fix(patch): cherry-pick 601a639 to release/v0.11.0-preview.0-pr-11889 to patch version v0.11.0-preview.0 and create version 0.11.0-preview.1

[gemini-cli-robot]

This PR automatically cherry-picks commit 601a639 to patch version v0.11.0-preview.0 in the preview release to create version 0.11.0-preview.1.

[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 enhances the configuration system by introducing dynamic control over the model router based on the authentication method. It allows for specific authentication types to automatically disable the model router, while also ensuring that any user-selected model is consistently maintained across authentication refreshes. The primary goal is to provide more flexible and context-aware management of model routing within the application.

Highlights

• Dynamic Model Router Control: The useModelRouter setting can now be dynamically enabled or disabled based on the active authentication method, providing more granular control over model routing behavior.
• Auth-Specific Disablement: A new configuration option, disableModelRouterForAuth, has been introduced to specify authentication types for which the model router should be automatically disabled. By default, AuthType.LOGIN_WITH_GOOGLE (oauth-personal) will disable the model router.
• Model Preservation: The user's explicitly chosen model is now preserved across refreshAuth calls, ensuring that model selections are maintained even if the model router's state changes due to authentication type.
• Updated Test Coverage: New tests have been added to validate the dynamic behavior of the model router with different authentication types and to confirm proper model preservation.

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 introduces a mechanism to conditionally disable the model router based on the authentication method. It adds a disableModelRouterForAuth configuration option, which defaults to disabling the router for personal Google accounts. The logic in refreshAuth is updated to handle this, and new tests are added to verify the behavior.

The changes are logical, but I've identified one high-severity issue in config.ts where the user's explicitly configured model can be silently overridden when useModelRouter is enabled. This could lead to unexpected behavior and model usage. My review includes a specific suggestion to correct this by removing the implicit model-switching logic, ensuring the user's configuration is always respected.

[gemini-code-assist]

This else if block can lead to unexpected behavior by implicitly changing the user's configured model. If a user explicitly sets useModelRouter: true and model: 'gemini-2.5-pro' (which is DEFAULT_GEMINI_MODEL), this logic will silently change their model to 'auto'. This violates the principle of least astonishment.

A user should be required to explicitly set model: 'auto' to opt into the model routing classification strategy. The model router can still provide value for other strategies (like FallbackStrategy) even when a specific model is pinned.

To avoid this surprising side-effect, it's better to remove this automatic model switching.

    }

[github-actions]

Size Change: +689 B (0%)

Total Size: 20.1 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	20.1 MB	+689 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}