Repository navigation
fix: replace retired gemini-2.5-flash with gemini-3.8-flash - #25
Merged
Merged
Conversation
gemini-2.5-flash was retired for new API keys: it still shows up in ListModels but 404s on generateContent, so anyone bringing a new Gemini key through LLM Settings or the server-side proxy got a broken model with no obvious cause. Points to gemini-3.8-flash everywhere the model id was hardcoded (streaming chat path, the API proxy route, and the local verify script). Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
FloareDor
added a commit
that referenced
this pull request
Nov 8, 2026
fix: replace retired gemini-2.5-flash with gemini-3.8-flash
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
gemini-2.5-flashwas retired for new API keys: it still shows up inListModelsbut 404s ongenerateContent, so anyone bringing a new key through LLM Settings or the server-side proxy got a broken model with no obvious cause.gemini-3.8-flashin the three places it was set: the streaming chat path (src/lib/llm.ts), the server-side API proxy (src/app/api/gemini/route.ts), and the local key-verification script (scripts/verify-gemini.js).Test plan
node scripts/verify-gemini.jswith a fresh key and confirm success🤖 Generated with Claude Code