feat(model-availability): introduce ModelPolicy and PolicyCatalog

[adamfweidman]

Summary

This PR introduces the ModelPolicy and PolicyCatalog to enhance the management of model availability and fallback behavior within the CLI. It provides a structured way to define actions and state transitions based on different model failure kinds.

Details

The primary goal is to provide a flexible and configurable mechanism for model fallback, user prompting, and error handling. This allows us to easily control how gemini-cli should act in response to quota limits, capacity problems, or transient errors per Model.

Related Issues

Fixes https://github.com/google-gemini/maintainers-gemini-cli/issues/1073

How to Validate

npm run preflight

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 @adamfweidman, 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 establishes a robust framework for managing how the CLI interacts with different models, particularly when facing availability issues. It introduces a policy-driven approach to define fallback actions and state transitions, ensuring a more resilient and configurable system for handling various model failure scenarios like quota limits or transient errors.

Highlights

• Introduce ModelPolicy: A new ModelPolicy interface is introduced to define how the system should react to different model failure kinds, including actions (silent/prompt) and state transitions (terminal/sticky_retry).
• Introduce PolicyCatalog: A PolicyCatalog is added to manage and provide ordered chains of ModelPolicy objects, allowing for flexible model fallback behavior based on configurations like preview mode.
• Structured Fallback Behavior: This change provides a structured and configurable mechanism for handling model availability issues, such as quota limits, capacity problems, or transient errors, by defining specific actions and state changes per model.

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 well-structured ModelPolicy and PolicyCatalog system to manage model availability and fallback logic. The changes are clear, well-tested, and provide a flexible foundation for handling model failures. The separation of policy definition from its application is a good design choice. I have one suggestion to improve type consistency in getModelPolicyChain.

[github-actions]

Size Change: -2 B (0%)

Total Size: 21.2 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	21.2 MB	-2 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}