I'm glad you're exploring how to access data from

JobContext

at runtime after calling

await ctx.connect()

. You can interact with several helpful properties and methods exposed by the

JobContext

object. Let me walk you through some of the key elements: •

room

: This is an instance of

rtc.Room

, allowing you to interact with the LiveKit room, including participants and tracks. •

agent

: Represents the local participant (that’s you, the agent) once connected to the room. •

job

: Contains valuable information about the current job, like metadata for configuration or user-specific data. •

worker_id

: This is the ID of the worker running the job, handy for tracking purposes. •

proc

: Gives you access to process-specific state through

JobProcess.userData

, which is great for storing persistent data during the job lifecycle. Here’s a simple example in Python to illustrate these points:

async def entrypoint(ctx: JobContext):
    await ctx.connect()  # Establish connection to the room

    # Access the room and agent (local participant)
    room = ctx.room
    agent = ctx.agent

    # Access job metadata (e.g., passed during dispatch)
    job_metadata = ctx.job.metadata
    print(f"Job metadata: {job_metadata}")

    # Access worker ID
    worker_id = ctx.worker_id
    print(f"Worker ID: {worker_id}")

    # Store and retrieve custom data in process
    ctx.proc.userData["custom_state"] = "example_value"
    print(f"Custom state: {ctx.proc.userData.get('custom_state')}")

If you’d like to dive deeper, I highly recommend checking out the Job Lifecycle documentation. It’s a great resource, and I’m here if you have any questions or need further guidance! Sources: livekit-agents/livekit/agents/ipc/job_proc_lazy_main.py | Job lifecycle | LiveKit Docs