Mark Backman
a0595adbdc
Merge pull request #4012 from pipecat-ai/mb/deprecate-old-local-smart-turn
2026-03-16 21:09:26 -04:00
Mark Backman
dc1632bbac
Merge pull request #4023 from pipecat-ai/mb/update-small-webrtc-prebuilt-2.4.0
2026-03-16 21:09:08 -04:00
Mark Backman
53f49ac094
Merge pull request #4024 from pipecat-ai/mb/fix-lang-enum-stt-tts
2026-03-16 21:08:48 -04:00
Mark Backman
154a8d1987
Merge pull request #4035 from pipecat-ai/mb/bump-pyjwt-version
2026-03-16 21:06:31 -04:00
Aleix Conchillo Flaqué
59486d5abf
Add changelog entries for PR #4047
2026-03-16 17:58:12 -07:00
Aleix Conchillo Flaqué
1a1d5e6a84
Merge pull request #4006 from pipecat-ai/aleix/task-frame-flush-ordering
...
handle EndTaskFrame, StopTaskFrame and CancelTaskFrame downstream
2026-03-16 17:35:11 -07:00
Om Chauhan
ed0f5ab09b
added changelog
2026-03-15 19:15:18 +05:30
Mark Backman
e8415b7451
Add changelog for #4035
2026-03-15 08:56:54 -04:00
Mark Backman
1ea23ad362
Add changelog for #4024
2026-03-13 10:58:51 -04:00
Mark Backman
7365ebfdf9
Add changelog for #4023
2026-03-13 10:22:58 -04:00
Mark Backman
ed0b8dadb5
Add changelog for #4012
2026-03-12 17:22:13 -04:00
kompfner
30d95e3b84
Merge pull request #4009 from pipecat-ai/pk/perplexity-message-ordering-strictness
...
Add PerplexityLLMAdapter for message ordering strictness
2026-03-12 16:51:11 -04:00
Paul Kompfner
e4bf6281c6
Add changelog for #4009
2026-03-12 14:56:37 -04:00
Aleix Conchillo Flaqué
f6f08d19a8
Add changelog for #4006
2026-03-12 11:34:25 -07:00
Aleix Conchillo Flaqué
374bfd4068
Merge pull request #4007 from pipecat-ai/aleix/fix-parallel-pipeline-flush-and-tts-stop-order
...
Fix ParallelPipeline flush ordering and TTS stop sequence
2026-03-12 10:21:31 -07:00
Aleix Conchillo Flaqué
a461b2b9e6
Add changelog entries for PR #4007
2026-03-12 10:16:29 -07:00
kompfner
383300979d
Merge pull request #4004 from pipecat-ai/pk/service-settings-update-frame-can-target-specific-service
...
Add optional `service` field to `ServiceUpdateSettingsFrame` for targ…
2026-03-12 11:48:41 -04:00
Mark Backman
1fe1f0f439
Apply ensure_ascii=False to remaining LLM services and fix changelog format
2026-03-12 10:35:19 -04:00
Ali Alhoshaiyan
765fbeec63
Add changelog
2026-03-12 10:35:19 -04:00
Mark Backman
bf66ae7e46
Add changelog for #4005
2026-03-12 09:22:31 -04:00
Paul Kompfner
36b57252b4
Add changelog for PR #4004
2026-03-11 21:47:51 -04:00
Mark Backman
904331bba1
Merge pull request #4001 from pipecat-ai/mb/simli-settings
...
Migrate SimliVideoService to AIService with Settings pattern
2026-03-11 17:45:59 -04:00
Mark Backman
11b14b7857
Add changelog for PR #4001
2026-03-11 17:40:53 -04:00
Mark Backman
59dc30a84d
Merge pull request #3997 from pipecat-ai/mb/sarvam-package-0.1.26
...
Update sarvamai dependency from 0.1.26a2 to 0.1.26
2026-03-11 16:59:32 -04:00
Mark Backman
4a45145cba
Restored the default model to gpt-4.1 for OpenAI and Azure LLM services
...
The default model for OpenAILLMService and AzureLLMService was still set
to gpt-4o. Restored it to gpt-4.1. Also, removed hardcoded gpt-4o/gpt-4o-mini
model references from examples so they pick up the new default.
2026-03-11 16:18:47 -04:00
Mark Backman
71e6158861
Add changelog for PR #3997
2026-03-11 14:18:47 -04:00
Paul Kompfner
3cbd27d202
Add changelog for PR #3991
2026-03-11 10:44:15 -04:00
aconchillo
610dc25fb1
Update changelog for version 0.0.105
2026-03-10 17:58:32 -07:00
Aleix Conchillo Flaqué
a4310d4335
Merge pull request #3980 from pipecat-ai/aleix/move-google-vertex-openai
...
