wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Not forcing the bot resume speaking in case we receive no transcription.

Browse Source
This commit is contained in:
Filipi Fuchter
2025-06-24 20:12:49 -03:00
parent 7953e1e9d9
commit d5cd742237
1 changed files with 13 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src/pipecat/processors/aggregators/llm_response.py
View File

@@ -364,13 +364,13 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
# is received, this safeguard ensures # is received, this safeguard ensures
# the bot doesn't hang indefinitely while waiting to speak again. # the bot doesn't hang indefinitely while waiting to speak again.
elif not self._seen_interim_results and self._was_bot_speaking and not self._bot_speaking: elif not self._seen_interim_results and self._was_bot_speaking and not self._bot_speaking:
logger.warning( logger.warning("User stopped speaking but no new aggregation received.")
"User stopped speaking but no new aggregation received. Forcing aggregation processing to resume bot response."
)
# Resetting it so we don't trigger this twice # Resetting it so we don't trigger this twice
self._was_bot_speaking = False self._was_bot_speaking = False
# TODO: we are not enabling this for now, due to some STT services which can take as long as 2 seconds two return a transcription
# So we need more tests and probably make this feature configurable, disabled it by default.
# We are just pushing the same previous context to be processed again in this case # We are just pushing the same previous context to be processed again in this case
await self.push_frame(OpenAILLMContextFrame(self._context)) # await self.push_frame(OpenAILLMContextFrame(self._context))
async def _should_interrupt_based_on_strategies(self) -> bool: async def _should_interrupt_based_on_strategies(self) -> bool:
"""Check if interruption should occur based on configured strategies.""" """Check if interruption should occur based on configured strategies."""
@@ -410,8 +410,15 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
# We just stopped speaking. Let's see if there's some aggregation to # We just stopped speaking. Let's see if there's some aggregation to
# push. If the last thing we saw is an interim transcription, let's wait # push. If the last thing we saw is an interim transcription, let's wait
# pushing the aggregation as we will probably get a final transcription. # pushing the aggregation as we will probably get a final transcription.
if len(self._aggregation) > 0 and not self._seen_interim_results: if len(self._aggregation) > 0:
await self.push_aggregation() if not self._seen_interim_results:
await self.push_aggregation()
# Handles the case where both the user and the bot are not speaking,
# and the bot was previously speaking before the user interruption.
# So in this case we are resetting the aggregation timer
elif not self._seen_interim_results and self._was_bot_speaking and not self._bot_speaking:
# Reset aggregation timer.
self._aggregation_event.set()
async def _handle_bot_started_speaking(self, _: BotStartedSpeakingFrame): async def _handle_bot_started_speaking(self, _: BotStartedSpeakingFrame):
self._bot_speaking = True self._bot_speaking = True