Merge branch 'pipecat-ai:main' into telemetry-fix-system-message

changelog/3804.added.md

@@ -1 +0,0 @@
-- Added concurrent audio context support: `CartesiaTTSService` can now synthesize the next sentence while the previous one is still playing, by setting `pause_frame_processing=False` and routing each sentence through its own audio context queue.

changelog/3804.changed.md

@@ -1 +0,0 @@
-- Audio context management (previously in `AudioContextTTSService`) is now built into `TTSService`. All WebSocket providers (`cartesia`, `elevenlabs`, `asyncai`, `inworld`, `rime`, `gradium`, `resembleai`) now inherit from `WebsocketTTSService` directly. Word-timestamp baseline is set automatically on the first audio chunk of each context instead of requiring each provider to call `start_word_timestamps()` in their receive loop.

changelog/3804.deprecated.md

@@ -1,2 +0,0 @@
-- Deprecated `AudioContextTTSService` and `AudioContextWordTTSService`. Subclass `WebsocketTTSService` directly instead; audio context management is now part of the base `TTSService`.
-- Deprecated `WordTTSService`, `WebsocketWordTTSService`, and `InterruptibleWordTTSService`. Word timestamp logic is now always active in `TTSService` and no longer needs to be opted into via a subclass.

changelog/3804.removed.md

@@ -1 +0,0 @@
-- ⚠️ Removed `supports_word_timestamps` parameter from `TTSService.__init__()`. Word timestamp logic is now always active. Remove this argument from any custom subclass `super().__init__()` calls.

changelog/3848.changed.md

@@ -1 +0,0 @@
-- ⚠️ Updated `DeepgramSTTService` to use `deepgram-sdk` v6. The `LiveOptions` class was removed from the SDK and is now provided by pipecat directly; import it from `pipecat.services.deepgram.stt` instead of `deepgram`.

changelog/3848.fixed.md

@@ -1 +0,0 @@
-- Fixed `DeepgramSTTService` keepalive ping timeout disconnections. The deepgram-sdk v6 removed automatic keepalive; pipecat now sends explicit `KeepAlive` messages every 5 seconds, within the recommended 3–5 second interval before Deepgram's 10-second inactivity timeout.

changelog/3889.changed.md

@@ -1,3 +0,0 @@
-- Support for Voice Focus 2.0 models.
-  - Updated `aic-sdk` to `~=2.1.0` to support Voice Focus 2.0 models.
-  - Cleaned unused `ParameterFixedError` exception handling in `AICFilter` parameter setup. 

changelog/3889.fixed.md

@@ -1 +0,0 @@
-- Fixed `BufferError: Existing exports of data: object cannot be re-sized` in `AICFilter` caused by holding a `memoryview` on the mutable audio buffer across async yield points.

changelog/3914.changed.md

@@ -1 +0,0 @@
-- `max_context_tokens` and `max_unsummarized_messages` in `LLMAutoContextSummarizationConfig` (and deprecated `LLMContextSummarizationConfig`) can now be set to `None` independently to disable that summarization threshold. At least one must remain set.

changelog/3915.added.md

@@ -1 +0,0 @@
-- Added optional `timeout_secs` parameter to `register_function()` and `register_direct_function()` for per-tool function call timeout control, overriding the global `function_call_timeout_secs` default.

changelog/3916.added.md

@@ -1 +0,0 @@
-- Added `cloud-audio-only` recording option to Daily transport's `enable_recording` property.

changelog/3918.added.md

@@ -1,15 +0,0 @@
-- Wired up `system_instruction` in `BaseOpenAILLMService`, `AnthropicLLMService`, and `AWSBedrockLLMService` so it works as a default system prompt, matching the behavior of the Google services. This enables sharing a single `LLMContext` across multiple LLM services, where each service provides its own system instruction independently.
-
-  ```python
-  llm = OpenAILLMService(
-      api_key=os.getenv("OPENAI_API_KEY"),
-      system_instruction="You are a helpful assistant.",
-  )
-
-  context = LLMContext()
-
-  @transport.event_handler("on_client_connected")
-  async def on_client_connected(transport, client):
-      context.add_message({"role": "user", "content": "Please introduce yourself."})
-      await task.queue_frames([LLMRunFrame()])
-  ```

changelog/3918.other.md

@@ -1 +0,0 @@
-- Updated foundational examples to use `system_instruction` on LLM services instead of adding system messages to `LLMContext`.

changelog/3927.added.md

@@ -1 +0,0 @@
-- Added `vad_threshold` parameter to `AssemblyAIConnectionParams` for configuring voice activity detection sensitivity in U3 Pro. Aligning this with external VAD thresholds (e.g., Silero VAD) prevents the "dead zone" where AssemblyAI transcribes speech that VAD hasn't detected yet.

changelog/3927.changed.md

@@ -1 +0,0 @@
-- ⚠️ Removed `formatted_finals` and `word_finalization_max_wait_time` from `AssemblyAIConnectionParams` as these were v2 API parameters not supported in v3. Clarified that `format_turns` only applies to Universal-Streaming models; U3 Pro has automatic formatting built-in.

changelog/3929.other.md

@@ -1 +0,0 @@
-- Updated AssemblyAI turn detection example to use `keyterms_prompt` list format instead of `prompt` string for improved clarity.

