Post interruption context timing bleed

open

1 independent reportacross 1 sourceon 1 stacklast reported 2026-08-14

What this is

After the caller interrupts the agent, word-timing data from the interrupted turn keeps being applied because generation timing isn't scoped per turn, corrupting the record of which words the caller actually heard.

Status open: reported and still open where it was reported.

Evidence

timofey-TK2026-08-14pipecatGitHub issuesgithub.com/…/5325
...explicit synthetic sequence because timestamp transport is asynchronous and old-context events can arrive after interruption. ### Expected Behavior Generation offsets should be scoped by contextId. flushCompleted(A) must only advance A....

First seen 2026-08-14 · our copy fetched 2026-08-14T14:12:15Z · SHA-256 of that copy begins 459d3f56cebca7a5… · profile

Quotes run to 30 words around the reported failure and link to the post.Add your call to this entryTake a quote down within 24 hours.

What is measurable

SignalThis record stands on its own linked sources. To put a number on your own call, hotato autopsy ./call.wav reads a recording you already have and ranks the timing incidents in it.
EstablishesEvery report below links to the original post and names the handle that wrote it; the quote is at most 30 words around the reported failure.
What else it establishes, and what your own trace settles
  • The status changes only when a re-check stores the evidence link, the quote and the date behind the change.
  • Every timestamp comes from the fetched artifact it describes, recorded with the sha256 of the response body it was read from.

What your trace settles

  • Reproducing the mode on your own stack is the next step: the reports below carry the configuration each reporter was running.
TierAtlas record: every field on this page traces to a fetched public artifact. hotato is MIT and runs locally, getting started.

Status history

The record has carried one status since it opened: open, reported and still open where it was reported. A move lands here with the link, the quote and the date that show it.

Discussion

Reader discussion of this mode: what fixed it and what did not. The reports above are attributed and linked; a comment is a comment.

Open this discussion on GitHub

The record

Ids, digests, every link this entry stands on, and how to take a quote down
Atlas idVFA-2026-0034
Mode idpat_6a864297563c010350974440
Content digestsha256:6a864297563c0103509744409a1d0a91695ce6968978b49f2ae97dbccc19aad7
First reported2026-08-14
Last reported2026-08-14
First seen by the atlas2026-08-14T08:59:30Z
Last re-checked2026-08-14T08:59:30Z
Reported onpipecat
SourcesGitHub issues
Scope1 independent public report across 1 source. This entry states where the mode has been reported; where else it can occur is what the next report settles.
References
  1. reporthttps://github.com/pipecat-ai/pipecat/issues/5325 · timofey-TK · GitHub issues · 2026-08-14
Machine surfacesfeed.jsonfeed.atomfeed.schema.jsonatlas.llms.txt
RemovalIf you wrote something quoted on this page and want it gone, one email to [email protected] 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.