Remove proxy warning for telephony bots

Quickstart to use Pipecat CLI

CHANGELOG.md

@@ -7,8 +7,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- `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`.
+
+### Fixed
+
+- Fixed an issue in `ServiceSwitcher` where the `STTService`s would result in
+  all STT services producing `TranscriptionFrame`s.
+
+## [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:
 
@@ -38,9 +60,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   # or
   context: OpenAILLMContext
 
-  # Reading messages from context
-  messages = context.messages
-
   ## AFTER:
 
   # Context aggregator type
@@ -51,9 +70,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
   # Context type
   context: LLMContext
-
-  # Reading messages from context
-  messages = context.get_messages()
   ```
 
 - Added support for `bulbul:v3` model in `SarvamTTSService` and
@@ -85,6 +101,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### 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:
@@ -106,8 +125,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### 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.
+  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

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.

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/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/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/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

@@ -50,7 +50,7 @@ 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 = []

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/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/processors/aggregators/llm_context.py

@@ -106,6 +106,19 @@ 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(self, llm_specific_filter: Optional[str] = None) -> List[LLMContextMessage]:
         """Get the current messages list.
 
@@ -113,7 +126,8 @@ 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/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

@@ -76,6 +76,7 @@ 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,
@@ -92,6 +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.
@@ -129,7 +131,7 @@ async def configure(
         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. "

src/pipecat/runner/run.py

@@ -82,6 +82,7 @@ from loguru import logger
 
 from pipecat.runner.types import (
     DailyRunnerArguments,
+    RunnerArguments,
     SmallWebRTCRunnerArguments,
     WebSocketRunnerArguments,
 )
@@ -309,7 +310,7 @@ def _setup_webrtc_routes(
     ):
         """Mimic Pipecat Cloud's proxy."""
         active_session = active_sessions.get(session_id)
-        if not active_session:
+        if active_session is None:
             return Response(content="Invalid or not-yet-ready session_id", status_code=404)
 
         if path.endswith("api/offer"):
@@ -529,9 +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
 
@@ -546,11 +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 },
@@ -567,45 +568,32 @@ 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()
+
+        result = None
+        if create_daily_room:
+            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)
 
-        from pipecat.runner.daily import configure
+        # Start the bot in the background
+        asyncio.create_task(bot_module.bot(runner_args))
 
-        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):
@@ -800,10 +788,6 @@ 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")

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/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

@@ -10,7 +10,8 @@ This module provides specialized context aggregators and message handling for AW
 including conversation history management and role-specific message processing.
 
 .. deprecated:: 0.0.91
-    AWS Nova Sonic now supports `LLMContext` and `LLMContextAggregatorPair`.
+    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:
@@ -26,9 +27,6 @@ including conversation history management and role-specific message processing.
     context: AWSNovaSonicLLMContext
     # or
     context: OpenAILLMContext
-
-    # Reading messages from context
-    messages = context.messages
     ```
 
     AFTER:
@@ -42,9 +40,6 @@ including conversation history management and role-specific message processing.
 
     # Context type
     context: LLMContext
-
-    # Reading messages from context
-    messages = context.get_messages()
     ```
 """
 
@@ -53,8 +48,10 @@ import warnings
 with warnings.catch_warnings():
     warnings.simplefilter("always")
     warnings.warn(
-        "Types in pipecat.services.aws.nova_sonic.context are deprecated. \n"
-        "AWS Nova Sonic now supports `LLMContext` and `LLMContextAggregatorPair`. \n"
+        "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"
@@ -67,8 +64,6 @@ with warnings.catch_warnings():
         "context: AWSNovaSonicLLMContext\n"
         "# or\n"
         "context: OpenAILLMContext\n\n"
-        "# Reading messages from context\n"
-        "messages = context.messages\n"
         "```\n\n"
         "AFTER:\n"
         "```\n"
@@ -79,9 +74,363 @@ with warnings.catch_warnings():
         "frame: LLMContextFrame\n\n"
         "# Context type\n"
         "context: LLMContext\n\n"
-        "# Reading messages from context\n"
-        "messages = context.messages\n"
         "```",
         DeprecationWarning,
         stacklevel=2,
     )
+
+import copy
+from dataclasses import dataclass, field
+from enum import Enum
+
+from loguru import logger
+
+from pipecat.frames.frames import (
+    BotStoppedSpeakingFrame,
+    DataFrame,
+    Frame,
+    FunctionCallResultFrame,
+    InterruptionFrame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMMessagesAppendFrame,
+    LLMMessagesUpdateFrame,
+    LLMSetToolChoiceFrame,
+    LLMSetToolsFrame,
+    TextFrame,
+    UserImageRawFrame,
+)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.services.aws.nova_sonic.frames import AWSNovaSonicFunctionCallResultFrame
+from pipecat.services.openai.llm import (
+    OpenAIAssistantContextAggregator,
+    OpenAIUserContextAggregator,
+)
+
+
+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
+
+
+@dataclass
+class AWSNovaSonicConversationHistory:
+    """Complete conversation history for AWS Nova Sonic initialization.
+
+    Parameters:
+        system_instruction: System-level instruction for the conversation.
+        messages: List of conversation messages between user and assistant.
+    """
+
+    system_instruction: str = None
+    messages: list[AWSNovaSonicConversationHistoryMessage] = field(default_factory=list)
+
+
+class AWSNovaSonicLLMContext(OpenAILLMContext):
+    """Specialized LLM context for AWS Nova Sonic service.
+
+    Extends OpenAI context with Nova Sonic-specific message handling,
+    conversation history management, and text buffering capabilities.
+    """
+
+    def __init__(self, messages=None, tools=None, **kwargs):
+        """Initialize AWS Nova Sonic LLM context.
+
+        Args:
+            messages: Initial messages for the context.
+            tools: Available tools for the context.
+            **kwargs: Additional arguments passed to parent class.
+        """
+        super().__init__(messages=messages, tools=tools, **kwargs)
+        self.__setup_local()
+
+    def __setup_local(self, system_instruction: str = ""):
+        self._assistant_text = ""
+        self._user_text = ""
+        self._system_instruction = system_instruction
+
+    @staticmethod
+    def upgrade_to_nova_sonic(
+        obj: OpenAILLMContext, system_instruction: str
+    ) -> "AWSNovaSonicLLMContext":
+        """Upgrade an OpenAI context to AWS Nova Sonic context.
+
+        Args:
+            obj: The OpenAI context to upgrade.
+            system_instruction: System instruction for the context.
+
+        Returns:
+            The upgraded AWS Nova Sonic context.
+        """
+        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, AWSNovaSonicLLMContext):
+            obj.__class__ = AWSNovaSonicLLMContext
+            obj.__setup_local(system_instruction)
+        return obj
+
+    # NOTE: this method has the side-effect of updating _system_instruction from messages
+    def get_messages_for_initializing_history(self) -> AWSNovaSonicConversationHistory:
+        """Get conversation history for initializing AWS Nova Sonic session.
+
+        Processes stored messages and extracts system instruction and conversation
+        history in the format expected by AWS Nova Sonic.
+
+        Returns:
+            Formatted conversation history with system instruction and messages.
+        """
+        history = AWSNovaSonicConversationHistory(system_instruction=self._system_instruction)
+
+        # Bail if there are no messages
+        if not self.messages:
+            return history
+
+        messages = copy.deepcopy(self.messages)
+
+        # If we have a "system" message as our first message, let's pull that out into "instruction"
+        if messages[0].get("role") == "system":
+            system = messages.pop(0)
+            content = system.get("content")
+            if isinstance(content, str):
+                history.system_instruction = content
+            elif isinstance(content, list):
+                history.system_instruction = content[0].get("text")
+            if history.system_instruction:
+                self._system_instruction = history.system_instruction
+
+        # Process remaining messages to fill out conversation history.
+        # Nova Sonic supports "user" and "assistant" messages in history.
+        for message in messages:
+            history_message = self.from_standard_message(message)
+            if history_message:
+                history.messages.append(history_message)
+
+        return history
+
+    def get_messages_for_persistent_storage(self):
+        """Get messages formatted for persistent storage.
+
+        Returns:
+            List of messages including system instruction if present.
+        """
+        messages = super().get_messages_for_persistent_storage()
+        # If we have a system instruction and messages doesn't already contain it, add it
+        if self._system_instruction and not (messages and messages[0].get("role") == "system"):
+            messages.insert(0, {"role": "system", "content": self._system_instruction})
+        return messages
+
+    def from_standard_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
+
+    def buffer_user_text(self, text):
+        """Buffer user text for later flushing to context.
+
+        Args:
+            text: User text to buffer.
+        """
+        self._user_text += f" {text}" if self._user_text else text
+        # logger.debug(f"User text buffered: {self._user_text}")
+
+    def flush_aggregated_user_text(self) -> str:
+        """Flush buffered user text to context as a complete message.
+
+        Returns:
+            The flushed user text, or empty string if no text was buffered.
+        """
+        if not self._user_text:
+            return ""
+        user_text = self._user_text
+        message = {
+            "role": "user",
+            "content": [{"type": "text", "text": user_text}],
+        }
+        self._user_text = ""
+        self.add_message(message)
+        # logger.debug(f"Context updated (user): {self.get_messages_for_logging()}")
+        return user_text
+
+    def buffer_assistant_text(self, text):
+        """Buffer assistant text for later flushing to context.
+
+        Args:
+            text: Assistant text to buffer.
+        """
+        self._assistant_text += text
+        # logger.debug(f"Assistant text buffered: {self._assistant_text}")
+
+    def flush_aggregated_assistant_text(self):
+        """Flush buffered assistant text to context as a complete message."""
+        if not self._assistant_text:
+            return
+        message = {
+            "role": "assistant",
+            "content": [{"type": "text", "text": self._assistant_text}],