changelog/3930.added.md

@@ -1 +0,0 @@
-- Added `push_empty_transcripts` parameter to `BaseWhisperSTTService` and `OpenAISTTService` to allow empty transcripts to be pushed downstream as `TranscriptionFrame` instead of discarding them (the default behavior). This is intended for situations where VAD fires even though the user did not speak. In these cases, it is useful to know that nothing was transcribed so that the agent can resume speaking, instead of waiting longer for a transcription.

changelog/3931.other.md

@@ -1 +0,0 @@
-- Updated foundational examples and eval scripts to use `"user"` role instead of `"system"` when adding messages to `LLMContext`, since system prompts should be set via `system_instruction` on the LLM service.

changelog/3932.added.md

@@ -1 +0,0 @@
-- LLM services (`BaseOpenAILLMService`, `AnthropicLLMService`, `AWSBedrockLLMService`) now log a warning when both `system_instruction` and a system message in the context are set. The constructor's `system_instruction` takes precedence.

changelog/3936.fixed.md

@@ -1 +0,0 @@
-- Fixed TTS context not being appended to the assistant message history when using `TTSSpeakFrame` with `append_to_context=True` with some TTS providers.

changelog/3937.fixed.md

@@ -1 +0,0 @@
-- Fixed context summarization leaving orphaned tool responses in the kept context when tool calls were moved to the summarized portion.

changelog/3946.added.md

@@ -1 +0,0 @@
-- Runtime settings updates (via `STTUpdateSettingsFrame`) now work for AWS Transcribe, Azure, Cartesia, Deepgram, ElevenLabs Realtime, Gradium, and Soniox STT services. Previously, changing settings at runtime only stored the new values without reconnecting.

changelog/3947.added.md

@@ -1 +0,0 @@
-- Exposed `on_summary_applied` event on `LLMAssistantAggregator`, allowing users to listen for context summarization events without accessing private members.

changelog/3953.added.md

@@ -1 +0,0 @@
-- Deepgram Flux STT settings (`keyterm`, `eot_threshold`, `eager_eot_threshold`, `eot_timeout_ms`) can now be updated mid-stream via `STTUpdateSettingsFrame` without triggering a reconnect. The new values are sent to Deepgram as a Configure WebSocket message on the existing connection.

changelog/3956.fixed.md

@@ -1 +0,0 @@
-- Fixed turn completion state not resetting at end of LLM responses. `LLMFullResponseEndFrame` is pushed (not received) by the LLM service, so the mixin now handles it in `push_frame` instead of `process_frame`.

changelog/3957.fixed.md

@@ -1 +0,0 @@
-- Fixed turn completion instructions being injected as a context system message instead of using `system_instruction`. This caused warning spam when `system_instruction` was also set and didn't persist across full context updates.

changelog/3959.fixed.md

@@ -1 +0,0 @@
-- Fixed `on_call_state_updated` event handler in LiveKit transport receiving incorrect number of arguments due to redundant `self` passed to `_call_event_handler`.

changelog/3962.fixed.md

@@ -1 +0,0 @@
-- Fixed `SmallWebRTCConnection` silently discarding messages sent before the data channel is open by queuing them and flushing once the channel is ready. A bounded queue (`MAX_MESSAGE_QUEUE_SIZE = 50`) prevents unbounded memory growth, and a 10-second timeout after connection clears the queue and falls back to discard mode if the data channel never opens.

changelog/3967.fixed.md

@@ -1 +0,0 @@
-- Fixed `AzureSTTService` failing to initialize when `private_endpoint` is provided. The Azure Speech SDK's `SpeechConfig` does not accept both `region` and `endpoint` simultaneously, so they are now passed conditionally.

changelog/4029.added.2.md

@@ -0,0 +1 @@
+- Added `frame_order` parameter to `SyncParallelPipeline`. Set `frame_order=FrameOrder.PIPELINE` to push synchronized output frames in pipeline definition order (all frames from the first pipeline, then the second, etc.) instead of the default arrival order.

changelog/4029.added.md

@@ -0,0 +1 @@
+- Added `sync_with_audio` field to `OutputImageRawFrame`. When set to `True`, the output transport queues image frames with audio so they are displayed only after all preceding audio has been sent, enabling synchronized audio/image playback.

changelog/4029.fixed.3.md

@@ -0,0 +1 @@
+- Fixed `SyncParallelPipeline` breaking the Whisker debugger.

changelog/4029.fixed.md

@@ -0,0 +1 @@
+- Fixed `SyncParallelPipeline` race condition where concurrent SystemFrame processing (e.g. from RTVI) could corrupt sink queues and cause deadlocks. SystemFrames now take a fast path that passes them through without draining queued output.

changelog/4074.added.md

@@ -0,0 +1 @@
+- Added `OpenAIResponsesLLMService`, a new LLM service that uses the OpenAI Responses API. Supports streaming text, function calling, usage metrics, and out-of-band inference. Works with the universal `LLMContext` and `LLMContextAggregatorPair`. See `examples/foundational/07-interruptible-openai-responses.py` and `14-function-calling-openai-responses.py`.

changelog/4075.fixed.md

@@ -0,0 +1 @@
+- Fixed TTS frame ordering so that non-system frames always arrive in correct order relative to the `TTSStartedFrame`/`TTSAudioRawFrame`/`TTSStoppedFrame` sequence. Previously these frames could race ahead of or behind audio context frames, producing out-of-order output downstream.