fix: preserve LLM response telemetry on cancellation - #2048
Merged
Conversation
Finalize response attributes before stream cleanup so cancelled generations retain text, TTFT, and Python-compatible function calls. Co-authored-by: Cursor <cursoragent@cursor.com>
🦋 Changeset detectedLatest commit: c23ab51 The changes in this PR will be included in the next version bump. This PR includes changesets to release 37 packages
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 |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c23ab516be
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
u9g
approved these changes
Jul 16, 2026
Contributor
|
Thank you! |
Merged
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
llm_nodespans using the Python-compatible{ id, call_id, name, arguments }wire shapeAbortErrorregression coverage plus patch release metadataCloses #2043.
Test plan
pnpm test -- --run agents/src/voice/generation_telemetry.test.ts(2 passed)pnpm buildpnpm --filter @livekit/agents typecheckCue voice E2E
Exact head:
c23ab516sid_d83932e98ba4— real LiveKit Inference providers (OpenAI GPT-4.1 mini, Deepgram Nova-3, Cartesia Sonic-3). Path-specific predicatedebug_message(.payload.has_function_calls=true)resolved. The persisted event contains agetWeathercall serialized withid,call_id,name, and JSONarguments.sid_0562f88a1092— real STT, TTS, and adaptive interruption with a deterministic slow streaming LLM boundary. Predicateoverlapping_speech(.is_interruption=true) -> debug_message(.payload.controlled_stream_cancelled=true,.payload.response_text_length>0,.payload.has_ttft=true)[10s]resolved. The cancelled span retained 8,832 characters and TTFT; Cue also persisted the interrupted spoken prefix.manifest.json,events.jsonl, and per-commandresult.json/meta.jsonunder~/.cue-cli/sessions/<session>/. Both sessions were ended to flush artifacts. This Cue environment reported empty track maps, so it did not produce WAV files.