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

Fix LLMTask._finish_function_call to bypass deferral

Browse Source 
self.queue_frame would defer the LLMMessagesAppendFrame because
_finish_function_call always runs inside a tool call. The subsequent
_flush_pipeline() then returned before the goodbye/handoff LLM output
was actually delivered. Use super().queue_frame to push the frame
straight into the pipeline, matching the pattern used in
_flush_pipeline().
This commit is contained in:
Aleix Conchillo Flaqué
2026-05-14 16:33:53 -07:00
parent 402cf8dade
commit a5bb9f65de
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/pipecat/tasks/llm/llm_task.py
View File

@@ -327,7 +327,10 @@ class LLMTask(PipelineTask):
messages: Optional LLM messages to inject before completing. messages: Optional LLM messages to inject before completing.
""" """
if messages: if messages:
await self.queue_frame(LLMMessagesAppendFrame(messages=messages, run_llm=True)) # Bypass our deferral override: this runs inside a tool call, so
# self.queue_frame would defer the frame and the flush below would
# return before the LLM output is delivered.
await super().queue_frame(LLMMessagesAppendFrame(messages=messages, run_llm=True))
await self._flush_pipeline() await self._flush_pipeline()
if not result_callback: if not result_callback: