Skip to main content

Real-Time Streaming

In progress — not available yet

Real-time streaming is under active development and is not enabled on accounts yet. Everything on these pages is documented ahead of availability and is subject to change — do not build against it as though it were live.

To show assistant replies today, poll conversation-state instead. A run typically settles in 7–11 seconds, so a 2-second poll gives a responsive-enough experience without Firebase.

Talk to your account team if you want to be told when this ships.

Assistant replies arrive token by token over Firebase Realtime Database, so a client can render text as it is generated instead of waiting for the finished message.

How It Works​

During generation, the platform emits token chunks, run lifecycle events, and finalized messages onto internal Kafka topics. A platform component (the Firebase bridge) subscribes to those topics and mirrors each event into RTDB, keyed by conversation. Your client attaches a Firebase listener to the relevant node and receives every write in order.

send-message (POST)  ──▶  runId
        │
        ▼
  generation runs ──▶ Kafka ──▶ Firebase bridge ──▶ RTDB nodes
        │                                               │
        │                             client listener ◀─┘  (real-time)
        ▼
  poll conversation-state  (alternative, no Firebase)

You authenticate to RTDB with the same Firebase ID token you send as the Authorization: Bearer header on REST calls (see the Mobile App example). Database security rules scope each user to their own conversations.

RTDB Node Layout​

All nodes are keyed by the conversation. {conversationId} is the threadId returned by create-thread (the same value you pass as conversation_key).

NodePurpose
streaming/{conversationId}/{messageSequence}Incremental token chunks for the in-flight assistant message
streaming/{conversationId}/{messageSequence}/metaStream status for that message (streaming → complete/error)
conversations/{conversationId}/statusAuthoritative conversation activity state (busy/idle)
events/{eventName}/{conversationId}/messagesFinalized messages once a turn settles
events/{eventName}/{conversationId}/runsGeneration started / completed markers

{messageSequence} is the sequence number of the assistant message being generated. Read the current sequence from the seq field on the conversations/{conversationId}/status node.

{eventName} is a sanitized event type, e.g. llm_v1_common_v1_conversationmessagepublishedevent for messages.

Where to next​

PageCovers
PayloadsChunk shape, conversation status, finalized messages
SubscribingA worked client subscription, and when to poll instead