chore: use pytest's new strict mode and fix duplicate tests

[radoering]

No description provided.

[sourcery-ai]

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

• In test_peeled_tag the parametrized tag argument is immediately overwritten (tag = peeled_tag("my-tag")), so the parameter (and new ids) are effectively unused; consider either asserting behavior that depends on the input type or removing the parametrize and hard-coding the value to keep the test intention clear.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- In `test_peeled_tag` the parametrized `tag` argument is immediately overwritten (`tag = peeled_tag("my-tag")`), so the parameter (and new `ids`) are effectively unused; consider either asserting behavior that depends on the input type or removing the parametrize and hard-coding the value to keep the test intention clear.

## Individual Comments

### Comment 1
<location path="tests/vcs/git/test_backend.py" line_range="105" />
<code_context>


[email protected](("tag"), ["my-tag", b"my-tag"])
[email protected]("tag", ["my-tag", b"my-tag"], ids=["str", "bytes"])
 def test_peeled_tag(tag: str | bytes) -> None:
     tag = peeled_tag("my-tag")
</code_context>
<issue_to_address>
**issue (testing):** Use the parametrized `tag` value inside the test to actually exercise both `str` and `bytes` inputs.

Right now `test_peeled_tag` ignores the parametrized `tag` and always calls `peeled_tag("my-tag")`, so it never exercises the bytes path. Use the parameter in the call, e.g.

```python
@pytest.mark.parametrize("tag", ["my-tag", b"my-tag"], ids=["str", "bytes"])
def test_peeled_tag(tag: str | bytes) -> None:
    result = peeled_tag(tag)
    assert result == b"my-tag^{}"  # or the correct expected value
```

so the parametrization actually validates both input types and protects against regressions in their handling.
</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.}