Delay parsing requests timeout environment variable

[nightt5879]

Summary

• Delay parsing POETRY_REQUESTS_TIMEOUT until an HTTP request actually needs the timeout value.
• Keep the default timeout constant import-safe and parse the environment value through Poetry's integer normalizer helper.
• Add regression coverage for python -m poetry --version with an invalid timeout environment value.

Fixes #10969

Validation

• POETRY_REQUESTS_TIMEOUT=abc .\.venv\Scripts\python.exe -m poetry --version -> Poetry (version 2.5.0.dev0)
• .\.venv\Scripts\python.exe -m pytest -n 0 --basetemp=.pytest-tmp tests\utils\test_constants.py tests\console\test_application.py::test_application_version_ignores_invalid_requests_timeout -> 4 passed
• .\.venv\Scripts\python.exe -m pytest -n 0 --basetemp=.pytest-tmp tests\utils\test_authenticator.py tests\repositories\test_http_repository.py tests\repositories\test_pypi_repository.py tests\publishing -> 173 passed
• uvx ruff check src\poetry\utils\constants.py src\poetry\utils\authenticator.py src\poetry\utils\helpers.py src\poetry\repositories\http_repository.py src\poetry\repositories\pypi_repository.py src\poetry\publishing\uploader.py tests\console\test_application.py tests\utils\test_constants.py -> passed

Notes

• Full pytest --basetemp=.pytest-tmp on this Windows/Python 3.13.13 environment reached 3183 passed / 11 skipped, with 10 existing environment-sensitive failures unrelated to this change. The failures involved Windows path URI expectations, active Python discovery preferring Anaconda Python, and missing embedded pip wheels from the locally resolved virtualenv package.

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• In PypiRepository._get and HTTPRepository._get_response the timeout argument has been removed from session.get, which makes those requests behave differently from others using get_requests_timeout() and may unintentionally rely on the default requests timeout—consider restoring an explicit timeout for consistency.
• get_requests_timeout() re-reads and parses POETRY_REQUESTS_TIMEOUT from the environment on every call; if this is used frequently, consider caching the parsed value (including the invalid-case behavior) to avoid repeated env lookups and parsing.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `PypiRepository._get` and `HTTPRepository._get_response` the `timeout` argument has been removed from `session.get`, which makes those requests behave differently from others using `get_requests_timeout()` and may unintentionally rely on the default requests timeout—consider restoring an explicit timeout for consistency.
- `get_requests_timeout()` re-reads and parses `POETRY_REQUESTS_TIMEOUT` from the environment on every call; if this is used frequently, consider caching the parsed value (including the invalid-case behavior) to avoid repeated env lookups and parsing.

## Individual Comments

### Comment 1
<location path="src/poetry/repositories/http_repository.py" line_range="542-541" />
<code_context>
         url = self._url + endpoint
         try:
             response: requests.Response = self.session.get(
-                url, raise_for_status=False, timeout=REQUESTS_TIMEOUT, headers=headers
+                url, raise_for_status=False, headers=headers
             )
             if response.status_code in (401, 403):
</code_context>
<issue_to_address>
**issue (bug_risk):** Removing the timeout here may cause requests to hang indefinitely under network issues.

These calls were previously bounded by `REQUESTS_TIMEOUT`; without it, they now use the library default (`None`), so a slow or stalled connection can block indefinitely. If you’re standardizing timeouts, please either use `get_requests_timeout()` here or expose a configurable per-repository timeout instead of removing it completely.
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}