Code review fixes

examples/function-calling/function-calling-inception.py

@@ -39,6 +39,10 @@ async def fetch_weather_from_api(params: FunctionCallParams):
     await params.result_callback({"conditions": "nice", "temperature": "75"})
 
 
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
@@ -72,23 +76,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = InceptionLLMService(
         api_key=os.environ["INCEPTION_API_KEY"],
         settings=InceptionLLMService.Settings(
-            reasoning_effort="medium",
+            reasoning_effort="instant",
-            system_instruction="""You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
-
-You have one functions available:
-
-1. get_current_weather is used to get current weather information.
-
-Infer whether to use Fahrenheit or Celsius automatically based on the location, unless the user specifies a preference.
-
-Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
-
-    Respond to what the user said in a creative and helpful way.""",
         ),
     )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
 
     @llm.event_handler("on_function_calls_started")
     async def on_function_calls_started(service, function_calls):
@@ -110,7 +105,19 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
         },
         required=["location", "format"],
     )
-    tools = ToolsSchema(standard_tools=[weather_function])
+
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
 
     context = LLMContext(tools=tools)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
@@ -143,6 +150,9 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

scripts/evals/run-release-evals.py

@@ -198,6 +198,7 @@ TESTS_FUNCTION_CALLING = [
     ("function-calling/function-calling-sarvam.py", EVAL_WEATHER),
     ("function-calling/function-calling-novita.py", EVAL_WEATHER),
     ("function-calling/function-calling-deepseek.py", EVAL_WEATHER),
+    ("function-calling/function-calling-inception.py", EVAL_WEATHER),
     # Video
     ("function-calling/function-calling-anthropic-video.py", EVAL_VISION_CAMERA),
     ("function-calling/function-calling-aws-video.py", EVAL_VISION_CAMERA),

src/pipecat/services/inception/llm.py

@@ -24,7 +24,8 @@ class InceptionLLMSettings(BaseOpenAILLMService.Settings):
 
     Parameters:
         reasoning_effort: Controls how much reasoning the model applies.
-            One of "instant", "low", "medium", or "high". Defaults to "medium".
+            One of "instant", "low", "medium", or "high". When unset, the
+            parameter is omitted and Inception's server-side default applies.
         realtime: When True, reduces time to first diffusion block (TTFT).
     """
 
@@ -53,7 +54,6 @@ class InceptionLLMService(OpenAILLMService):
         *,
         api_key: str,
         base_url: str = "https://api.inceptionlabs.ai/v1",
-        model: str | None = None,
         settings: Settings | None = None,
         **kwargs,
     ):
@@ -62,20 +62,14 @@ class InceptionLLMService(OpenAILLMService):
         Args:
             api_key: The API key for accessing Inception's API.
             base_url: The base URL for Inception API. Defaults to "https://api.inceptionlabs.ai/v1".
-            model: The model identifier to use. Defaults to "mercury-2".
+            settings: Runtime-updatable settings.
-
-                .. deprecated:: 0.0.105
-                    Use ``settings=InceptionLLMService.Settings(model=...)`` instead.
-
-            settings: Runtime-updatable settings. When provided alongside deprecated
-                parameters, ``settings`` values take precedence.
             **kwargs: Additional keyword arguments passed to OpenAILLMService.
         """
-        default_settings = self.Settings(model="mercury-2", reasoning_effort=None, realtime=None)
+        default_settings = self.Settings(
-
+            model="mercury-2",
-        if model is not None:
+            reasoning_effort=None,
-            self._warn_init_param_moved_to_settings("model", "model")
+            realtime=None,
-            default_settings.model = model
+        )
 
         if settings is not None:
             default_settings.apply_update(settings)

uv.lock

@@ -4574,7 +4574,7 @@ requires-dist = [
     { name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1,<1" },
     { name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" },
 ]
-provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "kokoro", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "nebius", "neuphonic", "novita", "nvidia", "openai", "rnnoise", "openrouter", "perplexity", "piper", "qwen", "resembleai", "rime", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "vonage-video-connector", "webrtc", "websocket", "websockets-base", "whisper", "xai"]
+provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inception", "inworld", "koala", "kokoro", "langchain", "lemonslice", "livekit", "lmnt", "local", "local-smart-turn", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "nebius", "neuphonic", "novita", "nvidia", "openai", "rnnoise", "openrouter", "perplexity", "piper", "qwen", "resembleai", "rime", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "smallest", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "vonage-video-connector", "webrtc", "websocket", "websockets-base", "whisper", "xai"]
 
 [package.metadata.requires-dev]
 dev = [