Merge pull request #1261 from pipecat-ai/aleix/emualted-frames-being-triggered-prematurely

LLMUserContextAggregator: don't reset timer with interim transcription

CHANGELOG.md

@@ -36,7 +36,12 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 
 ### Fixed
 
-- Fixed an issue where `EndTaskFrame` was not triggering `on_client_disconnected` or closing the WebSocket in FastAPI.
+- Fixed an issue that would cause undesired interruptions via
+  `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
+  final transcriptions) where received.
+
+- Fixed an issue where `EndTaskFrame` was not triggering
+  `on_client_disconnected` or closing the WebSocket in FastAPI.
 
 - Fixed a context aggregator issue that would not append the LLM text response
   to the context if a function call happened in the same LLM turn.

src/pipecat/processors/aggregators/llm_response.py

@@ -293,7 +293,13 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
             await self.push_aggregation()
 
     async def _handle_transcription(self, frame: TranscriptionFrame):
-        self._aggregation += f" {frame.text}" if self._aggregation else frame.text
+        text = frame.text
+
+        # Make sure we really have some text.
+        if not text.strip():
+            return
+
+        self._aggregation += f" {text}" if self._aggregation else text
         # We just got a final result, so let's reset interim results.
         self._seen_interim_results = False
         # Reset aggregation timer.
@@ -301,8 +307,6 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
 
     async def _handle_interim_transcription(self, _: InterimTranscriptionFrame):
         self._seen_interim_results = True
-        # Reset aggregation timer.
-        self._aggregation_event.set()
 
     def _create_aggregation_task(self):
         self._aggregation_task = self.create_task(self._aggregation_task_handler())