feat: include gen_ai.conversation.id in OTEL spans (#421)
Ref #421
This change adds the gen_ai.conversation.id attribute to OTEL spans, allowing messages within the same conversation to be linked in AI evaluation and observability platforms.
Changes
- Added
genAiConversationIDconstant - Stored
sessionIDin variable to avoid duplicate method calls - Added
gen_ai.conversation.idattribute toTraceLLMCall
Testing Plan
- All existing tests pass (
go test ./...) - Verified with
go buildandgolangci-lint run - New attribute appears in OTEL spans alongside
gcp.vertex.agent.session_id
Reference
- OTEL GenAI Semantic Conventions: https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/
Summary of Changes
Hello @JEETDESAI25, I'm Gemini Code Assist[^1]! 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 enhances the observability of AI conversations by adding a new gen_ai.conversation.id attribute to OpenTelemetry spans. This change allows for a clearer understanding of conversational flows in AI evaluation platforms by explicitly linking related messages, thereby improving the ability to trace and analyze user interactions.
Highlights
-
New OTEL Span Attribute: Introduced the
gen_ai.conversation.idattribute to OpenTelemetry spans, enabling better linking of messages within the same conversation for AI evaluation and observability. -
Code Optimization: Refactored the
TraceLLMCallfunction to store thesessionIDin a local variable, avoiding duplicate method calls and addressing previous feedback.
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.
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 :thumbsup: and :thumbsdown: 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.
[^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.