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

Fix Gemini Live session resumption hanging after reconnect

Browse Source 
After a reconnect, _ready_for_realtime_input was never set back to True
because _create_initial_response (which sets the flag) is only called on
initial connection. This caused all audio/video/text to be silently
dropped after reconnecting, making the bot appear to hang.

Set the flag in _handle_session_ready when context already exists
(i.e. reconnect case) since we don't need to go through
_create_initial_response again.
This commit is contained in:
Paul Kompfner
2026-04-03 16:27:57 -04:00
parent 56aaebe1b0
commit 9df1e18b43
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/pipecat/services/google/gemini_live/llm.py
View File

@@ -1360,6 +1360,9 @@ class GeminiLiveLLMService(LLMService):
if self._run_llm_when_session_ready: if self._run_llm_when_session_ready:
self._run_llm_when_session_ready = False self._run_llm_when_session_ready = False
await self._create_initial_response() await self._create_initial_response()
elif self._context:
# Reconnect case: context already exists, no need for _create_initial_response
self._ready_for_realtime_input = True
async def _handle_msg_model_turn(self, msg: LiveServerMessage): async def _handle_msg_model_turn(self, msg: LiveServerMessage):
"""Handle the model turn message.""" """Handle the model turn message."""