TTSSpeakFrame context demo

feat: add generation_config support for Cartesia Sonic-3

CHANGELOG.md

@@ -9,15 +9,350 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `generation_config` parameter support to `CartesiaTTSService` and
+  `CartesiaHttpTTSService` for Cartesia Sonic-3 models. Includes a new
+  `GenerationConfig` class with `volume` (0.5-2.0), `speed` (0.6-1.5),
+  and `emotion` (60+ options) parameters for fine-grained speech generation
+  control.
+
+- Expanded support for univeral `LLMContext` to `OpenAIRealtimeLLMService`.
+  As a reminder, the context-setup pattern when using `LLMContext` is:
+
+  ```python
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(
+    context,
+    # This part is `OpenAIRealtimeLLMService`-specific.
+    # `expect_stripped_words=False` needed when OpenAI Realtime used with
+    # "audio" modality (the default).
+    assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+  )
+  ```
+
+  (Note that even though `OpenAIRealtimeLLMService` now supports the universal
+  `LLMContext`, it is not meant to be swapped out for another LLM service at
+  runtime with `LLMSwitcher`.)
+
+  Note: `TranscriptionFrame`s and `InterimTranscriptionFrame`s now go upstream
+  from `OpenAIRealtimeLLMService`, so if you're using `TranscriptProcessor`,
+  say, you'll want to adjust accordingly:
+
+  ```python
+  pipeline = Pipeline(
+    [
+      transport.input(),
+      context_aggregator.user(),
+
+      # BEFORE
+      llm,
+      transcript.user(),
+
+      # AFTER
+      transcript.user(),
+      llm,
+
+      transport.output(),
+      transcript.assistant(),
+      context_aggregator.assistant(),
+    ]
+  )
+  ```
+
+  Also worth noting: whether or not you use the new context-setup pattern with
+  `OpenAIRealtimeLLMService`, some types have changed under the hood:
+
+  ```python
+  ## BEFORE:
+
+  # Context aggregator type
+  context_aggregator: OpenAIContextAggregatorPair
+
+  # Context frame type
+  frame: OpenAILLMContextFrame
+
+  # Context type
+  context: OpenAIRealtimeLLMContext
+  # or
+  context: OpenAILLMContext
+
+  ## AFTER:
+
+  # Context aggregator type
+  context_aggregator: LLMContextAggregatorPair
+
+  # Context frame type
+  frame: LLMContextFrame
+
+  # Context type
+  context: LLMContext
+  ```
+
+  Also note that `RealtimeMessagesUpdateFrame` and
+  `RealtimeFunctionCallResultFrame` have been deprecated, since they're no
+  longer used by `OpenAIRealtimeLLMService`. OpenAI Realtime now works more
+  like other LLM services in Pipecat, relying on updates to its context, pushed
+  by context aggregators, to update its internal state. Listen for
+  `LLMContextFrame`s for context updates.
+
+  Finally, `LLMTextFrame`s are no longer pushed from `OpenAIRealtimeLLMService`
+  when it's configured with `output_modalities=['audio']`. If you need
+  to process its output, listen for `TTSTextFrame`s instead.
+
+- Expanded support for universal `LLMContext` to `GeminiLiveLLMService`.
+  As a reminder, the context-setup pattern when using `LLMContext` is:
+
+  ```python
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(
+    context,
+    # This part is `GeminiLiveLLMService`-specific.
+    # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+    #  modality (the default).
+    assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+  )
+  ```
+
+  (Note that even though `GeminiLiveLLMService` now supports the universal
+  `LLMContext`, it is not meant to be swapped out for another LLM service at
+  runtime with `LLMSwitcher`.)
+
+  Worth noting: whether or not you use the new context-setup pattern with
+  `GeminiLiveLLMService`, some types have changed under the hood:
+
+  ```python
+  ## BEFORE:
+
+  # Context aggregator type
+  context_aggregator: GeminiLiveContextAggregatorPair
+
+  # Context frame type
+  frame: OpenAILLMContextFrame
+
+  # Context type
+  context: GeminiLiveLLMContext
+  # or
+  context: OpenAILLMContext
+
+  ## AFTER:
+
+  # Context aggregator type
+  context_aggregator: LLMContextAggregatorPair
+
+  # Context frame type
+  frame: LLMContextFrame
+
+  # Context type
+  context: LLMContext
+  ```
+
+  Also note that `LLMTextFrame`s are no longer pushed from `GeminiLiveLLMService`
+  when it's configured with `modalities=GeminiModalities.AUDIO`. If you need
+  to process its output, listen for `TTSTextFrame`s instead.
+
+### Changed
+
+- `DailyTransport` triggers `on_error` event if transcription can't be started
+  or stopped.
+
+- `DailyTransport` updates: `start_dialout()` now returns two values:
+  `session_id` and `error`. `start_recording()` now returns two values:
+  `stream_id` and `error`.
+
+- Updated `daily-python` to 0.21.0.
+
+- `SimliVideoService` now accepts `api_key` and `face_id` parameters directly,
+  with optional `params` for `max_session_length` and `max_idle_time`
+  configuration, aligning with other Pipecat service patterns.
+
+- Updated the default model to `sonic-3` for `CartesiaTTSService` and
+  `CartesiaHttpTTSService`.
+
+- `FunctionFilter` now has a `filter_system_frames` arg, which controls whether
+  or not SystemFrames are filtered.
+
+- Upgraded `aws_sdk_bedrock_runtime` to v0.1.1 to resolve potential CPU issues
+  when running `AWSNovaSonicLLMService`.
+
+### Deprecated
+
+- The `send_transcription_frames` argument to `OpenAIRealtimeLLMService` is
+  deprecated. Transcription frames are now always sent. They go upstream, to be
+  handled by the user context aggregator. See "Added" section for details.
+
+- Types in `pipecat.services.openai.realtime.context` and
+  `pipecat.services.openai.realtime.frames` are deprecated, as they're no
+  longer used by `OpenAIRealtimeLLMService`. See "Added" section for details.
+
+- `SimliVideoService` `simli_config` parameter is deprecated. Use `api_key` and
+  `face_id` parameters instead.
+
+### Removed
+
+- Removed the `aiohttp_session` arg from `SarvamTTSService` as it's no longer
+  used.
+
+### Fixed
+
+- Fixed an issue where `DailyTransport` would timeout prematurely on join and on
+  leave.
+
+- Fixed an issue in the runner where starting a DailyTransport room via
+  `/start` didn't support using the `DAILY_SAMPLE_ROOM_URL` env var.
+
+- Fixed an issue in `ServiceSwitcher` where the `STTService`s would result in
+  all STT services producing `TranscriptionFrame`s.
+
+- Fixed an issue in `HumeTTSService` that was only using Octave 2, which does not support the `description` field. Now, if a description is provided, it switches to Octave 1.
+
+## [0.0.91] - 2025-10-21
+
+### Added
+
+- It is now possible to start a bot from the `/start` endpoint when using the
+  runner Daily's transport. This follows the Pipecat Cloud format with
+  `createDailyRoom` and `body` fields in the POST request body.
+
+- Added an ellipsis character (`…`) to the end of sentence detection in the
+  string utils.
+
+- Expanded support for universal `LLMContext` to `AWSNovaSonicLLMService`.
+  As a reminder, the context-setup pattern when using `LLMContext` is:
+
+  ```python
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(context)
+  ```
+
+  (Note that even though `AWSNovaSonicLLMService` now supports the universal
+  `LLMContext`, it is not meant to be swapped out for another LLM service at
+  runtime with `LLMSwitcher`.)
+
+  Worth noting: whether or not you use the new context-setup pattern with
+  `AWSNovaSonicLLMService`, some types have changed under the hood:
+
+  ```python
+  ## BEFORE:
+
+  # Context aggregator type
+  context_aggregator: AWSNovaSonicContextAggregatorPair
+
+  # Context frame type
+  frame: OpenAILLMContextFrame
+
+  # Context type
+  context: AWSNovaSonicLLMContext
+  # or
+  context: OpenAILLMContext
+
+  ## AFTER:
+
+  # Context aggregator type
+  context_aggregator: LLMContextAggregatorPair
+
+  # Context frame type
+  frame: LLMContextFrame
+
+  # Context type
+  context: LLMContext
+  ```
+
+- Added support for `bulbul:v3` model in `SarvamTTSService` and
+  `SarvamHttpTTSService`.
+
+- Added `keyterms_prompt` parameter to `AssemblyAIConnectionParams`.
+
+- Added `speech_model` parameter to `AssemblyAIConnectionParams` to access the
+  multilingual model.
+
+- Added support for trickle ICE to the `SmallWebRTCTransport`.
+
+- Added support for updating `OpenAITTSService` settings (`instructions` and
+  `speed`) at runtime via `TTSUpdateSettingsFrame`.
+
+- Added `--whatsapp` flag to runner to better surface WhatsApp transport logs.
+
+- Added `on_connected` and `on_disconnected` events to TTS and STT
+  websocket-based services.
+
+- Added an `aggregate_sentences` arg in `ElevenLabsHttpTTSService`, where the
+  default value is True.
+
+- Added a `room_properties` arg to the Daily runner's `configure()` method,
+  allowing `DailyRoomProperties` to be provided.
+
 - The runner `--folder` argument now supports downloading files from
   subdirectories.
 
+### Changed
+
+- `RunnerArguments` now include the `body` field, so there's no need to add it
+  to subclasses. Also, all `RunnerArguments` fields are now keyword-only.
+
+- `CartesiaSTTService` now inherits from `WebsocketSTTService`.
+
+- Package upgrades:
+
+  - `daily-python` upgraded to 0.20.0.
+  - `openai` upgraded to support up to 2.x.x.
+  - `openpipe` upgraded to support up to 5.x.x.
+
+- `SpeechmaticsSTTService` updated dependencies for `speechmatics-rt>=0.5.0`.
+
+### Deprecated
+
+- The `send_transcription_frames` argument to `AWSNovaSonicLLMService` is
+  deprecated. Transcription frames are now always sent. They go upstream, to be
+  handled by the user context aggregator. See "Added" section for details.
+
+- Types in `pipecat.services.aws.nova_sonic.context` are deprecated, as they're
+  no longer used by `AWSNovaSonicLLMService`. See "Added" section for
+  details.
+
 ### Fixed
 
+- Fixed an issue where the `RTVIProcessor` was sending duplicate
+  `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` messages.
+
+- Fixed an issue in `AWSBedrockLLMService` where both `temperature` and `top_p`
+  were always sent together, causing conflicts with models like Claude Sonnet 4.5
+  that don't allow both parameters simultaneously. The service now only includes
+  inference parameters that are explicitly set, and `InputParams` defaults have
+  been changed to `None` to rely on AWS Bedrock's built-in model defaults.
+
+- Fixed an issue in `RivaSegmentedSTTService` where a runtime error occurred due
+  to a mismatch in the `_handle_transcription` method's signature.
+
+- Fixed multiple pipeline task cancellation issues. `asyncio.CancelledError` is
+  now handled properly in `PipelineTask` making it possible to cancel an asyncio
+  task that it's executing a `PipelineRunner` cleanly. Also,
+  `PipelineTask.cancel()` does not block anymore waiting for the `CancelFrame`
+  to reach the end of the pipeline (going back to the behavior in < 0.0.83).
+
+- Fixed an issue in `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` where
+  the Flash models would split words, resulting in a space being inserted
+  between words.
+
+- Fixed an issue where audio filters' `stop()` would not be called when using
+  `CancelFrame`.
+
+- Fixed an issue in `ElevenLabsHttpTTSService`, where
+  `apply_text_normalization` was incorrectly set as a query parameter. It's now
+  being added as a request parameter.
+
 - Fixed an issue where `RimeHttpTTSService` and `PiperTTSService` could generate
   incorrectly 16-bit aligned audio frames, potentially leading to internal
   errors or static audio.
 
+- Fixed an issue in `SpeechmaticsSTTService` where `AdditionalVocabEntry` items
+  needed to have `sounds_like` for the session to start.
+
+### Other
+
+- Added foundational example `47-sentry-metrics.py`, demonstrating how to use the
+  `SentryMetrics` processor.
+
+- Added foundational example `14x-function-calling-openpipe.py`.
+
 ## [0.0.90] - 2025-10-10
 
 ### Added

README.md

@@ -44,6 +44,10 @@ Looking to build structured conversations? Check out [Pipecat Flows](https://git
 
 Want to build beautiful and engaging experiences? Checkout the [Voice UI Kit](https://github.com/pipecat-ai/voice-ui-kit), a collection of components, hooks and templates for building voice AI applications quickly.
 
+### 🛠️ Create and deploy projects
+
+Create a new project in under a minute with the [Pipecat CLI](https://github.com/pipecat-ai/pipecat-cli). Then use the CLI to monitor and deploy your agent to production.
+
 ### 🔍 Debugging
 
 Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
@@ -63,24 +67,24 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
     <br/>
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>&nbsp;
-    <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
+    <a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.png" width="400" /></a>
 </p>
 
 ## 🧩 Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                              |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                    |
 | Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 

env.example

@@ -4,6 +4,9 @@ AICOUSTICS_LICENSE_KEY=...
 # Anthropic
 ANTHROPIC_API_KEY=...
 
+# Assembly AI
+ASSEMBLYAI_API_KEY=...
+
 # Async
 ASYNCAI_API_KEY=...
 ASYNCAI_VOICE_ID=...
@@ -21,12 +24,19 @@ AZURE_CHATGPT_API_KEY=...
 AZURE_CHATGPT_ENDPOINT=https://...
 AZURE_CHATGPT_MODEL=...
 
+AZURE_REALTIME_API_KEY=...
+AZURE_REALTIME_BASE_URL=...
+
 AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
 # Cartesia
 CARTESIA_API_KEY=...
+CARTESIA_VOICE_ID=...
+
+# Cerebras
+CEREBRAS_API_KEY=...
 
 # Daily
 DAILY_API_KEY=...
@@ -35,57 +45,48 @@ DAILY_SAMPLE_ROOM_URL=https://...
 # Deepgram
 DEEPGRAM_API_KEY=...
 
+# DeepSeek
+DEEPSEEK_API_KEY=...
+
 # ElevenLabs
 ELEVENLABS_API_KEY=...
 ELEVENLABS_VOICE_ID=...
 
-# Neuphonic
-NEUPHONIC_API_KEY=...
-
 # Fal
 FAL_KEY=...
 
 # Fireworks
 FIREWORKS_API_KEY=...
 
+# Fish Audio
+FISH_API_KEY=...
+
 # Gladia
 GLADIA_API_KEY=...
 GLADIA_REGION=...
 
 # Google
 GOOGLE_API_KEY=...
-GOOGLE_CLOUD_PROJECT_ID=...
-GOOGLE_TEST_CREDENTIALS=...
 GOOGLE_VERTEX_TEST_CREDENTIALS=...
+GOOGLE_CLOUD_PROJECT_ID=...
+GOOGLE_CLOUD_LOCATION=...
+GOOGLE_TEST_CREDENTIALS=...
+
+# Grok
+GROK_API_KEY=...
+
+# Groq
+GROQ_API_KEY=...
+
+# Heygen
+HEYGEN_API_KEY=...
 
 # Hume
 HUME_API_KEY=...
+HUME_VOICE_ID=...
 
-# LMNT
-LMNT_API_KEY=...
-LMNT_VOICE_ID=...
-
-# Perplexity
-PERPLEXITY_API_KEY=...
-
-# PlayHT
-PLAYHT_USER_ID=...
-PLAYHT_API_KEY=...
-
-# OpenAI
-OPENAI_API_KEY=...
-
-# OpenPipe
-OPENPIPE_API_KEY=...
-
-# Tavus
-TAVUS_API_KEY=...
-TAVUS_REPLICA_ID=...
-TAVUS_PERSONA_ID=...
-
-# Simli
-SIMLI_API_KEY=...
-SIMLI_FACE_ID=...
+# Inworld
+INWORLD_API_KEY=...
 
 # Krisp
 KRISP_MODEL_PATH=...
@@ -93,77 +94,100 @@ KRISP_MODEL_PATH=...
 # Krisp Viva
 KRISP_VIVA_MODEL_PATH=...
 
-# DeepSeek
-DEEPSEEK_API_KEY=...
+# LiveKit
+LIVEKIT_API_KEY=...
+LIVEKIT_API_SECRET=...
 
-# Groq
-GROQ_API_KEY=...
-
-# Grok
-GROK_API_KEY=...
-
-# Inworld
-INWORLD_API_KEY=...
-
-# Together.ai
-TOGETHER_API_KEY=...
-
-# Cerebras
-CEREBRAS_API_KEY=...
-
-# Fish Audio
-FISH_API_KEY=...
-
-# Assembly AI
-ASSEMBLYAI_API_KEY=...
-
-# OpenRouter
-OPENROUTER_API_KEY=...
-
-# Piper
-PIPER_BASE_URL=...
-
-# Smart turn
-LOCAL_SMART_TURN_MODEL_PATH=...
-FAL_SMART_TURN_API_KEY=...
-
-# Twilio
-TWILIO_ACCOUNT_SID=...
-TWILIO_AUTH_TOKEN=...
+# LMNT
+LMNT_API_KEY=...
+LMNT_VOICE_ID=...
 
 # MiniMax
 MINIMAX_API_KEY=...
 MINIMAX_GROUP_ID=...
 
-# Sarvam AI
-SARVAM_API_KEY=...
-
-# Soniox
-SONIOX_API_KEY=
-
-# Speechmatics
-SPEECHMATICS_API_KEY=...
-
-# SambaNova
-SAMBANOVA_API_KEY=...
-
-# Sentry
-SENTRY_DSN=...
-
-# Heygen
-HEYGEN_API_KEY=...
-
 # Mistral
 MISTRAL_API_KEY=...
 
+# Neuphonic
+NEUPHONIC_API_KEY=...
+
 # NVIDIA
 NVIDIA_API_KEY=...
 
+# OpenAI
+OPENAI_API_KEY=...
+
+# OpenPipe
+OPENPIPE_API_KEY=...
+
+# OpenRouter
+OPENROUTER_API_KEY=...
+
+# Perplexity
+PERPLEXITY_API_KEY=...
+
+# Picovoice Koala
+KOALA_ACCESS_KEY=...
+
+# Piper
+PIPER_BASE_URL=...
+
+# PlayHT
+PLAYHT_USER_ID=...
+PLAYHT_API_KEY=...
+
+# Plivo
+PLIVO_AUTH_ID=...
+PLIVO_AUTH_TOKEN=...
+
 # Qwen
 QWEN_API_KEY=...
 
+# Rime
+RIME_API_KEY=...
+RIME_VOICE_ID=...
+
+# SambaNova
+SAMBANOVA_API_KEY=...
+
+# Sarvam AI
+SARVAM_API_KEY=...
+
+# Sentry
+SENTRY_DSN=...
+
+# Simli
+SIMLI_API_KEY=...
+SIMLI_FACE_ID=...
+
+# Smart turn
+LOCAL_SMART_TURN_MODEL_PATH=...
+FAL_SMART_TURN_API_KEY=...
+
+# Soniox
+SONIOX_API_KEY=...
+
+# Speechmatics
+SPEECHMATICS_API_KEY=...
+
+# Tavus
+TAVUS_API_KEY=...
+TAVUS_REPLICA_ID=...
+
+# Telnyx
+TELNYX_API_KEY=...
+TELNYX_ACCOUNT_SID=...
+
+# Together.ai
+TOGETHER_API_KEY=...
+
+# Twilio
+TWILIO_ACCOUNT_SID=...
+TWILIO_AUTH_TOKEN=...
+
 # WhatsApp
-WHATSAPP_TOKEN=
-WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=
-WHATSAPP_PHONE_NUMBER_ID=
-WHATSAPP_APP_SECRET=
+WHATSAPP_TOKEN=...
+WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
+WHATSAPP_PHONE_NUMBER_ID=...
+WHATSAPP_APP_SECRET=...

examples/foundational/07-interruptible.py

@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.stt import CartesiaSTTService
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -58,7 +58,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/07m-interruptible-aws.py

@@ -67,8 +67,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
+        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
     )
 
     messages = [

examples/foundational/08-bots-arguing.py

@@ -1,147 +0,0 @@
-import asyncio
-import logging
-import os
-from typing import Tuple
-
-import aiohttp
-from dotenv import load_dotenv
-
-from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMContextFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.processors.aggregators import SentenceAggregator
-from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.runner.daily import configure
-from pipecat.services.azure import AzureLLMService, AzureTTSService
-from pipecat.services.elevenlabs import ElevenLabsTTSService
-from pipecat.services.fal import FalImageGenService
-from pipecat.transports.daily.transport import DailyTransport
-
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("pipecat")
-logger.setLevel(logging.DEBUG)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Respond bot",
-            duration_minutes=10,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            camera_enabled=True,
-            camera_width=1024,
-            camera_height=1024,
-        )
-
-        llm = AzureLLMService(
-            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
-            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-            model=os.getenv("AZURE_CHATGPT_MODEL"),
-        )
-        tts1 = AzureTTSService(
-            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
-            region=os.getenv("AZURE_SPEECH_REGION"),
-        )
-        tts2 = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id="jBpfuIE2acCO8z3wKNLl",
-        )
-        dalle = FalImageGenService(
-            params=FalImageGenService.InputParams(image_size="1024x1024"),
-            aiohttp_session=session,
-            key=os.getenv("FAL_KEY"),
-        )
-
-        bot1_messages = [
-            {
-                "role": "system",
-                "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long.",
-            },
-        ]
-        bot2_messages = [
-            {
-                "role": "system",
-                "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich.",
-            },
-        ]
-
-        async def get_text_and_audio(messages) -> Tuple[str, bytearray]:
-            """This function streams text from the LLM and uses the TTS service to convert
-            that text to speech as it's received.
-            """
-            source_queue = asyncio.Queue()
-            sink_queue = asyncio.Queue()
-            sentence_aggregator = SentenceAggregator()
-            pipeline = Pipeline([llm, sentence_aggregator, tts1], source_queue, sink_queue)
-
-            await source_queue.put(LLMContextFrame(LLMContext(messages)))
-            await source_queue.put(EndFrame())
-            await pipeline.run_pipeline()
-
-            message = ""
-            all_audio = bytearray()
-            while sink_queue.qsize():
-                frame = sink_queue.get_nowait()
-                if isinstance(frame, TextFrame):
-                    message += frame.text
-                elif isinstance(frame, AudioFrame):
-                    all_audio.extend(frame.audio)
-
-            return (message, all_audio)
-
-        async def get_bot1_statement():
-            message, audio = await get_text_and_audio(bot1_messages)
-
-            bot1_messages.append({"role": "assistant", "content": message})
-            bot2_messages.append({"role": "user", "content": message})
-
-            return audio
-
-        async def get_bot2_statement():
-            message, audio = await get_text_and_audio(bot2_messages)
-
-            bot2_messages.append({"role": "assistant", "content": message})
-            bot1_messages.append({"role": "user", "content": message})
-
-            return audio
-
-        async def argue():
-            for i in range(100):
-                print(f"In iteration {i}")
-
-                bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed"
-
-                (audio1, image_data1) = await asyncio.gather(
-                    get_bot1_statement(), dalle.run_image_gen(bot1_description)
-                )
-                await transport.send_queue.put(
-                    [
-                        ImageFrame(image_data1[1], image_data1[2]),
-                        AudioFrame(audio1),
-                    ]
-                )
-
-                bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed"
-
-                (audio2, image_data2) = await asyncio.gather(
-                    get_bot2_statement(), dalle.run_image_gen(bot2_description)
-                )
-                await transport.send_queue.put(
-                    [
-                        ImageFrame(image_data2[1], image_data2[2]),
-                        AudioFrame(audio2),
-                    ]
-                )
-
-        await asyncio.gather(transport.run(), argue())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/08-custom-frame-processor.py

@@ -0,0 +1,170 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import io
+import os
+import re
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import (
+    Frame,
+    LLMRunFrame,
+    MetricsFrame,
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+def format_metrics(metrics, indent=0):
+    lines = []
+    tab = "\t" * indent
+
+    for metric in metrics:
+        lines.append(tab + type(metric).__name__)
+        for field, value in vars(metric).items():
+            if hasattr(value, "__dict__") and not isinstance(
+                value, (str, int, float, bool, type(None))
+            ):
+                lines.append(f"{tab}\t{field}={type(value).__name__}")
+                for k, v in vars(value).items():
+                    lines.append(f"{tab}\t\t{k}={repr(v)}")
+            else:
+                lines.append(f"{tab}\t{field}={repr(value)}")
+
+    return "\n".join(lines)
+
+
+class MetricsFrameLogger(FrameProcessor):
+    """MetricsFrameLogger formats and logs all MetericsFrames"""
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, MetricsFrame):
+            logger.info(f"{frame.name}\n    {format_metrics(frame.data)}")
+            await self.push_frame(frame, direction)
+
+        # ALWAYS push all frames
+        else:
+            # SUPER IMPORTANT: always push every frame!
+            await self.push_frame(frame, direction)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    metrics_frame_processor = MetricsFrameLogger()
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+            metrics_frame_processor,  # pretty print metrics frames
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/13f-cartesia-transcription.py

@@ -48,10 +48,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = CartesiaSTTService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        base_url=os.getenv("CARTESIA_BASE_URL"),
-    )
+    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
     tl = TranscriptionLogger()
 

examples/foundational/14r-function-calling-aws.py

@@ -79,8 +79,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
+        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
     )
 
     # You can also register a function_name of None to get all functions

examples/foundational/14x-function-calling-openpipe.py

@@ -0,0 +1,182 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+import time
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openpipe.llm import OpenPipeLLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    timestamp = int(time.time())
+    llm = OpenPipeLLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
+        tags={"conversation_id": f"pipecat-{timestamp}"},
+    )
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/17-detect-user-idle.py

@@ -82,25 +82,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def handle_user_idle(user_idle: UserIdleProcessor, retry_count: int) -> bool:
         if retry_count == 1:
             # First attempt: Add a gentle prompt to the conversation
-            message = {
-                "role": "system",
-                "content": "The user has been quiet. Politely and briefly ask if they're still there.",
-            }
-            await user_idle.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
+            await user_idle.push_frame(TTSSpeakFrame("First check."))
             return True
         elif retry_count == 2:
             # Second attempt: More direct prompt
-            message = {
-                "role": "system",
-                "content": "The user is still inactive. Ask if they'd like to continue our conversation.",
-            }
-            await user_idle.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
+            await user_idle.push_frame(TTSSpeakFrame("Second check."))
             return True
         else:
             # Third attempt: End the conversation
-            await user_idle.push_frame(
-                TTSSpeakFrame("It seems like you're busy right now. Have a nice day!")
-            )
+            await user_idle.push_frame(TTSSpeakFrame("Third check."))
             await task.queue_frame(EndFrame())
             return False
 
@@ -128,6 +118,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
+    turn_observer = task.turn_tracking_observer
+    if turn_observer:
+
+        @turn_observer.event_handler("on_turn_ended")
+        async def on_turn_ended(observer, turn_number, duration, was_interrupted):
+            # Log the context after every turn
+            logger.info(f"📝 Context after turn {turn_number}: {context.get_messages()}")
+
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")

examples/foundational/19-openai-realtime.py

@@ -5,6 +5,7 @@
 #
 
 
+import asyncio
 import os
 from datetime import datetime
 
@@ -14,12 +15,14 @@ from loguru import logger
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage
+from pipecat.frames.frames import LLMRunFrame, LLMSetToolsFrame, TranscriptionMessage
 from pipecat.observers.loggers.transcription_log_observer import TranscriptionLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -52,6 +55,18 @@ async def fetch_weather_from_api(params: FunctionCallParams):
     )
 
 
+async def get_news(params: FunctionCallParams):
+    await params.result_callback(
+        {
+            "news": [
+                "Massive UFO currently hovering above New York City",
+                "Stock markets reach all-time highs",
+                "Living dinosaur species discovered in the Amazon rainforest",
+            ],
+        }
+    )
+
+
 async def fetch_restaurant_recommendation(params: FunctionCallParams):
     await params.result_callback({"name": "The Golden Dragon"})
 
@@ -73,6 +88,13 @@ weather_function = FunctionSchema(
     required=["location", "format"],
 )
 
+get_news_function = FunctionSchema(
+    name="get_news",
+    description="Get the current news.",
+    properties={},
+    required=[],
+)
+
 restaurant_function = FunctionSchema(
     name="get_restaurant_recommendation",
     description="Get a restaurant recommendation",
@@ -140,10 +162,6 @@ even if you're asked about them.
 You are participating in a voice conversation. Keep your responses concise, short, and to the point
 unless specifically asked to elaborate on a topic.
 
-You have access to the following tools:
-- get_current_weather: Get the current weather for a given location.
-- get_restaurant_recommendation: Get a restaurant recommendation for a given location.
-
 Remember, your responses should be short. Just one or two sentences, usually. Respond in English.""",
     )
 
@@ -157,25 +175,31 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
     # llm.register_function(None, fetch_weather_from_api)
     llm.register_function("get_current_weather", fetch_weather_from_api)
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+    llm.register_function("get_news", get_news)
 
     transcript = TranscriptProcessor()
 
     # Create a standard OpenAI LLM context object using the normal messages format. The
     # OpenAIRealtimeLLMService will convert this internally to messages that the
     # openai WebSocket API can understand.
-    context = OpenAILLMContext(
+    context = LLMContext(
         [{"role": "user", "content": "Say hello!"}],
         tools,
     )
 
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when OpenAI Realtime used with
+        # "audio" modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             context_aggregator.user(),
+            transcript.user(),  # LLM pushes TranscriptionFrames upstream
             llm,  # LLM
-            transcript.user(),  # Placed after the LLM, as LLM pushes TranscriptionFrames downstream
             transport.output(),  # Transport bot output
             transcript.assistant(),  # After the transcript output, to time with the audio output
             context_aggregator.assistant(),
@@ -198,6 +222,13 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         # Kick off the conversation.
         await task.queue_frames([LLMRunFrame()])
 
+        # Add a new tool at runtime after a delay.
+        await asyncio.sleep(15)
+        new_tools = ToolsSchema(
+            standard_tools=[weather_function, restaurant_function, get_news_function]
+        )
+        await task.queue_frames([LLMSetToolsFrame(tools=new_tools)])
+
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):
         logger.info(f"Client disconnected")

examples/foundational/19a-azure-realtime.py

@@ -18,7 +18,9 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
@@ -155,10 +157,10 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
     llm.register_function("get_current_weather", fetch_weather_from_api)
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
 
-    # Create a standard OpenAI LLM context object using the normal messages format. The
+    # Create a standard LLM context object using the normal messages format. The
     # OpenAIRealtimeBetaLLMService will convert this internally to messages that the
     # openai WebSocket API can understand.
-    context = OpenAILLMContext(
+    context = LLMContext(
         [{"role": "user", "content": "Say hello!"}],
         # [{"role": "user", "content": [{"type": "text", "text": "Say hello!"}]}],
         #     [
@@ -173,7 +175,12 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         tools,
     )
 
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when OpenAI Realtime used with
+        # "audio" modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/19b-openai-realtime-text.py

@@ -18,7 +18,8 @@ from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -169,20 +170,20 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
     # Create a standard OpenAI LLM context object using the normal messages format. The
     # OpenAIRealtimeLLMService will convert this internally to messages that the
     # openai WebSocket API can understand.
-    context = OpenAILLMContext(
+    context = LLMContext(
         [{"role": "user", "content": "Say hello!"}],
         tools,
     )
 
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             context_aggregator.user(),
+            transcript.user(),  # LLM pushes TranscriptionFrames upstream
             llm,  # LLM
             tts,  # TTS
-            transcript.user(),  # Placed after the LLM, as LLM pushes TranscriptionFrames downstream
             transport.output(),  # Transport bot output
             transcript.assistant(),  # After the transcript output, to time with the audio output
             context_aggregator.assistant(),

examples/foundational/20b-persistent-context-openai-realtime.py

@@ -13,14 +13,15 @@ from datetime import datetime
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import (
-    OpenAILLMContext,
-)
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -69,11 +70,11 @@ async def save_conversation(params: FunctionCallParams):
     timestamp = datetime.now().strftime("%Y-%m-%d_%H:%M:%S")
     filename = f"{BASE_FILENAME}{timestamp}.json"
     logger.debug(
-        f"writing conversation to {filename}\n{json.dumps(params.context.messages, indent=4)}"
+        f"writing conversation to {filename}\n{json.dumps(params.context.get_messages(), indent=4)}"
     )
     try:
         with open(filename, "w") as file:
-            messages = params.context.get_messages_for_persistent_storage()
+            messages = params.context.get_messages()
             # remove the last message, which is the instruction we just gave to save the conversation
             messages.pop()
             json.dump(messages, file, indent=2)
@@ -90,6 +91,10 @@ async def load_conversation(params: FunctionCallParams):
             with open(filename, "r") as file:
                 params.context.set_messages(json.load(file))
                 await params.llm.reset_conversation()
+                # NOTE: we manually create a response here rather than relying
+                # on the function callback to trigger one since we've reset the
+                # conversation so the remote service doesn't know about the
+                # in-progress tool call.
                 await params.llm._create_response()
         except Exception as e:
             await params.result_callback({"success": False, "error": str(e)})
@@ -97,14 +102,12 @@ async def load_conversation(params: FunctionCallParams):
     asyncio.create_task(_reset())
 
 
-tools = [
-    {
-        "type": "function",
-        "name": "get_current_weather",
-        "description": "Get the current weather",
-        "parameters": {
-            "type": "object",
-            "properties": {
+tools = ToolsSchema(
+    standard_tools=[
+        FunctionSchema(
+            name="get_current_weather",
+            description="Get the current weather",
+            properties={
                 "location": {
                     "type": "string",
                     "description": "The city and state, e.g. San Francisco, CA",
@@ -115,45 +118,33 @@ tools = [
                     "description": "The temperature unit to use. Infer this from the users location.",
                 },
             },
-            "required": ["location", "format"],
-        },
-    },
-    {
-        "type": "function",
-        "name": "save_conversation",
-        "description": "Save the current conversatione. Use this function to persist the current conversation to external storage.",
-        "parameters": {
-            "type": "object",
-            "properties": {},
-            "required": [],
-        },
-    },
-    {
-        "type": "function",
-        "name": "get_saved_conversation_filenames",
-        "description": "Get a list of saved conversation histories. Returns a list of filenames. Each filename includes a date and timestamp. Each file is conversation history that can be loaded into this session.",
-        "parameters": {
-            "type": "object",
-            "properties": {},
-            "required": [],
-        },
-    },
-    {
-        "type": "function",
-        "name": "load_conversation",
-        "description": "Load a conversation history. Use this function to load a conversation history into the current session.",
-        "parameters": {
-            "type": "object",
-            "properties": {
+            required=["location", "format"],
+        ),
+        FunctionSchema(
+            name="save_conversation",
+            description="Save the current conversatione. Use this function to persist the current conversation to external storage.",
+            properties={},
+            required=[],
+        ),
+        FunctionSchema(
+            name="get_saved_conversation_filenames",
+            description="Get a list of saved conversation histories. Returns a list of filenames. Each filename includes a date and timestamp. Each file is conversation history that can be loaded into this session.",
+            properties={},
+            required=[],
+        ),
+        FunctionSchema(
+            name="load_conversation",
+            description="Load a conversation history. Use this function to load a conversation history into the current session.",
+            properties={
                 "filename": {
                     "type": "string",
                     "description": "The filename of the conversation history to load.",
                 }
             },
-            "required": ["filename"],
-        },
-    },
-]
+            required=["filename"],
+        ),
+    ]
+)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -224,8 +215,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
     llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
     llm.register_function("load_conversation", load_conversation)
 
-    context = OpenAILLMContext([], tools)
-    context_aggregator = llm.create_context_aggregator(context)
+    context = LLMContext([{"role": "user", "content": "Say hello!"}], tools)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [

examples/foundational/20c-persistent-context-anthropic.py

@@ -72,7 +72,6 @@ async def save_conversation(params: FunctionCallParams):
     )
     try:
         with open(filename, "w") as file:
-            # todo: extract 'system' into the first message in the list
             messages = params.context.get_messages()
             # remove the last message, which is the instruction we just gave to save the conversation
             messages.pop()

examples/foundational/20d-persistent-context-gemini.py

@@ -90,7 +90,6 @@ async def save_conversation(params: FunctionCallParams):
     )
     try:
         with open(filename, "w") as file:
-            # todo: extract 'system' into the first message in the list
             messages = params.context.get_messages()
             # remove the last message (the instruction to save the context)
             messages.pop()

examples/foundational/20e-persistent-context-aws-nova-sonic.py

@@ -20,6 +20,8 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -75,7 +77,7 @@ async def save_conversation(params: FunctionCallParams):
     filename = f"{BASE_FILENAME}{timestamp}.json"
     try:
         with open(filename, "w") as file:
-            messages = params.context.get_messages_for_persistent_storage()
+            messages = params.context.get_messages()
             # remove the last few messages. in reverse order, they are:
             # - the in progress save tool call
             # - the invocation of the save tool call
@@ -223,13 +225,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
     llm.register_function("load_conversation", load_conversation)
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         messages=[
             {"role": "system", "content": f"{system_instruction}"},
         ],
         tools=tools,
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [

examples/foundational/26a-gemini-live-transcription.py

@@ -16,7 +16,9 @@ from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -72,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # inference_on_context_initialization=False,
     )
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         [
             {
                 "role": "user",
@@ -90,7 +92,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             #     },
         ],
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     transcript = TranscriptProcessor()
 

examples/foundational/26b-gemini-live-function-calling.py

@@ -19,7 +19,9 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
@@ -139,10 +141,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("get_current_weather", fetch_weather_from_api)
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         [{"role": "user", "content": "Say hello."}],
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/26c-gemini-live-video.py

@@ -17,7 +17,9 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
     create_transport,
@@ -65,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # inference_on_context_initialization=False,
     )
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         [
             {
                 "role": "user",
@@ -73,7 +75,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             },
         ],
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/26d-gemini-live-text.py

@@ -16,7 +16,8 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -109,8 +110,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Set up conversation context and management
     # The context_aggregator will automatically collect conversation context
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [

examples/foundational/26e-gemini-live-google-search.py

@@ -16,7 +16,9 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
@@ -90,7 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         tools=tools,
     )
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         [
             {
                 "role": "user",
@@ -98,7 +100,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             }
         ],
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/26f-gemini-live-files-api.py

@@ -16,7 +16,9 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
@@ -129,7 +131,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         mime_type = "text/plain"
 
         # Create context with file reference
-        context = OpenAILLMContext(
+        context = LLMContext(
             [
                 {
                     "role": "user",
@@ -152,7 +154,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     except Exception as e:
         logger.error(f"Error uploading file: {e}")
         # Continue with a basic context if file upload fails
-        context = OpenAILLMContext(
+        context = LLMContext(
             [
                 {
                     "role": "user",
@@ -162,7 +164,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         )
 
     # Create context aggregator
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     # Build the pipeline
     pipeline = Pipeline(

examples/foundational/26g-gemini-live-groundingMetadata.py

@@ -10,7 +10,9 @@ from pipecat.frames.frames import Frame, LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -124,8 +126,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     # Set up conversation context and management
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/26h-gemini-live-vertex-function-calling.py

@@ -9,21 +9,21 @@ import os
 from datetime import datetime
 
 from dotenv import load_dotenv
-from google.genai.types import HttpOptions
 from loguru import logger
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.services.google.gemini_live.llm_vertex import GeminiLiveVertexLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -139,10 +139,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("get_current_weather", fetch_weather_from_api)
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
 
-    context = OpenAILLMContext(
-        [{"role": "user", "content": "Say hello."}],
+    context = LLMContext([{"role": "user", "content": "Say hello."}])
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
     )
-    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [

examples/foundational/26i-gemini-live-graceful-end.py

@@ -18,7 +18,9 @@ from pipecat.frames.frames import EndTaskFrame, LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -62,7 +64,7 @@ You have three tools available to you:
 
 After you've responded to the user three times, do two things, in order:
 1. Politely let them know that that's all the time you have today and say goodbye.
-2. Call the end_conversation tool to gracefully end the conversation.
+2. *WITHOUT WAITING FOR THE USER TO RESPOND*, call the end_conversation tool to gracefully end the conversation.
 """
 
 
@@ -152,10 +154,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
     llm.register_function("end_conversation", end_conversation)
 
-    context = OpenAILLMContext(
+    context = LLMContext(
         [{"role": "user", "content": "Say hello."}],
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/27-simli-layer.py

@@ -9,7 +9,6 @@ import os
 
 from dotenv import load_dotenv
 from loguru import logger
-from simli import SimliConfig
 
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
@@ -66,11 +65,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",
     )
 
     simli_ai = SimliVideoService(
-        SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_ID")),
+        api_key=os.getenv("SIMLI_API_KEY"),
+        face_id="cace3ef7-a4c4-425d-a8cf-a5358eb0c427",
     )
 
     llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")

examples/foundational/40-aws-nova-sonic.py

@@ -18,7 +18,8 @@ from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService
@@ -119,9 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("get_current_weather", fetch_weather_from_api)
 
     # Set up context and context management.
-    # AWSNovaSonicService will adapt OpenAI LLM context objects with standard message format to
-    # what's expected by Nova Sonic.
-    context = OpenAILLMContext(
+    context = LLMContext(
         messages=[
             {"role": "system", "content": f"{system_instruction}"},
             {
@@ -131,7 +130,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ],
         tools=tools,
     )
-    context_aggregator = llm.create_context_aggregator(context)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     # Build the pipeline
     pipeline = Pipeline(

examples/foundational/46-video-processing.py

@@ -15,7 +15,9 @@ from pipecat.frames.frames import Frame, InputImageRawFrame, LLMRunFrame, Output
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response import LLMAssistantAggregatorParams
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
@@ -108,8 +110,13 @@ async def run_bot(pipecat_transport):
         }
     ]
 
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
+        #  modality (the default)
+        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
+    )
 
     # RTVI events for Pipecat client UI
     rtvi = RTVIProcessor()

examples/foundational/47-sentry-metrics.py

@@ -0,0 +1,142 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import sentry_sdk
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.metrics.sentry import SentryMetrics
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Sentry
+    sentry_sdk.init(
+        dsn=os.getenv("SENTRY_DSN"),
+        traces_sample_rate=1.0,
+    )
+
+    stt = DeepgramSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        metrics=SentryMetrics(),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        metrics=SentryMetrics(),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        metrics=SentryMetrics(),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/48-service-switcher.py

@@ -0,0 +1,153 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, ManuallySwitchServiceFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.service_switcher import ServiceSwitcher, ServiceSwitcherStrategyManual
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.stt import CartesiaSTTService
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt_cartesia = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
+    stt_deepgram = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt_switcher = ServiceSwitcher(
+        services=[stt_cartesia, stt_deepgram], strategy_type=ServiceSwitcherStrategyManual
+    )
+
+    tts_cartesia = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",
+    )
+    tts_deepgram = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    tts_switcher = ServiceSwitcher(
+        services=[tts_cartesia, tts_deepgram], strategy_type=ServiceSwitcherStrategyManual
+    )
+
+    llm_openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm_google = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    llm_switcher = ServiceSwitcher(
+        services=[llm_openai, llm_google], strategy_type=ServiceSwitcherStrategyManual
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt_switcher,
+            context_aggregator.user(),  # User responses
+            llm_switcher,  # LLM
+            tts_switcher,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+        await asyncio.sleep(15)
+        print(f"Switching to {stt_deepgram}")
+        await task.queue_frames([ManuallySwitchServiceFrame(service=stt_deepgram)])
+        await asyncio.sleep(15)
+        print(f"Switching to {llm_google}")
+        await task.queue_frames([ManuallySwitchServiceFrame(service=llm_google)])
+        await asyncio.sleep(15)
+        print(f"Switching to {tts_deepgram}")
+        await task.queue_frames([ManuallySwitchServiceFrame(service=tts_deepgram)])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/quickstart/README.md

@@ -73,13 +73,13 @@ Transform your local bot into a production-ready service. Pipecat Cloud handles
 
 1. [Sign up for Pipecat Cloud](https://pipecat.daily.co/sign-up).
 
-2. Install the Pipecat Cloud CLI:
+2. Install the Pipecat CLI:
 
    ```bash
-   uv add pipecatcloud
+   uv tool install pipecat-ai-cli
    ```
 
-> 💡 Tip: You can run the `pipecatcloud` CLI using the `pcc` alias.
+> 💡 Tip: You can run the `pipecat` CLI using the `pc` alias.
 
 3. Set up Docker for building your bot image:
 
@@ -113,12 +113,22 @@ secret_set = "quickstart-secrets"
 
 > 💡 Tip: [Set up `image_credentials`](https://docs.pipecat.ai/deployment/pipecat-cloud/fundamentals/secrets#image-pull-secrets) in your TOML file for authenticated image pulls
 
+### Log in to Pipecat Cloud
+
+To start using the CLI, authenticate to Pipecat Cloud:
+
+```bash
+pipecat cloud auth login
+```
+
+You'll be presented with a link that you can click to authenticate your client.
+
 ### Configure secrets
 
 Upload your API keys to Pipecat Cloud's secure storage:
 
 ```bash
-uv run pcc secrets set quickstart-secrets --file .env
+pipecat cloud secrets set quickstart-secrets --file .env
 ```
 
 This creates a secret set called `quickstart-secrets` (matching your TOML file) and uploads all your API keys from `.env`.
@@ -128,13 +138,13 @@ This creates a secret set called `quickstart-secrets` (matching your TOML file)
 Build your Docker image and push to Docker Hub:
 
 ```bash
-uv run pcc docker build-push
+pipecat cloud docker build-push
 ```
 
 Deploy to Pipecat Cloud:
 
 ```bash
-uv run pcc deploy
+pipecat cloud deploy
 ```
 
 ### Connect to your agent

examples/quickstart/pcc-deploy.toml

@@ -1,6 +1,11 @@
 agent_name = "quickstart"
 image = "your_username/quickstart:0.1"
 secret_set = "quickstart-secrets"
+agent_profile = "agent-1x"
+
+# RECOMMENDED: Set an image pull secret:
+# https://docs.pipecat.ai/deployment/pipecat-cloud/fundamentals/secrets#image-pull-secrets
+# image_credentials = "your_image_pull_secret"
 
 [scaling]
 	min_agents = 1

examples/quickstart/pyproject.toml

@@ -4,13 +4,14 @@ version = "0.1.0"
 description = "Quickstart example for building voice AI bots with Pipecat"
 requires-python = ">=3.10"
 dependencies = [
-    "pipecat-ai[webrtc,daily,silero,deepgram,openai,cartesia,local-smart-turn-v3,runner]>=0.0.86",
-    "pipecatcloud>=0.2.4"
+    "pipecat-ai[webrtc,daily,silero,deepgram,openai,cartesia,local-smart-turn-v3,runner]",
+    "pipecat-ai-cli"
 ]
 
 [dependency-groups]
 dev = [
-    "ruff~=0.12.1",
+    "pyright>=1.1.404,<2",
+    "ruff>=0.12.11,<1",
 ]
 
 [tool.ruff]

pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
     "pyloudnorm~=0.1.1",
     "resampy~=0.4.3",
     "soxr~=0.5.0",
-    "openai>=1.74.0,<=1.99.1",
+    "openai>=1.74.0,<3",
     # Pinning numba to resolve package dependencies
     "numba==0.61.2",
     "wait_for2>=0.4.1; python_version<'3.12'",
@@ -50,12 +50,12 @@ anthropic = [ "anthropic~=0.49.0" ]
 assemblyai = [ "pipecat-ai[websockets-base]" ]
 asyncai = [ "pipecat-ai[websockets-base]" ]
 aws = [ "aioboto3~=15.0.0", "pipecat-ai[websockets-base]" ]
-aws-nova-sonic = [ "aws_sdk_bedrock_runtime~=0.1.0; python_version>='3.12'" ]
+aws-nova-sonic = [ "aws_sdk_bedrock_runtime~=0.1.1; python_version>='3.12'" ]
 azure = [ "azure-cognitiveservices-speech~=1.42.0"]
 cartesia = [ "cartesia~=2.0.3", "pipecat-ai[websockets-base]" ]
 cerebras = []
 deepseek = []
-daily = [ "daily-python~=0.19.9" ]
+daily = [ "daily-python~=0.21.0" ]
 deepgram = [ "deepgram-sdk~=4.7.0" ]
 elevenlabs = [ "pipecat-ai[websockets-base]" ]
 fal = [ "fal-client~=0.5.9" ]
@@ -84,7 +84,7 @@ nim = []
 neuphonic = [ "pipecat-ai[websockets-base]" ]
 noisereduce = [ "noisereduce~=3.0.3" ]
 openai = [ "pipecat-ai[websockets-base]" ]
-openpipe = [ "openpipe~=4.50.0" ]
+openpipe = [ "openpipe>=4.50.0,<6" ]
 openrouter = []
 perplexity = []
 playht = [ "pipecat-ai[websockets-base]" ]
@@ -102,7 +102,7 @@ silero = [ "onnxruntime>=1.20.1,<2" ]
 simli = [ "simli-ai~=0.1.10"]
 soniox = [ "pipecat-ai[websockets-base]" ]
 soundfile = [ "soundfile~=0.13.0" ]
-speechmatics = [ "speechmatics-rt>=0.4.0" ]
+speechmatics = [ "speechmatics-rt>=0.5.0" ]
 strands = [ "strands-agents>=1.9.1,<2" ]
 tavus=[]
 together = []

scripts/evals/run-release-evals.py

@@ -136,6 +136,7 @@ TESTS_14 = [
     ("14r-function-calling-aws.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("14v-function-calling-openai.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("14w-function-calling-mistral.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
+    ("14x-function-calling-openpipe.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     # Currently not working.
     # ("14c-function-calling-together.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     # ("14l-function-calling-deepseek.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),

src/pipecat/adapters/schemas/tools_schema.py

@@ -22,9 +22,12 @@ class AdapterType(Enum):
 
     Parameters:
         GEMINI: Google Gemini adapter - currently the only service supporting custom tools.
+        SHIM: Backward compatibility shim for creating ToolsSchemas from lists of tools in
+              any format, used by LLMContext.from_openai_context.
     """
 
     GEMINI = "gemini"  # that is the only service where we are able to add custom tools for now
+    SHIM = "shim"  # for use as backward compatibility shim for creating ToolsSchemas from list of tools in any format
 
 
 class ToolsSchema:

src/pipecat/adapters/services/anthropic_adapter.py

@@ -110,7 +110,7 @@ class AnthropicLLMAdapter(BaseLLMAdapter[AnthropicLLMInvocationParams]):
         system = NOT_GIVEN
         messages = []
 
-        # first, map messages using self._from_universal_context_message(m)
+        # First, map messages using self._from_universal_context_message(m)
         try:
             messages = [self._from_universal_context_message(m) for m in universal_context_messages]
         except Exception as e:

src/pipecat/adapters/services/aws_nova_sonic_adapter.py

@@ -6,13 +6,47 @@
 
 """AWS Nova Sonic LLM adapter for Pipecat."""
 
+import copy
 import json
-from typing import Any, Dict, List, TypedDict
+from dataclasses import dataclass
+from enum import Enum
+from typing import Any, Dict, List, Optional, TypedDict
+
+from loguru import logger
 
 from pipecat.adapters.base_llm_adapter import BaseLLMAdapter
 from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+from pipecat.processors.aggregators.llm_context import LLMContext, LLMContextMessage
+
+
+class Role(Enum):
+    """Roles supported in AWS Nova Sonic conversations.
+
+    Parameters:
+        SYSTEM: System-level messages (not used in conversation history).
+        USER: Messages sent by the user.
+        ASSISTANT: Messages sent by the assistant.
+        TOOL: Messages sent by tools (not used in conversation history).
+    """
+
+    SYSTEM = "SYSTEM"
+    USER = "USER"
+    ASSISTANT = "ASSISTANT"
+    TOOL = "TOOL"
+
+
+@dataclass
+class AWSNovaSonicConversationHistoryMessage:
+    """A single message in AWS Nova Sonic conversation history.
+
+    Parameters:
+        role: The role of the message sender (USER or ASSISTANT only).
+        text: The text content of the message.
+    """
+
+    role: Role  # only USER and ASSISTANT
+    text: str
 
 
 class AWSNovaSonicLLMInvocationParams(TypedDict):
@@ -21,7 +55,9 @@ class AWSNovaSonicLLMInvocationParams(TypedDict):
     This is a placeholder until support for universal LLMContext machinery is added for AWS Nova Sonic.
     """
 
-    pass
+    system_instruction: Optional[str]
+    messages: List[AWSNovaSonicConversationHistoryMessage]
+    tools: List[Dict[str, Any]]
 
 
 class AWSNovaSonicLLMAdapter(BaseLLMAdapter[AWSNovaSonicLLMInvocationParams]):
@@ -34,7 +70,7 @@ class AWSNovaSonicLLMAdapter(BaseLLMAdapter[AWSNovaSonicLLMInvocationParams]):
     @property
     def id_for_llm_specific_messages(self) -> str:
         """Get the identifier used in LLMSpecificMessage instances for AWS Nova Sonic."""
-        raise NotImplementedError("Universal LLMContext is not yet supported for AWS Nova Sonic.")
+        return "aws-nova-sonic"
 
     def get_llm_invocation_params(self, context: LLMContext) -> AWSNovaSonicLLMInvocationParams:
         """Get AWS Nova Sonic-specific LLM invocation parameters from a universal LLM context.
@@ -47,7 +83,13 @@ class AWSNovaSonicLLMAdapter(BaseLLMAdapter[AWSNovaSonicLLMInvocationParams]):
         Returns:
             Dictionary of parameters for invoking AWS Nova Sonic's LLM API.
         """
-        raise NotImplementedError("Universal LLMContext is not yet supported for AWS Nova Sonic.")
+        messages = self._from_universal_context_messages(self.get_messages(context))
+        return {
+            "system_instruction": messages.system_instruction,
+            "messages": messages.messages,
+            # NOTE: LLMContext's tools are guaranteed to be a ToolsSchema (or NOT_GIVEN)
+            "tools": self.from_standard_tools(context.tools) or [],
+        }
 
     def get_messages_for_logging(self, context) -> List[Dict[str, Any]]:
         """Get messages from a universal LLM context in a format ready for logging about AWS Nova Sonic.
@@ -62,7 +104,75 @@ class AWSNovaSonicLLMAdapter(BaseLLMAdapter[AWSNovaSonicLLMInvocationParams]):
         Returns:
             List of messages in a format ready for logging about AWS Nova Sonic.
         """
-        raise NotImplementedError("Universal LLMContext is not yet supported for AWS Nova Sonic.")
+        return self._from_universal_context_messages(self.get_messages(context)).messages
+
+    @dataclass
+    class ConvertedMessages:
+        """Container for Google-formatted messages converted from universal context."""
+
+        messages: List[AWSNovaSonicConversationHistoryMessage]
+        system_instruction: Optional[str] = None
+
+    def _from_universal_context_messages(
+        self, universal_context_messages: List[LLMContextMessage]
+    ) -> ConvertedMessages:
+        system_instruction = None
+        messages = []
+
+        # Bail if there are no messages
+        if not universal_context_messages:
+            return self.ConvertedMessages()
+
+        universal_context_messages = copy.deepcopy(universal_context_messages)
+
+        # If we have a "system" message as our first message, let's pull that out into "instruction"
+        if universal_context_messages[0].get("role") == "system":
+            system = universal_context_messages.pop(0)
+            content = system.get("content")
+            if isinstance(content, str):
+                system_instruction = content
+            elif isinstance(content, list):
+                system_instruction = content[0].get("text")
+            if system_instruction:
+                self._system_instruction = system_instruction
+
+        # Process remaining messages to fill out conversation history.
+        # Nova Sonic supports "user" and "assistant" messages in history.
+        for universal_context_message in universal_context_messages:
+            message = self._from_universal_context_message(universal_context_message)
+            if message:
+                messages.append(message)
+
+        return self.ConvertedMessages(messages=messages, system_instruction=system_instruction)
+
+    def _from_universal_context_message(self, message) -> AWSNovaSonicConversationHistoryMessage:
+        """Convert standard message format to Nova Sonic format.
+
+        Args:
+            message: Standard message dictionary to convert.
+
+        Returns:
+            Nova Sonic conversation history message, or None if not convertible.
+        """
+        role = message.get("role")
+        if message.get("role") == "user" or message.get("role") == "assistant":
+            content = message.get("content")
+            if isinstance(message.get("content"), list):
+                content = ""
+                for c in message.get("content"):
+                    if c.get("type") == "text":
+                        content += " " + c.get("text")
+                    else:
+                        logger.error(
+                            f"Unhandled content type in context message: {c.get('type')} - {message}"
+                        )
+            # There won't be content if this is an assistant tool call entry.
+            # We're ignoring those since they can't be loaded into AWS Nova Sonic conversation
+            # history
+            if content:
+                return AWSNovaSonicConversationHistoryMessage(role=Role[role.upper()], text=content)
+        # NOTE: we're ignoring messages with role "tool" since they can't be loaded into AWS Nova
+        # Sonic conversation history
 
     @staticmethod
     def _to_aws_nova_sonic_function_format(function: FunctionSchema) -> Dict[str, Any]:
@@ -100,4 +210,18 @@ class AWSNovaSonicLLMAdapter(BaseLLMAdapter[AWSNovaSonicLLMInvocationParams]):
             List of dictionaries in AWS Nova Sonic function format.
         """
         functions_schema = tools_schema.standard_tools
-        return [self._to_aws_nova_sonic_function_format(func) for func in functions_schema]
+        standard_tools = [
+            self._to_aws_nova_sonic_function_format(func) for func in functions_schema
+        ]
+
+        # For backward compatibility, AWS Nova Sonic can still be used with
+        # tools in dict format, even though it always uses `LLMContext` under
+        # the hood (via `LLMContext.from_openai_context()`).
+        # To support this behavior, we use "shimmed" custom tools here.
+        # (We maintain this backward compatibility because users aren't
+        # *knowingly* opting into the new `LLMContext`.)
+        shimmed_tools = []
+        if tools_schema.custom_tools:
+            shimmed_tools = tools_schema.custom_tools.get(AdapterType.SHIM, [])
+
+        return standard_tools + shimmed_tools

src/pipecat/adapters/services/bedrock_adapter.py

@@ -107,7 +107,7 @@ class AWSBedrockLLMAdapter(BaseLLMAdapter[AWSBedrockLLMInvocationParams]):
         system = None
         messages = []
 
-        # first, map messages using self._from_universal_context_message(m)
+        # First, map messages using self._from_universal_context_message(m)
         try:
             messages = [self._from_universal_context_message(m) for m in universal_context_messages]
         except Exception as e:

src/pipecat/adapters/services/gemini_adapter.py

@@ -8,8 +8,8 @@
 
 import base64
 import json
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, TypedDict
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Tuple, TypedDict
 
 from loguru import logger
 from openai import NotGiven
@@ -24,13 +24,7 @@ from pipecat.processors.aggregators.llm_context import (
 )
 
 try:
-    from google.genai.types import (
-        Blob,
-        Content,
-        FunctionCall,
-        FunctionResponse,
-        Part,
-    )
+    from google.genai.types import Blob, Content, FileData, FunctionCall, FunctionResponse, Part
 except ModuleNotFoundError as e:
     logger.error(f"Exception: {e}")
     logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.")
@@ -133,6 +127,28 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
         messages: List[Content]
         system_instruction: Optional[str] = None
 
+    @dataclass
+    class MessageConversionResult:
+        """Result of converting a single universal context message to Google format.
+
+        Either content (a Google Content object) or a system instruction string
+        is guaranteed to be set.
+
+        Also returns a tool call ID to name mapping for any tool calls
+        discovered in the message.
+        """
+
+        content: Optional[Content] = None
+        system_instruction: Optional[str] = None
+        tool_call_id_to_name_mapping: Dict[str, str] = field(default_factory=dict)
+
+    @dataclass
+    class MessageConversionParams:
+        """Parameters for converting a single universal context message to Google format."""
+
+        already_have_system_instruction: bool
+        tool_call_id_to_name_mapping: Dict[str, str]
+
     def _from_universal_context_messages(
         self, universal_context_messages: List[LLMContextMessage]
     ) -> ConvertedMessages:
@@ -156,24 +172,26 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
         """
         system_instruction = None
         messages = []
+        tool_call_id_to_name_mapping = {}
 
         # Process each message, preserving Google-formatted messages and converting others
         for message in universal_context_messages:
-            if isinstance(message, LLMSpecificMessage):
-                # Assume that LLMSpecificMessage wraps a message in Google format
-                messages.append(message.message)
-                continue
-
-            # Convert standard format to Google format
-            converted = self._from_standard_message(
-                message, already_have_system_instruction=bool(system_instruction)
+            result = self._from_universal_context_message(
+                message,
+                params=self.MessageConversionParams(
+                    already_have_system_instruction=bool(system_instruction),
+                    tool_call_id_to_name_mapping=tool_call_id_to_name_mapping,
+                ),
             )
-            if isinstance(converted, Content):
-                # Regular (non-system) message
-                messages.append(converted)
-            else:
-                # System instruction
-                system_instruction = converted
+            # Each result is either a Content or a system instruction
+            if result.content:
+                messages.append(result.content)
+            elif result.system_instruction:
+                system_instruction = result.system_instruction
+
+            # Merge tool call ID to name mapping
+            if result.tool_call_id_to_name_mapping:
+                tool_call_id_to_name_mapping.update(result.tool_call_id_to_name_mapping)
 
         # Check if we only have function-related messages (no regular text)
         has_regular_messages = any(
@@ -193,9 +211,16 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
 
         return self.ConvertedMessages(messages=messages, system_instruction=system_instruction)
 
+    def _from_universal_context_message(
+        self, message: LLMContextMessage, *, params: MessageConversionParams
+    ) -> MessageConversionResult:
+        if isinstance(message, LLMSpecificMessage):
+            return self.MessageConversionResult(content=message.message)
+        return self._from_standard_message(message, params=params)
+
     def _from_standard_message(
-        self, message: LLMStandardMessage, already_have_system_instruction: bool
-    ) -> Content | str:
+        self, message: LLMStandardMessage, *, params: MessageConversionParams
+    ) -> MessageConversionResult:
         """Convert standard universal context message to Google Content object.
 
         Handles conversion of text, images, and function calls to Google's
@@ -205,10 +230,11 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
         Args:
             message: Message in standard universal context format.
             already_have_system_instruction: Whether we already have a system instruction
+            params: Parameters for conversion.
 
         Returns:
-            Content object with role and parts, or a plain string for system
-            messages.
+            MessageConversionResult containing either a Content object or a
+            system instruction string.
 
         Examples:
             Standard text message::
@@ -242,38 +268,49 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
             Converts to Google Content with::
 
                 Content(
-                    role="model",
+                    role="user",
                     parts=[Part(function_call=FunctionCall(name="search", args={"query": "test"}))]
                 )
         """
         role = message["role"]
         content = message.get("content", [])
+
         if role == "system":
-            if already_have_system_instruction:
+            if params.already_have_system_instruction:
                 role = "user"  # Convert system message to user role if we already have a system instruction
             else:
-                # System instructions are returned as plain text
+                system_instruction: str = None
                 if isinstance(content, str):
-                    return content
+                    system_instruction = content
                 elif isinstance(content, list):
                     # If content is a list, we assume it's a list of text parts, per the standard
-                    return " ".join(part["text"] for part in content if part.get("type") == "text")
+                    system_instruction = " ".join(
+                        part["text"] for part in content if part.get("type") == "text"
+                    )
+                if system_instruction:
+                    return self.MessageConversionResult(system_instruction=system_instruction)
         elif role == "assistant":
             role = "model"
 
         parts = []
+        tool_call_id_to_name_mapping = {}
+
         if message.get("tool_calls"):
             for tc in message["tool_calls"]:
+                id = tc["id"]
+                name = tc["function"]["name"]
+                tool_call_id_to_name_mapping[id] = name
                 parts.append(
                     Part(
                         function_call=FunctionCall(
-                            name=tc["function"]["name"],
+                            id=id,
+                            name=name,
                             args=json.loads(tc["function"]["arguments"]),
                         )
                     )
                 )
         elif role == "tool":
-            role = "model"
+            role = "user"
             try:
                 response = json.loads(message["content"])
                 if isinstance(response, dict):
@@ -284,10 +321,18 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
                 # Response might not be JSON-deserializable.
                 # This occurs with a UserImageFrame, for example, where we get a plain "COMPLETED" string.
                 response_dict = {"value": message["content"]}
+
+            # Get function name from mapping using tool_call_id, or fallback
+            tool_call_id = message.get("tool_call_id")
+            function_name = "tool_call_result"  # Default fallback
+            if tool_call_id and tool_call_id in params.tool_call_id_to_name_mapping:
+                function_name = params.tool_call_id_to_name_mapping[tool_call_id]
+
             parts.append(
                 Part(
                     function_response=FunctionResponse(
-                        name="tool_call_result",  # seems to work to hard-code the same name every time
+                        id=tool_call_id,
+                        name=function_name,
                         response=response_dict,
                     )
                 )
@@ -311,5 +356,18 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
                     input_audio = c["input_audio"]
                     audio_bytes = base64.b64decode(input_audio["data"])
                     parts.append(Part(inline_data=Blob(mime_type="audio/wav", data=audio_bytes)))
+                elif c["type"] == "file_data":
+                    file_data = c["file_data"]
+                    parts.append(
+                        Part(
+                            file_data=FileData(
+                                mime_type=file_data.get("mime_type"),
+                                file_uri=file_data.get("file_uri"),
+                            )
+                        )
+                    )
 
-        return Content(role=role, parts=parts)
+        return self.MessageConversionResult(
+            content=Content(role=role, parts=parts),
+            tool_call_id_to_name_mapping=tool_call_id_to_name_mapping,
+        )

src/pipecat/adapters/services/open_ai_realtime_adapter.py

@@ -6,12 +6,18 @@
 
 """OpenAI Realtime LLM adapter for Pipecat."""
 
-from typing import Any, Dict, List, TypedDict
+import copy
+import json
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, TypedDict
+
+from loguru import logger
 
 from pipecat.adapters.base_llm_adapter import BaseLLMAdapter
 from pipecat.adapters.schemas.function_schema import FunctionSchema
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+from pipecat.processors.aggregators.llm_context import LLMContext, LLMContextMessage
+from pipecat.services.openai.realtime import events
 
 
 class OpenAIRealtimeLLMInvocationParams(TypedDict):
@@ -20,7 +26,9 @@ class OpenAIRealtimeLLMInvocationParams(TypedDict):
     This is a placeholder until support for universal LLMContext machinery is added for OpenAI Realtime.
     """
 
-    pass
+    system_instruction: Optional[str]
+    messages: List[events.ConversationItem]
+    tools: List[Dict[str, Any]]
 
 
 class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
@@ -33,7 +41,7 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
     @property
     def id_for_llm_specific_messages(self) -> str:
         """Get the identifier used in LLMSpecificMessage instances for OpenAI Realtime."""
-        raise NotImplementedError("Universal LLMContext is not yet supported for OpenAI Realtime.")
+        return "openai-realtime"
 
     def get_llm_invocation_params(self, context: LLMContext) -> OpenAIRealtimeLLMInvocationParams:
         """Get OpenAI Realtime-specific LLM invocation parameters from a universal LLM context.
@@ -46,7 +54,13 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
         Returns:
             Dictionary of parameters for invoking OpenAI Realtime's API.
         """
-        raise NotImplementedError("Universal LLMContext is not yet supported for OpenAI Realtime.")
+        messages = self._from_universal_context_messages(self.get_messages(context))
+        return {
+            "system_instruction": messages.system_instruction,
+            "messages": messages.messages,
+            # NOTE: LLMContext's tools are guaranteed to be a ToolsSchema (or NOT_GIVEN)
+            "tools": self.from_standard_tools(context.tools) or [],
+        }
 
     def get_messages_for_logging(self, context) -> List[Dict[str, Any]]:
         """Get messages from a universal LLM context in a format ready for logging about OpenAI Realtime.
@@ -61,7 +75,124 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
         Returns:
             List of messages in a format ready for logging about OpenAI Realtime.
         """
-        raise NotImplementedError("Universal LLMContext is not yet supported for OpenAI Realtime.")
+        # NOTE: this is the same as in OpenAIAdapter, as that's what it was
+        # prior to a refactor. Worth noting that for OpenAI Realtime
+        # specifically, not everything handled here is necessarily supported
+        # (or supported yet).
+        msgs = []
+        for message in self.get_messages(context):
+            msg = copy.deepcopy(message)
+            if "content" in msg:
+                if isinstance(msg["content"], list):
+                    for item in msg["content"]:
+                        if item["type"] == "image_url":
+                            if item["image_url"]["url"].startswith("data:image/"):
+                                item["image_url"]["url"] = "data:image/..."
+                        if item["type"] == "input_audio":
+                            item["input_audio"]["data"] = "..."
+            if "mime_type" in msg and msg["mime_type"].startswith("image/"):
+                msg["data"] = "..."
+            msgs.append(msg)
+        return msgs
+
+    @dataclass
+    class ConvertedMessages:
+        """Container for OpenAI-formatted messages converted from universal context."""
+
+        messages: List[events.ConversationItem]
+        system_instruction: Optional[str] = None
+
+    def _from_universal_context_messages(
+        self, universal_context_messages: List[LLMContextMessage]
+    ) -> ConvertedMessages:
+        # We can't load a long conversation history into the openai realtime api yet. (The API/model
+        # forgets that it can do audio, if you do a series of `conversation.item.create` calls.) So
+        # our general strategy until this is fixed is just to put everything into a first "user"
+        # message as a single input.
+
+        if not universal_context_messages:
+            return self.ConvertedMessages(messages=[])
+
+        messages = copy.deepcopy(universal_context_messages)
+        system_instruction = None
+
+        # If we have a "system" message as our first message, let's pull that out into session
+        # "instructions"
+        if messages[0].get("role") == "system":
+            system = messages.pop(0)
+            content = system.get("content")
+            if isinstance(content, str):
+                system_instruction = content
+            elif isinstance(content, list):
+                system_instruction = content[0].get("text")
+            if not messages:
+                return self.ConvertedMessages(messages=[], system_instruction=system_instruction)
+
+        # If we have just a single "user" item, we can just send it normally
+        if len(messages) == 1 and messages[0].get("role") == "user":
+            return self.ConvertedMessages(
+                messages=[self._from_universal_context_message(messages[0])],
+                system_instruction=system_instruction,
+            )
+
+        # Otherwise, let's pack everything into a single "user" message with a bit of
+        # explanation for the LLM
+        intro_text = """
+        This is a previously saved conversation. Please treat this conversation history as a
+        starting point for the current conversation."""
+
+        trailing_text = """
+        This is the end of the previously saved conversation. Please continue the conversation
+        from here. If the last message is a user instruction or question, act on that instruction
+        or answer the question. If the last message is an assistant response, simple say that you
+        are ready to continue the conversation."""
+
+        return self.ConvertedMessages(
+            messages=[
+                {
+                    "role": "user",
+                    "type": "message",
+                    "content": [
+                        {
+                            "type": "input_text",
+                            "text": "\n\n".join(
+                                [intro_text, json.dumps(messages, indent=2), trailing_text]
+                            ),
+                        }
+                    ],
+                }
+            ],
+            system_instruction=system_instruction,
+        )
+
+    def _from_universal_context_message(
+        self, message: LLMContextMessage
+    ) -> events.ConversationItem:
+        if message.get("role") == "user":
+            content = message.get("content")
+            if isinstance(message.get("content"), list):
+                content = ""
+                for c in message.get("content"):
+                    if c.get("type") == "text":
+                        content += " " + c.get("text")
+                    else:
+                        logger.error(
+                            f"Unhandled content type in context message: {c.get('type')} - {message}"
+                        )
+            return events.ConversationItem(
+                role="user",
+                type="message",
+                content=[events.ItemContent(type="input_text", text=content)],
+            )
+        if message.get("role") == "assistant" and message.get("tool_calls"):
+            tc = message.get("tool_calls")[0]
+            return events.ConversationItem(
+                type="function_call",
+                call_id=tc["id"],
+                name=tc["function"]["name"],
+                arguments=tc["function"]["arguments"],
+            )
+        logger.error(f"Unhandled message type in _from_universal_context_message: {message}")
 
     @staticmethod
     def _to_openai_realtime_function_format(function: FunctionSchema) -> Dict[str, Any]:
@@ -94,4 +225,18 @@ class OpenAIRealtimeLLMAdapter(BaseLLMAdapter):
             List of function definitions in OpenAI Realtime format.
         """
         functions_schema = tools_schema.standard_tools
-        return [self._to_openai_realtime_function_format(func) for func in functions_schema]
+        standard_tools = [
+            self._to_openai_realtime_function_format(func) for func in functions_schema
+        ]
+
+        # For backward compatibility, OpenAI Realtime can still be used with
+        # tools in dict format, even though it always uses `LLMContext` under
+        # the hood (via `LLMContext.from_openai_context()`).
+        # To support this behavior, we use "shimmed" custom tools here.
+        # (We maintain this backward compatibility because users aren't
+        # *knowingly* opting into the new `LLMContext`.)
+        shimmed_tools = []
+        if tools_schema.custom_tools:
+            shimmed_tools = tools_schema.custom_tools.get(AdapterType.SHIM, [])
+
+        return standard_tools + shimmed_tools

src/pipecat/pipeline/llm_switcher.py

@@ -14,20 +14,41 @@ from pipecat.services.llm_service import LLMService
 
 
 class LLMSwitcher(ServiceSwitcher[StrategyType]):
-    """A pipeline that switches between different LLMs at runtime."""
+    """A pipeline that switches between different LLMs at runtime.
+
+    Example::
+
+        llm_switcher = LLMSwitcher(
+            llms=[openai_llm, anthropic_llm],
+            strategy_type=ServiceSwitcherStrategyManual
+        )
+    """
 
     def __init__(self, llms: List[LLMService], strategy_type: Type[StrategyType]):
-        """Initialize the service switcher with a list of LLMs and a switching strategy."""
+        """Initialize the service switcher with a list of LLMs and a switching strategy.
+
+        Args:
+            llms: List of LLM services to switch between.
+            strategy_type: The strategy class to use for switching between LLMs.
+        """
         super().__init__(llms, strategy_type)
 
     @property
     def llms(self) -> List[LLMService]:
-        """Get the list of LLMs managed by this switcher."""
+        """Get the list of LLMs managed by this switcher.
+
+        Returns:
+            List of LLM services managed by this switcher.
+        """
         return self.services
 
     @property
     def active_llm(self) -> Optional[LLMService]:
-        """Get the currently active LLM, if any."""
+        """Get the currently active LLM.
+
+        Returns:
+            The currently active LLM service, or None if no LLM is active.
+        """
         return self.strategy.active_service
 
     async def run_inference(self, context: LLMContext) -> Optional[str]:

src/pipecat/pipeline/runner.py

@@ -70,11 +70,15 @@ class PipelineRunner(BaseObject):
         """
         logger.debug(f"Runner {self} started running {task}")
         self._tasks[task.name] = task
-        params = PipelineTaskParams(loop=self._loop)
+
+        # PipelineTask handles asyncio.CancelledError to shutdown the pipeline
+        # properly and re-raises it in case there's more cleanup to do.
         try:
+            params = PipelineTaskParams(loop=self._loop)
             await task.run(params)
         except asyncio.CancelledError:
-            await self._cancel()
+            pass
+
         del self._tasks[task.name]
 
         # Cleanup base object.

src/pipecat/pipeline/service_switcher.py

@@ -21,10 +21,22 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 
 
 class ServiceSwitcherStrategy:
-    """Base class for service switching strategies."""
+    """Base class for service switching strategies.
+
+    Note:
+        Strategy classes are instantiated internally by ServiceSwitcher.
+        Developers should pass the strategy class (not an instance) to ServiceSwitcher.
+    """
 
     def __init__(self, services: List[FrameProcessor]):
-        """Initialize the service switcher strategy with a list of services."""
+        """Initialize the service switcher strategy with a list of services.
+
+        Note:
+            This is called internally by ServiceSwitcher. Do not instantiate directly.
+
+        Args:
+            services: List of frame processors to switch between.
+        """
         self.services = services
         self.active_service: Optional[FrameProcessor] = None
 
@@ -46,10 +58,24 @@ class ServiceSwitcherStrategyManual(ServiceSwitcherStrategy):
 
     This strategy allows the user to manually select which service is active.
     The initial active service is the first one in the list.
+
+    Example::
+
+        stt_switcher = ServiceSwitcher(
+            services=[stt_1, stt_2],
+            strategy_type=ServiceSwitcherStrategyManual
+        )
     """
 
     def __init__(self, services: List[FrameProcessor]):
-        """Initialize the manual service switcher strategy with a list of services."""
+        """Initialize the manual service switcher strategy with a list of services.
+
+        Note:
+            This is called internally by ServiceSwitcher. Do not instantiate directly.
+
+        Args:
+            services: List of frame processors to switch between.
+        """
         super().__init__(services)
         self.active_service = services[0] if services else None
 
@@ -85,7 +111,12 @@ class ServiceSwitcher(ParallelPipeline, Generic[StrategyType]):
     """A pipeline that switches between different services at runtime."""
 
     def __init__(self, services: List[FrameProcessor], strategy_type: Type[StrategyType]):
-        """Initialize the service switcher with a list of services and a switching strategy."""
+        """Initialize the service switcher with a list of services and a switching strategy.
+
+        Args:
+            services: List of frame processors to switch between.
+            strategy_type: The strategy class to use for switching between services.
+        """
         strategy = strategy_type(services)
         super().__init__(*self._make_pipeline_definitions(services, strategy))
         self.services = services
@@ -100,14 +131,20 @@ class ServiceSwitcher(ParallelPipeline, Generic[StrategyType]):
             active_service: FrameProcessor,
             direction: FrameDirection,
         ):
-            """Initialize the service switcher filter with a strategy and direction."""
+            """Initialize the service switcher filter with a strategy and direction.
+
+            Args:
+                wrapped_service: The service that this filter wraps.
+                active_service: The currently active service.
+                direction: The direction of frame flow to filter.
+            """
+            self._wrapped_service = wrapped_service
+            self._active_service = active_service
 
             async def filter(_: Frame) -> bool:
                 return self._wrapped_service == self._active_service
 
-            super().__init__(filter, direction)
-            self._wrapped_service = wrapped_service
-            self._active_service = active_service
+            super().__init__(filter, direction, filter_system_frames=True)
 
         async def process_frame(self, frame, direction):
             """Process a frame through the filter, handling special internal filter-updating frames."""

src/pipecat/pipeline/task.py

@@ -269,6 +269,9 @@ class PipelineTask(BasePipelineTask):
         # StopFrame) has been received at the end of the pipeline.
         self._pipeline_end_event = asyncio.Event()
 
+        # This event is set when the pipeline truly finishes.
+        self._pipeline_finished_event = asyncio.Event()
+
         # This is the final pipeline. It is composed of a source processor,
         # followed by the user pipeline, and ending with a sink processor. The
         # source allows us to receive and react to upstream frames, and the sink
@@ -401,11 +404,7 @@ class PipelineTask(BasePipelineTask):
         await self.queue_frame(EndFrame())
 
     async def cancel(self):
-        """Immediately stop the running pipeline.
-
-        Cancels all running tasks and stops frame processing without
-        waiting for completion.
-        """
+        """Request the running pipeline to cancel."""
         if not self._finished:
             await self._cancel()
 
@@ -417,51 +416,38 @@ class PipelineTask(BasePipelineTask):
         """
         if self.has_finished():
             return
-        cleanup_pipeline = True
+
+        # Setup processors.
+        await self._setup(params)
+
+        # Create all main tasks and wait for the main push task. This is the
+        # task that pushes frames to the very beginning of our pipeline (i.e. to
+        # our controlled source processor).
+        await self._create_tasks()
+
         try:
-            # Setup processors.
-            await self._setup(params)
-
-            # Create all main tasks and wait of the main push task. This is the
-            # task that pushes frames to the very beginning of our pipeline (our
-            # controlled source processor).
-            push_task = await self._create_tasks()
-            await push_task
-
-            # We have already cleaned up the pipeline inside the task.
-            cleanup_pipeline = False
-
-            # Pipeline has finished nicely.
-            self._finished = True
+            # Wait for pipeline to finish.
+            await self._wait_for_pipeline_finished()
         except asyncio.CancelledError:
-            # Raise exception back to the pipeline runner so it can cancel this
-            # task properly.
+            logger.debug(f"Pipeline task {self} got cancelled from outside...")
+            # We have been cancelled from outside, let's just cancel everything.
+            await self._cancel()
+            # Wait again for pipeline to finish. This time we have really
+            # cancelled, so it should really finish.
+            await self._wait_for_pipeline_finished()
+            # Re-raise in case there's more cleanup to do.
             raise
         finally:
             # We can reach this point for different reasons:
             #
-            # 1. The task has finished properly (e.g. `EndFrame`).
-            # 2. By calling `PipelineTask.cancel()`.
-            # 3. By asyncio task cancellation.
-            #
-            # Case (1) will execute the code below without issues because
-            # `self._finished` is true.
-            #
-            # Case (2) will execute the code below without issues because
-            # `self._cancelled` is true.
-            #
-            # Case (3) will raise the exception above (because we are cancelling
-            # the asyncio task). This will be then captured by the
-            # `PipelineRunner` which will call `PipelineTask.cancel()` and
-            # therefore becoming case (2).
-            if self._finished or self._cancelled:
-                logger.debug(f"Pipeline task {self} is finishing cleanup...")
-                await self._cancel_tasks()
-                await self._cleanup(cleanup_pipeline)
-                if self._check_dangling_tasks:
-                    self._print_dangling_tasks()
-                self._finished = True
-                logger.debug(f"Pipeline task {self} has finished")
+            # 1. The pipeline task has finished (try case).
+            # 2. By an asyncio task cancellation (except case).
+            logger.debug(f"Pipeline task {self} is finishing...")
+            await self._cancel_tasks()
+            if self._check_dangling_tasks:
+                self._print_dangling_tasks()
+            self._finished = True
+            logger.debug(f"Pipeline task {self} has finished")
 
     async def queue_frame(self, frame: Frame):
         """Queue a single frame to be pushed down the pipeline.
@@ -489,19 +475,7 @@ class PipelineTask(BasePipelineTask):
         if not self._cancelled:
             logger.debug(f"Cancelling pipeline task {self}")
             self._cancelled = True
-            cancel_frame = CancelFrame()
-            # Make sure everything is cleaned up downstream. This is sent
-            # out-of-band from the main streaming task which is what we want since
-            # we want to cancel right away.
-            await self._pipeline.queue_frame(cancel_frame)
-            # Wait for CancelFrame to make it through the pipeline.
-            await self._wait_for_pipeline_end(cancel_frame)
-            # Only cancel the push task, we don't want to be able to process any
-            # other frame after cancel. Everything else will be cancelled in
-            # run().
-            if self._process_push_task:
-                await self._task_manager.cancel_task(self._process_push_task)
-                self._process_push_task = None
+            await self.queue_frame(CancelFrame())
 
     async def _create_tasks(self):
         """Create and start all pipeline processing tasks."""
@@ -603,6 +577,17 @@ class PipelineTask(BasePipelineTask):
 
         self._pipeline_end_event.clear()
 
+        # We are really done.
+        self._pipeline_finished_event.set()
+
+    async def _wait_for_pipeline_finished(self):
+        await self._pipeline_finished_event.wait()
+        self._pipeline_finished_event.clear()
+        # Make sure we wait for the main task to complete.
+        if self._process_push_task:
+            await self._process_push_task
+            self._process_push_task = None
+
     async def _setup(self, params: PipelineTaskParams):
         """Set up the pipeline task and all processors."""
         mgr_params = TaskManagerParams(loop=params.loop)

src/pipecat/pipeline/task_observer.py

@@ -189,7 +189,7 @@ class TaskObserver(BaseObserver):
             if isinstance(data, FramePushed):
                 if on_push_frame_deprecated:
                     await observer.on_push_frame(
-                        data.src, data.dst, data.frame, data.direction, data.timestamp
+                        data.source, data.destination, data.frame, data.direction, data.timestamp
                     )
                 else:
                     await observer.on_push_frame(data)

src/pipecat/processors/aggregators/llm_context.py

@@ -17,7 +17,7 @@ service-specific adapter.
 import base64
 import io
 from dataclasses import dataclass
-from typing import Any, List, Optional, TypeAlias, Union
+from typing import TYPE_CHECKING, Any, List, Optional, TypeAlias, Union
 
 from loguru import logger
 from openai._types import NOT_GIVEN as OPEN_AI_NOT_GIVEN
@@ -28,9 +28,12 @@ from openai.types.chat import (
 )
 from PIL import Image
 
-from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
 from pipecat.frames.frames import AudioRawFrame
 
+if TYPE_CHECKING:
+    from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+
 # "Re-export" types from OpenAI that we're using as universal context types.
 # NOTE: if universal message types need to someday diverge from OpenAI's, we
 # should consider managing our own definitions. But we should do so carefully,
@@ -65,6 +68,34 @@ class LLMContext:
     and content formatting.
     """
 
+    @staticmethod
+    def from_openai_context(openai_context: "OpenAILLMContext") -> "LLMContext":
+        """Create a universal LLM context from an OpenAI-specific context.
+
+        NOTE: this should only be used internally, for facilitating migration
+        from OpenAILLMContext to LLMContext. New user code should use
+        LLMContext directly.
+
+        Args:
+            openai_context: The OpenAI LLM context to convert.
+
+        Returns:
+            New LLMContext instance with converted messages and settings.
+        """
+        # Convert tools to ToolsSchema if needed.
+        # If the tools are already a ToolsSchema, this is a no-op.
+        # Otherwise, we wrap them in a shim ToolsSchema.
+        converted_tools = openai_context.tools
+        if isinstance(converted_tools, list):
+            converted_tools = ToolsSchema(
+                standard_tools=[], custom_tools={AdapterType.SHIM: converted_tools}
+            )
+        return LLMContext(
+            messages=openai_context.get_messages(),
+            tools=converted_tools,
+            tool_choice=openai_context.tool_choice,
+        )
+
     def __init__(
         self,
         messages: Optional[List[LLMContextMessage]] = None,
@@ -82,6 +113,46 @@ class LLMContext:
         self._tools: ToolsSchema | NotGiven = LLMContext._normalize_and_validate_tools(tools)
         self._tool_choice: LLMContextToolChoice | NotGiven = tool_choice
 
+    @property
+    def messages(self) -> List[LLMContextMessage]:
+        """Get the current messages list.
+
+        NOTE: This is equivalent to calling `get_messages()` with no filter. If
+        you want to filter out LLM-specific messages that don't pertain to your
+        LLM, use `get_messages()` directly.
+
+        Returns:
+            List of conversation messages.
+        """
+        return self.get_messages()
+
+    def get_messages_for_persistent_storage(self) -> List[LLMContextMessage]:
+        """Get messages suitable for persistent storage.
+
+        NOTE: the only reason this method exists is because we're "silently"
+        switching from OpenAILLMContext to LLMContext under the hood in some
+        services and don't want to trip up users who may have been relying on
+        this method, which is part of the public API of OpenAILLMContext but
+        doesn't need to be for LLMContext.
+
+        .. deprecated::
+            Use `get_messages()` instead.
+
+        Returns:
+            List of conversation messages.
+        """
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "get_messages_for_persistent_storage() is deprecated, use get_messages() instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+        return self.get_messages()
+
     def get_messages(self, llm_specific_filter: Optional[str] = None) -> List[LLMContextMessage]:
         """Get the current messages list.
 
@@ -89,7 +160,8 @@ class LLMContext:
             llm_specific_filter: Optional filter to return LLM-specific
                 messages for the given LLM, in addition to the standard
                 messages. If messages end up being filtered, an error will be
-                logged.
+                logged; this is intended to catch accidental use of
+                incompatible LLM-specific messages.
 
         Returns:
             List of conversation messages.

src/pipecat/processors/aggregators/llm_response_universal.py

@@ -290,6 +290,12 @@ class LLMUserAggregator(LLMContextAggregator):
             await self._handle_llm_messages_update(frame)
         elif isinstance(frame, LLMSetToolsFrame):
             self.set_tools(frame.tools)
+            # Push the LLMSetToolsFrame as well, since speech-to-speech LLM
+            # services (like OpenAI Realtime) may need to know about tool
+            # changes; unlike text-based LLM services they won't just "pick up
+            # the change" on the next LLM run, as the LLM is continuously
+            # running.
+            await self.push_frame(frame, direction)
         elif isinstance(frame, LLMSetToolChoiceFrame):
             self.set_tool_choice(frame.tool_choice)
         elif isinstance(frame, SpeechControlParamsFrame):

src/pipecat/processors/filters/function_filter.py

@@ -12,7 +12,7 @@ allowing for flexible frame filtering logic in processing pipelines.
 
 from typing import Awaitable, Callable
 
-from pipecat.frames.frames import EndFrame, Frame, SystemFrame
+from pipecat.frames.frames import CancelFrame, EndFrame, Frame, StartFrame, SystemFrame
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 
 
@@ -28,6 +28,7 @@ class FunctionFilter(FrameProcessor):
         self,
         filter: Callable[[Frame], Awaitable[bool]],
         direction: FrameDirection = FrameDirection.DOWNSTREAM,
+        filter_system_frames: bool = False,
     ):
         """Initialize the function filter.
 
@@ -36,22 +37,32 @@ class FunctionFilter(FrameProcessor):
                 frame should pass through, False otherwise.
             direction: The direction to apply filtering. Only frames moving in
                 this direction will be filtered. Defaults to DOWNSTREAM.
+            filter_system_frames: Whether to filter system frames. Defaults to False.
         """
         super().__init__()
         self._filter = filter
         self._direction = direction
+        self._filter_system_frames = filter_system_frames
 
     #
     # Frame processor
     #
 
-    # Ignore system frames, end frames and frames that are not following the
-    # direction of this gate
     def _should_passthrough_frame(self, frame, direction):
         """Check if a frame should pass through without filtering."""
-        # Ignore system frames, end frames and frames that are not following the
-        # direction of this gate
-        return isinstance(frame, (SystemFrame, EndFrame)) or direction != self._direction
+        # Always passthrough frames in the wrong direction
+        if direction != self._direction:
+            return True
+
+        # Always passthrough lifecycle frames
+        if isinstance(frame, (StartFrame, EndFrame, CancelFrame)):
+            return True
+
+        # If not filtering system frames, passthrough all other system frames
+        if not self._filter_system_frames and isinstance(frame, SystemFrame):
+            return True
+
+        return False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         """Process a frame through the filter.

src/pipecat/processors/frameworks/rtvi.py

@@ -1018,6 +1018,7 @@ class RTVIObserver(BaseObserver):
 
         if (
             isinstance(frame, (UserStartedSpeakingFrame, UserStoppedSpeakingFrame))
+            and (direction == FrameDirection.DOWNSTREAM)
             and self._params.user_speaking_enabled
         ):
             await self._handle_interruptions(frame)

src/pipecat/runner/daily.py

@@ -76,12 +76,14 @@ class DailyRoomConfig(BaseModel):
 async def configure(
     aiohttp_session: aiohttp.ClientSession,
     *,
+    api_key: Optional[str] = None,
     room_exp_duration: Optional[float] = 2.0,
     token_exp_duration: Optional[float] = 2.0,
     sip_caller_phone: Optional[str] = None,
     sip_enable_video: Optional[bool] = False,
     sip_num_endpoints: Optional[int] = 1,
     sip_codecs: Optional[Dict[str, List[str]]] = None,
+    room_properties: Optional[DailyRoomProperties] = None,
 ) -> DailyRoomConfig:
     """Configure Daily room URL and token with optional SIP capabilities.
 
@@ -91,6 +93,7 @@ async def configure(
 
     Args:
         aiohttp_session: HTTP session for making API requests.
+        api_key: Daily API key.
         room_exp_duration: Room expiration time in hours.
         token_exp_duration: Token expiration time in hours.
         sip_caller_phone: Phone number or identifier for SIP display name.
@@ -99,6 +102,10 @@ async def configure(
         sip_num_endpoints: Number of allowed SIP endpoints.
         sip_codecs: Codecs to support for audio and video. If None, uses Daily defaults.
             Example: {"audio": ["OPUS"], "video": ["H264"]}
+        room_properties: Optional DailyRoomProperties to use instead of building from
+            individual parameters. When provided, this overrides room_exp_duration and
+            SIP-related parameters. If not provided, properties are built from the
+            individual parameters as before.
 
