Respect backend definitions for 3.5 flash and Update auto mode to use 3.5 flash when the flag is enabled.#27645
Conversation
…t backend naming conventions while properly dispalyign what model is being used.
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 introduces logic to prioritize Gemini 3.5 Flash for autonomous tasks when the appropriate feature flag is active. By refining the model resolution and classifier routing, the changes ensure that the 'auto' and 'flash' aliases align with the GA model while preserving the ability for users to manually select preview models. The update also includes necessary UI adjustments and comprehensive test coverage to validate the new routing logic. 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 configuration and resolution logic updates to support Gemini 3.5 Flash GA access, integrating the useGemini3_5Flash flag across CLI components, configuration services, and model dialogs. Feedback on the changes highlights a few issues: an unused property useGemini3_Flash was added to ModelResolutionContext, the 'gemini-3-flash' model needs to be added to VALID_GEMINI_MODELS to prevent it from being treated as inactive, and some test descriptions in config.test.ts and models.test.ts are inaccurate and contradict their corresponding assertions.
Note: Security Review did not run due to the size of the PR.
|
Size Change: +1.4 kB (0%) Total Size: 33.9 MB
ℹ️ View Unchanged
|
gemini-cli
Bot
added
the
status/need-issue
…kends that require 3-flash as the sent name.
…t config to have been able to update default model names.
|
/patch preview |
|
🚀 [Step 1/4] Patch workflow(s) waiting for approval! 📋 Details:
⏳ Status: The patch creation workflow has been triggered and is waiting for deployment approval. Please visit the specific workflow links below and approve the runs. 🔗 Track Progress: |
|
🚀 [Step 2/4] Patch PR Created! 📋 Patch Details:
📝 Next Steps:
🔗 Track Progress: |
|
🚀 [Step 3/4] Patch Release Waiting for Approval! 📋 Release Details:
⏳ Status: The patch release has been triggered and is waiting for deployment approval. Please visit the specific workflow run link below and approve the deployment. You'll receive another update when it completes. 🔗 Track Progress: |
|
✅ [Step 4/4] Patch Release Complete! 📦 Release Details:
🎉 Status: Your patch has been successfully released and published to npm! 📝 What's Available:
🔗 Links: |
… 3.5 flash when the flag is enabled. (google-gemini#27645)
… 3.5 flash when the flag is enabled. (google-gemini#27645)
… 3.5 flash when the flag is enabled. (#27645)
… 3.5 flash when the flag is enabled. (google-gemini#27645)
2 participants
Summary
This PR updates the model resolution logic to prioritize Gemini 3.5 Flash over Gemini 3 Flash Preview when the
useGemini3_5Flashflag is active (controlled byhasGemini35FlashGAAccess). This ensures that the 'auto' model alias and the 'flash' classifier tier consistently use the GA model for autonomous tasks, while still allowing users to manually select the preview model if needed.Details
getAutoModelDescriptionto include "Gemini 3.5 Flash" in the UI when the launch flag is set.resolveModelandresolveClassifierModelinpackages/core/src/config/models.tsto route 'auto' and 'flash' aliases togemini-3.5-flash.gemini-3-flash-previewis respected and not auto-upgraded, preserving compatibility for users with specific backend requirements.DEFAULT_MODEL_CONFIGSto align dynamic resolution with the legacy path.ModelDialog.tsxandacpUtils.tsto correctly calculate and pass theuseGemini3_5Flashstate.models.test.tsto verify the new resolution behavior and parity between legacy and dynamic paths.Related Issues
Related to Gemini 3.5 Flash integration.
How to Validate
npm test -w @google/gemini-cli-core -- src/config/models.test.tsnpm test -w @google/gemini-cli -- src/ui/components/ModelDialog.test.tsxnpm run startand then/modelor use the UI) and verify that "Gemini 3.5 Flash" appears in the "Auto" description.Pre-Merge Checklist