fix: correct Lunary tool-error logging#5505
Conversation
Summary of ChangesHello @moona3k, 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 specific logging inaccuracy within the Lunary integration. Previously, errors originating from tools were mistakenly attributed to the LLM run tracker, leading to miscategorized failure spans. The change redirects these error logs to the correct tool tracker, ensuring that all tool-related failures are accurately recorded and easily identifiable for debugging and monitoring purposes. Highlights
Using Gemini Code AssistThe 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
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request addresses a bug in Lunary's tool-error logging. Previously, tool failures were incorrectly logged under the LLM run tracker, causing them to appear under the wrong span. The change correctly redirects the error logging to use the tool tracker, ensuring that tool failures are associated with the correct span. The fix is straightforward and effectively resolves the issue.
moona3k
changed the title
moona3k
changed the title
|
thank you! |
fix: log lunary tool errors with the correct run id
2 participants
Lunary tool-error logs were using the LLM run tracker, so tool call failures showed under the wrong span. This PR points the tool-error handler to the tool tracker so failures tag the correct span. Every other analytics provider (LangSmith, LangFuse, etc) already follows this pattern.