     Returns:
         DailyRoomConfig: Object with room_url, token, and optional sip_endpoint.
@@ -115,18 +122,48 @@ async def configure(
         # SIP-enabled room
         sip_config = await configure(session, sip_caller_phone="+15551234567")
         print(f"SIP endpoint: {sip_config.sip_endpoint}")
+
+        # Custom room properties with recording enabled
+        custom_props = DailyRoomProperties(
+            enable_recording="cloud",
+            max_participants=2,
+        )
+        config = await configure(session, room_properties=custom_props)
     """
     # Check for required API key
-    api_key = os.getenv("DAILY_API_KEY")
+    api_key = api_key or os.getenv("DAILY_API_KEY")
     if not api_key:
         raise Exception(
             "DAILY_API_KEY environment variable is required. "
             "Get your API key from https://dashboard.daily.co/developers"
         )
 
+    # Warn if both room_properties and individual parameters are provided
+    if room_properties is not None:
+        individual_params_provided = any(
+            [
+                room_exp_duration != 2.0,
+                token_exp_duration != 2.0,
+                sip_caller_phone is not None,
+                sip_enable_video is not False,
+                sip_num_endpoints != 1,
+                sip_codecs is not None,
+            ]
+        )
+        if individual_params_provided:
+            logger.warning(
+                "Both room_properties and individual parameters (room_exp_duration, token_exp_duration, "
+                "sip_*) were provided. The room_properties will be used and individual parameters "
+                "will be ignored."
+            )
+
     # Determine if SIP mode is enabled
     sip_enabled = sip_caller_phone is not None
 
+    # If room_properties is provided, check if it has SIP configuration
+    if room_properties and room_properties.sip:
+        sip_enabled = True
+
     daily_rest_helper = DailyRESTHelper(
         daily_api_key=api_key,
         daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
@@ -150,27 +187,29 @@ async def configure(
     room_name = f"{room_prefix}-{uuid.uuid4().hex[:8]}"
     logger.info(f"Creating new Daily room: {room_name}")
 
-    # Calculate expiration time
-    expiration_time = time.time() + (room_exp_duration * 60 * 60)
+    # Use provided room_properties or build from parameters
+    if room_properties is None:
+        # Calculate expiration time
+        expiration_time = time.time() + (room_exp_duration * 60 * 60)
 
-    # Create room properties
-    room_properties = DailyRoomProperties(
-        exp=expiration_time,
-        eject_at_room_exp=True,
-    )
-
-    # Add SIP configuration if enabled
-    if sip_enabled:
-        sip_params = DailyRoomSipParams(
-            display_name=sip_caller_phone,
-            video=sip_enable_video,
-            sip_mode="dial-in",
-            num_endpoints=sip_num_endpoints,
-            codecs=sip_codecs,
+        # Create room properties
+        room_properties = DailyRoomProperties(
+            exp=expiration_time,
+            eject_at_room_exp=True,
         )
-        room_properties.sip = sip_params
-        room_properties.enable_dialout = True  # Enable outbound calls if needed
-        room_properties.start_video_off = not sip_enable_video  # Voice-only by default
+
+        # Add SIP configuration if enabled
+        if sip_enabled:
+            sip_params = DailyRoomSipParams(
+                display_name=sip_caller_phone,
+                video=sip_enable_video,
+                sip_mode="dial-in",
+                num_endpoints=sip_num_endpoints,
+                codecs=sip_codecs,
+            )
+            room_properties.sip = sip_params
+            room_properties.enable_dialout = True  # Enable outbound calls if needed
+            room_properties.start_video_off = not sip_enable_video  # Voice-only by default
 
     # Create room parameters
     room_params = DailyRoomParams(name=room_name, properties=room_properties)

src/pipecat/runner/run.py

@@ -70,16 +70,19 @@ import asyncio
 import mimetypes
 import os
 import sys
+import uuid
 from contextlib import asynccontextmanager
+from http import HTTPMethod
 from pathlib import Path
-from typing import Optional
+from typing import Any, Dict, List, Optional, TypedDict
 
 import aiohttp
-from fastapi.responses import FileResponse
+from fastapi.responses import FileResponse, Response
 from loguru import logger
 
 from pipecat.runner.types import (
     DailyRunnerArguments,
+    RunnerArguments,
     SmallWebRTCRunnerArguments,
     WebSocketRunnerArguments,
 )
@@ -166,6 +169,7 @@ def _create_server_app(
     host: str = "localhost",
     proxy: str,
     esp32_mode: bool = False,
+    whatsapp_enabled: bool = False,
     folder: Optional[str] = None,
 ):
     """Create FastAPI app with transport-specific routes."""
@@ -182,7 +186,8 @@ def _create_server_app(
     # Set up transport-specific routes
     if transport_type == "webrtc":
         _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host, folder=folder)
-        _setup_whatsapp_routes(app)
+        if whatsapp_enabled:
+            _setup_whatsapp_routes(app)
     elif transport_type == "daily":
         _setup_daily_routes(app)
     elif transport_type in TELEPHONY_TRANSPORTS:
@@ -200,8 +205,10 @@ def _setup_webrtc_routes(
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
-        from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
+        from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
         from pipecat.transports.smallwebrtc.request_handler import (
+            IceCandidate,
+            SmallWebRTCPatchRequest,
             SmallWebRTCRequest,
             SmallWebRTCRequestHandler,
         )
@@ -209,6 +216,16 @@ def _setup_webrtc_routes(
         logger.error(f"WebRTC transport dependencies not installed: {e}")
         return
 
+    class IceConfig(TypedDict):
+        iceServers: List[IceServer]
+
+    class StartBotResult(TypedDict, total=False):
+        sessionId: str
+        iceConfig: Optional[IceConfig]
+
+    # In-memory store of active sessions: session_id -> session info
+    active_sessions: Dict[str, Dict[str, Any]] = {}
+
     # Mount the frontend
     app.mount("/client", SmallWebRTCPrebuiltUI)
 
@@ -254,6 +271,74 @@ def _setup_webrtc_routes(
         )
         return answer
 
+    @app.patch("/api/offer")
+    async def ice_candidate(request: SmallWebRTCPatchRequest):
+        """Handle WebRTC new ice candidate requests."""
+        logger.debug(f"Received patch request: {request}")
+        await small_webrtc_handler.handle_patch_request(request)
+        return {"status": "success"}
+
+    @app.post("/start")
+    async def rtvi_start(request: Request):
+        """Mimic Pipecat Cloud's /start endpoint."""
+        # Parse the request body
+        try:
+            request_data = await request.json()
+            logger.debug(f"Received request: {request_data}")
+        except Exception as e:
+            logger.error(f"Failed to parse request body: {e}")
+            request_data = {}
+
+        # Store session info immediately in memory, replicate the behavior expected on Pipecat Cloud
+        session_id = str(uuid.uuid4())
+        active_sessions[session_id] = request_data
+
+        result: StartBotResult = {"sessionId": session_id}
+        if request_data.get("enableDefaultIceServers"):
+            result["iceConfig"] = IceConfig(
+                iceServers=[IceServer(urls="stun:stun.l.google.com:19302")]
+            )
+
+        return result
+
+    @app.api_route(
+        "/sessions/{session_id}/{path:path}",
+        methods=["GET", "POST", "PUT", "PATCH", "DELETE"],
+    )
+    async def proxy_request(
+        session_id: str, path: str, request: Request, background_tasks: BackgroundTasks
+    ):
+        """Mimic Pipecat Cloud's proxy."""
+        active_session = active_sessions.get(session_id)
+        if active_session is None:
+            return Response(content="Invalid or not-yet-ready session_id", status_code=404)
+
+        if path.endswith("api/offer"):
+            # Parse the request body and convert to SmallWebRTCRequest
+            try:
+                request_data = await request.json()
+                if request.method == HTTPMethod.POST.value:
+                    webrtc_request = SmallWebRTCRequest(
+                        sdp=request_data["sdp"],
+                        type=request_data["type"],
+                        pc_id=request_data.get("pc_id"),
+                        restart_pc=request_data.get("restart_pc"),
+                        request_data=request_data,
+                    )
+                    return await offer(webrtc_request, background_tasks)
+                elif request.method == HTTPMethod.PATCH.value:
+                    patch_request = SmallWebRTCPatchRequest(
+                        pc_id=request_data["pc_id"],
+                        candidates=[IceCandidate(**c) for c in request_data.get("candidates", [])],
+                    )
+                    return await ice_candidate(patch_request)
+            except Exception as e:
+                logger.error(f"Failed to parse WebRTC request: {e}")
+                return Response(content="Invalid WebRTC request", status_code=400)
+
+        logger.info(f"Received request for path: {path}")
+        return Response(status_code=200)
+
     @asynccontextmanager
     async def smallwebrtc_lifespan(app: FastAPI):
         """Manage FastAPI application lifecycle and cleanup connections."""
@@ -289,6 +374,29 @@ def _add_lifespan_to_app(app: FastAPI, new_lifespan):
 
 def _setup_whatsapp_routes(app: FastAPI):
     """Set up WebRTC-specific routes."""
+    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
+    WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
+    WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
+
+    if not all(
+        [
+            WHATSAPP_APP_SECRET,
+            WHATSAPP_PHONE_NUMBER_ID,
+            WHATSAPP_TOKEN,
+            WHATSAPP_WEBHOOK_VERIFICATION_TOKEN,
+        ]
+    ):
+        logger.error(
+            """Missing required environment variables for WhatsApp transport:
+    WHATSAPP_APP_SECRET
+    WHATSAPP_PHONE_NUMBER_ID
+    WHATSAPP_TOKEN
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN
+            """
+        )
+        return
+
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
@@ -300,24 +408,7 @@ def _setup_whatsapp_routes(app: FastAPI):
         from pipecat.transports.whatsapp.api import WhatsAppWebhookRequest
         from pipecat.transports.whatsapp.client import WhatsAppClient
     except ImportError as e:
-        logger.error(f"WebRTC transport dependencies not installed: {e}")
-        return
-
-    WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
-    WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
-    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
-    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
-
-    if not all(
-        [
-            WHATSAPP_TOKEN,
-            WHATSAPP_PHONE_NUMBER_ID,
-            WHATSAPP_WEBHOOK_VERIFICATION_TOKEN,
-        ]
-    ):
-        logger.debug(
-            "Missing required environment variables for WhatsApp transport. Keeping it disabled."
-        )
+        logger.error(f"WhatsApp transport dependencies not installed: {e}")
         return
 
     # Global WhatsApp client instance
@@ -439,9 +530,9 @@ def _setup_daily_routes(app: FastAPI):
     """Set up Daily-specific routes."""
 
     @app.get("/")
-    async def start_agent():
+    async def create_room_and_start_agent():
         """Launch a Daily bot and redirect to room."""
-        print("Starting bot with Daily transport")
+        print("Starting bot with Daily transport and redirecting to Daily room")
 
         import aiohttp
 
@@ -456,11 +547,11 @@ def _setup_daily_routes(app: FastAPI):
             asyncio.create_task(bot_module.bot(runner_args))
             return RedirectResponse(room_url)
 
-    async def _handle_rtvi_request(request: Request):
-        """Common handler for both /start and /connect endpoints.
+    @app.post("/start")
+    async def start_agent(request: Request):
+        """Handler for /start endpoints.
 
         Expects POST body like::
-
             {
                 "createDailyRoom": true,
                 "dailyRoomProperties": { "start_video_off": true },
@@ -477,47 +568,38 @@ def _setup_daily_routes(app: FastAPI):
             logger.error(f"Failed to parse request body: {e}")
             request_data = {}
 
-        # Extract the body data that should be passed to the bot
-        # This mimics Pipecat Cloud's behavior
-        bot_body = request_data.get("body", {})
+        create_daily_room = request_data.get("createDailyRoom", False)
+        body = request_data.get("body", {})
 
-        # Log the extracted body data for debugging
-        if bot_body:
-            logger.info(f"Extracted body data for bot: {bot_body}")
+        bot_module = _get_bot_module()
+
+        existing_room_url = os.getenv("DAILY_SAMPLE_ROOM_URL")
+
+        result = None
+
+        # Configure room if:
+        # 1. Explicitly requested via createDailyRoom in payload
+        # 2. Using pre-configured room from DAILY_SAMPLE_ROOM_URL env var
+        if create_daily_room or existing_room_url:
+            import aiohttp
+
+            from pipecat.runner.daily import configure
+
+            async with aiohttp.ClientSession() as session:
+                room_url, token = await configure(session)
+                runner_args = DailyRunnerArguments(room_url=room_url, token=token, body=body)
+                result = {
+                    "dailyRoom": room_url,
+                    "dailyToken": token,
+                    "sessionId": str(uuid.uuid4()),
+                }
         else:
-            logger.debug("No body data provided in request")
+            runner_args = RunnerArguments(body=body)
 
-        import aiohttp
+        # Start the bot in the background
+        asyncio.create_task(bot_module.bot(runner_args))
 
-        from pipecat.runner.daily import configure
-
-        async with aiohttp.ClientSession() as session:
-            room_url, token = await configure(session)
-
-            # Start the bot in the background with extracted body data
-            bot_module = _get_bot_module()
-            runner_args = DailyRunnerArguments(room_url=room_url, token=token, body=bot_body)
-            asyncio.create_task(bot_module.bot(runner_args))
-            # Match PCC /start endpoint response format:
-            return {"dailyRoom": room_url, "dailyToken": token}
-
-    @app.post("/start")
-    async def rtvi_start(request: Request):
-        """Launch a Daily bot and return connection info for RTVI clients."""
-        return await _handle_rtvi_request(request)
-
-    @app.post("/connect")
-    async def rtvi_connect(request: Request):
-        """Launch a Daily bot and return connection info for RTVI clients.
-
-        .. deprecated:: 0.0.78
-            Use /start instead. This endpoint will be removed in a future version.
-        """
-        logger.warning(
-            "DEPRECATED: /connect endpoint is deprecated. Please use /start instead. "
-            "This endpoint will be removed in a future version."
-        )
-        return await _handle_rtvi_request(request)
+        return result
 
 
 def _setup_telephony_routes(app: FastAPI, *, transport_type: str, proxy: str):
@@ -576,8 +658,6 @@ def _setup_telephony_routes(app: FastAPI, *, transport_type: str, proxy: str):
 async def _run_daily_direct():
     """Run Daily bot with direct connection (no FastAPI server)."""
     try:
-        import aiohttp
-
         from pipecat.runner.daily import configure
     except ImportError as e:
         logger.error("Daily transport dependencies not installed.")
@@ -689,6 +769,12 @@ def main():
     parser.add_argument(
         "--verbose", "-v", action="count", default=0, help="Increase logging verbosity"
     )
+    parser.add_argument(
+        "--whatsapp",
+        action="store_true",
+        default=False,
+        help="Ensure requried WhatsApp environment variables are present",
+    )
 
     args = parser.parse_args()
 
@@ -708,10 +794,6 @@ def main():
         logger.error("For ESP32, you need to specify `--host IP` so we can do SDP munging.")
         return
 
-    if args.transport in TELEPHONY_TRANSPORTS and not args.proxy:
-        logger.error(f"For telephony transports, you need to specify `--proxy PROXY`.")
-        return
-
     # Log level
     logger.remove()
     logger.add(sys.stderr, level="TRACE" if args.verbose else "DEBUG")
@@ -731,10 +813,11 @@ def main():
         print()
         if args.esp32:
             print(f"🚀 Bot ready! (ESP32 mode)")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        elif args.whatsapp:
+            print(f"🚀 Bot ready! (WhatsApp)")
         else:
             print(f"🚀 Bot ready!")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        print(f"   → Open http://{args.host}:{args.port}/client in your browser")
         print()
     elif args.transport == "daily":
         print()
@@ -752,6 +835,7 @@ def main():
         host=args.host,
         proxy=args.proxy,
         esp32_mode=args.esp32,
+        whatsapp_enabled=args.whatsapp,
         folder=args.folder,
     )
 

src/pipecat/runner/types.py

@@ -20,9 +20,11 @@ from fastapi import WebSocket
 class RunnerArguments:
     """Base class for runner session arguments."""
 
-    handle_sigint: bool = field(init=False)
-    handle_sigterm: bool = field(init=False)
-    pipeline_idle_timeout_secs: int = field(init=False)
+    # Use kw_only so subclasses don't need to worry about ordering.
+    handle_sigint: bool = field(init=False, kw_only=True)
+    handle_sigterm: bool = field(init=False, kw_only=True)
+    pipeline_idle_timeout_secs: int = field(init=False, kw_only=True)
+    body: Optional[Any] = field(default_factory=dict, kw_only=True)
 
     def __post_init__(self):
         self.handle_sigint = False
@@ -42,7 +44,6 @@ class DailyRunnerArguments(RunnerArguments):
 
     room_url: str
     token: Optional[str] = None
-    body: Optional[Any] = field(default_factory=dict)
 
 
 @dataclass
@@ -55,7 +56,6 @@ class WebSocketRunnerArguments(RunnerArguments):
     """
 
     websocket: WebSocket
-    body: Optional[Any] = field(default_factory=dict)
 
 
 @dataclass

src/pipecat/services/assemblyai/models.py

@@ -108,6 +108,8 @@ class AssemblyAIConnectionParams(BaseModel):
         end_of_turn_confidence_threshold: Confidence threshold for end-of-turn detection.
         min_end_of_turn_silence_when_confident: Minimum silence duration when confident about end-of-turn.
         max_turn_silence: Maximum silence duration before forcing end-of-turn.
+        keyterms_prompt: List of key terms to guide transcription. Will be JSON serialized before sending.
+        speech_model: Select between English and multilingual models. Defaults to "universal-streaming-english".
     """
 
     sample_rate: int = 16000
@@ -117,3 +119,7 @@ class AssemblyAIConnectionParams(BaseModel):
     end_of_turn_confidence_threshold: Optional[float] = None
     min_end_of_turn_silence_when_confident: Optional[int] = None
     max_turn_silence: Optional[int] = None
+    keyterms_prompt: Optional[List[str]] = None
+    speech_model: Literal["universal-streaming-english", "universal-streaming-multilingual"] = (
+        "universal-streaming-english"
+    )

src/pipecat/services/assemblyai/stt.py

@@ -174,11 +174,16 @@ class AssemblyAISTTService(STTService):
 
     def _build_ws_url(self) -> str:
         """Build WebSocket URL with query parameters using urllib.parse.urlencode."""
-        params = {
-            k: str(v).lower() if isinstance(v, bool) else v
-            for k, v in self._connection_params.model_dump().items()
-            if v is not None
-        }
+        params = {}
+        for k, v in self._connection_params.model_dump().items():
+            if v is not None:
+                if k == "keyterms_prompt":
+                    params[k] = json.dumps(v)
+                elif isinstance(v, bool):
+                    params[k] = str(v).lower()
+                else:
+                    params[k] = v
+
         if params:
             query_string = urlencode(params)
             return f"{self._api_endpoint_base_url}?{query_string}"
@@ -197,6 +202,8 @@ class AssemblyAISTTService(STTService):
             )
             self._connected = True
             self._receive_task = self.create_task(self._receive_task_handler())
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"Failed to connect to AssemblyAI: {e}")
             self._connected = False
@@ -238,6 +245,7 @@ class AssemblyAISTTService(STTService):
             self._websocket = None
             self._connected = False
             self._receive_task = None
+            await self._call_event_handler("on_disconnected")
 
     async def _receive_task_handler(self):
         """Handle incoming WebSocket messages."""

src/pipecat/services/asyncai/tts.py

@@ -235,6 +235,8 @@ class AsyncAITTSService(InterruptibleTTSService):
             }
 
             await self._get_websocket().send(json.dumps(init_msg))
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -252,6 +254,7 @@ class AsyncAITTSService(InterruptibleTTSService):
         finally:
             self._websocket = None
             self._started = False
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

src/pipecat/services/aws/llm.py

@@ -720,11 +720,11 @@ class AWSBedrockLLMService(LLMService):
             additional_model_request_fields: Additional model-specific parameters.
         """
 
-        max_tokens: Optional[int] = Field(default_factory=lambda: 4096, ge=1)
-        temperature: Optional[float] = Field(default_factory=lambda: 0.7, ge=0.0, le=1.0)
-        top_p: Optional[float] = Field(default_factory=lambda: 0.999, ge=0.0, le=1.0)
+        max_tokens: Optional[int] = Field(default=None, ge=1)
+        temperature: Optional[float] = Field(default=None, ge=0.0, le=1.0)
+        top_p: Optional[float] = Field(default=None, ge=0.0, le=1.0)
         stop_sequences: Optional[List[str]] = Field(default_factory=lambda: [])
-        latency: Optional[str] = Field(default_factory=lambda: "standard")
+        latency: Optional[str] = Field(default=None)
         additional_model_request_fields: Optional[Dict[str, Any]] = Field(default_factory=dict)
 
     def __init__(
@@ -801,6 +801,24 @@ class AWSBedrockLLMService(LLMService):
         """
         return True
 
+    def _build_inference_config(self) -> Dict[str, Any]:
+        """Build inference config with only the parameters that are set.
+
+        This prevents conflicts with models (e.g., Claude Sonnet 4.5) that don't
+        allow certain parameter combinations like temperature and top_p together.
+
+        Returns:
+            Dictionary containing only the inference parameters that are not None.
+        """
+        inference_config = {}
+        if self._settings["max_tokens"] is not None:
+            inference_config["maxTokens"] = self._settings["max_tokens"]
+        if self._settings["temperature"] is not None:
+            inference_config["temperature"] = self._settings["temperature"]
+        if self._settings["top_p"] is not None:
+            inference_config["topP"] = self._settings["top_p"]
+        return inference_config
+
     async def run_inference(self, context: LLMContext | OpenAILLMContext) -> Optional[str]:
         """Run a one-shot, out-of-band (i.e. out-of-pipeline) inference with the given LLM context.
 
@@ -826,16 +844,16 @@ class AWSBedrockLLMService(LLMService):
         model_id = self.model_name
 
         # Prepare request parameters
+        inference_config = self._build_inference_config()
+
         request_params = {
             "modelId": model_id,
             "messages": messages,
-            "inferenceConfig": {
-                "maxTokens": 8192,
-                "temperature": 0.7,
-                "topP": 0.9,
-            },
         }
 
+        if inference_config:
+            request_params["inferenceConfig"] = inference_config
+
         if system:
             request_params["system"] = system
 
@@ -974,21 +992,20 @@ class AWSBedrockLLMService(LLMService):
             tools = params_from_context["tools"]
             tool_choice = params_from_context["tool_choice"]
 
-            # Set up inference config
-            inference_config = {
-                "maxTokens": self._settings["max_tokens"],
-                "temperature": self._settings["temperature"],
-                "topP": self._settings["top_p"],
-            }
+            # Set up inference config - only include parameters that are set
+            inference_config = self._build_inference_config()
 
             # Prepare request parameters
             request_params = {
                 "modelId": self.model_name,
                 "messages": messages,
-                "inferenceConfig": inference_config,
                 "additionalModelRequestFields": self._settings["additional_model_request_fields"],
             }
 
+            # Only add inference config if it has parameters
+            if inference_config:
+                request_params["inferenceConfig"] = inference_config
+
             # Add system message
             if system:
                 request_params["system"] = system

src/pipecat/services/aws/nova_sonic/context.py

@@ -8,8 +8,77 @@
 
 This module provides specialized context aggregators and message handling for AWS Nova Sonic,
 including conversation history management and role-specific message processing.
+
+.. deprecated:: 0.0.91
+    AWS Nova Sonic no longer uses types from this module under the hood.
+    It now uses `LLMContext` and `LLMContextAggregatorPair`.
+    Using the new patterns should allow you to not need types from this module.
+
+    BEFORE:
+    ```
+    # Setup
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # Context frame type
+    frame: OpenAILLMContextFrame
+
+    # Context type
+    context: AWSNovaSonicLLMContext
+    # or
+    context: OpenAILLMContext
+    ```
+
+    AFTER:
+    ```
+    # Setup
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    # Context frame type
+    frame: LLMContextFrame
+
+    # Context type
+    context: LLMContext
+    ```
 """
 
+import warnings
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws.nova_sonic.context (or "
+        "pipecat.services.aws_nova_sonic.context) are deprecated. \n"
+        "AWS Nova Sonic no longer uses types from this module under the hood. \n"
+        "It now uses `LLMContext` and `LLMContextAggregatorPair`. \n"
+        "Using the new patterns should allow you to not need types from this module.\n\n"
+        "BEFORE:\n"
+        "```\n"
+        "# Setup\n"
+        "context = OpenAILLMContext(messages, tools)\n"
+        "context_aggregator = llm.create_context_aggregator(context)\n\n"
+        "# Context frame type\n"
+        "frame: OpenAILLMContextFrame\n\n"
+        "# Context type\n"
+        "context: AWSNovaSonicLLMContext\n"
+        "# or\n"
+        "context: OpenAILLMContext\n\n"
+        "```\n\n"
+        "AFTER:\n"
+        "```\n"
+        "# Setup\n"
+        "context = LLMContext(messages, tools)\n"
+        "context_aggregator = LLMContextAggregatorPair(context)\n\n"
+        "# Context frame type\n"
+        "frame: LLMContextFrame\n\n"
+        "# Context type\n"
+        "context: LLMContext\n\n"
+        "```",
+        DeprecationWarning,
+        stacklevel=2,
+    )
+
 import copy
 from dataclasses import dataclass, field
 from enum import Enum

src/pipecat/services/aws/nova_sonic/llm.py

@@ -25,7 +25,7 @@ from loguru import logger
 from pydantic import BaseModel, Field
 
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
-from pipecat.adapters.services.aws_nova_sonic_adapter import AWSNovaSonicLLMAdapter
+from pipecat.adapters.services.aws_nova_sonic_adapter import AWSNovaSonicLLMAdapter, Role
 from pipecat.frames.frames import (
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -33,35 +33,30 @@ from pipecat.frames.frames import (
     Frame,
     FunctionCallFromLLM,
     InputAudioRawFrame,
-    InterimTranscriptionFrame,
+    InterruptionFrame,
     LLMContextFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
-    LLMTextFrame,
     StartFrame,
     TranscriptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
     TTSTextFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
 )
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response import (
     LLMAssistantAggregatorParams,
     LLMUserAggregatorParams,
 )
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
     OpenAILLMContextFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.aws.nova_sonic.context import (
-    AWSNovaSonicAssistantContextAggregator,
-    AWSNovaSonicContextAggregatorPair,
-    AWSNovaSonicLLMContext,
-    AWSNovaSonicUserContextAggregator,
-    Role,
-)
-from pipecat.services.aws.nova_sonic.frames import AWSNovaSonicFunctionCallResultFrame
 from pipecat.services.llm_service import LLMService
 from pipecat.utils.time import time_now_iso8601
 
@@ -217,6 +212,11 @@ class AWSNovaSonicLLMService(LLMService):
             system_instruction: System-level instruction for the model.
             tools: Available tools/functions for the model to use.
             send_transcription_frames: Whether to emit transcription frames.
+
+                .. deprecated:: 0.0.91
+                    This parameter is deprecated and will be removed in a future version.
+                    Transcription frames are always sent.
+
             **kwargs: Additional arguments passed to the parent LLMService.
         """
         super().__init__(**kwargs)
@@ -230,8 +230,20 @@ class AWSNovaSonicLLMService(LLMService):
         self._params = params or Params()
         self._system_instruction = system_instruction
         self._tools = tools
-        self._send_transcription_frames = send_transcription_frames
-        self._context: Optional[AWSNovaSonicLLMContext] = None
+
+        if not send_transcription_frames:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "`send_transcription_frames` is deprecated and will be removed in a future version. "
+                    "Transcription frames are always sent.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+
+        self._context: Optional[LLMContext] = None
         self._stream: Optional[
             DuplexEventStream[
                 InvokeModelWithBidirectionalStreamInput,
@@ -244,12 +256,17 @@ class AWSNovaSonicLLMService(LLMService):
         self._input_audio_content_name: Optional[str] = None
         self._content_being_received: Optional[CurrentContent] = None
         self._assistant_is_responding = False
+        self._may_need_repush_assistant_text = False
         self._ready_to_send_context = False
         self._handling_bot_stopped_speaking = False
         self._triggering_assistant_response = False
+        self._waiting_for_trigger_transcription = False
         self._disconnecting = False
         self._connected_time: Optional[float] = None
         self._wants_connection = False
+        self._user_text_buffer = ""
+        self._assistant_text_buffer = ""
+        self._completed_tool_calls = set()
 
         file_path = files("pipecat.services.aws.nova_sonic").joinpath("ready.wav")
         with wave.open(file_path.open("rb"), "rb") as wav_file:
@@ -302,12 +319,12 @@ class AWSNovaSonicLLMService(LLMService):
         logger.debug("Resetting conversation")
         await self._handle_bot_stopped_speaking(delay_to_catch_trailing_assistant_text=False)
 
-        # Carry over previous context through disconnect
+        # Grab context to carry through disconnect/reconnect
         context = self._context
-        await self._disconnect()
-        self._context = context
 
+        await self._disconnect()
         await self._start_connecting()
+        await self._handle_context(context)
 
     #
     # frame processing
@@ -322,28 +339,35 @@ class AWSNovaSonicLLMService(LLMService):
         """
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, OpenAILLMContextFrame):
-            await self._handle_context(frame.context)
-        elif isinstance(frame, LLMContextFrame):
-            raise NotImplementedError(
-                "Universal LLMContext is not yet supported for AWS Nova Sonic."
+        if isinstance(frame, (LLMContextFrame, OpenAILLMContextFrame)):
+            context = (
+                frame.context
+                if isinstance(frame, LLMContextFrame)
+                else LLMContext.from_openai_context(frame.context)
             )
+            await self._handle_context(context)
         elif isinstance(frame, InputAudioRawFrame):
             await self._handle_input_audio_frame(frame)
         elif isinstance(frame, BotStoppedSpeakingFrame):
             await self._handle_bot_stopped_speaking(delay_to_catch_trailing_assistant_text=True)
-        elif isinstance(frame, AWSNovaSonicFunctionCallResultFrame):
-            await self._handle_function_call_result(frame)
+        elif isinstance(frame, InterruptionFrame):
+            await self._handle_interruption_frame()
 
         await self.push_frame(frame, direction)
 
-    async def _handle_context(self, context: OpenAILLMContext):
+    async def _handle_context(self, context: LLMContext):
+        if self._disconnecting:
+            return
+
         if not self._context:
-            # We got our initial context - try to finish connecting
-            self._context = AWSNovaSonicLLMContext.upgrade_to_nova_sonic(
-                context, self._system_instruction
-            )
+            # We got our initial context
+            # Try to finish connecting
+            self._context = context
             await self._finish_connecting_if_context_available()
+        else:
+            # We got an updated context
+            # Send results for any newly-completed function calls
+            await self._process_completed_function_calls(send_new_results=True)
 
     async def _handle_input_audio_frame(self, frame: InputAudioRawFrame):
         # Wait until we're done sending the assistant response trigger audio before sending audio
@@ -393,9 +417,9 @@ class AWSNovaSonicLLMService(LLMService):
         else:
             await finalize_assistant_response()
 
-    async def _handle_function_call_result(self, frame: AWSNovaSonicFunctionCallResultFrame):
-        result = frame.result_frame
-        await self._send_tool_result(tool_call_id=result.tool_call_id, result=result.result)
+    async def _handle_interruption_frame(self):
+        if self._assistant_is_responding:
+            self._may_need_repush_assistant_text = True
 
     #
     # LLM communication: lifecycle
@@ -431,6 +455,17 @@ class AWSNovaSonicLLMService(LLMService):
             logger.error(f"{self} initialization error: {e}")
             await self._disconnect()
 
+    async def _process_completed_function_calls(self, send_new_results: bool):
+        # Check for set of completed function calls in the context
+        for message in self._context.get_messages():
+            if message.get("role") and message.get("content") != "IN_PROGRESS":
+                tool_call_id = message.get("tool_call_id")
+                if tool_call_id and tool_call_id not in self._completed_tool_calls:
+                    # Found a newly-completed function call - send the result to the service
+                    if send_new_results:
+                        await self._send_tool_result(tool_call_id, message.get("content"))
+                    self._completed_tool_calls.add(tool_call_id)
+
     async def _finish_connecting_if_context_available(self):
         # We can only finish connecting once we've gotten our initial context and we're ready to
         # send it
@@ -439,30 +474,38 @@ class AWSNovaSonicLLMService(LLMService):
 
         logger.info("Finishing connecting (setting up session)...")
 
+        # Initialize our bookkeeping of already-completed tool calls in the
+        # context
+        await self._process_completed_function_calls(send_new_results=False)
+
         # Read context
-        history = self._context.get_messages_for_initializing_history()
+        adapter: AWSNovaSonicLLMAdapter = self.get_llm_adapter()
+        llm_connection_params = adapter.get_llm_invocation_params(self._context)
 
         # Send prompt start event, specifying tools.
         # Tools from context take priority over self._tools.
         tools = (
-            self._context.tools
-            if self._context.tools
-            else self.get_llm_adapter().from_standard_tools(self._tools)
+            llm_connection_params["tools"]
+            if llm_connection_params["tools"]
+            else adapter.from_standard_tools(self._tools)
         )
         logger.debug(f"Using tools: {tools}")
         await self._send_prompt_start_event(tools)
 
         # Send system instruction.
         # Instruction from context takes priority over self._system_instruction.
-        # (NOTE: this prioritizing occurred automatically behind the scenes: the context was
-        # initialized with self._system_instruction and then updated itself from its messages when
-        # get_messages_for_initializing_history() was called).
-        logger.debug(f"Using system instruction: {history.system_instruction}")
-        if history.system_instruction:
-            await self._send_text_event(text=history.system_instruction, role=Role.SYSTEM)
+        system_instruction = (
+            llm_connection_params["system_instruction"]
+            if llm_connection_params["system_instruction"]
+            else self._system_instruction
+        )
+        logger.debug(f"Using system instruction: {system_instruction}")
+        if system_instruction:
+            await self._send_text_event(text=system_instruction, role=Role.SYSTEM)
 
         # Send conversation history
-        for message in history.messages:
+        for message in llm_connection_params["messages"]:
+            # logger.debug(f"Seeding conversation history with message: {message}")
             await self._send_text_event(text=message.text, role=message.role)
 
         # Start audio input
@@ -492,9 +535,12 @@ class AWSNovaSonicLLMService(LLMService):
                 await self._send_session_end_events()
                 self._client = None
 
+            # Clean up context
+            self._context = None
+
             # Clean up stream
             if self._stream:
-                await self._stream.input_stream.close()
+                await self._stream.close()
                 self._stream = None
 
             # NOTE: see explanation of HACK, below
@@ -510,15 +556,23 @@ class AWSNovaSonicLLMService(LLMService):
                 self._receive_task = None
 
             # Reset remaining connection-specific state
+            # Should be all private state except:
+            # - _wants_connection
+            # - _assistant_response_trigger_audio
             self._prompt_name = None
             self._input_audio_content_name = None
             self._content_being_received = None
             self._assistant_is_responding = False
+            self._may_need_repush_assistant_text = False
             self._ready_to_send_context = False
             self._handling_bot_stopped_speaking = False
             self._triggering_assistant_response = False
+            self._waiting_for_trigger_transcription = False
             self._disconnecting = False
             self._connected_time = None
+            self._user_text_buffer = ""
+            self._assistant_text_buffer = ""
+            self._completed_tool_calls = set()
 
             logger.info("Finished disconnecting")
         except Exception as e:
@@ -826,6 +880,10 @@ class AWSNovaSonicLLMService(LLMService):
                             # Handle the LLM completion ending
                             await self._handle_completion_end_event(event_json)
         except Exception as e:
+            if self._disconnecting:
+                # Errors are kind of expected while disconnecting, so just
+                # ignore them and do nothing
+                return
             logger.error(f"{self} error processing responses: {e}")
             if self._wants_connection:
                 await self.reset_conversation()
@@ -956,7 +1014,7 @@ class AWSNovaSonicLLMService(LLMService):
     async def _report_assistant_response_started(self):
         logger.debug("Assistant response started")
 
-        # Report that the assistant has started their response.
+        # Report the start of the assistant response.
         await self.push_frame(LLMFullResponseStartFrame())
 
         # Report that equivalent of TTS (this is a speech-to-speech model) started
@@ -968,23 +1026,16 @@ class AWSNovaSonicLLMService(LLMService):
 
         logger.debug(f"Assistant response text added: {text}")
 
-        # Report some text added to the ongoing assistant response
-        await self.push_frame(LLMTextFrame(text))
-
-        # Report some text added to the *equivalent* of TTS (this is a speech-to-speech model)
+        # Report the text of the assistant response.
         await self.push_frame(TTSTextFrame(text))
 
-        # TODO: this is a (hopefully temporary) HACK. Here we directly manipulate the context rather
-        # than relying on the frames pushed to the assistant context aggregator. The pattern of
-        # receiving full-sentence text after the assistant has spoken does not easily fit with the
-        # Pipecat expectation of chunks of text streaming in while the assistant is speaking.
-        # Interruption handling was especially challenging. Rather than spend days trying to fit a
-        # square peg in a round hole, I decided on this hack for the time being. We can most cleanly
-        # abandon this hack if/when AWS Nova Sonic implements streaming smaller text chunks
-        # interspersed with audio. Note that when we move away from this hack, we need to make sure
-        # that on an interruption we avoid sending LLMFullResponseEndFrame, which gets the
-        # LLMAssistantContextAggregator into a bad state.
-        self._context.buffer_assistant_text(text)
+        # HACK: here we're also buffering the assistant text ourselves as a
+        # backup rather than relying solely on the assistant context aggregator
+        # to do it, because the text arrives from Nova Sonic only after all the
+        # assistant audio frames have been pushed, meaning that if an
+        # interruption frame were to arrive we would lose all of it (the text
+        # frames sitting in the queue would be wiped).
+        self._assistant_text_buffer += text
 
     async def _report_assistant_response_ended(self):
         if not self._context:  # should never happen
@@ -992,14 +1043,34 @@ class AWSNovaSonicLLMService(LLMService):
 
         logger.debug("Assistant response ended")
 
-        # Report that the assistant has finished their response.
+        # If an interruption frame arrived while the assistant was responding
+        # we may have lost all of the assistant text (see HACK, above), so
+        # re-push it downstream to the aggregator now.
+        if self._may_need_repush_assistant_text:
+            # Just in case, check that assistant text hasn't already made it
+            # into the context (sometimes it does, despite the interruption).
+            messages = self._context.get_messages()
+            last_message = messages[-1] if messages else None
+            if (
+                not last_message
+                or last_message.get("role") != "assistant"
+                or last_message.get("content") != self._assistant_text_buffer
+            ):
+                # We also need to re-push the LLMFullResponseStartFrame since the
+                # TTSTextFrame would be ignored otherwise (the interruption frame
+                # would have cleared the assistant aggregator state).
+                await self.push_frame(LLMFullResponseStartFrame())
+                await self.push_frame(TTSTextFrame(self._assistant_text_buffer))
+            self._may_need_repush_assistant_text = False
+
+        # Report the end of the assistant response.
         await self.push_frame(LLMFullResponseEndFrame())
 
         # Report that equivalent of TTS (this is a speech-to-speech model) stopped.
         await self.push_frame(TTSStoppedFrame())
 
-        # For an explanation of this hack, see _report_assistant_response_text_added.
-        self._context.flush_aggregated_assistant_text()
+        # Clear out the buffered assistant text
+        self._assistant_text_buffer = ""
 
     #
     # user transcription reporting
@@ -1016,33 +1087,67 @@ class AWSNovaSonicLLMService(LLMService):
 
         logger.debug(f"User transcription text added: {text}")
 
-        # Manually add new user transcription text to context.
-        # We can't rely on the user context aggregator to do this since it's upstream from the LLM.
-        self._context.buffer_user_text(text)
-
-        # Report that some new user transcription text is available.
-        if self._send_transcription_frames:
-            await self.push_frame(
-                InterimTranscriptionFrame(text=text, user_id="", timestamp=time_now_iso8601())
-            )
+        # HACK: here we're buffering the user text ourselves rather than
+        # relying on the upstream user context aggregator to do it, because the
+        # text arrives in fairly large chunks spaced fairly far apart in time.
+        # That means the user text would be split between different messages in
+        # context. Even if we sent placeholder InterimTranscriptionFrames in
+        # between each TranscriptionFrame to tell the aggregator to hold off on
+        # finalizing the user message, the aggregator would likely get the last
+        # chunk too late.
+        self._user_text_buffer += f" {text}" if self._user_text_buffer else text
 
     async def _report_user_transcription_ended(self):
         if not self._context:  # should never happen
             return
 
-        # Manually add user transcription to context (if any has been buffered).
-        # We can't rely on the user context aggregator to do this since it's upstream from the LLM.
-        transcription = self._context.flush_aggregated_user_text()
-
-        if not transcription:
-            return
-
         logger.debug(f"User transcription ended")
 
-        if self._send_transcription_frames:
-            await self.push_frame(
-                TranscriptionFrame(text=transcription, user_id="", timestamp=time_now_iso8601())
+        # Report to the upstream user context aggregator that some new user
+        # transcription text is available.
+
+        # HACK: Check if this transcription was triggered by our own
+        # assistant response trigger. If so, we need to wrap it with
+        # UserStarted/StoppedSpeakingFrames; otherwise the user aggregator
+        # would fire an EmulatedUserStartedSpeakingFrame, which would
+        # trigger an interruption, which would prevent us from writing the
+        # assistant response to context.
+        #
+        # Sending an EmulateUserStartedSpeakingFrame ourselves doesn't
+        # work: it just causes the interruption we're trying to avoid.
+        #
+        # Setting enable_emulated_vad_interruptions also doesn't work: at
+        # the time the user aggregator receives the TranscriptionFrame, it
+        # doesn't yet know the assistant has started responding, so it
+        # doesn't know that emulating the user starting to speak would
+        # cause an interruption.
+        should_wrap_in_user_started_stopped_speaking_frames = (
+            self._waiting_for_trigger_transcription
+            and self._user_text_buffer.strip().lower() == "ready"
+        )
+
+        # Start wrapping the upstream transcription in UserStarted/StoppedSpeakingFrames if needed
+        if should_wrap_in_user_started_stopped_speaking_frames:
+            logger.debug(
+                "Wrapping assistant response trigger transcription with upstream UserStarted/StoppedSpeakingFrames"
             )
+            await self.push_frame(UserStartedSpeakingFrame(), direction=FrameDirection.UPSTREAM)
+
+        # Send the transcription upstream for the user context aggregator
+        frame = TranscriptionFrame(
+            text=self._user_text_buffer, user_id="", timestamp=time_now_iso8601()
+        )
+        await self.push_frame(frame, direction=FrameDirection.UPSTREAM)
+
+        # Finish wrapping the upstream transcription in UserStarted/StoppedSpeakingFrames if needed
+        if should_wrap_in_user_started_stopped_speaking_frames:
+            await self.push_frame(UserStoppedSpeakingFrame(), direction=FrameDirection.UPSTREAM)
+
+        # Clear out the buffered user text
+        self._user_text_buffer = ""
+
+        # We're no longer waiting for a trigger transcription
+        self._waiting_for_trigger_transcription = False
 
     #
     # context
@@ -1054,23 +1159,26 @@ class AWSNovaSonicLLMService(LLMService):
         *,
         user_params: LLMUserAggregatorParams = LLMUserAggregatorParams(),
         assistant_params: LLMAssistantAggregatorParams = LLMAssistantAggregatorParams(),
-    ) -> AWSNovaSonicContextAggregatorPair:
+    ) -> LLMContextAggregatorPair:
         """Create context aggregator pair for managing conversation context.
 
+        NOTE: this method exists only for backward compatibility. New code
+        should instead do:
+            context = LLMContext(...)
+            context_aggregator = LLMContextAggregatorPair(context)
+
         Args:
-            context: The OpenAI LLM context to upgrade.
+            context: The OpenAI LLM context.
             user_params: Parameters for the user context aggregator.
             assistant_params: Parameters for the assistant context aggregator.
 
         Returns:
             A pair of user and assistant context aggregators.
         """
-        context.set_llm_adapter(self.get_llm_adapter())
-
-        user = AWSNovaSonicUserContextAggregator(context=context, params=user_params)
-        assistant = AWSNovaSonicAssistantContextAggregator(context=context, params=assistant_params)
-
-        return AWSNovaSonicContextAggregatorPair(user, assistant)
+        context = LLMContext.from_openai_context(context)
+        return LLMContextAggregatorPair(
+            context, user_params=user_params, assistant_params=assistant_params
+        )
 
     #
     # assistant response trigger (HACK)
@@ -1108,6 +1216,8 @@ class AWSNovaSonicLLMService(LLMService):
         try:
             logger.debug("Sending assistant response trigger...")
 
+            self._waiting_for_trigger_transcription = True
+
             chunk_duration = 0.02  # what we might get from InputAudioRawFrame
             chunk_size = int(
                 chunk_duration

src/pipecat/services/aws/stt.py

@@ -286,6 +286,7 @@ class AWSTranscribeSTTService(STTService):
 
                 logger.info(f"{self} Successfully connected to AWS Transcribe")
 
+                await self._call_event_handler("on_connected")
             except Exception as e:
                 logger.error(f"{self} Failed to connect to AWS Transcribe: {e}")
                 await self._disconnect()
@@ -310,6 +311,7 @@ class AWSTranscribeSTTService(STTService):
             logger.warning(f"{self} Error closing WebSocket connection: {e}")
         finally:
             self._ws_client = None
+            await self._call_event_handler("on_disconnected")
 
     def language_to_service_language(self, language: Language) -> str | None:
         """Convert internal language enum to AWS Transcribe language code.

src/pipecat/services/aws_nova_sonic/context.py

@@ -8,18 +8,14 @@
 
 This module provides specialized context aggregators and message handling for AWS Nova Sonic,
 including conversation history management and role-specific message processing.
+
+.. deprecated:: 0.0.91
+    AWS Nova Sonic no longer uses types from this module under the hood.
+    It now uses `LLMContext` and `LLMContextAggregatorPair`.
+    Using the new patterns should allow you to not need types from this module.
+
+    See deprecation warning in pipecat.services.aws.nova_sonic.context for more
+    details.
 """
 
-import warnings
-
 from pipecat.services.aws.nova_sonic.context import *
-
-with warnings.catch_warnings():
-    warnings.simplefilter("always")
-    warnings.warn(
-        "Types in pipecat.services.aws_nova_sonic.context are deprecated. "
-        "Please use the equivalent types from "
-        "pipecat.services.aws.nova_sonic.context instead.",
-        DeprecationWarning,
-        stacklevel=2,
-    )

src/pipecat/services/azure/realtime/llm.py

@@ -38,7 +38,7 @@ class AzureRealtimeLLMService(OpenAIRealtimeLLMService):
         Args:
             api_key: The API key for the Azure OpenAI service.
             base_url: The full Azure WebSocket endpoint URL including api-version and deployment.
-                Example: "wss://my-project.openai.azure.com/openai/realtime?api-version=2024-10-01-preview&deployment=my-realtime-deployment"
+                Example: "wss://my-project.openai.azure.com/openai/realtime?api-version=2025-04-01-preview&deployment=my-realtime-deployment"
             **kwargs: Additional arguments passed to parent OpenAIRealtimeLLMService.
         """
         super().__init__(base_url=base_url, api_key=api_key, **kwargs)
@@ -52,7 +52,7 @@ class AzureRealtimeLLMService(OpenAIRealtimeLLMService):
                 # handle disconnections in the send/recv code paths.
                 return
 
-            logger.info(f"Connecting to {self.base_url}, api key: {self.api_key}")
+            logger.info(f"Connecting to {self.base_url}")
             self._websocket = await websocket_connect(
                 uri=self.base_url,
                 additional_headers={

src/pipecat/services/cartesia/stt.py

@@ -28,13 +28,12 @@ from pipecat.frames.frames import (
     UserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.stt_service import STTService
+from pipecat.services.stt_service import WebsocketSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.utils.time import time_now_iso8601
 from pipecat.utils.tracing.service_decorators import traced_stt
 
 try:
-    import websockets
     from websockets.asyncio.client import connect as websocket_connect
     from websockets.protocol import State
 except ModuleNotFoundError as e:
@@ -124,7 +123,7 @@ class CartesiaLiveOptions:
         return cls(**json.loads(json_str))
 
 
-class CartesiaSTTService(STTService):
+class CartesiaSTTService(WebsocketSTTService):
     """Speech-to-text service using Cartesia Live API.
 
     Provides real-time speech transcription through WebSocket connection
@@ -176,8 +175,7 @@ class CartesiaSTTService(STTService):
         self.set_model_name(merged_options.model)
         self._api_key = api_key
         self._base_url = base_url or "api.cartesia.ai"
-        self._connection = None
-        self._receiver_task = None
+        self._receive_task = None
 
     def can_generate_metrics(self) -> bool:
         """Check if the service can generate processing metrics.
@@ -214,6 +212,27 @@ class CartesiaSTTService(STTService):
         await super().cancel(frame)
         await self._disconnect()
 
+    async def start_metrics(self):
+        """Start performance metrics collection for transcription processing."""
+        await self.start_ttfb_metrics()
+        await self.start_processing_metrics()
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Process incoming frames and handle speech events.
+
+        Args:
+            frame: The frame to process.
+            direction: Direction of frame flow in the pipeline.
+        """
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserStartedSpeakingFrame):
+            await self.start_metrics()
+        elif isinstance(frame, UserStoppedSpeakingFrame):
+            # Send finalize command to flush the transcription session
+            if self._websocket and self._websocket.state is State.OPEN:
+                await self._websocket.send("finalize")
+
     async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
         """Process audio data for speech-to-text transcription.
 
@@ -224,45 +243,71 @@ class CartesiaSTTService(STTService):
             None - transcription results are handled via WebSocket responses.
         """
         # If the connection is closed, due to timeout, we need to reconnect when the user starts speaking again
-        if not self._connection or self._connection.state is State.CLOSED:
+        if not self._websocket or self._websocket.state is State.CLOSED:
             await self._connect()
 
-        await self._connection.send(audio)
+        await self._websocket.send(audio)
         yield None
 
     async def _connect(self):
-        params = self._settings.to_dict()
-        ws_url = f"wss://{self._base_url}/stt/websocket?{urllib.parse.urlencode(params)}"
-        logger.debug(f"Connecting to Cartesia: {ws_url}")
-        headers = {"Cartesia-Version": "2025-04-16", "X-API-Key": self._api_key}
+        await self._connect_websocket()
 
+        if self._websocket and not self._receive_task:
+            self._receive_task = asyncio.create_task(self._receive_task_handler(self._report_error))
+
+    async def _disconnect(self):
+        if self._receive_task:
+            await self.cancel_task(self._receive_task)
+            self._receive_task = None
+
+        await self._disconnect_websocket()
+
+    async def _connect_websocket(self):
         try:
-            self._connection = await websocket_connect(ws_url, additional_headers=headers)
-            # Setup the receiver task to handle the incoming messages from the Cartesia server
-            if self._receiver_task is None or self._receiver_task.done():
-                self._receiver_task = asyncio.create_task(self._receive_messages())
-            logger.debug(f"Connected to Cartesia")
+            if self._websocket and self._websocket.state is State.OPEN:
+                return
+            logger.debug("Connecting to Cartesia STT")
+
+            params = self._settings.to_dict()
+            ws_url = f"wss://{self._base_url}/stt/websocket?{urllib.parse.urlencode(params)}"
+            headers = {"Cartesia-Version": "2025-04-16", "X-API-Key": self._api_key}
+
+            self._websocket = await websocket_connect(ws_url, additional_headers=headers)
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self}: unable to connect to Cartesia: {e}")
 
-    async def _receive_messages(self):
+    async def _disconnect_websocket(self):
         try:
-            while True:
-                if not self._connection or self._connection.state is State.CLOSED:
-                    break
-
-                message = await self._connection.recv()
-                try:
-                    data = json.loads(message)
-                    await self._process_response(data)
-                except json.JSONDecodeError:
-                    logger.warning(f"Received non-JSON message: {message}")
-        except asyncio.CancelledError:
-            pass
-        except websockets.exceptions.ConnectionClosed as e:
-            logger.debug(f"WebSocket connection closed: {e}")
+            if self._websocket and self._websocket.state is State.OPEN:
+                logger.debug("Disconnecting from Cartesia STT")
+                await self._websocket.close()
         except Exception as e:
-            logger.error(f"Error in message receiver: {e}")
+            logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
+
+    def _get_websocket(self):
+        if self._websocket:
+            return self._websocket
+        raise Exception("Websocket not connected")
+
+    async def _process_messages(self):
+        async for message in self._get_websocket():
+            try:
+                data = json.loads(message)
+                await self._process_response(data)
+            except json.JSONDecodeError:
+                logger.warning(f"Received non-JSON message: {message}")
+
+    async def _receive_messages(self):
+        while True:
+            await self._process_messages()
+            # Cartesia times out after 5 minutes of innactivity (no keepalive
+            # mechanism is available). So, we try to reconnect.
+            logger.debug(f"{self} Cartesia connection was disconnected (timeout?), reconnecting")
+            await self._connect_websocket()
 
     async def _process_response(self, data):
         if "type" in data:
@@ -316,41 +361,3 @@ class CartesiaSTTService(STTService):
                         language,
                     )
                 )
-
-    async def _disconnect(self):
-        if self._receiver_task:
-            self._receiver_task.cancel()
-            try:
-                await self._receiver_task
-            except asyncio.CancelledError:
-                pass
-            except Exception as e:
-                logger.exception(f"Unexpected exception while cancelling task: {e}")
-            self._receiver_task = None
-
-        if self._connection and self._connection.state is State.OPEN:
-            logger.debug("Disconnecting from Cartesia")
-
-            await self._connection.close()
-            self._connection = None
-
-    async def start_metrics(self):
-        """Start performance metrics collection for transcription processing."""
-        await self.start_ttfb_metrics()
-        await self.start_processing_metrics()
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process incoming frames and handle speech events.
-
-        Args:
-            frame: The frame to process.
-            direction: Direction of frame flow in the pipeline.
-        """
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserStartedSpeakingFrame):
-            await self.start_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
-            # Send finalize command to flush the transcription session
-            if self._connection and self._connection.state is State.OPEN:
-                await self._connection.send("finalize")

src/pipecat/services/cartesia/tts.py

@@ -48,6 +48,26 @@ except ModuleNotFoundError as e:
     raise Exception(f"Missing module: {e}")
 
 
+class GenerationConfig(BaseModel):
+    """Configuration for Cartesia Sonic-3 generation parameters.
+
+    Sonic-3 interprets these parameters as guidance to ensure natural speech.
+    Test against your content for best results.
+
+    Parameters:
+        volume: Volume multiplier for generated speech. Valid range: [0.5, 2.0]. Default is 1.0.
+        speed: Speed multiplier for generated speech. Valid range: [0.6, 1.5]. Default is 1.0.
+        emotion: Single emotion string to guide the emotional tone. Examples include neutral,
+            angry, excited, content, sad, scared. Over 60 emotions are supported. For best
+            results, use with recommended voices: Leo, Jace, Kyle, Gavin, Maya, Tessa, Dana,
+            and Marian.
+    """
+
+    volume: Optional[float] = None
+    speed: Optional[float] = None
+    emotion: Optional[str] = None
+
+
 def language_to_cartesia_language(language: Language) -> Optional[str]:
     """Convert a Language enum to Cartesia language code.
 
@@ -101,16 +121,20 @@ class CartesiaTTSService(AudioContextWordTTSService):
 
         Parameters:
             language: Language to use for synthesis.
-            speed: Voice speed control.
-            emotion: List of emotion controls.
+            speed: Voice speed control for non-Sonic-3 models (literal values).
+            emotion: List of emotion controls for non-Sonic-3 models.
 
                 .. deprecated:: 0.0.68
                         The `emotion` parameter is deprecated and will be removed in a future version.
+
+            generation_config: Generation configuration for Sonic-3 models. Includes volume,
+                speed (numeric), and emotion (string) parameters.
         """
 
         language: Optional[Language] = Language.EN
         speed: Optional[Literal["slow", "normal", "fast"]] = None
         emotion: Optional[List[str]] = []
+        generation_config: Optional[GenerationConfig] = None
 
     def __init__(
         self,
@@ -119,7 +143,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
         voice_id: str,
         cartesia_version: str = "2025-04-16",
         url: str = "wss://api.cartesia.ai/tts/websocket",
-        model: str = "sonic-2",
+        model: str = "sonic-3",
         sample_rate: Optional[int] = None,
         encoding: str = "pcm_s16le",
         container: str = "raw",
@@ -135,7 +159,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
             voice_id: ID of the voice to use for synthesis.
             cartesia_version: API version string for Cartesia service.
             url: WebSocket URL for Cartesia TTS API.
-            model: TTS model to use (e.g., "sonic-2").
+            model: TTS model to use (e.g., "sonic-3").
             sample_rate: Audio sample rate. If None, uses default.
             encoding: Audio encoding format.
             container: Audio container format.
@@ -179,6 +203,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
             else "en",
             "speed": params.speed,
             "emotion": params.emotion,
+            "generation_config": params.generation_config,
         }
         self.set_model_name(model)
         self.set_voice(voice_id)
@@ -297,6 +322,11 @@ class CartesiaTTSService(AudioContextWordTTSService):
         if self._settings["speed"]:
             msg["speed"] = self._settings["speed"]
 
+        if self._settings["generation_config"]:
+            msg["generation_config"] = self._settings["generation_config"].model_dump(
+                exclude_none=True
+            )
+
         return json.dumps(msg)
 
     async def start(self, frame: StartFrame):
@@ -344,10 +374,11 @@ class CartesiaTTSService(AudioContextWordTTSService):
         try:
             if self._websocket and self._websocket.state is State.OPEN:
                 return
-            logger.debug("Connecting to Cartesia")
+            logger.debug("Connecting to Cartesia TTS")
             self._websocket = await websocket_connect(
                 f"{self._url}?api_key={self._api_key}&cartesia_version={self._cartesia_version}"
             )
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -365,6 +396,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
         finally:
             self._context_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:
@@ -480,23 +512,27 @@ class CartesiaHttpTTSService(TTSService):
 
         Parameters:
             language: Language to use for synthesis.
-            speed: Voice speed control.
-            emotion: List of emotion controls.
+            speed: Voice speed control for non-Sonic-3 models (literal values).
+            emotion: List of emotion controls for non-Sonic-3 models.
 
                 .. deprecated:: 0.0.68
                         The `emotion` parameter is deprecated and will be removed in a future version.
+
+            generation_config: Generation configuration for Sonic-3 models. Includes volume,
+                speed (numeric), and emotion (string) parameters.
         """
 
         language: Optional[Language] = Language.EN
         speed: Optional[Literal["slow", "normal", "fast"]] = None
         emotion: Optional[List[str]] = Field(default_factory=list)
+        generation_config: Optional[GenerationConfig] = None
 
     def __init__(
         self,
         *,
         api_key: str,
         voice_id: str,
-        model: str = "sonic-2",
+        model: str = "sonic-3",
         base_url: str = "https://api.cartesia.ai",
         cartesia_version: str = "2024-11-13",
         sample_rate: Optional[int] = None,
@@ -510,7 +546,7 @@ class CartesiaHttpTTSService(TTSService):
         Args:
             api_key: Cartesia API key for authentication.
             voice_id: ID of the voice to use for synthesis.
-            model: TTS model to use (e.g., "sonic-2").
+            model: TTS model to use (e.g., "sonic-3").
             base_url: Base URL for Cartesia HTTP API.
             cartesia_version: API version string for Cartesia service.
             sample_rate: Audio sample rate. If None, uses default.
@@ -537,6 +573,7 @@ class CartesiaHttpTTSService(TTSService):
             else "en",
             "speed": params.speed,
             "emotion": params.emotion,
+            "generation_config": params.generation_config,
         }
         self.set_voice(voice_id)
         self.set_model_name(model)
@@ -630,6 +667,11 @@ class CartesiaHttpTTSService(TTSService):
             if self._settings["speed"]:
                 payload["speed"] = self._settings["speed"]
 
+            if self._settings["generation_config"]:
+                payload["generation_config"] = self._settings["generation_config"].model_dump(
+                    exclude_none=True
+                )
+
             yield TTSStartedFrame()
 
             session = await self._client._get_session()

src/pipecat/services/deepgram/flux/stt.py

@@ -205,6 +205,7 @@ class DeepgramFluxSTTService(WebsocketSTTService):
                 additional_headers={"Authorization": f"Token {self._api_key}"},
             )
             logger.debug("Connected to Deepgram Flux Websocket")
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -225,6 +226,9 @@ class DeepgramFluxSTTService(WebsocketSTTService):
                 await self._websocket.close()
         except Exception as e:
             logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     async def _send_close_stream(self) -> None:
         """Sends a CloseStream control message to the Deepgram Flux WebSocket API.

src/pipecat/services/elevenlabs/tts.py

@@ -168,16 +168,24 @@ def build_elevenlabs_voice_settings(
 
 
 def calculate_word_times(
-    alignment_info: Mapping[str, Any], cumulative_time: float
-) -> List[Tuple[str, float]]:
+    alignment_info: Mapping[str, Any],
+    cumulative_time: float,
+    partial_word: str = "",
+    partial_word_start_time: float = 0.0,
+) -> tuple[List[Tuple[str, float]], str, float]:
     """Calculate word timestamps from character alignment information.
 
     Args:
         alignment_info: Character alignment data from ElevenLabs API.
         cumulative_time: Base time offset for this chunk.
+        partial_word: Partial word carried over from previous chunk.
+        partial_word_start_time: Start time of the partial word.
 
     Returns:
-        List of (word, timestamp) tuples.
+        Tuple of (word_times, new_partial_word, new_partial_word_start_time):
+        - word_times: List of (word, timestamp) tuples for complete words
+        - new_partial_word: Incomplete word at end of chunk (empty if chunk ends with space)
+        - new_partial_word_start_time: Start time of the incomplete word
     """
     chars = alignment_info["chars"]
     char_start_times_ms = alignment_info["charStartTimesMs"]
@@ -186,41 +194,37 @@ def calculate_word_times(
         logger.error(
             f"calculate_word_times: length mismatch - chars={len(chars)}, times={len(char_start_times_ms)}"
         )
-        return []
+        return ([], partial_word, partial_word_start_time)
 
     # Build words and track their start positions
     words = []
-    word_start_indices = []
-    current_word = ""
-    word_start_index = None
+    word_start_times = []
+    current_word = partial_word  # Start with any partial word from previous chunk
+    word_start_time = partial_word_start_time if partial_word else None
 
     for i, char in enumerate(chars):
         if char == " ":
             # End of current word
             if current_word:  # Only add non-empty words
                 words.append(current_word)
-                word_start_indices.append(word_start_index)
+                word_start_times.append(word_start_time)
                 current_word = ""
-                word_start_index = None
+                word_start_time = None
         else:
             # Building a word
-            if word_start_index is None:  # First character of new word
-                word_start_index = i
+            if word_start_time is None:  # First character of new word
+                # Convert from milliseconds to seconds and add cumulative offset
+                word_start_time = cumulative_time + (char_start_times_ms[i] / 1000.0)
             current_word += char
 
-    # Handle the last word if there's no trailing space
-    if current_word and word_start_index is not None:
-        words.append(current_word)
-        word_start_indices.append(word_start_index)
+    # Build result for complete words
+    word_times = list(zip(words, word_start_times))
 
-    # Calculate timestamps for each word
-    word_times = []
-    for word, start_idx in zip(words, word_start_indices):
-        # Convert from milliseconds to seconds and add cumulative offset
-        start_time_seconds = cumulative_time + (char_start_times_ms[start_idx] / 1000.0)
-        word_times.append((word, start_time_seconds))
+    # Return any incomplete word at the end of this chunk
+    new_partial_word = current_word if current_word else ""
+    new_partial_word_start_time = word_start_time if word_start_time is not None else 0.0
 
-    return word_times
+    return (word_times, new_partial_word, new_partial_word_start_time)
 
 
 class ElevenLabsTTSService(AudioContextWordTTSService):
@@ -332,6 +336,9 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
         # there's an interruption or TTSStoppedFrame.
         self._started = False
         self._cumulative_time = 0
+        # Track partial words that span across alignment chunks
+        self._partial_word = ""
+        self._partial_word_start_time = 0.0
 
         # Context management for v1 multi API
         self._context_id = None
@@ -521,6 +528,7 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
                 url, max_size=16 * 1024 * 1024, additional_headers={"xi-api-key": self._api_key}
             )
 
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -543,6 +551,7 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
             self._started = False
             self._context_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:
@@ -570,6 +579,8 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
                 logger.error(f"Error closing context on interruption: {e}")
             self._context_id = None
             self._started = False
+            self._partial_word = ""
+            self._partial_word_start_time = 0.0
 
     async def _receive_messages(self):
         """Handle incoming WebSocket messages from ElevenLabs."""
@@ -609,7 +620,14 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
 
             if msg.get("alignment"):
                 alignment = msg["alignment"]
-                word_times = calculate_word_times(alignment, self._cumulative_time)
+                word_times, self._partial_word, self._partial_word_start_time = (
+                    calculate_word_times(
+                        alignment,
+                        self._cumulative_time,
+                        self._partial_word,
+                        self._partial_word_start_time,
+                    )
+                )
 
                 if word_times:
                     await self.add_word_timestamps(word_times)
@@ -683,6 +701,8 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
                     yield TTSStartedFrame()
                     self._started = True
                     self._cumulative_time = 0
+                    self._partial_word = ""
+                    self._partial_word_start_time = 0.0
                     # If a context ID does not exist, create a new one and
                     # register it. If an ID exists, that means the Pipeline is
                     # configured for allow_interruptions=False, so continue
@@ -756,6 +776,7 @@ class ElevenLabsHttpTTSService(WordTTSService):
         base_url: str = "https://api.elevenlabs.io",
         sample_rate: Optional[int] = None,
         params: Optional[InputParams] = None,
+        aggregate_sentences: Optional[bool] = True,
         **kwargs,
     ):
         """Initialize the ElevenLabs HTTP TTS service.
@@ -768,10 +789,11 @@ class ElevenLabsHttpTTSService(WordTTSService):
             base_url: Base URL for ElevenLabs HTTP API.
             sample_rate: Audio sample rate. If None, uses default.
             params: Additional input parameters for voice customization.
+            aggregate_sentences: Whether to aggregate sentences within the TTSService.
             **kwargs: Additional arguments passed to the parent service.
         """
         super().__init__(
-            aggregate_sentences=True,
+            aggregate_sentences=aggregate_sentences,
             push_text_frames=False,
             push_stop_frames=True,
             sample_rate=sample_rate,
@@ -809,6 +831,10 @@ class ElevenLabsHttpTTSService(WordTTSService):
         # Store previous text for context within a turn
         self._previous_text = ""
 
+        # Track partial words that span across alignment chunks
+        self._partial_word = ""
+        self._partial_word_start_time = 0.0
+
     def language_to_service_language(self, language: Language) -> Optional[str]:
         """Convert pipecat Language to ElevenLabs language code.
 
@@ -836,6 +862,8 @@ class ElevenLabsHttpTTSService(WordTTSService):
         self._cumulative_time = 0
         self._started = False
         self._previous_text = ""
+        self._partial_word = ""
+        self._partial_word_start_time = 0.0
         logger.debug(f"{self}: Reset internal state")
 
     async def start(self, frame: StartFrame):
@@ -870,11 +898,13 @@ class ElevenLabsHttpTTSService(WordTTSService):
     def calculate_word_times(self, alignment_info: Mapping[str, Any]) -> List[Tuple[str, float]]:
         """Calculate word timing from character alignment data.
 
+        This method handles partial words that may span across multiple alignment chunks.
+
         Args:
             alignment_info: Character timing data from ElevenLabs.
 
         Returns:
-            List of (word, timestamp) pairs.
+            List of (word, timestamp) pairs for complete words in this chunk.
 
         Example input data::
 
@@ -900,30 +930,28 @@ class ElevenLabsHttpTTSService(WordTTSService):
         # Build the words and find their start times
         words = []
         word_start_times = []
-        current_word = ""
-        first_char_idx = -1
+        # Start with any partial word from previous chunk
+        current_word = self._partial_word
+        word_start_time = self._partial_word_start_time if self._partial_word else None
 
         for i, char in enumerate(chars):
             if char == " ":
                 if current_word:  # Only add non-empty words
                     words.append(current_word)
-                    # Use time of the first character of the word, offset by cumulative time
-                    word_start_times.append(
-                        self._cumulative_time + char_start_times[first_char_idx]
-                    )
+                    word_start_times.append(word_start_time)
                     current_word = ""
-                    first_char_idx = -1
+                    word_start_time = None
             else:
-                if not current_word:  # This is the first character of a new word
-                    first_char_idx = i
+                if word_start_time is None:  # First character of a new word
+                    # Use time of the first character of the word, offset by cumulative time
+                    word_start_time = self._cumulative_time + char_start_times[i]
                 current_word += char
 
-        # Don't forget the last word if there's no trailing space
-        if current_word and first_char_idx >= 0:
-            words.append(current_word)
-            word_start_times.append(self._cumulative_time + char_start_times[first_char_idx])
+        # Store any incomplete word at the end of this chunk
+        self._partial_word = current_word if current_word else ""
+        self._partial_word_start_time = word_start_time if word_start_time is not None else 0.0
 
-        # Create word-time pairs
+        # Create word-time pairs for complete words only
         word_times = list(zip(words, word_start_times))
 
         return word_times
@@ -959,6 +987,9 @@ class ElevenLabsHttpTTSService(WordTTSService):
         if self._voice_settings:
             payload["voice_settings"] = self._voice_settings
 
+        if self._settings["apply_text_normalization"] is not None:
+            payload["apply_text_normalization"] = self._settings["apply_text_normalization"]
+
         language = self._settings["language"]
         if self._model_name in ELEVENLABS_MULTILINGUAL_MODELS and language:
             payload["language_code"] = language
@@ -979,8 +1010,6 @@ class ElevenLabsHttpTTSService(WordTTSService):
         }
         if self._settings["optimize_streaming_latency"] is not None:
             params["optimize_streaming_latency"] = self._settings["optimize_streaming_latency"]
-        if self._settings["apply_text_normalization"] is not None:
-            params["apply_text_normalization"] = self._settings["apply_text_normalization"]
 
         try:
             await self.start_ttfb_metrics()
@@ -1041,6 +1070,14 @@ class ElevenLabsHttpTTSService(WordTTSService):
                         logger.error(f"Error processing response: {e}", exc_info=True)
                         continue
 
+                # After processing all chunks, emit any remaining partial word
+                # since this is the end of the utterance
+                if self._partial_word:
+                    final_word_time = [(self._partial_word, self._partial_word_start_time)]
+                    await self.add_word_timestamps(final_word_time)
+                    self._partial_word = ""
+                    self._partial_word_start_time = 0.0
+
                 # After processing all chunks, add the total utterance duration
                 # to the cumulative time to ensure next utterance starts after this one
                 if utterance_duration > 0:

src/pipecat/services/fish/tts.py

@@ -225,6 +225,8 @@ class FishAudioTTSService(InterruptibleTTSService):
             start_message = {"event": "start", "request": {"text": "", **self._settings}}
             await self._websocket.send(ormsgpack.packb(start_message))
             logger.debug("Sent start message to Fish Audio")
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"Fish Audio initialization error: {e}")
             self._websocket = None
@@ -245,6 +247,7 @@ class FishAudioTTSService(InterruptibleTTSService):
             self._request_id = None
             self._started = False
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     async def flush_audio(self):
         """Flush any buffered audio by sending a flush event to Fish Audio."""

src/pipecat/services/google/gemini_live/llm.py

@@ -17,6 +17,7 @@ import json
 import random
 import time
 import uuid
+import warnings
 from dataclasses import dataclass
 from enum import Enum
 from typing import Any, Dict, List, Optional, Union
@@ -56,10 +57,12 @@ from pipecat.frames.frames import (
     UserStoppedSpeakingFrame,
 )
 from pipecat.metrics.metrics import LLMTokenUsage
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response import (
     LLMAssistantAggregatorParams,
     LLMUserAggregatorParams,
 )
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
     OpenAILLMContextFrame,
@@ -219,6 +222,10 @@ class GeminiLiveContext(OpenAILLMContext):
 
     Provides Gemini-specific context management including system instruction
     extraction and message format conversion for the Live API.
+
+    .. deprecated:: 0.0.92
+        Gemini Live no longer uses `GeminiLiveContext` under the hood.
+        It now uses `LLMContext`.
     """
 
     @staticmethod
@@ -231,6 +238,22 @@ class GeminiLiveContext(OpenAILLMContext):
         Returns:
             The upgraded Gemini context instance.
         """
+        # This warning is here rather than `__init__` since `upgrade()` was the
+        # "main" way that GeminiLiveContext instances were created.
+        # Almost no users should be seeing this message anyway, as
+        # GeminiLiveContext instances were typically created under the hood:
+        # the user would pass an OpenAILLMContext instance, which would be
+        # upgraded without them necessarily knowing.
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "GeminiLiveContext is deprecated. "
+                "Gemini Live no longer uses GeminiLiveContext under the hood. "
+                "It now uses LLMContext.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         if isinstance(obj, OpenAILLMContext) and not isinstance(obj, GeminiLiveContext):
             logger.debug(f"Upgrading to Gemini Live Context: {obj}")
             obj.__class__ = GeminiLiveContext
@@ -328,8 +351,28 @@ class GeminiLiveUserContextAggregator(OpenAIUserContextAggregator):
 
     Extends OpenAI user aggregator to handle Gemini-specific message passing
     while maintaining compatibility with the standard aggregation pipeline.
+
+    .. deprecated:: 0.0.92
+        Gemini Live no longer expects a `GeminiLiveUserContextAggregator`.
+        It now expects a `LLMUserAggregator`.
     """
 
+    def __init__(self, *args, **kwargs):
+        """Initialize Gemini Live user context aggregator."""
+        # Almost no users should be seeing this message, as
+        # `GeminiLiveUserContextAggregator`` instances were typically created
+        # under the hood, as part of `llm.create_context_aggregator()`.
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "GeminiLiveUserContextAggregator is deprecated. "
+                "Gemini Live no longer expects a GeminiLiveUserContextAggregator. "
+                "It now expects a LLMUserAggregator.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+        super().__init__(*args, **kwargs)
+
     async def process_frame(self, frame, direction):
         """Process incoming frames for user context aggregation.
 
@@ -349,8 +392,28 @@ class GeminiLiveAssistantContextAggregator(OpenAIAssistantContextAggregator):
     Handles assistant response aggregation while filtering out LLMTextFrames
     to prevent duplicate context entries, as Gemini Live pushes both
     LLMTextFrames and TTSTextFrames.
+
+    .. deprecated:: 0.0.92
+        Gemini Live no longer uses `GeminiLiveAssistantContextAggregator` under the hood.
+        It now uses `LLMAssistantAggregator`.
     """
 
+    def __init__(self, *args, **kwargs):
+        """Initialize Gemini Live assistant context aggregator."""
+        # Almost no users should be seeing this message, as
+        # `GeminiLiveAssistantContextAggregator` instances were typically
+        # created under the hood, as part of `llm.create_context_aggregator()`.
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "GeminiLiveAssistantContextAggregator is deprecated. "
+                "Gemini Live no longer uses GeminiLiveAssistantContextAggregator under the hood. "
+                "It now uses LLMAssistantAggregator.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+        super().__init__(*args, **kwargs)
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         """Process incoming frames for assistant context aggregation.
 
@@ -380,6 +443,10 @@ class GeminiLiveAssistantContextAggregator(OpenAIAssistantContextAggregator):
 class GeminiLiveContextAggregatorPair:
     """Pair of user and assistant context aggregators for Gemini Live.
 
+    .. deprecated:: 0.0.92
+        `GeminiLiveContextAggregatorPair` is deprecated.
+        Use `LLMContextAggregatorPair` instead.
+
     Parameters:
         _user: The user context aggregator instance.
         _assistant: The assistant context aggregator instance.
@@ -388,6 +455,19 @@ class GeminiLiveContextAggregatorPair:
     _user: GeminiLiveUserContextAggregator
     _assistant: GeminiLiveAssistantContextAggregator
 
+    def __post_init__(self):
+        # Almost no users should be seeing this message, as
+        # `GeminiLiveContextAggregatorPair` instances were typically created
+        # under the hood, with `llm.create_context_aggregator()`.
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "GeminiLiveContextAggregatorPair is deprecated. "
+                "Use LLMContextAggregatorPair instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
     def user(self) -> GeminiLiveUserContextAggregator:
         """Get the user context aggregator.
 
@@ -609,7 +689,7 @@ class GeminiLiveLLMService(LLMService):
         self._run_llm_when_session_ready = False
 
         self._user_is_speaking = False
-        self._bot_is_speaking = False
+        self._bot_is_responding = False
         self._user_audio_buffer = bytearray()
         self._user_transcription_buffer = ""
         self._last_transcription_sent = ""
@@ -665,6 +745,9 @@ class GeminiLiveLLMService(LLMService):
         # Initialize the API client. Subclasses can override this if needed.
         self.create_client()
 
+        # Bookkeeping for tool calls
+        self._completed_tool_calls = set()
+
     def create_client(self):
         """Create the Gemini API client instance. Subclasses can override this."""
         self._client = Client(api_key=self._api_key, http_options=self._http_options)
@@ -787,9 +870,13 @@ class GeminiLiveLLMService(LLMService):
     #
 
     async def _handle_interruption(self):
-        await self._set_bot_is_speaking(False)
-        await self.push_frame(TTSStoppedFrame())
-        await self.push_frame(LLMFullResponseEndFrame())
+        if self._bot_is_responding:
+            await self._set_bot_is_responding(False)
+            if self._settings.get("modalities") == GeminiModalities.AUDIO:
+                await self.push_frame(TTSStoppedFrame())
+            # Do not send LLMFullResponseEndFrame here - an interruption
+            # already tells the assistant context aggregator that the response
+            # is over.
 
     async def _handle_user_started_speaking(self, frame):
         self._user_is_speaking = True
@@ -807,7 +894,6 @@ class GeminiLiveLLMService(LLMService):
 
     #
     # frame processing
-    #
     # StartFrame, StopFrame, CancelFrame implemented in base class
     #
 
@@ -820,7 +906,7 @@ class GeminiLiveLLMService(LLMService):
         """
         # Defer EndFrame handling until after the bot turn is finished
         if isinstance(frame, EndFrame):
-            if self._bot_is_speaking:
+            if self._bot_is_responding:
                 logger.debug("Deferring handling EndFrame until bot turn is finished")
                 self._end_frame_pending_bot_turn_finished = frame
                 return
@@ -829,22 +915,13 @@ class GeminiLiveLLMService(LLMService):
 
         if isinstance(frame, TranscriptionFrame):
             await self.push_frame(frame, direction)
-        elif isinstance(frame, OpenAILLMContextFrame):
-            context: GeminiLiveContext = GeminiLiveContext.upgrade(frame.context)
-            # For now, we'll only trigger inference here when either:
-            #   1. We have not seen a context frame before
-            #   2. The last message is a tool call result
-            if not self._context:
-                self._context = context
-                if frame.context.tools:
-                    self._tools = frame.context.tools
-                await self._create_initial_response()
-            elif context.messages and context.messages[-1].get("role") == "tool":
-                # Support just one tool call per context frame for now
-                tool_result_message = context.messages[-1]
-                await self._tool_result(tool_result_message)
-        elif isinstance(frame, LLMContextFrame):
-            raise NotImplementedError("Universal LLMContext is not yet supported for Gemini Live.")
+        elif isinstance(frame, (LLMContextFrame, OpenAILLMContextFrame)):
+            context = (
+                frame.context
+                if isinstance(frame, LLMContextFrame)
+                else LLMContext.from_openai_context(frame.context)
+            )
+            await self._handle_context(context)
         elif isinstance(frame, InputTextRawFrame):
             await self._send_user_text(frame.text)
             await self.push_frame(frame, direction)
@@ -883,13 +960,48 @@ class GeminiLiveLLMService(LLMService):
         else:
             await self.push_frame(frame, direction)
 
-    async def _set_bot_is_speaking(self, speaking: bool):
-        if self._bot_is_speaking == speaking:
+    async def _handle_context(self, context: LLMContext):
+        if not self._context:
+            # We got our initial context
+            self._context = context
+            if context.tools:
+                self._tools = context.tools
+            # Initialize our bookkeeping of already-completed tool calls in
+            # the context
+            await self._process_completed_function_calls(send_new_results=False)
+            await self._create_initial_response()
+        else:
+            # We got an updated context.
+            # This may contain a new user message or tool call result.
+            self._context = context
+            # Send results for newly-completed function calls, if any.
+            await self._process_completed_function_calls(send_new_results=True)
+
+    async def _process_completed_function_calls(self, send_new_results: bool):
+        # Check for set of completed function calls in the context
+        adapter: GeminiLLMAdapter = self.get_llm_adapter()
+        messages = adapter.get_llm_invocation_params(self._context).get("messages", [])
+        for message in messages:
+            if message.parts:
+                for part in message.parts:
+                    if part.function_response:
+                        tool_call_id = part.function_response.id
+                        tool_name = part.function_response.name
+                        if tool_call_id and tool_call_id not in self._completed_tool_calls:
+                            # Found a newly-completed function call - send the result to the service
+                            if send_new_results:
+                                await self._tool_result(
+                                    tool_call_id, tool_name, part.function_response.response
+                                )
+                            self._completed_tool_calls.add(tool_call_id)
+
+    async def _set_bot_is_responding(self, responding: bool):
+        if self._bot_is_responding == responding:
             return
 
-        self._bot_is_speaking = speaking
+        self._bot_is_responding = responding
 
-        if not self._bot_is_speaking and self._end_frame_pending_bot_turn_finished:
+        if not self._bot_is_responding and self._end_frame_pending_bot_turn_finished:
             await self.queue_frame(self._end_frame_pending_bot_turn_finished)
             self._end_frame_pending_bot_turn_finished = None
 
@@ -1116,6 +1228,7 @@ class GeminiLiveLLMService(LLMService):
             if self._session:
                 await self._session.close()
                 self._session = None
+            self._completed_tool_calls = set()
             self._disconnecting = False
         except Exception as e:
             logger.error(f"{self} error disconnecting: {e}")
@@ -1195,7 +1308,8 @@ class GeminiLiveLLMService(LLMService):
             self._run_llm_when_session_ready = True
             return
 
-        messages = self._context.get_messages_for_initializing_history()
+        adapter: GeminiLLMAdapter = self.get_llm_adapter()
+        messages = adapter.get_llm_invocation_params(self._context).get("messages", [])
         if not messages:
             return
 
@@ -1223,8 +1337,9 @@ class GeminiLiveLLMService(LLMService):
 
         # Create a throwaway context just for the purpose of getting messages
         # in the right format
-        context = GeminiLiveContext.upgrade(OpenAILLMContext(messages=messages_list))
-        messages = context.get_messages_for_initializing_history()
+        context = LLMContext(messages=messages_list)
+        adapter: GeminiLLMAdapter = self.get_llm_adapter()
+        messages = adapter.get_llm_invocation_params(context).get("messages", [])
 
         if not messages:
             return
@@ -1239,17 +1354,16 @@ class GeminiLiveLLMService(LLMService):
             await self._handle_send_error(e)
 
     @traced_gemini_live(operation="llm_tool_result")
-    async def _tool_result(self, tool_result_message):
+    async def _tool_result(
+        self, tool_call_id: str, tool_name: str, tool_result_message: Dict[str, Any]
+    ):
         """Send tool result back to the API."""
         if self._disconnecting or not self._session:
             return
 
         # For now we're shoving the name into the tool_call_id field, so this
         # will work until we revisit that.
-        id = tool_result_message.get("tool_call_id")
-        name = tool_result_message.get("tool_call_name")
-        result = json.loads(tool_result_message.get("content") or "")
-        response = FunctionResponse(name=name, id=id, response=result)
+        response = FunctionResponse(name=tool_name, id=tool_call_id, response=tool_result_message)
 
         try:
             await self._session.send_tool_response(function_responses=response)
@@ -1277,7 +1391,10 @@ class GeminiLiveLLMService(LLMService):
         # part.text is added when `modalities` is set to TEXT; otherwise, it's None
         text = part.text
         if text:
-            if not self._bot_text_buffer:
+            if not self._bot_is_responding:
+                # Update bot responding state and send service start frame
+                # (AUDIO modality case)
+                await self._set_bot_is_responding(True)
                 await self.push_frame(LLMFullResponseStartFrame())
 
             self._bot_text_buffer += text
@@ -1288,6 +1405,8 @@ class GeminiLiveLLMService(LLMService):
         if msg.server_content and msg.server_content.grounding_metadata:
             self._accumulated_grounding_metadata = msg.server_content.grounding_metadata
 
+        # If we have no audio, stop here.
+        # All logic below this point pertains to the AUDIO modality.
         inline_data = part.inline_data
         if not inline_data:
             return
@@ -1313,8 +1432,10 @@ class GeminiLiveLLMService(LLMService):
         if not audio:
             return
 
-        if not self._bot_is_speaking:
-            await self._set_bot_is_speaking(True)
+        # Update bot responding state and send service start frames
+        # (AUDIO modality case)
+        if not self._bot_is_responding:
+            await self._set_bot_is_responding(True)
             await self.push_frame(TTSStartedFrame())
             await self.push_frame(LLMFullResponseStartFrame())
 
@@ -1354,7 +1475,6 @@ class GeminiLiveLLMService(LLMService):
     @traced_gemini_live(operation="llm_response")
     async def _handle_msg_turn_complete(self, message: LiveServerMessage):
         """Handle the turn complete message."""
-        await self._set_bot_is_speaking(False)
         text = self._bot_text_buffer
 
         # Trace the complete LLM response (this will be handled by the decorator)
@@ -1373,13 +1493,15 @@ class GeminiLiveLLMService(LLMService):
         self._search_result_buffer = ""
         self._accumulated_grounding_metadata = None
 
-        # Only push the TTSStoppedFrame if the bot is outputting audio
-        # when text is found, modalities is set to TEXT and no audio
-        # is produced.
-        if not text:
-            await self.push_frame(TTSStoppedFrame())
-
-        await self.push_frame(LLMFullResponseEndFrame())
+        if self._bot_is_responding:
+            await self._set_bot_is_responding(False)
+            if not text:
+                # AUDIO modality case
+                await self.push_frame(TTSStoppedFrame())
+                await self.push_frame(LLMFullResponseEndFrame())
+            else:
+                # TEXT modality case
+                await self.push_frame(LLMFullResponseEndFrame())
 
     @traced_stt
     async def _handle_user_transcription(
@@ -1442,8 +1564,8 @@ class GeminiLiveLLMService(LLMService):
             return
 
         # This is the output transcription text when modalities is set to AUDIO.
-        # In this case, we push LLMTextFrame and TTSTextFrame to be handled by the
-        # downstream assistant context aggregator.
+        # In this case, we push TTSTextFrame to be handled by the downstream
+        # assistant context aggregator.
         text = message.server_content.output_transcription.text
 
         if not text:
@@ -1458,7 +1580,17 @@ class GeminiLiveLLMService(LLMService):
         # Collect text for tracing
         self._llm_output_buffer += text
 
-        await self.push_frame(LLMTextFrame(text=text))
+        # NOTE: Shoot. When using Vertex AI, output transcription messages
+        # arrive *before* the model_turn messages with audio, so we need to
+        # handle sending TTSStartedFrame and LLMFullResponseStartFrame here as
+        # well. These messages also contain much *more* text (it looks further
+        # ahead). That means that on an interruption our recorded context will
+        # contain some text that was actually never spoken.
+        if not self._bot_is_responding:
+            await self._set_bot_is_responding(True)
+            await self.push_frame(TTSStartedFrame())
+            await self.push_frame(LLMFullResponseStartFrame())
+
         await self.push_frame(TTSTextFrame(text=text))
 
     async def _handle_msg_grounding_metadata(self, message: LiveServerMessage):
@@ -1557,26 +1689,26 @@ class GeminiLiveLLMService(LLMService):
         *,
         user_params: LLMUserAggregatorParams = LLMUserAggregatorParams(),
         assistant_params: LLMAssistantAggregatorParams = LLMAssistantAggregatorParams(),
-    ) -> GeminiLiveContextAggregatorPair:
+    ) -> LLMContextAggregatorPair:
         """Create an instance of GeminiLiveContextAggregatorPair from an OpenAILLMContext.
 
         Constructor keyword arguments for both the user and assistant aggregators can be provided.
 
+        NOTE: this method exists only for backward compatibility. New code
+        should instead do:
+            context = LLMContext(...)
+            context_aggregator = LLMContextAggregatorPair(context)
+
         Args:
             context: The LLM context to use.
             user_params: User aggregator parameters. Defaults to LLMUserAggregatorParams().
             assistant_params: Assistant aggregator parameters. Defaults to LLMAssistantAggregatorParams().
 
         Returns:
-            GeminiLiveContextAggregatorPair: A pair of context
-            aggregators, one for the user and one for the assistant,
-            encapsulated in an GeminiLiveContextAggregatorPair.
+            A pair of user and assistant context aggregators.
         """
-        context.set_llm_adapter(self.get_llm_adapter())
-
-        GeminiLiveContext.upgrade(context)
-        user = GeminiLiveUserContextAggregator(context, params=user_params)
-
+        context = LLMContext.from_openai_context(context)
         assistant_params.expect_stripped_words = False
-        assistant = GeminiLiveAssistantContextAggregator(context, params=assistant_params)
-        return GeminiLiveContextAggregatorPair(_user=user, _assistant=assistant)
+        return LLMContextAggregatorPair(
+            context, user_params=user_params, assistant_params=assistant_params
+        )

src/pipecat/services/google/llm.py

@@ -1034,6 +1034,23 @@ class GoogleLLMService(LLMService):
         if context:
             await self._process_context(context)
 
+    async def stop(self, frame):
+        """Override stop to gracefully close the client."""
+        await super().stop(frame)
+        await self._close_client()
+
+    async def cancel(self, frame):
+        """Override cancel to gracefully close the client."""
+        await super().cancel(frame)
+        await self._close_client()
+
+    async def _close_client(self):
+        try:
+            await self._client.aio.aclose()
+        except Exception:
+            # Do nothing - we're shutting down anyway
+            pass
+
     def create_context_aggregator(
         self,
         context: OpenAILLMContext,

src/pipecat/services/google/stt.py

@@ -730,6 +730,8 @@ class GoogleSTTService(STTService):
         self._request_queue = asyncio.Queue()
         self._streaming_task = self.create_task(self._stream_audio())
 
+        await self._call_event_handler("on_connected")
+
     async def _disconnect(self):
         """Clean up streaming recognition resources."""
         if self._streaming_task:
@@ -737,6 +739,8 @@ class GoogleSTTService(STTService):
             await self.cancel_task(self._streaming_task)
             self._streaming_task = None
 
+        await self._call_event_handler("on_disconnected")
+
     async def _request_generator(self):
         """Generates requests for the streaming recognize method."""
         recognizer_path = f"projects/{self._project_id}/locations/{self._location}/recognizers/_"

src/pipecat/services/hume/tts.py

@@ -184,11 +184,15 @@ class HumeTTSService(TTSService):
             # Hume emits mono PCM at 48 kHz; downstream can resample if needed.
             # We buffer audio bytes before sending to prevent glitches.
             self._audio_bytes = b""
+
+            # Use version "2" by default if no description is provided
+            # Version "1" is needed when description is used
+            version = "1" if self._params.description is not None else "2"
             async for chunk in self._client.tts.synthesize_json_streaming(
                 utterances=[utterance],
                 format=pcm_fmt,
                 instant_mode=True,
-                version="2",
+                version=version,
             ):
                 audio_b64 = getattr(chunk, "audio", None)
                 if not audio_b64:

src/pipecat/services/lmnt/tts.py

@@ -222,6 +222,7 @@ class LmntTTSService(InterruptibleTTSService):
             # Send initialization message
             await self._websocket.send(json.dumps(init_msg))
 
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -243,6 +244,7 @@ class LmntTTSService(InterruptibleTTSService):
         finally:
             self._started = False
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         """Get the WebSocket connection if available."""

src/pipecat/services/neuphonic/tts.py

@@ -293,6 +293,8 @@ class NeuphonicTTSService(InterruptibleTTSService):
             headers = {"x-api-key": self._api_key}
 
             self._websocket = await websocket_connect(url, additional_headers=headers)
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -311,6 +313,7 @@ class NeuphonicTTSService(InterruptibleTTSService):
         finally:
             self._started = False
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     async def _receive_messages(self):
         """Receive and process messages from Neuphonic WebSocket."""

src/pipecat/services/openai/realtime/context.py

@@ -4,7 +4,85 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""OpenAI Realtime LLM context and aggregator implementations."""
+"""OpenAI Realtime LLM context and aggregator implementations.
+
+.. deprecated:: 0.0.92
+    OpenAI Realtime no longer uses types from this module under the hood.
+    It now uses `LLMContext` and `LLMContextAggregatorPair`.
+    Using the new patterns should allow you to not need types from this module.
+
+    BEFORE:
+    ```
+    # Setup
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # Context aggregator type
+    context_aggregator: OpenAIContextAggregatorPair
+
+    # Context frame type
+    frame: OpenAILLMContextFrame
+
+    # Context type
+    context: OpenAIRealtimeLLMContext
+    # or
+    context: OpenAILLMContext
+    ```
+
+    AFTER:
+    ```
+    # Setup
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    # Context aggregator type
+    context_aggregator: LLMContextAggregatorPair
+
+    # Context frame type
+    frame: LLMContextFrame
+
+    # Context type
+    context: LLMContext
+    ```
+"""
+
+import warnings
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai.realtime.llm (or "
+        "pipecat.services.openai_realtime.llm) are deprecated. \n"
+        "OpenAI Realtime no longer uses types from this module under the hood. \n"
+        "It now uses `LLMContext` and `LLMContextAggregatorPair`. \n"
+        "Using the new patterns should allow you to not need types from this module.\n\n"
+        "BEFORE:\n"
+        "```\n"
+        "# Setup\n"
+        "context = OpenAILLMContext(messages, tools)\n"
+        "context_aggregator = llm.create_context_aggregator(context)\n\n"
+        "# Context aggregator type\n"
+        "context_aggregator: OpenAIContextAggregatorPair\n\n"
+        "# Context frame type\n"
+        "frame: OpenAILLMContextFrame\n\n"
+        "# Context type\n"
+        "context: OpenAIRealtimeLLMContext\n"
+        "# or\n"
+        "context: OpenAILLMContext\n\n"
+        "```\n\n"
+        "AFTER:\n"
+        "```\n"
+        "# Setup\n"
+        "context = LLMContext(messages, tools)\n"
+        "context_aggregator = LLMContextAggregatorPair(context)\n\n"
+        "# Context aggregator type\n"
+        "context_aggregator: LLMContextAggregatorPair\n\n"
+        "# Context frame type\n"
+        "frame: LLMContextFrame\n\n"
+        "# Context type\n"
+        "context: LLMContext\n\n"
+        "```\n",
+    )
 
 import copy
 import json

src/pipecat/services/openai/realtime/frames.py

@@ -4,7 +4,28 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""Custom frame types for OpenAI Realtime API integration."""
+"""Custom frame types for OpenAI Realtime API integration.
+
+.. deprecated:: 0.0.92
+    OpenAI Realtime no longer uses types from this module under the hood.
+
+    It now works more like most LLM services in Pipecat, relying on updates to
+    its context, pushed by context aggregators, to update its internal state.
+
+    Listen for `LLMContextFrame`s for context updates.
+"""
+
+import warnings
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai.realtime.frames are deprecated. \n"
+        "OpenAI Realtime no longer uses types from this module under the hood. \n\n"
+        "It now works more like other LLM services in Pipecat, relying on updates to \n"
+        "its context, pushed by context aggregators, to update its internal state.\n\n"
+        "Listen for `LLMContextFrame`s for context updates.\n"
+    )
 
 from dataclasses import dataclass
 from typing import TYPE_CHECKING

src/pipecat/services/openai/realtime/llm.py

@@ -14,7 +14,9 @@ from typing import Optional
 
 from loguru import logger
 
-from pipecat.adapters.services.open_ai_realtime_adapter import OpenAIRealtimeLLMAdapter
+from pipecat.adapters.services.open_ai_realtime_adapter import (
+    OpenAIRealtimeLLMAdapter,
+)
 from pipecat.frames.frames import (
     BotStoppedSpeakingFrame,
     CancelFrame,
@@ -41,10 +43,12 @@ from pipecat.frames.frames import (
     UserStoppedSpeakingFrame,
 )
 from pipecat.metrics.metrics import LLMTokenUsage
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response import (
     LLMAssistantAggregatorParams,
     LLMUserAggregatorParams,
 )
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
     OpenAILLMContextFrame,
@@ -57,12 +61,6 @@ from pipecat.utils.time import time_now_iso8601
 from pipecat.utils.tracing.service_decorators import traced_openai_realtime, traced_stt
 
 from . import events
-from .context import (
-    OpenAIRealtimeAssistantContextAggregator,
-    OpenAIRealtimeLLMContext,
-    OpenAIRealtimeUserContextAggregator,
-)
-from .frames import RealtimeFunctionCallResultFrame, RealtimeMessagesUpdateFrame
 
 try:
     from websockets.asyncio.client import connect as websocket_connect
@@ -108,22 +106,39 @@ class OpenAIRealtimeLLMService(LLMService):
         base_url: str = "wss://api.openai.com/v1/realtime",
         session_properties: Optional[events.SessionProperties] = None,
         start_audio_paused: bool = False,
-        send_transcription_frames: bool = True,
+        send_transcription_frames: Optional[bool] = None,
         **kwargs,
     ):
         """Initialize the OpenAI Realtime LLM service.
 
