Mark Backman
5f64dae0cf
Filter RTVIObserver to downstream frames only and broadcast FunctionCallCancelFrame
...
RTVIObserver now skips upstream frames to prevent duplicate RTVI messages
when frames are broadcast in both directions. Also changed
FunctionCallCancelFrame to use broadcast_frame for consistency with
other function call frames.
2026-02-09 12:39:25 -05:00
Mark Backman
d34f416281
Merge pull request #3598 from dhruvladia-sarvam/sarvam-v3-update
...
ASR and TTS v3 update
2026-02-07 10:51:35 -05:00
Mark Backman
5a1deb7cb4
Merge pull request #3659 from pipecat-ai/mb/change-vad-defaults
...
Set VADParams stop_secs to 0.2 by default
2026-02-06 23:51:50 -05:00
Mark Backman
a5fc2b1650
Set VADParams stop_secs to 0.2 by default
2026-02-06 23:49:08 -05:00
Aleix Conchillo Flaqué
5cb8d91431
added changelog file for #3616
2026-02-06 16:45:23 -08:00
Aleix Conchillo Flaqué
ce690848c0
Merge pull request #3616 from omChauhanDev/fix/function-call-timeout-task-cleanup
...
fix: ensure function call timeout task is always cancelled
2026-02-06 16:40:56 -08:00
Aleix Conchillo Flaqué
30f51edfcd
Merge pull request #3668 from pipecat-ai/aleix/parallel-pipeline-buffering
...
Buffer internal frames during ParallelPipeline lifecycle sync
2026-02-06 15:25:32 -08:00
Aleix Conchillo Flaqué
cd03d449cb
Update changelog skill with skip rules and allowed types
2026-02-06 15:23:14 -08:00
Aleix Conchillo Flaqué
57df03aade
Update CLAUDE.md with PR workflow instructions
2026-02-06 15:23:14 -08:00
Aleix Conchillo Flaqué
4945cfbd8f
Buffer internal frames during ParallelPipeline lifecycle synchronization
...
Processors inside parallel sub-pipelines can push frames during
StartFrame/EndFrame/CancelFrame processing. Previously these frames
could escape the ParallelPipeline before all branches finished
processing the lifecycle frame. Now they are buffered and flushed
after synchronization completes.
2026-02-06 15:15:46 -08:00
Mark Backman
8d37d3bae7
Merge pull request #3666 from pipecat-ai/mb/deepgram-stt-smart-format
...
DeepgramSTTService: disable smart_format by default
2026-02-06 14:04:37 -05:00
Mark Backman
d7b1624d3c
Merge pull request #3663 from lukepayyapilli/fix/stream-close-sambanova-google
...
fix: close stream on cancellation for SambaNova and Google OpenAI services
2026-02-06 14:02:31 -05:00
Mark Backman
7f65204c3b
DeepgramSTTService: disable smart_format by default
2026-02-06 13:45:10 -05:00
Aleix Conchillo Flaqué
97eff414c3
Merge pull request #3660 from pipecat-ai/aleix/interruption-frame-completion-event
...
Attach asyncio.Event to InterruptionFrame for completion signaling
2026-02-06 10:14:26 -08:00
Aleix Conchillo Flaqué
5b67e76de7
Add changelog for PR #3660
2026-02-06 10:11:00 -08:00
Aleix Conchillo Flaqué
b9e79bd06a
CLAUDE.md: explain about InterruptionFrame.complete()
2026-02-06 10:11:00 -08:00
Aleix Conchillo Flaqué
d5105a78e6
STTMuteFilter should call frame.complete() when InterruptionFrame is blocked
2026-02-06 10:11:00 -08:00
Aleix Conchillo Flaqué
a352b2d7a0
Add tests for InterruptionFrame completion event
...
Add tests for the event-based interruption completion: complete() sets
the event, complete() is safe without an event, the event fires at
the pipeline sink, and a warning is logged when the frame is blocked.
Also remove the unconditional await after the timeout so the function
returns instead of hanging when complete() is never called.
2026-02-06 09:57:24 -08:00
Aleix Conchillo Flaqué
2345090b10
Attach asyncio.Event to InterruptionFrame for completion signaling
...
Move the interruption wait event from per-processor instance state to
the frame itself. The event is created in
push_interruption_task_frame_and_wait(), threaded through
InterruptionTaskFrame → InterruptionFrame, and set when the frame
reaches the pipeline sink. This scopes the event to each interruption
flow rather than sharing mutable state on the processor.
Also adds a 2s timeout warning to help diagnose cases where
InterruptionFrame.complete() is never called.
2026-02-06 09:57:24 -08:00
Mark Backman
af562bf9a8
Merge pull request #3664 from pipecat-ai/mb/elevenlabs-scribe-v2
...
