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

LLMAssistantAggregator: no need to use BotStoppedSpeakingFrame

Browse Source 
The end of turn is already handle with interruptions or with
LLMFullResponseEndFrame. LLMFullResponseEndFrame should never be blocked,
otherwise the assistant would not work.
This commit is contained in:
Aleix Conchillo Flaqué
2026-01-08 16:30:22 -08:00
parent 4b61fd2d7d
commit cdb1074e11
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/pipecat/processors/aggregators/llm_response_universal.py
View File

@@ -23,7 +23,6 @@ from loguru import logger
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.frames.frames import (
AssistantImageRawFrame,
BotStoppedSpeakingFrame,
CancelFrame,
EndFrame,
Frame,
@@ -651,9 +650,6 @@ class LLMAssistantAggregator(LLMContextAggregator):
await self._handle_user_image_frame(frame)
elif isinstance(frame, AssistantImageRawFrame):
await self._handle_assistant_image_frame(frame)
elif isinstance(frame, BotStoppedSpeakingFrame):
await self.push_aggregation()
await self.push_frame(frame, direction)
else:
await self.push_frame(frame, direction)