Can I resume a session after being closed? How should I manage the conversation context?

Thanks for reaching out, Roman. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

how do you save the conversation context if you want to resume a previous chat? I understand that context is lost once the session is over

Hey there! If you want to save your conversation in LiveKit and pick up right where you left off after your session ends, here’s a simple way to do it: 1. Access the Conversation History: • While your session is active, just use

session.history

to grab the full chat history. 2. Save the Conversation History: • Use the

add_shutdown_callback

method to save that history somewhere safe, like a database or a file. For example, you could save it as a JSON file like this:

from datetime import datetime
import json

def on_shutdown(session):
    history = session.history
    timestamp = datetime.now().strftime("%Y%m%d-%H%M%S")
    filename = f"conversation_{timestamp}.json"
    with open(filename, 'w') as f:
        json.dump([{"role": item.role, "content": item.content} for item in history], f)
    print(f"Conversation saved to {filename}")

agent.add_shutdown_callback(on_shutdown)

3. Load the Conversation History: • When you’re ready to resume, just load that saved history and use the

ChatContext

class to pass it to your new agent like this:

from livekit.agents import ChatContext

with open("conversation.json", 'r') as f:
    history_data = json.load(f)

chat_ctx = ChatContext()
for item in history_data:
    chat_ctx.add_message(role=item["role"], content=item["content"])

agent = MyAgent(chat_ctx=chat_ctx)

Just a couple of things to keep in mind: • You’ll want to set up your own storage for keeping conversations long-term, like a database. • It’s also a good idea to listen for events like

user_speech_committed

if you want to save messages as they happen. If you hit any bumps or want me to walk you through it, just let me know—I’m here to help!