You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We saw an error from the recognize task while the LLM was streaming, which in turn caused our agent to freeze/get stuck. When this happens, it seems that a coroutine never yielded as our background timers never went off after this.
{"message": "Error in _recognize_task\nTraceback (most recent call last):\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs\n return await fn(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/pipeline/human_input.py", line 150, in _recognize_task\n await asyncio.gather(*tasks)\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/pipeline/human_input.py", line 136, in _stt_stream_co\n async for ev in stt_stream:\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/stt/stt.py", line 315, in anext\n raise exc from None\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/stt/stt.py", line 215, in _main_task\n return await self._run()\n ^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/plugins/deepgram/stt.py", line 489, in _run\n ws = await self._connect_ws()\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/plugins/deepgram/stt.py", line 533, in _connect_ws\n ws = await asyncio.wait_for(\n ^^^^^^^^^^^^^^^^^^^^^^^\n File "/usr/local/lib/python3.12/asyncio/tasks.py", line 520, in wait_for\n return await fut\n ^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/aiohttp/client.py", line 1019, in _ws_connect\n raise WSServerHandshakeError(\naiohttp.client_exceptions.WSServerHandshakeError: 402, message='Invalid response status', url='wss://api.deepgram.com/v1/listen?model=nova-2-general&punctuate=true&smart_format=true&no_delay=true&interim_results=true&encoding=linear16&vad_events=true&sample_rate=16000&channels=1&endpointing=25&profanity_filter=false&language=en-US'", "level": "ERROR", "name": "livekit.agents.pipeline", "pid": 87, "job_id": "AJ_4FqHxRhbBWUc", "timestamp": "2024-12-18T14:08:29.478321+00:00"}
The text was updated successfully, but these errors were encountered:
We saw an error from the recognize task while the LLM was streaming, which in turn caused our agent to freeze/get stuck. When this happens, it seems that a coroutine never yielded as our background timers never went off after this.
{"message": "Error in _recognize_task\nTraceback (most recent call last):\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs\n return await fn(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/pipeline/human_input.py", line 150, in _recognize_task\n await asyncio.gather(*tasks)\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/pipeline/human_input.py", line 136, in _stt_stream_co\n async for ev in stt_stream:\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/stt/stt.py", line 315, in anext\n raise exc from None\n File "/app/.venv/lib/python3.12/site-packages/livekit/agents/stt/stt.py", line 215, in _main_task\n return await self._run()\n ^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/plugins/deepgram/stt.py", line 489, in _run\n ws = await self._connect_ws()\n ^^^^^^^^^^^^^^^^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/livekit/plugins/deepgram/stt.py", line 533, in _connect_ws\n ws = await asyncio.wait_for(\n ^^^^^^^^^^^^^^^^^^^^^^^\n File "/usr/local/lib/python3.12/asyncio/tasks.py", line 520, in wait_for\n return await fut\n ^^^^^^^^^\n File "/app/.venv/lib/python3.12/site-packages/aiohttp/client.py", line 1019, in _ws_connect\n raise WSServerHandshakeError(\naiohttp.client_exceptions.WSServerHandshakeError: 402, message='Invalid response status', url='wss://api.deepgram.com/v1/listen?model=nova-2-general&punctuate=true&smart_format=true&no_delay=true&interim_results=true&encoding=linear16&vad_events=true&sample_rate=16000&channels=1&endpointing=25&profanity_filter=false&language=en-US'", "level": "ERROR", "name": "livekit.agents.pipeline", "pid": 87, "job_id": "AJ_4FqHxRhbBWUc", "timestamp": "2024-12-18T14:08:29.478321+00:00"}
The text was updated successfully, but these errors were encountered: