> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Supports Gateway Runtime • AI Agent SDK

> SupportsGatewayRuntime: Contract for channel adapters that accept the gateway runtime seams.

# SupportsGatewayRuntime

> Defined in the [**protocols**](../modules/protocols) module.

<Badge color="blue">AI Agent</Badge>

Contract for channel adapters that accept the gateway runtime seams.

Instead of the gateway reaching into an adapter's private session and
splicing `_identity_resolver` / `_delivery_router` / `_admission_gate`
/ `_locks` via `getattr`/`hasattr` (which silently no-ops on any
adapter whose session does not match the built-in shape), an adapter — in
tree or `pip`-installed — implements this one method. The gateway calls it
once with a :class:`GatewayRuntimeSeams`, so the same reliability guarantees
(admission/backpressure, delivery routing, cross-platform turn locking)
hold for *every* adapter.

Adapters whose `__init__` creates a `BotSessionManager` get this for
free — the session manager implements `attach_gateway_runtime` and the
adapter can simply delegate to `self._session.attach_gateway_runtime(...)`.

## Methods

<CardGroup cols={2}>
  <Card title="attach_gateway_runtime()" icon="function" href="../functions/SupportsGatewayRuntime-attach_gateway_runtime">
    Wire the gateway runtime seams into this adapter.
  </Card>
</CardGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/bots/protocols.py#L348">
  `praisonaiagents/bots/protocols.py` at line 348
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Gateway Feature" icon="tower-broadcast" href="/docs/docs/features/gateway" />
</CardGroup>