Uh oh!
There was an error while loading. Please reload this page.
fix(llm): serialize overlapping OpenAI reasoning - #37022
fix(llm): serialize overlapping OpenAI reasoning#37022xiaodream551-a11y wants to merge 1 commit into
Conversation
Thanks for your contribution! This PR doesn't have a linked issue. All PRs must reference an existing issue. Please:
See CONTRIBUTING.md for details. |
Thanks for updating your PR! It now meets our contributing guidelines. 👍 |
xiaodream551-a11y
commented
Jul 15, 2026
The linked issue is #36892 and the PR template now references it as |
Automated PR Cleanup Thank you for contributing to opencode. Due to the high volume of PRs from users and AI agents, we periodically close older PRs using automated criteria so maintainers can focus review time on the most active and community-supported contributions. This PR was closed because it matched the following cleanup criteria:
PRs created within the last month are not affected by this cleanup. If you believe this PR was closed incorrectly, or if you are still actively working on it, please leave a comment explaining why it should be reopened. A maintainer can review and reopen it if appropriate. Thanks again for taking the time to contribute. |
Issue for this PR
Fixes#36892
Type of change
What does this PR do?
OpenAI Responses can start another reasoning summary before the previous item has fully ended. V2 persists one reasoning block at a time, so those overlapping starts terminate the run with
reasoning start before end.This serializes overlapping reasoning events before publishing them, while retaining text/tool order and final encrypted continuation metadata. Reused provider block IDs are isolated so late deltas cannot merge into an earlier block.
How did you verify your code works?
bun run testinpackages/llm(319 passed, 29 skipped).bun run typecheckinpackages/llmandpackages/core.bun turbo typecheck --concurrency=3hook passed across 32 packages.Screenshots / recordings
Not applicable; this is a non-UI stream parser fix.
Checklist