam.h
+
+Python/frozen_modules/frozen_only.h: Tools/freeze/flag.py $(FREEZE_MODULE_DEPS)
+	$(FREEZE_MODULE) frozen_only $(srcdir)/Tools/freeze/flag.py Python/frozen_modules/frozen_only.h
+
+# END: freezing modules
+
+Tools/build/freeze_modules.py: $(FREEZE_MODULE)
+
+.PHONY: regen-frozen
+regen-frozen: Tools/build/freeze_modules.py $(FROZEN_FILES_IN)
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/freeze_modules.py --frozen-modules
+	@echo "The Makefile was updated, you may need to re-run make."
+
+# We keep this renamed target around for folks with muscle memory.
+.PHONY: regen-importlib
+regen-importlib: regen-frozen
+
+############################################################################
+# Global objects
+
+# Dependencies which can add and/or remove _Py_ID() identifiers:
+# - "make clinic"
+.PHONY: regen-global-objects
+regen-global-objects: $(srcdir)/Tools/build/generate_global_objects.py clinic
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_global_objects.py
+
+############################################################################
+# ABI
+
+.PHONY: regen-abidump
+regen-abidump: all
+	@$(MKDIR_P) $(srcdir)/Doc/data/
+	abidw "libpython$(LDVERSION).so" --no-architecture --out-file $(srcdir)/Doc/data/python$(LDVERSION).abi.new
+	@$(UPDATE_FILE) --create $(srcdir)/Doc/data/python$(LDVERSION).abi $(srcdir)/Doc/data/python$(LDVERSION).abi.new
+
+.PHONY: check-abidump
+check-abidump: all
+	abidiff $(srcdir)/Doc/data/python$(LDVERSION).abi "libpython$(LDVERSION).so" --drop-private-types --no-architecture --no-added-syms
+
+.PHONY: regen-limited-abi
+regen-limited-abi: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/build/stable_abi.py --generate-all $(srcdir)/Misc/stable_abi.toml
+
+############################################################################
+# Regenerate Unicode Data
+
+.PHONY: regen-unicodedata
+regen-unicodedata:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/unicode/makeunicodedata.py
+
+
+############################################################################
+# Regenerate all generated files
+
+# "clinic" is regenerated implicitly via "regen-global-objects".
+.PHONY: regen-all
+regen-all: regen-cases regen-typeslots \
+	regen-token regen-ast regen-keyword regen-sre regen-frozen \
+	regen-pegen-metaparser regen-pegen regen-test-frozenmain \
+	regen-test-levenshtein regen-global-objects
+	@echo
+	@echo "Note: make regen-stdlib-module-names, make regen-limited-abi, "
+	@echo "make regen-configure, make regen-sbom, and make regen-unicodedata should be run manually"
+
+############################################################################
+# Special rules for object files
+
+Modules/getbuildinfo.o: $(PARSER_OBJS) \
+		$(OBJECT_OBJS) \
+		$(PYTHON_OBJS) \
+		$(MODULE_OBJS) \
+		$(MODOBJS) \
+		$(DTRACE_OBJS) \
+		$(srcdir)/Modules/getbuildinfo.c
+	$(CC) -c $(PY_CORE_CFLAGS) \
+	      -DGITVERSION="\"`LC_ALL=C $(GITVERSION)`\"" \
+	      -DGITTAG="\"`LC_ALL=C $(GITTAG)`\"" \
+	      -DGITBRANCH="\"`LC_ALL=C $(GITBRANCH)`\"" \
+	      -o $@ $(srcdir)/Modules/getbuildinfo.c
+
+Modules/getpath.o: $(srcdir)/Modules/getpath.c Python/frozen_modules/getpath.h Makefile $(PYTHON_HEADERS)
+	$(CC) -c $(PY_CORE_CFLAGS) -DPYTHONPATH='"$(PYTHONPATH)"' \
+		-DPREFIX='"$(prefix)"' \
+		-DEXEC_PREFIX='"$(exec_prefix)"' \
+		-DVERSION='"$(VERSION)"' \
+		-DVPATH='"$(VPATH)"' \
+		-DPLATLIBDIR='"$(PLATLIBDIR)"' \
+		-DPYTHONFRAMEWORK='"$(PYTHONFRAMEWORK)"' \
+		-o $@ $(srcdir)/Modules/getpath.c
+
+Programs/python.o: $(srcdir)/Programs/python.c
+	$(CC) -c $(PY_CORE_CFLAGS) -o $@ $(srcdir)/Programs/python.c
+
+Programs/_testembed.o: $(srcdir)/Programs/_testembed.c Programs/test_frozenmain.h $(PYTHON_HEADERS)
+	$(CC) -c $(PY_CORE_CFLAGS) -o $@ $(srcdir)/Programs/_testembed.c
+
+Modules/_sre/sre.o: $(srcdir)/Modules/_sre/sre.c $(srcdir)/Modules/_sre/sre.h $(srcdir)/Modules/_sre/sre_constants.h $(srcdir)/Modules/_sre/sre_lib.h
+
+Modules/posixmodule.o: $(srcdir)/Modules/posixmodule.c $(srcdir)/Modules/posixmodule.h
+
+Modules/grpmodule.o: $(srcdir)/Modules/grpmodule.c $(srcdir)/Modules/posixmodule.h
+
+Modules/pwdmodule.o: $(srcdir)/Modules/pwdmodule.c $(srcdir)/Modules/posixmodule.h
+
+Modules/signalmodule.o: $(srcdir)/Modules/signalmodule.c $(srcdir)/Modules/posixmodule.h
+
+Modules/_interpretersmodule.o: $(srcdir)/Modules/_interpretersmodule.c $(srcdir)/Modules/_interpreters_common.h
+
+Modules/_interpqueuesmodule.o: $(srcdir)/Modules/_interpqueuesmodule.c $(srcdir)/Modules/_interpreters_common.h
+
+Modules/_interpchannelsmodule.o: $(srcdir)/Modules/_interpchannelsmodule.c $(srcdir)/Modules/_interpreters_common.h
+
+Python/crossinterp.o: $(srcdir)/Python/crossinterp.c $(srcdir)/Python/crossinterp_data_lookup.h $(srcdir)/Python/crossinterp_exceptions.h
+
+Python/initconfig.o: $(srcdir)/Python/initconfig.c $(srcdir)/Python/config_common.h
+
+Python/interpconfig.o: $(srcdir)/Python/interpconfig.c $(srcdir)/Python/config_common.h
+
+Python/dynload_shlib.o: $(srcdir)/Python/dynload_shlib.c Makefile
+	$(CC) -c $(PY_CORE_CFLAGS) \
+		$(if $(MULTIARCH),-DMULTIARCH='"$(MULTIARCH)"') \
+		-DSOABI='"$(SOABI)"' \
+		$(MULTIARCH_CPPFLAGS) \
+		-o $@ $(srcdir)/Python/dynload_shlib.c
+
+Python/dynload_hpux.o: $(srcdir)/Python/dynload_hpux.c Makefile
+	$(CC) -c $(PY_CORE_CFLAGS) \
+		-DSHLIB_EXT='"$(EXT_SUFFIX)"' \
+		-o $@ $(srcdir)/Python/dynload_hpux.c
+
+Python/sysmodule.o: $(srcdir)/Python/sysmodule.c Makefile $(srcdir)/Include/pydtrace.h
+	$(CC) -c $(PY_CORE_CFLAGS) \
+		-DABIFLAGS='"$(ABIFLAGS)"' \
+		$(MULTIARCH_CPPFLAGS) \
+		-o $@ $(srcdir)/Python/sysmodule.c
+
+$(IO_OBJS): $(IO_H)
+
+.PHONY: regen-pegen-metaparser
+regen-pegen-metaparser:
+	@$(MKDIR_P) $(srcdir)/Tools/peg_generator/pegen
+	PYTHONPATH=$(srcdir)/Tools/peg_generator $(PYTHON_FOR_REGEN) -m pegen -q python \
+	$(srcdir)/Tools/peg_generator/pegen/metagrammar.gram \
+	-o $(srcdir)/Tools/peg_generator/pegen/grammar_parser.py.new
+	$(UPDATE_FILE) $(srcdir)/Tools/peg_generator/pegen/grammar_parser.py \
+	$(srcdir)/Tools/peg_generator/pegen/grammar_parser.py.new
+
+.PHONY: regen-pegen
+regen-pegen:
+	@$(MKDIR_P) $(srcdir)/Parser
+	@$(MKDIR_P) $(srcdir)/Parser/tokenizer
+	@$(MKDIR_P) $(srcdir)/Parser/lexer
+	PYTHONPATH=$(srcdir)/Tools/peg_generator $(PYTHON_FOR_REGEN) -m pegen -q c \
+		$(srcdir)/Grammar/python.gram \
+		$(srcdir)/Grammar/Tokens \
+		-o $(srcdir)/Parser/parser.c.new
+	$(UPDATE_FILE) $(srcdir)/Parser/parser.c $(srcdir)/Parser/parser.c.new
+
+.PHONY: regen-ast
+regen-ast:
+	# Regenerate 3 files using Parser/asdl_c.py:
+	# - Include/internal/pycore_ast.h
+	# - Include/internal/pycore_ast_state.h
+	# - Python/Python-ast.c
+	$(MKDIR_P) $(srcdir)/Include
+	$(MKDIR_P) $(srcdir)/Python
+	$(PYTHON_FOR_REGEN) $(srcdir)/Parser/asdl_c.py \
+		$(srcdir)/Parser/Python.asdl \
+		-H $(srcdir)/Include/internal/pycore_ast.h.new \
+		-I $(srcdir)/Include/internal/pycore_ast_state.h.new \
+		-C $(srcdir)/Python/Python-ast.c.new
+
+	$(UPDATE_FILE) $(srcdir)/Include/internal/pycore_ast.h $(srcdir)/Include/internal/pycore_ast.h.new
+	$(UPDATE_FILE) $(srcdir)/Include/internal/pycore_ast_state.h $(srcdir)/Include/internal/pycore_ast_state.h.new
+	$(UPDATE_FILE) $(srcdir)/Python/Python-ast.c $(srcdir)/Python/Python-ast.c.new
+
+.PHONY: regen-token
+regen-token:
+	# Regenerate Doc/library/token-list.inc from Grammar/Tokens
+	# using Tools/build/generate_token.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_token.py rst \
+		$(srcdir)/Grammar/Tokens \
+		$(srcdir)/Doc/library/token-list.inc \
+		$(srcdir)/Doc/library/token.rst
+	# Regenerate Include/internal/pycore_token.h from Grammar/Tokens
+	# using Tools/build/generate_token.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_token.py h \
+		$(srcdir)/Grammar/Tokens \
+		$(srcdir)/Include/internal/pycore_token.h
+	# Regenerate Parser/token.c from Grammar/Tokens
+	# using Tools/build/generate_token.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_token.py c \
+		$(srcdir)/Grammar/Tokens \
+		$(srcdir)/Parser/token.c
+	# Regenerate Lib/token.py from Grammar/Tokens
+	# using Tools/build/generate_token.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_token.py py \
+		$(srcdir)/Grammar/Tokens \
+		$(srcdir)/Lib/token.py
+
+.PHONY: regen-keyword
+regen-keyword:
+	# Regenerate Lib/keyword.py from Grammar/python.gram and Grammar/Tokens
+	# using Tools/peg_generator/pegen
+	PYTHONPATH=$(srcdir)/Tools/peg_generator $(PYTHON_FOR_REGEN) -m pegen.keywordgen \
+		$(srcdir)/Grammar/python.gram \
+		$(srcdir)/Grammar/Tokens \
+		$(srcdir)/Lib/keyword.py.new
+	$(UPDATE_FILE) $(srcdir)/Lib/keyword.py $(srcdir)/Lib/keyword.py.new
+
+.PHONY: regen-stdlib-module-names
+regen-stdlib-module-names: all Programs/_testembed
+	# Regenerate Python/stdlib_module_names.h
+	# using Tools/build/generate_stdlib_module_names.py
+	$(RUNSHARED) ./$(BUILDPYTHON) \
+		$(srcdir)/Tools/build/generate_stdlib_module_names.py \
+		> $(srcdir)/Python/stdlib_module_names.h.new
+	$(UPDATE_FILE) $(srcdir)/Python/stdlib_module_names.h $(srcdir)/Python/stdlib_module_names.h.new
+
+.PHONY: regen-sre
+regen-sre:
+	# Regenerate Modules/_sre/sre_constants.h and Modules/_sre/sre_targets.h
+	# from Lib/re/_constants.py using Tools/build/generate_sre_constants.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_sre_constants.py \
+		$(srcdir)/Lib/re/_constants.py \
+		$(srcdir)/Modules/_sre/sre_constants.h \
+		$(srcdir)/Modules/_sre/sre_targets.h
+
+Python/compile.o Python/symtable.o Python/ast_unparse.o Python/ast.o Python/future.o: $(srcdir)/Include/internal/pycore_ast.h $(srcdir)/Include/internal/pycore_ast.h
+
+Python/getplatform.o: $(srcdir)/Python/getplatform.c
+		$(CC) -c $(PY_CORE_CFLAGS) -DPLATFORM='"$(MACHDEP)"' -o $@ $(srcdir)/Python/getplatform.c
+
+Python/importdl.o: $(srcdir)/Python/importdl.c
+		$(CC) -c $(PY_CORE_CFLAGS) -I$(DLINCLDIR) -o $@ $(srcdir)/Python/importdl.c
+
+Objects/unicodectype.o:	$(srcdir)/Objects/unicodectype.c \
+				$(srcdir)/Objects/unicodetype_db.h
+
+BYTESTR_DEPS = \
+		$(srcdir)/Objects/stringlib/count.h \
+		$(srcdir)/Objects/stringlib/ctype.h \
+		$(srcdir)/Objects/stringlib/fastsearch.h \
+		$(srcdir)/Objects/stringlib/find.h \
+		$(srcdir)/Objects/stringlib/join.h \
+		$(srcdir)/Objects/stringlib/partition.h \
+		$(srcdir)/Objects/stringlib/split.h \
+		$(srcdir)/Objects/stringlib/stringdefs.h \
+		$(srcdir)/Objects/stringlib/transmogrify.h
+
+UNICODE_DEPS = \
+		$(srcdir)/Objects/stringlib/asciilib.h \
+		$(srcdir)/Objects/stringlib/codecs.h \
+		$(srcdir)/Objects/stringlib/count.h \
+		$(srcdir)/Objects/stringlib/fastsearch.h \
+		$(srcdir)/Objects/stringlib/find.h \
+		$(srcdir)/Objects/stringlib/find_max_char.h \
+		$(srcdir)/Objects/stringlib/localeutil.h \
+		$(srcdir)/Objects/stringlib/partition.h \
+		$(srcdir)/Objects/stringlib/replace.h \
+		$(srcdir)/Objects/stringlib/split.h \
+		$(srcdir)/Objects/stringlib/ucs1lib.h \
+		$(srcdir)/Objects/stringlib/ucs2lib.h \
+		$(srcdir)/Objects/stringlib/ucs4lib.h \
+		$(srcdir)/Objects/stringlib/undef.h \
+		$(srcdir)/Objects/stringlib/unicode_format.h
+
+Objects/bytes_methods.o: $(srcdir)/Objects/bytes_methods.c $(BYTESTR_DEPS)
+Objects/bytesobject.o: $(srcdir)/Objects/bytesobject.c $(BYTESTR_DEPS)
+Objects/bytearrayobject.o: $(srcdir)/Objects/bytearrayobject.c $(BYTESTR_DEPS)
+
+Objects/unicodeobject.o: $(srcdir)/Objects/unicodeobject.c $(UNICODE_DEPS)
+
+Objects/dictobject.o: $(srcdir)/Objects/stringlib/eq.h
+Objects/setobject.o: $(srcdir)/Objects/stringlib/eq.h
+
+Objects/obmalloc.o: $(srcdir)/Objects/mimalloc/alloc.c \
+		$(srcdir)/Objects/mimalloc/alloc-aligned.c \
+		$(srcdir)/Objects/mimalloc/alloc-posix.c \
+		$(srcdir)/Objects/mimalloc/arena.c \
+		$(srcdir)/Objects/mimalloc/bitmap.c \
+		$(srcdir)/Objects/mimalloc/heap.c \
+		$(srcdir)/Objects/mimalloc/init.c \
+		$(srcdir)/Objects/mimalloc/options.c \
+		$(srcdir)/Objects/mimalloc/os.c \
+		$(srcdir)/Objects/mimalloc/page.c \
+		$(srcdir)/Objects/mimalloc/random.c \
+		$(srcdir)/Objects/mimalloc/segment.c \
+		$(srcdir)/Objects/mimalloc/segment-map.c \
+		$(srcdir)/Objects/mimalloc/stats.c \
+		$(srcdir)/Objects/mimalloc/prim/prim.c \
+		$(srcdir)/Objects/mimalloc/prim/osx/prim.c \
+		$(srcdir)/Objects/mimalloc/prim/unix/prim.c \
+		$(srcdir)/Objects/mimalloc/prim/wasi/prim.c
+
+Objects/mimalloc/page.o: $(srcdir)/Objects/mimalloc/page-queue.c
+
+
+# Regenerate various files from Python/bytecodes.c
+# Pass CASESFLAG=-l to insert #line directives in the output
+
+.PHONY: regen-cases
+regen-cases: \
+        regen-opcode-ids regen-opcode-targets regen-uop-ids regen-opcode-metadata-py \
+		regen-generated-cases regen-executor-cases regen-optimizer-cases \
+		regen-opcode-metadata regen-uop-metadata
+
+.PHONY: regen-opcode-ids
+regen-opcode-ids:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/opcode_id_generator.py \
+	    -o $(srcdir)/Include/opcode_ids.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Include/opcode_ids.h $(srcdir)/Include/opcode_ids.h.new
+
+.PHONY: regen-opcode-targets
+regen-opcode-targets:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/target_generator.py \
+	    -o $(srcdir)/Python/opcode_targets.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Python/opcode_targets.h $(srcdir)/Python/opcode_targets.h.new
+
+.PHONY: regen-uop-ids
+regen-uop-ids:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/uop_id_generator.py \
+	    -o $(srcdir)/Include/internal/pycore_uop_ids.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Include/internal/pycore_uop_ids.h $(srcdir)/Include/internal/pycore_uop_ids.h.new
+
+.PHONY: regen-opcode-metadata-py
+regen-opcode-metadata-py:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/py_metadata_generator.py \
+	    -o $(srcdir)/Lib/_opcode_metadata.py.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Lib/_opcode_metadata.py $(srcdir)/Lib/_opcode_metadata.py.new
+
+.PHONY: regen-generated-cases
+regen-generated-cases:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/tier1_generator.py \
+	    -o $(srcdir)/Python/generated_cases.c.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Python/generated_cases.c.h $(srcdir)/Python/generated_cases.c.h.new
+
+.PHONY: regen-executor-cases
+regen-executor-cases:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/tier2_generator.py \
+	    -o $(srcdir)/Python/executor_cases.c.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Python/executor_cases.c.h $(srcdir)/Python/executor_cases.c.h.new
+
+.PHONY: regen-optimizer-cases
+regen-optimizer-cases:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/optimizer_generator.py \
+	    -o $(srcdir)/Python/optimizer_cases.c.h.new \
+	    $(srcdir)/Python/optimizer_bytecodes.c \
+	    $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Python/optimizer_cases.c.h $(srcdir)/Python/optimizer_cases.c.h.new
+
+.PHONY: regen-opcode-metadata
+regen-opcode-metadata:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/opcode_metadata_generator.py \
+	    -o $(srcdir)/Include/internal/pycore_opcode_metadata.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Include/internal/pycore_opcode_metadata.h $(srcdir)/Include/internal/pycore_opcode_metadata.h.new
+
+.PHONY: regen-uop-metadata
+regen-uop-metadata:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/cases_generator/uop_metadata_generator.py -o \
+	    $(srcdir)/Include/internal/pycore_uop_metadata.h.new $(srcdir)/Python/bytecodes.c
+	$(UPDATE_FILE) $(srcdir)/Include/internal/pycore_uop_metadata.h $(srcdir)/Include/internal/pycore_uop_metadata.h.new
+
+Python/compile.o Python/assemble.o Python/flowgraph.o Python/instruction_sequence.o: \
+                $(srcdir)/Include/internal/pycore_compile.h \
+                $(srcdir)/Include/internal/pycore_flowgraph.h \
+                $(srcdir)/Include/internal/pycore_instruction_sequence.h \
+                $(srcdir)/Include/internal/pycore_opcode_metadata.h \
+                $(srcdir)/Include/internal/pycore_opcode_utils.h
+
+Python/ceval.o: \
+		$(srcdir)/Python/ceval_macros.h \
+		$(srcdir)/Python/condvar.h \
+		$(srcdir)/Python/generated_cases.c.h \
+		$(srcdir)/Python/executor_cases.c.h \
+		$(srcdir)/Python/opcode_targets.h
+
+Python/flowgraph.o: \
+		$(srcdir)/Include/internal/pycore_opcode_metadata.h
+
+Python/optimizer.o: \
+		$(srcdir)/Python/executor_cases.c.h \
+		$(srcdir)/Include/internal/pycore_opcode_metadata.h \
+		$(srcdir)/Include/internal/pycore_optimizer.h
+
+Python/optimizer_analysis.o: \
+		$(srcdir)/Include/internal/pycore_opcode_metadata.h \
+		$(srcdir)/Include/internal/pycore_optimizer.h \
+		$(srcdir)/Python/optimizer_cases.c.h
+
+Python/frozen.o: $(FROZEN_FILES_OUT)
+
+# Generate DTrace probe macros, then rename them (PYTHON_ -> PyDTrace_) to
+# follow our naming conventions. dtrace(1) uses the output filename to generate
+# an include guard, so we can't use a pipeline to transform its output.
+Include/pydtrace_probes.h: $(srcdir)/Include/pydtrace.d
+	$(MKDIR_P) Include
+	CC="$(CC)" CFLAGS="$(CFLAGS)" $(DTRACE) $(DFLAGS) -o $@ -h -s $(srcdir)/Include/pydtrace.d
+	: sed in-place edit with POSIX-only tools
+	sed 's/PYTHON_/PyDTrace_/' $@ > $@.tmp
+	mv $@.tmp $@
+
+Python/ceval.o: $(srcdir)/Include/pydtrace.h
+Python/gc.o: $(srcdir)/Include/pydtrace.h
+Python/import.o: $(srcdir)/Include/pydtrace.h
+
+Python/pydtrace.o: $(srcdir)/Include/pydtrace.d $(DTRACE_DEPS)
+	CC="$(CC)" CFLAGS="$(CFLAGS)" $(DTRACE) $(DFLAGS) -o $@ -G -s $(srcdir)/Include/pydtrace.d $(DTRACE_DEPS)
+
+Objects/typeobject.o: Objects/typeslots.inc
+
+.PHONY: regen-typeslots
+regen-typeslots:
+	# Regenerate Objects/typeslots.inc from Include/typeslotsh
+	# using Objects/typeslots.py
+	$(PYTHON_FOR_REGEN) $(srcdir)/Objects/typeslots.py \
+		< $(srcdir)/Include/typeslots.h \
+		$(srcdir)/Objects/typeslots.inc.new
+	$(UPDATE_FILE) $(srcdir)/Objects/typeslots.inc $(srcdir)/Objects/typeslots.inc.new
+
+$(LIBRARY_OBJS) $(MODOBJS) Programs/python.o: $(PYTHON_HEADERS)
+
+
+######################################################################
+
+TESTOPTS=	$(EXTRATESTOPTS)
+TESTPYTHON=	$(RUNSHARED) $(PYTHON_FOR_BUILD) $(TESTPYTHONOPTS)
+TESTRUNNER=	$(TESTPYTHON) -m test
+TESTTIMEOUT=
+
+# Remove "test_python_*" directories of previous failed test jobs.
+# Pass TESTOPTS options because it can contain --tempdir option.
+.PHONY: cleantest
+cleantest: all
+	$(TESTRUNNER) $(TESTOPTS) --cleanup
+
+# Run a basic set of regression tests.
+# This excludes some tests that are particularly resource-intensive.
+# Similar to buildbottest, but use --fast-ci option, instead of --slow-ci.
+.PHONY: test
+test: all
+	$(TESTRUNNER) --fast-ci --timeout=$(TESTTIMEOUT) $(TESTOPTS)
+
+# Run the test suite for both architectures in a Universal build on OSX.
+# Must be run on an Intel box.
+.PHONY: testuniversal
+testuniversal: all
+	@if [ `arch` != 'i386' ]; then \
+		echo "This can only be used on OSX/i386" ;\
+		exit 1 ;\
+	fi
+	$(TESTRUNNER) --slow-ci --timeout=$(TESTTIMEOUT) $(TESTOPTS)
+	$(RUNSHARED) /usr/libexec/oah/translate \
+		./$(BUILDPYTHON) -E -m test -j 0 -u all $(TESTOPTS)
+
+# Run the test suite on the iOS simulator. Must be run on a macOS machine with
+# a full Xcode install that has an iPhone SE (3rd edition) simulator available.
+# This must be run *after* a `make install` has completed the build. The
+# `--with-framework-name` argument *cannot* be used when configuring the build.
+XCFOLDER:=iOSTestbed.$(MULTIARCH).$(shell date +%s).$$PPID
+.PHONY: testios
+testios:
+	@if test "$(MACHDEP)" != "ios"; then \
+		echo "Cannot run the iOS testbed for a non-iOS build."; \
+		exit 1;\
+	fi
+	@if test "$(findstring -iphonesimulator,$(MULTIARCH))" != "-iphonesimulator"; then \
+		echo "Cannot run the iOS testbed for non-simulator builds."; \
+		exit 1;\
+	fi
+	@if test $(PYTHONFRAMEWORK) != "Python"; then \
+		echo "Cannot run the iOS testbed with a non-default framework name."; \
+		exit 1;\
+	fi
+	@if ! test -d $(PYTHONFRAMEWORKPREFIX); then \
+		echo "Cannot find a finalized iOS Python.framework. Have you run 'make install' to finalize the framework build?"; \
+		exit 1;\
+	fi
+
+	# Clone the testbed project into the XCFOLDER
+	$(PYTHON_FOR_BUILD) $(srcdir)/iOS/testbed clone --framework $(PYTHONFRAMEWORKPREFIX) "$(XCFOLDER)"
+
+	# Run the testbed project
+	$(PYTHON_FOR_BUILD) "$(XCFOLDER)" run --verbose -- test -uall --single-process --rerun -W
+
+# Like test, but using --slow-ci which enables all test resources and use
+# longer timeout. Run an optional pybuildbot.identify script to include
+# information about the build environment.
+.PHONY: buildbottest
+buildbottest: all
+	-@if which pybuildbot.identify >/dev/null 2>&1; then \
+		pybuildbot.identify "CC='$(CC)'" "CXX='$(CXX)'"; \
+	fi
+	$(TESTRUNNER) --slow-ci --timeout=$(TESTTIMEOUT) $(TESTOPTS)
+
+.PHONY: pythoninfo
+pythoninfo: all
+		$(RUNSHARED) $(HOSTRUNNER) ./$(BUILDPYTHON) -m test.pythoninfo
+
+QUICKTESTOPTS=	-x test_subprocess test_io \
+		test_multibytecodec test_urllib2_localnet test_itertools \
+		test_multiprocessing_fork test_multiprocessing_spawn \
+		test_multiprocessing_forkserver \
+		test_mailbox test_socket test_poll \
+		test_select test_zipfile test_concurrent_futures
+
+.PHONY: quicktest
+quicktest: all
+	$(TESTRUNNER) --fast-ci --timeout=$(TESTTIMEOUT) $(TESTOPTS) $(QUICKTESTOPTS)
+
+# SSL tests
+.PHONY: multisslcompile
+multisslcompile: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/ssl/multissltests.py --steps=modules
+
+.PHONY: multissltest
+multissltest: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/ssl/multissltests.py
+
+# All install targets use the "all" target as synchronization point to
+# prevent race conditions with PGO builds. PGO builds use recursive make,
+# which can lead to two parallel `./python setup.py build` processes that
+# step on each others toes.
+.PHONY: install
+install:  commoninstall bininstall maninstall 
+	if test "x$(ENSUREPIP)" != "xno"  ; then \
+		case $(ENSUREPIP) in \
+			upgrade) ensurepip="--upgrade" ;; \
+			install|*) ensurepip="" ;; \
+		esac; \
+		$(RUNSHARED) $(PYTHON_FOR_BUILD) -m ensurepip \
+			$$ensurepip --root=$(DESTDIR)/ ; \
+	fi
+
+.PHONY: altinstall
+altinstall: commoninstall
+	if test "x$(ENSUREPIP)" != "xno"  ; then \
+		case $(ENSUREPIP) in \
+			upgrade) ensurepip="--altinstall --upgrade" ;; \
+			install|*) ensurepip="--altinstall" ;; \
+		esac; \
+		$(RUNSHARED) $(PYTHON_FOR_BUILD) -m ensurepip \
+			$$ensurepip --root=$(DESTDIR)/ ; \
+	fi
+
+.PHONY: commoninstall
+commoninstall:  check-clean-src  \
+		altbininstall libinstall inclinstall libainstall \
+		sharedinstall altmaninstall 
+
+# Install shared libraries enabled by Setup
+DESTDIRS=	$(exec_prefix) $(LIBDIR) $(BINLIBDEST) $(DESTSHARED)
+
+.PHONY: sharedinstall
+sharedinstall: all
+		@for i in $(DESTDIRS); \
+		do \
+			if test ! -d $(DESTDIR)$$i; then \
+				echo "Creating directory $$i"; \
+				$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+			else    true; \
+			fi; \
+		done
+		@for i in X $(SHAREDMODS); do \
+		  if test $$i != X; then \
+		    echo $(INSTALL_SHARED) $$i $(DESTSHARED)/`basename $$i`; \
+		    $(INSTALL_SHARED) $$i $(DESTDIR)$(DESTSHARED)/`basename $$i`; \
+			if test -d "$$i.dSYM"; then \
+				echo $(DSYMUTIL_PATH) $(DESTDIR)$(DESTSHARED)/`basename $$i`; \
+				$(DSYMUTIL_PATH) $(DESTDIR)$(DESTSHARED)/`basename $$i`; \
+			fi; \
+		  fi; \
+		done
+
+# Install the interpreter with $(VERSION) affixed
+# This goes into $(exec_prefix)
+.PHONY: altbininstall
+altbininstall: $(BUILDPYTHON) 
+	@for i in $(BINDIR) $(LIBDIR); \
+	do \
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	if test "$(PYTHONFRAMEWORKDIR)" = "no-framework" ; then \
+		$(INSTALL_PROGRAM) $(BUILDPYTHON) $(DESTDIR)$(BINDIR)/python$(LDVERSION)$(EXE); \
+	else \
+		$(INSTALL_PROGRAM) $(STRIPFLAG) Mac/pythonw $(DESTDIR)$(BINDIR)/python$(LDVERSION)$(EXE); \
+	fi
+	-if test "$(VERSION)" != "$(LDVERSION)"; then \
+		if test -f $(DESTDIR)$(BINDIR)/python$(VERSION)$(EXE) -o -h $(DESTDIR)$(BINDIR)/python$(VERSION)$(EXE); \
+		then rm -f $(DESTDIR)$(BINDIR)/python$(VERSION)$(EXE); \
+		fi; \
+		(cd $(DESTDIR)$(BINDIR); $(LN) python$(LDVERSION)$(EXE) python$(VERSION)$(EXE)); \
+	fi
+	@if test "$(PY_ENABLE_SHARED)" = 1 -o "$(STATIC_LIBPYTHON)" = 1; then \
+		if test -f $(LDLIBRARY) && test "$(PYTHONFRAMEWORKDIR)" = "no-framework" ; then \
+			if test -n "$(DLLLIBRARY)" ; then \
+				$(INSTALL_SHARED) $(DLLLIBRARY) $(DESTDIR)$(BINDIR); \
+			else \
+				$(INSTALL_SHARED) $(LDLIBRARY) $(DESTDIR)$(LIBDIR)/$(INSTSONAME); \
+				if test $(LDLIBRARY) != $(INSTSONAME); then \
+					(cd $(DESTDIR)$(LIBDIR); $(LN) -sf $(INSTSONAME) $(LDLIBRARY)) \
+				fi \
+			fi; \
+			if test -n "$(PY3LIBRARY)"; then \
+				$(INSTALL_SHARED) $(PY3LIBRARY) $(DESTDIR)$(LIBDIR)/$(PY3LIBRARY); \
+			fi; \
+		else	true; \
+		fi; \
+	fi
+	if test "x$(LIPO_32BIT_FLAGS)" != "x" ; then \
+		rm -f $(DESTDIR)$(BINDIR)/python$(VERSION)-32$(EXE); \
+		lipo $(LIPO_32BIT_FLAGS) \
+			-output $(DESTDIR)$(BINDIR)/python$(VERSION)-32$(EXE) \
+			$(DESTDIR)$(BINDIR)/python$(VERSION)$(EXE); \
+	fi
+	if test "x$(LIPO_INTEL64_FLAGS)" != "x" ; then \
+		rm -f $(DESTDIR)$(BINDIR)/python$(VERSION)-intel64$(EXE); \
+		lipo $(LIPO_INTEL64_FLAGS) \
+			-output $(DESTDIR)$(BINDIR)/python$(VERSION)-intel64$(EXE) \
+			$(DESTDIR)$(BINDIR)/python$(VERSION)$(EXE); \
+	fi
+	# Install macOS debug information (if available)
+	if test -d "$(BUILDPYTHON).dSYM"; then \
+		echo $(DSYMUTIL_PATH) $(DESTDIR)$(BINDIR)/python$(LDVERSION)$(EXE); \
+		$(DSYMUTIL_PATH) $(DESTDIR)$(BINDIR)/python$(LDVERSION)$(EXE); \
+	fi
+	if test "$(PYTHONFRAMEWORKDIR)" = "no-framework" ; then \
+		if test -d "$(LDLIBRARY).dSYM"; then \
+			echo $(DSYMUTIL_PATH) $(DESTDIR)$(LIBDIR)/$(INSTSONAME); \
+			$(DSYMUTIL_PATH) $(DESTDIR)$(LIBDIR)/$(INSTSONAME); \
+		fi \
+	else \
+		if test -d "$(LDLIBRARY).dSYM"; then \
+			echo $(DSYMUTIL_PATH) $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/$(INSTSONAME); \
+      $(DSYMUTIL_PATH) $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/$(INSTSONAME); \
+		fi \
+	fi
+
+.PHONY: bininstall
+# We depend on commoninstall here to make sure the installation is already usable
+# before we possibly overwrite the global 'python3' symlink to avoid causing
+# problems for anything else trying to run 'python3' while we install, particularly
+# if we're installing in parallel with -j.
+bininstall: commoninstall altbininstall
+	if test ! -d $(DESTDIR)$(LIBPC); then \
+		echo "Creating directory $(LIBPC)"; \
+		$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(LIBPC); \
+	fi
+	-if test -f $(DESTDIR)$(BINDIR)/python3$(EXE) -o -h $(DESTDIR)$(BINDIR)/python3$(EXE); \
+	then rm -f $(DESTDIR)$(BINDIR)/python3$(EXE); \
+	else true; \
+	fi
+	(cd $(DESTDIR)$(BINDIR); $(LN) -s python$(VERSION)$(EXE) python3$(EXE))
+	-if test "$(VERSION)" != "$(LDVERSION)"; then \
+		rm -f $(DESTDIR)$(BINDIR)/python$(VERSION)-config; \
+		(cd $(DESTDIR)$(BINDIR); $(LN) -s python$(LDVERSION)-config python$(VERSION)-config); \
+		rm -f $(DESTDIR)$(LIBPC)/python-$(VERSION).pc; \
+		(cd $(DESTDIR)$(LIBPC); $(LN) -s python-$(LDVERSION).pc python-$(VERSION).pc); \
+		rm -f $(DESTDIR)$(LIBPC)/python-$(VERSION)-embed.pc; \
+		(cd $(DESTDIR)$(LIBPC); $(LN) -s python-$(LDVERSION)-embed.pc python-$(VERSION)-embed.pc); \
+	fi
+	-rm -f $(DESTDIR)$(BINDIR)/python3-config
+	(cd $(DESTDIR)$(BINDIR); $(LN) -s python$(VERSION)-config python3-config)
+	-rm -f $(DESTDIR)$(LIBPC)/python3.pc
+	(cd $(DESTDIR)$(LIBPC); $(LN) -s python-$(VERSION).pc python3.pc)
+	-rm -f $(DESTDIR)$(LIBPC)/python3-embed.pc
+	(cd $(DESTDIR)$(LIBPC); $(LN) -s python-$(VERSION)-embed.pc python3-embed.pc)
+	-rm -f $(DESTDIR)$(BINDIR)/idle3
+	(cd $(DESTDIR)$(BINDIR); $(LN) -s idle$(VERSION) idle3)
+	-rm -f $(DESTDIR)$(BINDIR)/pydoc3
+	(cd $(DESTDIR)$(BINDIR); $(LN) -s pydoc$(VERSION) pydoc3)
+	if test "x$(LIPO_32BIT_FLAGS)" != "x" ; then \
+		rm -f $(DESTDIR)$(BINDIR)/python3-32$(EXE); \
+		(cd $(DESTDIR)$(BINDIR); $(LN) -s python$(VERSION)-32$(EXE) python3-32$(EXE)) \
+	fi
+	if test "x$(LIPO_INTEL64_FLAGS)" != "x" ; then \
+		rm -f $(DESTDIR)$(BINDIR)/python3-intel64$(EXE); \
+		(cd $(DESTDIR)$(BINDIR); $(LN) -s python$(VERSION)-intel64$(EXE) python3-intel64$(EXE)) \
+	fi
+
+# Install the versioned manual page
+.PHONY: altmaninstall
+altmaninstall:
+	@for i in $(MANDIR) $(MANDIR)/man1; \
+	do \
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	$(INSTALL_DATA) $(srcdir)/Misc/python.man \
+		$(DESTDIR)$(MANDIR)/man1/python$(VERSION).1
+
+# Install the unversioned manual page
+.PHONY: maninstall
+maninstall:	altmaninstall
+	-rm -f $(DESTDIR)$(MANDIR)/man1/python3.1
+	(cd $(DESTDIR)$(MANDIR)/man1; $(LN) -s python$(VERSION).1 python3.1)
+
+# Install the library
+XMLLIBSUBDIRS=  xml xml/dom xml/etree xml/parsers xml/sax
+LIBSUBDIRS=	asyncio \
+		collections \
+		concurrent concurrent/futures \
+		csv \
+		ctypes ctypes/macholib \
+		curses \
+		dbm \
+		email email/mime \
+		encodings \
+		ensurepip ensurepip/_bundled \
+		html \
+		http \
+		idlelib idlelib/Icons \
+		importlib importlib/resources importlib/metadata \
+		json \
+		logging \
+		multiprocessing multiprocessing/dummy \
+		pathlib \
+		pydoc_data \
+		re \
+		site-packages \
+		sqlite3 \
+		sysconfig \
+		tkinter \
+		tomllib \
+		turtledemo \
+		unittest \
+		urllib \
+		venv venv/scripts venv/scripts/common venv/scripts/posix \
+		wsgiref \
+		$(XMLLIBSUBDIRS) \
+		xmlrpc \
+		zipfile zipfile/_path \
+		zoneinfo \
+		_pyrepl \
+		__phello__
+TESTSUBDIRS=	idlelib/idle_test \
+		test \
+		test/test_ast \
+		test/archivetestdata \
+		test/audiodata \
+		test/certdata \
+		test/certdata/capath \
+		test/cjkencodings \
+		test/configdata \
+		test/crashers \
+		test/data \
+		test/decimaltestdata \
+		test/dtracedata \
+		test/encoded_modules \
+		test/leakers \
+		test/libregrtest \
+		test/mathdata \
+		test/regrtestdata \
+		test/regrtestdata/import_from_tests \
+		test/regrtestdata/import_from_tests/test_regrtest_b \
+		test/subprocessdata \
+		test/support \
+		test/support/_hypothesis_stubs \
+		test/support/interpreters \
+		test/test_asyncio \
+		test/test_capi \
+		test/test_cext \
+		test/test_concurrent_futures \
+		test/test_cppext \
+		test/test_ctypes \
+		test/test_dataclasses \
+		test/test_doctest \
+		test/test_email \
+		test/test_email/data \
+		test/test_free_threading \
+		test/test_future_stmt \
+		test/test_gdb \
+		test/test_import \
+		test/test_import/data \
+		test/test_import/data/circular_imports \
+		test/test_import/data/circular_imports/subpkg \
+		test/test_import/data/circular_imports/subpkg2 \
+		test/test_import/data/circular_imports/subpkg2/parent \
+		test/test_import/data/package \
+		test/test_import/data/package2 \
+		test/test_import/data/package3 \
+		test/test_import/data/package4 \
+		test/test_import/data/unwritable \
+		test/test_importlib \
+		test/test_importlib/builtin \
+		test/test_importlib/extension \
+		test/test_importlib/frozen \
+		test/test_importlib/import_ \
+		test/test_importlib/metadata \
+		test/test_importlib/metadata/data \
+		test/test_importlib/metadata/data/sources \
+		test/test_importlib/metadata/data/sources/example \
+		test/test_importlib/metadata/data/sources/example/example \
+		test/test_importlib/metadata/data/sources/example2 \
+		test/test_importlib/metadata/data/sources/example2/example2 \
+		test/test_importlib/namespace_pkgs \
+		test/test_importlib/namespace_pkgs/both_portions \
+		test/test_importlib/namespace_pkgs/both_portions/foo \
+		test/test_importlib/namespace_pkgs/module_and_namespace_package \
+		test/test_importlib/namespace_pkgs/module_and_namespace_package/a_test \
+		test/test_importlib/namespace_pkgs/not_a_namespace_pkg \
+		test/test_importlib/namespace_pkgs/not_a_namespace_pkg/foo \
+		test/test_importlib/namespace_pkgs/portion1 \
+		test/test_importlib/namespace_pkgs/portion1/foo \
+		test/test_importlib/namespace_pkgs/portion2 \
+		test/test_importlib/namespace_pkgs/portion2/foo \
+		test/test_importlib/namespace_pkgs/project1 \
+		test/test_importlib/namespace_pkgs/project1/parent \
+		test/test_importlib/namespace_pkgs/project1/parent/child \
+		test/test_importlib/namespace_pkgs/project2 \
+		test/test_importlib/namespace_pkgs/project2/parent \
+		test/test_importlib/namespace_pkgs/project2/parent/child \
+		test/test_importlib/namespace_pkgs/project3 \
+		test/test_importlib/namespace_pkgs/project3/parent \
+		test/test_importlib/namespace_pkgs/project3/parent/child \
+		test/test_importlib/partial \
+		test/test_importlib/resources \
+		test/test_importlib/source \
+		test/test_inspect \
+		test/test_interpreters \
+		test/test_json \
+		test/test_module \
+		test/test_multiprocessing_fork \
+		test/test_multiprocessing_forkserver \
+		test/test_multiprocessing_spawn \
+		test/test_pathlib \
+		test/test_peg_generator \
+		test/test_pydoc \
+		test/test_pyrepl \
+		test/test_sqlite3 \
+		test/test_tkinter \
+		test/test_tomllib \
+		test/test_tomllib/data \
+		test/test_tomllib/data/invalid \
+		test/test_tomllib/data/invalid/array \
+		test/test_tomllib/data/invalid/array-of-tables \
+		test/test_tomllib/data/invalid/boolean \
+		test/test_tomllib/data/invalid/dates-and-times \
+		test/test_tomllib/data/invalid/dotted-keys \
+		test/test_tomllib/data/invalid/inline-table \
+		test/test_tomllib/data/invalid/keys-and-vals \
+		test/test_tomllib/data/invalid/literal-str \
+		test/test_tomllib/data/invalid/multiline-basic-str \
+		test/test_tomllib/data/invalid/multiline-literal-str \
+		test/test_tomllib/data/invalid/table \
+		test/test_tomllib/data/valid \
+		test/test_tomllib/data/valid/array \
+		test/test_tomllib/data/valid/dates-and-times \
+		test/test_tomllib/data/valid/multiline-basic-str \
+		test/test_tools \
+		test/test_tools/i18n_data \
+		test/test_tools/msgfmt_data \
+		test/test_ttk \
+		test/test_unittest \
+		test/test_unittest/testmock \
+		test/test_warnings \
+		test/test_warnings/data \
+		test/test_zipfile \
+		test/test_zipfile/_path \
+		test/test_zoneinfo \
+		test/test_zoneinfo/data \
+		test/tkinterdata \
+		test/tokenizedata \
+		test/tracedmodules \
+		test/translationdata \
+		test/translationdata/argparse \
+		test/translationdata/getopt \
+		test/translationdata/optparse \
+		test/typinganndata \
+		test/wheeldata \
+		test/xmltestdata \
+		test/xmltestdata/c14n-20 \
+		test/zipimport_data
+
+COMPILEALL_OPTS=-j0
+
+TEST_MODULES=yes
+
+.PHONY: libinstall
+libinstall:	all $(srcdir)/Modules/xxmodule.c
+	@for i in $(SCRIPTDIR) $(LIBDEST); \
+	do \
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	@if test "$(TEST_MODULES)" = yes; then \
+		subdirs="$(LIBSUBDIRS) $(TESTSUBDIRS)"; \
+	else \
+		subdirs="$(LIBSUBDIRS)"; \
+	fi; \
+	for d in $$subdirs; \
+	do \
+		a=$(srcdir)/Lib/$$d; \
+		if test ! -d $$a; then continue; else true; fi; \
+		b=$(LIBDEST)/$$d; \
+		if test ! -d $(DESTDIR)$$b; then \
+			echo "Creating directory $$b"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$b; \
+		else	true; \
+		fi; \
+	done
+	@for i in $(srcdir)/Lib/*.py; \
+	do \
+		if test -x $$i; then \
+			$(INSTALL_SCRIPT) $$i $(DESTDIR)$(LIBDEST); \
+			echo $(INSTALL_SCRIPT) $$i $(LIBDEST); \
+		else \
+			$(INSTALL_DATA) $$i $(DESTDIR)$(LIBDEST); \
+			echo $(INSTALL_DATA) $$i $(LIBDEST); \
+		fi; \
+	done
+	@if test "$(TEST_MODULES)" = yes; then \
+		subdirs="$(LIBSUBDIRS) $(TESTSUBDIRS)"; \
+	else \
+		subdirs="$(LIBSUBDIRS)"; \
+	fi; \
+	for d in $$subdirs; \
+	do \
+		a=$(srcdir)/Lib/$$d; \
+		if test ! -d $$a; then continue; else true; fi; \
+		if test `ls $$a | wc -l` -lt 1; then continue; fi; \
+		b=$(LIBDEST)/$$d; \
+		for i in $$a/*; \
+		do \
+			case $$i in \
+			*CVS) ;; \
+			*.py[co]) ;; \
+			*.orig) ;; \
+			*~) ;; \
+			*) \
+				if test -d $$i; then continue; fi; \
+				if test -x $$i; then \
+				    echo $(INSTALL_SCRIPT) $$i $$b; \
+				    $(INSTALL_SCRIPT) $$i $(DESTDIR)$$b; \
+				else \
+				    echo $(INSTALL_DATA) $$i $$b; \
+				    $(INSTALL_DATA) $$i $(DESTDIR)$$b; \
+				fi;; \
+			esac; \
+		done; \
+	done
+	$(INSTALL_DATA) `cat pybuilddir.txt`/_sysconfigdata_$(ABIFLAGS)_$(MACHDEP)_$(MULTIARCH).py \
+		$(DESTDIR)$(LIBDEST); \
+	$(INSTALL_DATA) $(srcdir)/LICENSE $(DESTDIR)$(LIBDEST)/LICENSE.txt
+	@ # If app store compliance has been configured, apply the patch to the
+	@ # installed library code. The patch has been previously validated against
+	@ # the original source tree, so we can ignore any errors that are raised
+	@ # due to files that are missing because of --disable-test-modules etc.
+	@if [ "$(APP_STORE_COMPLIANCE_PATCH)" != "" ]; then \
+		echo "Applying app store compliance patch"; \
+		patch --force --reject-file "$(abs_builddir)/app-store-compliance.rej" --strip 2 --directory "$(DESTDIR)$(LIBDEST)" --input "$(abs_srcdir)/$(APP_STORE_COMPLIANCE_PATCH)" || true ; \
+	fi
+	@ # Build PYC files for the 3 optimization levels (0, 1, 2)
+	-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
+		$(PYTHON_FOR_BUILD) -Wi $(DESTDIR)$(LIBDEST)/compileall.py \
+		-o 0 -o 1 -o 2 $(COMPILEALL_OPTS) -d $(LIBDEST) -f \
+		-x 'bad_coding|badsyntax|site-packages' \
+		$(DESTDIR)$(LIBDEST)
+	-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
+		$(PYTHON_FOR_BUILD) -Wi $(DESTDIR)$(LIBDEST)/compileall.py \
+		-o 0 -o 1 -o 2 $(COMPILEALL_OPTS) -d $(LIBDEST)/site-packages -f \
+		-x badsyntax $(DESTDIR)$(LIBDEST)/site-packages
+
+# bpo-21536: Misc/python-config.sh is generated in the build directory
+# from $(srcdir)Misc/python-config.sh.in.
+python-config: $(srcdir)/Misc/python-config.in Misc/python-config.sh
+	@ # Substitution happens here, as the completely-expanded BINDIR
+	@ # is not available in configure
+	sed -e "s,@EXENAME@,$(EXENAME)," < $(srcdir)/Misc/python-config.in >python-config.py
+	@ # Replace makefile compat. variable references with shell script compat. ones; $(VAR) -> ${VAR}
+	LC_ALL=C sed -e 's,\$$(\([A-Za-z0-9_]*\)),\$$\{\1\},g' < Misc/python-config.sh >python-config
+	@ # On Darwin, always use the python version of the script, the shell
+	@ # version doesn't use the compiler customizations that are provided
+	@ # in python (_osx_support.py).
+	@if test `uname -s` = Darwin; then \
+		cp python-config.py python-config; \
+	fi
+
+# macOS' make seems to ignore a dependency on a
+# "$(BUILD_SCRIPTS_DIR): $(MKDIR_P) $@" rule.
+BUILD_SCRIPTS_DIR=build/scripts-$(VERSION)
+SCRIPT_IDLE=$(BUILD_SCRIPTS_DIR)/idle$(VERSION)
+SCRIPT_PYDOC=$(BUILD_SCRIPTS_DIR)/pydoc$(VERSION)
+
+$(SCRIPT_IDLE): $(srcdir)/Tools/scripts/idle3
+	@$(MKDIR_P) $(BUILD_SCRIPTS_DIR)
+	sed -e "s,/usr/bin/env python3,$(EXENAME)," < $(srcdir)/Tools/scripts/idle3 > $@
+	@chmod +x $@
+
+$(SCRIPT_PYDOC): $(srcdir)/Tools/scripts/pydoc3
+	@$(MKDIR_P) $(BUILD_SCRIPTS_DIR)
+	sed -e "s,/usr/bin/env python3,$(EXENAME)," < $(srcdir)/Tools/scripts/pydoc3 > $@
+	@chmod +x $@
+
+.PHONY: scripts
+scripts: $(SCRIPT_IDLE) $(SCRIPT_PYDOC) python-config
+
+# Install the include files
+INCLDIRSTOMAKE=$(INCLUDEDIR) $(CONFINCLUDEDIR) $(INCLUDEPY) $(CONFINCLUDEPY)
+
+.PHONY: inclinstall
+inclinstall:
+	@for i in $(INCLDIRSTOMAKE); \
+	do \
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	@if test ! -d $(DESTDIR)$(INCLUDEPY)/cpython; then \
+		echo "Creating directory $(DESTDIR)$(INCLUDEPY)/cpython"; \
+		$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(INCLUDEPY)/cpython; \
+	else	true; \
+	fi
+	@if test ! -d $(DESTDIR)$(INCLUDEPY)/internal; then \
+		echo "Creating directory $(DESTDIR)$(INCLUDEPY)/internal"; \
+		$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(INCLUDEPY)/internal; \
+	else	true; \
+	fi
+	@if test "$(INSTALL_MIMALLOC)" = "yes"; then \
+		if test ! -d $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc; then \
+			echo "Creating directory $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc; \
+		fi; \
+	fi
+	@for i in $(srcdir)/Include/*.h; \
+	do \
+		echo $(INSTALL_DATA) $$i $(INCLUDEPY); \
+		$(INSTALL_DATA) $$i $(DESTDIR)$(INCLUDEPY); \
+	done
+	@for i in $(srcdir)/Include/cpython/*.h; \
+	do \
+		echo $(INSTALL_DATA) $$i $(INCLUDEPY)/cpython; \
+		$(INSTALL_DATA) $$i $(DESTDIR)$(INCLUDEPY)/cpython; \
+	done
+	@for i in $(srcdir)/Include/internal/*.h; \
+	do \
+		echo $(INSTALL_DATA) $$i $(INCLUDEPY)/internal; \
+		$(INSTALL_DATA) $$i $(DESTDIR)$(INCLUDEPY)/internal; \
+	done
+	@if test "$(INSTALL_MIMALLOC)" = "yes"; then \
+		echo $(INSTALL_DATA) $(srcdir)/Include/internal/mimalloc/mimalloc.h $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc.h; \
+		$(INSTALL_DATA) $(srcdir)/Include/internal/mimalloc/mimalloc.h $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc.h; \
+		for i in $(srcdir)/Include/internal/mimalloc/mimalloc/*.h; \
+		do \
+			echo $(INSTALL_DATA) $$i $(INCLUDEPY)/internal/mimalloc/mimalloc; \
+			$(INSTALL_DATA) $$i $(DESTDIR)$(INCLUDEPY)/internal/mimalloc/mimalloc; \
+		done; \
+	fi
+	echo $(INSTALL_DATA) pyconfig.h $(DESTDIR)$(CONFINCLUDEPY)/pyconfig.h
+	$(INSTALL_DATA) pyconfig.h $(DESTDIR)$(CONFINCLUDEPY)/pyconfig.h
+
+# Install the library and miscellaneous stuff needed for extending/embedding
+# This goes into $(exec_prefix)
+LIBPL=		$(prefix)/lib/python3.13/config-$(VERSION)$(ABIFLAGS)-x86_64-linux-gnu
+
+# pkgconfig directory
+LIBPC=		$(LIBDIR)/pkgconfig
+
+.PHONY: libainstall
+libainstall: all scripts
+	@for i in $(LIBDIR) $(LIBPL) $(LIBPC) $(BINDIR); \
+	do \
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	@if test "$(STATIC_LIBPYTHON)" = 1; then \
+		if test -d $(LIBRARY); then :; else \
+			if test "$(PYTHONFRAMEWORKDIR)" = no-framework; then \
+				if test "$(SHLIB_SUFFIX)" = .dll; then \
+					$(INSTALL_DATA) $(LDLIBRARY) $(DESTDIR)$(LIBPL) ; \
+				else \
+					$(INSTALL_DATA) $(LIBRARY) $(DESTDIR)$(LIBPL)/$(LIBRARY) ; \
+				fi; \
+			else \
+				echo Skip install of $(LIBRARY) - use make frameworkinstall; \
+			fi; \
+		fi; \
+		$(INSTALL_DATA) Programs/python.o $(DESTDIR)$(LIBPL)/python.o; \
+	fi
+	$(INSTALL_DATA) Modules/config.c $(DESTDIR)$(LIBPL)/config.c
+	$(INSTALL_DATA) $(srcdir)/Modules/config.c.in $(DESTDIR)$(LIBPL)/config.c.in
+	$(INSTALL_DATA) Makefile $(DESTDIR)$(LIBPL)/Makefile
+	$(INSTALL_DATA) $(srcdir)/Modules/Setup $(DESTDIR)$(LIBPL)/Setup
+	$(INSTALL_DATA) Modules/Setup.bootstrap $(DESTDIR)$(LIBPL)/Setup.bootstrap
+	$(INSTALL_DATA) Modules/Setup.stdlib $(DESTDIR)$(LIBPL)/Setup.stdlib
