# Python Quality Matrix

## Configuration detection
- Read `pyproject.toml` first.
- Detect the configured Python version.
- Detect `mypy`, `ty`, `ruff`, `deptry`, `pytest`, and formatter configuration.

## Review rules
- If `mypy` is configured, check the actual options before judging missing annotations or strictness violations.
- If `ty` is configured, use its configured expectations and error model.
- If both exist, respect whichever toolchain the project clearly treats as authoritative, and flag inconsistent duplication.
- If `ruff` is configured, review for meaningful rule violations, not cosmetic churn.
- If `deptry` is configured, verify dependency placement, unused dependencies, and hidden transitive reliance.

## Modern Python usage
- Use modern typing syntax only when the configured Python version supports it.
- Prefer `typing.Self`, `typing.TypeAliasType`, `typing.override`, `collections.abc` imports, `match`, `enum.StrEnum`, dataclass slots, and other newer features only when they improve clarity and compatibility.
- Do not suggest a newer language feature that the configured interpreter cannot run.

## Common harsh checks
- Weak or missing type boundaries.
- Hidden `Any` spread.
- Async misuse.
- Leaky ORM or transport models.
- Overly dynamic code that defeats static analysis.
- Wrong dependency classification.