Fixed an issue that start_callback was not invoked for some LLM services.

CHANGELOG.md

@@ -27,6 +27,8 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 
 ### Fixed
 
+- Fixed an issue that `start_callback` was not invoked for some LLM services.
+
 - Fixed an issue that would cause `DeepgramSTTService` to stop working after an
   error occurred (e.g. sudden network loss). If the network recovered we would
   not reconnect.

examples/foundational/14e-function-calling-gemini.py

@@ -14,6 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -30,6 +31,12 @@ logger.add(sys.stderr, level="DEBUG")
 video_participant_id = None
 
 
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
+    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
     location = arguments["location"]
     await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
@@ -63,7 +70,7 @@ async def main():
         )
 
         llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather)
+        llm.register_function("get_weather", get_weather, start_fetch_weather)
         llm.register_function("get_image", get_image)
 
         tools = [

src/pipecat/services/ai_services.py

@@ -175,6 +175,7 @@ class LLMService(AIService):
             f = self._callbacks[None]
         else:
             return None
+        await self.call_start_function(context, function_name)
         await context.call_function(
             f,
             function_name=function_name,

src/pipecat/services/openai.py

@@ -266,7 +266,6 @@ class BaseOpenAILLMService(LLMService):
                 if tool_call.function and tool_call.function.name:
                     function_name += tool_call.function.name
                     tool_call_id = tool_call.id
-                    await self.call_start_function(context, function_name)
                 if tool_call.function and tool_call.function.arguments:
                     # Keep iterating through the response to collect all the argument fragments
                     arguments += tool_call.function.arguments