Related Issues/PRs

#xxx

What changes are proposed in this pull request?

The db_uri fixture was creating SQLite database files in the tmp_path directory, which could interfere with tests that use tmp_path and expect a clean directory.

Changes:

• Replaced tmp_path / "mlflow.db" with tempfile.TemporaryDirectory()
• Used context manager pattern with yield for automatic cleanup
• Removed tmp_path parameter dependency from the fixture
• Creates database file inside a temporary directory to avoid Windows permission errors

# Before
@pytest.fixture
def db_uri(tmp_path: Path, cached_db: Path) -> str:
    db_path = tmp_path / "mlflow.db"
    ...
    return f"sqlite:///{db_path}"

# After
@pytest.fixture
def db_uri(cached_db: Path):
    with tempfile.TemporaryDirectory() as tmp_dir:
        db_path = Path(tmp_dir) / "mlflow.db"
        ...
        yield f"sqlite:///{db_path}"

Note: Initially used NamedTemporaryFile, but switched to TemporaryDirectory to fix a Windows PermissionError that occurred when trying to copy data to an open file handle.

How is this PR tested?

• Existing unit/integration tests
• New unit/integration tests
• Manual tests

Verified with existing tests in tests/store/model_registry/, tests/store/tracking/, and tests/artifacts/.

Does this PR require documentation update?

• No. You can skip the rest of this section.
• Yes. I've updated:
  • Examples
  • API references
  • Instructions

Release Notes

Is this a user-facing change?

• No. You can skip the rest of this section.
• Yes. Give a description of this change to be included in the release notes for MLflow users.

What component(s), interfaces, languages, and integrations does this PR affect?

Components

• area/tracking: Tracking Service, tracking client APIs, autologging
• area/models: MLmodel format, model serialization/deserialization, flavors
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/scoring: MLflow Model server, model deployment tools, Spark UDFs
• area/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflows
• area/gateway: MLflow AI Gateway client APIs, server, and third-party integrations
• area/prompts: MLflow prompt engineering features, prompt templates, and prompt management
• area/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionality
• area/projects: MLproject format, project running backends
• area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
• area/build: Build and test infrastructure for MLflow
• area/docs: MLflow documentation pages

How should the PR be classified in the release notes? Choose one:

• rn/none - No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" section
• rn/breaking-change - The PR will be mentioned in the "Breaking Changes" section
• rn/feature - A new user-facing feature worth mentioning in the release notes
• rn/bug-fix - A user-facing bug fix worth mentioning in the release notes
• rn/documentation - A user-facing documentation change worth mentioning in the release notes

Should this PR be included in the next patch release?

• Yes (this PR will be cherry-picked and included in the next patch release)
• No (this PR will be included in the next minor release)

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.