chore: use low reasoning_effort in Inception function-calling example

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

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = InceptionLLMService(
         api_key=os.environ["INCEPTION_API_KEY"],
         settings=InceptionLLMService.Settings(
-            reasoning_effort="instant",
+            reasoning_effort="low",
             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.",
         ),
     )

src/pipecat/services/inception/llm.py

@@ -27,6 +27,7 @@ class InceptionLLMSettings(BaseOpenAILLMService.Settings):
             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).
+            Defaults to True.
     """
 
     reasoning_effort: Literal["instant", "low", "medium", "high"] | None | _NotGiven = field(
@@ -68,7 +69,7 @@ class InceptionLLMService(OpenAILLMService):
         default_settings = self.Settings(
             model="mercury-2",
             reasoning_effort=None,
-            realtime=None,
+            realtime=True,
         )
 
         if settings is not None: