fix(self-improving-mastra): use gemini-2.5-flash on GCP (broadly available)#652
Merged
Merged
Conversation
…lable) gemini-3.5-flash (Gemini 3.x) is served only via Vertex's global endpoint and is not offered on-demand in many regions (including the sample's europe-west2), so using it needs per-org enablement / manual setup — and Defang ties VERTEXAI_LOCATION to the deploy region for explicit models. Switch GCP back to the GA gemini-2.5-flash, which is broadly available on-demand across regions (including europe-west2) with no special configuration. AWS keeps z.ai GLM 5. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #651.
Why
gemini-3.5-flash(Gemini 3.x) turned out to need human/org setup to deploy: it's served only via Vertex's global endpoint and isn't offered on-demand in many regions (including the sample'seurope-west2), and Defang tiesVERTEXAI_LOCATIONto the deploy region for explicit models. That's too much friction for a sample.What
Switch GCP back to the GA
gemini-2.5-flash— broadly available on-demand across regions (includingeurope-west2) with no special configuration. This is the model the sample used before (as thechat-defaultalias), so it's already known-good in the current region.AWS is unchanged (
zai.glm-5/ z.ai GLM 5).Files:
.env.gcp(CHAT_MODEL), plus README model references (dropped the global-endpoint caveat).🤖 Generated with Claude Code
Samples Checklist
✅ All good!