Skip to content

Conversation

@yarolegovich
Copy link
Member

@yarolegovich yarolegovich commented Nov 24, 2025

Event processor is delaying some events until the whole LLM response is consumed to send them as terminal events.
Those events were referencing the same metadata as events sent before the delayed dispatch.
Metadata was accessed by task update processor leading to a race with meta modification during terminal event dispatch.

The fix is to make delayed events reference metadata shallow copy so that the original metadata is not affected by root-level key updates.

Fixes nightly.

image

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @yarolegovich, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical data race in the adka2a integration. Previously, delayed terminal events would reference the same metadata as earlier events, leading to race conditions when the metadata was modified concurrently. The fix ensures that delayed events operate on a shallow copy of the metadata, thereby preventing these race conditions and enhancing the stability and correctness of event processing.

Highlights

  • Data Race Resolution: Resolved a data race condition within the adka2a integration's event processing logic, specifically concerning delayed terminal events.
  • Metadata Shallow Copying: Implemented shallow copying of event metadata for delayed terminal events to prevent concurrent modification issues.
  • Usage of maps.Clone: Utilized the maps.Clone function to ensure that metadata passed to delayed events is a distinct copy, safeguarding the original metadata from unintended changes.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request effectively resolves a data race within the adka2a integration by ensuring metadata for delayed events is properly isolated. The core of the fix is the strategic use of maps.Clone to create shallow copies of metadata maps. This prevents shared state modification when events are queued for later dispatch, specifically for terminal failure and completion events. The changes are correct, well-targeted, and improve the code's robustness against concurrent data access issues. Additionally, replacing make and maps.Copy with maps.Clone is a welcome simplification.

kdroste-google
kdroste-google previously approved these changes Nov 24, 2025
Copy link
Collaborator

@kdroste-google kdroste-google left a comment

Choose a reason for hiding this comment

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

Please add comments explaining reason why we have to copy at those points

Copy link
Collaborator

@kdroste-google kdroste-google left a comment

Choose a reason for hiding this comment

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

LGTM

@yarolegovich yarolegovich merged commit f5e8b6d into main Nov 24, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants