fix(gemini): fix tool calling and thought-signature round-trip - #1389
Merged
Conversation
- send tool declarations, system prompt, and sampling/thinking settings in the camelCase shape the Google SDK forwards so tool calls reach the model - thread tool-call extras (thought signatures) through the loop tool-call event into context so Gemini 3 can resume a tool turn - update and add tests for the corrected request shape and signature round-trip
🦋 Changeset detectedLatest commit: 1d90bac The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
commit: |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Related Issue
No linked issue. The problem is described below.
Problem
Tool calling was broken for the Google Gemini provider: tool definitions, system prompts, and most sampling/thinking settings were silently dropped before reaching the model, so Gemini models never issued tool calls. Separately, on Gemini 3 thinking models the thought signature returned with a function call was not echoed back, so the turn after a tool call was rejected.
What changed
Verified end-to-end against a live Gemini model: a forced shell tool call executed and the model returned its final answer (exit 0).
Checklist
gen-changesetsskill, or this PR needs no changeset.gen-docsskill, or this PR needs no doc update.