Add deprecation version, fix foundational example double system message

examples/foundational/07f-interruptible-azure-http.py

@@ -65,8 +65,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AzureLLMService(
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-        model=os.getenv("AZURE_CHATGPT_MODEL"),
         settings=AzureLLMSettings(
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
             system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         ),
     )

examples/foundational/07f-interruptible-azure.py

@@ -65,8 +65,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AzureLLMService(
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-        model=os.getenv("AZURE_CHATGPT_MODEL"),
         settings=AzureLLMSettings(
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
             system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         ),
     )

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

@@ -63,9 +63,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8),
         settings=AWSBedrockLLMSettings(
+            model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+            temperature=0.8,
             system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         ),
     )

examples/foundational/07o-interruptible-assemblyai-turn-detection.py

@@ -94,7 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("ASSEMBLYAI_API_KEY"),
         vad_force_turn_endpoint=False,  # Use AssemblyAI's built-in turn detection
         settings=AssemblyAISTTSettings(
-            speech_model="u3-rt-pro",
+            model="u3-rt-pro",
             # Optional: Tune turn detection timing (defaults shown below)
             # min_turn_silence=100,  # Default
             # max_turn_silence=1000,  # Default

examples/foundational/14d-function-calling-aws-video.py

@@ -99,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
         settings=AWSBedrockLLMSettings(
-            model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+            model="us.anthropic.claude-sonnet-4-6",
             # Note: usually, prefer providing latency="optimized" param.
             # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
             # which we need for image input.
@@ -170,7 +170,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         context.add_message(
             {
                 "role": "user",
-                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+                "content": f"Please introduce yourself to the user briefly; don't mention the camera. Use '{client_id}' as the user ID during function calls.",
             }
         )
         await task.queue_frames([LLMRunFrame()])

examples/foundational/55zzn-update-settings-groq-stt.py

@@ -99,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
-        context.add_message({"user": "system", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
         await asyncio.sleep(10)

src/pipecat/processors/aggregators/llm_context.py

@@ -255,7 +255,7 @@ class LLMContext:
         this method, which is part of the public API of OpenAILLMContext but
         doesn't need to be for LLMContext.
 
-        .. deprecated::
+        .. deprecated:: 0.0.92
             Use `get_messages()` instead.
 
         Returns:

src/pipecat/processors/user_idle_processor.py

@@ -27,7 +27,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 class UserIdleProcessor(FrameProcessor):
     """Monitors user inactivity and triggers callbacks after timeout periods.
 
-    .. deprecated::
+    .. deprecated:: 0.0.100
         UserIdleProcessor is deprecated in 0.0.100 and will be removed in a future version.
         Use LLMUserAggregator with user_idle_timeout parameter instead.
 

src/pipecat/services/anthropic/llm.py

@@ -170,7 +170,7 @@ class AnthropicLLMService(LLMService):
     class InputParams(BaseModel):
         """Input parameters for Anthropic model inference.
 
-        .. deprecated::
+        .. deprecated:: 0.0.105
             Use ``AnthropicLLMSettings`` instead. Pass settings directly via the
             ``settings`` parameter of :class:`AnthropicLLMService`.
 
@@ -231,12 +231,12 @@ class AnthropicLLMService(LLMService):
             api_key: Anthropic API key for authentication.
             model: Model name to use.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AnthropicLLMSettings(model=...)`` instead.
 
             params: Optional model parameters for inference.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AnthropicLLMSettings(...)`` instead.
 
             settings: Runtime-updatable settings for this service.  When both

src/pipecat/services/assemblyai/stt.py

@@ -657,7 +657,7 @@ class AssemblyAISTTService(WebsocketSTTService):
         await self.start_processing_metrics()
         await self.broadcast_frame(UserStartedSpeakingFrame)
         if self._should_interrupt:
-            await self.push_interruption_task_frame_and_wait()
+            await self.broadcast_interruption()
         self._user_speaking = True
 
     async def _handle_termination(self, message: TerminationMessage):

src/pipecat/services/aws/llm.py

@@ -754,7 +754,7 @@ class AWSBedrockLLMService(LLMService):
     class InputParams(BaseModel):
         """Input parameters for AWS Bedrock LLM service.
 
-        .. deprecated::
+        .. deprecated:: 0.0.105
             Use ``AWSBedrockLLMSettings`` instead. Pass settings directly via the
             ``settings`` parameter of :class:`AWSBedrockLLMService`.
 
@@ -795,7 +795,7 @@ class AWSBedrockLLMService(LLMService):
         Args:
             model: The AWS Bedrock model identifier to use.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AWSBedrockLLMSettings(model=...)`` instead.
 
             aws_access_key: AWS access key ID. If None, uses default credentials.
@@ -804,7 +804,7 @@ class AWSBedrockLLMService(LLMService):
             aws_region: AWS region for the Bedrock service.
             params: Model parameters and configuration.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AWSBedrockLLMSettings(...)`` instead.
 
             settings: Runtime-updatable settings for this service.  When both

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

@@ -280,7 +280,7 @@ class AWSNovaSonicLLMService(LLMService):
                 - Nova Sonic (the older model): "us-east-1", "ap-northeast-1"
             model: Model identifier. Defaults to "amazon.nova-2-sonic-v1:0".
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AWSNovaSonicLLMSettings(model=...)`` instead.
 
