wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,479 Commits 276 Branches 111 Tags
1c8a8f51d46a4e23f74b68b26902fa7b837b7e54
Commit Graph

8479 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mark Backman
1c8a8f51d4 Code review fixes 2026-03-24 08:46:03 -04:00
dhruvladia-sarvam
349b8645f3 Merge branch 'main' into feat/sarvam-llm-integration 2026-03-24 16:34:12 +05:30
dhruvladia-sarvam
696196e30c alignment with pr 4081 2026-03-24 16:29:58 +05:30
Aleix Conchillo Flaqué
7414b30308 Merge pull request #4116 from pipecat-ai/changelog-0.0.107 
Release 0.0.107 - Changelog Update
v0.0.107 		2026-03-23 20:13:49 -07:00
aconchillo
3268cb93d5 Update changelog for version 0.0.107 2026-03-23 20:11:31 -07:00
Aleix Conchillo Flaque
9211379720 update uv.lock 2026-03-23 20:06:28 -07:00
Filipi da Silva Fuchter
12dc429761 Merge pull request #4104 from pipecat-ai/filipi/audio_issue 
Allow defining whether to insert silence in the output transport.
 2026-03-23 17:17:37 -04:00
filipi87
066b206b3d Renaming insert_silence to auto_silence 2026-03-23 18:12:26 -03:00
filipi87
ddd1b71b56 Renaming audio_out_insert_silence to audio_out_auto_silence 2026-03-23 17:57:42 -03:00
filipi87
8612c9f50a Updating to use daily-python 0.27.0 2026-03-23 17:52:41 -03:00
Mark Backman
fd0bfe141f Merge pull request #4109 from pipecat-ai/pk/tiny-fix 2026-03-23 15:17:19 -04:00
filipi87
3042929989 Fixing changelog description. 2026-03-23 15:57:25 -03:00
dhruvladia-sarvam
0f6cc231cf removing error wraps and model validation check 2026-03-24 00:06:15 +05:30
dhruvladia-sarvam
3428a4c6ad fixes post PR 4081 2026-03-23 23:45:27 +05:30
Mark Backman
f283cc5bc6 Merge pull request #4091 from pipecat-ai/mb/gradium-multiplexing-setup 
feat: send per-context setup in Gradium TTS multiplexing
 2026-03-23 12:00:53 -04:00
Mark Backman
70552d7697 Add changelog entry for #4091 2026-03-23 11:58:14 -04:00
Mark Backman
84c2a24c9f feat: send per-context setup messages in Gradium TTS multiplexing 
Send a setup message with client_req_id before the first text message
for each context, matching Gradium multiplexing protocol. This allows
Gradium to associate each session with its setup configuration when
using close_ws_on_eos=False.
 2026-03-23 11:58:14 -04:00
Paul Kompfner
e93b0ace06 Remove an unnecessary check in SyncParallelPipeline 2026-03-23 10:00:32 -04:00
filipi87
e6602f9244 Disabling auto_silence for tavus video service. 2026-03-22 18:28:57 -03:00
filipi87
9a30b18f21 Configuring Daily CustomAudioSource to automatically inject silence or not. 2026-03-22 17:29:01 -03:00
filipi87
936a39f4a1 Updating tavus examples to not send silence. 2026-03-22 14:41:23 -03:00
filipi87
3b1cb30926 Adding changelog entry. 2026-03-22 13:26:00 -03:00
filipi87
ce36487143 Allow defining whether to insert silence in the output transport. 2026-03-22 13:09:09 -03:00
Mark Backman
ec3bd8c5b1 Merge pull request #4097 from pipecat-ai/mb/update-minimax-docs-link 
Update MiniMaxHttpTTSService platform docs link
 2026-03-21 07:08:40 -04:00
Mark Backman
622ebd5d74 Update MiniMaxHttpTTSService platform docs link 2026-03-21 07:02:06 -04:00
Mark Backman
a9a1941a45 Merge pull request #4093 from poislagarde/fix/genesys-pong-parameters 2026-03-20 19:52:58 -04:00
Pablo Ois Lagarde
53e0136366 chore: rename changelog fragment to PR #4093 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 16:46:35 -03:00
Pablo Ois Lagarde
bc0e7130b8 fix: always include parameters field in Genesys AudioHook messages 
The AudioHook protocol requires every message to carry a `parameters`
object. `_create_message` conditionally included it only when parameters
were truthy, so pong responses and closed responses without
outputVariables were sent without the field.

