> ## 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.

# Gateway Request Channel Protocol • AI Agent SDK

> GatewayRequestChannelProtocol: Protocol for server→client interactive request/reply over the transport.

# GatewayRequestChannelProtocol

> Defined in the [**protocols**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/protocols.md) module.

AI Agent

Protocol for server→client interactive request/reply over the transport.

A concrete implementation is bound by the running gateway (in praisonai-bot)
and registered into the per-turn context so a blocked HITL turn can deliver
an :class:`GatewayServerRequest` to the connected client and await the
correlated :class:`GatewayServerReply`. `open_requests` returns the
still-open requests for a session so the gateway's resume path can re-issue
them alongside the event replay — a dropped connection never wedges a turn.

## Methods

> **[request()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/GatewayRequestChannelProtocol-request.md)**
>
> Deliver `req` to the session's client and await its reply.

> **[open\_requests()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/GatewayRequestChannelProtocol-open_requests.md)**
>
> Return the still-open (unanswered) requests for `session_id`.

## Source

> **[View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/gateway/protocols.py#L3769)**
>
> `praisonaiagents/gateway/protocols.py` at line 3769

***

## Related Documentation

> **[Gateway Feature](https://praison.ai/docs/docs/features/gateway)**


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.