Skip to content

Fix litellm autolog for versions >= 1.78#19459

Merged
harupy merged 1 commit intomlflow:masterfrom
harupy:fix-litellm-autolog-newer-versions
Dec 17, 2025
Merged

Fix litellm autolog for versions >= 1.78#19459
harupy merged 1 commit intomlflow:masterfrom
harupy:fix-litellm-autolog-newer-versions

Conversation

@harupy
Copy link
Member

@harupy harupy commented Dec 17, 2025

🛠 DevTools 🛠

Open in GitHub Codespaces

Install mlflow from this PR

# mlflow
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/19459/merge
# mlflow-skinny
pip install git+https://github.com/mlflow/mlflow.git@refs/pull/19459/merge#subdirectory=libs/skinny

For Databricks, use the following command:

%sh curl -LsSf https://raw.githubusercontent.com/mlflow/mlflow/HEAD/dev/install-skinny.sh | sh -s pull/19459/merge

Related Issues/PRs

#xxx

What changes are proposed in this pull request?

Fix litellm autolog compatibility with litellm >= 1.78.

In litellm >= 1.78, the success_handler callback is wrapped in a function named run instead of being submitted directly to the thread pool executor. MLflow's patch was only checking for "success_handler", causing callbacks to run asynchronously and traces to not be available immediately after completion calls.

This PR updates the executor patch to check for both "success_handler" (litellm < 1.78) and "run" (litellm >= 1.78) function names.

How is this PR tested?

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

Tested with both litellm 1.75.9 and 1.80.10:

uv run --with litellm==1.75.9 pytest tests/litellm/test_litellm_autolog.py -v  # passes
uv run --with litellm==1.80.10 pytest tests/litellm/test_litellm_autolog.py -v  # passes

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.

Fix litellm autolog compatibility with litellm versions >= 1.78, ensuring traces are correctly captured.

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 should be selected for bug fixes, documentation updates, and other small changes. No should be selected for new features and larger changes. If you're unsure about the release classification of this PR, leave this unchecked to let the maintainers decide.

What is a minor/patch release?
  • Minor release: a release that increments the second part of the version number (e.g., 1.2.0 -> 1.3.0).
    Bug fixes, doc updates and new features usually go into minor releases.
  • Patch release: a release that increments the third part of the version number (e.g., 1.2.0 -> 1.2.1).
    Bug fixes and doc updates usually go into patch releases.
  • 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)

🤖 Generated with Claude Code

Copilot AI review requested due to automatic review settings December 17, 2025 11:27
@github-actions github-actions bot added v3.8.0 area/tracing MLflow Tracing and its integrations area/tracking Tracking service, tracking client APIs, autologging rn/bug-fix Mention under Bug Fixes in Changelogs. labels Dec 17, 2025
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR fixes a compatibility issue with litellm versions >= 1.78 where the success_handler callback is wrapped in a function named "run" instead of being submitted directly to the thread pool executor. The fix ensures MLflow traces are captured correctly by updating the executor patch to recognize both function names.

  • Updated function name detection to check for both "success_handler" (< 1.78) and "run" (>= 1.78)
  • Added inline comments explaining the version-specific behavior
  • Tested with both litellm 1.75.9 and 1.80.10

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@harupy harupy added the team-review Trigger a team review request label Dec 17, 2025
In litellm >= 1.78, the success_handler callback is wrapped in a
function named 'run' instead of being submitted directly. Update
the executor patch to check for both function names to ensure
callbacks are run synchronously in all supported versions.

Signed-off-by: harupy <17039389+harupy@users.noreply.github.com>
@harupy harupy force-pushed the fix-litellm-autolog-newer-versions branch from 33657ee to 8a2eef8 Compare December 17, 2025 11:31
@github-actions
Copy link
Contributor

Documentation preview for 8a2eef8 is available at:

More info
  • Ignore this comment if this PR does not change the documentation.
  • The preview is updated when a new commit is pushed to this PR.
  • This comment was created by this workflow run.
  • The documentation was built by this workflow run.

Copy link
Collaborator

@WeichenXu123 WeichenXu123 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM.

@harupy harupy added this pull request to the merge queue Dec 17, 2025
Merged via the queue into mlflow:master with commit aafa06c Dec 17, 2025
64 of 66 checks passed
@harupy harupy deleted the fix-litellm-autolog-newer-versions branch December 17, 2025 13:40
WeichenXu123 pushed a commit to WeichenXu123/mlflow that referenced this pull request Dec 19, 2025
Signed-off-by: harupy <17039389+harupy@users.noreply.github.com>
WeichenXu123 pushed a commit that referenced this pull request Dec 19, 2025
Signed-off-by: harupy <17039389+harupy@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area/tracing MLflow Tracing and its integrations area/tracking Tracking service, tracking client APIs, autologging rn/bug-fix Mention under Bug Fixes in Changelogs. team-review Trigger a team review request v3.8.0

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants