Skip to content

overview.mdx

Latest commit

 

History

History
90 lines (73 loc) · 4.79 KB

overview.mdx

File metadata and controls

90 lines (73 loc) · 4.79 KB
title AI Agents
sidebarTitle Overview
description Durable multi-turn AI chats — one Trigger.dev task per conversation, surviving refreshes, deploys, and crashes.

import RcBanner from "/snippets/ai-chat-rc-banner.mdx";

An AI chat isn't a request — it's a session. chat.agent runs every conversation as a single long-lived Trigger.dev task: you write the loop, it wakes up when a message arrives, freezes when none do, and the same in-memory state and on-disk workspace survive across page refreshes, deploys, idle gaps, and crashes. The substrate handles the parts most teams stitch together by hand — turn lifecycle, mid-stream resume, recovery from cancel/crash/OOM, HITL approvals, deploy upgrades — so your code is the loop you'd write anyway: messages in, streamText out.

A minimal example

A chat.agent task takes messages, calls streamText, and returns the result. The frontend wires the Vercel AI SDK's useChat to a TriggerChatTransport. No API routes.

import { chat } from "@trigger.dev/sdk/ai";
import { streamText, stepCountIs } from "ai";
import { anthropic } from "@ai-sdk/anthropic";

export const myChat = chat.agent({
  id: "my-chat",
  run: async ({ messages, signal }) =>
    streamText({
      model: anthropic("claude-sonnet-4-5"),
      messages,
      abortSignal: signal,
      stopWhen: stepCountIs(15),
    }),
});
import { useChat } from "@ai-sdk/react";
import { useTriggerChatTransport } from "@trigger.dev/sdk/chat/react";

export function Chat() {
  const transport = useTriggerChatTransport<typeof myChat>({
    task: "my-chat",
    accessToken: ({ chatId }) => mintChatAccessToken(chatId),
    startSession: ({ chatId, clientData }) =>
      startChatSession({ chatId, clientData }),
  });
  const { messages, sendMessage } = useChat({ transport });
  // ... render UI
}

See Quick Start for the matching server actions and a runnable project.

Why use AI Agents on Trigger.dev

  • Resume across refreshes, deploys, and crashes. A chat in progress when you redeploy keeps streaming on the new version. Mid-stream refreshes pick up where they left off.
  • Native AI SDK support. Text, tool calls, reasoning, and custom data-* parts all flow through useChat over a custom ChatTransport. No custom protocol to maintain.
  • Multi-turn for free. Each turn is a step inside the same durable task; conversation history accumulates server-side, so clients only ship the new message.
  • Fast cold starts. Opt-in Head Start runs the first streamText step in your warm Next.js / Hono / SvelteKit server while the agent boots in parallel — cuts time-to-first-chunk roughly in half.
  • Production primitives ship in the box. Stop generation, steering, edits, branching, sub-agents, HITL tool approvals, version upgrades, recovery from cancel/crash/OOM — all first-class.
  • Observable. Every turn is a span in the Trigger.dev dashboard. Sessions are queryable via sessions.list for inbox-style UIs.

How it fits together

Three primitives, related but distinct:

  • Chat agents — the SDK surface you define with chat.agent(). Owns the turn loop, lifecycle hooks, and the response stream.
  • Sessions — the durable, bi-directional channel keyed on chatId that holds the conversation across run boundaries. A chat agent runs on top of a Session.
  • Sub-agents — Delegate work from one agent to another via AgentChat. The sub-agent runs as its own durable agent on its own session; its response streams back through the parent as preliminary tool results, so the frontend sees the sub-agent working inside the parent's tool card.

Next steps

Get a working chat in three steps — agent, token, frontend. Sessions, the turn loop, durable streams, and what survives a refresh. `chat.agent` options, lifecycle hooks, and the raw-task primitives. Declare tools so `toModelOutput` survives across turns, typed in `run()`. HITL approvals, branching, sub-agents, OOM/crash recovery. Size and release connection pools so agents don't exhaust your database.