+	$(INSTALL_DATA) Modules/Setup.local $(DESTDIR)$(LIBPL)/Setup.local
+	$(INSTALL_DATA) Misc/python.pc $(DESTDIR)$(LIBPC)/python-$(LDVERSION).pc
+	$(INSTALL_DATA) Misc/python-embed.pc $(DESTDIR)$(LIBPC)/python-$(LDVERSION)-embed.pc
+	$(INSTALL_SCRIPT) $(srcdir)/Modules/makesetup $(DESTDIR)$(LIBPL)/makesetup
+	$(INSTALL_SCRIPT) $(srcdir)/install-sh $(DESTDIR)$(LIBPL)/install-sh
+	$(INSTALL_SCRIPT) python-config.py $(DESTDIR)$(LIBPL)/python-config.py
+	$(INSTALL_SCRIPT) python-config $(DESTDIR)$(BINDIR)/python$(LDVERSION)-config
+	$(INSTALL_SCRIPT) $(SCRIPT_IDLE) $(DESTDIR)$(BINDIR)/idle$(VERSION)
+	$(INSTALL_SCRIPT) $(SCRIPT_PYDOC) $(DESTDIR)$(BINDIR)/pydoc$(VERSION)
+	@if [ -s Modules/python.exp -a \
+		"`echo $(MACHDEP) | sed 's/^\(...\).*/\1/'`" = "aix" ]; then \
+		echo; echo "Installing support files for building shared extension modules on AIX:"; \
+		$(INSTALL_DATA) Modules/python.exp		\
+				$(DESTDIR)$(LIBPL)/python.exp;		\
+		echo; echo "$(LIBPL)/python.exp";		\
+		$(INSTALL_SCRIPT) $(srcdir)/Modules/makexp_aix	\
+				$(DESTDIR)$(LIBPL)/makexp_aix;		\
+		echo "$(LIBPL)/makexp_aix";			\
+		$(INSTALL_SCRIPT) Modules/ld_so_aix	\
+				$(DESTDIR)$(LIBPL)/ld_so_aix;		\
+		echo "$(LIBPL)/ld_so_aix";			\
+		echo; echo "See Misc/README.AIX for details.";	\
+	else true; \
+	fi
+
+# Here are a couple of targets for MacOSX again, to install a full
+# framework-based Python. frameworkinstall installs everything, the
+# subtargets install specific parts. Much of the actual work is offloaded to
+# the Makefile in Mac
+#
+#
+# This target is here for backward compatibility, previous versions of Python
+# hadn't integrated framework installation in the normal install process.
+.PHONY: frameworkinstall
+frameworkinstall: install
+
+# On install, we re-make the framework
+# structure in the install location, /Library/Frameworks/ or the argument to
+# --enable-framework. If --enable-framework has been specified then we have
+# automatically set prefix to the location deep down in the framework, so we
+# only have to cater for the structural bits of the framework.
+
+.PHONY: frameworkinstallframework
+frameworkinstallframework:  install frameworkinstallmaclib
+
+# macOS uses a versioned frameworks structure that includes a full install
+.PHONY: frameworkinstallversionedstructure
+frameworkinstallversionedstructure:	$(LDLIBRARY)
+	@if test "$(PYTHONFRAMEWORKDIR)" = no-framework; then \
+		echo Not configured with --enable-framework; \
+		exit 1; \
+	else true; \
+	fi
+	@for i in $(prefix)/Resources/English.lproj $(prefix)/lib; do\
+		if test ! -d $(DESTDIR)$$i; then \
+			echo "Creating directory $(DESTDIR)$$i"; \
+			$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$$i; \
+		else	true; \
+		fi; \
+	done
+	$(LN) -fsn include/python$(LDVERSION) $(DESTDIR)$(prefix)/Headers
+	sed 's/%VERSION%/'"`$(RUNSHARED) ./$(BUILDPYTHON) -c 'import platform; print(platform.python_version())'`"'/g' < $(RESSRCDIR)/Info.plist > $(DESTDIR)$(prefix)/Resources/Info.plist
+	$(LN) -fsn $(VERSION) $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Versions/Current
+	$(LN) -fsn Versions/Current/$(PYTHONFRAMEWORK) $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/$(PYTHONFRAMEWORK)
+	$(LN) -fsn Versions/Current/Headers $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Headers
+	$(LN) -fsn Versions/Current/Resources $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Resources
+	$(INSTALL_SHARED) $(LDLIBRARY) $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/$(LDLIBRARY)
+
+# iOS/tvOS/watchOS uses a non-versioned framework with Info.plist in the
+# framework root, no .lproj data, and only stub compilation assistance binaries
+.PHONY: frameworkinstallunversionedstructure
+frameworkinstallunversionedstructure:	$(LDLIBRARY)
+	@if test "$(PYTHONFRAMEWORKDIR)" = no-framework; then \
+		echo Not configured with --enable-framework; \
+		exit 1; \
+	else true; \
+	fi
+	if test -d $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/include; then \
+		echo "Clearing stale header symlink directory"; \
+		rm -rf $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/include; \
+	fi
+	$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)
+	sed 's/%VERSION%/'"`$(RUNSHARED) $(PYTHON_FOR_BUILD) -c 'import platform; print(platform.python_version())'`"'/g' < $(RESSRCDIR)/Info.plist > $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Info.plist
+	$(INSTALL_SHARED) $(LDLIBRARY) $(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/$(LDLIBRARY)
+	$(INSTALL) -d -m $(DIRMODE) $(DESTDIR)$(BINDIR)
+	for file in $(srcdir)/$(RESSRCDIR)/bin/* ; do \
+		$(INSTALL) -m $(EXEMODE) $$file $(DESTDIR)$(BINDIR); \
+	done
+
+# This installs Mac/Lib into the framework
+# Install a number of symlinks to keep software that expects a normal unix
+# install (which includes python-config) happy.
+.PHONY: frameworkinstallmaclib
+frameworkinstallmaclib:
+	$(LN) -fs "../../../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(LIBPL)/libpython$(LDVERSION).a"
+	$(LN) -fs "../../../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(LIBPL)/libpython$(LDVERSION).dylib"
+	$(LN) -fs "../../../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(LIBPL)/libpython$(VERSION).a"
+	$(LN) -fs "../../../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(LIBPL)/libpython$(VERSION).dylib"
+	$(LN) -fs "../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(prefix)/lib/libpython$(LDVERSION).dylib"
+	$(LN) -fs "../$(PYTHONFRAMEWORK)" "$(DESTDIR)$(prefix)/lib/libpython$(VERSION).dylib"
+
+# This installs the IDE, the Launcher and other apps into /Applications
+.PHONY: frameworkinstallapps
+frameworkinstallapps:
+	cd Mac && $(MAKE) installapps DESTDIR="$(DESTDIR)"
+
+# Build the bootstrap executable that will spawn the interpreter inside
+# an app bundle within the framework.  This allows the interpreter to
+# run OS X GUI APIs.
+.PHONY: frameworkpythonw
+frameworkpythonw:
+	cd Mac && $(MAKE) pythonw
+
+# This installs the python* and other bin symlinks in $prefix/bin or in
+# a bin directory relative to the framework root
+.PHONY: frameworkinstallunixtools
+frameworkinstallunixtools:
+	cd Mac && $(MAKE) installunixtools DESTDIR="$(DESTDIR)"
+
+.PHONY: frameworkaltinstallunixtools
+frameworkaltinstallunixtools:
+	cd Mac && $(MAKE) altinstallunixtools DESTDIR="$(DESTDIR)"
+
+# This installs the Tools into the applications directory.
+# It is not part of a normal frameworkinstall
+.PHONY: frameworkinstallextras
+frameworkinstallextras:
+	cd Mac && $(MAKE) installextras DESTDIR="$(DESTDIR)"
+
+# On iOS, bin/lib can't live inside the framework; include needs to be called
+# "Headers", but *must* be in the framework, and *not* include the `python3.X`
+# subdirectory. The install has put these folders in the same folder as
+# Python.framework; Move the headers to their final framework-compatible home.
+.PHONY: frameworkinstallmobileheaders
+frameworkinstallmobileheaders: frameworkinstallunversionedstructure inclinstall
+	if test -d $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Headers; then \
+		echo "Removing old framework headers"; \
+		rm -rf $(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Headers; \
+	fi
+	mv "$(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/include/python$(LDVERSION)" "$(DESTDIR)$(PYTHONFRAMEWORKINSTALLDIR)/Headers"
+	$(LN) -fs "../$(PYTHONFRAMEWORKDIR)/Headers" "$(DESTDIR)$(PYTHONFRAMEWORKPREFIX)/include/python$(LDVERSION)"
+
+# Build the toplevel Makefile
+Makefile.pre: $(srcdir)/Makefile.pre.in config.status
+	CONFIG_FILES=Makefile.pre CONFIG_HEADERS= ./config.status
+	$(MAKE) -f Makefile.pre Makefile
+
+# Run the configure script.
+config.status:	$(srcdir)/configure
+	$(srcdir)/configure $(CONFIG_ARGS)
+
+.PRECIOUS: config.status $(BUILDPYTHON) Makefile Makefile.pre
+
+Python/asm_trampoline.o: $(srcdir)/Python/asm_trampoline.S
+	$(CC) -c $(PY_CORE_CFLAGS) -o $@ $<
+
+
+JIT_DEPS = \
+		$(srcdir)/Tools/jit/*.c \
+		$(srcdir)/Tools/jit/*.py \
+		$(srcdir)/Python/executor_cases.c.h \
+		pyconfig.h
+
+jit_stencils.h: $(JIT_DEPS)
+	
+
+Python/jit.o: $(srcdir)/Python/jit.c 
+	$(CC) -c $(PY_CORE_CFLAGS) -o $@ $<
+
+.PHONY: regen-jit
+regen-jit:
+	
+
+# Some make's put the object file in the current directory
+.c.o:
+	$(CC) -c $(PY_CORE_CFLAGS) -o $@ $<
+
+# bpo-30104: dtoa.c uses union to cast double to unsigned long[2]. clang 4.0
+# with -O2 or higher and strict aliasing miscompiles the ratio() function
+# causing rounding issues. Compile dtoa.c using -fno-strict-aliasing on clang.
+# https://bugs.llvm.org//show_bug.cgi?id=31928
+Python/dtoa.o: Python/dtoa.c
+	$(CC) -c $(PY_CORE_CFLAGS) $(CFLAGS_ALIASING) -o $@ $<
+
+# Run reindent on the library
+.PHONY: reindent
+reindent:
+	./$(BUILDPYTHON) $(srcdir)/Tools/patchcheck/reindent.py -r $(srcdir)/Lib
+
+# Rerun configure with the same options as it was run last time,
+# provided the config.status script exists
+.PHONY: recheck
+recheck:
+	./config.status --recheck
+	./config.status
+
+# Regenerate configure and pyconfig.h.in
+.PHONY: autoconf
+autoconf:
+	(cd $(srcdir); autoreconf -ivf -Werror)
+
+.PHONY: regen-configure
+regen-configure:
+	$(srcdir)/Tools/build/regen-configure.sh
+
+.PHONY: regen-sbom
+regen-sbom:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/build/generate_sbom.py
+
+# Create a tags file for vi
+tags::
+	ctags -w $(srcdir)/Include/*.h $(srcdir)/Include/cpython/*.h $(srcdir)/Include/internal/*.h
+	for i in $(SRCDIRS); do ctags -f tags -w -a $(srcdir)/$$i/*.[ch]; done
+	ctags -f tags -w -a $(srcdir)/Modules/_ctypes/*.[ch]
+	find $(srcdir)/Lib -type f -name "*.py" -not -name "test_*.py" -not -path "*/test/*" -not -path "*/tests/*" -not -path "*/*_test/*" | ctags -f tags -w -a -L -
+	LC_ALL=C sort -o tags tags
+
+# Create a tags file for GNU Emacs
+TAGS::
+	cd $(srcdir); \
+	etags Include/*.h Include/cpython/*.h Include/internal/*.h; \
+	for i in $(SRCDIRS); do etags -a $$i/*.[ch]; done
+	etags -a $(srcdir)/Modules/_ctypes/*.[ch]
+	find $(srcdir)/Lib -type f -name "*.py" -not -name "test_*.py" -not -path "*/test/*" -not -path "*/tests/*" -not -path "*/*_test/*" | etags - -a
+
+# Sanitation targets -- clean leaves libraries, executables and tags
+# files, which clobber removes as well
+.PHONY: pycremoval
+pycremoval:
+	-find $(srcdir) -depth -name '__pycache__' -exec rm -rf {} ';'
+	-find $(srcdir) -name '*.py[co]' -exec rm -f {} ';'
+
+.PHONY: rmtestturds
+rmtestturds:
+	-rm -f *BAD *GOOD *SKIPPED
+	-rm -rf OUT
+	-rm -f *.TXT
+	-rm -f *.txt
+	-rm -f gb-18030-2000.xml
+
+.PHONY: docclean
+docclean:
+	$(MAKE) -C $(srcdir)/Doc clean
+
+# like the 'clean' target but retain the profile guided optimization (PGO)
+# data.  The PGO data is only valid if source code remains unchanged.
+.PHONY: clean-retain-profile
+clean-retain-profile: pycremoval
+	find . -name '*.[oa]' -exec rm -f {} ';'
+	find . -name '*.s[ol]' -exec rm -f {} ';'
+	find . -name '*.so.[0-9]*.[0-9]*' -exec rm -f {} ';'
+	find . -name '*.lto' -exec rm -f {} ';'
+	find . -name '*.wasm' -exec rm -f {} ';'
+	find . -name '*.lst' -exec rm -f {} ';'
+	find build -name 'fficonfig.h' -exec rm -f {} ';' || true
+	find build -name '*.py' -exec rm -f {} ';' || true
+	find build -name '*.py[co]' -exec rm -f {} ';' || true
+	-rm -f pybuilddir.txt
+	-rm -f _bootstrap_python
+	-rm -f python.html python*.js python.data python*.symbols python*.map
+	-rm -f $(WASM_STDLIB)
+	-rm -f Programs/_testembed Programs/_freeze_module
+	-rm -rf Python/deepfreeze
+	-rm -f Python/frozen_modules/*.h
+	-rm -f Python/frozen_modules/MANIFEST
+	-find build -type f -a ! -name '*.gc??' -exec rm -f {} ';'
+	-rm -f Include/pydtrace_probes.h
+	-rm -f profile-gen-stamp
+	-rm -rf iOS/testbed/Python.xcframework/ios-*/bin
+	-rm -rf iOS/testbed/Python.xcframework/ios-*/lib
+	-rm -rf iOS/testbed/Python.xcframework/ios-*/include
+	-rm -rf iOS/testbed/Python.xcframework/ios-*/Python.framework
+
+.PHONY: profile-removal
+profile-removal:
+	find . -name '*.gc??' -exec rm -f {} ';'
+	find . -name '*.profclang?' -exec rm -f {} ';'
+	find . -name '*.dyn' -exec rm -f {} ';'
+	rm -f $(COVERAGE_INFO)
+	rm -rf $(COVERAGE_REPORT)
+	rm -f profile-run-stamp
+	rm -f profile-bolt-stamp
+
+.PHONY: clean-profile
+clean-profile: clean-retain-profile clean-bolt
+	@if test build_all = profile-opt -o build_all = bolt-opt; then \
+		rm -f profile-gen-stamp profile-clean-stamp; \
+		$(MAKE) profile-removal; \
+	fi
+
+# gh-141808: The JIT stencils are deliberately kept in clean-profile
+.PHONY: clean-jit-stencils
+clean-jit-stencils:
+	-rm -f jit_stencils*.h
+
+.PHONY: clean
+clean: clean-profile clean-jit-stencils
+
+.PHONY: clobber
+clobber: clean
+	-rm -f $(BUILDPYTHON) $(LIBRARY) $(LDLIBRARY) $(DLLLIBRARY) \
+		tags TAGS \
+		config.cache config.log pyconfig.h Modules/config.c
+	-rm -rf build platform
+	-rm -rf $(PYTHONFRAMEWORKDIR)
+	-rm -rf iOS/Frameworks
+	-rm -rf iOSTestbed.*
+	-rm -f python-config.py python-config
+	-rm -rf cross-build
+
+# Make things extra clean, before making a distribution:
+# remove all generated files, even Makefile[.pre]
+# Keep configure and Python-ast.[ch], it's possible they can't be generated
+.PHONY: distclean
+distclean: clobber docclean
+	for file in $(srcdir)/Lib/test/data/* ; do \
+	    if test "$$file" != "$(srcdir)/Lib/test/data/README"; then rm "$$file"; fi; \
+	done
+	-rm -f core Makefile Makefile.pre config.status Modules/Setup.local \
+	    Modules/Setup.bootstrap Modules/Setup.stdlib \
+		Modules/ld_so_aix Modules/python.exp Misc/python.pc \
+		Misc/python-embed.pc Misc/python-config.sh
+	-rm -f python*-gdb.py
+	# Issue #28258: set LC_ALL to avoid issues with Estonian locale.
+	# Expansion is performed here by shell (spawned by make) itself before
+	# arguments are passed to find. So LC_ALL=C must be set as a separate
+	# command.
+	LC_ALL=C; find $(srcdir)/[a-zA-Z]* '(' -name '*.fdc' -o -name '*~' \
+				     -o -name '[@,#]*' -o -name '*.old' \
+				     -o -name '*.orig' -o -name '*.rej' \
+				     -o -name '*.bak' ')' \
+				     -exec rm -f {} ';'
+
+# Check that all symbols exported by libpython start with "Py" or "_Py"
+.PHONY: smelly
+smelly: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/build/smelly.py
+
+# Check if any unsupported C global variables have been added.
+.PHONY: check-c-globals
+check-c-globals:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/c-analyzer/check-c-globals.py \
+		--format summary \
+		--traceback
+
+# Check for undocumented C APIs.
+.PHONY: check-c-api-docs
+check-c-api-docs:
+	$(PYTHON_FOR_REGEN) $(srcdir)/Tools/check-c-api-docs/main.py
+
+# Find files with funny names
+.PHONY: funny
+funny:
+	find $(SUBDIRS) $(SUBDIRSTOO) \
+		-type d \
+		-o -name '*.[chs]' \
+		-o -name '*.py' \
+		-o -name '*.pyw' \
+		-o -name '*.dat' \
+		-o -name '*.el' \
+		-o -name '*.fd' \
+		-o -name '*.in' \
+		-o -name '*.gif' \
+		-o -name '*.txt' \
+		-o -name '*.xml' \
+		-o -name '*.xbm' \
+		-o -name '*.xpm' \
+		-o -name '*.uue' \
+		-o -name '*.decTest' \
+		-o -name '*.tmCommand' \
+		-o -name '*.tmSnippet' \
+		-o -name 'Setup' \
+		-o -name 'Setup.*' \
+		-o -name README \
+		-o -name NEWS \
+		-o -name HISTORY \
+		-o -name Makefile \
+		-o -name ChangeLog \
+		-o -name .hgignore \
+		-o -name MANIFEST \
+		-o -print
+
+# Perform some verification checks on any modified files.
+.PHONY: patchcheck
+patchcheck: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/patchcheck/patchcheck.py
+
+.PHONY: check-limited-abi
+check-limited-abi: all
+	$(RUNSHARED) ./$(BUILDPYTHON) $(srcdir)/Tools/build/stable_abi.py --all $(srcdir)/Misc/stable_abi.toml
+
+.PHONY: update-config
+update-config:
+	curl -sL -o config.guess 'https://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD'
+	curl -sL -o config.sub 'https://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD'
+	chmod +x config.guess config.sub
+
+# Dependencies
+
+Python/thread.o:  $(srcdir)/Python/thread_nt.h $(srcdir)/Python/thread_pthread.h $(srcdir)/Python/thread_pthread_stubs.h $(srcdir)/Python/condvar.h
+
+##########################################################################
+# Module dependencies and platform-specific files
+
+# force rebuild when header file or module build flavor (static/shared) is changed
+MODULE_DEPS_STATIC=Modules/config.c
+MODULE_DEPS_SHARED=$(MODULE_DEPS_STATIC) $(EXPORTSYMS)
+
+MODULE__CURSES_DEPS=$(srcdir)/Include/py_curses.h
+MODULE__CURSES_PANEL_DEPS=$(srcdir)/Include/py_curses.h
+MODULE__DATETIME_DEPS=$(srcdir)/Include/datetime.h
+MODULE_CMATH_DEPS=$(srcdir)/Modules/_math.h
+MODULE_MATH_DEPS=$(srcdir)/Modules/_math.h
+MODULE_PYEXPAT_DEPS=$(LIBEXPAT_HEADERS) $(LIBEXPAT_A)
+MODULE_UNICODEDATA_DEPS=$(srcdir)/Modules/unicodedata_db.h $(srcdir)/Modules/unicodename_db.h
+MODULE__BLAKE2_DEPS=$(srcdir)/Modules/_blake2/impl/blake2-config.h $(srcdir)/Modules/_blake2/impl/blake2-impl.h $(srcdir)/Modules/_blake2/impl/blake2.h $(srcdir)/Modules/_blake2/impl/blake2b-load-sse2.h $(srcdir)/Modules/_blake2/impl/blake2b-load-sse41.h $(srcdir)/Modules/_blake2/impl/blake2b-ref.c $(srcdir)/Modules/_blake2/impl/blake2b-round.h $(srcdir)/Modules/_blake2/impl/blake2b.c $(srcdir)/Modules/_blake2/impl/blake2s-load-sse2.h $(srcdir)/Modules/_blake2/impl/blake2s-load-sse41.h $(srcdir)/Modules/_blake2/impl/blake2s-load-xop.h $(srcdir)/Modules/_blake2/impl/blake2s-ref.c $(srcdir)/Modules/_blake2/impl/blake2s-round.h $(srcdir)/Modules/_blake2/impl/blake2s.c $(srcdir)/Modules/_blake2/blake2module.h $(srcdir)/Modules/hashlib.h
+MODULE__CTYPES_DEPS=$(srcdir)/Modules/_ctypes/ctypes.h
+MODULE__CTYPES_MALLOC_CLOSURE=
+MODULE__DECIMAL_DEPS=$(srcdir)/Modules/_decimal/docstrings.h $(LIBMPDEC_HEADERS) $(LIBMPDEC_A)
+MODULE__ELEMENTTREE_DEPS=$(srcdir)/Modules/pyexpat.c $(LIBEXPAT_HEADERS) $(LIBEXPAT_A)
+MODULE__HASHLIB_DEPS=$(srcdir)/Modules/hashlib.h
+MODULE__IO_DEPS=$(srcdir)/Modules/_io/_iomodule.h
+MODULE__MD5_DEPS=$(srcdir)/Modules/hashlib.h $(LIBHACL_HEADERS) Modules/_hacl/Hacl_Hash_MD5.h Modules/_hacl/Hacl_Hash_MD5.c
+MODULE__SHA1_DEPS=$(srcdir)/Modules/hashlib.h $(LIBHACL_HEADERS) Modules/_hacl/Hacl_Hash_SHA1.h Modules/_hacl/Hacl_Hash_SHA1.c
+MODULE__SHA2_DEPS=$(srcdir)/Modules/hashlib.h $(LIBHACL_SHA2_HEADERS) $(LIBHACL_SHA2_A)
+MODULE__SHA3_DEPS=$(srcdir)/Modules/hashlib.h $(LIBHACL_HEADERS) Modules/_hacl/Hacl_Hash_SHA3.h Modules/_hacl/Hacl_Hash_SHA3.c
+MODULE__SOCKET_DEPS=$(srcdir)/Modules/socketmodule.h $(srcdir)/Modules/addrinfo.h $(srcdir)/Modules/getaddrinfo.c $(srcdir)/Modules/getnameinfo.c
+MODULE__SSL_DEPS=$(srcdir)/Modules/_ssl.h $(srcdir)/Modules/_ssl/cert.c $(srcdir)/Modules/_ssl/debughelpers.c $(srcdir)/Modules/_ssl/misc.c $(srcdir)/Modules/_ssl_data_111.h $(srcdir)/Modules/_ssl_data_300.h $(srcdir)/Modules/socketmodule.h
+MODULE__TESTCAPI_DEPS=$(srcdir)/Modules/_testcapi/parts.h $(srcdir)/Modules/_testcapi/util.h
+MODULE__TESTLIMITEDCAPI_DEPS=$(srcdir)/Modules/_testlimitedcapi/testcapi_long.h $(srcdir)/Modules/_testlimitedcapi/parts.h $(srcdir)/Modules/_testlimitedcapi/util.h
+MODULE__TESTINTERNALCAPI_DEPS=$(srcdir)/Modules/_testinternalcapi/parts.h
+MODULE__SQLITE3_DEPS=$(srcdir)/Modules/_sqlite/connection.h $(srcdir)/Modules/_sqlite/cursor.h $(srcdir)/Modules/_sqlite/microprotocols.h $(srcdir)/Modules/_sqlite/module.h $(srcdir)/Modules/_sqlite/prepare_protocol.h $(srcdir)/Modules/_sqlite/row.h $(srcdir)/Modules/_sqlite/util.h
+
+CODECS_COMMON_HEADERS=$(srcdir)/Modules/cjkcodecs/multibytecodec.h $(srcdir)/Modules/cjkcodecs/cjkcodecs.h
+MODULE__CODECS_CN_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_cn.h $(CODECS_COMMON_HEADERS)
+MODULE__CODECS_HK_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_hk.h  $(CODECS_COMMON_HEADERS)
+MODULE__CODECS_ISO2022_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_jisx0213_pair.h $(srcdir)/Modules/cjkcodecs/alg_jisx0201.h $(srcdir)/Modules/cjkcodecs/emu_jisx0213_2000.h $(CODECS_COMMON_HEADERS)
+MODULE__CODECS_JP_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_jisx0213_pair.h $(srcdir)/Modules/cjkcodecs/alg_jisx0201.h $(srcdir)/Modules/cjkcodecs/emu_jisx0213_2000.h $(srcdir)/Modules/cjkcodecs/mappings_jp.h $(CODECS_COMMON_HEADERS)
+MODULE__CODECS_KR_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_kr.h $(CODECS_COMMON_HEADERS)
+MODULE__CODECS_TW_DEPS=$(srcdir)/Modules/cjkcodecs/mappings_tw.h $(CODECS_COMMON_HEADERS)
+MODULE__MULTIBYTECODEC_DEPS=$(srcdir)/Modules/cjkcodecs/multibytecodec.h
+
+# IF YOU PUT ANYTHING HERE IT WILL GO AWAY
+# Local Variables:
+# mode: makefile
+# End:
--- a/Misc/python-config.sh	1970-01-01 04:00:00.000000000 +0400
+++ b/Misc/python-config.sh	2026-05-26 14:44:41.281797661 +0400
@@ -0,0 +1,122 @@
+#!/bin/sh
+
+# Keep this script in sync with python-config.in
+
+exit_with_usage ()
+{
+    local usage
+    usage="Usage: $0 --prefix|--exec-prefix|--includes|--libs|--cflags|--ldflags|--extension-suffix|--help|--abiflags|--configdir|--embed"
+    if [ "$1" -eq 0 ]; then
+        echo "$usage"
+    else
+        echo "$usage" >&2
+    fi
+    exit $1
+}
+
+if [ "$1" = "" ] ; then
+    exit_with_usage 1
+fi
+
+# Returns the actual prefix where this script was installed to.
+installed_prefix ()
+{
+    RESULT=$(dirname $(cd $(dirname "$1") && pwd -P)

[truncated 1586375 bytes]

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/importlib/__pycache__/_abc.cpython-313.pyc, Lib/logging/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/_abc.cpython-313.pyc, Lib/pathlib/__pycache__/_local.cpython-313.pyc, Lib/re/__pycache__/__init__.cpython-313.pyc, Lib/re/__pycache__/_casefix.cpython-313.pyc, Lib/re/__pycache__/_compiler.cpython-313.pyc, Lib/re/__pycache__/_constants.cpyth

[truncated 29270 bytes]

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` with high sampled CPU, but the syscall evidence shows a one-second `poll()` timeout followed by `wait4(-1, WNOHANG) = ECHILD`. The process state was sleeping in `poll_schedule_timeout`, and the raw investigation files referenced by `evidence.json` are not available in this workspace. This does not currently implicate a CPython runtime bug.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose as an application-level `supervisord` polling finding unless independent reproduction produces CPython-specific evidence.

## Patch Plan
Do not edit CPython in this pass. The evidence starts at the script/application entrypoint (`supervisord`), while CPython’s entrypoint is only `Programs/python.c -> Py_BytesMain() -> Py_RunMain()`.

Relevant CPython conventions/helpers found: `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, `_PyDeadline_Get()`, and existing socket/SSL poll wrappers in `Modules/socketmodule.c` and `Modules/_ssl.c`. These already use bounded waits and GIL release around blocking syscalls. No relevant local helper is missing for the observed `supervisord` loop.

No prior Fixer patch is present to improve or replace (`git status --short` clean, baseline commit only). No awkward control-flow change, including avoidable `goto`, is planned because no source patch is justified by the available evidence.

## Risks
A CPython patch based only on this profile would likely invent a runtime failure not shown by the evidence. The `wait4(ECHILD)` cadence may be normal or suboptimal supervisor behavior, and changing CPython polling/wait semantics could regress subprocess, socket, or signal behavior.

## Validation
Before reporting any narrow check, try the project-level entrypoint from the workspace root: `./configure && make`.

Bounded independent reproduction attempt: if `supervisord` and its config are available, run `timeout 6 strace -tt -e poll,wait4 /usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` to see whether the same one-second `poll()`/`wait4(ECHILD)` signal appears. In this workspace, `/usr/bin/supervisord` and `/etc/supervisor/supervisord.conf` are not present, so this may be skipped with that exact reason.

## Patch Pass

Subject: Diagnose supervisord polling outside CPython

## Commit Message
No source change. The collected evidence points to `supervisord` waking once per second to poll and reap children, not to a CPython primitive spinning in the interpreter. A CPython patch would be speculative without a local reproduction or a trace that identifies Python runtime code as the cause.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace/proc signal for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`: sampled CPU was high, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`.

The likely root cause is the application’s supervision loop waking on a one-second timeout and checking for children, not CPython entering a tight busy loop. The CPython entrypoint is just `Programs/python.c` calling `Py_BytesMain()`, then `Py_RunMain()`. Nearby runtime wrappers already use CPython conventions such as `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, and `_PyDeadline_Get()` around blocking `poll()`/socket work.

I followed the saved plan and made no source change. No relevant local helper was missing, and no cleaner control-flow patch exists because the available evidence does not identify a CPython code-level fault. The expected effect is that this proposal remains an upstreamable diagnosis instead of a speculative runtime patch.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. The command completed with exit code 0. Configure found `poll`, `wait4`, and `waitpid`; it reported optional modules `_dbm`, `_gdbm`, and `_tkinter` missing. During the build’s module import check, `_ssl` was removed after failing to import with `undefined symbol: TLSv1_method`, while `make` still exited successfully.

Independent reproduction attempt was blocked: `/usr/bin/supervisord` is not installed and `/etc/supervisor/supervisord.conf` is missing in this environment. `strace` is installed, but the captured command cannot be run here, so I did not independently reproduce the observed polling signal.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: Diagnose supervisord polling outside CPython

## Commit Message
No source change. The collected evidence points to `supervisord` waking once per second to poll and reap children, not to a CPython primitive spinning in the interpreter. This refinement addresses the review finding by removing generated validation artifacts from the working tree.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace/proc signal for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`: sampled CPU was high, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`.

The cautious inference is that the application’s supervision loop wakes on a one-second timeout and checks for children; the available evidence does not show CPython entering a tight busy loop. The CPython entrypoint remains `Programs/python.c` calling `Py_BytesMain()`, then `Py_RunMain()`. Nearby runtime wrappers already use CPython conventions such as `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, and `_PyDeadline_Get()` around blocking `poll()`/socket work.

I made no source change. The review finding was metadata drift from generated build files, so I removed those artifacts with CPython’s `make distclean` target and verified the working tree is clean. The expected effect is that the proposal now matches `## Git Add Paths: None` and remains a no-patch diagnosis rather than a speculative runtime change.

## Git Add Paths
None

## Validation
Prior authoring validation ran `./configure && make` from the workspace root; it completed with exit code 0. Configure found `poll`, `wait4`, and `waitpid`; optional modules `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` failed import during module checks with `undefined symbol: TLSv1_method`, but `make` still exited successfully.

This refinement ran `make distclean` to address the review’s generated-artifact finding, then `git status --short`, which produced no output. Independent reproduction remains blocked because `/usr/bin/supervisord` is not installed and `/etc/supervisor/supervisord.conf` is missing in this environment, although `strace` is installed.

## Review Pass 2

RESULT: ok

No source diff is present, and `git status --short` is clean. The refined response is consistent with `## Git Add Paths: None`, uses a valid `inferred` evidence confidence for an indirect profiler/strace diagnosis, avoids claiming a reproduced CPython bug, and explains why the evidence points at `supervisord` rather than an upstream CPython code change. Validation notes include the project-level `./configure && make` result and the blocked independent reproduction command context.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/importlib/__pycache__/_abc.cpython-313.pyc, Lib/logging/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/_abc.cpython-313.pyc, Lib/pathlib/__pycache__/_local.cpython-313.pyc, Lib/re/__pycache__/__init__.cpython-313.pyc, Lib/re/__pycache__/_casefix.cpython-313.pyc, Lib/re/__pycache__/_compiler.cpython-313.pyc, Lib/re/__pycache__/_constants.cpyth

[truncated 29270 bytes]

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` with high sampled CPU, but the syscall evidence shows a one-second `poll()` timeout followed by `wait4(-1, WNOHANG) = ECHILD`. The process state was sleeping in `poll_schedule_timeout`, and the raw investigation files referenced by `evidence.json` are not available in this workspace. This does not currently implicate a CPython runtime bug.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose as an application-level `supervisord` polling finding unless independent reproduction produces CPython-specific evidence.

## Patch Plan
Do not edit CPython in this pass. The evidence starts at the script/application entrypoint (`supervisord`), while CPython’s entrypoint is only `Programs/python.c -> Py_BytesMain() -> Py_RunMain()`.

Relevant CPython conventions/helpers found: `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, `_PyDeadline_Get()`, and existing socket/SSL poll wrappers in `Modules/socketmodule.c` and `Modules/_ssl.c`. These already use bounded waits and GIL release around blocking syscalls. No relevant local helper is missing for the observed `supervisord` loop.

No prior Fixer patch is present to improve or replace (`git status --short` clean, baseline commit only). No awkward control-flow change, including avoidable `goto`, is planned because no source patch is justified by the available evidence.

## Risks
A CPython patch based only on this profile would likely invent a runtime failure not shown by the evidence. The `wait4(ECHILD)` cadence may be normal or suboptimal supervisor behavior, and changing CPython polling/wait semantics could regress subprocess, socket, or signal behavior.

## Validation
Before reporting any narrow check, try the project-level entrypoint from the workspace root: `./configure && make`.

Bounded independent reproduction attempt: if `supervisord` and its config are available, run `timeout 6 strace -tt -e poll,wait4 /usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` to see whether the same one-second `poll()`/`wait4(ECHILD)` signal appears. In this workspace, `/usr/bin/supervisord` and `/etc/supervisor/supervisord.conf` are not present, so this may be skipped with that exact reason.

## Patch Pass

Subject: Diagnose supervisord polling outside CPython

## Commit Message
No source change. The collected evidence points to `supervisord` waking once per second to poll and reap children, not to a CPython primitive spinning in the interpreter. A CPython patch would be speculative without a local reproduction or a trace that identifies Python runtime code as the cause.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace/proc signal for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`: sampled CPU was high, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`.

The likely root cause is the application’s supervision loop waking on a one-second timeout and checking for children, not CPython entering a tight busy loop. The CPython entrypoint is just `Programs/python.c` calling `Py_BytesMain()`, then `Py_RunMain()`. Nearby runtime wrappers already use CPython conventions such as `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, and `_PyDeadline_Get()` around blocking `poll()`/socket work.

I followed the saved plan and made no source change. No relevant local helper was missing, and no cleaner control-flow patch exists because the available evidence does not identify a CPython code-level fault. The expected effect is that this proposal remains an upstreamable diagnosis instead of a speculative runtime patch.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. The command completed with exit code 0. Configure found `poll`, `wait4`, and `waitpid`; it reported optional modules `_dbm`, `_gdbm`, and `_tkinter` missing. During the build’s module import check, `_ssl` was removed after failing to import with `undefined symbol: TLSv1_method`, while `make` still exited successfully.

Independent reproduction attempt was blocked: `/usr/bin/supervisord` is not installed and `/etc/supervisor/supervisord.conf` is missing in this environment. `strace` is installed, but the captured command cannot be run here, so I did not independently reproduce the observed polling signal.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: Diagnose supervisord polling outside CPython

## Commit Message
No source change. The collected evidence points to `supervisord` waking once per second to poll and reap children, not to a CPython primitive spinning in the interpreter. This refinement addresses the review finding by removing generated validation artifacts from the working tree.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace/proc signal for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`: sampled CPU was high, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`.

The cautious inference is that the application’s supervision loop wakes on a one-second timeout and checks for children; the available evidence does not show CPython entering a tight busy loop. The CPython entrypoint remains `Programs/python.c` calling `Py_BytesMain()`, then `Py_RunMain()`. Nearby runtime wrappers already use CPython conventions such as `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_AsMilliseconds()`, `_PyDeadline_Init()`, and `_PyDeadline_Get()` around blocking `poll()`/socket work.

I made no source change. The review finding was metadata drift from generated build files, so I removed those artifacts with CPython’s `make distclean` target and verified the working tree is clean. The expected effect is that the proposal now matches `## Git Add Paths: None` and remains a no-patch diagnosis rather than a speculative runtime change.

## Git Add Paths
None

## Validation
Prior authoring validation ran `./configure && make` from the workspace root; it completed with exit code 0. Configure found `poll`, `wait4`, and `waitpid`; optional modules `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` failed import during module checks with `undefined symbol: TLSv1_method`, but `make` still exited successfully.

This refinement ran `make distclean` to address the review’s generated-artifact finding, then `git status --short`, which produced no output. Independent reproduction remains blocked because `/usr/bin/supervisord` is not installed and `/etc/supervisor/supervisord.conf` is missing in this environment, although `strace` is installed.

## Review Pass 2

RESULT: ok

No source diff is present, and `git status --short` is clean. The refined response is consistent with `## Git Add Paths: None`, uses a valid `inferred` evidence confidence for an indirect profiler/strace diagnosis, avoids claiming a reproduced CPython bug, and explains why the evidence points at `supervisord` rather than an upstream CPython code change. Validation notes include the project-level `./configure && make` result and the blocked independent reproduction command context.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bisect.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/dataclasses.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/difflib.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/pickle.cpython-313.pyc, Lib/__pycache__/platform.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/pprint.cpython-313.pyc, Lib/__pycache__/random.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shlex.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/tempfile.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/trace.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/i

[truncated 31631 bytes]

Response

## Plan Pass

## Problem
Fixer observed high aggregate CPU for `/usr/bin/python3.13` while running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, but the captured syscall pattern is `poll(..., 1000)` timing out once per second with `wait4(-1, ..., WNOHANG)` returning `ECHILD`. That looks like supervisord’s application event loop, not a demonstrated CPython runtime busy loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch in this pass: diagnose/report the evidence as insufficient for an upstream `python3.13` runtime fix.

## Patch Plan
Do not edit CPython unless additional evidence connects the CPU use to a CPython defect. The current evidence is profiler/syscall-only, the raw artifact directory named in `evidence.json` is unavailable, and the process is a script entrypoint (`supervisord`) rather than a standalone interpreter workload.

If more evidence is collected before editing, start from the application entrypoint: identify supervisord’s polling code and fd 4, then only inspect CPython runtime paths if the application trace shows incorrect behavior from `select.poll`, `os.wait4`, signal handling, or subprocess reaping.

Relevant CPython conventions/helpers found: `Modules/selectmodule.c` already uses `_PyTime_FromMillisecondsObject`, `_PyDeadline_Init`, `_PyDeadline_Get`, `Py_BEGIN_ALLOW_THREADS`, and EINTR retry handling; `Modules/posixmodule.c` wraps `wait4()` with `Py_BEGIN_ALLOW_THREADS`, `PyErr_CheckSignals()`, `posix_error()`, and `wait_helper()`. No missing local helper or cleaner bounded code path was identified for the observed pattern.

No prior Fixer patch related to this issue was found in `.pc` or `debian/patches`.

## Risks
Patching CPython from this evidence would likely paper over normal application polling behavior and risk changing stable `select.poll()` or `os.wait4()` semantics without a reproducer. The misleading `pthread_attr_destroy`/`PyMem_Realloc` backtrace is not enough to justify a runtime change because the syscall evidence shows blocking one-second polls, not a tight interpreter loop.

## Validation
If a source patch becomes justified, first run the project entrypoint from the workspace root: `./configure && make`.

For this no-patch diagnosis, use a bounded independent check instead: run a small Python process under `strace` that performs `wait4(-1, WNOHANG)` with no children and `select.poll().poll(1000)`, confirming it produces the same `ECHILD` plus one-second timeout shape without implying a CPython defect. Then, if a patch is later proposed, run the narrow relevant tests such as `make test TESTOPTS="-v test_poll test_wait4"` after the project build.

## Patch Pass

Subject: No patch: diagnose supervisord poll loop evidence

## Commit Message
No source change. The collected evidence does not show a CPython runtime bug: it shows a `supervisord` process repeatedly checking for child processes and then sleeping in a one-second `poll()` timeout.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was high sampled CPU attributed to `/usr/bin/python3.13`, with perf showing kernel `read_tsc` and `_PyEval_EvalFrameDefault`, `/proc` showing the sampled process as sleeping in `poll_schedule_timeout`, and strace showing a repeating `wait4(-1, WNOHANG) = ECHILD` followed by `poll(..., 1000) = 0` after about one second.

The likely root cause is an application-level supervisord event loop, not a CPython busy loop. `ECHILD` means there are no child processes to reap, and the following `poll(..., 1000)` blocks for the requested one-second timeout. CPython’s relevant code already uses the local wrappers and conventions: `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and releases the GIL around `poll()`, while `Modules/posixmodule.c` releases the GIL around `wait4()` and reports `ECHILD` through the normal POSIX error path.

I followed the saved plan and did not leave a source diff. The expected effect is that this proposal becomes an upstream-ready diagnosis/report instead of a speculative CPython patch for behavior that the evidence does not connect to a runtime defect.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional module issues: `_ssl` failed to import due to undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing.

Ran `./python -m test -v test_poll test_wait4`: success, 9 tests run, 1 skipped.

Attempted independent syscall reproduction with `strace -e trace=poll,wait4`, but ptrace is blocked in the sandbox: `PTRACE_TRACEME: Operation not permitted`. Fallback Python-level check confirmed the semantic pattern: `os.wait4(-1, os.WNOHANG)` raised `ChildProcessError errno=10`, and `select.poll().poll(1000)` returned no events after about `1.001s`.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bisect.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/dataclasses.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/difflib.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/pickle.cpython-313.pyc`, `Lib/__pycache__/platform.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/pprint.cpython-313.pyc`, `Lib/__pycache__/random.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shlex.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/tempfile.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/trace.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/json/__pycache__/__init__.cpython-313.pyc`, `Lib/json/__pycache__/decoder.cpython-313.pyc`, `Lib/json/__pycache__/encoder.cpython-313.pyc`, `Lib/json/__pycache__/scanner.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/__init__.cpython-313.pyc`, `Lib/test/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/fork_wait.cpython-313.pyc`, `Lib/test/__pycache__/test_poll.cpython-313.pyc`, `Lib/test/__pycache__/test_wait4.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/__init__.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/cmdline.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/filter.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/findtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/logger.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/main.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/pgo.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/result.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/results.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/runtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/save_env.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/setup.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/single.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/testresult.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/tsan.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/utils.cpython-313.pyc`, `Lib/test/support/__pycache__/__init__.cpython-313.pyc`, `Lib/test/support/__pycache__/os_helper.cpython-313.pyc`, `Lib/test/support/__pycache__/threading_helper.cpython-313.pyc`, `Lib/unittest/__pycache__/__init__.cpython-313.pyc`, `Lib/unittest/__pycache__/case.cpython-313.pyc`, `Lib/unittest/__pycache__/loader.cpython-313.pyc`, `Lib/unittest/__pycache__/main.cpython-313.pyc`, `Lib/unittest/__pycache__/result.cpython-313.pyc`, `Lib/unittest/__pycache__/runner.cpython-313.pyc`, `Lib/unittest/__pycache__/signals.cpython-313.pyc`, `Lib/unittest/__pycache__/suite.cpython-313.pyc`, `Lib/unittest/__pycache__/util.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bisect.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/dataclasses.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/difflib.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/pickle.cpython-313.pyc`, `Lib/__pycache__/platform.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/pprint.cpython-313.pyc`, `Lib/__pycache__/random.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shlex.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/tempfile.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/trace.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/json/__pycache__/__init__.cpython-313.pyc`, `Lib/json/__pycache__/decoder.cpython-313.pyc`, `Lib/json/__pycache__/encoder.cpython-313.pyc`, `Lib/json/__pycache__/scanner.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/__init__.cpython-313.pyc`, `Lib/test/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/fork_wait.cpython-313.pyc`, `Lib/test/__pycache__/test_poll.cpython-313.pyc`, `Lib/test/__pycache__/test_wait4.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/__init__.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/cmdline.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/filter.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/findtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/logger.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/main.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/pgo.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/result.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/results.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/runtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/save_env.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/setup.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/single.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/testresult.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/tsan.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/utils.cpython-313.pyc`, `Lib/test/support/__pycache__/__init__.cpython-313.pyc`, `Lib/test/support/__pycache__/os_helper.cpython-313.pyc`, `Lib/test/support/__pycache__/threading_helper.cpython-313.pyc`, `Lib/unittest/__pycache__/__init__.cpython-313.pyc`, `Lib/unittest/__pycache__/case.cpython-313.pyc`, `Lib/unittest/__pycache__/loader.cpython-313.pyc`, `Lib/unittest/__pycache__/main.cpython-313.pyc`, `Lib/unittest/__pycache__/result.cpython-313.pyc`, `Lib/unittest/__pycache__/runner.cpython-313.pyc`, `Lib/unittest/__pycache__/signals.cpython-313.pyc`, `Lib/unittest/__pycache__/suite.cpython-313.pyc`, `Lib/unittest/__pycache__/util.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: No patch: keep supervisord poll diagnosis artifact-free

## Commit Message
No source change. The evidence still points to a `supervisord` event loop sleeping in one-second `poll()` calls, not to a demonstrated CPython runtime defect. This refinement removes generated build/test artifacts so the no-patch diagnosis matches the worktree.

## Evidence Confidence
inferred

## Issue Connection
The collected signal is high sampled CPU attributed to `/usr/bin/python3.13`, while `/proc` shows the sampled `supervisord` process sleeping in `poll_schedule_timeout` and strace shows repeated `wait4(-1, WNOHANG) = ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The cautious code-level inference is unchanged: this looks like supervisord’s application loop checking for children and then blocking in `poll()`, not a CPython busy loop. CPython’s relevant local conventions are already in place: `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and releases the GIL around `poll()`, and `Modules/posixmodule.c` releases the GIL around `wait4()` and reports `ECHILD` through the normal POSIX path.

I followed the plan and did not make a source change. The review finding was metadata drift from generated validation artifacts; I removed those artifacts and verified the repo status is clean. The expected effect is a no-patch upstream diagnosis with no accidental build outputs in the proposal.

## Git Add Paths
None

## Validation
This refinement changed no source files, so I did not rerun the full build after cleaning generated outputs.

Previously run from the workspace root: `./configure && make`. It exited 0, with optional module notes: `_ssl` failed to import due to undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing.

Previously run: `./python -m test -v test_poll test_wait4`, which passed: 9 tests run, 1 skipped.

Independent syscall reproduction with `strace -e trace=poll,wait4` was blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted`. The Python-level fallback confirmed `wait4` produced `ChildProcessError errno=10` and `select.poll().poll(1000)` returned after about `1.001s`.

Review cleanup validation: `git status --short` now produces no output.

## Review Pass 2

RESULT: ok

No source changes are present and `git status --short` is clean. The refined response is consistent with `## Git Add Paths: None`, keeps evidence confidence at `inferred`, avoids claiming a reproduced CPython bug, and explains why the observed `supervisord` `wait4(..., WNOHANG)` plus one-second `poll()` pattern is not enough for an upstream runtime patch.

The validation summary is acceptable for a no-patch diagnosis: it reports the prior project-level `./configure && make`, focused `test_poll`/`test_wait4`, the blocked `strace` attempt, and the cleanup verification.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bisect.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/dataclasses.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/difflib.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/pickle.cpython-313.pyc, Lib/__pycache__/platform.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/pprint.cpython-313.pyc, Lib/__pycache__/random.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shlex.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/tempfile.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/trace.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/i

[truncated 31631 bytes]

Response

## Plan Pass

## Problem
Fixer observed high aggregate CPU for `/usr/bin/python3.13` while running `/usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, but the captured syscall pattern is `poll(..., 1000)` timing out once per second with `wait4(-1, ..., WNOHANG)` returning `ECHILD`. That looks like supervisord’s application event loop, not a demonstrated CPython runtime busy loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch in this pass: diagnose/report the evidence as insufficient for an upstream `python3.13` runtime fix.

## Patch Plan
Do not edit CPython unless additional evidence connects the CPU use to a CPython defect. The current evidence is profiler/syscall-only, the raw artifact directory named in `evidence.json` is unavailable, and the process is a script entrypoint (`supervisord`) rather than a standalone interpreter workload.

If more evidence is collected before editing, start from the application entrypoint: identify supervisord’s polling code and fd 4, then only inspect CPython runtime paths if the application trace shows incorrect behavior from `select.poll`, `os.wait4`, signal handling, or subprocess reaping.

Relevant CPython conventions/helpers found: `Modules/selectmodule.c` already uses `_PyTime_FromMillisecondsObject`, `_PyDeadline_Init`, `_PyDeadline_Get`, `Py_BEGIN_ALLOW_THREADS`, and EINTR retry handling; `Modules/posixmodule.c` wraps `wait4()` with `Py_BEGIN_ALLOW_THREADS`, `PyErr_CheckSignals()`, `posix_error()`, and `wait_helper()`. No missing local helper or cleaner bounded code path was identified for the observed pattern.

No prior Fixer patch related to this issue was found in `.pc` or `debian/patches`.

## Risks
Patching CPython from this evidence would likely paper over normal application polling behavior and risk changing stable `select.poll()` or `os.wait4()` semantics without a reproducer. The misleading `pthread_attr_destroy`/`PyMem_Realloc` backtrace is not enough to justify a runtime change because the syscall evidence shows blocking one-second polls, not a tight interpreter loop.

## Validation
If a source patch becomes justified, first run the project entrypoint from the workspace root: `./configure && make`.

For this no-patch diagnosis, use a bounded independent check instead: run a small Python process under `strace` that performs `wait4(-1, WNOHANG)` with no children and `select.poll().poll(1000)`, confirming it produces the same `ECHILD` plus one-second timeout shape without implying a CPython defect. Then, if a patch is later proposed, run the narrow relevant tests such as `make test TESTOPTS="-v test_poll test_wait4"` after the project build.

## Patch Pass

Subject: No patch: diagnose supervisord poll loop evidence

## Commit Message
No source change. The collected evidence does not show a CPython runtime bug: it shows a `supervisord` process repeatedly checking for child processes and then sleeping in a one-second `poll()` timeout.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was high sampled CPU attributed to `/usr/bin/python3.13`, with perf showing kernel `read_tsc` and `_PyEval_EvalFrameDefault`, `/proc` showing the sampled process as sleeping in `poll_schedule_timeout`, and strace showing a repeating `wait4(-1, WNOHANG) = ECHILD` followed by `poll(..., 1000) = 0` after about one second.

The likely root cause is an application-level supervisord event loop, not a CPython busy loop. `ECHILD` means there are no child processes to reap, and the following `poll(..., 1000)` blocks for the requested one-second timeout. CPython’s relevant code already uses the local wrappers and conventions: `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and releases the GIL around `poll()`, while `Modules/posixmodule.c` releases the GIL around `wait4()` and reports `ECHILD` through the normal POSIX error path.

I followed the saved plan and did not leave a source diff. The expected effect is that this proposal becomes an upstream-ready diagnosis/report instead of a speculative CPython patch for behavior that the evidence does not connect to a runtime defect.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional module issues: `_ssl` failed to import due to undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing.

Ran `./python -m test -v test_poll test_wait4`: success, 9 tests run, 1 skipped.

Attempted independent syscall reproduction with `strace -e trace=poll,wait4`, but ptrace is blocked in the sandbox: `PTRACE_TRACEME: Operation not permitted`. Fallback Python-level check confirmed the semantic pattern: `os.wait4(-1, os.WNOHANG)` raised `ChildProcessError errno=10`, and `select.poll().poll(1000)` returned no events after about `1.001s`.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bisect.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/dataclasses.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/difflib.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/pickle.cpython-313.pyc`, `Lib/__pycache__/platform.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/pprint.cpython-313.pyc`, `Lib/__pycache__/random.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shlex.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/tempfile.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/trace.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/json/__pycache__/__init__.cpython-313.pyc`, `Lib/json/__pycache__/decoder.cpython-313.pyc`, `Lib/json/__pycache__/encoder.cpython-313.pyc`, `Lib/json/__pycache__/scanner.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/__init__.cpython-313.pyc`, `Lib/test/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/fork_wait.cpython-313.pyc`, `Lib/test/__pycache__/test_poll.cpython-313.pyc`, `Lib/test/__pycache__/test_wait4.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/__init__.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/cmdline.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/filter.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/findtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/logger.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/main.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/pgo.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/result.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/results.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/runtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/save_env.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/setup.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/single.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/testresult.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/tsan.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/utils.cpython-313.pyc`, `Lib/test/support/__pycache__/__init__.cpython-313.pyc`, `Lib/test/support/__pycache__/os_helper.cpython-313.pyc`, `Lib/test/support/__pycache__/threading_helper.cpython-313.pyc`, `Lib/unittest/__pycache__/__init__.cpython-313.pyc`, `Lib/unittest/__pycache__/case.cpython-313.pyc`, `Lib/unittest/__pycache__/loader.cpython-313.pyc`, `Lib/unittest/__pycache__/main.cpython-313.pyc`, `Lib/unittest/__pycache__/result.cpython-313.pyc`, `Lib/unittest/__pycache__/runner.cpython-313.pyc`, `Lib/unittest/__pycache__/signals.cpython-313.pyc`, `Lib/unittest/__pycache__/suite.cpython-313.pyc`, `Lib/unittest/__pycache__/util.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bisect.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/dataclasses.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/difflib.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/pickle.cpython-313.pyc`, `Lib/__pycache__/platform.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/pprint.cpython-313.pyc`, `Lib/__pycache__/random.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shlex.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/tempfile.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/trace.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/json/__pycache__/__init__.cpython-313.pyc`, `Lib/json/__pycache__/decoder.cpython-313.pyc`, `Lib/json/__pycache__/encoder.cpython-313.pyc`, `Lib/json/__pycache__/scanner.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/__init__.cpython-313.pyc`, `Lib/test/__pycache__/__main__.cpython-313.pyc`, `Lib/test/__pycache__/fork_wait.cpython-313.pyc`, `Lib/test/__pycache__/test_poll.cpython-313.pyc`, `Lib/test/__pycache__/test_wait4.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/__init__.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/cmdline.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/filter.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/findtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/logger.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/main.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/pgo.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/result.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/results.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/runtests.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/save_env.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/setup.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/single.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/testresult.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/tsan.cpython-313.pyc`, `Lib/test/libregrtest/__pycache__/utils.cpython-313.pyc`, `Lib/test/support/__pycache__/__init__.cpython-313.pyc`, `Lib/test/support/__pycache__/os_helper.cpython-313.pyc`, `Lib/test/support/__pycache__/threading_helper.cpython-313.pyc`, `Lib/unittest/__pycache__/__init__.cpython-313.pyc`, `Lib/unittest/__pycache__/case.cpython-313.pyc`, `Lib/unittest/__pycache__/loader.cpython-313.pyc`, `Lib/unittest/__pycache__/main.cpython-313.pyc`, `Lib/unittest/__pycache__/result.cpython-313.pyc`, `Lib/unittest/__pycache__/runner.cpython-313.pyc`, `Lib/unittest/__pycache__/signals.cpython-313.pyc`, `Lib/unittest/__pycache__/suite.cpython-313.pyc`, `Lib/unittest/__pycache__/util.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: No patch: keep supervisord poll diagnosis artifact-free

## Commit Message
No source change. The evidence still points to a `supervisord` event loop sleeping in one-second `poll()` calls, not to a demonstrated CPython runtime defect. This refinement removes generated build/test artifacts so the no-patch diagnosis matches the worktree.

## Evidence Confidence
inferred

## Issue Connection
The collected signal is high sampled CPU attributed to `/usr/bin/python3.13`, while `/proc` shows the sampled `supervisord` process sleeping in `poll_schedule_timeout` and strace shows repeated `wait4(-1, WNOHANG) = ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The cautious code-level inference is unchanged: this looks like supervisord’s application loop checking for children and then blocking in `poll()`, not a CPython busy loop. CPython’s relevant local conventions are already in place: `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and releases the GIL around `poll()`, and `Modules/posixmodule.c` releases the GIL around `wait4()` and reports `ECHILD` through the normal POSIX path.

I followed the plan and did not make a source change. The review finding was metadata drift from generated validation artifacts; I removed those artifacts and verified the repo status is clean. The expected effect is a no-patch upstream diagnosis with no accidental build outputs in the proposal.

## Git Add Paths
None

## Validation
This refinement changed no source files, so I did not rerun the full build after cleaning generated outputs.

Previously run from the workspace root: `./configure && make`. It exited 0, with optional module notes: `_ssl` failed to import due to undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing.

Previously run: `./python -m test -v test_poll test_wait4`, which passed: 9 tests run, 1 skipped.

Independent syscall reproduction with `strace -e trace=poll,wait4` was blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted`. The Python-level fallback confirmed `wait4` produced `ChildProcessError errno=10` and `select.poll().poll(1000)` returned after about `1.001s`.

Review cleanup validation: `git status --short` now produces no output.

## Review Pass 2

RESULT: ok

No source changes are present and `git status --short` is clean. The refined response is consistent with `## Git Add Paths: None`, keeps evidence confidence at `inferred`, avoids claiming a reproduced CPython bug, and explains why the observed `supervisord` `wait4(..., WNOHANG)` plus one-second `poll()` pattern is not enough for an upstream runtime patch.

The validation summary is acceptable for a no-patch diagnosis: it reports the prior project-level `./configure && make`, focused `test_poll`/`test_wait4`, the blocked `strace` attempt, and the cleanup verification.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` under `/usr/bin/python3.13` with repeated `wait4(-1, WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`. The embedded trace shows the process sleeping in `poll_schedule_timeout`, so the available evidence does not establish a CPython interpreter busy loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose the Fixer signal as supervisord’s application-level one-second reap/poll loop, not an upstream Python 3.13 runtime defect.

## Patch Plan
Do not edit CPython unless new evidence ties the CPU use to a CPython runtime path. The current application entrypoint is `supervisord`; the relevant syscall pattern is generated above CPython’s C runtime.

Local checks found CPython contribution/build guidance in `README.rst`, pointing to the Developer Guide and `./configure`, `make`, `make test`. Relevant local conventions/helpers include `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS` around `waitpid` in `Modules/posixmodule.c`, `posix_error()` for syscall errors, and selector timeout rounding in `Lib/selectors.py`. No relevant local helper suggests changing `waitpid`, `poll`, `PyMem_Realloc`, or pthread handling for this evidence.

No prior Fixer source patch was present in the workspace. No `goto`-style control-flow change should be introduced; if later evidence identifies a real bounded CPython defect, the fix should be a direct local change with a focused regression test.

## Risks
A CPython patch here would likely mask or misattribute an application or profiling artifact. Changing `os.waitpid`, selector polling, thread teardown, or memory allocation behavior without a reproducer could regress broad runtime semantics.

The backtrace excerpt is low-symbol quality and includes inconsistent frames; it is not enough to connect `pthread_attr_destroy` or `PyMem_Realloc` to the syscall loop.

## Validation
Before any focused check, try the project entrypoint from the workspace root: `./configure && make`. If it fails, record the exact command and dependency/generated-file failure.

For diagnosis, run a bounded independent syscall-pattern check, explicitly not a claimed failure reproducer: use `timeout` plus `strace -e trace=poll,wait4` around a minimal Python loop that calls `os.wait4(-1, os.WNOHANG)` and a one-second `select.poll().poll(1000)`, confirming the observed pattern can occur with blocking sleeps and low CPU.

If later evidence justifies a CPython patch, validate with the project build first, then the narrowest relevant tests such as `./python -m test test_posix test_selectors test_subprocess`.

## Patch Pass

Subject: Diagnose supervisord poll loop without CPython changes

## Commit Message
No CPython source change is proposed. The collected evidence most likely shows supervisord’s periodic child-reap loop: it calls nonblocking `wait4(..., WNOHANG)`, gets `ECHILD`, then blocks in `poll(..., 1000)` for one second. That pattern is not a tight CPython runtime loop.

## Evidence Confidence
observed

## Issue Connection
Fixer observed a Python 3.13 process running `/usr/bin/supervisord` with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, `/proc` state `S (sleeping)`, kernel stack `poll_schedule_timeout`, and strace excerpts repeating `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by one-second `poll` timeouts. I did not independently reproduce the collected strace because ptrace is blocked in this environment.

The cautious code-level inference is that the loop is in the Python application’s event loop, not in CPython’s syscall wrappers. CPython’s `os.waitpid`/`wait4` code already uses `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS` and `posix_error()`, while `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. The `pthread_attr_destroy` backtrace frame is too low-quality to identify a CPython threading bug.

I followed the saved plan and made no source change. No relevant local helper or compatibility wrapper was found that would justify changing CPython for this evidence. The expected effect is that this proposal remains an upstream-ready no-patch diagnosis instead of shipping a speculative runtime change.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional module issues: `_ssl` failed to import because of `undefined symbol: TLSv1_method`, and `_dbm`, `_gdbm`, and `_tkinter` dependencies were missing.

Attempted independent syscall reproduction with:
`strace -f -tt -e trace=poll,wait4 ./python - ...`
This was blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `PTRACE_SEIZE ... Operation not permitted`.

Ran a narrower Python-level smoke check with the same `wait4(WNOHANG)` plus one-second `poll` sequence. It returned `ChildProcessError` three times, took `3.002` wall seconds, and used `0.00015` CPU seconds, supporting the diagnosis that this pattern blocks rather than spins.

## Review Pass 1

RESULT: ok

No source diff is present, and the workspace is clean. The no-patch diagnosis matches the evidence: the collected signal shows `supervisord` repeatedly doing nonblocking child reaping followed by one-second `poll` sleeps, while `/proc` reports the process sleeping in `poll_schedule_timeout`.

The author response includes the required `## Evidence Confidence` value (`observed`), does not claim independent reproduction, and reports the ptrace blocker for the attempted `strace` comparison. It also attempted the project-level `./configure && make` entrypoint and names the local CPython conventions inspected (`Py_BEGIN_ALLOW_THREADS`, `posix_error()`, selector timeout rounding). No source patch is proposed, so there are no code-level regressions, helper/API misuse, or security-sensitive source changes to reject.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` under `/usr/bin/python3.13` with repeated `wait4(-1, WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0`. The embedded trace shows the process sleeping in `poll_schedule_timeout`, so the available evidence does not establish a CPython interpreter busy loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose the Fixer signal as supervisord’s application-level one-second reap/poll loop, not an upstream Python 3.13 runtime defect.

## Patch Plan
Do not edit CPython unless new evidence ties the CPU use to a CPython runtime path. The current application entrypoint is `supervisord`; the relevant syscall pattern is generated above CPython’s C runtime.

Local checks found CPython contribution/build guidance in `README.rst`, pointing to the Developer Guide and `./configure`, `make`, `make test`. Relevant local conventions/helpers include `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS` around `waitpid` in `Modules/posixmodule.c`, `posix_error()` for syscall errors, and selector timeout rounding in `Lib/selectors.py`. No relevant local helper suggests changing `waitpid`, `poll`, `PyMem_Realloc`, or pthread handling for this evidence.

No prior Fixer source patch was present in the workspace. No `goto`-style control-flow change should be introduced; if later evidence identifies a real bounded CPython defect, the fix should be a direct local change with a focused regression test.

## Risks
A CPython patch here would likely mask or misattribute an application or profiling artifact. Changing `os.waitpid`, selector polling, thread teardown, or memory allocation behavior without a reproducer could regress broad runtime semantics.

The backtrace excerpt is low-symbol quality and includes inconsistent frames; it is not enough to connect `pthread_attr_destroy` or `PyMem_Realloc` to the syscall loop.

## Validation
Before any focused check, try the project entrypoint from the workspace root: `./configure && make`. If it fails, record the exact command and dependency/generated-file failure.

For diagnosis, run a bounded independent syscall-pattern check, explicitly not a claimed failure reproducer: use `timeout` plus `strace -e trace=poll,wait4` around a minimal Python loop that calls `os.wait4(-1, os.WNOHANG)` and a one-second `select.poll().poll(1000)`, confirming the observed pattern can occur with blocking sleeps and low CPU.

If later evidence justifies a CPython patch, validate with the project build first, then the narrowest relevant tests such as `./python -m test test_posix test_selectors test_subprocess`.

## Patch Pass

Subject: Diagnose supervisord poll loop without CPython changes

## Commit Message
No CPython source change is proposed. The collected evidence most likely shows supervisord’s periodic child-reap loop: it calls nonblocking `wait4(..., WNOHANG)`, gets `ECHILD`, then blocks in `poll(..., 1000)` for one second. That pattern is not a tight CPython runtime loop.

## Evidence Confidence
observed

## Issue Connection
Fixer observed a Python 3.13 process running `/usr/bin/supervisord` with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, `/proc` state `S (sleeping)`, kernel stack `poll_schedule_timeout`, and strace excerpts repeating `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by one-second `poll` timeouts. I did not independently reproduce the collected strace because ptrace is blocked in this environment.

The cautious code-level inference is that the loop is in the Python application’s event loop, not in CPython’s syscall wrappers. CPython’s `os.waitpid`/`wait4` code already uses `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS` and `posix_error()`, while `Lib/selectors.py` intentionally rounds positive poll timeouts up to milliseconds. The `pthread_attr_destroy` backtrace frame is too low-quality to identify a CPython threading bug.

I followed the saved plan and made no source change. No relevant local helper or compatibility wrapper was found that would justify changing CPython for this evidence. The expected effect is that this proposal remains an upstream-ready no-patch diagnosis instead of shipping a speculative runtime change.

## Git Add Paths
None

## Validation
Ran `./configure && make` from the workspace root. It completed with exit code 0. The build reported optional module issues: `_ssl` failed to import because of `undefined symbol: TLSv1_method`, and `_dbm`, `_gdbm`, and `_tkinter` dependencies were missing.

Attempted independent syscall reproduction with:
`strace -f -tt -e trace=poll,wait4 ./python - ...`
This was blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `PTRACE_SEIZE ... Operation not permitted`.

Ran a narrower Python-level smoke check with the same `wait4(WNOHANG)` plus one-second `poll` sequence. It returned `ChildProcessError` three times, took `3.002` wall seconds, and used `0.00015` CPU seconds, supporting the diagnosis that this pattern blocks rather than spins.

## Review Pass 1

RESULT: ok

No source diff is present, and the workspace is clean. The no-patch diagnosis matches the evidence: the collected signal shows `supervisord` repeatedly doing nonblocking child reaping followed by one-second `poll` sleeps, while `/proc` reports the process sleeping in `poll_schedule_timeout`.

The author response includes the required `## Evidence Confidence` value (`observed`), does not claim independent reproduction, and reports the ptrace blocker for the attempted `strace` comparison. It also attempted the project-level `./configure && make` entrypoint and names the local CPython conventions inspected (`Py_BEGIN_ALLOW_THREADS`, `posix_error()`, selector timeout rounding). No source patch is proposed, so there are no code-level regressions, helper/API misuse, or security-sensitive source changes to reject.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `python3.13`, but the evidence command line is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, so the script/application entrypoint is `supervisord`, not CPython runtime code. The embedded `strace` shows repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about one second, which is periodic supervisor polling rather than a tight interpreter spin.

## Evidence Confidence
observed

## Proposed Subject
No CPython upstream source patch. Prepare a no-patch diagnosis/report that the collected signal is insufficient for an upstream `python3.13` fix and appears to be an application-level supervisor/event-loop workload or a Fixer attribution issue.

## Patch Plan
Do not edit CPython in this pass. The observed evidence does not identify a CPython defect: `Modules/selectmodule.c` already releases the GIL around `poll()` and recomputes timeouts using `_PyDeadline_Get()` / `_PyTime_AsMilliseconds()`, `Modules/posixmodule.c` wraps `waitpid()` normally with `Py_BEGIN_ALLOW_THREADS`, and `Lib/subprocess.py` uses `_waitpid_lock`, `_try_wait()`, and selector helpers for process waits.

Document that the unresolved backtrace frames around `pthread_attr_destroy()` and `PyMem_Realloc()` are not enough to justify changing memory, threading, or polling runtime code. The evidence also says the process state was sleeping in `poll_schedule_timeout`, and the syscall trace shows one-second blocking `poll()` calls.

Follow CPython maintainer conventions found in `README.rst`: upstream changes should be validated through `./configure`, `make`, and relevant tests, with `make patchcheck` if a patch exists. Debian packaging uses quilt per `debian/README.source`, but this should not become a Debian-local workaround. No prior Fixer patch is present to replace; git history only shows the baseline.

Avoid any source patch that adds control-flow workarounds, including avoidable `goto`, because there is no localized CPython bug to address.

## Risks
A CPython patch here would likely mask or misattribute an application issue in `supervisord` or the supervised workload. Changing `poll()`, `waitpid()`, subprocess waiting, memory allocation, or pthread handling from this evidence could regress broad runtime behavior without a demonstrated bug.

## Validation
If a source patch is later justified, first try the project-level entrypoint from the workspace root: `./configure && make`. If that fails due to missing dependencies or generated files, record the exact failure and then run the narrowest relevant CPython test or compile.

For this no-patch diagnosis, use a bounded independent check: run a small `python3.13` snippet under `strace` that performs `os.waitpid(-1, os.WNOHANG)` with no children and `select.poll().poll(1000)`, confirming the same syscall pattern blocks for about one second rather than spinning. Also compare available investigation artifacts with the bundle; the referenced May 7 raw files are absent, and other same-fingerprint artifacts point to app-level sleeping/subprocess activity rather than CPython runtime failure.

## Patch Pass

Subject: Diagnose supervisor polling trace without CPython changes

## Commit Message
The collected perf, `strace`, and `/proc` evidence points to a Python-hosted `supervisord` process waking once per second to check children and poll a file descriptor. That is an application-level polling loop, not a demonstrated CPython runtime spin, so no upstream source change is safe from this evidence.

## Evidence Confidence
observed

## Issue Connection
Fixer observed a `python3.13` process with high sampled CPU, but the command line was `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The collected syscall trace shows `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000)` timing out after about one second, while `/proc` reported the task sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the visible behavior is supervisor’s periodic child/process event loop. CPython’s relevant local wrappers already use the expected patterns: `select.poll()` releases the GIL with `Py_BEGIN_ALLOW_THREADS` and recomputes timeouts via `_PyDeadline_Get()` / `_PyTime_AsMilliseconds()`, `os.waitpid()` also releases the GIL around `waitpid()`, and `subprocess.Popen` protects child waits with `_waitpid_lock` and `_try_wait()`.

I made no source change. This follows the saved plan and avoids inventing an upstream CPython fix for evidence that was observed by Fixer and not independently reproduced as a CPython bug. The expected effect is no runtime change; this is a no-patch diagnosis suitable for an upstream or packaging bug report if more application-level evidence is collected.

## Git Add Paths
None

## Validation
Checked project guidance and conventions: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `debian/README.source` says Debian patches are quilt-managed. Inspected nearby wait/poll code in `Modules/selectmodule.c`, `Modules/posixmodule.c`, and `Lib/subprocess.py`; relevant local helpers are `Py_BEGIN_ALLOW_THREADS`, `_PyDeadline_Get()`, `_PyTime_AsMilliseconds()`, `_waitpid_lock`, and `_try_wait()`.

Ran project-level validation from the workspace root: `./configure && make`. It exited `0`. The build completed, but reported optional module issues: `_dbm`, `_gdbm`, and `_tkinter` dependencies were missing, and `_ssl` was built then removed because it could not import due to `undefined symbol: TLSv1_method`.

Attempted bounded independent syscall reproduction with `strace -tt -T -e trace=wait4,poll ./python ...`; blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran a non-ptrace bounded smoke check with the built interpreter. `os.waitpid(-1, os.WNOHANG)` raised `ChildProcessError`, and `select.poll().poll(1000)` returned `[]` after `wall 1.001` seconds with `cpu 2.8e-05`, matching blocking poll behavior rather than a busy spin.

Cleaned generated build artifacts with `make distclean`; `git status --short` is clean.

## Review Pass 1

RESULT: ok

No source changes are present; `git status --short` and `git diff` are clean. The author response correctly treats the evidence as observed, not reproduced, and leaves a no-patch diagnosis instead of inventing a CPython source fix.

The diagnosis is consistent with the bundle: the command line is `supervisord`, the trace shows one-second `poll()` timeouts after `wait4(..., WNOHANG) = ECHILD`, and `/proc` reports the process sleeping in `poll_schedule_timeout`. The response also names relevant CPython local helpers and conventions, reports the project-level `./configure && make` result, and clearly states the ptrace blocker for the attempted `strace` reproduction.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed high CPU attributed to `python3.13`, but the evidence command line is `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, so the script/application entrypoint is `supervisord`, not CPython runtime code. The embedded `strace` shows repeated `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about one second, which is periodic supervisor polling rather than a tight interpreter spin.

## Evidence Confidence
observed

## Proposed Subject
No CPython upstream source patch. Prepare a no-patch diagnosis/report that the collected signal is insufficient for an upstream `python3.13` fix and appears to be an application-level supervisor/event-loop workload or a Fixer attribution issue.

## Patch Plan
Do not edit CPython in this pass. The observed evidence does not identify a CPython defect: `Modules/selectmodule.c` already releases the GIL around `poll()` and recomputes timeouts using `_PyDeadline_Get()` / `_PyTime_AsMilliseconds()`, `Modules/posixmodule.c` wraps `waitpid()` normally with `Py_BEGIN_ALLOW_THREADS`, and `Lib/subprocess.py` uses `_waitpid_lock`, `_try_wait()`, and selector helpers for process waits.

Document that the unresolved backtrace frames around `pthread_attr_destroy()` and `PyMem_Realloc()` are not enough to justify changing memory, threading, or polling runtime code. The evidence also says the process state was sleeping in `poll_schedule_timeout`, and the syscall trace shows one-second blocking `poll()` calls.

Follow CPython maintainer conventions found in `README.rst`: upstream changes should be validated through `./configure`, `make`, and relevant tests, with `make patchcheck` if a patch exists. Debian packaging uses quilt per `debian/README.source`, but this should not become a Debian-local workaround. No prior Fixer patch is present to replace; git history only shows the baseline.

Avoid any source patch that adds control-flow workarounds, including avoidable `goto`, because there is no localized CPython bug to address.

## Risks
A CPython patch here would likely mask or misattribute an application issue in `supervisord` or the supervised workload. Changing `poll()`, `waitpid()`, subprocess waiting, memory allocation, or pthread handling from this evidence could regress broad runtime behavior without a demonstrated bug.

## Validation
If a source patch is later justified, first try the project-level entrypoint from the workspace root: `./configure && make`. If that fails due to missing dependencies or generated files, record the exact failure and then run the narrowest relevant CPython test or compile.

For this no-patch diagnosis, use a bounded independent check: run a small `python3.13` snippet under `strace` that performs `os.waitpid(-1, os.WNOHANG)` with no children and `select.poll().poll(1000)`, confirming the same syscall pattern blocks for about one second rather than spinning. Also compare available investigation artifacts with the bundle; the referenced May 7 raw files are absent, and other same-fingerprint artifacts point to app-level sleeping/subprocess activity rather than CPython runtime failure.

## Patch Pass

Subject: Diagnose supervisor polling trace without CPython changes

## Commit Message
The collected perf, `strace`, and `/proc` evidence points to a Python-hosted `supervisord` process waking once per second to check children and poll a file descriptor. That is an application-level polling loop, not a demonstrated CPython runtime spin, so no upstream source change is safe from this evidence.

## Evidence Confidence
observed

## Issue Connection
Fixer observed a `python3.13` process with high sampled CPU, but the command line was `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The collected syscall trace shows `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000)` timing out after about one second, while `/proc` reported the task sleeping in `poll_schedule_timeout`.

The cautious code-level inference is that the visible behavior is supervisor’s periodic child/process event loop. CPython’s relevant local wrappers already use the expected patterns: `select.poll()` releases the GIL with `Py_BEGIN_ALLOW_THREADS` and recomputes timeouts via `_PyDeadline_Get()` / `_PyTime_AsMilliseconds()`, `os.waitpid()` also releases the GIL around `waitpid()`, and `subprocess.Popen` protects child waits with `_waitpid_lock` and `_try_wait()`.

I made no source change. This follows the saved plan and avoids inventing an upstream CPython fix for evidence that was observed by Fixer and not independently reproduced as a CPython bug. The expected effect is no runtime change; this is a no-patch diagnosis suitable for an upstream or packaging bug report if more application-level evidence is collected.

## Git Add Paths
None

## Validation
Checked project guidance and conventions: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`; `debian/README.source` says Debian patches are quilt-managed. Inspected nearby wait/poll code in `Modules/selectmodule.c`, `Modules/posixmodule.c`, and `Lib/subprocess.py`; relevant local helpers are `Py_BEGIN_ALLOW_THREADS`, `_PyDeadline_Get()`, `_PyTime_AsMilliseconds()`, `_waitpid_lock`, and `_try_wait()`.

Ran project-level validation from the workspace root: `./configure && make`. It exited `0`. The build completed, but reported optional module issues: `_dbm`, `_gdbm`, and `_tkinter` dependencies were missing, and `_ssl` was built then removed because it could not import due to `undefined symbol: TLSv1_method`.

Attempted bounded independent syscall reproduction with `strace -tt -T -e trace=wait4,poll ./python ...`; blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran a non-ptrace bounded smoke check with the built interpreter. `os.waitpid(-1, os.WNOHANG)` raised `ChildProcessError`, and `select.poll().poll(1000)` returned `[]` after `wall 1.001` seconds with `cpu 2.8e-05`, matching blocking poll behavior rather than a busy spin.

Cleaned generated build artifacts with `make distclean`; `git status --short` is clean.

## Review Pass 1

RESULT: ok

No source changes are present; `git status --short` and `git diff` are clean. The author response correctly treats the evidence as observed, not reproduced, and leaves a no-patch diagnosis instead of inventing a CPython source fix.

The diagnosis is consistent with the bundle: the command line is `supervisord`, the trace shows one-second `poll()` timeouts after `wait4(..., WNOHANG) = ECHILD`, and `/proc` reports the process sleeping in `poll_schedule_timeout`. The response also names relevant CPython local helpers and conventions, reports the project-level `./configure && make` result, and clearly states the ptrace blocker for the attempted `strace` reproduction.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord` with high sampled CPU, but the available strace excerpt shows a one-second cadence: `poll(..., 1000)` timing out, followed by `wait4(..., WNOHANG)` returning `ECHILD`. That looks like supervisord’s application loop, not a tight CPython runtime loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose this as an application-level supervisord polling signal that is not currently tied to a reproducible Python 3.13 runtime defect.

## Patch Plan
Do not edit files for this finding unless extra evidence connects the behavior to CPython. The raw investigation files referenced by `evidence.json` are unavailable, `/usr/bin/supervisord` and the `supervisor` module are not installed in this workspace, and a cheap local sanity check showed `select.poll(100)` blocking for about 100 ms and `os.wait4(-1, os.WNOHANG)` raising `ChildProcessError` normally.

Checked upstream conventions/docs: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. No top-level `CONTRIBUTING`/`HACKING` file was present. Relevant local helper conventions in the scanned subsystem are `Py_BEGIN_ALLOW_THREADS`/`Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, `_PyTime_*` deadline helpers, and CPython allocator families such as `PyMem_RawMalloc`/`PyMem_RawFree`; no relevant local helper suggests adding throttling inside CPython for this evidence.

No prior Fixer patch was found in the workspace; the Debian source snapshot only differs by job metadata directories.

## Risks
The main risk is misattribution: patching CPython based on a profiler-only sample could alter `poll`, `wait4`, subprocess, or thread behavior without a demonstrated interpreter bug. Any timing/throttling change would be security-sensitive enough to require a real reproducer and impact analysis first.

## Validation
If later evidence justifies a CPython patch, first try the project-level entrypoint from the workspace root:

`./configure && make`

Then run the narrowest relevant CPython test, likely `./python -m test test_select test_os test_subprocess`, depending on the touched code. For the current no-patch diagnosis, the bounded independent check is the local `python3.13` sanity script for `select.poll(100)` and `os.wait4(-1, os.WNOHANG)`, which did not reproduce the reported runaway signal.

## Patch Pass

Subject: Diagnose supervisord polling profile without CPython changes

## Commit Message
No source change is proposed. The collected signal points at a `supervisord` event loop running under Python, not at a demonstrated CPython runtime defect. The saved plan recommended a no-patch diagnosis; I followed that direction and classified the final confidence as `inferred` because the remaining evidence is profiler/strace-based and not independently reproduced.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace investigation for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The signal included high sampled CPU, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `poll(..., 1000)` calls that each blocked for about one second, followed by `wait4(..., WNOHANG)` returning `ECHILD`.

The cautious code-level inference is that this is supervisord’s application-level polling cadence, not a tight CPython busy loop. The scanned CPython paths for `os.wait4()` and `select.poll.poll()` use the normal local conventions: `Py_BEGIN_ALLOW_THREADS`/`Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, and `_PyTime_*` timeout handling. No relevant local helper or wrapper was missing.

I made no source change. The expected effect is no runtime behavior change; this avoids landing a speculative timing/throttling patch in CPython without reproduced evidence or security-impact analysis.

## Git Add Paths
None

## Validation
Checked contribution/style entrypoints: no top-level `CONTRIBUTING`, `HACKING`, or `README-hacking` was present; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Ran from workspace root: `./configure && make`. The command completed with exit code 0. The build reported `_ssl` was built but removed because it could not be imported: undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing optional modules.

Independent reproduction attempt: a built-interpreter smoke check using `select.poll().poll(1000)` and `os.wait4(-1, os.WNOHANG)` returned `poll_result []`, `elapsed_seconds 1.001`, and `wait4_error ChildProcessError 10`. That did not reproduce a tight busy loop.

Tried `strace -f -e trace=poll,wait4 ...`, but sandbox ptrace restrictions blocked it: `PTRACE_TRACEME: Operation not permitted`. The workspace is clean after removing build artifacts with `make distclean`.

## Review Pass 1

RESULT: ok

No source diff is present, the workspace is clean, and the no-patch diagnosis matches the evidence limits. The author used a valid `## Evidence Confidence` value, did not overclaim reproduction, attempted the project-level `./configure && make`, reported the `_ssl` optional-module issue clearly, and included a bounded smoke check plus the ptrace blocker for `strace`.

The maintainer-facing explanation reasonably connects the observed perf/strace/`/proc` signal to an application-level `supervisord` polling cadence rather than a demonstrated CPython runtime bug.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord` with high sampled CPU, but the available strace excerpt shows a one-second cadence: `poll(..., 1000)` timing out, followed by `wait4(..., WNOHANG)` returning `ECHILD`. That looks like supervisord’s application loop, not a tight CPython runtime loop.

## Evidence Confidence
observed

## Proposed Subject
No CPython source patch: diagnose this as an application-level supervisord polling signal that is not currently tied to a reproducible Python 3.13 runtime defect.

## Patch Plan
Do not edit files for this finding unless extra evidence connects the behavior to CPython. The raw investigation files referenced by `evidence.json` are unavailable, `/usr/bin/supervisord` and the `supervisor` module are not installed in this workspace, and a cheap local sanity check showed `select.poll(100)` blocking for about 100 ms and `os.wait4(-1, os.WNOHANG)` raising `ChildProcessError` normally.

Checked upstream conventions/docs: `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. No top-level `CONTRIBUTING`/`HACKING` file was present. Relevant local helper conventions in the scanned subsystem are `Py_BEGIN_ALLOW_THREADS`/`Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, `_PyTime_*` deadline helpers, and CPython allocator families such as `PyMem_RawMalloc`/`PyMem_RawFree`; no relevant local helper suggests adding throttling inside CPython for this evidence.

No prior Fixer patch was found in the workspace; the Debian source snapshot only differs by job metadata directories.

## Risks
The main risk is misattribution: patching CPython based on a profiler-only sample could alter `poll`, `wait4`, subprocess, or thread behavior without a demonstrated interpreter bug. Any timing/throttling change would be security-sensitive enough to require a real reproducer and impact analysis first.

## Validation
If later evidence justifies a CPython patch, first try the project-level entrypoint from the workspace root:

`./configure && make`

Then run the narrowest relevant CPython test, likely `./python -m test test_select test_os test_subprocess`, depending on the touched code. For the current no-patch diagnosis, the bounded independent check is the local `python3.13` sanity script for `select.poll(100)` and `os.wait4(-1, os.WNOHANG)`, which did not reproduce the reported runaway signal.

## Patch Pass

Subject: Diagnose supervisord polling profile without CPython changes

## Commit Message
No source change is proposed. The collected signal points at a `supervisord` event loop running under Python, not at a demonstrated CPython runtime defect. The saved plan recommended a no-patch diagnosis; I followed that direction and classified the final confidence as `inferred` because the remaining evidence is profiler/strace-based and not independently reproduced.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a perf/strace investigation for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`. The signal included high sampled CPU, but `/proc` showed the process sleeping in `poll_schedule_timeout`, and strace showed repeated `poll(..., 1000)` calls that each blocked for about one second, followed by `wait4(..., WNOHANG)` returning `ECHILD`.

The cautious code-level inference is that this is supervisord’s application-level polling cadence, not a tight CPython busy loop. The scanned CPython paths for `os.wait4()` and `select.poll.poll()` use the normal local conventions: `Py_BEGIN_ALLOW_THREADS`/`Py_END_ALLOW_THREADS`, `PyErr_CheckSignals()`, and `_PyTime_*` timeout handling. No relevant local helper or wrapper was missing.

I made no source change. The expected effect is no runtime behavior change; this avoids landing a speculative timing/throttling patch in CPython without reproduced evidence or security-impact analysis.

## Git Add Paths
None

## Validation
Checked contribution/style entrypoints: no top-level `CONTRIBUTING`, `HACKING`, or `README-hacking` was present; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Ran from workspace root: `./configure && make`. The command completed with exit code 0. The build reported `_ssl` was built but removed because it could not be imported: undefined symbol `TLSv1_method`; `_dbm`, `_gdbm`, and `_tkinter` were missing optional modules.

Independent reproduction attempt: a built-interpreter smoke check using `select.poll().poll(1000)` and `os.wait4(-1, os.WNOHANG)` returned `poll_result []`, `elapsed_seconds 1.001`, and `wait4_error ChildProcessError 10`. That did not reproduce a tight busy loop.

Tried `strace -f -e trace=poll,wait4 ...`, but sandbox ptrace restrictions blocked it: `PTRACE_TRACEME: Operation not permitted`. The workspace is clean after removing build artifacts with `make distclean`.

## Review Pass 1

RESULT: ok

No source diff is present, the workspace is clean, and the no-patch diagnosis matches the evidence limits. The author used a valid `## Evidence Confidence` value, did not overclaim reproduction, attempted the project-level `./configure && make`, reported the `_ssl` optional-module issue clearly, and included a bounded smoke check plus the ptrace blocker for `strace`.

The maintainer-facing explanation reasonably connects the observed perf/strace/`/proc` signal to an application-level `supervisord` polling cadence rather than a demonstrated CPython runtime bug.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/importlib/__pycache__/_abc.cpython-313.pyc, Lib/logging/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/_abc.cpython-313.pyc, Lib/pathlib/__pycache__/_local.cpython-313.pyc, Lib/re/__pycache__/__init__.cpython-313.pyc, Lib/re/__pycache__/_casefix.cpython-313.pyc, Lib/re/__pycache__/_compiler.cpython-313.pyc, Lib/re/__pycache__/_constants.cpyth

[truncated 29270 bytes]

Response

## Plan Pass

## Problem
Fixer attributed high CPU/runaway behavior to `python3.13`, but the evidence is process-level and indirect. The recorded command line is an application entrypoint (`/usr/bin/python3 /usr/bin/supervisord ...` in `evidence.json`), while the mounted investigation for the same `python3.13` fingerprint shows a user module (`home_audio_mesh.ml.live_enricher`) sleeping or supervising child work. The strace evidence includes blocking `poll(..., 1000)` calls and the mounted backtrace shows `time.sleep(10)`, not a CPython tight loop.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch: diagnose this as insufficient evidence for an upstream `python3.13` runtime bug and reject a speculative interpreter change.

## Patch Plan
Do not edit CPython in this pass. A source patch would not clearly address the observed signal because the evidence points to application scheduling/supervision behavior around `poll`, `wait4`, child processes, and `time.sleep`, rather than a faulty runtime loop.

If later evidence isolates a CPython runtime bug, inspect the specific runtime subsystem first. Relevant local conventions/helpers found: `README.rst` points contributors to the CPython Developer Guide and uses `./configure`, `make`, `make test`; blocking syscall code uses `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_*` conversion/deadline helpers, and `PyErr_CheckSignals()` for EINTR handling, as seen in `Modules/selectmodule.c` and `Modules/timemodule.c`. No relevant file IO/path/process wrapper needs to be introduced for the current evidence. Avoid awkward control flow such as avoidable `goto`; the existing bounded retry loops are the local style.

No prior Fixer patch or dirty workspace change was found to improve or replace.

## Risks
The main risk is mispatching CPython based on profiler attribution from a hosted Python application. Changing `select.poll`, `time.sleep`, `subprocess`, or interpreter entrypoint behavior without a reproducer could regress normal blocking semantics, signal handling, or child-process waiting.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root: `./configure && make`. If it fails due to missing dependencies or generated files, record the exact failure and then use the narrowest reproducible check available.

For the independent bounded signal check after a successful build: run a small `strace` smoke test such as `timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'` and, separately, a child-process wait smoke test using `subprocess`. These can show normal blocking behavior, but they should not be reported as reproducing the Fixer runaway unless they actually demonstrate the high-CPU loop.

## Patch Pass

Subject: Diagnose python3.13 profiler attribution as application wait loop

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` data point to CPython hosting an application loop, not to a CPython runtime spin: the sampled process is sleeping in `poll_schedule_timeout`, strace shows one-second `poll()` waits, and an available matching investigation shows `time.sleep()`.

I followed `plan-output.txt` and did not change course. A CPython patch would be speculative without stronger evidence that `select`, `subprocess`, `time.sleep`, or interpreter startup is misbehaving.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a `python3.13` process classified as runaway CPU, with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, repeated `wait4(..., WNOHANG) = ECHILD`, and `poll(..., 1000)` calls. The `/proc` evidence says the process was sleeping, with `wchan` at `poll_schedule_timeout`, and the strace time deltas show the `poll()` calls timing out after about one second rather than returning immediately.

The cautious code-level inference is that CPython is only the host process for an application or supervisor polling loop. Nearby CPython code already uses the expected blocking helpers and conventions: `select.poll()` releases the GIL with `Py_BEGIN_ALLOW_THREADS`, recomputes timeouts with `_PyTime_*` and `_PyDeadline_*`, and checks signals with `PyErr_CheckSignals()`; `time.sleep()` similarly blocks in `clock_nanosleep` when available. I found no relevant local helper that would justify a small upstream runtime change.

The specific change made is no source diff. The expected effect is to avoid an upstream-inappropriate CPython patch and leave a diagnosis suitable for redirecting the report toward the supervised Python application or the profiling attribution logic.

## Git Add Paths
None

## Validation
Checked contribution/style context before deciding not to patch: no root `CONTRIBUTING`, `HACKING`, `README-hacking`, `docs/`, or `dev-docs/` match was found by the requested names; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Ran project-level entrypoint from workspace root:

`./configure && make`

Result: exited 0 and produced `./python`. The build log reported `_ssl` was removed because it failed to import with `undefined symbol: TLSv1_method`, plus missing optional `_dbm`, `_gdbm`, and `_tkinter`; this did not block the local interpreter smoke checks and is unrelated to the poll/sleep evidence.

Independent reproduction attempt:

`timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'`

Result: blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`. I did not reproduce the collected syscall trace locally.

Narrow smoke checks:

`/usr/bin/time -f 'elapsed=%e user=%U sys=%S cpu=%P' ./python -c 'import time; time.sleep(2)'`

Result: `elapsed=2.00 user=0.00 sys=0.00 cpu=0%`.

`./python -c 'import select, time; p = select.poll(); t = time.monotonic(); p.poll(1000); print(round(time.monotonic() - t, 2))'`

Result: `1.0`.

`./python -c 'import subprocess, sys; p = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(0.2)"], stdout=subprocess.PIPE, stderr=subprocess.PIPE); out, err = p.communicate(timeout=5); print(p.returncode, len(out), len(err))'`

Result: `0 0 0`.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: Diagnose python3.13 profiler attribution as application wait loop

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` data point to CPython hosting an application wait loop, not to a CPython runtime spin. The review finding was metadata drift from generated build products, so I removed those artifacts and kept the proposal as a clean no-patch diagnosis.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a `python3.13` process classified as runaway CPU, with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, repeated `wait4(..., WNOHANG) = ECHILD`, and `poll(..., 1000)` calls. The `/proc` evidence says the process was sleeping in `poll_schedule_timeout`, and the strace timing shows one-second `poll()` timeouts rather than immediate returns.

The cautious code-level inference is that CPython is only the host process for an application or supervisor polling loop. The relevant CPython blocking paths already use local conventions: `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_*` and `_PyDeadline_*` timeout helpers, and `PyErr_CheckSignals()` for interrupted waits. No relevant local helper was missing, and no source patch is pull-request-ready from this indirect evidence.

The specific refinement change was to remove unintended generated build artifacts left by validation. The expected effect is a clean workspace with `Git Add Paths: None`, preserving the no-patch upstream diagnosis instead of accidentally proposing build products.

## Git Add Paths
None

## Validation
Reviewed the requested inputs: `evidence.json`, `plan-output.txt`, `patch-output.txt`, and `review-1-output.txt`. The review finding addressed was patch metadata drift from generated build artifacts.

Checked contribution/style context: no root `CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, or `dev-docs/` entry matched the requested names; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Cleanup validation:
`make distclean` exited 0 and removed generated build artifacts.
`git status --short` produced no output after cleanup.

Prior project-level validation from this proposal remains the relevant build check because no source changed in refinement:
`./configure && make` exited 0. It reported `_ssl` removed due to `undefined symbol: TLSv1_method`, and missing optional `_dbm`, `_gdbm`, and `_tkinter`.

Independent reproduction attempt from the prior pass:
`timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'`
was blocked by ptrace restrictions: `Operation not permitted`.

Prior smoke checks showed normal blocking behavior:
`time.sleep(2)` used `elapsed=2.00 user=0.00 sys=0.00 cpu=0%`.
`select.poll(1000)` measured about `1.0` seconds.
A `subprocess.communicate(timeout=5)` child sleep check returned `0 0 0`.

## Review Pass 2

RESULT: ok

No source diff is present and `git status --short` is clean, so the prior metadata drift from generated build artifacts is resolved.

The refined response keeps `## Evidence Confidence` as `inferred`, lists `Git Add Paths` as `None`, and does not overclaim a reproduced CPython bug. The no-patch diagnosis is consistent with the evidence: the traces show sleeping/blocking poll behavior and indirect process-level attribution rather than an isolated CPython runtime defect. Validation and the ptrace blocker are reported clearly.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1 (local metadata check)

Local metadata consistency check

## Refinement Pass 1

You are refining a fixer patch after an explicit code review.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Read the latest author response at `./patch-output.txt`. Read the review report at `./review-1-output.txt`. This is refinement round 1. The original pre-edit snapshot is available at `./source` if you need to compare the current patch against it. Re-read the planning pass at `./plan-output.txt` before editing. The workspace currently changes these repo-relative paths: Lib/__pycache__/__future__.cpython-313.pyc, Lib/__pycache__/_collections_abc.cpython-313.pyc, Lib/__pycache__/_colorize.cpython-313.pyc, Lib/__pycache__/_compat_pickle.cpython-313.pyc, Lib/__pycache__/_compression.cpython-313.pyc, Lib/__pycache__/_opcode_metadata.cpython-313.pyc, Lib/__pycache__/_sitebuiltins.cpython-313.pyc, Lib/__pycache__/_weakrefset.cpython-313.pyc, Lib/__pycache__/abc.cpython-313.pyc, Lib/__pycache__/argparse.cpython-313.pyc, Lib/__pycache__/ast.cpython-313.pyc, Lib/__pycache__/bz2.cpython-313.pyc, Lib/__pycache__/codecs.cpython-313.pyc, Lib/__pycache__/contextlib.cpython-313.pyc, Lib/__pycache__/contextvars.cpython-313.pyc, Lib/__pycache__/copy.cpython-313.pyc, Lib/__pycache__/copyreg.cpython-313.pyc, Lib/__pycache__/datetime.cpython-313.pyc, Lib/__pycache__/dis.cpython-313.pyc, Lib/__pycache__/enum.cpython-313.pyc, Lib/__pycache__/fnmatch.cpython-313.pyc, Lib/__pycache__/functools.cpython-313.pyc, Lib/__pycache__/genericpath.cpython-313.pyc, Lib/__pycache__/gettext.cpython-313.pyc, Lib/__pycache__/glob.cpython-313.pyc, Lib/__pycache__/heapq.cpython-313.pyc, Lib/__pycache__/inspect.cpython-313.pyc, Lib/__pycache__/io.cpython-313.pyc, Lib/__pycache__/keyword.cpython-313.pyc, Lib/__pycache__/linecache.cpython-313.pyc, Lib/__pycache__/locale.cpython-313.pyc, Lib/__pycache__/lzma.cpython-313.pyc, Lib/__pycache__/numbers.cpython-313.pyc, Lib/__pycache__/opcode.cpython-313.pyc, Lib/__pycache__/operator.cpython-313.pyc, Lib/__pycache__/os.cpython-313.pyc, Lib/__pycache__/posixpath.cpython-313.pyc, Lib/__pycache__/reprlib.cpython-313.pyc, Lib/__pycache__/selectors.cpython-313.pyc, Lib/__pycache__/shutil.cpython-313.pyc, Lib/__pycache__/signal.cpython-313.pyc, Lib/__pycache__/site.cpython-313.pyc, Lib/__pycache__/socket.cpython-313.pyc, Lib/__pycache__/ssl.cpython-313.pyc, Lib/__pycache__/stat.cpython-313.pyc, Lib/__pycache__/string.cpython-313.pyc, Lib/__pycache__/struct.cpython-313.pyc, Lib/__pycache__/subprocess.cpython-313.pyc, Lib/__pycache__/textwrap.cpython-313.pyc, Lib/__pycache__/threading.cpython-313.pyc, Lib/__pycache__/token.cpython-313.pyc, Lib/__pycache__/tokenize.cpython-313.pyc, Lib/__pycache__/traceback.cpython-313.pyc, Lib/__pycache__/types.cpython-313.pyc, Lib/__pycache__/typing.cpython-313.pyc, Lib/__pycache__/warnings.cpython-313.pyc, Lib/__pycache__/weakref.cpython-313.pyc, Lib/asyncio/__pycache__/__init__.cpython-313.pyc, Lib/asyncio/__pycache__/base_events.cpython-313.pyc, Lib/asyncio/__pycache__/base_futures.cpython-313.pyc, Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc, Lib/asyncio/__pycache__/constants.cpython-313.pyc, Lib/asyncio/__pycache__/coroutines.cpython-313.pyc, Lib/asyncio/__pycache__/events.cpython-313.pyc, Lib/asyncio/__pycache__/exceptions.cpython-313.pyc, Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc, Lib/asyncio/__pycache__/futures.cpython-313.pyc, Lib/asyncio/__pycache__/locks.cpython-313.pyc, Lib/asyncio/__pycache__/log.cpython-313.pyc, Lib/asyncio/__pycache__/mixins.cpython-313.pyc, Lib/asyncio/__pycache__/protocols.cpython-313.pyc, Lib/asyncio/__pycache__/queues.cpython-313.pyc, Lib/asyncio/__pycache__/runners.cpython-313.pyc, Lib/asyncio/__pycache__/selector_events.cpython-313.pyc, Lib/asyncio/__pycache__/sslproto.cpython-313.pyc, Lib/asyncio/__pycache__/staggered.cpython-313.pyc, Lib/asyncio/__pycache__/streams.cpython-313.pyc, Lib/asyncio/__pycache__/subprocess.cpython-313.pyc, Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc, Lib/asyncio/__pycache__/tasks.cpython-313.pyc, Lib/asyncio/__pycache__/threads.cpython-313.pyc, Lib/asyncio/__pycache__/timeouts.cpython-313.pyc, Lib/asyncio/__pycache__/transports.cpython-313.pyc, Lib/asyncio/__pycache__/trsock.cpython-313.pyc, Lib/asyncio/__pycache__/unix_events.cpython-313.pyc, Lib/collections/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc, Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc, Lib/encodings/__pycache__/__init__.cpython-313.pyc, Lib/encodings/__pycache__/aliases.cpython-313.pyc, Lib/encodings/__pycache__/ascii.cpython-313.pyc, Lib/encodings/__pycache__/utf_8.cpython-313.pyc, Lib/importlib/__pycache__/__init__.cpython-313.pyc, Lib/importlib/__pycache__/_abc.cpython-313.pyc, Lib/logging/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/__init__.cpython-313.pyc, Lib/pathlib/__pycache__/_abc.cpython-313.pyc, Lib/pathlib/__pycache__/_local.cpython-313.pyc, Lib/re/__pycache__/__init__.cpython-313.pyc, Lib/re/__pycache__/_casefix.cpython-313.pyc, Lib/re/__pycache__/_compiler.cpython-313.pyc, Lib/re/__pycache__/_constants.cpyth

[truncated 29270 bytes]

Response

## Plan Pass

## Problem
Fixer attributed high CPU/runaway behavior to `python3.13`, but the evidence is process-level and indirect. The recorded command line is an application entrypoint (`/usr/bin/python3 /usr/bin/supervisord ...` in `evidence.json`), while the mounted investigation for the same `python3.13` fingerprint shows a user module (`home_audio_mesh.ml.live_enricher`) sleeping or supervising child work. The strace evidence includes blocking `poll(..., 1000)` calls and the mounted backtrace shows `time.sleep(10)`, not a CPython tight loop.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch: diagnose this as insufficient evidence for an upstream `python3.13` runtime bug and reject a speculative interpreter change.

## Patch Plan
Do not edit CPython in this pass. A source patch would not clearly address the observed signal because the evidence points to application scheduling/supervision behavior around `poll`, `wait4`, child processes, and `time.sleep`, rather than a faulty runtime loop.

If later evidence isolates a CPython runtime bug, inspect the specific runtime subsystem first. Relevant local conventions/helpers found: `README.rst` points contributors to the CPython Developer Guide and uses `./configure`, `make`, `make test`; blocking syscall code uses `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_*` conversion/deadline helpers, and `PyErr_CheckSignals()` for EINTR handling, as seen in `Modules/selectmodule.c` and `Modules/timemodule.c`. No relevant file IO/path/process wrapper needs to be introduced for the current evidence. Avoid awkward control flow such as avoidable `goto`; the existing bounded retry loops are the local style.

No prior Fixer patch or dirty workspace change was found to improve or replace.

## Risks
The main risk is mispatching CPython based on profiler attribution from a hosted Python application. Changing `select.poll`, `time.sleep`, `subprocess`, or interpreter entrypoint behavior without a reproducer could regress normal blocking semantics, signal handling, or child-process waiting.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root: `./configure && make`. If it fails due to missing dependencies or generated files, record the exact failure and then use the narrowest reproducible check available.

For the independent bounded signal check after a successful build: run a small `strace` smoke test such as `timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'` and, separately, a child-process wait smoke test using `subprocess`. These can show normal blocking behavior, but they should not be reported as reproducing the Fixer runaway unless they actually demonstrate the high-CPU loop.

## Patch Pass

Subject: Diagnose python3.13 profiler attribution as application wait loop

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` data point to CPython hosting an application loop, not to a CPython runtime spin: the sampled process is sleeping in `poll_schedule_timeout`, strace shows one-second `poll()` waits, and an available matching investigation shows `time.sleep()`.

I followed `plan-output.txt` and did not change course. A CPython patch would be speculative without stronger evidence that `select`, `subprocess`, `time.sleep`, or interpreter startup is misbehaving.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a `python3.13` process classified as runaway CPU, with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, repeated `wait4(..., WNOHANG) = ECHILD`, and `poll(..., 1000)` calls. The `/proc` evidence says the process was sleeping, with `wchan` at `poll_schedule_timeout`, and the strace time deltas show the `poll()` calls timing out after about one second rather than returning immediately.

The cautious code-level inference is that CPython is only the host process for an application or supervisor polling loop. Nearby CPython code already uses the expected blocking helpers and conventions: `select.poll()` releases the GIL with `Py_BEGIN_ALLOW_THREADS`, recomputes timeouts with `_PyTime_*` and `_PyDeadline_*`, and checks signals with `PyErr_CheckSignals()`; `time.sleep()` similarly blocks in `clock_nanosleep` when available. I found no relevant local helper that would justify a small upstream runtime change.

The specific change made is no source diff. The expected effect is to avoid an upstream-inappropriate CPython patch and leave a diagnosis suitable for redirecting the report toward the supervised Python application or the profiling attribution logic.

## Git Add Paths
None

## Validation
Checked contribution/style context before deciding not to patch: no root `CONTRIBUTING`, `HACKING`, `README-hacking`, `docs/`, or `dev-docs/` match was found by the requested names; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Ran project-level entrypoint from workspace root:

`./configure && make`

Result: exited 0 and produced `./python`. The build log reported `_ssl` was removed because it failed to import with `undefined symbol: TLSv1_method`, plus missing optional `_dbm`, `_gdbm`, and `_tkinter`; this did not block the local interpreter smoke checks and is unrelated to the poll/sleep evidence.

Independent reproduction attempt:

`timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'`

Result: blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`. I did not reproduce the collected syscall trace locally.

Narrow smoke checks:

`/usr/bin/time -f 'elapsed=%e user=%U sys=%S cpu=%P' ./python -c 'import time; time.sleep(2)'`

Result: `elapsed=2.00 user=0.00 sys=0.00 cpu=0%`.

`./python -c 'import select, time; p = select.poll(); t = time.monotonic(); p.poll(1000); print(round(time.monotonic() - t, 2))'`

Result: `1.0`.

`./python -c 'import subprocess, sys; p = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(0.2)"], stdout=subprocess.PIPE, stderr=subprocess.PIPE); out, err = p.communicate(timeout=5); print(p.returncode, len(out), len(err))'`

Result: `0 0 0`.

## Review Pass 1 (local metadata check)

RESULT: fix-needed

## Findings
1. Patch metadata drift: the workspace currently changes `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`, but `## Git Add Paths` lists `None`. Update `## Git Add Paths` to match the real shipped file set exactly, and make sure `## Issue Connection` explains every functional file that remains in the patch.
2. Missing from `## Git Add Paths`: `Lib/__pycache__/__future__.cpython-313.pyc`, `Lib/__pycache__/_collections_abc.cpython-313.pyc`, `Lib/__pycache__/_colorize.cpython-313.pyc`, `Lib/__pycache__/_compat_pickle.cpython-313.pyc`, `Lib/__pycache__/_compression.cpython-313.pyc`, `Lib/__pycache__/_opcode_metadata.cpython-313.pyc`, `Lib/__pycache__/_sitebuiltins.cpython-313.pyc`, `Lib/__pycache__/_weakrefset.cpython-313.pyc`, `Lib/__pycache__/abc.cpython-313.pyc`, `Lib/__pycache__/argparse.cpython-313.pyc`, `Lib/__pycache__/ast.cpython-313.pyc`, `Lib/__pycache__/bz2.cpython-313.pyc`, `Lib/__pycache__/codecs.cpython-313.pyc`, `Lib/__pycache__/contextlib.cpython-313.pyc`, `Lib/__pycache__/contextvars.cpython-313.pyc`, `Lib/__pycache__/copy.cpython-313.pyc`, `Lib/__pycache__/copyreg.cpython-313.pyc`, `Lib/__pycache__/datetime.cpython-313.pyc`, `Lib/__pycache__/dis.cpython-313.pyc`, `Lib/__pycache__/enum.cpython-313.pyc`, `Lib/__pycache__/fnmatch.cpython-313.pyc`, `Lib/__pycache__/functools.cpython-313.pyc`, `Lib/__pycache__/genericpath.cpython-313.pyc`, `Lib/__pycache__/gettext.cpython-313.pyc`, `Lib/__pycache__/glob.cpython-313.pyc`, `Lib/__pycache__/heapq.cpython-313.pyc`, `Lib/__pycache__/inspect.cpython-313.pyc`, `Lib/__pycache__/io.cpython-313.pyc`, `Lib/__pycache__/keyword.cpython-313.pyc`, `Lib/__pycache__/linecache.cpython-313.pyc`, `Lib/__pycache__/locale.cpython-313.pyc`, `Lib/__pycache__/lzma.cpython-313.pyc`, `Lib/__pycache__/numbers.cpython-313.pyc`, `Lib/__pycache__/opcode.cpython-313.pyc`, `Lib/__pycache__/operator.cpython-313.pyc`, `Lib/__pycache__/os.cpython-313.pyc`, `Lib/__pycache__/posixpath.cpython-313.pyc`, `Lib/__pycache__/reprlib.cpython-313.pyc`, `Lib/__pycache__/selectors.cpython-313.pyc`, `Lib/__pycache__/shutil.cpython-313.pyc`, `Lib/__pycache__/signal.cpython-313.pyc`, `Lib/__pycache__/site.cpython-313.pyc`, `Lib/__pycache__/socket.cpython-313.pyc`, `Lib/__pycache__/ssl.cpython-313.pyc`, `Lib/__pycache__/stat.cpython-313.pyc`, `Lib/__pycache__/string.cpython-313.pyc`, `Lib/__pycache__/struct.cpython-313.pyc`, `Lib/__pycache__/subprocess.cpython-313.pyc`, `Lib/__pycache__/textwrap.cpython-313.pyc`, `Lib/__pycache__/threading.cpython-313.pyc`, `Lib/__pycache__/token.cpython-313.pyc`, `Lib/__pycache__/tokenize.cpython-313.pyc`, `Lib/__pycache__/traceback.cpython-313.pyc`, `Lib/__pycache__/types.cpython-313.pyc`, `Lib/__pycache__/typing.cpython-313.pyc`, `Lib/__pycache__/warnings.cpython-313.pyc`, `Lib/__pycache__/weakref.cpython-313.pyc`, `Lib/asyncio/__pycache__/__init__.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/base_tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/constants.cpython-313.pyc`, `Lib/asyncio/__pycache__/coroutines.cpython-313.pyc`, `Lib/asyncio/__pycache__/events.cpython-313.pyc`, `Lib/asyncio/__pycache__/exceptions.cpython-313.pyc`, `Lib/asyncio/__pycache__/format_helpers.cpython-313.pyc`, `Lib/asyncio/__pycache__/futures.cpython-313.pyc`, `Lib/asyncio/__pycache__/locks.cpython-313.pyc`, `Lib/asyncio/__pycache__/log.cpython-313.pyc`, `Lib/asyncio/__pycache__/mixins.cpython-313.pyc`, `Lib/asyncio/__pycache__/protocols.cpython-313.pyc`, `Lib/asyncio/__pycache__/queues.cpython-313.pyc`, `Lib/asyncio/__pycache__/runners.cpython-313.pyc`, `Lib/asyncio/__pycache__/selector_events.cpython-313.pyc`, `Lib/asyncio/__pycache__/sslproto.cpython-313.pyc`, `Lib/asyncio/__pycache__/staggered.cpython-313.pyc`, `Lib/asyncio/__pycache__/streams.cpython-313.pyc`, `Lib/asyncio/__pycache__/subprocess.cpython-313.pyc`, `Lib/asyncio/__pycache__/taskgroups.cpython-313.pyc`, `Lib/asyncio/__pycache__/tasks.cpython-313.pyc`, `Lib/asyncio/__pycache__/threads.cpython-313.pyc`, `Lib/asyncio/__pycache__/timeouts.cpython-313.pyc`, `Lib/asyncio/__pycache__/transports.cpython-313.pyc`, `Lib/asyncio/__pycache__/trsock.cpython-313.pyc`, `Lib/asyncio/__pycache__/unix_events.cpython-313.pyc`, `Lib/collections/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/__init__.cpython-313.pyc`, `Lib/concurrent/futures/__pycache__/_base.cpython-313.pyc`, `Lib/encodings/__pycache__/__init__.cpython-313.pyc`, `Lib/encodings/__pycache__/aliases.cpython-313.pyc`, `Lib/encodings/__pycache__/ascii.cpython-313.pyc`, `Lib/encodings/__pycache__/utf_8.cpython-313.pyc`, `Lib/importlib/__pycache__/__init__.cpython-313.pyc`, `Lib/importlib/__pycache__/_abc.cpython-313.pyc`, `Lib/logging/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/__init__.cpython-313.pyc`, `Lib/pathlib/__pycache__/_abc.cpython-313.pyc`, `Lib/pathlib/__pycache__/_local.cpython-313.pyc`, `Lib/re/__pycache__/__init__.cpython-313.pyc`, `Lib/re/__pycache__/_casefix.cpython-313.pyc`, `Lib/re/__pycache__/_compiler.cpython-313.pyc`, `Lib/re/__pycache__/_constants.cpython-313.pyc`, `Lib/re/__pycache__/_parser.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__init__.cpython-313.pyc`, `Lib/sysconfig/__pycache__/__main__.cpython-313.pyc`, `Lib/xml/__pycache__/__init__.cpython-313.pyc`, `Lib/xml/etree/__pycache__/ElementPath.cpython-313.pyc`, `Lib/xml/etree/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/__init__.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_common.cpython-313.pyc`, `Lib/zoneinfo/__pycache__/_tzpath.cpython-313.pyc`, `Makefile`, `Makefile.pre`, `Misc/python-config.sh`, `Misc/python-embed.pc`, `Misc/python.pc`, `Modules/Setup.bootstrap`, `Modules/Setup.local`, `Modules/Setup.stdlib`, `Modules/_abc.o`, `Modules/_asyncio.cpython-313-x86_64-linux-gnu.so`, `Modules/_asynciomodule.o`, `Modules/_bisect.cpython-313-x86_64-linux-gnu.so`, `Modules/_bisectmodule.o`, `Modules/_blake2.cpython-313-x86_64-linux-gnu.so`, `Modules/_blake2/blake2b_impl.o`, `Modules/_blake2/blake2module.o`, `Modules/_blake2/blake2s_impl.o`, `Modules/_bz2.cpython-313-x86_64-linux-gnu.so`, `Modules/_bz2module.o`, `Modules/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `Modules/_codecsmodule.o`, `Modules/_collectionsmodule.o`, `Modules/_contextvars.cpython-313-x86_64-linux-gnu.so`, `Modules/_contextvarsmodule.o`, `Modules/_csv.cpython-313-x86_64-linux-gnu.so`, `Modules/_csv.o`, `Modules/_ctypes.cpython-313-x86_64-linux-gnu.so`, `Modules/_ctypes/_ctypes.o`, `Modules/_ctypes/_ctypes_test.o`, `Modules/_ctypes/callbacks.o`, `Modules/_ctypes/callproc.o`, `Modules/_ctypes/cfield.o`, `Modules/_ctypes/stgdict.o`, `Modules/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `Modules/_curses_panel.o`, `Modules/_cursesmodule.o`, `Modules/_datetime.cpython-313-x86_64-linux-gnu.so`, `Modules/_datetimemodule.o`, `Modules/_decimal.cpython-313-x86_64-linux-gnu.so`, `Modules/_decimal/_decimal.o`, `Modules/_decimal/libmpdec/basearith.o`, `Modules/_decimal/libmpdec/constants.o`, `Modules/_decimal/libmpdec/context.o`, `Modules/_decimal/libmpdec/convolute.o`, `Modules/_decimal/libmpdec/crt.o`, `Modules/_decimal/libmpdec/difradix2.o`, `Modules/_decimal/libmpdec/fnt.o`, `Modules/_decimal/libmpdec/fourstep.o`, `Modules/_decimal/libmpdec/io.o`, `Modules/_decimal/libmpdec/libmpdec.a`, `Modules/_decimal/libmpdec/mpalloc.o`, `Modules/_decimal/libmpdec/mpdecimal.o`, `Modules/_decimal/libmpdec/numbertheory.o`, `Modules/_decimal/libmpdec/sixstep.o`, `Modules/_decimal/libmpdec/transpose.o`, `Modules/_elementtree.cpython-313-x86_64-linux-gnu.so`, `Modules/_elementtree.o`, `Modules/_functoolsmodule.o`, `Modules/_hacl/Hacl_Hash_MD5.o`, `Modules/_hacl/Hacl_Hash_SHA1.o`, `Modules/_hacl/Hacl_Hash_SHA2.o`, `Modules/_hacl/Hacl_Hash_SHA3.o`, `Modules/_hacl/libHacl_Hash_SHA2.a`, `Modules/_hashlib.cpython-313-x86_64-linux-gnu.so`, `Modules/_hashopenssl.o`, `Modules/_heapq.cpython-313-x86_64-linux-gnu.so`, `Modules/_heapqmodule.o`, `Modules/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpchannelsmodule.o`, `Modules/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpqueuesmodule.o`, `Modules/_interpreters.cpython-313-x86_64-linux-gnu.so`, `Modules/_interpretersmodule.o`, `Modules/_io/_iomodule.o`, `Modules/_io/bufferedio.o`, `Modules/_io/bytesio.o`, `Modules/_io/fileio.o`, `Modules/_io/iobase.o`, `Modules/_io/stringio.o`, `Modules/_io/textio.o`, `Modules/_json.cpython-313-x86_64-linux-gnu.so`, `Modules/_json.o`, `Modules/_localemodule.o`, `Modules/_lsprof.cpython-313-x86_64-linux-gnu.so`, `Modules/_lsprof.o`, `Modules/_lzma.cpython-313-x86_64-linux-gnu.so`, `Modules/_lzmamodule.o`, `Modules/_md5.cpython-313-x86_64-linux-gnu.so`, `Modules/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `Modules/_multiprocessing/multiprocessing.o`, `Modules/_multiprocessing/posixshmem.o`, `Modules/_multiprocessing/semaphore.o`, `Modules/_opcode.cpython-313-x86_64-linux-gnu.so`, `Modules/_opcode.o`, `Modules/_operator.o`, `Modules/_pickle.cpython-313-x86_64-linux-gnu.so`, `Modules/_pickle.o`, `Modules/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `Modules/_posixsubprocess.o`, `Modules/_queue.cpython-313-x86_64-linux-gnu.so`, `Modules/_queuemodule.o`, `Modules/_random.cpython-313-x86_64-linux-gnu.so`, `Modules/_randommodule.o`, `Modules/_sha1.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha2.cpython-313-x86_64-linux-gnu.so`, `Modules/_sha3.cpython-313-x86_64-linux-gnu.so`, `Modules/_socket.cpython-313-x86_64-linux-gnu.so`, `Modules/_sqlite/blob.o`, `Modules/_sqlite/connection.o`, `Modules/_sqlite/cursor.o`, `Modules/_sqlite/microprotocols.o`, `Modules/_sqlite/module.o`, `Modules/_sqlite/prepare_protocol.o`, `Modules/_sqlite/row.o`, `Modules/_sqlite/statement.o`, `Modules/_sqlite/util.o`, `Modules/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `Modules/_sre/sre.o`, `Modules/_ssl.o`, `Modules/_ssl_failed.cpython-313-x86_64-linux-gnu.so`, `Modules/_stat.o`, `Modules/_statistics.cpython-313-x86_64-linux-gnu.so`, `Modules/_statisticsmodule.o`, `Modules/_struct.cpython-313-x86_64-linux-gnu.so`, `Modules/_struct.o`, `Modules/_suggestions.o`, `Modules/_sysconfig.o`, `Modules/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `Modules/_testbuffer.o`, `Modules/_testcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testcapi/abstract.o`, `Modules/_testcapi/buffer.o`, `Modules/_testcapi/bytes.o`, `Modules/_testcapi/code.o`, `Modules/_testcapi/codec.o`, `Modules/_testcapi/complex.o`, `Modules/_testcapi/datetime.o`, `Modules/_testcapi/dict.o`, `Modules/_testcapi/docstring.o`, `Modules/_testcapi/exceptions.o`, `Modules/_testcapi/file.o`, `Modules/_testcapi/float.o`, `Modules/_testcapi/gc.o`, `Modules/_testcapi/getargs.o`, `Modules/_testcapi/hash.o`, `Modules/_testcapi/heaptype.o`, `Modules/_testcapi/immortal.o`, `Modules/_testcapi/list.o`, `Modules/_testcapi/long.o`, `Modules/_testcapi/mem.o`, `Modules/_testcapi/monitoring.o`, `Modules/_testcapi/numbers.o`, `Modules/_testcapi/object.o`, `Modules/_testcapi/pyatomic.o`, `Modules/_testcapi/run.o`, `Modules/_testcapi/set.o`, `Modules/_testcapi/structmember.o`, `Modules/_testcapi/time.o`, `Modules/_testcapi/tuple.o`, `Modules/_testcapi/unicode.o`, `Modules/_testcapi/vectorcall.o`, `Modules/_testcapi/watchers.o`, `Modules/_testcapimodule.o`, `Modules/_testclinic.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic.o`, `Modules/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `Modules/_testclinic_limited.o`, `Modules/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `Modules/_testexternalinspection.o`, `Modules/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `Modules/_testimportmultiple.o`, `Modules/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testinternalcapi.o`, `Modules/_testinternalcapi/pytime.o`, `Modules/_testinternalcapi/set.o`, `Modules/_testinternalcapi/test_critical_sections.o`, `Modules/_testinternalcapi/test_lock.o`, `Modules/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `Modules/_testlimitedcapi.o`, `Modules/_testlimitedcapi/abstract.o`, `Modules/_testlimitedcapi/bytearray.o`, `Modules/_testlimitedcapi/bytes.o`, `Modules/_testlimitedcapi/complex.o`, `Modules/_testlimitedcapi/dict.o`, `Modules/_testlimitedcapi/eval.o`, `Modules/_testlimitedcapi/file.o`, `Modules/_testlimitedcapi/float.o`, `Modules/_testlimitedcapi/heaptype_relative.o`, `Modules/_testlimitedcapi/import.o`, `Modules/_testlimitedcapi/list.o`, `Modules/_testlimitedcapi/long.o`, `Modules/_testlimitedcapi/object.o`, `Modules/_testlimitedcapi/pyos.o`, `Modules/_testlimitedcapi/set.o`, `Modules/_testlimitedcapi/sys.o`, `Modules/_testlimitedcapi/tuple.o`, `Modules/_testlimitedcapi/unicode.o`, `Modules/_testlimitedcapi/vectorcall_limited.o`, `Modules/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testmultiphase.o`, `Modules/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `Modules/_testsinglephase.o`, `Modules/_threadmodule.o`, `Modules/_tracemalloc.o`, `Modules/_typingmodule.o`, `Modules/_uuid.cpython-313-x86_64-linux-gnu.so`, `Modules/_uuidmodule.o`, `Modules/_weakref.o`, `Modules/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `Modules/_xxtestfuzz/_xxtestfuzz.o`, `Modules/_xxtestfuzz/fuzzer.o`, `Modules/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `Modules/_zoneinfo.o`, `Modules/array.cpython-313-x86_64-linux-gnu.so`, `Modules/arraymodule.o`, `Modules/atexitmodule.o`, `Modules/binascii.cpython-313-x86_64-linux-gnu.so`, `Modules/binascii.o`, `Modules/cjkcodecs/_codecs_cn.o`, `Modules/cjkcodecs/_codecs_hk.o`, `Modules/cjkcodecs/_codecs_iso2022.o`, `Modules/cjkcodecs/_codecs_jp.o`, `Modules/cjkcodecs/_codecs_kr.o`, `Modules/cjkcodecs/_codecs_tw.o`, `Modules/cjkcodecs/multibytecodec.o`, `Modules/cmath.cpython-313-x86_64-linux-gnu.so`, `Modules/cmathmodule.o`, `Modules/config.c`, `Modules/config.o`, `Modules/errnomodule.o`, `Modules/expat/libexpat.a`, `Modules/expat/xmlparse.o`, `Modules/expat/xmlrole.o`, `Modules/expat/xmltok.o`, `Modules/faulthandler.o`, `Modules/fcntl.cpython-313-x86_64-linux-gnu.so`, `Modules/fcntlmodule.o`, `Modules/gcmodule.o`, `Modules/getbuildinfo.o`, `Modules/getpath.o`, `Modules/getpath_noop.o`, `Modules/grp.cpython-313-x86_64-linux-gnu.so`, `Modules/grpmodule.o`, `Modules/itertoolsmodule.o`, `Modules/ld_so_aix`, `Modules/main.o`, `Modules/math.cpython-313-x86_64-linux-gnu.so`, `Modules/mathmodule.o`, `Modules/md5module.o`, `Modules/mmap.cpython-313-x86_64-linux-gnu.so`, `Modules/mmapmodule.o`, `Modules/posixmodule.o`, `Modules/pwdmodule.o`, `Modules/pyexpat.cpython-313-x86_64-linux-gnu.so`, `Modules/pyexpat.o`, `Modules/readline.cpython-313-x86_64-linux-gnu.so`, `Modules/readline.o`, `Modules/resource.cpython-313-x86_64-linux-gnu.so`, `Modules/resource.o`, `Modules/rotatingtree.o`, `Modules/select.cpython-313-x86_64-linux-gnu.so`, `Modules/selectmodule.o`, `Modules/sha1module.o`, `Modules/sha2module.o`, `Modules/sha3module.o`, `Modules/signalmodule.o`, `Modules/socketmodule.o`, `Modules/symtablemodule.o`, `Modules/syslog.cpython-313-x86_64-linux-gnu.so`, `Modules/syslogmodule.o`, `Modules/termios.cpython-313-x86_64-linux-gnu.so`, `Modules/termios.o`, `Modules/timemodule.o`, `Modules/unicodedata.cpython-313-x86_64-linux-gnu.so`, `Modules/unicodedata.o`, `Modules/xxlimited.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited.o`, `Modules/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `Modules/xxlimited_35.o`, `Modules/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `Modules/xxsubtype.o`, `Modules/zlib.cpython-313-x86_64-linux-gnu.so`, `Modules/zlibmodule.o`, `Objects/abstract.o`, `Objects/boolobject.o`, `Objects/bytearrayobject.o`, `Objects/bytes_methods.o`, `Objects/bytesobject.o`, `Objects/call.o`, `Objects/capsule.o`, `Objects/cellobject.o`, `Objects/classobject.o`, `Objects/codeobject.o`, `Objects/complexobject.o`, `Objects/descrobject.o`, `Objects/dictobject.o`, `Objects/enumobject.o`, `Objects/exceptions.o`, `Objects/fileobject.o`, `Objects/floatobject.o`, `Objects/frameobject.o`, `Objects/funcobject.o`, `Objects/genericaliasobject.o`, `Objects/genobject.o`, `Objects/iterobject.o`, `Objects/listobject.o`, `Objects/longobject.o`, `Objects/memoryobject.o`, `Objects/methodobject.o`, `Objects/moduleobject.o`, `Objects/namespaceobject.o`, `Objects/object.o`, `Objects/obmalloc.o`, `Objects/odictobject.o`, `Objects/picklebufobject.o`, `Objects/rangeobject.o`, `Objects/setobject.o`, `Objects/sliceobject.o`, `Objects/structseq.o`, `Objects/tupleobject.o`, `Objects/typeobject.o`, `Objects/typevarobject.o`, `Objects/unicodectype.o`, `Objects/unicodeobject.o`, `Objects/unionobject.o`, `Objects/weakrefobject.o`, `Parser/action_helpers.o`, `Parser/lexer/buffer.o`, `Parser/lexer/lexer.o`, `Parser/lexer/state.o`, `Parser/myreadline.o`, `Parser/parser.o`, `Parser/peg_api.o`, `Parser/pegen.o`, `Parser/pegen_errors.o`, `Parser/string_parser.o`, `Parser/token.o`, `Parser/tokenizer/file_tokenizer.o`, `Parser/tokenizer/helpers.o`, `Parser/tokenizer/readline_tokenizer.o`, `Parser/tokenizer/string_tokenizer.o`, `Parser/tokenizer/utf8_tokenizer.o`, `Programs/_bootstrap_python.o`, `Programs/_freeze_module`, `Programs/_freeze_module.o`, `Programs/_testembed`, `Programs/_testembed.o`, `Programs/python.o`, `Python/Python-ast.o`, `Python/Python-tokenize.o`, `Python/_warnings.o`, `Python/asdl.o`, `Python/asm_trampoline.o`, `Python/assemble.o`, `Python/ast.o`, `Python/ast_opt.o`, `Python/ast_unparse.o`, `Python/bltinmodule.o`, `Python/bootstrap_hash.o`, `Python/brc.o`, `Python/ceval.o`, `Python/ceval_gil.o`, `Python/codecs.o`, `Python/compile.o`, `Python/context.o`, `Python/critical_section.o`, `Python/crossinterp.o`, `Python/dtoa.o`, `Python/dynamic_annotations.o`, `Python/dynload_shlib.o`, `Python/errors.o`, `Python/fileutils.o`, `Python/flowgraph.o`, `Python/formatter_unicode.o`, `Python/frame.o`, `Python/frozen.o`, `Python/frozen_modules/__hello__.h`, `Python/frozen_modules/__phello__.h`, `Python/frozen_modules/__phello__.ham.eggs.h`, `Python/frozen_modules/__phello__.ham.h`, `Python/frozen_modules/__phello__.spam.h`, `Python/frozen_modules/_collections_abc.h`, `Python/frozen_modules/_sitebuiltins.h`, `Python/frozen_modules/abc.h`, `Python/frozen_modules/codecs.h`, `Python/frozen_modules/frozen_only.h`, `Python/frozen_modules/genericpath.h`, `Python/frozen_modules/getpath.h`, `Python/frozen_modules/importlib._bootstrap.h`, `Python/frozen_modules/importlib._bootstrap_external.h`, `Python/frozen_modules/importlib.machinery.h`, `Python/frozen_modules/importlib.util.h`, `Python/frozen_modules/io.h`, `Python/frozen_modules/ntpath.h`, `Python/frozen_modules/os.h`, `Python/frozen_modules/posixpath.h`, `Python/frozen_modules/runpy.h`, `Python/frozen_modules/site.h`, `Python/frozen_modules/stat.h`, `Python/frozen_modules/zipimport.h`, `Python/frozenmain.o`, `Python/future.o`, `Python/gc.o`, `Python/gc_free_threading.o`, `Python/gc_gil.o`, `Python/getargs.o`, `Python/getcompiler.o`, `Python/getcopyright.o`, `Python/getopt.o`, `Python/getplatform.o`, `Python/getversion.o`, `Python/hamt.o`, `Python/hashtable.o`, `Python/import.o`, `Python/importdl.o`, `Python/initconfig.o`, `Python/instruction_sequence.o`, `Python/instrumentation.o`, `Python/interpconfig.o`, `Python/intrinsics.o`, `Python/jit.o`, `Python/legacy_tracing.o`, `Python/lock.o`, `Python/marshal.o`, `Python/modsupport.o`, `Python/mysnprintf.o`, `Python/mystrtoul.o`, `Python/object_stack.o`, `Python/optimizer.o`, `Python/optimizer_analysis.o`, `Python/optimizer_symbols.o`, `Python/parking_lot.o`, `Python/pathconfig.o`, `Python/perf_jit_trampoline.o`, `Python/perf_trampoline.o`, `Python/preconfig.o`, `Python/pyarena.o`, `Python/pyctype.o`, `Python/pyfpe.o`, `Python/pyhash.o`, `Python/pylifecycle.o`, `Python/pymath.o`, `Python/pystate.o`, `Python/pystrcmp.o`, `Python/pystrhex.o`, `Python/pystrtod.o`, `Python/pythonrun.o`, `Python/pytime.o`, `Python/qsbr.o`, `Python/specialize.o`, `Python/structmember.o`, `Python/suggestions.o`, `Python/symtable.o`, `Python/sysmodule.o`, `Python/thread.o`, `Python/traceback.o`, `Python/tracemalloc.o`, `_bootstrap_python`, `build/lib.linux-x86_64-3.13/__pycache__/_sysconfigdata__linux_x86_64-linux-gnu.cpython-313.pyc`, `build/lib.linux-x86_64-3.13/_asyncio.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bisect.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_blake2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_bz2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_cn.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_hk.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_iso2022.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_jp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_kr.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_codecs_tw.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_contextvars.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_csv.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_ctypes_test.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_curses_panel.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_datetime.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_decimal.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_elementtree.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_hashlib.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_heapq.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpchannels.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpqueues.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_interpreters.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_json.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lsprof.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_lzma.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_md5.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multibytecodec.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_multiprocessing.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_opcode.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_pickle.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixshmem.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_posixsubprocess.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_queue.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_random.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha1.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha2.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sha3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_socket.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sqlite3.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_statistics.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_struct.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_sysconfigdata__linux_x86_64-linux-gnu.py`, `build/lib.linux-x86_64-3.13/_testbuffer.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testclinic_limited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testexternalinspection.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testimportmultiple.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testinternalcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testlimitedcapi.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testmultiphase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_testsinglephase.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_uuid.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_xxtestfuzz.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/_zoneinfo.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/array.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/binascii.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/cmath.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/fcntl.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/grp.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/math.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/mmap.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/pyexpat.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/readline.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/resource.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/select.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/syslog.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/termios.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/unicodedata.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxlimited_35.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/xxsubtype.cpython-313-x86_64-linux-gnu.so`, `build/lib.linux-x86_64-3.13/zlib.cpython-313-x86_64-linux-gnu.so`, `build/scripts-3.13/idle3.13`, `build/scripts-3.13/pydoc3.13`, `config.log`, `config.status`, `libpython3.13.a`, `platform`, `pybuilddir.txt`, `pyconfig.h`, `python`, `python-config`, `python-config.py`, `python-gdb.py`.
2. Listed in `## Git Add Paths` but not actually changed: `None`.

## Refinement Pass 1

Subject: Diagnose python3.13 profiler attribution as application wait loop

## Commit Message
No source change is proposed. The collected perf, strace, and `/proc` data point to CPython hosting an application wait loop, not to a CPython runtime spin. The review finding was metadata drift from generated build products, so I removed those artifacts and kept the proposal as a clean no-patch diagnosis.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a `python3.13` process classified as runaway CPU, with perf samples in `read_tsc` and `_PyEval_EvalFrameDefault`, repeated `wait4(..., WNOHANG) = ECHILD`, and `poll(..., 1000)` calls. The `/proc` evidence says the process was sleeping in `poll_schedule_timeout`, and the strace timing shows one-second `poll()` timeouts rather than immediate returns.

The cautious code-level inference is that CPython is only the host process for an application or supervisor polling loop. The relevant CPython blocking paths already use local conventions: `Py_BEGIN_ALLOW_THREADS` / `Py_END_ALLOW_THREADS`, `_PyTime_*` and `_PyDeadline_*` timeout helpers, and `PyErr_CheckSignals()` for interrupted waits. No relevant local helper was missing, and no source patch is pull-request-ready from this indirect evidence.

The specific refinement change was to remove unintended generated build artifacts left by validation. The expected effect is a clean workspace with `Git Add Paths: None`, preserving the no-patch upstream diagnosis instead of accidentally proposing build products.

## Git Add Paths
None

## Validation
Reviewed the requested inputs: `evidence.json`, `plan-output.txt`, `patch-output.txt`, and `review-1-output.txt`. The review finding addressed was patch metadata drift from generated build artifacts.

Checked contribution/style context: no root `CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, or `dev-docs/` entry matched the requested names; `README.rst` points to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.

Cleanup validation:
`make distclean` exited 0 and removed generated build artifacts.
`git status --short` produced no output after cleanup.

Prior project-level validation from this proposal remains the relevant build check because no source changed in refinement:
`./configure && make` exited 0. It reported `_ssl` removed due to `undefined symbol: TLSv1_method`, and missing optional `_dbm`, `_gdbm`, and `_tkinter`.

Independent reproduction attempt from the prior pass:
`timeout 15 strace -tt -T -e poll,wait4,clock_nanosleep ./python -c 'import time; time.sleep(2)'`
was blocked by ptrace restrictions: `Operation not permitted`.

Prior smoke checks showed normal blocking behavior:
`time.sleep(2)` used `elapsed=2.00 user=0.00 sys=0.00 cpu=0%`.
`select.poll(1000)` measured about `1.0` seconds.
A `subprocess.communicate(timeout=5)` child sleep check returned `0 0 0`.

## Review Pass 2

RESULT: ok

No source diff is present and `git status --short` is clean, so the prior metadata drift from generated build artifacts is resolved.

The refined response keeps `## Evidence Confidence` as `inferred`, lists `Git Add Paths` as `None`, and does not overclaim a reproduced CPython bug. The no-patch diagnosis is consistent with the evidence: the traces show sleeping/blocking poll behavior and indirect process-level attribution rather than an isolated CPython runtime defect. Validation and the ptrace blocker are reported clearly.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` with high sampled CPU attribution, but the embedded `strace` shows a sleeping one-second loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0 <~1.001s>`. The sampled process state is `S (sleeping)` and `wchan` is `poll_schedule_timeout`, so the evidence does not currently identify a CPython runtime bug.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch yet: diagnose the report as an application-level `supervisord` event loop/profiling attribution issue unless additional evidence shows Python itself spinning or mishandling `poll`, `wait4`, or thread setup.

## Patch Plan
Do not edit files in this pass. Start from the script/application entrypoint evidence, because the command is `supervisord`; treat CPython internals only as a secondary target.

Use the embedded evidence to explain that `select.poll().poll(1000)` timing out once per second and `wait4(..., WNOHANG)` returning `ECHILD` are normal observable syscalls for a supervisor loop with no child to reap. The local CPython wrappers already follow maintainer conventions: `Modules/selectmodule.c` releases the GIL with `Py_BEGIN_ALLOW_THREADS`, recomputes timeouts with `_PyDeadline_Init()` / `_PyDeadline_Get()`, and reports syscall errors with `PyErr_SetFromErrno`; `Modules/posixmodule.c` wraps `wait4()` with `Py_BEGIN_ALLOW_THREADS` and `posix_error()`.

If later artifacts prove an interpreter-side defect, prefer the existing helpers and Argument Clinic-generated entrypoints. Avoid awkward control flow such as avoidable `goto`; the nearby code uses bounded `do { ... } while` retry loops for EINTR, which is the cleaner local pattern here.

No prior Fixer patch is visible in the evidence/workspace that should be improved or replaced.

## Risks
A CPython patch based only on this bundle would be speculative and not pull-request-ready. The backtrace top frame at `pthread_attr_destroy()` is not enough to connect the CPU sample to thread creation; without symbols and the missing raw artifact files, it may be profiler noise or an interrupted frame.

Changing `select.poll`, `os.wait4`, or subprocess polling behavior would risk broad regressions in event loops, child watchers, and process management without evidence that those APIs are wrong.

## Validation
For any later source patch, first try the project-level entrypoint from the workspace root: `./configure && make`. If that fails due to missing dependencies or generated files, record the exact command and failure before running a narrower check.

For this no-patch diagnosis, the bounded independent check would be a clean smoke run with the built interpreter after `make`: run a tiny script under `strace -tt -T` that performs `select.poll().poll(1000)` on a readable-watched fd and `os.wait4(-1, os.WNOHANG)` with no children, confirming it sleeps for about one second and returns/raises normally rather than spinning. If a CPython patch later targets these paths, also run the focused relevant tests, such as `./python -m test test_poll test_wait4 test_subprocess`.

