Related Issues/PRs

What changes are proposed in this pull request?

Adds a reusable db_uri fixture to tests/conftest.py that provides a fresh SQLite database URI for each test by copying the session-scoped cached_db, and refactors all existing tests to use this new fixture instead of manually copying the database.

Implementation:

@pytest.fixture
def db_uri(tmp_path: Path, cached_db: Path) -> str:
    """Returns a fresh SQLite URI for each test by copying the cached database."""
    db_path = tmp_path / "mlflow.db"
    shutil.copy2(cached_db, db_path)
    return f"sqlite:///{db_path}"

Benefits:

• Eliminates boilerplate: tests no longer need to manually copy cached_db and construct URIs
• Ensures isolation: each test gets its own database copy in its temporary directory
• Standardizes pattern: consistent approach across the test suite
• Reduces code duplication: removed 86 lines of repetitive database copying code

Changes made:

# Before (manual pattern repeated in 13 test files)
db_path = tmp_path / "mlflow.db"
shutil.copy(cached_db, db_path)
uri = f"sqlite:///{db_path}"

# After (using the new fixture)
def test_example(db_uri):
    # uri ready to use

Files refactored to use db_uri fixture:

• tests/genai/evaluate/test_evaluation.py
• tests/store/model_registry/test_sqlalchemy_store.py
• tests/store/tracking/test_sqlalchemy_store.py
• tests/tracing/test_assessment.py
• tests/tracing/test_fluent.py
• tests/tracing/test_otel_loading.py
• tests/tracing/test_otel_logging.py
• tests/tracking/fluent/test_fluent.py
• tests/tracking/test_client.py
• tests/tracking/test_log_image.py
• tests/tracking/test_model_registry.py
• tests/tracking/test_rest_tracking.py
• tests/tracking/test_tracking.py

How is this PR tested?

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

Verified the fixture works correctly by running existing tests that previously used cached_db directly. All tests continue to pass with the new fixture-based approach.

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)

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.