Clients that validate message structure (including the Genesys reference
implementation) rejected these messages, which broke server sequence
tracking and prevented outputVariables from reaching the Architect flow.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-20 16:37:53 -03:00
Mark Backman
d8af4447ff Merge pull request #3449 from kingster/telemetry-fix-system-message 
fix: Record correct system_instruction in LLM spans for LLM services
 2026-03-20 13:42:47 -04:00
Mark Backman
c89e366739 refactor: align tracing attributes with OpenTelemetry GenAI conventions 
- gen_ai.system -> gen_ai.provider.name (deprecated)
- system / system_instructions -> gen_ai.system_instructions
- gen_ai.usage.cache_read_input_tokens -> gen_ai.usage.cache_read.input_tokens
- gen_ai.usage.cache_creation_input_tokens -> gen_ai.usage.cache_creation.input_tokens
 2026-03-20 13:36:20 -04:00
Mark Backman
b5c362d6e6 refactor: rename tracing span attribute "system" to "system_instructions" 
Align with the OpenTelemetry GenAI semantic convention
gen_ai.system_instructions for system prompts. The old "system"
attribute name was unrelated to gen_ai.system (which is for
provider name).
 2026-03-20 13:20:03 -04:00
Mark Backman
e5aaa4c4eb fix: read system_instruction from _settings instead of removed attribute 
Replace adapter-based extraction in traced_llm with direct reads from
_settings.system_instruction (priority) and context messages (fallback).
The old approach had three bugs: signature mismatch with Anthropic
adapter, key name inconsistency, and unnecessary overhead from full
message/tools conversion.

Also deduplicate the system instruction in spans -- it was appearing as
both "system" and "param.system_instruction".
 2026-03-20 13:12:40 -04:00
Varun Singh
a12ad27348 enable_dialout should not depend on sip_caller_phone being set (#4087) 
* enable_dialout should not depend on SIP being set

* we still need room_prefix to have pipecat-sip, s/sip/telephony in room prefix
 2026-03-20 10:01:31 -07:00
Mark Backman
44504efdc7 Merge pull request #4090 from pipecat-ai/mb/fix-tts-audio-context-routing 
fix: route TTS audio through audio context queue in Fish, LMNT, Neuph…
 2026-03-20 11:06:53 -04:00
Mark Backman
da8070e98e Add changelog entry for #4090 2026-03-20 10:46:36 -04:00
Mark Backman
b98ad7fb64 fix: route TTS audio through audio context queue in Fish, LMNT, Neuphonic, Rime NonJson 
These services were pushing audio frames directly via push_frame() in their
WebSocket receive loops, bypassing the base TTSService audio context
serialization queue. This causes incorrect frame ordering and broken
interruption handling.

Changes per service:
- Fish Audio: use append_to_audio_context(), replace _handle_interruption
  with on_audio_context_interrupted()
- LMNT: use append_to_audio_context(), remove redundant push_frame override
- Neuphonic: use append_to_audio_context(), remove redundant push_frame and
  process_frame overrides (base class handles pause/resume)
- Rime NonJson: use append_to_audio_context(), remove redundant push_frame
  override
 2026-03-20 10:41:43 -04:00
Mark Backman
10ddf45015 Merge pull request #4088 from pipecat-ai/mb/add-community-integrations-README 
Add community integrations to README
 2026-03-20 10:34:09 -04:00
Filipi da Silva Fuchter
e41cb2cd0c Merge pull request #4083 from pipecat-ai/filipi/deepgram_sagemaker_tts_improvements 
Improvements to DeepgramSageMakerTTSService
 2026-03-20 10:30:48 -04:00
Filipi da Silva Fuchter
a69abcc67a Merge pull request #4082 from pipecat-ai/filipi/sarvam_tts_improvements 
Improvements to SarvamTTSService.
 2026-03-20 10:28:02 -04:00
Mark Backman
a11c48d5b0 Add community integrations to README 2026-03-20 10:09:58 -04:00
Kinshuk Bairagi
7caec9018b Merge branch 'pipecat-ai:main' into telemetry-fix-system-message 2026-03-20 18:36:31 +05:30
kompfner
08052d8880 Merge pull request #4085 from pipecat-ai/pk/remove-broken-05a-example 
Remove 05a example, which was broken and isn't currently a priority t…
 2026-03-19 15:59:39 -04:00
Paul Kompfner
4c456ada04 Remove 05a example, which was broken and isn't currently a priority to fix 2026-03-19 15:52:48 -04:00
kompfner
488dc1d07e Merge pull request #4074 from pipecat-ai/pk/openai-responses-llm-service 
feat: add OpenAI Responses API LLM service
 2026-03-19 15:44:26 -04:00
Paul Kompfner
dafbb2eb66 fix: typo "conversatione" → "conversation" in 20- examples 2026-03-19 15:38:38 -04:00
Paul Kompfner
ea1534f9f8 docs: note input_audio coming soon, no conversion needed 
The LLMContext format already matches the expected Responses API
shape for input_audio, so no adapter conversion will be needed
once OpenAI enables support.
 2026-03-19 15:36:23 -04:00
kompfner
f6e7599e49 Merge pull request #4029 from pipecat-ai/pk/sync-parallel-pipeline-fixes 
`SyncParallelPipeline` and related fixes
 2026-03-19 14:41:16 -04:00
Paul Kompfner
6424c36666 refactor: remove model init param from OpenAIResponsesLLMService 
Model is only configurable via settings, matching the canonical API.
 2026-03-19 14:38:01 -04:00
Paul Kompfner
05e344b9ec docs: port _closing comments from BaseOpenAILLMService 2026-03-19 14:30:34 -04:00
Paul Kompfner
4ec7be8850 feat: include cached_tokens and reasoning_tokens in usage metrics 2026-03-19 14:23:39 -04:00