+        }
+        self._assistant_text = ""
+        self.add_message(message)
+        # logger.debug(f"Context updated (assistant): {self.get_messages_for_logging()}")
+
+
+@dataclass
+class AWSNovaSonicMessagesUpdateFrame(DataFrame):
+    """Frame containing updated AWS Nova Sonic context.
+
+    Parameters:
+        context: The updated AWS Nova Sonic LLM context.
+    """
+
+    context: AWSNovaSonicLLMContext
+
+
+class AWSNovaSonicUserContextAggregator(OpenAIUserContextAggregator):
+    """Context aggregator for user messages in AWS Nova Sonic conversations.
+
+    Extends the OpenAI user context aggregator to emit Nova Sonic-specific
+    context update frames.
+    """
+
+    async def process_frame(
+        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
+    ):
+        """Process frames and emit Nova Sonic-specific context updates.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction the frame is traveling.
+        """
+        await super().process_frame(frame, direction)
+
+        # Parent does not push LLMMessagesUpdateFrame
+        if isinstance(frame, LLMMessagesUpdateFrame):
+            await self.push_frame(AWSNovaSonicMessagesUpdateFrame(context=self._context))
+
+
+class AWSNovaSonicAssistantContextAggregator(OpenAIAssistantContextAggregator):
+    """Context aggregator for assistant messages in AWS Nova Sonic conversations.
+
+    Provides specialized handling for assistant responses and function calls
+    in AWS Nova Sonic context, with custom frame processing logic.
+    """
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Process frames with Nova Sonic-specific logic.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction the frame is traveling.
+        """
+        # HACK: For now, disable the context aggregator by making it just pass through all frames
+        # that the parent handles (except the function call stuff, which we still need).
+        # For an explanation of this hack, see
+        # AWSNovaSonicLLMService._report_assistant_response_text_added.
+        if isinstance(
+            frame,
+            (
+                InterruptionFrame,
+                LLMFullResponseStartFrame,
+                LLMFullResponseEndFrame,
+                TextFrame,
+                LLMMessagesAppendFrame,
+                LLMMessagesUpdateFrame,
+                LLMSetToolsFrame,
+                LLMSetToolChoiceFrame,
+                UserImageRawFrame,
+                BotStoppedSpeakingFrame,
+            ),
+        ):
+            await self.push_frame(frame, direction)
+        else:
+            await super().process_frame(frame, direction)
+
+    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
+        """Handle function call results for AWS Nova Sonic.
+
+        Args:
+            frame: The function call result frame to handle.
+        """
+        await super().handle_function_call_result(frame)
+
+        # The standard function callback code path pushes the FunctionCallResultFrame from the LLM
+        # itself, so we didn't have a chance to add the result to the AWS Nova Sonic server-side
+        # context. Let's push a special frame to do that.
+        await self.push_frame(
+            AWSNovaSonicFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
+        )
+
+
+@dataclass
+class AWSNovaSonicContextAggregatorPair:
+    """Pair of user and assistant context aggregators for AWS Nova Sonic.
+
+    Parameters:
+        _user: The user context aggregator.
+        _assistant: The assistant context aggregator.
+    """
+
+    _user: AWSNovaSonicUserContextAggregator
+    _assistant: AWSNovaSonicAssistantContextAggregator
+
+    def user(self) -> AWSNovaSonicUserContextAggregator:
+        """Get the user context aggregator.
+
+        Returns:
+            The user context aggregator instance.
+        """
+        return self._user
+
+    def assistant(self) -> AWSNovaSonicAssistantContextAggregator:
+        """Get the assistant context aggregator.
+
+        Returns:
+            The assistant context aggregator instance.
+        """
+        return self._assistant

src/pipecat/services/aws_nova_sonic/context.py

@@ -10,78 +10,12 @@ This module provides specialized context aggregators and message handling for AW
 including conversation history management and role-specific message processing.
 
 .. deprecated:: 0.0.91
-    AWS Nova Sonic now supports `LLMContext` and `LLMContextAggregatorPair`.
+    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
-
-    # Reading messages from context
-    messages = context.messages
-    ```
-
-    AFTER:
-    ```
-    # Setup
-    context = LLMContext(messages, tools)
-    context_aggregator = LLMContextAggregatorPair(context)
-
-    # Context frame type
-    frame: LLMContextFrame
-
-    # Context type
-    context: LLMContext
-
-    # Reading messages from context
-    messages = context.get_messages()
-    ```
+    See deprecation warning in pipecat.services.aws.nova_sonic.context for more
+    details.
 """
 
-import warnings
-
-with warnings.catch_warnings():
-    warnings.simplefilter("always")
-    warnings.warn(
-        "Types in pipecat.services.aws_nova_sonic.context are deprecated. \n"
-        "AWS Nova Sonic now supports `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"
-        "# Reading messages from context\n"
-        "messages = context.messages\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"
-        "# Reading messages from context\n"
-        "messages = context.messages\n"
-        "```",
-        DeprecationWarning,
-        stacklevel=2,
-    )
+from pipecat.services.aws.nova_sonic.context import *

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

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]]
@@ -4633,7 +4633,7 @@ 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" },
@@ -6483,16 +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]
@@ -6526,14 +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]