When

context.session.say

is interrupted, it does update the chat context, but only with the portion of speech that was actually heard before the interruption. The system uses a synchronized transcript to determine exactly what the user heard, truncates the message accordingly, and records it in the chat context with the

interrupted=True

flag. This ensures the chat history reflects only what was communicated up to the interruption point, preserving accuracy in the conversation log. Let me know if you need more technical details or code examples on this process. Sources: livekit-agents/livekit/agents/voice/agent_activity.py | Turn detection and interruptions | LiveKit Docs | Agent speech | LiveKit Docs