When the caller interrupts the agent mid-speech, the system's interrupt handling fails to cleanly tear down the in-progress turn, corrupting the conversation state.

What this is

Filed as Barge-in teardown race, the name every report of this mode is collected under.

A failure mode is one named thing that goes wrong on a live call. This record carries every public report of it the atlas has found, in each reporter's own words, and a status that moves only when a re-check stores the artifact behind the move. Status acknowledged: the thread it was reported in has been acknowledged upstream.

Evidence

Every independent public report of this mode, newest first: who wrote it, where, when, what they said, and the link back to the post it came from.

1. kyle_shechtmanon community.livekit.io2026-07-25livekit

   ...speech handle remained current for approximately 293 seconds and was repeatedly targeted by subsequent interruptions. During that period, eight later LLM and TTS operations completed successfully, but there were no...

   https://community.livekit.io/t/node-1-5-3-pre-playout-interruption-wedges-current-speech-later-llm-tts-succeed-but-the-call-stays-silent/1728

   first seen 2026-07-25 · fetched 2026-07-25T19:13:16Z · body sha256 567777915ec2711a

2. arsenieciprianon GitHub issues2026-07-24livekit

   Summary When the user interrupts the agent (barge-in) in a cascaded AgentSession using the Google plugin (Vertex AI), the truncated assistant message is committed to the chat context after...

   https://github.com/livekit/agents-js/issues/2108

   first seen 2026-07-24 · fetched 2026-07-25T17:50:27Z · body sha256 152a8e13216dffc9

3. Raysharron GitHub issues2026-07-19livekitsilero

   Describe the bug In @livekit/agents 1.5.3, when a pipeline reply is interrupted before its playout has started, AgentActivity.mainTask can hang forever on the interrupted speech handle's generation future. currentSpeech...

   https://github.com/livekit/agents-js/issues/2065

   first seen 2026-07-19 · fetched 2026-07-25T19:11:42Z · body sha256 cc6b78bc59ee42a3

4. thecarlmartinon GitHub issues2026-07-12livekitopenai-realtime

   Bug Description On a livekit-plugins-xai realtime call, an interruption can desync the plugin's local RemoteChatContext from xAI's server-side item list. Once that happens, every subsequent conversation.item.added is dropped, because...

   https://github.com/livekit/agents/issues/6391

   first seen 2026-07-12 · fetched 2026-07-26T22:06:27Z · body sha256 fb48d33249c3cc8f

5. timofey-TKon GitHub issues2026-06-01pipecat

   ...single aggregation buffer. That buffer is only cleared by push_aggregation() (on LLMFullResponseEndFrame) and by handle_interruptions(). The turn-start path does not clear it: python async def handle_llm_start(self, : LLMFullResponseStartFrame): await self.trigger_assistant_turn_started()...

   https://github.com/pipecat-ai/pipecat/issues/4611

   first seen 2026-06-01 · fetched 2026-07-25T17:50:31Z · body sha256 4891230123214ad1

6. OlliTapioon GitHub issues2026-03-27pipecattwilio

   ...function_name="save_notes", arguments={}, ) # Simulate: FunctionCallsStartedFrame adds orphan entry aggregator.function_calls_in_progress[call_1.tool_call_id] = None # Simulate: InterruptionFrame arrives — no FunctionCallCancelFrame emitted # aggregator.function_calls_in_progress still has {"call_1": None} # Turn 2: LLM...

   https://github.com/pipecat-ai/pipecat-flows/issues/246

   first seen 2026-03-27 · fetched 2026-07-25T17:50:33Z · body sha256 c4f08a35b3de8b4a

7. R_Studenton Stack Overflow2026-01-14openai-realtimetwilioCC BY-SA 4.0

   OpenAI Realtime Proper way to truncate a live streaming conversation on speech interruption Twilio media streams

   https://stackoverflow.com/questions/79867418/openai-realtime-proper-way-to-truncate-a-live-streaming-conversation-on-speech-i

   first seen 2026-01-14 · fetched 2026-07-24T20:54:01Z · body sha256 d2ac04d9774ae9aa

Each quote is at most 30 words around the reported failure and links to the post it came from. If you wrote one of these and want it off this page, the removal path takes it down within 24 hours.

What is measurable

Evidence tier: Tier 1 · dual-channel audio: caller and agent separated at capture, so overlap and timing are facts of the recording, exact to the sample.

What it establishes

• The seconds of overlap where the caller had taken the floor and the agent kept speaking, with the timestamp in the call where it started.
• The same recording produces the same overlap on every run, so the number is comparable across builds.

What your trace settles

• Your pipeline trace at that timestamp names what held the floor: the interrupt handler, the VAD threshold, or the realtime API's own turn logic.
• Whether the caller meant to interrupt is a judgement about the conversation; the measurement covers who held the floor and for how long.

# Printed as BARGE-IN: the caller took the floor and the agent kept speaking...
hotato autopsy ./call.wav

A shipped hotato subcommand maps to this mode, as detector kind overlap_while_agent_talking. Printed as BARGE-IN: the caller took the floor and the agent kept speaking, reported with the overlap in seconds. Needs the caller and agent on separate channels. hotato is MIT and runs locally. getting started.

Status history

A daily re-check reads every source thread on this page. The status moves when that re-check stores the link, the quote and the date behind the move, so every state on this record is one you can open.

1. open→acknowledged2026-07-26

   issue closed (completed)

   https://github.com/pipecat-ai/pipecat-flows/issues/246

   evidence dated 2026-07-02

Related modes

Entries this one shares evidence with. Each line names the share that put it there: a stack both were reported on, a post that named both, or the detector kind that measures both.

• Endpoint misdetectionacknowledgedVFA-2026-0002

  End-of-turn detection fires at the wrong moment, so the agent either answers before the caller has finished or waits after they have.

  shares: reported on livekit; reported on pipecat; reported on silero; reported on twilio; reported on github; reported on livekit_forum

• AMD premature timeout before answeropenVFA-2026-0019

  On outbound calls, the answering-machine-detection timer starts before the callee has actually answered, so ring or early media triggers a...

  shares: reported on livekit; reported on twilio; reported on github

• Agent dispatch latency before connectopenVFA-2026-0012

  The agent process is dispatched to an inbound call so many seconds after it arrives that the caller has already hung up before the agent...

  shares: reported on livekit; reported on twilio; reported on livekit_forum

• Agent interrupts calleropenVFA-2026-0004

  The agent starts speaking while the caller still holds the floor, cutting the caller off mid-utterance.

  shares: reported on livekit; reported on openai-realtime; reported on github

The record

Atlas id

VFA-2026-0001

Mode id

pat_d4645a0f0620c222f17fdbc4

Content digest

sha256:d4645a0f0620c222f17fdbc428d5e52274ae402e732d2d76a0b12913ed68d5b9

First reported

2026-01-14

Last reported

2026-07-25

First seen by the atlas

2026-07-15T10:59:40.675Z

Last re-checked

2026-07-25T18:58:59.839Z

Reported on

livekitopenai-realtimepipecatsilerotwilio

Sources

GitHub issues, community.livekit.io, Stack Overflow

Scope

7 independent public reports across 3 sources. This entry states where the mode has been reported; where else it can occur is what the next report settles.

References

Every link this entry stands on: the post behind each report, and the artifact behind each status move.

1. reporthttps://community.livekit.io/t/node-1-5-3-pre-playout-interruption-wedges-current-speech-later-llm-tts-succeed-but-the-call-stays-silent/1728 · kyle_shechtman · community.livekit.io · 2026-07-25
2. reporthttps://github.com/livekit/agents-js/issues/2108 · arsenieciprian · GitHub issues · 2026-07-24
3. reporthttps://github.com/livekit/agents-js/issues/2065 · Raysharr · GitHub issues · 2026-07-19
4. reporthttps://github.com/livekit/agents/issues/6391 · thecarlmartin · GitHub issues · 2026-07-12
5. reporthttps://github.com/pipecat-ai/pipecat/issues/4611 · timofey-TK · GitHub issues · 2026-06-01
6. reporthttps://github.com/pipecat-ai/pipecat-flows/issues/246 · OlliTapio · GitHub issues · 2026-03-27
7. reporthttps://stackoverflow.com/questions/79867418/openai-realtime-proper-way-to-truncate-a-live-streaming-conversation-on-speech-i · R_Student · Stack Overflow · 2026-01-14

Machine surfaces

Removal

If you wrote something quoted on this page and want it gone, one email does it. The removal path takes the quote, the handle and the link off this page, out of the feeds and out of the llms.txt within 24 hours, and tombstones the id so the entry cannot quietly return at a new address.