Related Issues/PRs

Related: https://github.com/mlflow/mlflow/actions/runs/19862282787/job/56926073936

What changes are proposed in this pull request?

The test test_log_metric_concurrent_logging_succeeds fails intermittently on Windows due to SQLite's database-level locking when multiple threads attempt concurrent writes:

sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) database is locked
[SQL: INSERT INTO metrics ("key", value, timestamp, step, is_nan, run_uuid) VALUES (?, ?, ?, ?, ?, ?)]

This PR skips the test on Windows using @pytest.mark.skipif(is_windows(), ...) since the test intentionally exercises concurrent write operations that trigger SQLite's inherent concurrency limitations on Windows.

@pytest.mark.skipif(
    is_windows(),
    reason="Flaky on Windows due to SQLite database locking issues with concurrent writes",
)
def test_log_metric_concurrent_logging_succeeds(store: SqlAlchemyStore):
    ...

How is this PR tested?

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

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.