Trigger Chat Agent Advanced Agent Skill

chat.agent — advanced & operational

The full, version-pinned reference ships inside your installed @trigger.dev/sdk. Read it before writing code — it always matches the SDK version in this project, so it never drifts:

• Skill: node_modules/@trigger.dev/sdk/skills/trigger-chat-agent-advanced/SKILL.md — Sessions primitive, custom transports/wire protocol, sub-agents, HITL, steering, actions, background injection, fast starts, resilience (compaction/recovery/OOM/large payloads), chat.local, testing, upgrades.
• Docs: the full, version-pinned docs ship bundled at node_modules/@trigger.dev/sdk/docs/ai-chat/ (including patterns/ for HITL, sub-agents, sessions); the skill above lists the exact pages it draws from in its sources: frontmatter. Grep for an API, e.g. grep -rl "mockChatAgent" node_modules/@trigger.dev/sdk/docs/.

If those paths don't exist, @trigger.dev/sdk isn't installed yet — install it first. In a non-hoisted layout, resolve the package with node -p "require.resolve('@trigger.dev/sdk/package.json')" and read skills/ + docs/ beside it.

Common mistakes

• CRITICAL: sending a follow-up by re-POSTing POST /api/v1/sessions.

  // Wrong - a cached re-POST silently drops basePayload.message; basePayload is trigger config, not a channel
  await fetch("/api/v1/sessions", { method: "POST", body: JSON.stringify({ ...createBody }) });
  // Correct - append to the session's input channel
  await fetch(`/realtime/v1/sessions/${id}/in/append`, { method: "POST", body: JSON.stringify({ kind: "message", payload }) });

• Using the wrong token for .in / .out. Use publicAccessToken from the create response

body (session-scoped). The x-trigger-jwt response header is run-scoped and cannot subscribe.

• Initializing chat.local in onChatStart. It is skipped on continuation runs, so run()

crashes with chat.local can only be modified after initialization. Init in onBoot.

• chat.defer for the message-history write. A mid-stream refresh would read []. await that

write inline before the model streams; reserve chat.defer for analytics, audit, cache warming.

• Giving the HITL tool an execute. streamText calls it immediately. Leave it execute-less;

the frontend supplies the answer via addToolOutput + sendAutomaticallyWhen.

• Declaring sub-agent / heavy tools only on streamText. Also declare them on

chat.agent({ tools }) (or pass to convertToModelMessages(uiMessages, { tools }) in a custom

agent) so toModelOutput re-applies on every turn.

• Importing heavy-execute tools into the Head Start route module. This is a build-time import

chain problem; runtime strip helpers do not fix it. Keep schemas in an ai + zod-only module.

• Returning a megabyte tool output on the stream. One tool-output-available record over ~1 MiB

throws ChatChunkTooLargeError. Persist to your store, write the row first, then emit only an id.

• Setting X-Peek-Settled: 1 on the active-send path. It races the new turn's first chunk and

closes the stream early. Use it only on reconnect-on-reload paths.

> Note on docs vocabulary: agent-side examples in some docs still use the legacy

> trigger:turn-complete chunk type. That is the agent-emit vocabulary. A custom reader must

> filter on the trigger-control header, not on chunk.type.

>

> MCP-driven agent chats (list_agents, start_agent_chat, send_agent_message,

> close_agent_chat) are MCP server tools used from Claude Code / Cursor, not importable SDK

> functions. See /mcp-tools#agent-chat-tools.

References

Sibling skills: trigger-authoring-chat-agent (the everyday chat.agent({...}) happy path), trigger-authoring-tasks and trigger-realtime-and-frontend (task + frontend foundations).