Eval Library
L
For LiveKitAI Platform

Rooms Participants And Tracks

LiveKit (Cloud + Agents) · LiveKit

Real-time Voice & Video Infra — LiveKit

LiveKit evals — Rooms, Participants & Tracks (relift v3 InfraRed)

About LiveKit

LiveKit is open-source real-time voice/video infrastructure used to build voice agents and live experiences — a WebRTC SFU, telephony (SIP), recording/egress, and the LiveKit Agents framework for STT→LLM→TTS pipelines, available as LiveKit Cloud and self-hosted.

Employees

~50

Industry

Voice AI Infrastructure

Headquarters

New York, NY

Website

livekit.io

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Two browser tabs of the same user join the same LiveKit room with identity='user-42'. The second join arrives while the first is still publishing audio.

Per LiveKit docs, participant identity is unique per room — the new join displaces the prior session. Integrator must detect the kicked-out event on the first client (disconnect with reason DUPLICATE_IDENTITY) and decide between (a) surface 'opened in another tab' UI, or (b) namespace identity per …

Pass / FailAi Platformhigh
02

Operator stores JSON in Room.metadata: '{"tenant":"acme","plan":"pro"}'. A client SDK reads room.metadata and expects an object.

Per docs, Room.metadata is an opaque string up to the published size cap. Clients receive a string and must JSON.parse client-side. Integrator should version the schema (e.g., {"v":1,...}) and tolerate unknown fields. Do not rely on the SDK to deserialize for you.

Pass / FailAi Platformmedium
03

CreateRoom sets empty_timeout=300 (5 min) and departure_timeout=20. After the last participant leaves, agent expects the room to live another 5 minutes for graceful reconnect.

empty_timeout governs lifetime when the room never had participants; departure_timeout governs lifetime after the last participant leaves. Choose both deliberately — short departure_timeout drops rooms during transient client reconnects (mobile network handover); long departure_timeout wastes resou…

Pass / FailAi Platformmedium

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Livekit
  • Ai Platform
  • Rooms Participants And Tracks

Recommended for

LiveKit (Cloud + Agents)LiveKit customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.