Update ElevenLabsSTTService to scribe_v2
2026-02-06 12:31:44 -05:00
Mark Backman
d4993f0dcf
Update ElevenLabsSTTService to scribe_v2
2026-02-06 11:37:23 -05:00
Luke Payyapilli
1790a84bfd
add changelog
2026-02-06 10:05:02 -05:00
Luke Payyapilli
29c53b99a4
fix: close stream on cancellation for SambaNova and Google OpenAI services
2026-02-06 10:02:40 -05:00
Mark Backman
aa5a855eab
Merge pull request #3656 from pipecat-ai/mb/openai-realtime-stt
...
Add OpenAIRealtimeSTTService
2026-02-06 09:15:58 -05:00
Mark Backman
e66d6f8ffe
Merge pull request #3658 from pipecat-ai/mb/bump-protobuf-5.29.6
...
Upgrade protobuf to >=5.29.6
2026-02-05 19:09:30 -05:00
Mark Backman
b8ac2ba713
Merge pull request #3593 from ianbbqzy/ian/inworld-auto-mode
...
Add auto_mode support for inworld plugin
2026-02-05 18:16:38 -05:00
Ian Lee
6eea40858e
fix lint and changelog
2026-02-05 15:10:36 -08:00
Mark Backman
90700d10aa
Upgrade protobuf to >=5.29.6
2026-02-05 18:08:52 -05:00
Mark Backman
fa85f7bbc7
Merge pull request #3640 from lukepayyapilli/fix/openai-stream-close
...
fix: close stream on cancellation to prevent socket leaks
2026-02-05 18:00:06 -05:00
Mark Backman
669f013970
Merge pull request #3657 from pipecat-ai/filipi/changing_no_audio_log_to_debug
...
Changing the ‘no audio received’ log from warning to debug.
2026-02-05 17:35:24 -05:00
filipi87
76f63e54e2
Changing the ‘no audio received’ log from warning to debug.
2026-02-05 18:07:14 -03:00
Filipi da Silva Fuchter
cce5a13444
Merge pull request #3650 from pipecat-ai/filipi/twilio_issues
...
Ignoring RTVI messages inside the Serializers by default.
2026-02-05 15:52:59 -05:00
Mark Backman
d11e1cd631
Update 13k to use ElevenLabsRealtimeSTTService
2026-02-05 15:48:00 -05:00
Mark Backman
8b9da632d1
Add OpenAIRealtimeSTTService
2026-02-05 15:48:00 -05:00
Mark Backman
b36f7892a4
Merge pull request #3654 from pipecat-ai/aleix/more-claude-update
...
CLAUDE.md: add RTVI and serializers
2026-02-05 15:23:35 -05:00
Mark Backman
9b43cde128
Merge pull request #3355 from itsderek23/user-bot-latency
...
Add `user_bot_latency_seconds` to OpenTelemetry turn spans
2026-02-05 15:23:15 -05:00
filipi87
6af4d872a8
Refactoring the serializers to ignore the RTVI messages by default.
2026-02-05 16:52:53 -03:00
Ian Lee
22398e1410
add changelog back
2026-02-05 11:39:39 -08:00
Ian Lee
d10467e043
update timestamps reset handling
2026-02-05 11:39:39 -08:00
Ian Lee
cbe131636d
add changelog
2026-02-05 11:39:39 -08:00
Ian Lee
fef9e3ea32
Add auto_mode support for inworld plugin
2026-02-05 11:39:39 -08:00
Mark Backman
56d8ef2bf4
Deprecate UserBotLatencyLogObserver, update 29 example
2026-02-05 14:29:45 -05:00
Derek Haynes
8791559351
Add changelog entry for PR #3355
2026-02-05 14:29:45 -05:00
Derek Haynes
f6c919354f
Add test for user bot latency
2026-02-05 14:29:45 -05:00
Derek Haynes
93138466d6
Feat: Add user-bot latency to OTel turn spans
...
This adds user-to-bot response latency tracking to OpenTelemetry spans:
- Created UserBotLatencyObserver as a reusable component for tracking
user-to-bot response latency
- Records the value as an attribute on turn spans (turn.user_bot_latency_seconds)
- Updated TurnTraceObserver to use UserBotLatencyObserver, following the same pattern as TurnTrackingObserver
- Updated PipelineTask to automatically create and wire UserBotLatencyObserver
when tracing is enabled (same as TurnTrackingObserver)
2026-02-05 14:29:42 -05:00
Mark Backman
5a5a98b497
Merge pull request #3649 from itsderek23/fix/tracing-orphan-spans
...
Fix orphan otel spans during flow initialization and transitions
2026-02-05 14:23:52 -05:00
Aleix Conchillo Flaqué
2b4f507d37
CLAUDE.md: add RTVI and serializers
2026-02-05 11:06:00 -08:00
Mark Backman
d6f3a90662
Merge pull request #3652 from pipecat-ai/mb/upgrade-small-webrtc-prebuilt-2.1.0
...
Upgrade pipecat-ai-small-webrtc-prebuilt to 2.1.0
2026-02-05 13:48:54 -05:00
Derek Haynes
8fb0e37965
Update changelog for #3649
2026-02-05 11:35:22 -07:00
Derek Haynes
0d45b48f7b
Fix import placement
2026-02-05 11:26:58 -07:00