fix(ai-chat): close chat stream on socket disconnect#1487
Merged
Conversation
🦋 Changeset detectedLatest commit: 31deea1 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
agents
@cloudflare/ai-chat
@cloudflare/codemode
hono-agents
@cloudflare/shell
@cloudflare/think
@cloudflare/voice
@cloudflare/worker-bundler
commit: |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
threepointone
added a commit
that referenced
this pull request
May 11, 2026
* fix(voice): harden Workers AI STT turn handling Follow up on PR #1458 by preserving Flux turn transcripts across lifecycle events and using model-detected speech start for low-latency barge-in. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(chat): harden stream resume negotiation close races Follow-up to PR #1463: route stream-resume negotiation sends through close-safe helpers so WebSocket close races do not crash resume handling in think and ai-chat. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(voice): parse raw NDJSON text streams Follow-up to PR #1462: make the voice text stream parser honor its documented NDJSON support while preserving SSE parsing for AI text streams. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(agents): defer recovered agent-tool finish hooks (#1476) Co-authored-by: Cursor <cursoragent@cursor.com> * test(voice): cover useVoiceAgent enabled lifecycle (#1478) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(ai-chat): close resumed streams on disconnect (#1487) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(voice): invalidate playback on client interrupt (#1458) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(voice): invalidate playback when ending calls (#1458) Co-authored-by: Cursor <cursoragent@cursor.com> * Run deferred finish hooks after successful startup Ensure recovered agent-tool finish hooks are only executed after a successful user onStart. Await _runDeferredAgentToolFinishHooks inside the onStart flow so deferred finishes are skipped when startup fails. Add a test and helper (reconcileCompletedChildWithFailedStartupForTest) to verify finish hooks are not run on failed startup and to cover lifecycle ordering and event emission. --------- Co-authored-by: Cursor <cursoragent@cursor.com>
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.
Summary
Fixes #1485.
When an
AIChatAgentturn is interrupted by a Worker/socket restart,chatRecoverycan complete the recovered continuation under a new server-generated request id. The browser-sideWebSocketChatTransport.sendMessages()stream for the original request id was only closed by a matchingdone: trueframe. If the socket closed before that terminal frame arrived, the local stream stayed pending indefinitely, leaving AI SDKuseChat/useAgentChatstuck instatus === "streaming"even after the recovered continuation finished.This PR closes the original local
sendMessages()stream when the underlying socket closes, cleaning up its active request id so the AI SDK is not left waiting on an impossible terminal frame.Changes
closeevent listener inWebSocketChatTransport.sendMessages()that closes and cleans up the local stream.donelifecycle.@cloudflare/ai-chat.Verification
cd packages/ai-chat && npx vitest --run src/tests/ws-transport-resume.test.tsnpm run checkwas run;Notes
The fix is intentionally narrow: socket close means the original local stream can no longer receive its matching terminal frame on that socket. Closing it allows the AI SDK request state to settle while recovery/resume paths continue to handle any recovered stream under the new request id.