## Patch Pass

Subject: Diagnose supervisord poll evidence without CPython patch

## Commit Message
No source change is proposed. The collected evidence points to `supervisord` periodically calling `wait4(..., WNOHANG)` and then sleeping in `poll(..., 1000)`, not to a CPython busy loop.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a high-CPU Fixer profile for `/usr/bin/python3.13` running `/usr/bin/supervisord`, with samples attributed to kernel `read_tsc` and `_PyEval_EvalFrameDefault`. The `/proc` evidence says the sampled process was sleeping in `poll_schedule_timeout`, and the `strace` excerpt shows `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The likely root cause is a normal supervisor event-loop cadence being classified as a busy-poll loop by indirect profiling evidence. CPython’s local wrappers do not show an actionable defect: `Modules/selectmodule.c` uses `Py_BEGIN_ALLOW_THREADS`, `_PyDeadline_Init()` / `_PyDeadline_Get()`, and `PyErr_SetFromErrno`; `Modules/posixmodule.c` uses Argument Clinic entrypoints, `Py_BEGIN_ALLOW_THREADS`, bounded EINTR retry loops, and `posix_error()`.

I made no source change, following the saved plan. The expected effect is to avoid an upstream CPython patch that would change broad `poll` or `wait4` behavior without reproduced evidence of a runtime bug.

## Git Add Paths
None

## Validation
Read contribution/build guidance in `README.rst`; it points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. No new helper APIs were introduced.

Ran the project-level entrypoint from the workspace root:

`./configure && make`

Result: command exited successfully. Build output reported optional module issues: `_ssl failed to import: ... undefined symbol: TLSv1_method`, `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` was removed after import failure. These are optional-module environment issues and not related to `poll`/`wait4`.

Attempted bounded syscall reproduction:

`strace -tt -T -e trace=poll,wait4 ./python - <<'PY' ...`

Blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran the same smoke behavior without `strace` using the built interpreter:

`./python - <<'PY' ...`

Result: `os.wait4(-1, os.WNOHANG)` raised `ChildProcessError`, `select.poll().poll(1000)` returned `[]`, and elapsed time was `1.001` seconds. This matches a sleeping one-second poll timeout, not an independently reproduced busy loop.

## Review Pass 1

RESULT: ok

No findings. The workspace is clean, `## Evidence Confidence` is valid and appropriately `inferred`, no speculative source diff was left, and the diagnosis stays within the profiler/strace evidence. Validation includes the project-level `./configure && make`, the ptrace blocker for syscall reproduction, and a narrower smoke check showing one-second `poll` sleep behavior.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` with high sampled CPU attribution, but the embedded `strace` shows a sleeping one-second loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0 <~1.001s>`. The sampled process state is `S (sleeping)` and `wchan` is `poll_schedule_timeout`, so the evidence does not currently identify a CPython runtime bug.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch yet: diagnose the report as an application-level `supervisord` event loop/profiling attribution issue unless additional evidence shows Python itself spinning or mishandling `poll`, `wait4`, or thread setup.

## Patch Plan
Do not edit files in this pass. Start from the script/application entrypoint evidence, because the command is `supervisord`; treat CPython internals only as a secondary target.

Use the embedded evidence to explain that `select.poll().poll(1000)` timing out once per second and `wait4(..., WNOHANG)` returning `ECHILD` are normal observable syscalls for a supervisor loop with no child to reap. The local CPython wrappers already follow maintainer conventions: `Modules/selectmodule.c` releases the GIL with `Py_BEGIN_ALLOW_THREADS`, recomputes timeouts with `_PyDeadline_Init()` / `_PyDeadline_Get()`, and reports syscall errors with `PyErr_SetFromErrno`; `Modules/posixmodule.c` wraps `wait4()` with `Py_BEGIN_ALLOW_THREADS` and `posix_error()`.

If later artifacts prove an interpreter-side defect, prefer the existing helpers and Argument Clinic-generated entrypoints. Avoid awkward control flow such as avoidable `goto`; the nearby code uses bounded `do { ... } while` retry loops for EINTR, which is the cleaner local pattern here.

No prior Fixer patch is visible in the evidence/workspace that should be improved or replaced.

## Risks
A CPython patch based only on this bundle would be speculative and not pull-request-ready. The backtrace top frame at `pthread_attr_destroy()` is not enough to connect the CPU sample to thread creation; without symbols and the missing raw artifact files, it may be profiler noise or an interrupted frame.

Changing `select.poll`, `os.wait4`, or subprocess polling behavior would risk broad regressions in event loops, child watchers, and process management without evidence that those APIs are wrong.

## Validation
For any later source patch, first try the project-level entrypoint from the workspace root: `./configure && make`. If that fails due to missing dependencies or generated files, record the exact command and failure before running a narrower check.

For this no-patch diagnosis, the bounded independent check would be a clean smoke run with the built interpreter after `make`: run a tiny script under `strace -tt -T` that performs `select.poll().poll(1000)` on a readable-watched fd and `os.wait4(-1, os.WNOHANG)` with no children, confirming it sleeps for about one second and returns/raises normally rather than spinning. If a CPython patch later targets these paths, also run the focused relevant tests, such as `./python -m test test_poll test_wait4 test_subprocess`.

## Patch Pass

Subject: Diagnose supervisord poll evidence without CPython patch

## Commit Message
No source change is proposed. The collected evidence points to `supervisord` periodically calling `wait4(..., WNOHANG)` and then sleeping in `poll(..., 1000)`, not to a CPython busy loop.

## Evidence Confidence
inferred

## Issue Connection
The collected signal was a high-CPU Fixer profile for `/usr/bin/python3.13` running `/usr/bin/supervisord`, with samples attributed to kernel `read_tsc` and `_PyEval_EvalFrameDefault`. The `/proc` evidence says the sampled process was sleeping in `poll_schedule_timeout`, and the `strace` excerpt shows `wait4(-1, ..., WNOHANG)` returning `ECHILD` followed by `poll(..., 1000)` timing out after about one second.

The likely root cause is a normal supervisor event-loop cadence being classified as a busy-poll loop by indirect profiling evidence. CPython’s local wrappers do not show an actionable defect: `Modules/selectmodule.c` uses `Py_BEGIN_ALLOW_THREADS`, `_PyDeadline_Init()` / `_PyDeadline_Get()`, and `PyErr_SetFromErrno`; `Modules/posixmodule.c` uses Argument Clinic entrypoints, `Py_BEGIN_ALLOW_THREADS`, bounded EINTR retry loops, and `posix_error()`.

I made no source change, following the saved plan. The expected effect is to avoid an upstream CPython patch that would change broad `poll` or `wait4` behavior without reproduced evidence of a runtime bug.

## Git Add Paths
None

## Validation
Read contribution/build guidance in `README.rst`; it points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`. No new helper APIs were introduced.

Ran the project-level entrypoint from the workspace root:

`./configure && make`

Result: command exited successfully. Build output reported optional module issues: `_ssl failed to import: ... undefined symbol: TLSv1_method`, `_dbm`, `_gdbm`, and `_tkinter` were missing, and `_ssl` was removed after import failure. These are optional-module environment issues and not related to `poll`/`wait4`.

Attempted bounded syscall reproduction:

`strace -tt -T -e trace=poll,wait4 ./python - <<'PY' ...`

Blocked by sandbox ptrace restrictions: `PTRACE_TRACEME: Operation not permitted` and `ptrace(PTRACE_SEIZE, 5): Operation not permitted`.

Ran the same smoke behavior without `strace` using the built interpreter:

`./python - <<'PY' ...`

Result: `os.wait4(-1, os.WNOHANG)` raised `ChildProcessError`, `select.poll().poll(1000)` returned `[]`, and elapsed time was `1.001` seconds. This matches a sleeping one-second poll timeout, not an independently reproduced busy loop.

## Review Pass 1

RESULT: ok

No findings. The workspace is clean, `## Evidence Confidence` is valid and appropriately `inferred`, no speculative source diff was left, and the diagnosis stays within the profiler/strace evidence. Validation includes the project-level `./configure && make`, the ptrace blocker for syscall reproduction, and a narrower smoke check showing one-second `poll` sleep behavior.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` under high CPU attribution, but the captured syscall evidence shows a normal one-second loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about 1.001s. The process was sleeping in `poll_schedule_timeout`, not spinning in a zero-timeout loop. The available evidence does not prove a CPython runtime bug.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch in this pass. Prepare a diagnosis/report that the evidence is insufficient for an upstream `python3.13` patch and should be redirected to the application entrypoint (`supervisord`), its configuration, or the profiler/kernel attribution path.

## Patch Plan
Do not edit files.

The maintainer-facing explanation should say that Fixer observed the issue but did not capture a reproducible CPython failure. The evidence identifies `supervisord` as the script/application entrypoint, while the runtime evidence only shows CPython executing ordinary `poll`/`waitpid` style operations.

Local conventions/helpers inspected:
- `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.
- `Modules/posixmodule.c` wraps `waitpid()`/`wait4()` with `Py_BEGIN_ALLOW_THREADS`, EINTR retry, `PyErr_CheckSignals()`, and `posix_error()`.
- `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and a `poll_running` guard around `poll()`.
- `Lib/subprocess.py` already handles `ECHILD` from `waitpid()` in `Popen._internal_poll()`/`_try_wait()`, with existing regression coverage in `Lib/test/subprocessdata/sigchild_ignore.py`.

No prior Fixer patch related to this finding was found in `.agents`, `.codex`, `debian`, or `.pc`. If later evidence proves a CPython bug, the patch should follow the existing bounded helper style above and avoid awkward control flow such as introducing avoidable `goto`.

## Risks
A CPython patch based only on this evidence would likely change correct behavior. `ECHILD` with `WNOHANG` can be normal when there are no child processes or children have been reaped elsewhere, and a one-second `poll()` timeout is not a busy poll.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails due to missing Debian build dependencies or generated files, record the exact failure and then run the narrowest relevant check.

Bounded independent reproduction attempt: after a successful build, run the built interpreter with a small script that calls `os.waitpid(-1, os.WNOHANG)` and `select.poll().poll(1000)` and confirm it blocks for about one second rather than spinning. This can validate the evidence interpretation, but it should not be reported as reproducing the original runaway CPU finding.

## Patch Pass

Subject: No patch: diagnose supervisord poll profile

## Commit Message
No source change is proposed. The likely root cause from the collected evidence is not a CPython busy loop: the traced `supervisord` process was sleeping in `poll_schedule_timeout`, and each `poll(..., 1000)` call timed out after about one second while `wait4(-1, ..., WNOHANG)` returned `ECHILD`.

CPython already has local wrappers/patterns for this area: `Modules/posixmodule.c` wraps `waitpid()`/`wait4()` with `Py_BEGIN_ALLOW_THREADS`, EINTR retry, `PyErr_CheckSignals()`, and `posix_error()`, while `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and a `poll_running` guard around `poll()`.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU profile for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, with hot samples in kernel `read_tsc` and CPython eval frames. The concrete `/proc` and strace excerpts, however, show the process in sleeping state `S`, blocked in `poll_schedule_timeout`, with repeated `wait4(..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about one second.

The cautious code-level inference is that the evidence points at a `supervisord` event loop or profiler attribution issue, not a proven CPython runtime defect. `ECHILD` means there are no waitable child processes, and a one-second `poll()` timeout is not a tight busy poll.

I followed the saved plan and made no source change. An inferred source patch would not be upstream-ready without stronger evidence that CPython is mishandling `wait4`, `waitpid`, or `poll`.

The expected effect of this no-patch diagnosis is to avoid landing a speculative CPython workaround and to redirect follow-up evidence collection toward the application entrypoint, its configuration, or the profiler/kernel attribution path.

## Git Add Paths
None

## Validation
Ran the workspace-root entrypoint:

```sh
./configure && make
```

Result: completed with exit code 0. `configure` detected `poll`, `wait4`, and `waitpid`, and reported `checking for broken poll()... no`. During `make`, optional `_ssl` was built then removed because it failed to import with: `undefined symbol: TLSv1_method`.

Bounded independent signal check, run with the built `./python` before cleanup:

```sh
./python - <<'PY'
import os, select, time
for i in range(3):
    try:
        os.waitpid(-1, os.WNOHANG)
    except ChildProcessError as exc:
        wait_result = f"ECHILD errno={exc.errno}"
    r, w = os.pipe()
    try:
        p = select.poll()
        p.register(r, select.POLLIN | select.POLLPRI | select.POLLHUP)
        start = time.monotonic()
        events = p.poll(1000)
        elapsed = time.monotonic() - start
    finally:
        os.close(r); os.close(w)
    print(wait_result, events, f"{elapsed:.3f}s")
PY
```

Result: all three iterations returned `ECHILD errno=10`, no events, and elapsed times of `1.001s`. That did not reproduce runaway CPU; it matched the evidence interpretation that the observed loop sleeps for the requested timeout.

Ran `make distclean` afterward to remove generated build artifacts. Final `git status --short` is clean.

## Review Pass 1

RESULT: ok

No findings. The first pass correctly leaves no source diff for indirect/profiler evidence, uses a valid `## Evidence Confidence` value (`inferred`), and does not overclaim reproduction. The diagnosis connects the collected `perf`, `strace`, and `/proc` signals to the decision not to patch CPython.

Validation is acceptable: it attempted the project-level `./configure && make`, reported the `_ssl` import issue, ran a bounded independent wait/poll smoke check, and cleaned generated artifacts. `git status --short` is clean, and comparison with the original snapshot shows only workspace metadata directories.

Prompt

## Plan Pass

You are planning a fixer patch before any edits happen.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. The original pre-edit snapshot is available at `./source` if you need to inspect it. For interpreter processes, plan from the script/application entrypoint evidence first and include the runtime only as a second investigation target unless the evidence proves a runtime bug.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. Inspect the relevant code, nearby callers, project contribution docs, and local helper/compat APIs, but do not edit files in this pass.

Return a short markdown plan with these exact sections:

## Problem
## Evidence Confidence
## Proposed Subject
## Patch Plan
## Risks
## Validation

Classify `## Evidence Confidence` as exactly one of `reproduced`, `observed`, or `inferred`. Use `inferred` only for a no-patch diagnosis/report plan unless you can name the extra evidence you will collect before editing; inferred source patches are blocked by Fixer because they are not pull-request-ready. For `observed` source-patch plans, plan to say in the final `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. If the plan touches authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior, treat it as security-sensitive: do not plan a source patch unless validation can reproduce the behavior and analyze the security impact; otherwise plan a no-patch diagnosis/report. The plan must explain how the proposed code change addresses the observed issue evidence, call out any prior Fixer patch that should be improved or replaced, reject awkward control flow such as avoidable `goto` if there is a cleaner bounded alternative, name any local helper APIs or maintainer conventions the patch should follow, and keep the intended maintainer-facing explanation clear enough that someone unfamiliar with the local complaint wording can still follow the fix. In `## Validation`, name the reproducible configure/build/test entrypoint you will try from the workspace root before any focused leaf compile or smoke check, and include one bounded independent reproduction attempt for the collected failure signal when it is safe and cheap. Do not plan to claim `reproduced` unless that reproduction command or test can actually show the failure.

## Patch Pass

You are working on a bounded fixer proposal.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Produce the smallest reasonable patch for the target repository, keep the change upstreamable, prefer the clearest control flow available, and do not keep avoidable `goto` when a simpler structure would read better. Before introducing new file, process, allocation, locking, networking, or platform APIs, inspect nearby code and project contribution docs for existing helpers or compatibility wrappers and use those local patterns unless you can explain why they do not fit. Validate from a reproducible workspace-root entrypoint before falling back to focused leaf commands; if a build or test cannot run, report the exact command, the exact blocker, and any narrower check you ran instead. During validation, also try one bounded independent reproduction of the collected failure signal when it is safe and cheap, such as a failing test, smoke command, perf/strace comparison, or before/after runtime check. Only use `reproduced` if that command or test actually reproduced the failure; otherwise keep `observed` and report the reproduction blocker. The final explanation must connect the observed issue evidence to the actual code change, not just paraphrase the diff. Write like a maintainer is going to read the patch mail cold: explain the bug in plain language, define subsystem-specific jargon the first time you need it, and make the causal story obvious. Explicitly classify evidence confidence as `reproduced`, `observed`, or `inferred`: `reproduced` means you reproduced the failure locally; `observed` means Fixer has direct crash/log/trace evidence but you did not independently reproduce it; `inferred` means the source patch is not pull-request-ready, so do not leave a source diff unless you first gather stronger observed/reproduced evidence; otherwise return a no-patch diagnosis/report. For any source-changing `observed` patch, say explicitly in `## Issue Connection` that the failure was observed by Fixer and not independently reproduced. Security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior need reproduced evidence plus explicit security-impact analysis before leaving a source diff; otherwise return a no-patch diagnosis/report for human review. If you introduce non-obvious state translation, index remapping, or backend split logic, add a short source comment that explains the invariant being preserved.

Start by explaining the likely root cause from the collected perf, strace, and /proc evidence. If you cannot land a safe patch, leave a diagnosis that is strong enough for an upstream bug report.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround. 

Keep the change narrowly scoped and summarize validation clearly.

In every authoring pass, your final response must start with `Subject: <single-line git commit subject>` and then include these markdown sections exactly:

## Commit Message
A short upstream-friendly explanation of what changed and why. Write it in plain language that a maintainer can follow without local complaint context. If you use subsystem jargon, define it immediately.

## Evidence Confidence
Exactly one word: `reproduced`, `observed`, or `inferred`. Use `reproduced` only when you reproduced the failure locally with a command or test, and include that command/test in `## Validation`. Use `observed` when Fixer has direct crash/log/trace evidence but you did not independently reproduce it. If `## Git Add Paths` lists source files for an `observed` patch, `## Issue Connection` must explicitly say the failure was observed by Fixer and not independently reproduced. Security-sensitive source changes touching authentication, authorization, credentials, cryptography, sandboxing, permissions, or timing/throttling behavior require reproduced evidence and explicit security-impact analysis; otherwise list `None` under `## Git Add Paths` and write a no-patch diagnosis/report. Use `inferred` for profiler/strace/indirect evidence; inferred responses may be no-patch diagnoses or reports, but inferred source patches are not pull-request-ready until stronger evidence is gathered.

## Issue Connection
Write this as maintainer-facing patch mail, not as local Fixer notes. Cover four things explicitly in readable sentences: the user-visible symptom or the exact collected signal, the code-level cause or the cautious inference from evidence, the specific change you made, and the expected effect. Do not invent a reproducer, command line, crash, or user-visible failure that is not present in the evidence bundle. If the evidence is direct-but-not-reproduced, say it was observed by Fixer and not independently reproduced. If the evidence is indirect and you did not gather stronger evidence, do not leave a source diff; write a no-patch diagnosis/report instead. Include an explicit effect sentence such as `The expected effect is ...`, `This should reduce ...`, or `This prevents ...` for source patches. If the logic is non-obvious in code, mention that you added a short explanatory comment.

## Git Add Paths
List the repo-relative paths that belong in the final patch, one per line. Use `None` only when you intentionally made no source changes. Include intentionally new files, and do not list generated build artifacts.

## Validation
List the checks you ran, or say clearly that you could not run them. Include the independent reproduction command/test and result when `## Evidence Confidence` is `reproduced`; if reproduction was attempted but blocked, name the exact blocker and keep confidence at `observed` or `inferred`.

Before editing, read the plan at `./plan-output.txt` and follow it unless the code proves part of it wrong. If you change course, say so explicitly in the final write-up instead of silently drifting from the plan.

## Review Pass 1

You are reviewing a freshly generated fixer patch.

Read the evidence bundle at `./evidence.json`. The prepared workspace is `./workspace` and it was acquired via `debian-source`. Review the first patch pass. The original pre-edit snapshot is available at `./source` for diffing.

Upstream-style expectation: before planning or editing, check for contribution/style docs (`CONTRIBUTING`, `HACKING`, `README-hacking`, `README.md`, `docs/`, `dev-docs/`) and scan the touched subsystem for local helpers. If the project has wrappers for file IO, path-relative IO, process spawning, memory allocation, logging, locking, or platform compatibility, prefer those wrappers over generic libc/std APIs. Do not invent a reproducer or user-visible failure that is not in the evidence bundle; if the evidence is profiler-only or indirect, describe it as a targeted mitigation or stop with a diagnosis instead of presenting a speculative patch as a confirmed bug fix. In the plan and final validation, name any such helper, convention, or evidence limit you found, or say that no relevant local helper was found. Treat this as a `python3.13` upstream patch, not just a Debian-local workaround.

Validation expectation: try the project-level build/test entrypoint from the workspace root before reporting only a focused leaf compile. Detected candidate(s): `./configure && make`. If the project-level command fails because dependencies or generated files are missing, include the exact command and failure reason in `## Validation`, then run the narrowest relevant compile/test that is still reproducible from a clean checkout. The latest author response is at `./patch-output.txt`. Inspect the current code and changed paths like a strict code reviewer. Focus on correctness, regressions, maintainability, awkward control flow such as avoidable `goto`, missing validation, weak or non-gittable commit message text, and explanations that fail to connect the observed issue evidence to the code change. Also review the maintainer experience: the patch mail should be easy to accept upstream, the user-visible bug should be explained in plain language, subsystem-specific jargon should be defined when first used, and any non-obvious state translation or index remapping in code should have a short explanatory comment. Reject patches that omit `## Evidence Confidence`, use anything other than `reproduced`, `observed`, or `inferred`, or sound more certain than that evidence level allows. Reject patches that claim `reproduced` unless `## Validation` names the concrete reproduction command or test and its result. Reject source patches in security-sensitive areas such as authentication, authorization, credentials, cryptography, sandboxing, permissions, and timing/throttling behavior unless the author reproduced the behavior and explicitly analyzed the security impact of the change; observed-only evidence should become a diagnosis/report, not a PR-ready source diff. Reject patches that invent a reproducer, command line, crash, or user-visible failure not present in the evidence bundle; indirect profiler or strace evidence may justify a cautious mitigation, but the author must say it is indirect instead of presenting it as a confirmed upstream bug. Reject patches that introduce generic libc/std APIs when nearby code or project docs provide a local compat/helper API for the same job, unless the author explicitly justifies the exception. Reject validation that only reports a leaf object/syntax build when a project-level configure/build/test entrypoint exists and was not attempted; if a full build cannot run, the author must show the exact failed command and blocker.

Do not apply code changes in this pass.

Return a short markdown review report. The first non-empty line must be exactly one of:

RESULT: ok
RESULT: fix-needed

If you choose `RESULT: fix-needed`, add a `## Findings` section with concrete, actionable items.

Response

## Plan Pass

## Problem
Fixer observed `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf` under high CPU attribution, but the captured syscall evidence shows a normal one-second loop: `wait4(-1, ..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about 1.001s. The process was sleeping in `poll_schedule_timeout`, not spinning in a zero-timeout loop. The available evidence does not prove a CPython runtime bug.

## Evidence Confidence
inferred

## Proposed Subject
No CPython source patch in this pass. Prepare a diagnosis/report that the evidence is insufficient for an upstream `python3.13` patch and should be redirected to the application entrypoint (`supervisord`), its configuration, or the profiler/kernel attribution path.

## Patch Plan
Do not edit files.

The maintainer-facing explanation should say that Fixer observed the issue but did not capture a reproducible CPython failure. The evidence identifies `supervisord` as the script/application entrypoint, while the runtime evidence only shows CPython executing ordinary `poll`/`waitpid` style operations.

Local conventions/helpers inspected:
- `README.rst` points contributors to the CPython Developer Guide and documents `./configure`, `make`, and `make test`.
- `Modules/posixmodule.c` wraps `waitpid()`/`wait4()` with `Py_BEGIN_ALLOW_THREADS`, EINTR retry, `PyErr_CheckSignals()`, and `posix_error()`.
- `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and a `poll_running` guard around `poll()`.
- `Lib/subprocess.py` already handles `ECHILD` from `waitpid()` in `Popen._internal_poll()`/`_try_wait()`, with existing regression coverage in `Lib/test/subprocessdata/sigchild_ignore.py`.

No prior Fixer patch related to this finding was found in `.agents`, `.codex`, `debian`, or `.pc`. If later evidence proves a CPython bug, the patch should follow the existing bounded helper style above and avoid awkward control flow such as introducing avoidable `goto`.

## Risks
A CPython patch based only on this evidence would likely change correct behavior. `ECHILD` with `WNOHANG` can be normal when there are no child processes or children have been reaped elsewhere, and a one-second `poll()` timeout is not a busy poll.

## Validation
Before any focused check, try the project-level entrypoint from the workspace root:

```sh
./configure && make
```

If that fails due to missing Debian build dependencies or generated files, record the exact failure and then run the narrowest relevant check.

Bounded independent reproduction attempt: after a successful build, run the built interpreter with a small script that calls `os.waitpid(-1, os.WNOHANG)` and `select.poll().poll(1000)` and confirm it blocks for about one second rather than spinning. This can validate the evidence interpretation, but it should not be reported as reproducing the original runaway CPU finding.

## Patch Pass

Subject: No patch: diagnose supervisord poll profile

## Commit Message
No source change is proposed. The likely root cause from the collected evidence is not a CPython busy loop: the traced `supervisord` process was sleeping in `poll_schedule_timeout`, and each `poll(..., 1000)` call timed out after about one second while `wait4(-1, ..., WNOHANG)` returned `ECHILD`.

CPython already has local wrappers/patterns for this area: `Modules/posixmodule.c` wraps `waitpid()`/`wait4()` with `Py_BEGIN_ALLOW_THREADS`, EINTR retry, `PyErr_CheckSignals()`, and `posix_error()`, while `Modules/selectmodule.c` uses `_PyTime_*` deadline helpers and a `poll_running` guard around `poll()`.

## Evidence Confidence
inferred

## Issue Connection
Fixer collected a high-CPU profile for `/usr/bin/python3 /usr/bin/supervisord -n -c /etc/supervisor/supervisord.conf`, with hot samples in kernel `read_tsc` and CPython eval frames. The concrete `/proc` and strace excerpts, however, show the process in sleeping state `S`, blocked in `poll_schedule_timeout`, with repeated `wait4(..., WNOHANG) = -1 ECHILD` followed by `poll(..., 1000) = 0` after about one second.

The cautious code-level inference is that the evidence points at a `supervisord` event loop or profiler attribution issue, not a proven CPython runtime defect. `ECHILD` means there are no waitable child processes, and a one-second `poll()` timeout is not a tight busy poll.

I followed the saved plan and made no source change. An inferred source patch would not be upstream-ready without stronger evidence that CPython is mishandling `wait4`, `waitpid`, or `poll`.

The expected effect of this no-patch diagnosis is to avoid landing a speculative CPython workaround and to redirect follow-up evidence collection toward the application entrypoint, its configuration, or the profiler/kernel attribution path.

## Git Add Paths
None

## Validation
Ran the workspace-root entrypoint:

```sh
./configure && make
```

Result: completed with exit code 0. `configure` detected `poll`, `wait4`, and `waitpid`, and reported `checking for broken poll()... no`. During `make`, optional `_ssl` was built then removed because it failed to import with: `undefined symbol: TLSv1_method`.

Bounded independent signal check, run with the built `./python` before cleanup:

```sh
./python - <<'PY'
import os, select, time
for i in range(3):
    try:
        os.waitpid(-1, os.WNOHANG)
    except ChildProcessError as exc:
        wait_result = f"ECHILD errno={exc.errno}"
    r, w = os.pipe()
    try:
        p = select.poll()
        p.register(r, select.POLLIN | select.POLLPRI | select.POLLHUP)
        start = time.monotonic()
        events = p.poll(1000)
        elapsed = time.monotonic() - start
    finally:
        os.close(r); os.close(w)
    print(wait_result, events, f"{elapsed:.3f}s")
PY
```

Result: all three iterations returned `ECHILD errno=10`, no events, and elapsed times of `1.001s`. That did not reproduce runaway CPU; it matched the evidence interpretation that the observed loop sleeps for the requested timeout.

Ran `make distclean` afterward to remove generated build artifacts. Final `git status --short` is clean.

## Review Pass 1

RESULT: ok

No findings. The first pass correctly leaves no source diff for indirect/profiler evidence, uses a valid `## Evidence Confidence` value (`inferred`), and does not overclaim reproduction. The diagnosis connects the collected `perf`, `strace`, and `/proc` signals to the decision not to patch CPython.

Validation is acceptable: it attempted the project-level `./configure && make`, reported the `_ssl` import issue, ran a bounded independent wait/poll smoke check, and cleaned generated artifacts. `git status --short` is clean, and comparison with the original snapshot shows only workspace metadata directories.