Add the

@session.on("conversation_item_added")

event handler right after you create the

AgentSession

but before you call

session.start()

in your

agent.py

file. Here’s a friendly example to help you set it up:

from livekit.agents import ConversationItemAddedEvent

async def entrypoint(ctx: JobContext):
    # 1. Create the session
    session = AgentSession(
        llm=openai.LLM(model="gpt-4o-mini"),
        # ... other session configuration
    )

    # 2. Add event handlers here (after session creation, before session.start)
    @session.on("conversation_item_added")
    def on_conversation_item_added(event: ConversationItemAddedEvent):
        print(f"Conversation item added from {event.item.role}: {event.item.text_content}. interrupted: {event.item.interrupted}")
        # To check out all types of content:
        for content in event.item.content:
            if isinstance(content, str):
                print(f" - text: {content}")
            elif isinstance(content, ImageContent):
                print(f" - image: {content.image}")
            elif isinstance(content, AudioContent):
                print(f" - audio: {content.frame}, transcript: {content.transcript}")

    # 3. Start the session
    await session.start(
        agent=MyAgent(),
        room=ctx.room,
        # ... room options
    )

Don’t forget to import the event types you need:

from livekit.agents import ConversationItemAddedEvent
from livekit.agents.llm import ImageContent, AudioContent

Sources: Events and error handling | LiveKit Docs