fix(kun): preserve partial response on interrupt#276
Merged
XingYu-Zhong merged 1 commit intoJun 14, 2026
Merged
Conversation
4a27699 to
7159434
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Root cause
Assistant text deltas were emitted over SSE during streaming, but the accumulated assistant item was only persisted after a normal model completion. If the turn was aborted first, recovery from the runtime snapshot had no assistant item to render, so the UI appeared to roll back to the last user prompt.
Validation
Notes
npm --prefix kun test -- loop.test.tsstill has 3 existing compaction assertion failures unrelated to this change.