# def llm_wrapper(metrics: LLMMetrics): # asyncio.create_task(on_llm_metrics(metrics)) # # async def on_llm_metrics(metrics: LLMMetrics): # logger.info(f"Received metrics llm: {metrics}") # # session.llm.on("metrics_collected", llm_wrapper) # # def tts_wrapper(metrics: TTSMetrics): # asyncio.create_task(on_tts_metrics(metrics)) # # async def on_tts_metrics(metrics: TTSMetrics): # logger.info(f"Received metrics tts: {metrics}") # # session.tts.on("metrics_collected", tts_wrapper) # def stt_wrapper(metrics: STTMetrics): # asyncio.create_task(on_stt_metrics(metrics)) # # async def on_stt_metrics(metrics: STTMetrics): # logger.info(f"Received metrics stt: {metrics}") I can use per plugin instance to subscribe over the metrics_collected event, as sessiion level metrics collected event is deprecated. but how will I track eou? there is no plugin instance to track eou

Hi Harshita Sukumar Patil, ⚠️ This channel will be deleted soon ⚠️ Please use our new community at https://community.livekit.io for technical discussions and to post technical questions. The Slack community is not going away, but we are migrating technical questions to our new forum. Please see full details here.

You’re right that moving metrics to the plugin level makes sense since session-level metrics are deprecated. For EOU, you won’t find it on a plugin instance because it isn’t really a plugin concern—it’s a turn-taking signal. The usual way is to infer it from the STT stream ending or final transcript event, or from the VAD/speech boundary signals in the session layer, depending on what your stack exposes. So instead of tracking EOU directly, you treat it as a session-level transition derived from those speech end indicators. @adorable-bear-14321