Open
Conversation
Coverage Report •
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit ac18405. Configure here.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.

Note
Medium Risk
Changes core agent streaming/parsing behavior for function-calling and parallel tool execution, which could affect event ordering and consumers that rely on prior streaming semantics. Risk is mitigated by new integration tests that validate streaming event sequences across inference modes.
Overview
Tool-input streaming is now more structured and reliable. The streaming parser emits a dedicated
tool_input_startevent (via newAgentToolInputStartData) before the firsttool_inputdelta, and refactors JSON-mode parsing to immediately advance to subsequent fields within the same chunk (fixing missedaction_inputwhen reasoning completes).Parallel tool-call metadata is enriched. Per-tool
thoughtis propagated through parallel tool-call schemas (ToolCallItem.thought) and into streamed batch reasoning payloads, and single-tool reasoning events are suppressed for tools executed in parallel to avoid duplicate/incorrect reasoning emission.Integration coverage is expanded for streaming correctness. Adds an FSM-based streaming assertion helper and updates/extends integration tests to enable streaming and verify valid event transitions across
DEFAULT,XML,STRUCTURED_OUTPUT, and nativeFUNCTION_CALLINGparallel modes.Reviewed by Cursor Bugbot for commit ac18405. Bugbot is set up for automated code reviews on this repo. Configure here.