         Args:
             api_key: OpenAI API key for authentication.
-            model: OpenAI model name. Defaults to "gpt-4o-realtime-preview-2025-06-03".
+            model: OpenAI model name. Defaults to "gpt-realtime".
             base_url: WebSocket base URL for the realtime API.
                 Defaults to "wss://api.openai.com/v1/realtime".
             session_properties: Configuration properties for the realtime session.
                 If None, uses default SessionProperties.
             start_audio_paused: Whether to start with audio input paused. Defaults to False.
-            send_transcription_frames: Whether to emit transcription frames. Defaults to True.
+            send_transcription_frames: Whether to emit transcription frames.
+
+                .. deprecated:: 0.0.92
+                    This parameter is deprecated and will be removed in a future version.
+                    Transcription frames are always sent.
+
             **kwargs: Additional arguments passed to parent LLMService.
         """
+        if send_transcription_frames is not None:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "`send_transcription_frames` is deprecated and will be removed in a future version. "
+                    "Transcription frames are always sent.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+
         full_url = f"{base_url}?model={model}"
         super().__init__(base_url=full_url, **kwargs)
 
@@ -135,10 +150,11 @@ class OpenAIRealtimeLLMService(LLMService):
             session_properties or events.SessionProperties()
         )
         self._audio_input_paused = start_audio_paused
-        self._send_transcription_frames = send_transcription_frames
         self._websocket = None
         self._receive_task = None
-        self._context = None
+        self._context: LLMContext = None
+
+        self._llm_needs_conversation_setup = True
 
         self._disconnecting = False
         self._api_session_ready = False
@@ -148,8 +164,8 @@ class OpenAIRealtimeLLMService(LLMService):
         self._current_audio_response = None
 
         self._messages_added_manually = {}
-        self._user_and_response_message_tuple = None
         self._pending_function_calls = {}  # Track function calls by call_id
+        self._completed_tool_calls = set()
 
         self._register_event_handler("on_conversation_item_created")
         self._register_event_handler("on_conversation_item_updated")
@@ -347,22 +363,13 @@ class OpenAIRealtimeLLMService(LLMService):
 
         if isinstance(frame, TranscriptionFrame):
             pass
-        elif isinstance(frame, OpenAILLMContextFrame):
-            context: OpenAIRealtimeLLMContext = OpenAIRealtimeLLMContext.upgrade_to_realtime(
+        elif isinstance(frame, (LLMContextFrame, OpenAILLMContextFrame)):
+            context = (
                 frame.context
+                if isinstance(frame, LLMContextFrame)
+                else LLMContext.from_openai_context(frame.context)
             )
-            if not self._context:
-                self._context = context
-            elif frame.context is not self._context:
-                # If the context has changed, reset the conversation
-                self._context = context
-                await self.reset_conversation()
-            # Run the LLM at next opportunity
-            await self._create_response()
-        elif isinstance(frame, LLMContextFrame):
-            raise NotImplementedError(
-                "Universal LLMContext is not yet supported for OpenAI Realtime."
-            )
+            await self._handle_context(context)
         elif isinstance(frame, InputAudioRawFrame):
             if not self._audio_input_paused:
                 await self._send_user_audio(frame)
@@ -376,29 +383,33 @@ class OpenAIRealtimeLLMService(LLMService):
             await self._handle_bot_stopped_speaking()
         elif isinstance(frame, LLMMessagesAppendFrame):
             await self._handle_messages_append(frame)
-        elif isinstance(frame, RealtimeMessagesUpdateFrame):
-            self._context = frame.context
         elif isinstance(frame, LLMUpdateSettingsFrame):
             self._session_properties = events.SessionProperties(**frame.settings)
             await self._update_settings()
         elif isinstance(frame, LLMSetToolsFrame):
             await self._update_settings()
-        elif isinstance(frame, RealtimeFunctionCallResultFrame):
-            await self._handle_function_call_result(frame.result_frame)
 
         await self.push_frame(frame, direction)
 
+    async def _handle_context(self, context: LLMContext):
+        if not self._context:
+            # We got our initial context
+            self._context = context
+            # Initialize our bookkeeping of already-completed tool calls in
+            # the context
+            await self._process_completed_function_calls(send_new_results=False)
+            # Run the LLM at next opportunity
+            await self._create_response()
+        else:
+            # We got an updated context.
+            # This may contain a new user message or tool call result.
+            self._context = context
+            # Send results for newly-completed function calls, if any.
+            await self._process_completed_function_calls(send_new_results=True)
+
     async def _handle_messages_append(self, frame):
         logger.error("!!! NEED TO IMPLEMENT MESSAGES APPEND")
 
-    async def _handle_function_call_result(self, frame):
-        item = events.ConversationItem(
-            type="function_call_output",
-            call_id=frame.tool_call_id,
-            output=json.dumps(frame.result),
-        )
-        await self.send_client_event(events.ConversationItemCreateEvent(item=item))
-
     #
     # websocket communication
     #
@@ -439,16 +450,21 @@ class OpenAIRealtimeLLMService(LLMService):
             if self._receive_task:
                 await self.cancel_task(self._receive_task, timeout=1.0)
                 self._receive_task = None
+            self._completed_tool_calls = set()
             self._disconnecting = False
         except Exception as e:
             logger.error(f"{self} error disconnecting: {e}")
 
     async def _ws_send(self, realtime_message):
         try:
-            if self._websocket:
+            if not self._disconnecting and self._websocket:
                 await self._websocket.send(json.dumps(realtime_message))
         except Exception as e:
-            if self._disconnecting:
+            if self._disconnecting or not self._websocket:
+                # We're in the process of disconnecting.
+                # (If not self._websocket, that could indicate that we
+                # somehow *started* the websocket send attempt while we still
+                # had a connection)
                 return
             logger.error(f"Error sending message to websocket: {e}")
             # In server-to-server contexts, a WebSocket error should be quite rare. Given how hard
@@ -459,13 +475,20 @@ class OpenAIRealtimeLLMService(LLMService):
 
     async def _update_settings(self):
         settings = self._session_properties
-        # tools given in the context override the tools in the session properties
-        if self._context and self._context.tools:
-            settings.tools = self._context.tools
-        # instructions in the context come from an initial "system" message in the
-        # messages list, and override instructions in the session properties
-        if self._context and self._context._session_instructions:
-            settings.instructions = self._context._session_instructions
+
+        if self._context:
+            adapter: OpenAIRealtimeLLMAdapter = self.get_llm_adapter()
+            llm_invocation_params = adapter.get_llm_invocation_params(self._context)
+
+            # tools given in the context override the tools in the session properties
+            if llm_invocation_params["tools"]:
+                settings.tools = llm_invocation_params["tools"]
+
+            # instructions in the context come from an initial "system" message in the
+            # messages list, and override instructions in the session properties
+            if llm_invocation_params["system_instruction"]:
+                settings.instructions = llm_invocation_params["system_instruction"]
+
         await self.send_client_event(events.SessionUpdateEvent(session=settings))
 
     #
@@ -571,12 +594,7 @@ class OpenAIRealtimeLLMService(LLMService):
             del self._messages_added_manually[evt.item.id]
             return
 
-        if evt.item.role == "user":
-            # We need to wait for completion of both user message and response message. Then we'll
-            # add both to the context. User message is complete when we have a "transcript" field
-            # that is not None. Response message is complete when we get a "response.done" event.
-            self._user_and_response_message_tuple = (evt.item, {"done": False, "output": []})
-        elif evt.item.role == "assistant":
+        if evt.item.role == "assistant":
             self._current_assistant_response = evt.item
             await self.push_frame(LLMFullResponseStartFrame())
 
@@ -587,11 +605,11 @@ class OpenAIRealtimeLLMService(LLMService):
         # For now, no additional logic needed beyond the event handler call
 
     async def _handle_evt_input_audio_transcription_delta(self, evt):
-        if self._send_transcription_frames:
-            await self.push_frame(
-                # no way to get a language code?
-                InterimTranscriptionFrame(evt.delta, "", time_now_iso8601(), result=evt)
-            )
+        await self.push_frame(
+            # no way to get a language code?
+            InterimTranscriptionFrame(evt.delta, "", time_now_iso8601(), result=evt),
+            direction=FrameDirection.UPSTREAM,
+        )
 
     @traced_stt
     async def _handle_user_transcription(
@@ -608,22 +626,12 @@ class OpenAIRealtimeLLMService(LLMService):
         """
         await self._call_event_handler("on_conversation_item_updated", evt.item_id, None)
 
-        if self._send_transcription_frames:
-            await self.push_frame(
-                # no way to get a language code?
-                TranscriptionFrame(evt.transcript, "", time_now_iso8601(), result=evt)
-            )
-            await self._handle_user_transcription(evt.transcript, True, Language.EN)
-        pair = self._user_and_response_message_tuple
-        if pair:
-            user, assistant = pair
-            user.content[0].transcript = evt.transcript
-            if assistant["done"]:
-                self._user_and_response_message_tuple = None
-                self._context.add_user_content_item_as_message(user)
-        else:
-            # User message without preceding conversation.item.created. Bug?
-            logger.warning(f"Transcript for unknown user message: {evt}")
+        await self.push_frame(
+            # no way to get a language code?
+            TranscriptionFrame(evt.transcript, "", time_now_iso8601(), result=evt),
+            FrameDirection.UPSTREAM,
+        )
+        await self._handle_user_transcription(evt.transcript, True, Language.EN)
 
     async def _handle_conversation_item_retrieved(self, evt: events.ConversationItemRetrieved):
         futures = self._retrieve_conversation_item_futures.pop(evt.item.id, None)
@@ -653,26 +661,17 @@ class OpenAIRealtimeLLMService(LLMService):
         # response content
         for item in evt.response.output:
             await self._call_event_handler("on_conversation_item_updated", item.id, item)
-        pair = self._user_and_response_message_tuple
-        if pair:
-            user, assistant = pair
-            assistant["done"] = True
-            assistant["output"] = evt.response.output
-            if user.content[0].transcript is not None:
-                self._user_and_response_message_tuple = None
-                self._context.add_user_content_item_as_message(user)
-        else:
-            # Response message without preceding user message (standalone response)
-            # Function calls in this response were already processed immediately when arguments were complete
-            logger.debug(f"Handling standalone response: {evt.response.id}")
 
     async def _handle_evt_text_delta(self, evt):
+        # We receive text deltas (as opposed to audio transcript deltas) when
+        # the output modality is "text"
         if evt.delta:
             await self.push_frame(LLMTextFrame(evt.delta))
 
     async def _handle_evt_audio_transcript_delta(self, evt):
+        # We receive audio transcript deltas (as opposed to text deltas) when
+        # the output modality is "audio" (the default)
         if evt.delta:
-            await self.push_frame(LLMTextFrame(evt.delta))
             await self.push_frame(TTSTextFrame(evt.delta))
 
     async def _handle_evt_function_call_arguments_done(self, evt):
@@ -760,9 +759,11 @@ class OpenAIRealtimeLLMService(LLMService):
         """
         logger.debug("Resetting conversation")
         await self._disconnect()
-        if self._context:
-            self._context.llm_needs_settings_update = True
-            self._context.llm_needs_initial_messages = True
+
+        # Prepare to setup server-side conversation from local context again
+        self._llm_needs_conversation_setup = True
+        await self._process_completed_function_calls(send_new_results=False)
+
         await self._connect()
 
     @traced_openai_realtime(operation="llm_request")
@@ -771,19 +772,29 @@ class OpenAIRealtimeLLMService(LLMService):
             self._run_llm_when_api_session_ready = True
             return
 
-        if self._context.llm_needs_initial_messages:
-            messages = self._context.get_messages_for_initializing_history()
+        adapter: OpenAIRealtimeLLMAdapter = self.get_llm_adapter()
+
+        # Configure the LLM for this session if needed
+        if self._llm_needs_conversation_setup:
+            logger.debug(
+                f"Setting up conversation on OpenAI Realtime LLM service with initial messages: {adapter.get_messages_for_logging(self._context)}"
+            )
+
+            # Send initial messages
+            llm_invocation_params = adapter.get_llm_invocation_params(self._context)
+            messages = llm_invocation_params["messages"]
             for item in messages:
                 evt = events.ConversationItemCreateEvent(item=item)
                 self._messages_added_manually[evt.item.id] = True
                 await self.send_client_event(evt)
-            self._context.llm_needs_initial_messages = False
 
-        if self._context.llm_needs_settings_update:
+            # Send new settings if needed
             await self._update_settings()
-            self._context.llm_needs_settings_update = False
 
-        logger.debug(f"Creating response: {self._context.get_messages_for_logging()}")
+            # We're done configuring the LLM for this session
+            self._llm_needs_conversation_setup = False
+
+        logger.debug(f"Creating response")
 
         await self.push_frame(LLMFullResponseStartFrame())
         await self.start_processing_metrics()
@@ -794,19 +805,50 @@ class OpenAIRealtimeLLMService(LLMService):
             )
         )
 
+    async def _process_completed_function_calls(self, send_new_results: bool):
+        # Check for set of completed function calls in the context
+        sent_new_result = False
+        for message in self._context.get_messages():
+            if message.get("role") and message.get("content") != "IN_PROGRESS":
+                tool_call_id = message.get("tool_call_id")
+                if tool_call_id and tool_call_id not in self._completed_tool_calls:
+                    # Found a newly-completed function call - send the result to the service
+                    if send_new_results:
+                        sent_new_result = True
+                        await self._send_tool_result(tool_call_id, message.get("content"))
+                    self._completed_tool_calls.add(tool_call_id)
+
+        # If we reported any new tool call results to the service, trigger
+        # another response
+        if sent_new_result:
+            await self._create_response()
+
     async def _send_user_audio(self, frame):
         payload = base64.b64encode(frame.audio).decode("utf-8")
         await self.send_client_event(events.InputAudioBufferAppendEvent(audio=payload))
 
+    async def _send_tool_result(self, tool_call_id: str, result: str):
+        item = events.ConversationItem(
+            type="function_call_output",
+            call_id=tool_call_id,
+            output=json.dumps(result),
+        )
+        await self.send_client_event(events.ConversationItemCreateEvent(item=item))
+
     def create_context_aggregator(
         self,
         context: OpenAILLMContext,
         *,
         user_params: LLMUserAggregatorParams = LLMUserAggregatorParams(),
         assistant_params: LLMAssistantAggregatorParams = LLMAssistantAggregatorParams(),
-    ) -> OpenAIContextAggregatorPair:
+    ) -> LLMContextAggregatorPair:
         """Create an instance of OpenAIContextAggregatorPair from an OpenAILLMContext.
 
+        NOTE: this method exists only for backward compatibility. New code
+        should instead do:
+            context = LLMContext(...)
+            context_aggregator = LLMContextAggregatorPair(context)
+
         Constructor keyword arguments for both the user and assistant aggregators can be provided.
 
         Args:
@@ -819,11 +861,41 @@ class OpenAIRealtimeLLMService(LLMService):
             the user and one for the assistant, encapsulated in an
             OpenAIContextAggregatorPair.
         """
-        context.set_llm_adapter(self.get_llm_adapter())
-
-        OpenAIRealtimeLLMContext.upgrade_to_realtime(context)
-        user = OpenAIRealtimeUserContextAggregator(context, params=user_params)
+        # Log warning about transcription frame direction change in 0.0.92.
+        # We're putting this warning here rather than in the constructor so
+        # that it shows up for folks who haven't updated their code at all
+        # since 0.0.92, gives them a way to acknowledge and dismiss the
+        # warning, and encourages adoption of a new preferred pattern.
+        logger.warning(
+            "As of version 0.0.92, TranscriptionFrames and InterimTranscriptionFrames "
+            "now go upstream from OpenAIRealtimeLLMService, so if you're using "
+            "TranscriptProcessor, say, you'll want to adjust accordingly:\n\n"
+            "pipeline = Pipeline(\n"
+            "  [\n"
+            "    transport.input(),\n"
+            "    context_aggregator.user(),\n\n"
+            "    # BEFORE\n"
+            "    llm,\n"
+            "    transcript.user(),\n\n"
+            "    # AFTER\n"
+            "    transcript.user(),\n"
+            "    llm,\n\n"
+            "    transport.output(),\n"
+            "    transcript.assistant(),\n"
+            "    context_aggregator.assistant(),\n"
+            "  ]\n"
+            ")\n\n"
+            "Also, LLMTextFrames are no longer pushed from "
+            "OpenAIRealtimeLLMService when it's configured with "
+            "output_modalities=['audio']. Listen for TTSTextFrames instead.\n\n"
+            "Once you've made the appropriate changes (if needed), you can "
+            "dismiss this warning by updating to the new context-setup pattern:\n\n"
+            "  context = LLMContext(messages, tools)\n"
+            "  context_aggregator = LLMContextAggregatorPair(context)\n"
+        )
 
+        context = LLMContext.from_openai_context(context)
         assistant_params.expect_stripped_words = False
-        assistant = OpenAIRealtimeAssistantContextAggregator(context, params=assistant_params)
-        return OpenAIContextAggregatorPair(_user=user, _assistant=assistant)
+        return LLMContextAggregatorPair(
+            context, user_params=user_params, assistant_params=assistant_params
+        )

src/pipecat/services/openai/tts.py

@@ -14,6 +14,7 @@ from typing import AsyncGenerator, Dict, Literal, Optional
 
 from loguru import logger
 from openai import AsyncOpenAI, BadRequestError
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     ErrorFrame,
@@ -55,6 +56,17 @@ class OpenAITTSService(TTSService):
 
     OPENAI_SAMPLE_RATE = 24000  # OpenAI TTS always outputs at 24kHz
 
+    class InputParams(BaseModel):
+        """Input parameters for OpenAI TTS configuration.
+
+        Parameters:
+            instructions: Instructions to guide voice synthesis behavior.
+            speed: Voice speed control (0.25 to 4.0, default 1.0).
+        """
+
+        instructions: Optional[str] = None
+        speed: Optional[float] = None
+
     def __init__(
         self,
         *,
@@ -65,6 +77,7 @@ class OpenAITTSService(TTSService):
         sample_rate: Optional[int] = None,
         instructions: Optional[str] = None,
         speed: Optional[float] = None,
+        params: Optional[InputParams] = None,
         **kwargs,
     ):
         """Initialize OpenAI TTS service.
@@ -77,7 +90,11 @@ class OpenAITTSService(TTSService):
             sample_rate: Output audio sample rate in Hz. If None, uses OpenAI's default 24kHz.
             instructions: Optional instructions to guide voice synthesis behavior.
             speed: Voice speed control (0.25 to 4.0, default 1.0).
+            params: Optional synthesis controls (acting instructions, speed, ...).
             **kwargs: Additional keyword arguments passed to TTSService.
+
+                .. deprecated:: 0.0.91
+                        The `instructions` and `speed` parameters are deprecated, use `InputParams` instead.
         """
         if sample_rate and sample_rate != self.OPENAI_SAMPLE_RATE:
             logger.warning(
@@ -86,12 +103,26 @@ class OpenAITTSService(TTSService):
             )
         super().__init__(sample_rate=sample_rate, **kwargs)
 
-        self._speed = speed
         self.set_model_name(model)
         self.set_voice(voice)
-        self._instructions = instructions
         self._client = AsyncOpenAI(api_key=api_key, base_url=base_url)
 
+        if instructions or speed:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "The `instructions` and `speed` parameters are deprecated, use `InputParams` instead.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+
+        self._settings = {
+            "instructions": params.instructions if params else instructions,
+            "speed": params.speed if params else speed,
+        }
+
     def can_generate_metrics(self) -> bool:
         """Check if this service can generate processing metrics.
 
@@ -144,11 +175,11 @@ class OpenAITTSService(TTSService):
                 "response_format": "pcm",
             }
 
-            if self._instructions:
-                create_params["instructions"] = self._instructions
+            if self._settings["instructions"]:
+                create_params["instructions"] = self._settings["instructions"]
 
-            if self._speed:
-                create_params["speed"] = self._speed
+            if self._settings["speed"]:
+                create_params["speed"] = self._settings["speed"]
 
             async with self._client.audio.speech.with_streaming_response.create(
                 **create_params

src/pipecat/services/openai_realtime/context.py

@@ -4,18 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""OpenAI Realtime LLM context and aggregator implementations."""
+"""OpenAI Realtime LLM context and aggregator implementations.
 
-import warnings
+.. deprecated:: 0.0.91
+    OpenAI Realtime no longer uses types from this module under the hood.
+    It now uses `LLMContext` and `LLMContextAggregatorPair`.
+    Using the new patterns should allow you to not need types from this module.
+
+    See deprecation warning in pipecat.services.openai.realtime.context for
+    more details.
+"""
 
 from pipecat.services.openai.realtime.context import *
-
-with warnings.catch_warnings():
-    warnings.simplefilter("always")
-    warnings.warn(
-        "Types in pipecat.services.openai_realtime.context are deprecated. "
-        "Please use the equivalent types from "
-        "pipecat.services.openai.realtime.context instead.",
-        DeprecationWarning,
-        stacklevel=2,
-    )

src/pipecat/services/openai_realtime_beta/azure.py

@@ -70,7 +70,7 @@ class AzureRealtimeBetaLLMService(OpenAIRealtimeBetaLLMService):
                 # handle disconnections in the send/recv code paths.
                 return
 
-            logger.info(f"Connecting to {self.base_url}, api key: {self.api_key}")
+            logger.info(f"Connecting to {self.base_url}")
             self._websocket = await websocket_connect(
                 uri=self.base_url,
                 additional_headers={

src/pipecat/services/playht/tts.py

@@ -269,6 +269,8 @@ class PlayHTTTSService(InterruptibleTTSService):
                 raise ValueError("WebSocket URL is not a string")
 
             self._websocket = await websocket_connect(self._websocket_url)
+
+            await self._call_event_handler("on_connected")
         except ValueError as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -291,6 +293,7 @@ class PlayHTTTSService(InterruptibleTTSService):
         finally:
             self._request_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     async def _get_websocket_url(self):
         """Retrieve WebSocket URL from PlayHT API."""

src/pipecat/services/rime/tts.py

@@ -255,6 +255,8 @@ class RimeTTSService(AudioContextWordTTSService):
             url = f"{self._url}?{params}"
             headers = {"Authorization": f"Bearer {self._api_key}"}
             self._websocket = await websocket_connect(url, additional_headers=headers)
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -272,6 +274,7 @@ class RimeTTSService(AudioContextWordTTSService):
         finally:
             self._context_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         """Get active websocket connection or raise exception."""

src/pipecat/services/riva/stt.py

@@ -583,7 +583,9 @@ class RivaSegmentedSTTService(SegmentedSTTService):
             self._config.language_code = self._language
 
     @traced_stt
-    async def _handle_transcription(self, transcript: str, language: Optional[Language] = None):
+    async def _handle_transcription(
+        self, transcript: str, is_final: bool, language: Optional[Language] = None
+    ):
         """Handle a transcription result with tracing."""
         pass
 

src/pipecat/services/sarvam/tts.py

@@ -76,17 +76,29 @@ class SarvamHttpTTSService(TTSService):
 
     Example::
 
-        tts = SarvamTTSService(
+        tts = SarvamHttpTTSService(
             api_key="your-api-key",
             voice_id="anushka",
             model="bulbul:v2",
             aiohttp_session=session,
-            params=SarvamTTSService.InputParams(
+            params=SarvamHttpTTSService.InputParams(
                 language=Language.HI,
                 pitch=0.1,
                 pace=1.2
             )
         )
+
+        # For bulbul v3 beta with any speaker:
+        tts_v3 = SarvamHttpTTSService(
+            api_key="your-api-key",
+            voice_id="speaker_name",
+            model="bulbul:v3,
+            aiohttp_session=session,
+            params=SarvamHttpTTSService.InputParams(
+                language=Language.HI,
+                temperature=0.8
+            )
+        )
     """
 
     class InputParams(BaseModel):
@@ -105,6 +117,14 @@ class SarvamHttpTTSService(TTSService):
         pace: Optional[float] = Field(default=1.0, ge=0.3, le=3.0)
         loudness: Optional[float] = Field(default=1.0, ge=0.1, le=3.0)
         enable_preprocessing: Optional[bool] = False
+        temperature: Optional[float] = Field(
+            default=0.6,
+            ge=0.01,
+            le=1.0,
+            description="Controls the randomness of the output for bulbul v3 beta. "
+            "Lower values make the output more focused and deterministic, while "
+            "higher values make it more random. Range: 0.01 to 1.0. Default: 0.6.",
+        )
 
     def __init__(
         self,
@@ -124,7 +144,7 @@ class SarvamHttpTTSService(TTSService):
             api_key: Sarvam AI API subscription key.
             aiohttp_session: Shared aiohttp session for making requests.
             voice_id: Speaker voice ID (e.g., "anushka", "meera"). Defaults to "anushka".
-            model: TTS model to use ("bulbul:v1" or "bulbul:v2"). Defaults to "bulbul:v2".
+            model: TTS model to use ("bulbul:v2" or "bulbul:v3-beta" or "bulbul:v3"). Defaults to "bulbul:v2".
             base_url: Sarvam AI API base URL. Defaults to "https://api.sarvam.ai".
             sample_rate: Audio sample rate in Hz (8000, 16000, 22050, 24000). If None, uses default.
             params: Additional voice and preprocessing parameters. If None, uses defaults.
@@ -138,16 +158,32 @@ class SarvamHttpTTSService(TTSService):
         self._base_url = base_url
         self._session = aiohttp_session
 
+        # Build base settings common to all models
         self._settings = {
             "language": (
                 self.language_to_service_language(params.language) if params.language else "en-IN"
             ),
-            "pitch": params.pitch,
-            "pace": params.pace,
-            "loudness": params.loudness,
             "enable_preprocessing": params.enable_preprocessing,
         }
 
+        # Add model-specific parameters
+        if model in ("bulbul:v3-beta", "bulbul:v3"):
+            self._settings.update(
+                {
+                    "temperature": getattr(params, "temperature", 0.6),
+                    "model": model,
+                }
+            )
+        else:
+            self._settings.update(
+                {
+                    "pitch": params.pitch,
+                    "pace": params.pace,
+                    "loudness": params.loudness,
+                    "model": model,
+                }
+            )
+
         self.set_model_name(model)
         self.set_voice(voice_id)
 
@@ -275,6 +311,18 @@ class SarvamTTSService(InterruptibleTTSService):
                 pace=1.2
             )
         )
+
+        # For bulbul v3 beta with any speaker and temperature:
+        # Note: pace and loudness are not supported for bulbul v3 and bulbul v3 beta
+        tts_v3 = SarvamTTSService(
+            api_key="your-api-key",
+            voice_id="speaker_name",
+            model="bulbul:v3",
+            params=SarvamTTSService.InputParams(
+                language=Language.HI,
+                temperature=0.8
+            )
+        )
     """
 
     class InputParams(BaseModel):
@@ -310,6 +358,14 @@ class SarvamTTSService(InterruptibleTTSService):
         output_audio_codec: Optional[str] = "linear16"
         output_audio_bitrate: Optional[str] = "128k"
         language: Optional[Language] = Language.EN
+        temperature: Optional[float] = Field(
+            default=0.6,
+            ge=0.01,
+            le=1.0,
+            description="Controls the randomness of the output for bulbul v3 beta. "
+            "Lower values make the output more focused and deterministic, while "
+            "higher values make it more random. Range: 0.01 to 1.0. Default: 0.6.",
+        )
 
     def __init__(
         self,
@@ -318,7 +374,6 @@ class SarvamTTSService(InterruptibleTTSService):
         model: str = "bulbul:v2",
         voice_id: str = "anushka",
         url: str = "wss://api.sarvam.ai/text-to-speech/ws",
-        aiohttp_session: Optional[aiohttp.ClientSession] = None,
         aggregate_sentences: Optional[bool] = True,
         sample_rate: Optional[int] = None,
         params: Optional[InputParams] = None,
@@ -329,13 +384,9 @@ class SarvamTTSService(InterruptibleTTSService):
         Args:
             api_key: Sarvam API key for authenticating TTS requests.
             model: Identifier of the Sarvam speech model (default "bulbul:v2").
+                Supports "bulbul:v2", "bulbul:v3-beta" and "bulbul:v3".
             voice_id: Voice identifier for synthesis (default "anushka").
             url: WebSocket URL for connecting to the TTS backend (default production URL).
-            aiohttp_session: Optional shared aiohttp session. To maintain backward compatibility.
-
-                .. deprecated:: 0.0.81
-                    aiohttp_session is no longer used. This parameter will be removed in a future version.
-
             aggregate_sentences: Whether to merge multiple sentences into one audio chunk (default True).
             sample_rate: Desired sample rate for the output audio in Hz (overrides default if set).
             params: Optional input parameters to override global configuration.
@@ -356,30 +407,18 @@ class SarvamTTSService(InterruptibleTTSService):
             **kwargs,
         )
         params = params or SarvamTTSService.InputParams()
-        if aiohttp_session is not None:
-            import warnings
 
-            with warnings.catch_warnings():
-                warnings.simplefilter("always")
-                warnings.warn(
-                    "The 'aiohttp_session' parameter is deprecated and will be removed in a future version. ",
-                    DeprecationWarning,
-                    stacklevel=2,
-                )
         # WebSocket endpoint URL
         self._websocket_url = f"{url}?model={model}"
         self._api_key = api_key
         self.set_model_name(model)
         self.set_voice(voice_id)
-        # Configuration parameters
+        # Build base settings common to all models
         self._settings = {
             "target_language_code": (
                 self.language_to_service_language(params.language) if params.language else "en-IN"
             ),
-            "pitch": params.pitch,
-            "pace": params.pace,
             "speaker": voice_id,
-            "loudness": params.loudness,
             "speech_sample_rate": 0,
             "enable_preprocessing": params.enable_preprocessing,
             "min_buffer_size": params.min_buffer_size,
@@ -387,6 +426,24 @@ class SarvamTTSService(InterruptibleTTSService):
             "output_audio_codec": params.output_audio_codec,
             "output_audio_bitrate": params.output_audio_bitrate,
         }
+
+        # Add model-specific parameters
+        if model in ("bulbul:v3-beta", "bulbul:v3"):
+            self._settings.update(
+                {
+                    "temperature": getattr(params, "temperature", 0.6),
+                    "model": model,
+                }
+            )
+        else:
+            self._settings.update(
+                {
+                    "pitch": params.pitch,
+                    "pace": params.pace,
+                    "loudness": params.loudness,
+                    "model": model,
+                }
+            )
         self._started = False
 
         self._receive_task = None
@@ -525,6 +582,7 @@ class SarvamTTSService(InterruptibleTTSService):
             logger.debug("Connected to Sarvam TTS Websocket")
             await self._send_config()
 
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -556,6 +614,10 @@ class SarvamTTSService(InterruptibleTTSService):
                 await self._websocket.close()
         except Exception as e:
             logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._started = False
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

src/pipecat/services/simli/video.py

@@ -7,9 +7,12 @@
 """Simli video service for real-time avatar generation."""
 
 import asyncio
+import warnings
+from typing import Optional
 
 import numpy as np
 from loguru import logger
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     CancelFrame,
@@ -41,30 +44,103 @@ class SimliVideoService(FrameProcessor):
     audio resampling, video frame processing, and connection management.
     """
 
+    class InputParams(BaseModel):
+        """Input parameters for Simli video configuration.
+
+        Parameters:
+            max_session_length: Absolute maximum session duration in seconds.
+                Avatar will disconnect after this time even if it's speaking.
+            max_idle_time: Maximum duration in seconds the avatar is not speaking
+                before the avatar disconnects.
+        """
+
+        max_session_length: Optional[int] = None
+        max_idle_time: Optional[int] = None
+
     def __init__(
         self,
-        simli_config: SimliConfig,
+        *,
+        api_key: Optional[str] = None,
+        face_id: Optional[str] = None,
+        simli_config: Optional[SimliConfig] = None,
         use_turn_server: bool = False,
         latency_interval: int = 0,
         simli_url: str = "https://api.simli.ai",
         is_trinity_avatar: bool = False,
+        params: Optional[InputParams] = None,
+        **kwargs,
     ):
         """Initialize the Simli video service.
 
         Args:
+            api_key: Simli API key for authentication.
+            face_id: Simli Face ID. For Trinity avatars, specify "faceId/emotionId"
+                to use a different emotion than the default.
             simli_config: Configuration object for Simli client settings.
-            use_turn_server: Whether to use TURN server for connection. Defaults to False.
-            latency_interval: Latency interval setting for sending health checks to check the latency to Simli Servers. Defaults to 0.
-            simli_url: URL of the simli servers. Can be changed for custom deployments of enterprise users.
-            is_trinity_avatar: boolean to tell simli client that this is a Trinity avatar which reduces latency when using Trinity.
+                Use api_key and face_id instead.
 
+                .. deprecated:: 0.0.92
+                    The 'simli_config' parameter is deprecated and will be removed in a future version.
+                    Please use 'api_key' and 'face_id' parameters instead.
+
+            use_turn_server: Whether to use TURN server for connection. Defaults to False.
+            latency_interval: Latency interval setting for sending health checks to check
+                the latency to Simli Servers. Defaults to 0.
+            simli_url: URL of the simli servers. Can be changed for custom deployments
+                of enterprise users.
+            is_trinity_avatar: Boolean to tell simli client that this is a Trinity avatar
+                which reduces latency when using Trinity.
+            params: Additional input parameters for session configuration.
+            **kwargs: Additional arguments passed to the parent FrameProcessor.
         """
-        super().__init__()
+        super().__init__(**kwargs)
+
+        params = params or SimliVideoService.InputParams()
+
+        # Handle deprecated simli_config parameter
+        if simli_config is not None:
+            if api_key is not None or face_id is not None:
+                raise ValueError(
+                    "Cannot specify both simli_config and api_key/face_id. "
+                    "Please use api_key and face_id (simli_config is deprecated)."
+                )
+
+            warnings.warn(
+                "The 'simli_config' parameter is deprecated and will be removed in a future version. "
+                "Please use 'api_key' and 'face_id' parameters instead, with optional 'params' for "
+                "max_session_length and max_idle_time configuration.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+            # Use the provided simli_config
+            config = simli_config
+        else:
+            # Validate new parameters
+            if api_key is None:
+                raise ValueError("api_key is required")
+            if face_id is None:
+                raise ValueError("face_id is required")
+
+            # Build SimliConfig from new parameters
+            # Only pass optional parameters if explicitly provided to use SimliConfig defaults
+            config_kwargs = {
+                "apiKey": api_key,
+                "faceId": face_id,
+            }
+            if params.max_session_length is not None:
+                config_kwargs["maxSessionLength"] = params.max_session_length
+            if params.max_idle_time is not None:
+                config_kwargs["maxIdleTime"] = params.max_idle_time
+
+            config = SimliConfig(**config_kwargs)
+
         self._initialized = False
-        simli_config.maxIdleTime += 5
-        simli_config.maxSessionLength += 5
+        # Add buffer time to session limits
+        config.maxIdleTime += 5
+        config.maxSessionLength += 5
         self._simli_client = SimliClient(
-            simli_config,
+            config,
             use_turn_server,
             latency_interval,
             simliURL=simli_url,

src/pipecat/services/speechmatics/stt.py

@@ -577,6 +577,7 @@ class SpeechmaticsSTTService(STTService):
                 ),
             )
             logger.debug(f"{self} Connected to Speechmatics STT service")
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} Error connecting to Speechmatics: {e}")
             self._client = None
@@ -595,6 +596,7 @@ class SpeechmaticsSTTService(STTService):
             logger.error(f"{self} Error closing Speechmatics client: {e}")
         finally:
             self._client = None
+            await self._call_event_handler("on_disconnected")
 
     def _process_config(self) -> None:
         """Create a formatted STT transcription config.
@@ -618,7 +620,7 @@ class SpeechmaticsSTTService(STTService):
             transcription_config.additional_vocab = [
                 {
                     "content": e.content,
-                    "sounds_like": e.sounds_like,
+                    **({"sounds_like": e.sounds_like} if e.sounds_like else {}),
                 }
                 for e in self._params.additional_vocab
             ]

src/pipecat/services/stt_service.py

@@ -35,6 +35,25 @@ class STTService(AIService):
     Provides common functionality for STT services including audio passthrough,
     muting, settings management, and audio processing. Subclasses must implement
     the run_stt method to provide actual speech recognition.
+
+    Event handlers:
+        on_connected: Called when connected to the STT service.
+        on_connected: Called when disconnected from the STT service.
+        on_connection_error: Called when a connection to the STT service error occurs.
+
+    Example::
+
+        @stt.event_handler("on_connected")
+        async def on_connected(stt: STTService):
+            logger.debug(f"STT connected")
+
+        @stt.event_handler("on_disconnected")
+        async def on_disconnected(stt: STTService):
+            logger.debug(f"STT disconnected")
+
+        @stt.event_handler("on_connection_error")
+        async def on_connection_error(stt: STTService, error: str):
+            logger.error(f"STT connection error: {error}")
     """
 
     def __init__(
@@ -62,6 +81,10 @@ class STTService(AIService):
         self._muted: bool = False
         self._user_id: str = ""
 
+        self._register_event_handler("on_connected")
+        self._register_event_handler("on_disconnected")
+        self._register_event_handler("on_connection_error")
+
     @property
     def is_muted(self) -> bool:
         """Check if the STT service is currently muted.
@@ -292,15 +315,6 @@ class WebsocketSTTService(STTService, WebsocketService):
 
     Combines STT functionality with websocket connectivity, providing automatic
     error handling and reconnection capabilities.
-
-    Event handlers:
-        on_connection_error: Called when a websocket connection error occurs.
-
-    Example::
-
-        @stt.event_handler("on_connection_error")
-        async def on_connection_error(stt: STTService, error: str):
-            logger.error(f"STT connection error: {error}")
     """
 
     def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
@@ -312,7 +326,6 @@ class WebsocketSTTService(STTService, WebsocketService):
         """
         STTService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)

src/pipecat/services/tts_service.py

@@ -59,6 +59,25 @@ class TTSService(AIService):
     Provides common functionality for TTS services including text aggregation,
     filtering, audio generation, and frame management. Supports configurable
     sentence aggregation, silence insertion, and frame processing control.
+
+    Event handlers:
+        on_connected: Called when connected to the STT service.
+        on_connected: Called when disconnected from the STT service.
+        on_connection_error: Called when a connection to the STT service error occurs.
+
+    Example::
+
+        @tts.event_handler("on_connected")
+        async def on_connected(tts: TTSService):
+            logger.debug(f"TTS connected")
+
+        @tts.event_handler("on_disconnected")
+        async def on_disconnected(tts: TTSService):
+            logger.debug(f"TTS disconnected")
+
+        @tts.event_handler("on_connection_error")
+        async def on_connection_error(stt: TTSService, error: str):
+            logger.error(f"TTS connection error: {error}")
     """
 
     def __init__(
@@ -143,6 +162,10 @@ class TTSService(AIService):
 
         self._processing_text: bool = False
 
+        self._register_event_handler("on_connected")
+        self._register_event_handler("on_disconnected")
+        self._register_event_handler("on_connection_error")
+
     @property
     def sample_rate(self) -> int:
         """Get the current sample rate for audio output.
@@ -626,7 +649,6 @@ class WebsocketTTSService(TTSService, WebsocketService):
         """
         TTSService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)
@@ -678,15 +700,6 @@ class WebsocketWordTTSService(WordTTSService, WebsocketService):
     """Base class for websocket-based TTS services that support word timestamps.
 
     Combines word timestamp functionality with websocket connectivity.
-
-    Event handlers:
-        on_connection_error: Called when a websocket connection error occurs.
-
-    Example::
-
-        @tts.event_handler("on_connection_error")
-        async def on_connection_error(tts: TTSService, error: str):
-            logger.error(f"TTS connection error: {error}")
     """
 
     def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
@@ -698,7 +711,6 @@ class WebsocketWordTTSService(WordTTSService, WebsocketService):
         """
         WordTTSService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)

src/pipecat/transports/base_input.py

@@ -232,6 +232,9 @@ class BaseInputTransport(FrameProcessor):
         """
         # Cancel and wait for the audio input task to finish.
         await self._cancel_audio_task()
+        # Stop audio filter.
+        if self._params.audio_in_filter:
+            await self._params.audio_in_filter.stop()
 
     async def set_transport_ready(self, frame: StartFrame):
         """Called when the transport is ready to stream.

src/pipecat/transports/base_output.py

@@ -293,15 +293,15 @@ class BaseOutputTransport(FrameProcessor):
         """
         await super().process_frame(frame, direction)
 
-        #
-        # System frames (like InterruptionFrame) are pushed immediately. Other
-        # frames require order so they are put in the sink queue.
-        #
         if isinstance(frame, StartFrame):
             # Push StartFrame before start(), because we want StartFrame to be
             # processed by every processor before any other frame is processed.
             await self.push_frame(frame, direction)
             await self.start(frame)
+        elif isinstance(frame, EndFrame):
+            await self.stop(frame)
+            # Keep pushing EndFrame down so all the pipeline stops nicely.
+            await self.push_frame(frame, direction)
         elif isinstance(frame, CancelFrame):
             await self.cancel(frame)
             await self.push_frame(frame, direction)
@@ -314,21 +314,6 @@ class BaseOutputTransport(FrameProcessor):
             await self.write_dtmf(frame)
         elif isinstance(frame, SystemFrame):
             await self.push_frame(frame, direction)
-        # Control frames.
-        elif isinstance(frame, EndFrame):
-            await self.stop(frame)
-            # Keep pushing EndFrame down so all the pipeline stops nicely.
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, MixerControlFrame):
-            await self._handle_frame(frame)
-        # Other frames.
-        elif isinstance(frame, OutputAudioRawFrame):
-            await self._handle_frame(frame)
-        elif isinstance(frame, (OutputImageRawFrame, SpriteFrame)):
-            await self._handle_frame(frame)
-        # TODO(aleix): Images and audio should support presentation timestamps.
-        elif frame.pts:
-            await self._handle_frame(frame)
         elif direction == FrameDirection.UPSTREAM:
             await self.push_frame(frame, direction)
         else:
@@ -410,6 +395,13 @@ class BaseOutputTransport(FrameProcessor):
 
             # Indicates if the bot is currently speaking.
             self._bot_speaking = False
+            # Last time a BotSpeakingFrame was pushed.
+            self._bot_speaking_frame_time = 0
+            # How often a BotSpeakingFrame should be pushed (value should be
+            # lower than the audio chunks).
+            self._bot_speaking_frame_period = 0.2
+            # Last time the bot actually spoke.
+            self._bot_speech_last_time = 0
 
             self._audio_task: Optional[asyncio.Task] = None
             self._video_task: Optional[asyncio.Task] = None
@@ -601,39 +593,71 @@ class BaseOutputTransport(FrameProcessor):
 
         async def _bot_started_speaking(self):
             """Handle bot started speaking event."""
-            if not self._bot_speaking:
-                logger.debug(
-                    f"Bot{f' [{self._destination}]' if self._destination else ''} started speaking"
-                )
+            if self._bot_speaking:
+                return
 
-                downstream_frame = BotStartedSpeakingFrame()
-                downstream_frame.transport_destination = self._destination
-                upstream_frame = BotStartedSpeakingFrame()
-                upstream_frame.transport_destination = self._destination
-                await self._transport.push_frame(downstream_frame)
-                await self._transport.push_frame(upstream_frame, FrameDirection.UPSTREAM)
+            logger.debug(
+                f"Bot{f' [{self._destination}]' if self._destination else ''} started speaking"
+            )
 
-                self._bot_speaking = True
+            downstream_frame = BotStartedSpeakingFrame()
+            downstream_frame.transport_destination = self._destination
+            upstream_frame = BotStartedSpeakingFrame()
+            upstream_frame.transport_destination = self._destination
+            await self._transport.push_frame(downstream_frame)
+            await self._transport.push_frame(upstream_frame, FrameDirection.UPSTREAM)
+
+            self._bot_speaking = True
 
         async def _bot_stopped_speaking(self):
             """Handle bot stopped speaking event."""
-            if self._bot_speaking:
-                logger.debug(
-                    f"Bot{f' [{self._destination}]' if self._destination else ''} stopped speaking"
-                )
+            if not self._bot_speaking:
+                return
 
-                downstream_frame = BotStoppedSpeakingFrame()
-                downstream_frame.transport_destination = self._destination
-                upstream_frame = BotStoppedSpeakingFrame()
-                upstream_frame.transport_destination = self._destination
-                await self._transport.push_frame(downstream_frame)
-                await self._transport.push_frame(upstream_frame, FrameDirection.UPSTREAM)
+            logger.debug(
+                f"Bot{f' [{self._destination}]' if self._destination else ''} stopped speaking"
+            )
 
-                self._bot_speaking = False
+            downstream_frame = BotStoppedSpeakingFrame()
+            downstream_frame.transport_destination = self._destination
+            upstream_frame = BotStoppedSpeakingFrame()
+            upstream_frame.transport_destination = self._destination
+            await self._transport.push_frame(downstream_frame)
+            await self._transport.push_frame(upstream_frame, FrameDirection.UPSTREAM)
 
-                # Clean audio buffer (there could be tiny left overs if not multiple
-                # to our output chunk size).
-                self._audio_buffer = bytearray()
+            self._bot_speaking = False
+
+            # Clean audio buffer (there could be tiny left overs if not multiple
+            # to our output chunk size).
+            self._audio_buffer = bytearray()
+
+        async def _bot_currently_speaking(self):
+            """Handle bot speaking event."""
+            await self._bot_started_speaking()
+
+            diff_time = time.time() - self._bot_speaking_frame_time
+            if diff_time >= self._bot_speaking_frame_period:
+                await self._transport.push_frame(BotSpeakingFrame())
+                await self._transport.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
+                self._bot_speaking_frame_time = time.time()
+
+            self._bot_speech_last_time = time.time()
+
+        async def _maybe_bot_currently_speaking(self, frame: SpeechOutputAudioRawFrame):
+            if not is_silence(frame.audio):
+                await self._bot_currently_speaking()
+            else:
+                silence_duration = time.time() - self._bot_speech_last_time
+                if silence_duration > BOT_VAD_STOP_SECS:
+                    await self._bot_stopped_speaking()
+
+        async def _handle_bot_speech(self, frame: Frame):
+            # TTS case.
+            if isinstance(frame, TTSAudioRawFrame):
+                await self._bot_currently_speaking()
+            # Speech stream case.
+            elif isinstance(frame, SpeechOutputAudioRawFrame):
+                await self._maybe_bot_currently_speaking(frame)
 
         async def _handle_frame(self, frame: Frame):
             """Handle various frame types with appropriate processing.
@@ -641,7 +665,9 @@ class BaseOutputTransport(FrameProcessor):
             Args:
                 frame: The frame to handle.
             """
-            if isinstance(frame, OutputImageRawFrame):
+            if isinstance(frame, OutputAudioRawFrame):
+                await self._handle_bot_speech(frame)
+            elif isinstance(frame, OutputImageRawFrame):
                 await self._set_video_image(frame)
             elif isinstance(frame, SpriteFrame):
                 await self._set_video_images(frame.images)
@@ -705,39 +731,7 @@ class BaseOutputTransport(FrameProcessor):
 
         async def _audio_task_handler(self):
             """Main audio processing task handler."""
-            # Push a BotSpeakingFrame every 200ms, we don't really need to push it
-            # at every audio chunk. If the audio chunk is bigger than 200ms, push at
-            # every audio chunk.
-            TOTAL_CHUNK_MS = self._params.audio_out_10ms_chunks * 10
-            BOT_SPEAKING_CHUNK_PERIOD = max(int(200 / TOTAL_CHUNK_MS), 1)
-            bot_speaking_counter = 0
-            speech_last_speaking_time = 0
-
             async for frame in self._next_frame():
-                # Notify the bot started speaking upstream if necessary and that
-                # it's actually speaking.
-                is_speaking = False
-                if isinstance(frame, TTSAudioRawFrame):
-                    is_speaking = True
-                elif isinstance(frame, SpeechOutputAudioRawFrame):
-                    if not is_silence(frame.audio):
-                        is_speaking = True
-                        speech_last_speaking_time = time.time()
-                    else:
-                        silence_duration = time.time() - speech_last_speaking_time
-                        if silence_duration > BOT_VAD_STOP_SECS:
-                            await self._bot_stopped_speaking()
-
-                if is_speaking:
-                    await self._bot_started_speaking()
-                    if bot_speaking_counter % BOT_SPEAKING_CHUNK_PERIOD == 0:
-                        await self._transport.push_frame(BotSpeakingFrame())
-                        await self._transport.push_frame(
-                            BotSpeakingFrame(), FrameDirection.UPSTREAM
-                        )
-                        bot_speaking_counter = 0
-                    bot_speaking_counter += 1
-
                 # No need to push EndFrame, it's pushed from process_frame().
                 if isinstance(frame, EndFrame):
                     break

src/pipecat/transports/daily/transport.py

@@ -16,7 +16,7 @@ import time
 from concurrent.futures import CancelledError as FuturesCancelledError
 from concurrent.futures import ThreadPoolExecutor
 from dataclasses import dataclass
-from typing import Any, Awaitable, Callable, Dict, Mapping, Optional
+from typing import Any, Awaitable, Callable, Dict, Mapping, Optional, Tuple
 
 import aiohttp
 from loguru import logger
@@ -419,6 +419,11 @@ class DailyAudioTrack:
     track: CustomAudioTrack
 
 
+# This is just a type alias for the errors returned by daily-python. Right now
+# they are just a string.
+CallClientError = str
+
+
 class DailyTransportClient(EventHandler):
     """Core client for interacting with Daily's API.
 
@@ -553,14 +558,17 @@ class DailyTransportClient(EventHandler):
 
     async def send_message(
         self, frame: OutputTransportMessageFrame | OutputTransportMessageUrgentFrame
-    ):
+    ) -> Optional[CallClientError]:
         """Send an application message to participants.
 
         Args:
             frame: The message frame to send.
+
+        Returns:
+            error: An error description or None.
         """
         if not self._joined:
-            return
+            return "Unable to send messages before joining."
 
         participant_id = None
         if isinstance(
@@ -572,7 +580,7 @@ class DailyTransportClient(EventHandler):
         self._client.send_app_message(
             frame.message, participant_id, completion=completion_callback(future)
         )
-        await future
+        return await future
 
     async def read_next_audio_frame(self) -> Optional[InputAudioRawFrame]:
         """Reads the next 20ms audio frame from the virtual speaker."""
@@ -744,32 +752,24 @@ class DailyTransportClient(EventHandler):
 
         self._client.set_user_name(self._bot_name)
 
-        try:
-            (data, error) = await self._join()
+        (data, error) = await self._join()
 
-            if not error:
-                self._joined = True
-                self._joining = False
-                # Increment leave counter if we successfully joined.
-                self._leave_counter += 1
-
-                logger.info(f"Joined {self._room_url}")
-
-                if self._params.transcription_enabled:
-                    await self.start_transcription(self._params.transcription_settings)
-
-                await self._callbacks.on_joined(data)
-
-                self._joined_event.set()
-            else:
-                error_msg = f"Error joining {self._room_url}: {error}"
-                logger.error(error_msg)
-                await self._callbacks.on_error(error_msg)
-        except asyncio.TimeoutError:
-            error_msg = f"Time out joining {self._room_url}"
-            logger.error(error_msg)
+        if not error:
+            self._joined = True
             self._joining = False
+            # Increment leave counter if we successfully joined.
+            self._leave_counter += 1
+
+            logger.info(f"Joined {self._room_url}")
+
+            await self._callbacks.on_joined(data)
+
+            self._joined_event.set()
+        else:
+            error_msg = f"Error joining {self._room_url}: {error}"
+            logger.error(error_msg)
             await self._callbacks.on_error(error_msg)
+            self._joining = False
 
     async def _join(self):
         """Execute the actual room join operation."""
@@ -828,7 +828,7 @@ class DailyTransportClient(EventHandler):
             },
         )
 
-        return await asyncio.wait_for(future, timeout=10)
+        return await future
 
     async def leave(self):
         """Leave the Daily room and cleanup resources."""
@@ -847,24 +847,16 @@ class DailyTransportClient(EventHandler):
         # Call callback before leaving.
         await self._callbacks.on_before_leave()
 
-        if self._params.transcription_enabled:
-            await self.stop_transcription()
-
         # Remove any custom tracks, if any.
         for track_name, _ in self._custom_audio_tracks.items():
             await self.remove_custom_audio_track(track_name)
 
-        try:
-            error = await self._leave()
-            if not error:
-                logger.info(f"Left {self._room_url}")
-                await self._callbacks.on_left()
-            else:
-                error_msg = f"Error leaving {self._room_url}: {error}"
-                logger.error(error_msg)
-                await self._callbacks.on_error(error_msg)
-        except asyncio.TimeoutError:
-            error_msg = f"Time out leaving {self._room_url}"
+        error = await self._leave()
+        if not error:
+            logger.info(f"Left {self._room_url}")
+            await self._callbacks.on_left()
+        else:
+            error_msg = f"Error leaving {self._room_url}: {error}"
             logger.error(error_msg)
             await self._callbacks.on_error(error_msg)
 
@@ -875,7 +867,7 @@ class DailyTransportClient(EventHandler):
 
         future = self._get_event_loop().create_future()
         self._client.leave(completion=completion_callback(future))
-        return await asyncio.wait_for(future, timeout=10)
+        return await future
 
     def _cleanup(self):
         """Cleanup the Daily client instance."""
@@ -883,7 +875,7 @@ class DailyTransportClient(EventHandler):
             self._client.release()
             self._client = None
 
-    def participants(self):
+    def participants(self) -> Mapping[str, Any]:
         """Get current participants in the room.
 
         Returns:
@@ -891,7 +883,7 @@ class DailyTransportClient(EventHandler):
         """
         return self._client.participants()
 
-    def participant_counts(self):
+    def participant_counts(self) -> Mapping[str, Any]:
         """Get participant count information.
 
         Returns:
@@ -899,165 +891,173 @@ class DailyTransportClient(EventHandler):
         """
         return self._client.participant_counts()
 
-    async def start_dialout(self, settings):
+    async def start_dialout(self, settings) -> Tuple[str, Optional[CallClientError]]:
         """Start a dial-out call to a phone number.
 
         Args:
             settings: Dial-out configuration settings.
-        """
-        logger.debug(f"Starting dialout: settings={settings}")
 
+        Returns:
+            session_id: Dail-out session ID.
+            error: An error description or None.
+        """
         future = self._get_event_loop().create_future()
         self._client.start_dialout(settings, completion=completion_callback(future))
-        error = await future
-        if error:
-            logger.error(f"Unable to start dialout: {error}")
+        return await future
 
-    async def stop_dialout(self, participant_id):
+    async def stop_dialout(self, participant_id) -> Optional[CallClientError]:
         """Stop a dial-out call for a specific participant.
 
         Args:
             participant_id: ID of the participant to stop dial-out for.
-        """
-        logger.debug(f"Stopping dialout: participant_id={participant_id}")
 
+        Returns:
+            error: An error description or None.
+        """
         future = self._get_event_loop().create_future()
         self._client.stop_dialout(participant_id, completion=completion_callback(future))
-        error = await future
-        if error:
-            logger.error(f"Unable to stop dialout: {error}")
+        return await future
 
-    async def send_dtmf(self, settings):
+    async def send_dtmf(self, settings) -> Optional[CallClientError]:
         """Send DTMF tones during a call.
 
         Args:
             settings: DTMF settings including tones and target session.
+
+        Returns:
+            error: An error description or None.
         """
         session_id = settings.get("sessionId") or self._dial_out_session_id
         if not session_id:
-            logger.error("Unable to send DTMF: 'sessionId' is not set")
-            return
+            return "Can't send DTMF if 'sessionId' is not set"
 
         # Update 'sessionId' field.
         settings["sessionId"] = session_id
 
         future = self._get_event_loop().create_future()
         self._client.send_dtmf(settings, completion=completion_callback(future))
-        await future
+        return await future
 
-    async def sip_call_transfer(self, settings):
+    async def sip_call_transfer(self, settings) -> Optional[CallClientError]:
         """Transfer a SIP call to another destination.
 
         Args:
             settings: SIP call transfer settings.
+
+        Returns:
+            error: An error description or None.
         """
         session_id = (
             settings.get("sessionId") or self._dial_out_session_id or self._dial_in_session_id
         )
         if not session_id:
-            logger.error("Unable to transfer SIP call: 'sessionId' is not set")
-            return
+            return "Can't transfer SIP call if 'sessionId' is not set"
 
         # Update 'sessionId' field.
         settings["sessionId"] = session_id
 
         future = self._get_event_loop().create_future()
         self._client.sip_call_transfer(settings, completion=completion_callback(future))
-        await future
+        return await future
 
-    async def sip_refer(self, settings):
+    async def sip_refer(self, settings) -> Optional[CallClientError]:
         """Send a SIP REFER request.
 
         Args:
             settings: SIP REFER settings.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.sip_refer(settings, completion=completion_callback(future))
-        await future
+        return await future
 
-    async def start_recording(self, streaming_settings, stream_id, force_new):
+    async def start_recording(
+        self, streaming_settings, stream_id, force_new
+    ) -> Tuple[str, Optional[CallClientError]]:
         """Start recording the call.
 
         Args:
             streaming_settings: Recording configuration settings.
             stream_id: Unique identifier for the recording stream.
             force_new: Whether to force a new recording session.
-        """
-        logger.debug(
-            f"Starting recording: stream_id={stream_id} force_new={force_new} settings={streaming_settings}"
-        )
 
+        Returns:
+            stream_id: Unique identifier for the recording stream.
+            error: An error description or None.
+        """
         future = self._get_event_loop().create_future()
         self._client.start_recording(
             streaming_settings, stream_id, force_new, completion=completion_callback(future)
         )
-        error = await future
-        if error:
-            logger.error(f"Unable to start recording: {error}")
+        return await future
 
-    async def stop_recording(self, stream_id):
+    async def stop_recording(self, stream_id) -> Optional[CallClientError]:
         """Stop recording the call.
 
         Args:
             stream_id: Unique identifier for the recording stream to stop.
-        """
-        logger.debug(f"Stopping recording: stream_id={stream_id}")
 
+        Returns:
+            error: An error description or None.
+        """
         future = self._get_event_loop().create_future()
         self._client.stop_recording(stream_id, completion=completion_callback(future))
-        error = await future
-        if error:
-            logger.error(f"Unable to stop recording: {error}")
+        return await future
 
-    async def start_transcription(self, settings):
+    async def start_transcription(self, settings) -> Optional[CallClientError]:
         """Start transcription for the call.
 
         Args:
             settings: Transcription configuration settings.
+
+        Returns:
+            error: An error description or None.
         """
         if not self._token:
-            logger.warning("Transcription can't be started without a room token")
-            return
-
-        logger.debug(f"Starting transcription: settings={settings}")
+            return "Transcription can't be started without a room token"
 
         future = self._get_event_loop().create_future()
         self._client.start_transcription(
             settings=self._params.transcription_settings.model_dump(exclude_none=True),
             completion=completion_callback(future),
         )
-        error = await future
-        if error:
-            logger.error(f"Unable to start transcription: {error}")
+        return await future
 
-    async def stop_transcription(self):
-        """Stop transcription for the call."""
+    async def stop_transcription(self) -> Optional[CallClientError]:
+        """Stop transcription for the call.
+
+        Returns:
+            error: An error description or None.
+        """
         if not self._token:
-            return
-
-        logger.debug(f"Stopping transcription")
+            return "Transcription can't be stopped without a room token"
 
         future = self._get_event_loop().create_future()
         self._client.stop_transcription(completion=completion_callback(future))
-        error = await future
-        if error:
-            logger.error(f"Unable to stop transcription: {error}")
+        return await future
 
-    async def send_prebuilt_chat_message(self, message: str, user_name: Optional[str] = None):
+    async def send_prebuilt_chat_message(
+        self, message: str, user_name: Optional[str] = None
+    ) -> Optional[CallClientError]:
         """Send a chat message to Daily's Prebuilt main room.
 
         Args:
             message: The chat message to send.
             user_name: Optional user name that will appear as sender of the message.
+
+        Returns:
+            error: An error description or None.
         """
         if not self._joined:
-            return
+            return "Can't send message if not joined"
 
         future = self._get_event_loop().create_future()
         self._client.send_prebuilt_chat_message(
             message, user_name=user_name, completion=completion_callback(future)
         )
-        await future
+        return await future
 
     async def capture_participant_transcription(self, participant_id: str):
         """Enable transcription capture for a specific participant.
@@ -1177,38 +1177,51 @@ class DailyTransportClient(EventHandler):
 
         return track
 
-    async def remove_custom_audio_track(self, track_name: str):
+    async def remove_custom_audio_track(self, track_name: str) -> Optional[CallClientError]:
         """Remove a custom audio track.
 
         Args:
             track_name: Name of the custom audio track to remove.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.remove_custom_audio_track(
             track_name=track_name,
             completion=completion_callback(future),
         )
-        await future
+        return await future
 
-    async def update_transcription(self, participants=None, instance_id=None):
+    async def update_transcription(
+        self, participants=None, instance_id=None
+    ) -> Optional[CallClientError]:
         """Update transcription settings for specific participants.
 
         Args:
             participants: List of participant IDs to enable transcription for.
             instance_id: Optional transcription instance ID.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.update_transcription(
             participants, instance_id, completion=completion_callback(future)
         )
-        await future
+        return await future
 
-    async def update_subscriptions(self, participant_settings=None, profile_settings=None):
+    async def update_subscriptions(
+        self, participant_settings=None, profile_settings=None
+    ) -> Optional[CallClientError]:
         """Update media subscription settings.
 
         Args:
             participant_settings: Per-participant subscription settings.
             profile_settings: Global subscription profile settings.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.update_subscriptions(
@@ -1216,32 +1229,42 @@ class DailyTransportClient(EventHandler):
             profile_settings=profile_settings,
             completion=completion_callback(future),
         )
-        await future
+        return await future
 
-    async def update_publishing(self, publishing_settings: Mapping[str, Any]):
+    async def update_publishing(
+        self, publishing_settings: Mapping[str, Any]
+    ) -> Optional[CallClientError]:
         """Update media publishing settings.
 
         Args:
             publishing_settings: Publishing configuration settings.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.update_publishing(
             publishing_settings=publishing_settings,
             completion=completion_callback(future),
         )
-        await future
+        return await future
 
-    async def update_remote_participants(self, remote_participants: Mapping[str, Any]):
+    async def update_remote_participants(
+        self, remote_participants: Mapping[str, Any]
+    ) -> Optional[CallClientError]:
         """Update settings for remote participants.
 
         Args:
             remote_participants: Remote participant configuration settings.
+
+        Returns:
+            error: An error description or None.
         """
         future = self._get_event_loop().create_future()
         self._client.update_remote_participants(
             remote_participants=remote_participants, completion=completion_callback(future)
         )
-        await future
+        return await future
 
     #
     #
@@ -1932,7 +1955,9 @@ class DailyOutputTransport(BaseOutputTransport):
         Args:
             frame: The transport message frame to send.
         """
-        await self._client.send_message(frame)
+        error = await self._client.send_message(frame)
+        if error:
+            logger.error(f"Unable to send message: {error}")
 
     async def register_video_destination(self, destination: str):
         """Register a video output destination.
@@ -2176,7 +2201,7 @@ class DailyTransport(BaseTransport):
         if self._output:
             await self._output.queue_frame(frame, FrameDirection.DOWNSTREAM)
 
-    def participants(self):
+    def participants(self) -> Mapping[str, Any]:
         """Get current participants in the room.
 
         Returns:
@@ -2184,7 +2209,7 @@ class DailyTransport(BaseTransport):
         """
         return self._client.participants()
 
-    def participant_counts(self):
+    def participant_counts(self) -> Mapping[str, Any]:
         """Get participant count information.
 
         Returns:
@@ -2192,76 +2217,155 @@ class DailyTransport(BaseTransport):
         """
         return self._client.participant_counts()
 
-    async def start_dialout(self, settings=None):
+    async def start_dialout(self, settings=None) -> Tuple[str, Optional[CallClientError]]:
         """Start a dial-out call to a phone number.
 
         Args:
             settings: Dial-out configuration settings.
-        """
-        await self._client.start_dialout(settings)
 
-    async def stop_dialout(self, participant_id):
+        Returns:
+            session_id: Dail-out session ID.
+            error: An error description or None.
+        """
+        logger.debug(f"Starting dialout: settings={settings}")
+
+        session_id, error = await self._client.start_dialout(settings)
+        if error:
+            logger.error(f"Unable to start dialout: {error}")
+        return session_id, error
+
+    async def stop_dialout(self, participant_id) -> Optional[CallClientError]:
         """Stop a dial-out call for a specific participant.
 
         Args:
             participant_id: ID of the participant to stop dial-out for.
-        """
-        await self._client.stop_dialout(participant_id)
 
-    async def sip_call_transfer(self, settings):
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Stopping dialout: participant_id={participant_id}")
+
+        error = await self._client.stop_dialout(participant_id)
+        if error:
+            logger.error(f"Unable to stop dialout: {error}")
+        return error
+
+    async def sip_call_transfer(self, settings) -> Optional[CallClientError]:
         """Transfer a SIP call to another destination.
 
         Args:
             settings: SIP call transfer settings.
-        """
-        await self._client.sip_call_transfer(settings)
 
-    async def sip_refer(self, settings):
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Staring SIP call transfer: settings={settings}")
+
+        error = await self._client.sip_call_transfer(settings)
+        if error:
+            logger.error(f"Unable to transfer SIP call: {error}")
+        return error
+
+    async def sip_refer(self, settings) -> Optional[CallClientError]:
         """Send a SIP REFER request.
 
         Args:
             settings: SIP REFER settings.
-        """
-        await self._client.sip_refer(settings)
 
-    async def start_recording(self, streaming_settings=None, stream_id=None, force_new=None):
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Staring SIP REFER: settings={settings}")
+
+        error = await self._client.sip_refer(settings)
+        if error:
+            logger.error(f"Unable to perform SIP REFER: {error}")
+        return error
+
+    async def start_recording(
+        self, streaming_settings=None, stream_id=None, force_new=None
+    ) -> Tuple[str, Optional[CallClientError]]:
         """Start recording the call.
 
         Args:
             streaming_settings: Recording configuration settings.
             stream_id: Unique identifier for the recording stream.
             force_new: Whether to force a new recording session.
-        """
-        await self._client.start_recording(streaming_settings, stream_id, force_new)
 
-    async def stop_recording(self, stream_id=None):
+        Returns:
+            stream_id: Unique identifier for the recording stream.
+            error: An error description or None.
+        """
+        logger.debug(
+            f"Starting recording: stream_id={stream_id} force_new={force_new} settings={streaming_settings}"
+        )
+
+        r_id, error = await self._client.start_recording(streaming_settings, stream_id, force_new)
+        if error:
+            logger.error(f"Unable to start recording: {error}")
+        return r_id, error
+
+    async def stop_recording(self, stream_id=None) -> Optional[CallClientError]:
         """Stop recording the call.
 
         Args:
             stream_id: Unique identifier for the recording stream to stop.
-        """
-        await self._client.stop_recording(stream_id)
 
-    async def start_transcription(self, settings=None):
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Stopping recording: stream_id={stream_id}")
+
+        error = await self._client.stop_recording(stream_id)
+        if error:
+            logger.error(f"Unable to stop recording: {error}")
+        return error
+
+    async def start_transcription(self, settings=None) -> Optional[CallClientError]:
         """Start transcription for the call.
 
         Args:
             settings: Transcription configuration settings.
+
+        Returns:
+            error: An error description or None.
         """
-        await self._client.start_transcription(settings)
+        logger.debug(f"Starting transcription: settings={settings}")
 
-    async def stop_transcription(self):
-        """Stop transcription for the call."""
-        await self._client.stop_transcription()
+        error = await self._client.start_transcription(settings)
+        if error:
+            logger.error(f"Unable to start transcription: {error}")
+        return error
 
-    async def send_prebuilt_chat_message(self, message: str, user_name: Optional[str] = None):
+    async def stop_transcription(self) -> Optional[CallClientError]:
+        """Stop transcription for the call.
+
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Stopping transcription")
+
+        error = await self._client.stop_transcription()
+        if error:
+            logger.error(f"Unable to stop transcription: {error}")
+        return error
+
+    async def send_prebuilt_chat_message(
+        self, message: str, user_name: Optional[str] = None
+    ) -> Optional[CallClientError]:
         """Send a chat message to Daily's Prebuilt main room.
 
         Args:
             message: The chat message to send.
             user_name: Optional user name that will appear as sender of the message.
+
+        Returns:
+            error: An error description or None.
         """
-        await self._client.send_prebuilt_chat_message(message, user_name)
+        error = await self._client.send_prebuilt_chat_message(message, user_name)
+        if error:
+            logger.error(f"Unable to send prebuilt chat message: {error}")
+        return error
 
     async def capture_participant_transcription(self, participant_id: str):
         """Enable transcription capture for a specific participant.
@@ -2307,32 +2411,66 @@ class DailyTransport(BaseTransport):
                 participant_id, framerate, video_source, color_format
             )
 
-    async def update_publishing(self, publishing_settings: Mapping[str, Any]):
+    async def update_publishing(
+        self, publishing_settings: Mapping[str, Any]
+    ) -> Optional[CallClientError]:
         """Update media publishing settings.
 
         Args:
             publishing_settings: Publishing configuration settings.
-        """
-        await self._client.update_publishing(publishing_settings=publishing_settings)
 
-    async def update_subscriptions(self, participant_settings=None, profile_settings=None):
+        Returns:
+            error: An error description or None.
+        """
+        logger.debug(f"Updating publishing settings: settings={publishing_settings}")
+
+        error = await self._client.update_publishing(publishing_settings=publishing_settings)
+        if error:
+            logger.error(f"Unable to update publishing settings: {error}")
+        return error
+
+    async def update_subscriptions(
+        self, participant_settings=None, profile_settings=None
+    ) -> Optional[CallClientError]:
         """Update media subscription settings.
 
         Args:
             participant_settings: Per-participant subscription settings.
             profile_settings: Global subscription profile settings.
+
+        Returns:
+            error: An error description or None.
         """
-        await self._client.update_subscriptions(
-            participant_settings=participant_settings, profile_settings=profile_settings
+        logger.debug(
+            f"Updating subscriptions: participant_settings={participant_settings} profile_settings={profile_settings}"
         )
 
-    async def update_remote_participants(self, remote_participants: Mapping[str, Any]):
+        error = await self._client.update_subscriptions(
+            participant_settings=participant_settings, profile_settings=profile_settings
+        )
+        if error:
+            logger.error(f"Unable to update subscription settings: {error}")
+        return error
+
+    async def update_remote_participants(
+        self, remote_participants: Mapping[str, Any]
+    ) -> Optional[CallClientError]:
         """Update settings for remote participants.
 
         Args:
             remote_participants: Remote participant configuration settings.
+
+        Returns:
+            error: An error description or None.
         """
-        await self._client.update_remote_participants(remote_participants=remote_participants)
+        logger.debug(f"Updating remote participants: remote_participants={remote_participants}")
+
+        error = await self._client.update_remote_participants(
+            remote_participants=remote_participants
+        )
+        if error:
+            logger.error(f"Unable to update remote participants: {error}")
+        return error
 
     async def _on_active_speaker_changed(self, participant: Any):
         """Handle active speaker change events."""
@@ -2340,6 +2478,12 @@ class DailyTransport(BaseTransport):
 
     async def _on_joined(self, data):
         """Handle room joined events."""
+        if self._params.transcription_enabled:
+            # We report an error because we are starting transcription
+            # internally and if it fails we need to know.
+            error = await self.start_transcription(self._params.transcription_settings)
+            if error:
+                await self._on_error(f"Unable to start transcription: {error}")
         await self._call_event_handler("on_joined", data)
 
     async def _on_left(self):
@@ -2348,6 +2492,12 @@ class DailyTransport(BaseTransport):
 
     async def _on_before_leave(self):
         """Handle before leave room events."""
+        if self._params.transcription_enabled:
+            # We report an error because we are stopping transcription
+            # internally and if it fails we need to know.
+            error = await self.stop_transcription()
+            if error:
+                await self._on_error(f"Unable to stop transcription: {error}")
         await self._call_event_handler("on_before_leave")
 
     async def _on_error(self, error):

src/pipecat/transports/smallwebrtc/connection.py

@@ -689,3 +689,8 @@ class SmallWebRTCConnection(BaseObject):
                 )()
                 if track:
                     track.set_enabled(signalling_message.enabled)
+
+    async def add_ice_candidate(self, candidate):
+        """Handle incoming ICE candidates."""
+        logger.debug(f"Adding remote candidate: {candidate}")
+        await self.pc.addIceCandidate(candidate)

src/pipecat/transports/smallwebrtc/request_handler.py

@@ -14,6 +14,7 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Any, Awaitable, Callable, Dict, List, Optional
 
+from aiortc.sdp import candidate_from_sdp
 from fastapi import HTTPException
 from loguru import logger
 
@@ -39,6 +40,34 @@ class SmallWebRTCRequest:
     request_data: Optional[Any] = None
 
 
+@dataclass
+class IceCandidate:
+    """The remote ice candidate object received from the peer connection.
+
+    Parameters:
+        candidate: The ice candidate patch SDP string (Session Description Protocol).
+        sdp_mid: The SDP mid for the candidate patch.
+        sdp_mline_index: The SDP mline index for the candidate patch.
+    """
+
+    candidate: str
+    sdp_mid: str
+    sdp_mline_index: int
+
+
+@dataclass
+class SmallWebRTCPatchRequest:
+    """Small WebRTC transport session arguments for the runner.
+
+    Parameters:
+        pc_id: Identifier for the peer connection.
+        candidates: A list of ICE candidate patches.
+    """
+
+    pc_id: str
+    candidates: List[IceCandidate]
+
+
 class ConnectionMode(Enum):
     """Enum defining the connection handling modes."""
 
@@ -197,6 +226,19 @@ class SmallWebRTCRequestHandler:
             logger.debug(f"SmallWebRTC request details: {request}")
             raise
 
+    async def handle_patch_request(self, request: SmallWebRTCPatchRequest):
+        """Handle a SmallWebRTC patch candidate request."""
+        peer_connection = self._pcs_map.get(request.pc_id)
+
+        if not peer_connection:
+            raise HTTPException(status_code=404, detail="Peer connection not found")
+
+        for c in request.candidates:
+            candidate = candidate_from_sdp(c.candidate)
+            candidate.sdpMid = c.sdp_mid
+            candidate.sdpMLineIndex = c.sdp_mline_index
+            await peer_connection.add_ice_candidate(candidate)
+
     async def close(self):
         """Clear the connection map."""
         coros = [pc.disconnect() for pc in self._pcs_map.values()]

src/pipecat/utils/string.py

@@ -47,6 +47,7 @@ SENTENCE_ENDING_PUNCTUATION: FrozenSet[str] = frozenset(
         "!",
         "?",
         ";",
+        "…",
         # East Asian punctuation (Chinese (Traditional & Simplified), Japanese, Korean)
         "。",  # Ideographic full stop
         "？",  # Full-width question mark

src/pipecat/utils/tracing/service_decorators.py

@@ -905,7 +905,9 @@ def traced_openai_realtime(operation: str) -> Callable:
                             # Capture context messages being sent
                             if hasattr(self, "_context") and self._context:
                                 try:
-                                    messages = self._context.get_messages_for_logging()
+                                    messages = self.get_llm_adapter().get_messages_for_logging(
+                                        self._context
+                                    )
                                     if messages:
                                         operation_attrs["context_messages"] = json.dumps(messages)
                                 except Exception as e:

tests/test_pipeline.py

@@ -254,7 +254,7 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
 
         try:
             await asyncio.wait_for(
-                asyncio.shield(task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))),
+                task.run(PipelineTaskParams(loop=asyncio.get_event_loop())),
                 timeout=1.0,
             )
         except asyncio.TimeoutError:
@@ -290,7 +290,7 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
         await task.queue_frame(TextFrame(text="Hello!"))
         try:
             await asyncio.wait_for(
-                asyncio.shield(task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))),
+                task.run(PipelineTaskParams(loop=asyncio.get_event_loop())),
                 timeout=1.0,
             )
         except asyncio.TimeoutError:
@@ -301,11 +301,8 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
         identity = IdentityFilter()
         pipeline = Pipeline([identity])
         task = PipelineTask(pipeline, idle_timeout_secs=0.2)
-        try:
-            await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
-            assert False
-        except asyncio.CancelledError:
-            assert True
+        # This shouldn't freeze, so nothing to check really.
+        await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
 
     async def test_no_idle_task(self):
         identity = IdentityFilter()
@@ -313,7 +310,7 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
         task = PipelineTask(pipeline, idle_timeout_secs=0.2, cancel_on_idle_timeout=False)
         try:
             await asyncio.wait_for(
-                asyncio.shield(task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))),
+                task.run(PipelineTaskParams(loop=asyncio.get_event_loop())),
                 timeout=0.3,
             )
         except asyncio.TimeoutError:
@@ -332,11 +329,7 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
             ),
             idle_timeout_secs=0.3,
         )
-        try:
-            await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
-            assert False
-        except asyncio.CancelledError:
-            assert True
+        await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
 
     async def test_idle_task_event_handler_no_frames(self):
         identity = IdentityFilter()
@@ -351,11 +344,8 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
             idle_timeout = True
             await task.cancel()
 
-        try:
-            await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
-            assert False
-        except asyncio.CancelledError:
-            assert idle_timeout
+        await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
+        assert idle_timeout
 
     async def test_idle_task_event_handler_quiet_user(self):
         identity = IdentityFilter()
@@ -416,12 +406,15 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
             asyncio.create_task(delayed_frames()),
         ]
 
-        await asyncio.wait(tasks, return_when=asyncio.FIRST_COMPLETED)
+        _, pending = await asyncio.wait(tasks, return_when=asyncio.FIRST_COMPLETED)
 
         diff_time = time.time() - start_time
 
         self.assertGreater(diff_time, sleep_time_secs * 3)
 
+        # Wait for the pending tasks to complete.
+        await asyncio.gather(*pending)
+
     async def test_task_cancel_timeout(self):
         class CancelFilter(FrameProcessor):
             def __init__(self, **kwargs):

tests/test_service_switcher.py

@@ -7,10 +7,12 @@
 """Unit tests for ServiceSwitcher and related components."""
 
 import unittest
+from dataclasses import dataclass
 
 from pipecat.frames.frames import (
     Frame,
     ManuallySwitchServiceFrame,
+    SystemFrame,
     TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
@@ -52,6 +54,13 @@ class MockFrameProcessor(FrameProcessor):
         self.frame_count = 0
 
 
+@dataclass
+class DummySystemFrame(SystemFrame):
+    """A dummy system frame for testing purposes."""
+
+    text: str = ""
+
+
 class TestServiceSwitcherStrategyManual(unittest.IsolatedAsyncioTestCase):
     """Test cases for ServiceSwitcherStrategyManual."""
 
@@ -140,14 +149,22 @@ class TestServiceSwitcher(unittest.IsolatedAsyncioTestCase):
         # Send some test frames
         frames_to_send = [
             TextFrame(text="Hello 1"),
+            DummySystemFrame(text="System Message 1"),
             TextFrame(text="Hello 2"),
+            DummySystemFrame(text="System Message 2"),
             TextFrame(text="Hello 3"),
         ]
 
         await run_test(
             switcher,
             frames_to_send=frames_to_send,
-            expected_down_frames=[TextFrame, TextFrame, TextFrame],
+            expected_down_frames=[
+                DummySystemFrame,
+                DummySystemFrame,
+                TextFrame,
+                TextFrame,
+                TextFrame,
+            ],
             expected_up_frames=[],  # Expect no error frames
         )
 
@@ -156,7 +173,13 @@ class TestServiceSwitcher(unittest.IsolatedAsyncioTestCase):
         text_frames = [f for f in self.service1.processed_frames if isinstance(f, TextFrame)]
         self.assertEqual(len(text_frames), 3)
 
-        # Check that other services don't receive text frames (they might get StartFrame/EndFrame)
+        # Only service1 should have processed the system frames
+        system_frames = [
+            f for f in self.service1.processed_frames if isinstance(f, DummySystemFrame)
+        ]
+        self.assertEqual(len(system_frames), 2)
+
+        # Check that other services don't receive text frames (they still get StartFrame/EndFrame)
         service2_text_frames = [
             f for f in self.service2.processed_frames if isinstance(f, TextFrame)
         ]
@@ -166,10 +189,24 @@ class TestServiceSwitcher(unittest.IsolatedAsyncioTestCase):
         self.assertEqual(len(service2_text_frames), 0)
         self.assertEqual(len(service3_text_frames), 0)
 
+        # Check that other services don't receive dummy system frames (they still get StartFrame/EndFrame)
+        service2_system_frames = [
+            f for f in self.service2.processed_frames if isinstance(f, DummySystemFrame)
+        ]
+        service3_system_frames = [
+            f for f in self.service3.processed_frames if isinstance(f, DummySystemFrame)
+        ]
+        self.assertEqual(len(service2_system_frames), 0)
+        self.assertEqual(len(service3_system_frames), 0)
+
         # Verify the actual text frames processed
         for i, frame in enumerate(text_frames):
             self.assertEqual(frame.text, f"Hello {i + 1}")
 
+        # Verify the actual system frames processed
+        for i, frame in enumerate(system_frames):
+            self.assertEqual(frame.text, f"System Message {i + 1}")
+
     async def test_service_switching(self):
         """Test that after service switching using ManuallySwitchServiceFrame, the new active service receives frames while others don't."""
         switcher = ServiceSwitcher(self.services, ServiceSwitcherStrategyManual)

uv.lock

@@ -410,16 +410,16 @@ wheels = [
 
 [[package]]
 name = "aws-sdk-bedrock-runtime"
-version = "0.1.0"
+version = "0.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "smithy-aws-core", extra = ["eventstream", "json"], marker = "python_full_version >= '3.12'" },
     { name = "smithy-core", marker = "python_full_version >= '3.12'" },
     { name = "smithy-http", extra = ["awscrt"], marker = "python_full_version >= '3.12'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/84/e1/39971b907c83a7525bab112c9b395e1bb6d4bc23bc1712d6d7a050662217/aws_sdk_bedrock_runtime-0.1.0.tar.gz", hash = "sha256:bd062de5a48404f64e1dfe6fb8841fbbf68e8f1798c357d14eb427274cb96a2b", size = 85419, upload-time = "2025-09-29T19:40:01.855Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1d/78/48574454b3cac869df67665e4a403ebfc3abfcfba2c2ff01ccfd67d55f8f/aws_sdk_bedrock_runtime-0.1.1.tar.gz", hash = "sha256:c896f99e675c3a1ab600633a07b785f3dc9fe8ab94f640b1f992b63da2dfc784", size = 82446, upload-time = "2025-10-21T20:25:25.845Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/3d/e1/5b36bffe85010cdcd44730d1c2d5244653d57c002f440141d7fc3b9f1347/aws_sdk_bedrock_runtime-0.1.0-py3-none-any.whl", hash = "sha256:aac6ff47069d456ca5e23083d96a01e3e0cbc215414e6753c289d7d9efef3335", size = 78853, upload-time = "2025-09-29T19:40:00.341Z" },
+    { url = "https://files.pythonhosted.org/packages/83/07/62c0b70223d178c138f29124ac2f7973a6ba803abc7735b6a01a85217f3d/aws_sdk_bedrock_runtime-0.1.1-py3-none-any.whl", hash = "sha256:c0336b377b2112cf88197d3d44302fbeb3efb1101989fa49ae55e78f49cfe345", size = 74954, upload-time = "2025-10-21T20:25:24.973Z" },
 ]
 
 [[package]]
@@ -433,31 +433,31 @@ wheels = [
 
 [[package]]
 name = "awscrt"
-version = "0.28.1"
+version = "0.28.2"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a0/1c/5c9e6a7375c2a1355aadeb2d06c96c95934ec37ff29ebaab2919f59c3ff1/awscrt-0.28.1.tar.gz", hash = "sha256:70a28fd6ff3e0abb7854ea8a9133bc9e5de681a0d9bdbd8a599a23d13a448685", size = 37956730, upload-time = "2025-09-19T00:58:31.564Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d4/1b/a885a699217967c3ff0e1c49ac5b1e2a050d1a8b87d1e85e958a56e3d3f5/awscrt-0.28.2.tar.gz", hash = "sha256:9715a888f2042e710dc8aeb355963a29b77e7a4cc25a14659cebd21a5fa476c1", size = 37894849, upload-time = "2025-10-14T19:06:16.867Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/2d/75/dd62276f2907a9ffcf9f8f780c08ce9938bd0550a15c887db198b47f24d3/awscrt-0.28.1-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:47f885104065918d311102e2b08b943966717c0f3b0c5de5908d2fd08de32198", size = 3376838, upload-time = "2025-09-19T00:57:32.988Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/93/562709cdf13a7606548426ecc31326ba3f6839f91e98a1e9230208308afb/awscrt-0.28.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3df2316e77ad88c456b7eb2c9928007d379ed892154c1969d35b98653617e576", size = 3821522, upload-time = "2025-09-19T00:57:35.456Z" },
-    { url = "https://files.pythonhosted.org/packages/43/f0/6c6ff81f5a4c6d085eb450854149087bf9240c37c467c747521f47901b32/awscrt-0.28.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3a060d930939f142345f46a344e19ffc0dada657b04d02216b8adffba550c0a0", size = 4087344, upload-time = "2025-09-19T00:57:36.62Z" },
-    { url = "https://files.pythonhosted.org/packages/37/0a/71c097505add4ceea4ac05153311715acb7489cd82ec69db4570130f4698/awscrt-0.28.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:43f81ca6bfe85c38ad9765605aaaa646a1ed6fd7210dbedf67c113dd245f425e", size = 3745148, upload-time = "2025-09-19T00:57:38Z" },
-    { url = "https://files.pythonhosted.org/packages/79/1b/2b02b705a47b64e6c4d401087ddd30d4ad9af70172812ae8c62fb2b7a70c/awscrt-0.28.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fc8e2307d9dbe76842015a14701ff7e9cf2619d674621b2d55b769414e17b3fc", size = 3972439, upload-time = "2025-09-19T00:57:39.74Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/19/429c81c7a0d81a5edce9cc6d9a878c8b65d8b5b69fa5a2725a6e0b1380c1/awscrt-0.28.1-cp310-cp310-win32.whl", hash = "sha256:6e7b094587e5332d428300340dcc18794a1fcfa76d636f216fc0f5c8405ba604", size = 3915231, upload-time = "2025-09-19T00:57:41.096Z" },
-    { url = "https://files.pythonhosted.org/packages/83/81/769ad51fc6dcfd8bf9e0aa59c252013da0eb9e32c050ecbd1fc25f71689a/awscrt-0.28.1-cp310-cp310-win_amd64.whl", hash = "sha256:ac02f10f7384fdb68187f8d5d94743a271b16fa94be81481ce7684942f6a4b35", size = 4051668, upload-time = "2025-09-19T00:57:42.696Z" },
-    { url = "https://files.pythonhosted.org/packages/9e/55/0ee537d146f24d6e76eaf02d462a83c572788233603bb9bda969fbf23307/awscrt-0.28.1-cp311-abi3-macosx_10_15_universal2.whl", hash = "sha256:cb36052f9aa34e77687a8037559bbea331fc9d5d77cd71ab0cf4e6d72af73f72", size = 3376673, upload-time = "2025-09-19T00:57:43.875Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/54/12700a4b9545680baa3e2d4d0e543bb4775a639df56ee51cbb29b71e0947/awscrt-0.28.1-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fc59829152a5806eb2708aca5c5084c11dd18ecbe765e03eb314d5a360eeaa62", size = 3782870, upload-time = "2025-09-19T00:57:45.737Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/e7/7b189ace9e187b9b55ed4a6ec9a451579b2f16bd01d402f79a19cc8e1603/awscrt-0.28.1-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d2f20bc774599b9d85ce66689415da529ddd1d2215da818e005deedc4688fe61", size = 4048789, upload-time = "2025-09-19T00:57:47.327Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/e0/2e5472019906dfcc5fadcdba4bad9e69dabb95bbc0c110cfe555ee8461dc/awscrt-0.28.1-cp311-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:491b8b9c73a288cfd5e0cbdac16aabb5313d5cfc33bbe461763a5ddc26624f70", size = 3687832, upload-time = "2025-09-19T00:57:48.563Z" },
-    { url = "https://files.pythonhosted.org/packages/71/f2/7e05d371bb888ee9f15e83d189287838f7b6ea40dfc91eacb3acd24b8529/awscrt-0.28.1-cp311-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:4c6c7125b7e9fcc999eb685d1cace8d4f2ffc63f8f3d8ef7f77e1a97d9552863", size = 3913378, upload-time = "2025-09-19T00:57:50.185Z" },
-    { url = "https://files.pythonhosted.org/packages/79/6b/a542a65a22edb85d64742970c21721e66e0f9f67911a11c7a5c3626a1b17/awscrt-0.28.1-cp311-abi3-win32.whl", hash = "sha256:1dcb33d7cf8f69881ac6ef75a5b9b40816be58678b1bb07ccbe0230281bdbc81", size = 3912809, upload-time = "2025-09-19T00:57:51.797Z" },
-    { url = "https://files.pythonhosted.org/packages/df/64/16cc8a0011e3ca5dda13605befa7e6db29bfb3073c67f6e8dad90be0a8ae/awscrt-0.28.1-cp311-abi3-win_amd64.whl", hash = "sha256:670caaf556876913bcfb9d8183d43d67a6c7b52998f2f398abd1c21632a006f8", size = 4048979, upload-time = "2025-09-19T00:57:53.061Z" },
-    { url = "https://files.pythonhosted.org/packages/ca/ac/debbd3a2f03c5953b56b1c3b321bab16293f857ea3005e3f7e5dded5e0b2/awscrt-0.28.1-cp313-abi3-macosx_10_15_universal2.whl", hash = "sha256:22311d25135b937ee5617e35a6554961727527dcfa3e06efdefe187a6abe65c4", size = 3375565, upload-time = "2025-09-19T00:57:54.598Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/4f/9388917ad45c043acd7c4ab2c28b9e2b5ddf29e21a82bfc01a7626c18c04/awscrt-0.28.1-cp313-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e58740cf0e41552fdf7909e10814b312ab090ebe54741354a61507e0c6d4ebfd", size = 3775366, upload-time = "2025-09-19T00:57:56.238Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/e3/3ef301cdef76b22ce14b041e04c6cf65ba4491d00e9f5b400c0699f6c63e/awscrt-0.28.1-cp313-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9e69f163a207a8b172abbfea1f51045301ed1ac8bbaf76958a6b5e81d72e5b89", size = 4043403, upload-time = "2025-09-19T00:57:57.4Z" },
-    { url = "https://files.pythonhosted.org/packages/60/9c/4f89922333724c4da851752549ca97dd147420734ef6c4ece56d5dd65e09/awscrt-0.28.1-cp313-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:592f4b234ecafa6cde86e55e42c4fe84c4e1ffe9fb11b0a8b8f0ffb8c62fa2cc", size = 3678742, upload-time = "2025-09-19T00:57:59.055Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/d4/adb97ba5f888ed201aa1f9e9f8d6cfc0dbaf80f0e937b3acb7411febdaa8/awscrt-0.28.1-cp313-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:b16321f1d2bf5b4991a213059c1b5dc07954edfc424d154b093824465ec94ce2", size = 3908438, upload-time = "2025-09-19T00:58:00.71Z" },
-    { url = "https://files.pythonhosted.org/packages/41/ac/600ea0a6f4ba6543c50417c8e78b09f2cd73dd0f0d4c3e9e52220a8badbe/awscrt-0.28.1-cp313-abi3-win32.whl", hash = "sha256:3e0a23635aa75b4af163ff9bf5a0873928369b1ac32c8b1351741a95472ccf71", size = 3907625, upload-time = "2025-09-19T00:58:03.235Z" },
-    { url = "https://files.pythonhosted.org/packages/9e/24/d22c7197b1e53c76b5eb71d640a4728b9b7621075d8dbcc054e16b5b98f0/awscrt-0.28.1-cp313-abi3-win_amd64.whl", hash = "sha256:9849c88ca0830396724acf988e2759895118fe7dd2a23dab21978c8600d01a11", size = 4043878, upload-time = "2025-09-19T00:58:04.595Z" },
+    { url = "https://files.pythonhosted.org/packages/73/b4/1a566e493bdfa6e918ba78bcd2e45dda99a25407a4fd974db2666228d154/awscrt-0.28.2-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:bec19c0dd780293a26c809aabb9f7675b28cb3a1bf05b4a5bc9f28d5ced75a81", size = 3380735, upload-time = "2025-10-14T19:05:16.58Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/53/6602a87aead1d413c7bd77d059b301745146635cda99ee2a61ec0d23691e/awscrt-0.28.2-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:01f33076759ba6285f25ccc6016355607df2e715d0bab3a1ef2416b87a6c3ade", size = 3827084, upload-time = "2025-10-14T19:05:19.335Z" },
+    { url = "https://files.pythonhosted.org/packages/d8/62/61fe39ae5950ad00e10dcbf6e4f4f344dc93957757160c0000390331a11b/awscrt-0.28.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2b5c807b9972795ce54c05aea6918c60983c51d879ebbff7a67adb8b0d28a121", size = 4092678, upload-time = "2025-10-14T19:05:20.8Z" },
+    { url = "https://files.pythonhosted.org/packages/25/7d/e38f18cfb203e8f09842c0e3f422992887ce285ecc3bf18816d559a13c80/awscrt-0.28.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:bf4ff9c8c6a233246320c2d41d939b6e25cdae97728d827186e4771a9edda688", size = 3749978, upload-time = "2025-10-14T19:05:22.16Z" },
+    { url = "https://files.pythonhosted.org/packages/16/6f/e8a3c0daed8f7b60c76fc2721bd4e83580ddecace24e0cb0ebb99564f699/awscrt-0.28.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:0c738b83b66d1a8b43089556247fbe4adf2b73d610c7938d3bae1718a0fe8b1d", size = 3977237, upload-time = "2025-10-14T19:05:23.368Z" },
+    { url = "https://files.pythonhosted.org/packages/92/3d/8400203f02dd924bcc8255703179b0c26efd03c84f838db6f026fcef9ba6/awscrt-0.28.2-cp310-cp310-win32.whl", hash = "sha256:23c30004c736a2f826a32c9720f1ccf71e8e4deb8535da5915d6073604853098", size = 3919413, upload-time = "2025-10-14T19:05:24.477Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/5e/b5ccf377880a70425b100f1e5f5ba516ff75e291585b3dc129239fbd1ec3/awscrt-0.28.2-cp310-cp310-win_amd64.whl", hash = "sha256:859ae8a195d51f15b631147d6792953a563bfe0a1cc7a75b6750977634de54b8", size = 4056024, upload-time = "2025-10-14T19:05:25.956Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/79/94e9f0ee7c60ec6233c7ad6293589c56d5145172e49eb5328eda37d3fdd1/awscrt-0.28.2-cp311-abi3-macosx_10_15_universal2.whl", hash = "sha256:025eab99b58586d8c95f8fafe1f4695ad477eda20d1207240ee4f8ee79742059", size = 3381061, upload-time = "2025-10-14T19:05:27.187Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/b8/0da80dd58682ddf3ec204e877d5891198654647c085e65b6b8eacd214edb/awscrt-0.28.2-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e5c18d035d6cd92228e1db2f043517c1bcf9e0f6430c0af60cc34257dcca092c", size = 3788011, upload-time = "2025-10-14T19:05:28.768Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/d2/f51cf4364364399fe90d557e2fed14c1f114720191a5825898b1242bd607/awscrt-0.28.2-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c75f077e90d0220a49b75a9bca914e5aa1a3c8f28af6bce4d0332be0b98dd3cb", size = 4055226, upload-time = "2025-10-14T19:05:30.054Z" },
+    { url = "https://files.pythonhosted.org/packages/41/47/0fde8738a8c76de278ce431d8468ef18aeaca424329decca9ad5092df812/awscrt-0.28.2-cp311-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:1432c5c59a7e36b33eb2746cfbf30058f19ed43f2c117863897681f70bc246ba", size = 3692839, upload-time = "2025-10-14T19:05:31.471Z" },
+    { url = "https://files.pythonhosted.org/packages/18/25/cb3762f6b47fe503eea7f337eca7cfd044ab28bcc2452fbf298c6492ec8b/awscrt-0.28.2-cp311-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:f96703c30b22ba1e43e1bb2fe996ac7af513bea411c54dbf09a3a1af329b9a76", size = 3918023, upload-time = "2025-10-14T19:05:33.162Z" },
+    { url = "https://files.pythonhosted.org/packages/95/0a/0b609acd45dbb83c04c7ecb8c7c789f5c15bbdd422129360bde093bc4a99/awscrt-0.28.2-cp311-abi3-win32.whl", hash = "sha256:3e94f63497b454d30892d7a7ce917a451c6f33590964d3a475d93f93b20083b6", size = 3917048, upload-time = "2025-10-14T19:05:34.745Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/38/bf33abd6d09c8572f8e09488db2b0a60124767d7f5d6d9a33cf8b051b7af/awscrt-0.28.2-cp311-abi3-win_amd64.whl", hash = "sha256:3e094772b1f6fd0f8c5f7cf37655d0984739f99493f66f534979a2a7bb7fc9f6", size = 4052877, upload-time = "2025-10-14T19:05:36.01Z" },
+    { url = "https://files.pythonhosted.org/packages/10/71/4be198e472d95702434cee1f9dd889c56e22bea8554b466fad754148fd24/awscrt-0.28.2-cp313-abi3-macosx_10_15_universal2.whl", hash = "sha256:5fda9e7d0eb800491fadebe2b6c2560ac2f5742b60f4106440dca4b49da7fb03", size = 3379585, upload-time = "2025-10-14T19:05:37.225Z" },
+    { url = "https://files.pythonhosted.org/packages/43/09/77084249d07dca71352341ad3fbcfa75deaccf25bd65f9fdbb36ce1f978b/awscrt-0.28.2-cp313-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:994a795bdc83344922a15891abb30155ec292093e856eef3929dd63dd6cadaca", size = 3779843, upload-time = "2025-10-14T19:05:38.774Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/bb/fcee9365e58e5860582398317571a9a5517da258cd81c3d987b9882f61d4/awscrt-0.28.2-cp313-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:28537c4517168927ef74aa007a2e0c9f436921227934d82da31e9a1cec7e0c4a", size = 4049154, upload-time = "2025-10-14T19:05:40.301Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/8e/ac92b2707dbe05e56d0dd5af73cb4e07a3da4aee66936071123966523759/awscrt-0.28.2-cp313-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:b9fc6be63832da3ff244d56c7d9a43326d89d79e68162419c35f33e6ad033be0", size = 3683672, upload-time = "2025-10-14T19:05:41.536Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/d0/15308ec37e762691f5d1871b0f1a6e462da8e421c6c38d6724e3cf0994b2/awscrt-0.28.2-cp313-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:efb57103a368de1d33148cb70a382c4f82ac376c744de9484e0f621cef8313f3", size = 3912823, upload-time = "2025-10-14T19:05:43.781Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/cd/7693b1d72069908b7a3ee30e4ef2b5fc8f54948a96397729277cb0b0c7b4/awscrt-0.28.2-cp313-abi3-win32.whl", hash = "sha256:594dc61f4f0c1c9fb7292364d25c21810b3608cd67c0de78a032ad48f7bfd88c", size = 3911514, upload-time = "2025-10-14T19:05:45.019Z" },
+    { url = "https://files.pythonhosted.org/packages/93/d6/5d8545c967690f03d55d44ed56ceff26d88363cd7d0435fd80a1c843ac2a/awscrt-0.28.2-cp313-abi3-win_amd64.whl", hash = "sha256:a17f0ab9dc5e5301da0fb00ccc4511a136d13abbd4a9564827547333fcd7ba16", size = 4047912, upload-time = "2025-10-14T19:05:46.302Z" },
 ]
 
 [[package]]
@@ -569,6 +569,30 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/39/54/db7a801933dd2537f5376fb8a9e28caff488ef5c2d61f3a8fced55fe6336/blake3-1.0.7-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:d9046bb1e22a8607e1d0d7c3ff47e56e0a197c988502df4bf4d78563f3e9fe2c", size = 553411, upload-time = "2025-09-29T16:40:45.667Z" },
     { url = "https://files.pythonhosted.org/packages/2c/08/949cf68d16d1f731d502968bb1486e1a4bf7ef032c38fbc2ef26a2353494/blake3-1.0.7-cp313-cp313t-win32.whl", hash = "sha256:bd2f638bcc00fc09ce985ea3c642d45940e1eda198ab1f4b90cfdecbebbc9315", size = 227049, upload-time = "2025-09-29T16:40:47.446Z" },
     { url = "https://files.pythonhosted.org/packages/f2/ae/6783a5ca6235024e00a1e92ab6ca2cd855f4c61c763cf8d6d643846d110c/blake3-1.0.7-cp313-cp313t-win_amd64.whl", hash = "sha256:cb3aa1db14231c2ef0ec5acd805505ce128c39ffa510deb3384eed96fe4addcb", size = 214101, upload-time = "2025-09-29T16:40:48.656Z" },
+    { url = "https://files.pythonhosted.org/packages/32/aa/99b4b6c22972b9a854f77d97846a717448a77d079e4bd38e46a3f8ecea76/blake3-1.0.7-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:f7db997205aa420d59fb5639346e40beafb9c09252e2ec6efedca8f230f7520c", size = 346664, upload-time = "2025-10-11T18:02:54.609Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/44/e98bc5450be415a335a191b154e299e335046d11fe9514d93961902b7aed/blake3-1.0.7-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:19afec6e276f3bc154541248d92b1ecb198af2ee920025f7ce521028f9a69d8b", size = 324576, upload-time = "2025-10-11T18:02:57.062Z" },
+    { url = "https://files.pythonhosted.org/packages/74/25/23a39913c8424ac3df705ed71a00efe34cc1cdbd4588ed6eaf458ea9d7ef/blake3-1.0.7-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:006a11bbba65a95e88ddc069cca751c8812fd144d582715eeea512452fdbe80d", size = 370545, upload-time = "2025-10-11T18:02:59.824Z" },
+    { url = "https://files.pythonhosted.org/packages/db/83/9f53a86de9a5999b043febfd84765d240014da42055aeac06d1005b20b07/blake3-1.0.7-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7febeffdc8412fed105ca517cee641ac521fb9cfb750bf7e27a5cdf3ddf74a08", size = 374370, upload-time = "2025-10-11T18:03:01.412Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/4c/3290aa4fb7483975a7b3322a73692aa3cf491a77ce7ac61c216c71c6f834/blake3-1.0.7-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6c032ce7c52b71015651c0abe9fe599aa2669e6be578aa17d5f993dc93373401", size = 447808, upload-time = "2025-10-11T18:03:02.893Z" },
+    { url = "https://files.pythonhosted.org/packages/66/26/92b6e15552865416aae1aedad8b9b4d8b47ca9b73d25373622b1798c05a9/blake3-1.0.7-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5b81455f7d24b58fe26be037cc3854c28ea6eb3671ceab3b1ec0b1239aeb6fef", size = 506118, upload-time = "2025-10-11T18:03:04.51Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/ef/f158fc43a03fd366bc428a52a845bd0f884e518deda901c9216bd469867e/blake3-1.0.7-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:41b0127b0e7c8610054c421959dbe7140a81ac2c88fa9e099994fbaa529af3c1", size = 393239, upload-time = "2025-10-11T18:03:07.102Z" },
+    { url = "https://files.pythonhosted.org/packages/10/49/2a56ce897ec7ed0e25953b3873da271ea60cc107ae02ecc6655252e554c7/blake3-1.0.7-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4755ca95b4114b629d8f3570bc661916d211d52d47f57ff70e9687377ab39cb9", size = 386267, upload-time = "2025-10-11T18:03:08.904Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/c4/ee4c03ea419198b91c889ef173015b5d637a390d3f7d63cb70033a7201d6/blake3-1.0.7-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:8abe929cfd27b375e02e3dd7a690192fa4efecc52ef510df91ef01651ef08dc7", size = 549641, upload-time = "2025-10-11T18:03:10.64Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/cc/a918d6649b56fe705133e06d9958d90978aad30063d42cca4dfe23db16e9/blake3-1.0.7-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:dd607eb5ad5a9b44ff62243759aa0af4085f6f43c9b01f503561a70da63e3b94", size = 553691, upload-time = "2025-10-11T18:03:12.108Z" },
+    { url = "https://files.pythonhosted.org/packages/fd/9f/568546f555fd1555d4867c497e9413f67bf769d076e773b9ca9e07a0b6f6/blake3-1.0.7-cp314-cp314-win32.whl", hash = "sha256:a51684d1f346e7680f7c244c25b0e279e3b297f1938126e4ea8e32425ea269f5", size = 227552, upload-time = "2025-10-11T18:03:13.468Z" },
+    { url = "https://files.pythonhosted.org/packages/97/2b/d4ef7365d9f601c8a127b5993f2662d45d2cb6d430bf3dbbb7a6f0b33639/blake3-1.0.7-cp314-cp314-win_amd64.whl", hash = "sha256:a6a481719e28e2c61aafd4273d32663365d97613341b72fcdf2f6afbd426319b", size = 214719, upload-time = "2025-10-11T18:03:14.835Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/53/f697cc34e382a225d163ea0c6a35c7eb4cfd1011e85db6610adfac98e522/blake3-1.0.7-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:daa8933cd7db19143bd6b59f7ac4c7c7446767d7b2c3a748a4559aa483275fa2", size = 347071, upload-time = "2025-10-11T18:03:16.637Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/85/836dcb5c5709c2331f02ce065f7ebfaae710a6c1768cdc47ee3197645f98/blake3-1.0.7-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:24074adfffffe0fa7a7dd930cc608d6e965e70306e2c1e14d412e29ec94fa360", size = 324341, upload-time = "2025-10-11T18:03:18.073Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/48/36b2c25007933619ce60e24b9f360baaa77d08939284045476c8e157fe62/blake3-1.0.7-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dce6e6f03de2674f9860cf330d8a4fcdb63a60659435e5e31d72d174fc102d8e", size = 370140, upload-time = "2025-10-11T18:03:19.582Z" },
+    { url = "https://files.pythonhosted.org/packages/70/82/8a8977e5d56b9fb719033940c8ce34afc733190d34ab868a647a9af7b584/blake3-1.0.7-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e783f33d53a2de8d2ab845235dd53393d521b5e4a76c23d03e77e472266359d3", size = 373022, upload-time = "2025-10-11T18:03:21.143Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/c4/44017ba40804a528568b35a36c05187786830c4d891c5540d59a121a7cec/blake3-1.0.7-cp314-cp314t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:782784aef18eb61f4ce8bf2b9506b7d90f0d183176b453345b221837a18041b7", size = 447243, upload-time = "2025-10-11T18:03:22.707Z" },
+    { url = "https://files.pythonhosted.org/packages/78/c1/4fa20e68624784082734d31b8c9c80ad226658c024e61b9f9b6751ba0a4a/blake3-1.0.7-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6062122e77f40e3733cac2ef3f25e0fc7f555e352fe6f513f8404ad11dc69974", size = 506149, upload-time = "2025-10-11T18:03:24.424Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/63/af65466e27e7b92800a068afaee11b2fa071e34a7f5900f8e13832f18185/blake3-1.0.7-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6c2614bc9d69fd6067571f3bb37b3b07a6b86a56167553ad4784a3c508771f39", size = 393243, upload-time = "2025-10-11T18:03:25.872Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/82/54a4807a3243d0e094ada9d65687aeb40059587e374b3beb9c89f6552c9b/blake3-1.0.7-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d6df2bd56c43bdeb6699d4af0a0dd0d77537d95cb4a5dde4b39ed6e54cc725d6", size = 386318, upload-time = "2025-10-11T18:03:27.338Z" },
+    { url = "https://files.pythonhosted.org/packages/42/e8/32b56531b5d9da67e476735ceaec7c3bf89310629abeeafb03c724145c88/blake3-1.0.7-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:8b635cf4350caf459ecb335b32be622068423245bda457d5bc159106eb20f912", size = 548945, upload-time = "2025-10-11T18:03:28.779Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/50/33b1aca708be629e285a537f1adf34dfcabc4c30b28c436361323d11f593/blake3-1.0.7-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:f96a685775f87ddf75ff495dc9698703268c66c170caca977347427ef8d52324", size = 553564, upload-time = "2025-10-11T18:03:30.247Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/07/8b17cbf40ccd9afeed6ae9f55018181786b30ff4e079ac8bf4ca4799e47b/blake3-1.0.7-cp314-cp314t-win32.whl", hash = "sha256:0633b7d9bad87dc7fce545042353f2e056604d993f71d1dce666a9f5edc13e05", size = 227345, upload-time = "2025-10-11T18:03:31.933Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/8a/ab9de8a73616350759356a483f440212bc2a22fc9aaa77cabbf06c3483db/blake3-1.0.7-cp314-cp314t-win_amd64.whl", hash = "sha256:5e356daa0089968dc1ff1d0d112e7cc1700533441d8f30ae99f835a94dc8b0f3", size = 213964, upload-time = "2025-10-11T18:03:33.919Z" },
 ]
 
 [[package]]
@@ -867,16 +891,16 @@ wheels = [
 
 [[package]]
 name = "compressed-tensors"
-version = "0.10.2"
+version = "0.10.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pydantic" },
     { name = "torch" },
     { name = "transformers" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c0/86/d43d369abc81ec63ec7b8f6f27fc8b113ea0fd18a4116ae12063387b8b34/compressed_tensors-0.10.2.tar.gz", hash = "sha256:6de13ac535d7ffdd8890fad3d229444c33076170acaa8fab6bab8ecfa96c1d8f", size = 173459, upload-time = "2025-06-23T13:19:06.135Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/40/eb/2229523a539e8074b238c225d168f734f6f056ab4ea2278eefe752f4a6f3/compressed_tensors-0.10.1.tar.gz", hash = "sha256:f99ce620ddcf8a657eaa7995daf5faa8e988d4b4cadc595bf2c4ff9346c2c19a", size = 126778, upload-time = "2025-06-06T18:25:16.538Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/43/ac/56bb4b6b3150783119479e2f05e32ebfc39ca6ff8e6fcd45eb178743b39e/compressed_tensors-0.10.2-py3-none-any.whl", hash = "sha256:e1b4d9bc2006e3fd3a938e59085f318fdb280c5af64688a4792bf1bc263e579d", size = 169030, upload-time = "2025-06-23T13:19:03.487Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/07/e70a0b9efc24a32740396c404e7213c62b8aeb4a577ed5a3f191f8d7806b/compressed_tensors-0.10.1-py3-none-any.whl", hash = "sha256:b8890735522c119900e8d4192cced0b0f70a98440ae070448cb699165c404659", size = 116998, upload-time = "2025-06-06T18:25:14.54Z" },
 ]
 
 [[package]]
@@ -1258,13 +1282,13 @@ wheels = [
 
 [[package]]
 name = "daily-python"
-version = "0.19.9"
+version = "0.21.0"
 source = { registry = "https://pypi.org/simple" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/22/85/6064c3225e5b190e522e8f3bc6a460efc5e3e6632f16fd5f9799c44ba57a/daily_python-0.19.9-cp37-abi3-macosx_10_15_x86_64.whl", hash = "sha256:cbc558ad7d49e79b550bf7567b9ceae75e2864d4fcaf41c90377b620e38a2461", size = 13365213, upload-time = "2025-09-06T00:31:00.224Z" },
-    { url = "https://files.pythonhosted.org/packages/23/58/af986c6881180a46a7b60dd418ce58d6d7c0c4ffc48d261748067c679317/daily_python-0.19.9-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:446bb9ee848d88bc68ca29a2216793c9b5ebaf5991bf604daf76f7c5a53d5919", size = 11711673, upload-time = "2025-09-06T00:31:02.526Z" },
-    { url = "https://files.pythonhosted.org/packages/9d/48/1cad4c3e92cdb5ef06467d972c76a510fe5e807513334b10ad7f8c21bf74/daily_python-0.19.9-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:2facaf82b614404c642c70bbf0874fb045d8ad46400acb051470cd4df93cb4db", size = 13679393, upload-time = "2025-09-06T00:31:04.999Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/e9/354f4699619e83d13e266256b2352b21741ac527e3e5ab5f2264d5c482cd/daily_python-0.19.9-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:ffc205efca7b47739efd358febab17577248c8db2ebc4d17d819307a83b9eefc", size = 14221932, upload-time = "2025-09-06T00:31:07.471Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/11/99590f8b7aad077f3f9b5b59d39b010aee0bd01b14dece8ae1e93d8080e7/daily_python-0.21.0-cp37-abi3-macosx_10_15_x86_64.whl", hash = "sha256:bdec96417825181559769bb2258ae688d1215949a1878336194e36fb452274a8", size = 13277066, upload-time = "2025-10-29T00:20:49.523Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/db/8c57f1a1b713ba3393584ac2be32d8074d3022a2c2c17c28eb4cd2aa3629/daily_python-0.21.0-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:18677fa1415a0dc48b891cdf2fb8fe9dabc70e1b019d5aaa3d0699ccc8d187c9", size = 11644908, upload-time = "2025-10-29T00:20:52.106Z" },
+    { url = "https://files.pythonhosted.org/packages/64/b6/b03f2f58a367d6ef4bb728715471542fdfa68afa8a177670139c3a2aadb7/daily_python-0.21.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:97eb97352fe74227061b678e330b8befcfa4c694feb6eb2b09fe6eacec00ad6d", size = 13652356, upload-time = "2025-10-29T00:20:54.813Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/76/bde65f6f8d4c1679dc6c185fa37dae9223f6ddb4b7ced728ef46504956f7/daily_python-0.21.0-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:68c3e36f609fc2fce79e4d17ecf1021eadd836506db6c5125f95c682bcf3612a", size = 14304643, upload-time = "2025-10-29T00:20:57.194Z" },
 ]
 
 [[package]]
@@ -2726,7 +2750,7 @@ wheels = [
 
 [[package]]
 name = "langchain-core"
-version = "0.3.77"
+version = "0.3.79"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "jsonpatch" },
@@ -2737,23 +2761,23 @@ dependencies = [
     { name = "tenacity" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/40/cc/786184e5f6a921a2aa4d2ac51d3adf0cd037289f3becff39644bee9654ee/langchain_core-0.3.77.tar.gz", hash = "sha256:1d6f2ad6bb98dd806c6c66a822fa93808d821e9f0348b28af0814b3a149830e7", size = 580255, upload-time = "2025-10-01T14:34:37.368Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c8/99/f926495f467e0f43289f12e951655d267d1eddc1136c3cf4dd907794a9a7/langchain_core-0.3.79.tar.gz", hash = "sha256:024ba54a346dd9b13fb8b2342e0c83d0111e7f26fa01f545ada23ad772b55a60", size = 580895, upload-time = "2025-10-09T21:59:08.359Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/64/18/e7462ae0ce57caa9f6d5d975dca861e9a751e5ca253d60a809e0d833eac3/langchain_core-0.3.77-py3-none-any.whl", hash = "sha256:9966dfe3d8365847c5fb85f97dd20e3e21b1904ae87cfd9d362b7196fb516637", size = 449525, upload-time = "2025-10-01T14:34:35.672Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/71/46b0efaf3fc6ad2c2bd600aef500f1cb2b7038a4042f58905805630dd29d/langchain_core-0.3.79-py3-none-any.whl", hash = "sha256:92045bfda3e741f8018e1356f83be203ec601561c6a7becfefe85be5ddc58fdb", size = 449779, upload-time = "2025-10-09T21:59:06.493Z" },
 ]
 
 [[package]]
 name = "langchain-openai"
-version = "0.3.23"
+version = "0.3.29"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "langchain-core" },
     { name = "openai" },
     { name = "tiktoken" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/74/f1/575120e829430f9bdcfc2c5c4121f04b1b5a143d96e572ff32399b787ef2/langchain_openai-0.3.23.tar.gz", hash = "sha256:73411c06e04bc145db7146a6fcf33dd0f1a85130499dcae988829a4441ddaa66", size = 647923, upload-time = "2025-06-13T14:24:31.388Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/5b/56/2e2010d15118ac52760f92ebf6ce75b3508e7a1023107ea04233fd6263e0/langchain_openai-0.3.29.tar.gz", hash = "sha256:83a0455f8ce874aa1806131ca3b4db08e482be037b7457a9b3ca21a213d2ab47", size = 766499, upload-time = "2025-08-08T15:12:32.402Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/71/65/88060305d5d627841bc8da7e9fb31fb603e5b103b4e5ec5b4d1a7edfbc3b/langchain_openai-0.3.23-py3-none-any.whl", hash = "sha256:624794394482c0923823f0aac44979968d77fdcfa810e42d4b0abd8096199a40", size = 65392, upload-time = "2025-06-13T14:24:30.263Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/f2/a6a73beec15e90605e6a24c4498a8592d79a72c8e81c18ed0f5e9b7308e9/langchain_openai-0.3.29-py3-none-any.whl", hash = "sha256:71ae6791b3e017ec892a8062f993edc882c6665fd8385aa66e9dc3bff8205996", size = 74316, upload-time = "2025-08-08T15:12:30.794Z" },
 ]
 
 [[package]]
@@ -3209,23 +3233,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4b/b4/b61eeb92c424947675492dec3a411bdbeae307dfd78162d65ab47e8c3b4f/mlx-0.29.2-cp313-cp313-manylinux_2_35_x86_64.whl", hash = "sha256:c3b9a9aee13f346d060966472954eebe99d9f1b295c9a237c9a000f1ef9adf2c", size = 648709, upload-time = "2025-09-26T22:26:03.452Z" },
 ]
 
-[[package]]
-name = "mlx-lm"
-version = "0.28.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "jinja2" },
-    { name = "mlx" },
-    { name = "numpy" },
-    { name = "protobuf" },
-    { name = "pyyaml" },
-    { name = "transformers" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/1c/d7/fdde445c7bd443a2ed23badda6064f1477c4051543922106f365e94082cd/mlx_lm-0.28.2.tar.gz", hash = "sha256:d28752635ed5c89ff2b41361916c928e6b16f765c07b2908044e1dcaf921ed9b", size = 209374, upload-time = "2025-10-02T14:23:57.497Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f2/1c/89e0f60d45e364de8507065f73aeb8d2fd810d6cb95a9a512880b09399d5/mlx_lm-0.28.2-py3-none-any.whl", hash = "sha256:1501529e625d0d648216f7bb543b8b449d5fd17bd598f635536dbc1fbde6d1d6", size = 284600, upload-time = "2025-10-02T14:23:56.395Z" },
-]
-
 [[package]]
 name = "mlx-metal"
 version = "0.29.2"
@@ -3851,7 +3858,7 @@ wheels = [
 
 [[package]]
 name = "openai"
-version = "1.74.0"
+version = "1.97.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
@@ -3863,9 +3870,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/75/86/c605a6e84da0248f2cebfcd864b5a6076ecf78849245af5e11d2a5ec7977/openai-1.74.0.tar.gz", hash = "sha256:592c25b8747a7cad33a841958f5eb859a785caea9ee22b9e4f4a2ec062236526", size = 427571, upload-time = "2025-04-14T16:45:25.062Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/a6/57/1c471f6b3efb879d26686d31582997615e969f3bb4458111c9705e56332e/openai-1.97.1.tar.gz", hash = "sha256:a744b27ae624e3d4135225da9b1c89c107a2a7e5bc4c93e5b7b5214772ce7a4e", size = 494267, upload-time = "2025-07-22T13:10:12.607Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a9/91/8c150f16a96367e14bd7d20e86e0bbbec3080e3eb593e63f21a7f013f8e4/openai-1.74.0-py3-none-any.whl", hash = "sha256:aff3e0f9fb209836382ec112778667027f4fd6ae38bdb2334bc9e173598b092a", size = 644790, upload-time = "2025-04-14T16:45:23.041Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/35/412a0e9c3f0d37c94ed764b8ac7adae2d834dbd20e69f6aca582118e0f55/openai-1.97.1-py3-none-any.whl", hash = "sha256:4e96bbdf672ec3d44968c9ea39d2c375891db1acc1794668d8149d5fa6000606", size = 764380, upload-time = "2025-07-22T13:10:10.689Z" },
 ]
 
 [[package]]
@@ -3904,7 +3911,7 @@ wheels = [
 
 [[package]]
 name = "openpipe"
-version = "4.50.0"
+version = "5.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anthropic" },
@@ -3913,9 +3920,9 @@ dependencies = [
     { name = "openai" },
     { name = "python-dateutil" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ec/0b/5ac4afd2253e058463fe46b44ebdf9cf153af343b457f13e9e592943c16d/openpipe-4.50.0.tar.gz", hash = "sha256:a2b1bf7a30a8d4c2cf45b85c749839ea9811e36f9d03916df8ffa343d9193a0e", size = 98954, upload-time = "2025-04-15T18:13:36.935Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/7c/34/b487bc0ff60d3ed634e6f7bc34b5138f04e6ae319cc6578001822df93901/openpipe-5.0.0.tar.gz", hash = "sha256:040acc526fece42ba505fcedd8cd584f42482c9bd01f16b2538c9ea9c82882f4", size = 98910, upload-time = "2025-07-31T01:36:29.482Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/92/39/04870a3157d4ad6e8b1671f584da3e064750ccd64aa08339c6fc6dbd3a1c/openpipe-4.50.0-py3-none-any.whl", hash = "sha256:2071c3edbba3e08ceb977ad8c12d407f4da86c0c3815447fa33674d918276e5e", size = 440892, upload-time = "2025-04-15T18:13:35.258Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/5e/516010c25a32884a87e1f8303a292f3981fa382cc7570a9ed88fb28681d5/openpipe-5.0.0-py3-none-any.whl", hash = "sha256:c04af7afb4d9bcd52e1250757dd93d0e0ed19c9ff4b524f131dd94aadf4c1a9b", size = 439951, upload-time = "2025-07-31T01:36:28.003Z" },
 ]
 
 [[package]]
@@ -3931,6 +3938,67 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/91/48/28ed9e55dcf2f453128df738210a980e09f4e468a456fa3c763dbc8be70a/opentelemetry_api-1.37.0-py3-none-any.whl", hash = "sha256:accf2024d3e89faec14302213bc39550ec0f4095d1cf5ca688e1bfb1c8612f47", size = 65732, upload-time = "2025-09-11T10:28:41.826Z" },
 ]
 
+[[package]]
+name = "opentelemetry-exporter-otlp"
+version = "1.37.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "opentelemetry-exporter-otlp-proto-grpc" },
+    { name = "opentelemetry-exporter-otlp-proto-http" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/64/df/47fde1de15a3d5ad410e98710fac60cd3d509df5dc7ec1359b71d6bf7e70/opentelemetry_exporter_otlp-1.37.0.tar.gz", hash = "sha256:f85b1929dd0d750751cc9159376fb05aa88bb7a08b6cdbf84edb0054d93e9f26", size = 6145, upload-time = "2025-09-11T10:29:03.075Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f5/23/7e35e41111e3834d918e414eca41555d585e8860c9149507298bb3b9b061/opentelemetry_exporter_otlp-1.37.0-py3-none-any.whl", hash = "sha256:bd44592c6bc7fc3e5c0a9b60f2ee813c84c2800c449e59504ab93f356cc450fc", size = 7019, upload-time = "2025-09-11T10:28:44.094Z" },
+]
+
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-common"
+version = "1.37.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "opentelemetry-proto" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dc/6c/10018cbcc1e6fff23aac67d7fd977c3d692dbe5f9ef9bb4db5c1268726cc/opentelemetry_exporter_otlp_proto_common-1.37.0.tar.gz", hash = "sha256:c87a1bdd9f41fdc408d9cc9367bb53f8d2602829659f2b90be9f9d79d0bfe62c", size = 20430, upload-time = "2025-09-11T10:29:03.605Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/08/13/b4ef09837409a777f3c0af2a5b4ba9b7af34872bc43609dda0c209e4060d/opentelemetry_exporter_otlp_proto_common-1.37.0-py3-none-any.whl", hash = "sha256:53038428449c559b0c564b8d718df3314da387109c4d36bd1b94c9a641b0292e", size = 18359, upload-time = "2025-09-11T10:28:44.939Z" },
+]
+
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-grpc"
+version = "1.37.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "googleapis-common-protos" },
+    { name = "grpcio" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-exporter-otlp-proto-common" },
+    { name = "opentelemetry-proto" },
+    { name = "opentelemetry-sdk" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d1/11/4ad0979d0bb13ae5a845214e97c8d42da43980034c30d6f72d8e0ebe580e/opentelemetry_exporter_otlp_proto_grpc-1.37.0.tar.gz", hash = "sha256:f55bcb9fc848ce05ad3dd954058bc7b126624d22c4d9e958da24d8537763bec5", size = 24465, upload-time = "2025-09-11T10:29:04.172Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/39/17/46630b74751031a658706bef23ac99cdc2953cd3b2d28ec90590a0766b3e/opentelemetry_exporter_otlp_proto_grpc-1.37.0-py3-none-any.whl", hash = "sha256:aee5104835bf7993b7ddaaf380b6467472abaedb1f1dbfcc54a52a7d781a3890", size = 19305, upload-time = "2025-09-11T10:28:45.776Z" },
+]
+
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-http"
+version = "1.37.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "googleapis-common-protos" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-exporter-otlp-proto-common" },
+    { name = "opentelemetry-proto" },
+    { name = "opentelemetry-sdk" },
+    { name = "requests" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5d/e3/6e320aeb24f951449e73867e53c55542bebbaf24faeee7623ef677d66736/opentelemetry_exporter_otlp_proto_http-1.37.0.tar.gz", hash = "sha256:e52e8600f1720d6de298419a802108a8f5afa63c96809ff83becb03f874e44ac", size = 17281, upload-time = "2025-09-11T10:29:04.844Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e9/e9/70d74a664d83976556cec395d6bfedd9b85ec1498b778367d5f93e373397/opentelemetry_exporter_otlp_proto_http-1.37.0-py3-none-any.whl", hash = "sha256:54c42b39945a6cc9d9a2a33decb876eabb9547e0dcb49df090122773447f1aef", size = 19576, upload-time = "2025-09-11T10:28:46.726Z" },
+]
+
 [[package]]
 name = "opentelemetry-instrumentation"
 version = "0.58b0"
@@ -3960,6 +4028,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a5/54/add1076cb37980e617723a96e29c84006983e8ad6fc589dde7f69ddc57d4/opentelemetry_instrumentation_threading-0.58b0-py3-none-any.whl", hash = "sha256:eacc072881006aceb5b9b6831bcdce718c67ef6f31ac0b32bd6a23a94d979b4a", size = 9312, upload-time = "2025-09-11T11:41:58.603Z" },
 ]
 
+[[package]]
+name = "opentelemetry-proto"
+version = "1.37.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dd/ea/a75f36b463a36f3c5a10c0b5292c58b31dbdde74f6f905d3d0ab2313987b/opentelemetry_proto-1.37.0.tar.gz", hash = "sha256:30f5c494faf66f77faeaefa35ed4443c5edb3b0aa46dad073ed7210e1a789538", size = 46151, upload-time = "2025-09-11T10:29:11.04Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c4/25/f89ea66c59bd7687e218361826c969443c4fa15dfe89733f3bf1e2a9e971/opentelemetry_proto-1.37.0-py3-none-any.whl", hash = "sha256:8ed8c066ae8828bbf0c39229979bdf583a126981142378a9cbe9d6fd5701c6e2", size = 72534, upload-time = "2025-09-11T10:28:56.831Z" },
+]
+
 [[package]]
 name = "opentelemetry-sdk"
 version = "1.37.0"
@@ -3987,6 +4067,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/07/90/68152b7465f50285d3ce2481b3aec2f82822e3f52e5152eeeaf516bab841/opentelemetry_semantic_conventions-0.58b0-py3-none-any.whl", hash = "sha256:5564905ab1458b96684db1340232729fce3b5375a06e140e8904c78e4f815b28", size = 207954, upload-time = "2025-09-11T10:28:59.218Z" },
 ]
 
+[[package]]
+name = "opentelemetry-semantic-conventions-ai"
+version = "0.4.13"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/e6/40b59eda51ac47009fb47afcdf37c6938594a0bd7f3b9fadcbc6058248e3/opentelemetry_semantic_conventions_ai-0.4.13.tar.gz", hash = "sha256:94efa9fb4ffac18c45f54a3a338ffeb7eedb7e1bb4d147786e77202e159f0036", size = 5368, upload-time = "2025-08-22T10:14:17.387Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/35/b5/cf25da2218910f0d6cdf7f876a06bed118c4969eacaf60a887cbaef44f44/opentelemetry_semantic_conventions_ai-0.4.13-py3-none-any.whl", hash = "sha256:883a30a6bb5deaec0d646912b5f9f6dcbb9f6f72557b73d0f2560bf25d13e2d5", size = 6080, upload-time = "2025-08-22T10:14:16.477Z" },
+]
+
 [[package]]
 name = "orjson"
 version = "3.11.3"
@@ -4544,11 +4633,11 @@ requires-dist = [
     { name = "aiortc", marker = "extra == 'webrtc'", specifier = ">=1.13.0,<2" },
     { name = "anthropic", marker = "extra == 'anthropic'", specifier = "~=0.49.0" },
     { name = "audioop-lts", marker = "python_full_version >= '3.13'", specifier = "~=0.2.1" },
-    { name = "aws-sdk-bedrock-runtime", marker = "python_full_version >= '3.12' and extra == 'aws-nova-sonic'", specifier = "~=0.1.0" },
+    { name = "aws-sdk-bedrock-runtime", marker = "python_full_version >= '3.12' and extra == 'aws-nova-sonic'", specifier = "~=0.1.1" },
     { name = "azure-cognitiveservices-speech", marker = "extra == 'azure'", specifier = "~=1.42.0" },
     { name = "cartesia", marker = "extra == 'cartesia'", specifier = "~=2.0.3" },
     { name = "coremltools", marker = "extra == 'local-smart-turn'", specifier = ">=8.0" },
-    { name = "daily-python", marker = "extra == 'daily'", specifier = "~=0.19.9" },
+    { name = "daily-python", marker = "extra == 'daily'", specifier = "~=0.21.0" },
     { name = "deepgram-sdk", marker = "extra == 'deepgram'", specifier = "~=4.7.0" },
     { name = "docstring-parser", specifier = "~=0.16" },
     { name = "einops", marker = "extra == 'moondream'", specifier = "~=0.8.0" },
@@ -4579,9 +4668,9 @@ requires-dist = [
     { name = "nvidia-riva-client", marker = "extra == 'riva'", specifier = "~=2.21.1" },
     { name = "onnxruntime", marker = "extra == 'local-smart-turn-v3'", specifier = ">=1.20.1,<2" },
     { name = "onnxruntime", marker = "extra == 'silero'", specifier = ">=1.20.1,<2" },
-    { name = "openai", specifier = ">=1.74.0,<=1.99.1" },
+    { name = "openai", specifier = ">=1.74.0,<3" },
     { name = "opencv-python", marker = "extra == 'webrtc'", specifier = ">=4.11.0.86,<5" },
-    { name = "openpipe", marker = "extra == 'openpipe'", specifier = "~=4.50.0" },
+    { name = "openpipe", marker = "extra == 'openpipe'", specifier = ">=4.50.0,<6" },
     { name = "opentelemetry-api", marker = "extra == 'tracing'", specifier = ">=1.33.0" },
     { name = "opentelemetry-instrumentation", marker = "extra == 'tracing'", specifier = ">=0.54b0" },
     { name = "opentelemetry-sdk", marker = "extra == 'tracing'", specifier = ">=1.33.0" },
@@ -4619,7 +4708,7 @@ requires-dist = [
     { name = "simli-ai", marker = "extra == 'simli'", specifier = "~=0.1.10" },
     { name = "soundfile", marker = "extra == 'soundfile'", specifier = "~=0.13.0" },
     { name = "soxr", specifier = "~=0.5.0" },
-    { name = "speechmatics-rt", marker = "extra == 'speechmatics'", specifier = ">=0.4.0" },
+    { name = "speechmatics-rt", marker = "extra == 'speechmatics'", specifier = ">=0.5.0" },
     { name = "strands-agents", marker = "extra == 'strands'", specifier = ">=1.9.1,<2" },
     { name = "tenacity", marker = "extra == 'livekit'", specifier = ">=8.2.3,<10.0.0" },
     { name = "timm", marker = "extra == 'moondream'", specifier = "~=1.0.13" },
@@ -4961,172 +5050,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a5/8b/7f9a061c1cc2b230f9ac02a6003fcd14c85ce1828013aecbaf45aa988d20/PyAudio-0.2.14-cp313-cp313-win_amd64.whl", hash = "sha256:692d8c1446f52ed2662120bcd9ddcb5aa2b71f38bda31e58b19fb4672fffba69", size = 173655, upload-time = "2024-11-20T19:12:13.616Z" },
 ]
 
