do not persist the fallback model

[sehoon38]

Summary

Do not persist the fallback model.

Details

When falling back from Auto mode to a Flash model, the change should not persist in the settings. This ensures that when a user restarts, they continue in Auto mode rather than remaining on the fallback model.

Related Issues

How to Validate

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run
    • npx
    • Docker
    • Podman
    • Seatbelt
  • Windows
    • npm run
    • npx
    • Docker
  • Linux
    • npm run
    • npx
    • Docker

[gemini-code-assist]

Summary of Changes

Hello @sehoon38, 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 introduces a crucial refinement to how model selections are handled, specifically preventing automatically applied fallback models from being permanently saved in user settings. By adding an isFallbackModel flag to the setModel method, the system can now differentiate between user-intended model changes and temporary, system-driven fallbacks. This ensures that users' original model preferences, such as 'Auto' mode, are preserved across sessions, providing a more consistent and predictable experience.

Highlights

• Config.setModel Update: The Config.setModel method now accepts an optional isFallbackModel boolean parameter, defaulting to false. This parameter signals whether the model change is a temporary fallback or a user-initiated selection.
• Persistence Logic Refinement: The onModelChange callback within Config.setModel (which is responsible for persisting model choices) will now only trigger if isFallbackModel is false. This ensures that temporary fallback models are not saved to user settings.
• useQuotaAndFallback Integration: The useQuotaAndFallback hook has been updated to pass true for the isFallbackModel parameter when it sets a fallback model, correctly preventing its persistence.
• Enhanced Test Coverage: New test cases have been added to config.test.ts to explicitly verify that onModelChange is not called when a model is set as a fallback. Existing tests in useQuotaAndFallback.test.ts were also updated to spy on setModel and confirm it's called with isFallbackModel: true during fallback scenarios.

🧠 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 👍 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. ↩

[github-actions]

Size Change: +49 B (0%)

Total Size: 22 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	22 MB	+49 B (0%)
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B

_{compressed-size-action}

[gemini-code-assist]

Code Review

This pull request aims to prevent fallback models from being persisted in the user's settings, which is a good goal. However, the current implementation in config.ts has a side effect: it modifies the user's configured model for the entire session, which can disrupt features like 'auto' model routing. I've suggested a refactor to setModel to correctly handle temporary fallbacks by only changing the active model for the session, not the user's saved configuration. I also found a misleading comment in useQuotaAndFallback.ts that should be updated to reflect the new behavior.