Paul Kompfner
be49a54856
Fast-exit in the fix for parallel function calling with Gemini 3, if we can determine up-front that there's no work to do
2026-01-13 17:32:20 -05:00
Paul Kompfner
30fbcfbf71
Rework fix for parallel function calling with Gemini 3
2026-01-13 16:33:59 -05:00
Paul Kompfner
8812686b17
Fix parallel function calling with Gemini 3.
...
Gemini expects parallel function calls to be passed in as a single multi-part `Content` block. This is important because only one of the function calls in a batch of parallel function calls gets a thought signature—if they're passed in as separate `Content` blocks, there'd be one or more missing thought signatures, which would result in a Gemini error.
2026-01-13 11:03:38 -05:00
kompfner
8b0f0b5bb4
Merge pull request #3425 from pipecat-ai/pk/gemini-3-flash-new-thinking-levels
...
Add Gemini 3 Flash-specific thinking levels
2026-01-13 11:02:53 -05:00
Mark Backman
a298ce3b41
Merge pull request #3424 from pipecat-ai/mb/tts-append-trailing-space
...
Add append_trailing_space to TTSService to prevent vocalizing trailin…
2026-01-13 10:42:40 -05:00
Mark Backman
31daa889e8
Add append_trailing_space to TTSService to prevent vocalizing trailing punctuation; update DeepgramTTSService and RimeTTSService to use the arg
2026-01-13 10:38:54 -05:00
Paul Kompfner
76a058178e
Add Gemini 3 Flash-specific thinking levels
2026-01-13 09:50:59 -05:00
Mark Backman
cd3290df1c
Small cleanup for task creation in SpeechmaticsSTTService
2026-01-12 16:00:32 -05:00
Mark Backman
90ded6658d
Merge pull request #3403 from pipecat-ai/mb/inworld-tts-add-keepalive
...
InworldTTSService: Add keepalive task
2026-01-12 13:31:24 -05:00
Mark Backman
7e97fb80a5
Merge pull request #3392 from pipecat-ai/mb/websocket-service-connection-closed-error
...
Add reconnect logic to WebsocketService in the event of ConnectionClo…
2026-01-12 13:11:43 -05:00
Aleix Conchillo Flaqué
46b4f9f29b
Merge pull request #3413 from pipecat-ai/aleix/fix-assistant-thought-aggregation
...
LLMAssistantAggregator: reset aggregation after adding the thought, not before
2026-01-12 09:21:42 -08:00
Aleix Conchillo Flaqué
ec20d72aba
LLMAssistantAggregator: reset aggregation after adding the thought, not before
2026-01-12 09:18:13 -08:00
Varun Pratap Singh
3e982f7a4a
refactor: rename audio_packet_bytes to fixed_audio_packet_size
2026-01-12 22:11:39 +05:30
Varun Pratap Singh
e96595fe59
feat: update FastAPI WebSocket transport and add Vonage serializer
2026-01-12 17:50:38 +05:30
Mark Backman
f58d21862b
WebsocketService: Add _maybe_try_reconnect and use for exception cases
2026-01-11 16:43:37 -05:00
Mark Backman
aac24ad2d4
InworldTTSService: Add keepalive task
2026-01-10 11:20:20 -05:00
Aleix Conchillo Flaqué
64609fe80f
BaseOutputTransport: ensure bot speaking flag is set on time
2026-01-09 20:40:25 -08:00
Aleix Conchillo Flaqué
b59c3eb470
GroqTTSService: switch to canopylabs/orpheus-v1-english
2026-01-09 18:14:48 -08:00
Aleix Conchillo Flaqué
d86ff4b1ee
Merge pull request #3397 from pipecat-ai/aleix/add-setup-pipeline-task
...
PipelineTask: add external pipeline task setup files
2026-01-09 17:39:25 -08:00
Mark Backman
9c81acb159
Track websocket disconnecting status to improve error handling
2026-01-09 20:24:07 -05:00
Aleix Conchillo Flaqué
d2696be03b
PipelineTask: add external pipeline task setup files
2026-01-09 16:42:27 -08:00
Aleix Conchillo Flaqué
2da4d420f9
PipelineTask: add pipeline property
2026-01-09 15:47:02 -08:00
Aleix Conchillo Flaqué
c813d43da0
Merge pull request #3343 from omChauhanDev/fix/auto-resolve-function-result
...
fix: keeping the Aggregator and Service states synchronized.
2026-01-09 10:04:20 -08:00
Aleix Conchillo Flaqué
25f6ba76d6
add start timestamp to user and assistant turn messages
2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
5f9e95038e
BaseObject: improve logging messages
2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
5cbb21afb2
deprecate TranscriptProcessor and related dataclasses and frames
2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
119fab2996
LLMAssistantAggregator: allow thought aggregation without appending to context
2026-01-09 09:42:41 -08:00
Aleix Conchillo Flaqué
38d354c4ed
LLMAssistantAggregator: add assistant turn and thought events
2026-01-09 09:42:41 -08:00
Aleix Conchillo Flaqué
cdb1074e11
LLMAssistantAggregator: no need to use BotStoppedSpeakingFrame
...
The end of turn is already handle with interruptions or with
LLMFullResponseEndFrame. LLMFullResponseEndFrame should never be blocked,
otherwise the assistant would not work.
2026-01-09 09:42:41 -08:00
Aleix Conchillo Flaqué
4b61fd2d7d
LLMUserAggregator: add user turn stopped message argument
...
It is now possible to get the user aggregation when a `on_user_turn_stopped`
event is emitted.
2026-01-09 09:42:41 -08:00
Aleix Conchillo Flaqué
d92926ae54
smartturn: rename on_vad_start_secs_updated to update_vad_start_secs
2026-01-09 09:34:15 -08:00
Aleix Conchillo Flaqué
fef79651ef
turns: add UserTurnProcessor for advanced pipeline user turn management
2026-01-09 09:21:28 -08:00
Aleix Conchillo Flaqué
3d54ca0a7c
LLMUserAggregator: user UserTurnController for user turn management
2026-01-09 09:21:28 -08:00
Aleix Conchillo Flaqué
199986815c
turns: add UserTurnController for user turn management
2026-01-09 09:21:28 -08:00
Filipi da Silva Fuchter
0a3c00f68b
Merge pull request #3391 from pipecat-ai/filipi/krisp_followup_improvements
...
Krisp VIVA follow-up improvements
2026-01-09 10:39:23 -05:00
marcus-daily
3e2467eb71
Fixing ruff formatting
2026-01-09 15:07:13 +00:00
marcus-daily
b075502c4c
Addressing code review comments
2026-01-09 15:07:13 +00:00
marcus-daily
35a99f92ab
Take into account VAD start_secs when passing audio data to Smart Turn, and add an extra 500ms of pre-speech audio for good measure
2026-01-09 15:07:13 +00:00
Mark Backman
4fe0836cf9
Add reconnect logic to WebsocketService in the event of ConnectionClosedError
2026-01-09 09:03:01 -05:00
filipi87
de5de0b162
Fixed KrispVivaTurn to properly release the Krisp SDK.
2026-01-09 10:31:17 -03:00
Garegin Harutyunyan
16819a5caa
Krisp VIVA SDK Filter and Turn support. ( #3261 )
...
* Krisp VIVA SDK Filter and Turn support.
* Reverted the krisp_filter.py as it's already deprectaed.
* enabled test with krisp_audio mock.
* More review comment fixes.
reverted the state logic in viva filter to be similar to the existing impl on main branch.
Fixed tests, ruff, etc.
* More review comments for Turn detection.
removed integration tests.
* Moved the SDK init/deinit into start/stop
2026-01-09 08:15:08 -05:00
Mark Backman
72a44c2fcd
Merge pull request #3386 from pipecat-ai/mb/deepgram-deprecate-vad-events
...
Deprecate support for vad_events in DeepgramSTTService
2026-01-09 07:56:03 -05:00
Mark Backman
7783b20b91
Merge pull request #3390 from dhruvladia-sarvam/update/sarvam-plugins
2026-01-09 07:11:13 -05:00
dhruvladia-sarvam
962ccbc0d7
fix
2026-01-09 14:26:28 +05:30
Mark Backman
4d61c5d7b2
Deprecate support for vad_events in DeepgramSTTService
2026-01-08 20:32:30 -05:00
Mark Backman
7ca4597ade
Merge pull request #3379 from lukepayyapilli/fix/fastapi-websocket-json-text-handling
...
Fix FastAPIWebsocketTransport to handle both binary and text messages
2026-01-08 17:26:35 -05:00
Luke Payyapilli
1874269a48
Remove FrameSerializerType enum and type property from serializers
2026-01-08 16:54:23 -05:00
Aleix Conchillo Flaqué
15dcb77a0c
Merge pull request #3364 from pipecat-ai/rajneesh/add-daily-sip-provider-option
...
Add support for specifying sip provider.
2026-01-08 11:47:09 -08:00
Mark Backman
682b253760
Merge pull request #3366 from lukepayyapilli/fix/cartesia-allow-none-language
...
Allow language=None in CartesiaTTSService for auto-detection
2026-01-08 14:42:09 -05:00
Luke Payyapilli
f440de82e2
Handle None language in _process_word_timestamps_for_language
2026-01-08 13:59:21 -05:00