Move Google Vertex and OpenAI LLM modules to subpackages
2026-03-10 13:37:02 -07:00
Aleix Conchillo Flaqué
23218aaed7
Add changelog for #3980
2026-03-10 13:04:16 -07:00
kollaikal-rupesh
80bd935c19
Add ServiceSwitcherStrategyFailover for automatic failover on service errors ( #3870 )
...
* Add ServiceSwitcherStrategyFailover for automatic error-based service switching
Introduce a strategy hierarchy: ServiceSwitcherStrategy (base) →
ServiceSwitcherStrategyManual (handles ManuallySwitchServiceFrame) →
ServiceSwitcherStrategyFailover (adds error-based failover). ServiceSwitcher
now defaults to ServiceSwitcherStrategyManual with strategy_type optional.
Non-fatal ErrorFrames are forwarded to the strategy via handle_error().
* Move metadata request into _set_active_if_available
Requesting metadata is part of making a service active, so it belongs
alongside setting _active_service and firing on_service_switched. This
removes the duplicate queue_frame calls from ServiceSwitcher push_frame
and process_frame.
2026-03-10 15:37:30 -04:00
Aleix Conchillo Flaqué
86597cc9ec
Add changelog entries for PR #3831
2026-03-10 11:32:16 -07:00
Mark Backman
9b26faff05
Merge pull request #3961 from ai-coustics/goekmengoergen/sys-663-re-enable-enhancement-level-feature-on-pipecat
...
Add enhancement_level support to `AICFilter`.
2026-03-10 14:24:15 -04:00
Aleix Conchillo Flaqué
c25d5af8c8
Merge pull request #3970 from pipecat-ai/aleix/update-daily-python
...
Update daily-python to 0.24.0
2026-03-10 10:49:27 -07:00
Aleix Conchillo Flaqué
6e52623959
Merge pull request #3976 from pipecat-ai/aleix/fix-google-system-instruction-priority
...
Fix Google LLM system instruction priority
2026-03-10 10:48:28 -07:00
Mark Backman
912f1be31c
Add system_instruction parameter to run_inference ( #3968 )
...
* Add system_instruction parameter to run_inference
Allow callers to provide a custom system instruction directly when calling
run_inference, without having to construct provider-specific context objects.
For OpenAI, the instruction is prepended as a system message (preserving
existing messages). For Anthropic, Google, and AWS Bedrock, it overrides the
single system field with a warning when an existing system instruction is
present in the context.
* Use system_instruction parameter in _generate_summary
Pass the summarization prompt via run_inference's system_instruction
parameter instead of embedding it as a system message in the context.
* Add changelog for #3968
2026-03-10 12:57:23 -04:00
Mark Backman
0817a57f4c
Merge pull request #3974 from pipecat-ai/mb/azure-stt-region-optional
...
Make Azure STT region optional when private_endpoint is used
2026-03-10 12:31:39 -04:00
Aleix Conchillo Flaqué
db27aaa790
Add changelog for #3976
2026-03-10 09:26:26 -07:00
Mark Backman
54c767cce3
Merge pull request #3960 from sysradium/fix-realtime-calls
...
Treat conversation_already_has_active_response as non-fatal in Realtime API
2026-03-10 11:40:34 -04:00
Mark Backman
2ce9179662
Merge pull request #3958 from pipecat-ai/mb/deepgram-tts-audio-context
...
Route Deepgram WebSocket TTS audio through audio context queue
2026-03-10 11:37:39 -04:00
Mark Backman
d5c0789ab5
Add changelog for #3958
2026-03-10 11:34:03 -04:00
sysradium
ba0ebd5525
Treat conversation_already_has_active_response as non-fatal in Realtime API
2026-03-10 15:57:55 +01:00
Gökmen Görgen
82b300298a
add changelog.
2026-03-10 13:36:15 +01:00
Mark Backman
edc65fc45e
Add changelog for #3974
2026-03-10 07:48:02 -04:00
yukiobata1
ceb53e044b
Add changelog for #3973
2026-03-10 19:29:47 +09:00
Aleix Conchillo Flaqué
d79e35d84f
Add changelog for #3970
2026-03-09 20:47:42 -07:00
Mark Backman
07b901c2a5
Add changelog for #3967
2026-03-09 15:05:20 -04:00
kompfner
f2debd9b1d
Merge pull request #3963 from pipecat-ai/pk/improve-claude-changelog-skill
...
Improve changelog skill: prioritize user-facing language and update e…
2026-03-09 13:00:32 -04:00
Filipi da Silva Fuchter
0c5e936aa5
Merge pull request #3936 from pipecat-ai/filipi/fix_push_aggregation
...
Fixed TTS context not being appended to the assistant message history
2026-03-09 11:14:38 -04:00
Paul Kompfner
7f9169269c
Improve changelog skill: prioritize user-facing language and update example changelog
2026-03-09 10:45:33 -04:00