             voice_id: Voice ID for speech synthesis.
@@ -289,7 +289,7 @@ class AWSNovaSonicLLMService(LLMService):
                 - Nova 2 Sonic (the default model): see https://docs.aws.amazon.com/nova/latest/nova2-userguide/sonic-language-support.html
                 - Nova Sonic (the older model): see https://docs.aws.amazon.com/nova/latest/userguide/available-voices.html.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=AWSNovaSonicLLMSettings(voice=...)`` instead.
 
             params: Model parameters for audio configuration and inference.

src/pipecat/services/aws/stt.py

@@ -99,13 +99,13 @@ class AWSTranscribeSTTService(WebsocketSTTService):
         # 1. Initialize default_settings with hardcoded defaults
         default_settings = AWSTranscribeSTTSettings(
             model=None,
-            language=self.language_to_service_language(Language.EN) or "en-US",
+            language=self.language_to_service_language(Language.EN),
         )
 
         # 2. Apply direct init arg overrides (deprecated)
         if language is not None:
             _warn_deprecated_param("language", AWSTranscribeSTTSettings, "language")
-            default_settings.language = self.language_to_service_language(language) or "en-US"
+            default_settings.language = self.language_to_service_language(language)
 
         # 3. No params to apply
 

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

@@ -552,7 +552,7 @@ class ContextWindowCompressionParams(BaseModel):
 class InputParams(BaseModel):
     """Input parameters for Gemini Live generation.
 
-    .. deprecated::
+    .. deprecated:: 0.0.105
         Use ``GeminiLiveLLMSettings`` instead.
 
     Parameters:
@@ -678,7 +678,7 @@ class GeminiLiveLLMService(LLMService):
 
             model: Model identifier to use.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GeminiLiveLLMSettings(model=...)`` instead.
 
             voice_id: TTS voice identifier. Defaults to "Charon".
@@ -691,7 +691,7 @@ class GeminiLiveLLMService(LLMService):
             tools: Tools/functions available to the model. Defaults to None.
             params: Configuration parameters for the model.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GeminiLiveLLMSettings(...)`` instead.
 
             settings: Gemini Live LLM settings. If provided together with deprecated

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

@@ -88,7 +88,7 @@ class GeminiLiveVertexLLMService(GeminiLiveLLMService):
             project_id: Google Cloud project ID.
             model: Model identifier to use.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GeminiLiveLLMSettings(model=...)`` instead.
 
             voice_id: TTS voice identifier. Defaults to "Charon".
@@ -102,7 +102,7 @@ class GeminiLiveVertexLLMService(GeminiLiveLLMService):
             params: Configuration parameters for the model along with Vertex AI
                 location and project ID.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GeminiLiveLLMSettings(...)`` instead.
 
             settings: Gemini Live LLM settings. If provided together with deprecated

src/pipecat/services/google/llm.py

@@ -754,7 +754,7 @@ class GoogleLLMService(LLMService):
     class InputParams(BaseModel):
         """Input parameters for Google AI models.
 
-        .. deprecated::
+        .. deprecated:: 0.0.105
             Use ``settings=GoogleLLMSettings(...)`` instead.
 
         Parameters:
@@ -797,12 +797,12 @@ class GoogleLLMService(LLMService):
             api_key: Google AI API key for authentication.
             model: Model name to use.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GoogleLLMSettings(model=...)`` instead.
 
             params: Optional model parameters for inference.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GoogleLLMSettings(...)`` instead.
 
             settings: Runtime-updatable settings for this service.  When both

src/pipecat/services/google/llm_vertex.py

@@ -128,14 +128,14 @@ class GoogleVertexLLMService(GoogleLLMService):
             credentials_path: Path to the service account JSON file.
             model: Model identifier (e.g., "gemini-2.5-flash").
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GoogleLLMSettings(model=...)`` instead.
 
             location: GCP region for Vertex AI endpoint (e.g., "us-east4").
             project_id: Google Cloud project ID.
             params: Input parameters for the model.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=GoogleLLMSettings(...)`` instead.
 
             settings: Runtime-updatable settings for this service.  When both

src/pipecat/services/google/stt.py

@@ -653,7 +653,7 @@ class GoogleSTTService(STTService):
     async def set_languages(self, languages: List[Language]):
         """Update the service's recognition languages.
 
-        .. deprecated::
+        .. deprecated:: 0.0.104
             Use ``STTUpdateSettingsFrame`` with ``GoogleSTTSettings(languages=...)``
             instead.
 

src/pipecat/services/openai_realtime_beta/openai.py

@@ -134,7 +134,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
             api_key: OpenAI API key for authentication.
             model: OpenAI model name.
 
-                .. deprecated::
+                .. deprecated:: 0.0.105
                     Use ``settings=OpenAIRealtimeBetaLLMSettings(model=...)`` instead.
 
             base_url: WebSocket base URL for the realtime API.

src/pipecat/services/sarvam/stt.py

@@ -414,7 +414,7 @@ class SarvamSTTService(STTService):
     async def set_prompt(self, prompt: Optional[str]):
         """Set the transcription/translation prompt and reconnect.
 
-        .. deprecated::
+        .. deprecated:: 0.0.104
             Use ``STTUpdateSettingsFrame(SarvamSTTSettings(prompt=...))`` instead.
 
         Args: