fix(gemma): resolve 404 errors and improve port resolution

[Abhijit-2592]

Summary

This PR resolves 404 errors encountered when using the LiteRT-LM server with the Gemini SDK by ensuring the correct API version (v1beta) is used. It also improves the user experience by dynamically resolving the server port from project settings in the gemma CLI commands.

Details

• LocalLiteRtLmClient: Explicitly set apiVersion: 'v1beta' and vertexai: false in the GoogleGenAI constructor. The local LiteRT-LM server follows the v1beta endpoint structure, and the SDK defaults to v1, causing 404s.
• gemma CLI commands: Updated start, status, and stop commands to read the port from experimental.gemmaModelRouter.classifier.host in the settings file if the --port flag is not provided.
• Linting: Fixed unsafe type assertions and restricted syntax (typeof on object properties) to comply with project standards.

Related Issues

Related to sameez/gemma-auto-setup.

How to Validate

1. Configure a custom port in your settings (e.g., experimental.gemmaModelRouter.classifier.host: "http://localhost:1234").
2. Run gemini gemma start and verify it uses the configured port.
3. Verify that LocalLiteRtLmClient tests pass: npm test -w @google/gemini-cli-core -- src/core/localLiteRtLmClient.test.ts.

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

[gemini-code-assist]

Summary of Changes

Hello, 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 improves the robustness of the LiteRT-LM server integration by fixing API version mismatches that caused 404 errors. Additionally, it streamlines the developer experience by allowing the CLI tools to intelligently detect the server port from existing project configurations, reducing the need for manual flag management.

Highlights

• API Compatibility: Updated the GoogleGenAI client configuration to explicitly use 'v1beta' and disable vertexai, resolving 404 errors when communicating with the LiteRT-LM server.
• Dynamic Port Resolution: Enhanced the CLI commands (start, status, stop) to automatically resolve the server port from the project settings if not explicitly provided via the --port flag.
• Testing: Added verification in the unit tests to ensure the client is initialized with the correct API version and base URL.

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.

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-cli]

Hi @Abhijit-2592, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.

We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: Improving Our Contribution Process & Introducing New Guidelines.

Key Update: Starting January 26, 2026, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.

Thank you for your understanding and for being a part of our community!

[gemini-code-assist]

Code Review

This pull request updates the Gemma-related CLI commands (start, status, stop) to resolve the server port from configuration settings if not explicitly provided via the command line. It also updates the LocalLiteRtLmClient to use the v1beta API version and adds corresponding test assertions. Feedback highlights significant code duplication in the port resolution logic across multiple files and identifies an issue where the status command's default Yargs configuration prevents the new settings-based port resolution from taking effect.

[Samee24]

LGTM