3.0 changes

[jason43211]

Summary

Details

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

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Summary of Changes

Hello @jason43211, 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 significantly enhances the Gemini CLI by integrating Gemini 3 Pro, revamping the settings and model selection experience, and improving error handling for model interactions. It introduces new documentation pages for Gemini 3 and a comprehensive settings reference, alongside updates to existing CLI and IDE integration guides. These changes aim to provide users with more control over their CLI experience, better transparency regarding model usage, and a smoother interaction with advanced AI models.

Highlights

• Gemini 3 Pro Integration: Introduces support for Gemini 3 Pro, including a waitlist mechanism and instructions on how to enable it via new 'Preview Features' settings. This allows users to access advanced models and manage their usage with new fallback options.
• Comprehensive Settings Management: A new /settings command and a dedicated documentation page provide a centralized and detailed reference for all Gemini CLI configuration options, categorized for clarity and ease of use. This includes UI, model, context, and tool-related settings.
• Enhanced Model Selection Dialog: The /model command now features an updated dialog that dynamically displays model options, including Gemini 3 Pro when 'Preview Features' are enabled, and provides more context on model routing and fallback behavior.
• Improved Fallback and Error Handling: Refined logic for handling model quota and capacity errors, including interactive prompts for users to choose fallback options (retry, switch, upgrade) and specific handling for Preview Model failures to ensure a smoother user experience.
• IDE Integration Updates: Adds support for 'Antigravity' IDE and clarifies error messages related to IDE companion extension, expanding the range of supported development environments.
• Persistent State Management: A new utility for simple JSON-based persistent state storage has been implemented, allowing the CLI to remember user preferences like banner display counts across sessions.

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 significant number of changes for the 3.0 release, including support for Gemini 3 preview models, a new settings system, dynamic UI banners, and greatly improved error and fallback handling. The changes are extensive and well-structured. I've identified one potential high-severity issue related to error handling for the new preview models that could affect the application's resilience. Overall, this is a solid update with many valuable improvements.

[gemini-code-assist]

The retry logic for InvalidStreamError is now restricted to only apply to Gemini 2.x models. This means that if a preview model (like Gemini 3) produces an invalid stream (e.g., a tool call without a finish reason), the request will fail immediately without any retries. Given that preview models can sometimes have unexpected behavior, removing this resilience mechanism could lead to a less stable experience for users on the preview track. Consider re-enabling this retry logic for all models or specifically for preview models to improve robustness.