When GitHub's API rate limits cause asyncio shutdown issues, the test
times out rather than failing with the underlying 429 error. Updated the
detection logic to check for 429 indicators in the captured output when
a timeout occurs.
Also increased the per-test timeout from 15s to 30s to give remote API
calls more breathing room.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The pytest-retry plugin was causing teardown crashes due to a bug with
pytest's tmp_path fixture stash. Removing `@pytest.mark.flaky` and instead
improving the rate limit detection to properly skip tests on 429 errors.
Also fixed a brittle error message regex - GitHub changed their error
format from "tool not found" to "unknown tool".
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
