fix(patch): cherry-pick ee6556c to release/v0.21.0-preview.1-pr-14691 to patch version v0.21.0-preview.1 and create version 0.21.0-preview.2

[gemini-cli-robot]

This PR automatically cherry-picks commit ee6556c to patch version v0.21.0-preview.1 in the preview release to create version 0.21.0-preview.2.

[gemini-code-assist]

Summary of Changes

Hello @gemini-cli-robot, 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 streamlines and enhances the chat session summary generation process within the CLI. By shifting summary creation to a background task on application startup and implementing more sophisticated logic for identifying eligible sessions, it aims to improve the user experience by ensuring summaries are generated efficiently and reliably without blocking application flow. The changes also involve a move to direct file system management for session data and include an authentication refresh step to support summary generation.

Highlights

• Refactored Session Summary Generation: The mechanism for generating chat session summaries has been significantly refactored, moving from a synchronous cleanup task to an asynchronous, fire-and-forget background process initiated on application startup.
• Improved Session Identification for Summaries: New logic (getPreviousSession) has been introduced to intelligently identify the most recent chat session that requires a summary, considering factors like existing summaries and the number of user messages.
• Direct File System Interaction: Summary generation now directly interacts with session files on the file system using node:fs/promises for reading and writing, enhancing control and robustness.
• Authentication for Summary Generation: Added a pre-check to refresh authentication for summary generation when the --list-sessions flag is used, ensuring summaries can be generated if authentication is configured.

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. ↩

[gemini-code-assist]

Code Review

This pull request refactors the session summary generation logic. Instead of generating a summary on application exit, it now generates a summary for the previous session on startup, running as a background, fire-and-forget task. This is a good improvement for user experience, as it avoids a delay on exit. The related changes across the CLI and core packages correctly support this new behavior. My review identifies one high severity issue: a race condition in the summary generation that could lead to redundant and costly LLM API calls if multiple CLI instances are started in quick succession. I've provided a code suggestion to resolve this using a file-based locking mechanism.

[github-actions]

Size Change: +2.97 kB (+0.01%)

Total Size: 21.6 MB

Filename	Size	Change
./bundle/gemini.js	21.5 MB	+2.97 kB (+0.01%)

ℹ️ View Unchanged

Filename	Size
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB
./bundle/sandbox-macos-permissive-open.sb	890 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB

_{compressed-size-action}