[AI] Add hybrid inference support in GenerativeModelSession

[andrewheard]

WIP - not ready for review

Started adding support for hybrid (on-device and cloud) inference. This is internally implemented as an array of fallback models, trying one model session and moving onto the next. This will be publicly exposed as "prefer cloud" or "prefer on-device", which just impacts the order of the models in the array. This could be expanded to other fallback strategies in the future if desired (e.g., Vertex AI --> Gemini Dev API, Gemini 3.1 --> Gemini 2.5) to handle cases when backends or models are resource constrained.

Note: Streaming is not yet implemented and fails if the first preference fails.

TODOs:

• Add a public API
• Add more integration tests and add unit tests
• Add documentation
• Add changelog entry
• Tons of cleanup

#no-changelog

[gemini-code-assist]

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

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.