Repository navigation
fix(ai): add missing results for trailing tool calls - #52421
Merged
Merged
Conversation
This was referenced Oct 6, 2026
Ichinose-Kazuki
pushed a commit
to Ichinose-Kazuki/opencode
that referenced
this pull request
Oct 7, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
No linked issue.
Type of change
What does this PR do?
Tool history normalization already adds a
Tool result missingerror result for an unanswered local tool call when the next user or assistant message arrives. A call at the very end of the history was left unanswered on purpose, so the request reached the provider with a call and no result, which providers reject.This adds the same error result at the end of the history. Real results are kept, and provider-executed calls are still left alone. The tool is not run and is not reported as successful; the model is told the result is missing.
The provider test changes are fixtures whose history ends with an unanswered call. They now check the call message itself, or include the added error result where it was part of the asserted list.
How did you verify your code works?
tool-historytests: trailing calls get an error result, available results are kept, and provider-executed calls are unchanged.bun testinpackages/ai: 1672 pass, 0 fail.bun test test/session-runner.test.ts test/session-runner-tool-events.test.tsinpackages/core: 246 pass.bun typecheckinpackages/aiand rootbun run check.Screenshots / recordings
Not a UI change.
Checklist