Transition to flash GA model when experiment flag is present.#27570
Conversation
|
Size Change: +4.3 kB (+0.01%) Total Size: 33.9 MB
ℹ️ View Unchanged
|
gemini-cli
Bot
added
the
status/need-issue
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 facilitates the transition of legacy Gemini Flash models to the GA version, gemini-3.5-flash. By implementing a gated rollout mechanism via experiment flags and updated access logic, the changes ensure that model resolution across the codebase correctly routes to the new GA model while maintaining backward compatibility for non-GA users. 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
|
![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 support for the gemini-3.5-flash model, including new configuration options, experiment flags, model resolution logic, and corresponding unit tests. Feedback on the changes highlights two key issues: first, the useGemini3_5Flash property is not handled in the matches method of ModelConfigService, which breaks dynamic model configuration resolution; second, when useGemini3_5Flash is false and preview access is disabled, gemini-3.5-flash should fall back to gemini-2.5-flash instead of gemini-3-flash-preview to prevent unauthorized model requests.
…h' into update_default_flash
…ll tool background tasks.
|
✅ 69 tests passed successfully on gemini-3-flash-preview. 🧠 Model Steering GuidanceThis PR modifies files that affect the model's behavior (prompts, tools, or instructions).
This is an automated guidance message triggered by steering logic signatures. |
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
|
/patch stable |
|
🚀 [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: |
2 participants
Summary
Transition legacy Gemini Flash models to GA by replacing them with
gemini-3.5-flash. This transition is gated by a new experiment flag and user access logic to ensure a safe rollout while maintaining backward compatibility for non-GA users.Details
GEMINI_3_5_FLASH_GA_LAUNCHEDexperiment flag (ID:45773135) (to be updated depending on final flag id).hasGemini35FlashGAAccess()in theConfigclass. GA access is automatically granted forUSE_GEMINI,USE_VERTEX_AI, andGATEWAYauthentication types, or if the experiment flag is active.resolveModelandresolveClassifierModelinmodels.tsto forced-resolve all flash models (gemini-2.5-flash,gemini-3-flash-preview, and theflashalias) togemini-3.5-flashwhen GA access is granted.resolveModelcall sites across the codebase (Client, GeminiChat, ContentGenerator, Routing Strategies, etc.) to pass the GA access status.gemini-3.5-flashindefaultModelConfigs.ts.ModelConfigServiceto handle the forced transition.packages/core/src/config/models.test.tsto verify resolution parity, GA transition, and fallback scenarios.Related Issues
Related to #27071
How to Validate
Run the dedicated model configuration unit tests:
All 82 tests (including new GA resolution cases) should pass.
Pre-Merge Checklist