fix: emit tool_call_end events in OpenAI handler when streaming ends #10280
Conversation
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
The OpenAiHandler was not emitting tool_call_end events when the API stream ended with finish_reason === 'tool_calls'. This could cause the extension to appear stuck waiting for more stream data. Changes: - Added tracking of active tool call IDs in createMessage() and handleStreamResponse() - Emit tool_call_end events when finish_reason === 'tool_calls' - Added test coverage for both regular and O3 family models Closes: #10275 Linear: ROO-269
dosubot
bot
added
size:M
Contributor
Review complete. No issues found. The refactoring correctly extracts duplicate tool call processing logic into the new Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues. |
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
![roomote[bot]](https://avatars.githubusercontent.com/in/1546624?s=60&v=4){kind=small}
Consolidates the duplicated tool call processing logic from createMessage() and handleStreamResponse() into a single private helper method. This improves maintainability and ensures consistent behavior across both code paths.
mrubens
approved these changes
Dec 22, 2025
github-project-automation
bot
moved this from PR [Needs Review]
to Done
in Roo Code Roadmap
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Outdated suggestions cannot be applied.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
The
OpenAiHandlerwas not emittingtool_call_endevents when the API stream ended withfinish_reason === 'tool_calls'. This could cause the extension to appear stuck waiting for more stream data.Changes
src/api/providers/openai.tscreateMessage()andhandleStreamResponse()finish_reason === 'tool_calls', emittool_call_endevents for all tracked tool callssrc/api/providers/__tests__/openai.spec.tstool_call_endevents are emitted whenfinish_reason === 'tool_calls'Related
Important
OpenAiHandlernow emitstool_call_endevents when streaming ends withfinish_reason === 'tool_calls', ensuring proper event handling.OpenAiHandlernow emitstool_call_endevents whenfinish_reason === 'tool_calls'inopenai.ts.createMessage()andhandleStreamResponse().openai.spec.tsto verifytool_call_endevents are emitted for both regular and O3 family models.This description was created by
for 4f9bc49. You can customize this summary. It will automatically update as commits are pushed.