Skip to main content

​
What is a session?

When you connect to a model, Reactor creates a session on a GPU running that model. The session holds all of the state for your interaction: the model’s current generation context, any prompts you have sent, and the media streams flowing between the model and your app. A session is independent of the network connection. If your connection drops, the session keeps running on the GPU. You can reconnect and pick up where you left off without losing any model state.

​
Connection lifecycle

Every connection goes through four states:
Connection lifecycle: disconnected → connecting → waiting → ready
StateMeaning
disconnectedNo active connection
connectingNegotiating with Reactor to create a session
waitingSession created, waiting for a GPU to be assigned
readyConnected to the GPU. You can send commands and receive media
The waiting state is normal – Reactor has accepted your request and is assigning a GPU, which typically takes a few seconds. Once the status reaches ready, the WebRTC connection to the GPU is established and media starts flowing.

​
Disconnecting

When you disconnect, you can choose whether to keep the session alive: Non-recoverable disconnect (default): the session is terminated and all state is released. Use this when the user is done with the session. Recoverable disconnect: the session stays alive on the GPU. You can reconnect later and the model resumes exactly where it left off. Use this to survive network interruptions or let users resume later. 
// Terminate the session
await reactor.disconnect();

// Keep the session alive
await reactor.disconnect(true);
await reactor.reconnect();
You are billed for the full duration of a session, from connection until termination.

​
Session ID

Each session has a unique ID that persists across reconnections. You can access it once connected: 
const sessionId = reactor.getSessionId();
Include the session ID in support requests or logs to help trace issues to a specific session.