fix(patch): cherry-pick f08b4af to release/v0.45.2-pr-27749 to patch version v0.45.2 and create version 0.45.3#27769
Conversation
Summary of ChangesHello, 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 implements a model mapping mechanism to allow for dynamic redirection of AI model requests. It introduces a new generator wrapper that intercepts content generation calls and updates the requested model based on a provided mapping configuration. This change ensures that specific environments or authentication types can route requests to appropriate model versions while maintaining existing logging and wrapping infrastructure. Highlights
Using Gemini Code AssistThe 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
Customization To customize the 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 Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. 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
|
|
📊 PR Size: size/L
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new ModelMappingContentGenerator to dynamically map model names (such as mapping gemini-3.5-flash to gemini-3-flash under certain authentication configurations like LOGIN_WITH_GOOGLE and COMPUTE_ADC). It also updates getCodeAssistServer to recursively unwrap both LoggingContentGenerator and ModelMappingContentGenerator wrappers. The feedback highlights a potential bug in ModelMappingContentGenerator where direct property lookup on a plain object could conflict with built-in Object.prototype properties, and suggests a safer, more efficient lookup implementation.
|
Size Change: +3.76 kB (+0.01%) Total Size: 33.9 MB
ℹ️ View Unchanged
|
Co-authored-by: Gal Zahavi <38544478+galz10@users.noreply.github.com>
galdawave
deleted the
hotfix/v0.45.2/0.45.3/stable/cherry-pick-f08b4af/pr-27749
branch
3 participants
This PR automatically cherry-picks commit f08b4af to patch version v0.45.2 in the stable release to create version 0.45.3.