-[[package]]
-name = "pybase64"
-version = "1.4.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/04/14/43297a7b7f0c1bf0c00b596f754ee3ac946128c64d21047ccf9c9bbc5165/pybase64-1.4.2.tar.gz", hash = "sha256:46cdefd283ed9643315d952fe44de80dc9b9a811ce6e3ec97fd1827af97692d0", size = 137246, upload-time = "2025-07-27T13:08:57.808Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f3/6d/0a7159c24ed35c8b9190b148376ad9b96598354f94ede29df74861da9ec6/pybase64-1.4.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:82b4593b480773b17698fef33c68bae0e1c474ba07663fad74249370c46b46c9", size = 38240, upload-time = "2025-07-27T13:02:17.876Z" },
-    { url = "https://files.pythonhosted.org/packages/86/2e/dad4cd832a90a49d98867e824180585e7c928504987d37304bccae11a314/pybase64-1.4.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a126f29d29cb4a498db179135dbf955442a0de5b00f374523f5dcceb9074ff58", size = 31658, upload-time = "2025-07-27T13:02:20.823Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/d8/30ea35dc2c8c568be93e1379efcaa35092e37efa2ce7f1985ccc63babee7/pybase64-1.4.2-cp310-cp310-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:1eef93c29cc5567480d168f9cc1ebd3fc3107c65787aed2019a8ea68575a33e0", size = 65963, upload-time = "2025-07-27T13:02:22.376Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/da/1c22f2a21d6bb9ec2a214d15ae02d5b20a95335de218a0ecbf769c535a5c/pybase64-1.4.2-cp310-cp310-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:17b871a34aaeb0644145cb6bf28feb163f593abea11aec3dbcc34a006edfc828", size = 68887, upload-time = "2025-07-27T13:02:23.606Z" },
-    { url = "https://files.pythonhosted.org/packages/ac/8d/e04d489ba99b444ce94b4d5b232365d00b0f0e8564275d7ba7434dcabe72/pybase64-1.4.2-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1f734e16293637a35d282ce594eb05a7a90ea3ae2bc84a3496a5df9e6b890725", size = 57503, upload-time = "2025-07-27T13:02:24.83Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/b8/5ec9c334f30cf898709a084d596bf4b47aec2e07870f07bac5cf39754eca/pybase64-1.4.2-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:22bd38db2d990d5545dde83511edeec366630d00679dbd945472315c09041dc6", size = 54517, upload-time = "2025-07-27T13:02:26.006Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/5a/6e4424ecca041e53aa7c14525f99edd43d0117c23c5d9cb14e931458a536/pybase64-1.4.2-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:dc65cee686dda72007b7541b2014f33ee282459c781b9b61305bd8b9cfadc8e1", size = 57167, upload-time = "2025-07-27T13:02:27.47Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/d0/13f1a9467cf565eecc21dce89fb0723458d8c563d2ccfb99b96e8318dfd5/pybase64-1.4.2-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:1e79641c420a22e49c67c046895efad05bf5f8b1dbe0dd78b4af3ab3f2923fe2", size = 57718, upload-time = "2025-07-27T13:02:28.631Z" },
-    { url = "https://files.pythonhosted.org/packages/3e/34/d80335c36ad9400b18b4f92e9f680cf7646102fe4919f7bce5786a2ccb7b/pybase64-1.4.2-cp310-cp310-manylinux_2_31_riscv64.whl", hash = "sha256:12f5e7db522ef780a8b333dab5f7d750d270b23a1684bc2235ba50756c7ba428", size = 53021, upload-time = "2025-07-27T13:02:29.823Z" },
-    { url = "https://files.pythonhosted.org/packages/68/57/504ff75f7c78df28be126fe6634083d28d7f84c17e04a74a7dcb50ab2377/pybase64-1.4.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a618b1e1a63e75dd40c2a397d875935ed0835464dc55cb1b91e8f880113d0444", size = 56306, upload-time = "2025-07-27T13:02:31.314Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/bc/2d21cda8b73c8c9f5cd3d7e6e26dd6dfc96491052112f282332a3d5bf1d9/pybase64-1.4.2-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:89b0a51702c7746fa914e75e680ad697b979cdead6b418603f56a6fc9de2f50f", size = 50101, upload-time = "2025-07-27T13:02:32.662Z" },
-    { url = "https://files.pythonhosted.org/packages/88/6d/51942e7737bb0711ca3e55db53924fd7f07166d79da5508ab8f5fd5972a8/pybase64-1.4.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:c5161b8b82f8ba5dbbc3f76e0270622a2c2fdb9ffaf092d8f774ad7ec468c027", size = 66555, upload-time = "2025-07-27T13:02:34.122Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/c8/c46024d196402e7be4d3fad85336863a34816c3436c51fcf9c7c0781bf11/pybase64-1.4.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:2168de920c9b1e57850e9ff681852923a953601f73cc96a0742a42236695c316", size = 55684, upload-time = "2025-07-27T13:02:35.427Z" },
-    { url = "https://files.pythonhosted.org/packages/6a/c5/953782c9d599ff5217ee87f19e317c494cd4840afcab4c48f99cb78ca201/pybase64-1.4.2-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:7a1e3dc977562abe40ab43483223013be71b215a5d5f3c78a666e70a5076eeec", size = 52475, upload-time = "2025-07-27T13:02:36.634Z" },
-    { url = "https://files.pythonhosted.org/packages/05/fb/57d36173631aab67ca4558cdbde1047fc67a09b77f9c53addd57c7e9fdd4/pybase64-1.4.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:4cf1e8a57449e48137ef4de00a005e24c3f1cffc0aafc488e36ceb5bb2cbb1da", size = 53943, upload-time = "2025-07-27T13:02:37.777Z" },
-    { url = "https://files.pythonhosted.org/packages/75/73/23e5bb0bffac0cabe2d11d1c618f6ef73da9f430da03c5249931e3c49b63/pybase64-1.4.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:d8e1a381ba124f26a93d5925efbf6e6c36287fc2c93d74958e8b677c30a53fc0", size = 68411, upload-time = "2025-07-27T13:02:39.302Z" },
-    { url = "https://files.pythonhosted.org/packages/ce/e7/0d5c99e5e61ff5e46949a0128b49fc2c47afc0d2b815333459b17aa9d467/pybase64-1.4.2-cp310-cp310-win32.whl", hash = "sha256:8fdd9c5b60ec9a1db854f5f96bba46b80a9520069282dc1d37ff433eb8248b1f", size = 33614, upload-time = "2025-07-27T13:02:40.478Z" },
-    { url = "https://files.pythonhosted.org/packages/23/40/879b6de61d7c07a2cbf76b75e9739c4938c3a1f66ac03243f2ff7ec9fb6b/pybase64-1.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:37a6c73f14c6539c0ad1aebf0cce92138af25c99a6e7aee637d9f9fc634c8a40", size = 35790, upload-time = "2025-07-27T13:02:41.864Z" },
-    { url = "https://files.pythonhosted.org/packages/d2/e2/75cec12880ce3f47a79a2b9a0cdc766dc0429a7ce967bb3ab3a4b55a7f6b/pybase64-1.4.2-cp310-cp310-win_arm64.whl", hash = "sha256:b3280d03b7b361622c469d005cc270d763d9e29d0a490c26addb4f82dfe71a79", size = 30900, upload-time = "2025-07-27T13:02:43.022Z" },
-    { url = "https://files.pythonhosted.org/packages/da/fb/edaa56bbf04715efc3c36966cc0150e01d7a8336c3da182f850b7fd43d32/pybase64-1.4.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:26284ef64f142067293347bcc9d501d2b5d44b92eab9d941cb10a085fb01c666", size = 38238, upload-time = "2025-07-27T13:02:44.224Z" },
-    { url = "https://files.pythonhosted.org/packages/28/a4/ca1538e9adf08f5016b3543b0060c18aea9a6e805dd20712a197c509d90d/pybase64-1.4.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:52dd32fe5cbfd8af8f3f034a4a65ee61948c72e5c358bf69d59543fc0dbcf950", size = 31659, upload-time = "2025-07-27T13:02:45.445Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/8f/f9b49926a60848ba98350dd648227ec524fb78340b47a450c4dbaf24b1bb/pybase64-1.4.2-cp311-cp311-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:37f133e8c96427995480bb6d396d9d49e949a3e829591845bb6a5a7f215ca177", size = 68318, upload-time = "2025-07-27T13:02:46.644Z" },
-    { url = "https://files.pythonhosted.org/packages/29/9b/6ed2dd2bc8007f33b8316d6366b0901acbdd5665b419c2893b3dd48708de/pybase64-1.4.2-cp311-cp311-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a6ee3874b0abbdd4c903d3989682a3f016fd84188622879f6f95a5dc5718d7e5", size = 71357, upload-time = "2025-07-27T13:02:47.937Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/69/be9ac8127da8d8339db7129683bd2975cecb0bf40a82731e1a492577a177/pybase64-1.4.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5c69f177b1e404b22b05802127d6979acf4cb57f953c7de9472410f9c3fdece7", size = 59817, upload-time = "2025-07-27T13:02:49.163Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/a2/e3e09e000b509609276ee28b71beb0b61462d4a43b3e0db0a44c8652880c/pybase64-1.4.2-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:80c817e88ef2ca3cc9a285fde267690a1cb821ce0da4848c921c16f0fec56fda", size = 56639, upload-time = "2025-07-27T13:02:50.384Z" },
-    { url = "https://files.pythonhosted.org/packages/01/70/ad7eff88aa4f1be06db705812e1f01749606933bf8fe9df553bb04b703e6/pybase64-1.4.2-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:7a4bb6e7e45bfdaea0f2aaf022fc9a013abe6e46ccea31914a77e10f44098688", size = 59368, upload-time = "2025-07-27T13:02:51.883Z" },
-    { url = "https://files.pythonhosted.org/packages/9d/82/0cd1b4bcd2a4da7805cfa04587be783bf9583b34ac16cadc29cf119a4fa2/pybase64-1.4.2-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:2710a80d41a2b41293cb0e5b84b5464f54aa3f28f7c43de88784d2d9702b8a1c", size = 59981, upload-time = "2025-07-27T13:02:53.16Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/4c/8029a03468307dfaf0f9694d31830487ee43af5f8a73407004907724e8ac/pybase64-1.4.2-cp311-cp311-manylinux_2_31_riscv64.whl", hash = "sha256:aa6122c8a81f6597e1c1116511f03ed42cf377c2100fe7debaae7ca62521095a", size = 54908, upload-time = "2025-07-27T13:02:54.363Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/8b/70bd0fe659e242efd0f60895a8ce1fe88e3a4084fd1be368974c561138c9/pybase64-1.4.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:b7e22b02505d64db308e9feeb6cb52f1d554ede5983de0befa59ac2d2ffb6a5f", size = 58650, upload-time = "2025-07-27T13:02:55.905Z" },
-    { url = "https://files.pythonhosted.org/packages/64/ca/9c1d23cbc4b9beac43386a32ad53903c816063cef3f14c10d7c3d6d49a23/pybase64-1.4.2-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:edfe4a3c8c4007f09591f49b46a89d287ef5e8cd6630339536fe98ff077263c2", size = 52323, upload-time = "2025-07-27T13:02:57.192Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/29/a6292e9047248c8616dc53131a49da6c97a61616f80e1e36c73d7ef895fe/pybase64-1.4.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:b79b4a53dd117ffbd03e96953f2e6bd2827bfe11afeb717ea16d9b0893603077", size = 68979, upload-time = "2025-07-27T13:02:58.594Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/e0/cfec7b948e170395d8e88066e01f50e71195db9837151db10c14965d6222/pybase64-1.4.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:fd9afa7a61d89d170607faf22287290045757e782089f0357b8f801d228d52c3", size = 58037, upload-time = "2025-07-27T13:02:59.753Z" },
-    { url = "https://files.pythonhosted.org/packages/74/7e/0ac1850198c9c35ef631174009cee576f4d8afff3bf493ce310582976ab4/pybase64-1.4.2-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:5c17b092e4da677a595178d2db17a5d2fafe5c8e418d46c0c4e4cde5adb8cff3", size = 54416, upload-time = "2025-07-27T13:03:00.978Z" },
-    { url = "https://files.pythonhosted.org/packages/1b/45/b0b037f27e86c50e62d927f0bc1bde8b798dd55ab39197b116702e508d05/pybase64-1.4.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:120799274cf55f3f5bb8489eaa85142f26170564baafa7cf3e85541c46b6ab13", size = 56257, upload-time = "2025-07-27T13:03:02.201Z" },
-    { url = "https://files.pythonhosted.org/packages/d2/0d/5034598aac56336d88fd5aaf6f34630330643b51d399336b8c788d798fc5/pybase64-1.4.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:522e4e712686acec2d25de9759dda0b0618cb9f6588523528bc74715c0245c7b", size = 70889, upload-time = "2025-07-27T13:03:03.437Z" },
-    { url = "https://files.pythonhosted.org/packages/8a/3b/0645f21bb08ecf45635b624958b5f9e569069d31ecbf125dc7e0e5b83f60/pybase64-1.4.2-cp311-cp311-win32.whl", hash = "sha256:bfd828792982db8d787515535948c1e340f1819407c8832f94384c0ebeaf9d74", size = 33631, upload-time = "2025-07-27T13:03:05.194Z" },
-    { url = "https://files.pythonhosted.org/packages/8f/08/24f8103c1f19e78761026cdd9f3b3be73239bc19cf5ab6fef0e8042d0bc6/pybase64-1.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:7a9e89d40dbf833af481d1d5f1a44d173c9c4b56a7c8dba98e39a78ee87cfc52", size = 35781, upload-time = "2025-07-27T13:03:06.779Z" },
-    { url = "https://files.pythonhosted.org/packages/66/cd/832fb035a0ea7eb53d776a5cfa961849e22828f6dfdfcdb9eb43ba3c0166/pybase64-1.4.2-cp311-cp311-win_arm64.whl", hash = "sha256:ce5809fa90619b03eab1cd63fec142e6cf1d361731a9b9feacf27df76c833343", size = 30903, upload-time = "2025-07-27T13:03:07.903Z" },
-    { url = "https://files.pythonhosted.org/packages/28/6d/11ede991e800797b9f5ebd528013b34eee5652df93de61ffb24503393fa5/pybase64-1.4.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:db2c75d1388855b5a1015b65096d7dbcc708e7de3245dcbedeb872ec05a09326", size = 38326, upload-time = "2025-07-27T13:03:09.065Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/84/87f1f565f42e2397e2aaa2477c86419f5173c3699881c42325c090982f0a/pybase64-1.4.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6b621a972a01841368fdb9dedc55fd3c6e0c7217d0505ba3b1ebe95e7ef1b493", size = 31661, upload-time = "2025-07-27T13:03:10.295Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/2a/a24c810e7a61d2cc6f73fe9ee4872a03030887fa8654150901b15f376f65/pybase64-1.4.2-cp312-cp312-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:f48c32ac6a16cbf57a5a96a073fef6ff7e3526f623cd49faa112b7f9980bafba", size = 68192, upload-time = "2025-07-27T13:03:11.467Z" },
-    { url = "https://files.pythonhosted.org/packages/ee/87/d9baf98cbfc37b8657290ad4421f3a3c36aa0eafe4872c5859cfb52f3448/pybase64-1.4.2-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:ace8b23093a6bb862477080d9059b784096ab2f97541e8bfc40d42f062875149", size = 71587, upload-time = "2025-07-27T13:03:12.719Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/89/3df043cc56ef3b91b7aa0c26ae822a2d7ec8da0b0fd7c309c879b0eb5988/pybase64-1.4.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1772c7532a7fb6301baea3dd3e010148dbf70cd1136a83c2f5f91bdc94822145", size = 59910, upload-time = "2025-07-27T13:03:14.266Z" },
-    { url = "https://files.pythonhosted.org/packages/75/4f/6641e9edf37aeb4d4524dc7ba2168eff8d96c90e77f6283c2be3400ab380/pybase64-1.4.2-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:f86f7faddcba5cbfea475f8ab96567834c28bf09ca6c7c3d66ee445adac80d8f", size = 56701, upload-time = "2025-07-27T13:03:15.6Z" },
-    { url = "https://files.pythonhosted.org/packages/2d/7f/20d8ac1046f12420a0954a45a13033e75f98aade36eecd00c64e3549b071/pybase64-1.4.2-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:0b8c8e275b5294089f314814b4a50174ab90af79d6a4850f6ae11261ff6a7372", size = 59288, upload-time = "2025-07-27T13:03:16.823Z" },
-    { url = "https://files.pythonhosted.org/packages/17/ea/9c0ca570e3e50b3c6c3442e280c83b321a0464c86a9db1f982a4ff531550/pybase64-1.4.2-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:864d85a0470c615807ae8b97d724d068b940a2d10ac13a5f1b9e75a3ce441758", size = 60267, upload-time = "2025-07-27T13:03:18.132Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/ac/46894929d71ccedebbfb0284173b0fea96bc029cd262654ba8451a7035d6/pybase64-1.4.2-cp312-cp312-manylinux_2_31_riscv64.whl", hash = "sha256:47254d97ed2d8351e30ecfdb9e2414547f66ba73f8a09f932c9378ff75cd10c5", size = 54801, upload-time = "2025-07-27T13:03:19.669Z" },
-    { url = "https://files.pythonhosted.org/packages/6a/1e/02c95218ea964f0b2469717c2c69b48e63f4ca9f18af01a5b2a29e4c1216/pybase64-1.4.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:264b65ecc4f0ee73f3298ab83bbd8008f7f9578361b8df5b448f985d8c63e02a", size = 58599, upload-time = "2025-07-27T13:03:20.951Z" },
-    { url = "https://files.pythonhosted.org/packages/15/45/ccc21004930789b8fb439d43e3212a6c260ccddb2bf450c39a20db093f33/pybase64-1.4.2-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:fbcc2b30cd740c16c9699f596f22c7a9e643591311ae72b1e776f2d539e9dd9d", size = 52388, upload-time = "2025-07-27T13:03:23.064Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/45/22e46e549710c4c237d77785b6fb1bc4c44c288a5c44237ba9daf5c34b82/pybase64-1.4.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:cda9f79c22d51ee4508f5a43b673565f1d26af4330c99f114e37e3186fdd3607", size = 68802, upload-time = "2025-07-27T13:03:24.673Z" },
-    { url = "https://files.pythonhosted.org/packages/55/0c/232c6261b81296e5593549b36e6e7884a5da008776d12665923446322c36/pybase64-1.4.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:0c91c6d2a7232e2a1cd10b3b75a8bb657defacd4295a1e5e80455df2dfc84d4f", size = 57841, upload-time = "2025-07-27T13:03:25.948Z" },
-    { url = "https://files.pythonhosted.org/packages/20/8a/b35a615ae6f04550d696bb179c414538b3b477999435fdd4ad75b76139e4/pybase64-1.4.2-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a370dea7b1cee2a36a4d5445d4e09cc243816c5bc8def61f602db5a6f5438e52", size = 54320, upload-time = "2025-07-27T13:03:27.495Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/a9/8bd4f9bcc53689f1b457ecefed1eaa080e4949d65a62c31a38b7253d5226/pybase64-1.4.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:9aa4de83f02e462a6f4e066811c71d6af31b52d7484de635582d0e3ec3d6cc3e", size = 56482, upload-time = "2025-07-27T13:03:28.942Z" },
-    { url = "https://files.pythonhosted.org/packages/75/e5/4a7735b54a1191f61c3f5c2952212c85c2d6b06eb5fb3671c7603395f70c/pybase64-1.4.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:83a1c2f9ed00fee8f064d548c8654a480741131f280e5750bb32475b7ec8ee38", size = 70959, upload-time = "2025-07-27T13:03:30.171Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/67/e2b6cb32c782e12304d467418e70da0212567f42bd4d3b5eb1fdf64920ad/pybase64-1.4.2-cp312-cp312-win32.whl", hash = "sha256:a6e5688b18d558e8c6b8701cc8560836c4bbeba61d33c836b4dba56b19423716", size = 33683, upload-time = "2025-07-27T13:03:31.775Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/bc/d5c277496063a09707486180f17abbdbdebbf2f5c4441b20b11d3cb7dc7c/pybase64-1.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:c995d21b8bd08aa179cd7dd4db0695c185486ecc72da1e8f6c37ec86cadb8182", size = 35817, upload-time = "2025-07-27T13:03:32.99Z" },
-    { url = "https://files.pythonhosted.org/packages/e6/69/e4be18ae685acff0ae77f75d4586590f29d2cd187bf603290cf1d635cad4/pybase64-1.4.2-cp312-cp312-win_arm64.whl", hash = "sha256:e254b9258c40509c2ea063a7784f6994988f3f26099d6e08704e3c15dfed9a55", size = 30900, upload-time = "2025-07-27T13:03:34.499Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/56/5337f27a8b8d2d6693f46f7b36bae47895e5820bfa259b0072574a4e1057/pybase64-1.4.2-cp313-cp313-android_21_arm64_v8a.whl", hash = "sha256:0f331aa59549de21f690b6ccc79360ffed1155c3cfbc852eb5c097c0b8565a2b", size = 33888, upload-time = "2025-07-27T13:03:35.698Z" },
-    { url = "https://files.pythonhosted.org/packages/4c/09/f3f4b11fc9beda7e8625e29fb0f549958fcbb34fea3914e1c1d95116e344/pybase64-1.4.2-cp313-cp313-android_21_x86_64.whl", hash = "sha256:9dad20bf1f3ed9e6fe566c4c9d07d9a6c04f5a280daebd2082ffb8620b0a880d", size = 40796, upload-time = "2025-07-27T13:03:36.927Z" },
-    { url = "https://files.pythonhosted.org/packages/e3/ff/470768f0fe6de0aa302a8cb1bdf2f9f5cffc3f69e60466153be68bc953aa/pybase64-1.4.2-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:69d3f0445b0faeef7bb7f93bf8c18d850785e2a77f12835f49e524cc54af04e7", size = 30914, upload-time = "2025-07-27T13:03:38.475Z" },
-    { url = "https://files.pythonhosted.org/packages/75/6b/d328736662665e0892409dc410353ebef175b1be5eb6bab1dad579efa6df/pybase64-1.4.2-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:2372b257b1f4dd512f317fb27e77d313afd137334de64c87de8374027aacd88a", size = 31380, upload-time = "2025-07-27T13:03:39.7Z" },
-    { url = "https://files.pythonhosted.org/packages/ca/96/7ff718f87c67f4147c181b73d0928897cefa17dc75d7abc6e37730d5908f/pybase64-1.4.2-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fb794502b4b1ec91c4ca5d283ae71aef65e3de7721057bd9e2b3ec79f7a62d7d", size = 38230, upload-time = "2025-07-27T13:03:41.637Z" },
-    { url = "https://files.pythonhosted.org/packages/4d/58/a3307b048d799ff596a3c7c574fcba66f9b6b8c899a3c00a698124ca7ad5/pybase64-1.4.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d5c532b03fd14a5040d6cf6571299a05616f925369c72ddf6fe2fb643eb36fed", size = 38319, upload-time = "2025-07-27T13:03:42.847Z" },
-    { url = "https://files.pythonhosted.org/packages/08/a7/0bda06341b0a2c830d348c6e1c4d348caaae86c53dc9a046e943467a05e9/pybase64-1.4.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0f699514dc1d5689ca9cf378139e0214051922732f9adec9404bc680a8bef7c0", size = 31655, upload-time = "2025-07-27T13:03:44.426Z" },
-    { url = "https://files.pythonhosted.org/packages/87/df/e1d6e8479e0c5113c2c63c7b44886935ce839c2d99884c7304ca9e86547c/pybase64-1.4.2-cp313-cp313-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:cd3e8713cbd32c8c6aa935feaf15c7670e2b7e8bfe51c24dc556811ebd293a29", size = 68232, upload-time = "2025-07-27T13:03:45.729Z" },
-    { url = "https://files.pythonhosted.org/packages/71/ab/db4dbdfccb9ca874d6ce34a0784761471885d96730de85cee3d300381529/pybase64-1.4.2-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:d377d48acf53abf4b926c2a7a24a19deb092f366a04ffd856bf4b3aa330b025d", size = 71608, upload-time = "2025-07-27T13:03:47.01Z" },
-    { url = "https://files.pythonhosted.org/packages/11/e9/508df958563951045d728bbfbd3be77465f9231cf805cb7ccaf6951fc9f1/pybase64-1.4.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d83c076e78d619b9e1dd674e2bf5fb9001aeb3e0b494b80a6c8f6d4120e38cd9", size = 59912, upload-time = "2025-07-27T13:03:48.277Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/58/7f2cef1ceccc682088958448d56727369de83fa6b29148478f4d2acd107a/pybase64-1.4.2-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:ab9cdb6a8176a5cb967f53e6ad60e40c83caaa1ae31c5e1b29e5c8f507f17538", size = 56413, upload-time = "2025-07-27T13:03:49.908Z" },
-    { url = "https://files.pythonhosted.org/packages/08/7c/7e0af5c5728fa7e2eb082d88eca7c6bd17429be819d58518e74919d42e66/pybase64-1.4.2-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:adf0c103ad559dbfb9fe69edfd26a15c65d9c991a5ab0a25b04770f9eb0b9484", size = 59311, upload-time = "2025-07-27T13:03:51.238Z" },
-    { url = "https://files.pythonhosted.org/packages/03/8b/09825d0f37e45b9a3f546e5f990b6cf2dd838e54ea74122c2464646e0c77/pybase64-1.4.2-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:0d03ef2f253d97ce0685d3624bf5e552d716b86cacb8a6c971333ba4b827e1fc", size = 60282, upload-time = "2025-07-27T13:03:52.56Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/3f/3711d2413f969bfd5b9cc19bc6b24abae361b7673ff37bcb90c43e199316/pybase64-1.4.2-cp313-cp313-manylinux_2_31_riscv64.whl", hash = "sha256:e565abf906efee76ae4be1aef5df4aed0fda1639bc0d7732a3dafef76cb6fc35", size = 54845, upload-time = "2025-07-27T13:03:54.167Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/3c/4c7ce1ae4d828c2bb56d144322f81bffbaaac8597d35407c3d7cbb0ff98f/pybase64-1.4.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e3c6a5f15fd03f232fc6f295cce3684f7bb08da6c6d5b12cc771f81c9f125cc6", size = 58615, upload-time = "2025-07-27T13:03:55.494Z" },
-    { url = "https://files.pythonhosted.org/packages/f5/8f/c2fc03bf4ed038358620065c75968a30184d5d3512d09d3ef9cc3bd48592/pybase64-1.4.2-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:bad9e3db16f448728138737bbd1af9dc2398efd593a8bdd73748cc02cd33f9c6", size = 52434, upload-time = "2025-07-27T13:03:56.808Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/0a/757d6df0a60327c893cfae903e15419914dd792092dc8cc5c9523d40bc9b/pybase64-1.4.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2683ef271328365c31afee0ed8fa29356fb8fb7c10606794656aa9ffb95e92be", size = 68824, upload-time = "2025-07-27T13:03:58.735Z" },
-    { url = "https://files.pythonhosted.org/packages/a0/14/84abe2ed8c29014239be1cfab45dfebe5a5ca779b177b8b6f779bd8b69da/pybase64-1.4.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:265b20089cd470079114c09bb74b101b3bfc3c94ad6b4231706cf9eff877d570", size = 57898, upload-time = "2025-07-27T13:04:00.379Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/c6/d193031f90c864f7b59fa6d1d1b5af41f0f5db35439988a8b9f2d1b32a13/pybase64-1.4.2-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e53173badead10ef8b839aa5506eecf0067c7b75ad16d9bf39bc7144631f8e67", size = 54319, upload-time = "2025-07-27T13:04:01.742Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/37/ec0c7a610ff8f994ee6e0c5d5d66b6b6310388b96ebb347b03ae39870fdf/pybase64-1.4.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:5823b8dcf74da7da0f761ed60c961e8928a6524e520411ad05fe7f9f47d55b40", size = 56472, upload-time = "2025-07-27T13:04:03.089Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/5a/e585b74f85cedd261d271e4c2ef333c5cfce7e80750771808f56fee66b98/pybase64-1.4.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:1237f66c54357d325390da60aa5e21c6918fbcd1bf527acb9c1f4188c62cb7d5", size = 70966, upload-time = "2025-07-27T13:04:04.361Z" },
-    { url = "https://files.pythonhosted.org/packages/ad/20/1b2fdd98b4ba36008419668c813025758214c543e362c66c49214ecd1127/pybase64-1.4.2-cp313-cp313-win32.whl", hash = "sha256:b0b851eb4f801d16040047f6889cca5e9dfa102b3e33f68934d12511245cef86", size = 33681, upload-time = "2025-07-27T13:04:06.126Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/64/3df4067d169c047054889f34b5a946cbe3785bca43404b93c962a5461a41/pybase64-1.4.2-cp313-cp313-win_amd64.whl", hash = "sha256:19541c6e26d17d9522c02680fe242206ae05df659c82a657aabadf209cd4c6c7", size = 35822, upload-time = "2025-07-27T13:04:07.752Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/fd/db505188adf812e60ee923f196f9deddd8a1895b2b29b37f5db94afc3b1c/pybase64-1.4.2-cp313-cp313-win_arm64.whl", hash = "sha256:77a191863d576c0a5dd81f8a568a5ca15597cc980ae809dce62c717c8d42d8aa", size = 30899, upload-time = "2025-07-27T13:04:09.062Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/27/5f5fecd206ec1e06e1608a380af18dcb76a6ab08ade6597a3251502dcdb2/pybase64-1.4.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:2e194bbabe3fdf9e47ba9f3e157394efe0849eb226df76432126239b3f44992c", size = 38677, upload-time = "2025-07-27T13:04:10.334Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/0f/abe4b5a28529ef5f74e8348fa6a9ef27d7d75fbd98103d7664cf485b7d8f/pybase64-1.4.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:39aef1dadf4a004f11dd09e703abaf6528a87c8dbd39c448bb8aebdc0a08c1be", size = 32066, upload-time = "2025-07-27T13:04:11.641Z" },
-    { url = "https://files.pythonhosted.org/packages/ac/7e/ea0ce6a7155cada5526017ec588b6d6185adea4bf9331565272f4ef583c2/pybase64-1.4.2-cp313-cp313t-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:91cb920c7143e36ec8217031282c8651da3b2206d70343f068fac0e7f073b7f9", size = 72300, upload-time = "2025-07-27T13:04:12.969Z" },
-    { url = "https://files.pythonhosted.org/packages/45/2d/e64c7a056c9ec48dfe130d1295e47a8c2b19c3984488fc08e5eaa1e86c88/pybase64-1.4.2-cp313-cp313t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:6958631143fb9e71f9842000da042ec2f6686506b6706e2dfda29e97925f6aa0", size = 75520, upload-time = "2025-07-27T13:04:14.374Z" },
-    { url = "https://files.pythonhosted.org/packages/43/e0/e5f93b2e1cb0751a22713c4baa6c6eaf5f307385e369180486c8316ed21e/pybase64-1.4.2-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:dc35f14141ef3f1ac70d963950a278a2593af66fe5a1c7a208e185ca6278fa25", size = 65384, upload-time = "2025-07-27T13:04:16.204Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/23/8c645a1113ad88a1c6a3d0e825e93ef8b74ad3175148767853a0a4d7626e/pybase64-1.4.2-cp313-cp313t-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:5d949d2d677859c3a8507e1b21432a039d2b995e0bd3fe307052b6ded80f207a", size = 60471, upload-time = "2025-07-27T13:04:17.947Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/81/edd0f7d8b0526b91730a0dd4ce6b4c8be2136cd69d424afe36235d2d2a06/pybase64-1.4.2-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:09caacdd3e15fe7253a67781edd10a6a918befab0052a2a3c215fe5d1f150269", size = 63945, upload-time = "2025-07-27T13:04:19.383Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/a5/edc224cd821fd65100b7af7c7e16b8f699916f8c0226c9c97bbae5a75e71/pybase64-1.4.2-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:e44b0e793b23f28ea0f15a9754bd0c960102a2ac4bccb8fafdedbd4cc4d235c0", size = 64858, upload-time = "2025-07-27T13:04:20.807Z" },
-    { url = "https://files.pythonhosted.org/packages/11/3b/92853f968f1af7e42b7e54d21bdd319097b367e7dffa2ca20787361df74c/pybase64-1.4.2-cp313-cp313t-manylinux_2_31_riscv64.whl", hash = "sha256:849f274d0bcb90fc6f642c39274082724d108e41b15f3a17864282bd41fc71d5", size = 58557, upload-time = "2025-07-27T13:04:22.229Z" },
-    { url = "https://files.pythonhosted.org/packages/76/09/0ec6bd2b2303b0ea5c6da7535edc9a608092075ef8c0cdd96e3e726cd687/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:528dba7ef1357bd7ce1aea143084501f47f5dd0fff7937d3906a68565aa59cfe", size = 63624, upload-time = "2025-07-27T13:04:23.952Z" },
-    { url = "https://files.pythonhosted.org/packages/73/6e/52cb1ced2a517a3118b2e739e9417432049013ac7afa15d790103059e8e4/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:1da54be743d9a68671700cfe56c3ab8c26e8f2f5cc34eface905c55bc3a9af94", size = 56174, upload-time = "2025-07-27T13:04:25.419Z" },
-    { url = "https://files.pythonhosted.org/packages/5b/9d/820fe79347467e48af985fe46180e1dd28e698ade7317bebd66de8a143f5/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:9b07c0406c3eaa7014499b0aacafb21a6d1146cfaa85d56f0aa02e6d542ee8f3", size = 72640, upload-time = "2025-07-27T13:04:26.824Z" },
-    { url = "https://files.pythonhosted.org/packages/53/58/e863e10d08361e694935c815b73faad7e1ab03f99ae154d86c4e2f331896/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:312f2aa4cf5d199a97fbcaee75d2e59ebbaafcd091993eb373b43683498cdacb", size = 62453, upload-time = "2025-07-27T13:04:28.562Z" },
-    { url = "https://files.pythonhosted.org/packages/95/f0/c392c4ac8ccb7a34b28377c21faa2395313e3c676d76c382642e19a20703/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:ad59362fc267bf15498a318c9e076686e4beeb0dfe09b457fabbc2b32468b97a", size = 58103, upload-time = "2025-07-27T13:04:29.996Z" },
-    { url = "https://files.pythonhosted.org/packages/32/30/00ab21316e7df8f526aa3e3dc06f74de6711d51c65b020575d0105a025b2/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:01593bd064e7dcd6c86d04e94e44acfe364049500c20ac68ca1e708fbb2ca970", size = 60779, upload-time = "2025-07-27T13:04:31.549Z" },
-    { url = "https://files.pythonhosted.org/packages/a6/65/114ca81839b1805ce4a2b7d58bc16e95634734a2059991f6382fc71caf3e/pybase64-1.4.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:5b81547ad8ea271c79fdf10da89a1e9313cb15edcba2a17adf8871735e9c02a0", size = 74684, upload-time = "2025-07-27T13:04:32.976Z" },
-    { url = "https://files.pythonhosted.org/packages/54/8f/aa9d445b9bb693b8f6bb1456bd6d8576d79b7a63bf6c69af3a539235b15f/pybase64-1.4.2-cp313-cp313t-win32.whl", hash = "sha256:7edbe70b5654545a37e6e6b02de738303b1bbdfcde67f6cfec374cfb5cc4099e", size = 33961, upload-time = "2025-07-27T13:04:34.806Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/e5/da37cfb173c646fd4fc7c6aae2bc41d40de2ee49529854af8f4e6f498b45/pybase64-1.4.2-cp313-cp313t-win_amd64.whl", hash = "sha256:385690addf87c25d6366fab5d8ff512eed8a7ecb18da9e8152af1c789162f208", size = 36199, upload-time = "2025-07-27T13:04:36.223Z" },
-    { url = "https://files.pythonhosted.org/packages/66/3e/1eb68fb7d00f2cec8bd9838e2a30d183d6724ae06e745fd6e65216f170ff/pybase64-1.4.2-cp313-cp313t-win_arm64.whl", hash = "sha256:c2070d0aa88580f57fe15ca88b09f162e604d19282915a95a3795b5d3c1c05b5", size = 31221, upload-time = "2025-07-27T13:04:37.704Z" },
-    { url = "https://files.pythonhosted.org/packages/99/bf/00a87d951473ce96c8c08af22b6983e681bfabdb78dd2dcf7ee58eac0932/pybase64-1.4.2-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:4157ad277a32cf4f02a975dffc62a3c67d73dfa4609b2c1978ef47e722b18b8e", size = 30924, upload-time = "2025-07-27T13:04:39.189Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/43/dee58c9d60e60e6fb32dc6da722d84592e22f13c277297eb4ce6baf99a99/pybase64-1.4.2-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:e113267dc349cf624eb4f4fbf53fd77835e1aa048ac6877399af426aab435757", size = 31390, upload-time = "2025-07-27T13:04:40.995Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/11/b28906fc2e330b8b1ab4bc845a7bef808b8506734e90ed79c6062b095112/pybase64-1.4.2-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:cea5aaf218fd9c5c23afacfe86fd4464dfedc1a0316dd3b5b4075b068cc67df0", size = 38212, upload-time = "2025-07-27T13:04:42.729Z" },
-    { url = "https://files.pythonhosted.org/packages/24/9e/868d1e104413d14b19feaf934fc7fad4ef5b18946385f8bb79684af40f24/pybase64-1.4.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:41213497abbd770435c7a9c8123fb02b93709ac4cf60155cd5aefc5f3042b600", size = 38303, upload-time = "2025-07-27T13:04:44.095Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/73/f7eac96ca505df0600280d6bfc671a9e2e2f947c2b04b12a70e36412f7eb/pybase64-1.4.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c8b522df7ee00f2ac1993ccd5e1f6608ae7482de3907668c2ff96a83ef213925", size = 31669, upload-time = "2025-07-27T13:04:45.845Z" },
-    { url = "https://files.pythonhosted.org/packages/c6/43/8e18bea4fd455100112d6a73a83702843f067ef9b9272485b6bdfd9ed2f0/pybase64-1.4.2-cp314-cp314-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:06725022e540c5b098b978a0418ca979773e2cbdbb76f10bd97536f2ad1c5b49", size = 68452, upload-time = "2025-07-27T13:04:47.788Z" },
-    { url = "https://files.pythonhosted.org/packages/e4/2e/851eb51284b97354ee5dfa1309624ab90920696e91a33cd85b13d20cc5c1/pybase64-1.4.2-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:a3e54dcf0d0305ec88473c9d0009f698cabf86f88a8a10090efeff2879c421bb", size = 71674, upload-time = "2025-07-27T13:04:49.294Z" },
-    { url = "https://files.pythonhosted.org/packages/57/0d/5cf1e5dc64aec8db43e8dee4e4046856d639a72bcb0fb3e716be42ced5f1/pybase64-1.4.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:67675cee727a60dc91173d2790206f01aa3c7b3fbccfa84fd5c1e3d883fe6caa", size = 60027, upload-time = "2025-07-27T13:04:50.769Z" },
-    { url = "https://files.pythonhosted.org/packages/a4/8e/3479266bc0e65f6cc48b3938d4a83bff045330649869d950a378f2ddece0/pybase64-1.4.2-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:753da25d4fd20be7bda2746f545935773beea12d5cb5ec56ec2d2960796477b1", size = 56461, upload-time = "2025-07-27T13:04:52.37Z" },
-    { url = "https://files.pythonhosted.org/packages/20/b6/f2b6cf59106dd78bae8717302be5b814cec33293504ad409a2eb752ad60c/pybase64-1.4.2-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:a78c768ce4ca550885246d14babdb8923e0f4a848dfaaeb63c38fc99e7ea4052", size = 59446, upload-time = "2025-07-27T13:04:53.967Z" },
-    { url = "https://files.pythonhosted.org/packages/16/70/3417797dfccdfdd0a54e4ad17c15b0624f0fc2d6a362210f229f5c4e8fd0/pybase64-1.4.2-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:51b17f36d890c92f0618fb1c8db2ccc25e6ed07afa505bab616396fc9b0b0492", size = 60350, upload-time = "2025-07-27T13:04:55.881Z" },
-    { url = "https://files.pythonhosted.org/packages/a0/c6/6e4269dd98d150ae95d321b311a345eae0f7fd459d97901b4a586d7513bb/pybase64-1.4.2-cp314-cp314-manylinux_2_31_riscv64.whl", hash = "sha256:f92218d667049ab4f65d54fa043a88ffdb2f07fff1f868789ef705a5221de7ec", size = 54989, upload-time = "2025-07-27T13:04:57.436Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/e8/18c1b0c255f964fafd0412b0d5a163aad588aeccb8f84b9bf9c8611d80f6/pybase64-1.4.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:3547b3d1499919a06491b3f879a19fbe206af2bd1a424ecbb4e601eb2bd11fea", size = 58724, upload-time = "2025-07-27T13:04:59.406Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/ad/ddfbd2125fc20b94865fb232b2e9105376fa16eee492e4b7786d42a86cbf/pybase64-1.4.2-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:958af7b0e09ddeb13e8c2330767c47b556b1ade19c35370f6451d139cde9f2a9", size = 52285, upload-time = "2025-07-27T13:05:01.198Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/4c/b9d4ec9224add33c84b925a03d1a53cd4106efb449ea8e0ae7795fed7bf7/pybase64-1.4.2-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:4facc57f6671e2229a385a97a618273e7be36a9ea0a9d1c1b9347f14d19ceba8", size = 69036, upload-time = "2025-07-27T13:05:03.109Z" },
-    { url = "https://files.pythonhosted.org/packages/92/38/7b96794da77bed3d9b4fea40f14ae563648fba83a696e7602fabe60c0eb7/pybase64-1.4.2-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:a32fc57d05d73a7c9b0ca95e9e265e21cf734195dc6873829a890058c35f5cfd", size = 57938, upload-time = "2025-07-27T13:05:04.744Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/c5/ae8bbce3c322d1b074e79f51f5df95961fe90cb8748df66c6bc97616e974/pybase64-1.4.2-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3dc853243c81ce89cc7318e6946f860df28ddb7cd2a0648b981652d9ad09ee5a", size = 54474, upload-time = "2025-07-27T13:05:06.662Z" },
-    { url = "https://files.pythonhosted.org/packages/15/9a/c09887c4bb1b43c03fc352e2671ef20c6686c6942a99106a45270ee5b840/pybase64-1.4.2-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:0e6d863a86b3e7bc6ac9bd659bebda4501b9da842521111b0b0e54eb51295df5", size = 56533, upload-time = "2025-07-27T13:05:08.368Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/0f/d5114d63d35d085639606a880cb06e2322841cd4b213adfc14d545c1186f/pybase64-1.4.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:6579475140ff2067903725d8aca47f5747bcb211597a1edd60b58f6d90ada2bd", size = 71030, upload-time = "2025-07-27T13:05:10.3Z" },
-    { url = "https://files.pythonhosted.org/packages/40/0e/fe6f1ed22ea52eb99f490a8441815ba21de288f4351aeef4968d71d20d2d/pybase64-1.4.2-cp314-cp314-win32.whl", hash = "sha256:373897f728d7b4f241a1f803ac732c27b6945d26d86b2741ad9b75c802e4e378", size = 34174, upload-time = "2025-07-27T13:05:12.254Z" },
-    { url = "https://files.pythonhosted.org/packages/71/46/0e15bea52ffc63e8ae7935e945accbaf635e0aefa26d3e31fdf9bc9dcd01/pybase64-1.4.2-cp314-cp314-win_amd64.whl", hash = "sha256:1afe3361344617d298c1d08bc657ef56d0f702d6b72cb65d968b2771017935aa", size = 36308, upload-time = "2025-07-27T13:05:13.898Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/dc/55849fee2577bda77c1e078da04cc9237e8e474a8c8308deb702a26f2511/pybase64-1.4.2-cp314-cp314-win_arm64.whl", hash = "sha256:f131c9360babe522f3d90f34da3f827cba80318125cf18d66f2ee27e3730e8c4", size = 31341, upload-time = "2025-07-27T13:05:15.553Z" },
-    { url = "https://files.pythonhosted.org/packages/39/44/c69d088e28b25e70ac742b6789cde038473815b2a69345c4bae82d5e244d/pybase64-1.4.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:2583ac304131c1bd6e3120b0179333610f18816000db77c0a2dd6da1364722a8", size = 38678, upload-time = "2025-07-27T13:05:17.544Z" },
-    { url = "https://files.pythonhosted.org/packages/00/93/2860ec067497b9cbb06242f96d44caebbd9eed32174e4eb8c1ffef760f94/pybase64-1.4.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:75a8116be4ea4cdd30a5c4f1a6f3b038e0d457eb03c8a2685d8ce2aa00ef8f92", size = 32066, upload-time = "2025-07-27T13:05:19.18Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/55/1e96249a38759332e8a01b31c370d88c60ceaf44692eb6ba4f0f451ee496/pybase64-1.4.2-cp314-cp314t-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:217ea776a098d7c08668e5526b9764f5048bbfd28cac86834217ddfe76a4e3c4", size = 72465, upload-time = "2025-07-27T13:05:20.866Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/ab/0f468605b899f3e35dbb7423fba3ff98aeed1ec16abb02428468494a58f4/pybase64-1.4.2-cp314-cp314t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:4ec14683e343c95b14248cdfdfa78c052582be7a3865fd570aa7cffa5ab5cf37", size = 75693, upload-time = "2025-07-27T13:05:22.896Z" },
-    { url = "https://files.pythonhosted.org/packages/91/d1/9980a0159b699e2489baba05b71b7c953b29249118ba06fdbb3e9ea1b9b5/pybase64-1.4.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:480ecf21e1e956c5a10d3cf7b3b7e75bce3f9328cf08c101e4aab1925d879f34", size = 65577, upload-time = "2025-07-27T13:05:25Z" },
-    { url = "https://files.pythonhosted.org/packages/16/86/b27e7b95f9863d245c0179a7245582eda3d262669d8f822777364d8fd7d5/pybase64-1.4.2-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.whl", hash = "sha256:1fe1ebdc55e9447142e2f6658944aadfb5a4fbf03dbd509be34182585515ecc1", size = 60662, upload-time = "2025-07-27T13:05:27.138Z" },
-    { url = "https://files.pythonhosted.org/packages/28/87/a7f0dde0abc26bfbee761f1d3558eb4b139f33ddd9fe1f6825ffa7daa22d/pybase64-1.4.2-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:c793a2b06753accdaf5e1a8bbe5d800aab2406919e5008174f989a1ca0081411", size = 64179, upload-time = "2025-07-27T13:05:28.996Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/88/5d6fa1c60e1363b4cac4c396978f39e9df4689e75225d7d9c0a5998e3a14/pybase64-1.4.2-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:6acae6e1d1f7ebe40165f08076c7a73692b2bf9046fefe673f350536e007f556", size = 64968, upload-time = "2025-07-27T13:05:30.818Z" },
-    { url = "https://files.pythonhosted.org/packages/20/6e/2ed585af5b2211040445d9849326dd2445320c9316268794f5453cfbaf30/pybase64-1.4.2-cp314-cp314t-manylinux_2_31_riscv64.whl", hash = "sha256:88b91cd0949358aadcea75f8de5afbcf3c8c5fb9ec82325bd24285b7119cf56e", size = 58738, upload-time = "2025-07-27T13:05:32.629Z" },
-    { url = "https://files.pythonhosted.org/packages/ce/94/e2960b56322eabb3fbf303fc5a72e6444594c1b90035f3975c6fe666db5c/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:53316587e1b1f47a11a5ff068d3cbd4a3911c291f2aec14882734973684871b2", size = 63802, upload-time = "2025-07-27T13:05:34.687Z" },
-    { url = "https://files.pythonhosted.org/packages/95/47/312139d764c223f534f751528ce3802887c279125eac64f71cd3b4e05abc/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:caa7f20f43d00602cf9043b5ba758d54f5c41707d3709b2a5fac17361579c53c", size = 56341, upload-time = "2025-07-27T13:05:36.554Z" },
-    { url = "https://files.pythonhosted.org/packages/3f/d7/aec9a6ed53b128dac32f8768b646ca5730c88eef80934054d7fa7d02f3ef/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:2d93817e24fdd79c534ed97705df855af6f1d2535ceb8dfa80da9de75482a8d7", size = 72838, upload-time = "2025-07-27T13:05:38.459Z" },
-    { url = "https://files.pythonhosted.org/packages/e3/a8/6ccc54c5f1f7c3450ad7c56da10c0f131d85ebe069ea6952b5b42f2e92d9/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:63cd769b51474d8d08f7f2ce73b30380d9b4078ec92ea6b348ea20ed1e1af88a", size = 62633, upload-time = "2025-07-27T13:05:40.624Z" },
-    { url = "https://files.pythonhosted.org/packages/34/22/2b9d89f8ff6f2a01d6d6a88664b20a4817049cfc3f2c62caca040706660c/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:cd07e6a9993c392ec8eb03912a43c6a6b21b2deb79ee0d606700fe276e9a576f", size = 58282, upload-time = "2025-07-27T13:05:42.565Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/14/dbf6266177532a6a11804ac080ebffcee272f491b92820c39886ee20f201/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:6a8944e8194adff4668350504bc6b7dbde2dab9244c88d99c491657d145b5af5", size = 60948, upload-time = "2025-07-27T13:05:44.48Z" },
-    { url = "https://files.pythonhosted.org/packages/fd/7a/b2ae9046a66dd5746cd72836a41386517b1680bea5ce02f2b4f1c9ebc688/pybase64-1.4.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:04ab398ec4b6a212af57f6a21a6336d5a1d754ff4ccb215951366ab9080481b2", size = 74854, upload-time = "2025-07-27T13:05:46.416Z" },
-    { url = "https://files.pythonhosted.org/packages/ef/7e/9856f6d6c38a7b730e001123d2d9fa816b8b1a45f0cdee1d509d5947b047/pybase64-1.4.2-cp314-cp314t-win32.whl", hash = "sha256:3b9201ecdcb1c3e23be4caebd6393a4e6615bd0722528f5413b58e22e3792dd3", size = 34490, upload-time = "2025-07-27T13:05:48.304Z" },
-    { url = "https://files.pythonhosted.org/packages/c7/38/8523a9dc1ec8704dedbe5ccc95192ae9a7585f7eec85cc62946fe3cacd32/pybase64-1.4.2-cp314-cp314t-win_amd64.whl", hash = "sha256:36e9b0cad8197136d73904ef5a71d843381d063fd528c5ab203fc4990264f682", size = 36680, upload-time = "2025-07-27T13:05:50.264Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/52/5600104ef7b85f89fb8ec54f73504ead3f6f0294027e08d281f3cafb5c1a/pybase64-1.4.2-cp314-cp314t-win_arm64.whl", hash = "sha256:f25140496b02db0e7401567cd869fb13b4c8118bf5c2428592ec339987146d8b", size = 31600, upload-time = "2025-07-27T13:05:52.24Z" },
-    { url = "https://files.pythonhosted.org/packages/32/34/b67371f4fcedd5e2def29b1cf92a4311a72f590c04850f370c75297b48ce/pybase64-1.4.2-graalpy311-graalpy242_311_native-macosx_10_9_x86_64.whl", hash = "sha256:b4eed40a5f1627ee65613a6ac834a33f8ba24066656f569c852f98eb16f6ab5d", size = 38667, upload-time = "2025-07-27T13:07:25.315Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/3e/e57fe09ed1c7e740d21c37023c5f7c8963b4c36380f41d10261cc76f93b4/pybase64-1.4.2-graalpy311-graalpy242_311_native-macosx_11_0_arm64.whl", hash = "sha256:57885fa521e9add235af4db13e9e048d3a2934cd27d7c5efac1925e1b4d6538d", size = 32094, upload-time = "2025-07-27T13:07:28.235Z" },
-    { url = "https://files.pythonhosted.org/packages/51/34/f40d3262c3953814b9bcdcf858436bd5bc1133a698be4bcc7ed2a8c0730d/pybase64-1.4.2-graalpy311-graalpy242_311_native-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:eef9255d926c64e2fca021d3aee98023bacb98e1518e5986d6aab04102411b04", size = 43212, upload-time = "2025-07-27T13:07:31.327Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/2a/5e05d25718cb8ffd68bd46553ddfd2b660893d937feda1716b8a3b21fb38/pybase64-1.4.2-graalpy311-graalpy242_311_native-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:89614ea2d2329b6708746c540e0f14d692125df99fb1203ff0de948d9e68dfc9", size = 35789, upload-time = "2025-07-27T13:07:34.026Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/9d/f56c3ee6e94faaae2896ecaf666428330cb24096abf7d2427371bb2b403a/pybase64-1.4.2-graalpy311-graalpy242_311_native-win_amd64.whl", hash = "sha256:e401cecd2d7ddcd558768b2140fd4430746be4d17fb14c99eec9e40789df136d", size = 35861, upload-time = "2025-07-27T13:07:37.099Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/04/bfe2bd0d76385750f3541724b4abfe4ea111b3cc01ff7e83f410054adc30/pybase64-1.4.2-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:4b29c93414ba965777643a9d98443f08f76ac04519ad717aa859113695372a07", size = 38226, upload-time = "2025-07-27T13:07:40.121Z" },
-    { url = "https://files.pythonhosted.org/packages/22/13/c717855760b78ded1a9d308984c7e3e99fcf79c6cac5a231ed8c1238218f/pybase64-1.4.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:5e0c3353c0bf099c5c3f8f750202c486abee8f23a566b49e9e7b1222fbf5f259", size = 31524, upload-time = "2025-07-27T13:07:43.946Z" },
-    { url = "https://files.pythonhosted.org/packages/cf/da/2b7e69abfc62abe4d54b10d1e09ec78021a6b9b2d7e6e7b632243a19433e/pybase64-1.4.2-pp310-pypy310_pp73-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:4f98c5c6152d3c01d933fcde04322cd9ddcf65b5346034aac69a04c1a7cbb012", size = 40667, upload-time = "2025-07-27T13:07:46.715Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/11/ba738655fb3ba85c7a0605eddd2709fef606e654840c72ee5c5ff7ab29bf/pybase64-1.4.2-pp310-pypy310_pp73-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:9096a4977b7aff7ef250f759fb6a4b6b7b6199d99c84070c7fc862dd3b208b34", size = 41290, upload-time = "2025-07-27T13:07:49.534Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/38/2d5502fcaf712297b95c1b6ca924656dd7d17501fd7f9c9e0b3bbf8892ef/pybase64-1.4.2-pp310-pypy310_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:49d8597e2872966399410502310b1e2a5b7e8d8ba96766ee1fe242e00bd80775", size = 35438, upload-time = "2025-07-27T13:07:52.327Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/db/e03b8b6daa60a3fbef21741403e0cf18b2aff3beebdf6e3596bb9bab16c7/pybase64-1.4.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:2ef16366565389a287df82659e055e88bdb6c36e46a3394950903e0a9cb2e5bf", size = 36121, upload-time = "2025-07-27T13:07:55.54Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/bf/5ebaa2d9ddb5fc506633bc8b820fc27e64da964937fb30929c0367c47d00/pybase64-1.4.2-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:0a5393be20b0705870f5a8969749af84d734c077de80dd7e9f5424a247afa85e", size = 38162, upload-time = "2025-07-27T13:07:58.364Z" },
-    { url = "https://files.pythonhosted.org/packages/25/41/795c5fd6e5571bb675bf9add8a048166dddf8951c2a903fea8557743886b/pybase64-1.4.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:448f0259a2f1a17eb086f70fe2ad9b556edba1fc5bc4e62ce6966179368ee9f8", size = 31452, upload-time = "2025-07-27T13:08:01.259Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/dd/c819003b59b2832256b72ad23cbeadbd95d083ef0318d07149a58b7a88af/pybase64-1.4.2-pp311-pypy311_pp73-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:1159e70cba8e76c3d8f334bd1f8fd52a1bb7384f4c3533831b23ab2df84a6ef3", size = 40668, upload-time = "2025-07-27T13:08:04.176Z" },
-    { url = "https://files.pythonhosted.org/packages/0e/c5/38c6aba28678c4a4db49312a6b8171b93a0ffe9f21362cf4c0f325caa850/pybase64-1.4.2-pp311-pypy311_pp73-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:7d943bc5dad8388971494554b97f22ae06a46cc7779ad0de3d4bfdf7d0bbea30", size = 41281, upload-time = "2025-07-27T13:08:07.395Z" },
-    { url = "https://files.pythonhosted.org/packages/e5/23/5927bd9e59714e4e8cefd1d21ccd7216048bb1c6c3e7104b1b200afdc63d/pybase64-1.4.2-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:10b99182c561d86422c5de4265fd1f8f172fb38efaed9d72c71fb31e279a7f94", size = 35433, upload-time = "2025-07-27T13:08:10.551Z" },
-    { url = "https://files.pythonhosted.org/packages/01/0f/fab7ed5bf4926523c3b39f7621cea3e0da43f539fbc2270e042f1afccb79/pybase64-1.4.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:bb082c1114f046e59fcbc4f2be13edc93b36d7b54b58605820605be948f8fdf6", size = 36131, upload-time = "2025-07-27T13:08:13.777Z" },
-]
-
 [[package]]
 name = "pycairo"
 version = "1.28.0"
@@ -6560,16 +6483,16 @@ wheels = [
 
 [[package]]
 name = "smithy-aws-core"
-version = "0.1.0"
+version = "0.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aws-sdk-signers", marker = "python_full_version >= '3.12'" },
     { name = "smithy-core", marker = "python_full_version >= '3.12'" },
     { name = "smithy-http", marker = "python_full_version >= '3.12'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ec/e8/8cef48be92ed09a112c54747a4515313ba96e767e7e0118a769aeb147e07/smithy_aws_core-0.1.0.tar.gz", hash = "sha256:5f197b69ad1380e9118e1e3c9032e0e305525ef56fb4fc97dea6414281065526", size = 11135, upload-time = "2025-09-29T19:37:13.072Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/56/d3/f847e0fd36b95aa36ce3a4c9ce1a08e16b2aa9a56b71714045c9c924e282/smithy_aws_core-0.1.1.tar.gz", hash = "sha256:78dfd7040fc2bc72b6af293096642fc9a7bfd2db28ddbdf7c4110535eab9d662", size = 11196, upload-time = "2025-10-21T20:21:18.648Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/46/7e/6d05275646bc2cdf7b0749e9bd54958a4e808aafeee4d8ff2fdaa8233dc2/smithy_aws_core-0.1.0-py3-none-any.whl", hash = "sha256:a8cda4011562f45f1fc5957c3a981b6016d736178450e5f2a1586937632af487", size = 18959, upload-time = "2025-09-29T19:37:12.041Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/04/87cb06f0f6d664b5cffdef6d4042dd52c11c138436084d30ffdaa3543031/smithy_aws_core-0.1.1-py3-none-any.whl", hash = "sha256:0d1634f276c2999dc2a04fafef63b9d28309de50d939d1d49df952773a7063c4", size = 18963, upload-time = "2025-10-21T20:21:17.692Z" },
 ]
 
 [package.optional-dependencies]
@@ -6603,14 +6526,14 @@ wheels = [
 
 [[package]]
 name = "smithy-http"
-version = "0.1.0"
+version = "0.2.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "smithy-core", marker = "python_full_version >= '3.12'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4e/62/5ba46c7432fbb0852acf8340402879ba53bb4c009b875e1b5b2e9df844ff/smithy_http-0.1.0.tar.gz", hash = "sha256:ed44552531f594e31101f7186c7b01b508ecd38a860b45390a1cce7da700df4b", size = 28269, upload-time = "2025-09-29T19:37:18.629Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/3c/1c/44e99a7dfb8c39bf0c3d998accdf4573a7a3488863b90f21af260cec2d45/smithy_http-0.2.0.tar.gz", hash = "sha256:2382562fa9af326be455f14b18615f16ffe9db756e51b2a4ca0d23e1b881cff8", size = 26729, upload-time = "2025-10-21T20:21:06.146Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5b/23/d18076ea45b3000c5e9eb8ebd75a4ea1b65b5c59e5c2080a119e2679dfba/smithy_http-0.1.0-py3-none-any.whl", hash = "sha256:7657aaf4b9e025cb9d317406f417b49cf19fba9d1b2ab4f5e6d9dc5a2dd7cdba", size = 38995, upload-time = "2025-09-29T19:37:17.506Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/e2/d475fad81ac74ec0e145cb6d72afe5ecde4e2358bd632c2fd5d3f4bc87dc/smithy_http-0.2.0-py3-none-any.whl", hash = "sha256:49ee2402d7737798d70f99f491fbfb2a5767283ae562e21b6f86e3fd14f3e3e0", size = 37328, upload-time = "2025-10-21T20:21:05.362Z" },
 ]
 
 [package.optional-dependencies]
@@ -6696,14 +6619,14 @@ wheels = [
 
 [[package]]
 name = "speechmatics-rt"
-version = "0.4.2"
+version = "0.5.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/17/2e/d694390d58b9b6807280441d1275856f5a316c3e8a815c2037502636bbea/speechmatics_rt-0.4.2.tar.gz", hash = "sha256:c0f7ed34442b0f505a12d1b19c8cc8dc2cc0b1a423aeb5669ca0738fc5e59f0d", size = 26142, upload-time = "2025-09-30T10:50:36.804Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/57/26/10359e1f16c2aa6a198eb11a9056f4a86a8bb8d4e610bbbe4a118b227b59/speechmatics_rt-0.5.0.tar.gz", hash = "sha256:ca974a186a012f946fd997deeaf3bf1c4f203f6d6e05a866172d27709183afc8", size = 26832, upload-time = "2025-10-15T15:54:25.695Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/9a/c7/2cd551c71e14256ca463f31feec17f466b57c2730d636e20803e7a541104/speechmatics_rt-0.4.2-py3-none-any.whl", hash = "sha256:70b91ff750e2f7516eaf1839d39f7a8ac65ff6665638b837cf67bab9cc9967bc", size = 32131, upload-time = "2025-09-30T10:50:35.656Z" },
+    { url = "https://files.pythonhosted.org/packages/47/2e/9931ebe9360e9d385c68826b33137c2c9a4cfa361cd929d1ac6e72ebfe53/speechmatics_rt-0.5.0-py3-none-any.whl", hash = "sha256:58151488f891fa00cf7054f0cfab1b1eb94b55c3441be587f7941c726caef991", size = 32850, upload-time = "2025-10-15T15:54:24.5Z" },
 ]
 
 [[package]]
@@ -7528,7 +7451,7 @@ wheels = [
 
 [[package]]
 name = "vllm"
-version = "0.9.2"
+version = "0.9.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp" },
@@ -7552,6 +7475,10 @@ dependencies = [
     { name = "numpy" },
     { name = "openai" },
     { name = "opencv-python-headless" },
+    { name = "opentelemetry-api" },
+    { name = "opentelemetry-exporter-otlp" },
+    { name = "opentelemetry-sdk" },
+    { name = "opentelemetry-semantic-conventions-ai" },
     { name = "outlines" },
     { name = "partial-json-parser" },
     { name = "pillow" },
@@ -7560,7 +7487,6 @@ dependencies = [
     { name = "protobuf" },
     { name = "psutil" },
     { name = "py-cpuinfo" },
-    { name = "pybase64" },
     { name = "pydantic" },
     { name = "python-json-logger" },
     { name = "pyyaml" },
@@ -7583,11 +7509,11 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "watchfiles" },
     { name = "xformers", marker = "platform_machine == 'x86_64' and sys_platform == 'linux'" },
-    { name = "xgrammar", marker = "platform_machine == 'aarch64' or platform_machine == 'arm64' or platform_machine == 'x86_64'" },
+    { name = "xgrammar", marker = "platform_machine == 'aarch64' or platform_machine == 'x86_64'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/35/89/2fbf95d398b5751b44c7256bd80e57c589142f1bfcc15f5dc76438b8853a/vllm-0.9.2.tar.gz", hash = "sha256:6b0d855ea8ba18d76364c9b82ea94bfcaa9c9e724055438b5733e4716ed104e1", size = 8997087, upload-time = "2025-07-08T04:49:01.722Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c5/5b/5f42b41d045c01821be62162fc6b1cfb14db1674027c7b623adb3a66dccf/vllm-0.9.1.tar.gz", hash = "sha256:c5ad11603f49a1fad05c88debabb8b839780403ce1b51751ec4da4e8a838082c", size = 8670972, upload-time = "2025-06-10T21:46:12.114Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/f4/72/c14ff1acac64294f45782769b9c8144a1c3e8d4f2228d4648197511b015a/vllm-0.9.2-cp38-abi3-manylinux1_x86_64.whl", hash = "sha256:f3c5da29a286f4933b480a5b4749fab226564f35c96928eeef547f88d385cd34", size = 383350132, upload-time = "2025-07-08T04:48:54.133Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/56/ffcf6215a571cf9aa58ded06a9640bff21b4918e27344677cd33290ab9da/vllm-0.9.1-cp38-abi3-manylinux1_x86_64.whl", hash = "sha256:28b99e8df39c7aaeda04f7e5353b18564a1a9d1c579691945523fc4777a1a8c8", size = 394637693, upload-time = "2025-06-10T21:46:01.784Z" },
 ]
 
 [[package]]
@@ -7897,7 +7823,6 @@ name = "xgrammar"
 version = "0.1.19"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "mlx-lm", marker = "platform_machine == 'arm64' and sys_platform == 'darwin'" },
     { name = "ninja" },
     { name = "pydantic" },
     { name = "sentencepiece" },