Repository navigation
fix(google): correct model discovery and embedding limits - #120
Merged
Merged
Conversation
Fodesu
force-pushed
the
fix/google-embedding-model-discovery
branch
from
October 13, 2026 13:04
868703c to
2528eb1
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
nextPageTokenwhen listing both generative and embedding modelsTests
go test ./...GOTOOLCHAIN=go1.26.1 golangci-lint rungo vet ./provider/google/...git diff --check origin/main...HEADLive smoke test
Ran the PR branch's actual providers against TokenFlux's Gemini-native
https://tokenflux.dev/v1beta/modelsendpoint using a disposable test credential:generativeai.Provider.ListModels: succeeded and decoded 3 generative modelsembedding.Provider.ListModels: request and decoding succeeded; this credential exposes no embedding modelspageSize=1000requestTokenFlux returned no
nextPageTokenand ignorespageSize=1, so multi-page traversal remains covered by the mock-server tests rather than this live smoke test. The batch embedding limit was not exercised because the credential exposes no embedding model.