Raw LiveKit

agent-transport's AudioStreamServer wires observability internally. When you drive LiveKit Agents directly — your own AgentServer with @server.rtc_session(...) — two helpers replace the hand-rolled plumbing:

• init_observability(ctx.tagger, …) — validates the upload URL (raises if unset) and emits the full tag bundle (agent_id, account_id, agent.name, transport) the server's ingest path expects. One call instead of ~20 lines of tagger.add(...).
• run_judges_on_report(report, judges=…) — wraps the JudgeGroup construction, exception handling, structured logging, and llm.aclose() cleanup. Mix LiveKit built-ins with SDK judges freely.

Minimal worker

from agent_observability.livekit import init_observability, run_judges_on_report
from agent_observability.livekit.judges import default_judges
from livekit.agents import AgentServer, JobContext
from livekit.agents.evals import accuracy_judge

server = AgentServer()


async def on_session_end(ctx: JobContext) -> None:
    report = ctx.make_session_report()
    await run_judges_on_report(
        report,
        judges=[
            accuracy_judge(),     # LiveKit built-in
            *default_judges(),    # 4 ground-truth-free SDK judges
        ],
    )


@server.rtc_session(agent_name="support-bot", on_session_end=on_session_end)
async def entrypoint(ctx: JobContext) -> None:
    init_observability(
        ctx.tagger,
        agent_id="9c2f7e3d-…",   # stable opaque UUID
        agent_name="support-bot",
        account_id="acct-7",
        transport="text",
    )
    # …your usual AgentSession.start(...) setup

That's the whole observability surface for a raw-LiveKit worker — no hand-rolled tagger.add(...), no JudgeGroup boilerplate, no llm.aclose() cleanup.

Conversation goals (deprecated)

init_observability still accepts a goals=[Goal(name, description), …] parameter, and the server still stores the goal:<name>:<description> tags it emits — but no longer judges them. Conversation goals are superseded by custom judges: a name and a plain-language pass/fail description, created through the judges API and mapped onto an agent, in place of the goal declared in code. Drop goals from new integrations.

Running on agent-transport's AudioStreamServer (which wires the observability bootstrap internally)? add_goal_tags(ctx.tagger, goals) is deprecated the same way.

URL resolution

init_observability raises if neither LIVEKIT_OBSERVABILITY_URL nor the AGENT_OBSERVABILITY_URL fallback is set — there's no point continuing if the report has nowhere to go. For a non-fatal, warn-only contract, call ensure_observability_url() yourself instead.

Runnable example

A complete text-only worker (tool call, recording options, judges at end-of-call) lives in the repo at plugins/examples/python/text_only_livekit_worker.py:

export LIVEKIT_OBSERVABILITY_URL=https://obs.example.com
export AGENT_OBSERVABILITY_AGENT_ID=9c2f7e3d-4b8a-4d2e-9f1b-textonly
export OPENAI_API_KEY=sk-...
uv run plugins/examples/python/text_only_livekit_worker.py console --text --record

See the judge reference for the full catalogue.