-
Notifications
You must be signed in to change notification settings - Fork 7.8k
feat(sessions): Integrate chat recording into GeminiChat #6721
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(sessions): Integrate chat recording into GeminiChat #6721
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @bl-ue, 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, the second in a series, integrates the chat recording functionality into the non-interactive mode of the CLI. It ensures that user messages, Gemini's responses, token usage, and detailed tool call information are captured and recorded, providing a comprehensive log of non-interactive sessions.
Highlights
- Comprehensive Chat Recording: Implements the recording of user inputs, Gemini's textual responses, and detailed token usage metadata within non-interactive CLI sessions.
- Enhanced Tool Call Logging: Captures the state of tool calls both before and after their execution, including success, error, and associated results or error messages.
- Standardized Event Structure: Updates the core Finished event type to consistently include both the finish reason and usage metadata, improving data consistency across the application.
- Robust Test Coverage: Adds extensive unit tests for the non-interactive CLI to validate the new chat recording and tool call logging features, ensuring reliability.
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command>
or @gemini-code-assist <command>
. Below is a summary of the supported commands.
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 issue 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
-
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. ↩
There was a problem hiding this 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 integrates chat recording into the non-interactive CLI mode. The changes include adding the ChatRecordingService
to record user messages, Gemini responses, tool calls, and token usage. The event structure for Finished
events has been updated across the codebase to include usageMetadata
, and tests have been added or updated to reflect these changes.
My review found a couple of issues: a duplicate module export and a potential bug related to a shallow copy being used where a deep copy was intended. Both are high-severity issues that should be addressed.
Hi @NTaylorMullen and @jacob314, this is PR tested and ready to merge. |
Hi @bl-ue! Really excited about this chat recording implementation series. I just commented on #3882 offering to help with testing - this feature addresses exactly what I was looking for. Specific help I could offer: 🧪 Testing:
📋 Code Review:
📖 Documentation:
Questions:
This looks like a substantial and well-thought-out implementation! 🚀 |
bf228df
to
def21c6
Compare
Next: #7662 |
This PR is the second in a series of 9 PRs that implement automatic chat recording and resuming in both interactive and non-interactive modes, with command line flags for non-interactive resuming and session management, and an interactive session browser.
PR #4401 was the original monolithic PR, which implemented this feature from the ground up. It's too large to merge as-is, however, and so it was broken up into 9 smaller PRs, of which this PR is the second.
Please see #4401's description for the full context of this PR. The original monolithic PR's description contains a detailed analysis of the entire system, with an example of the recording JSON, 30+ linked issues, and a demo video.