trigger-authoring-chat-agent

Authoring a chat.agent

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-authoring-chat-agent/SKILL.md — the per-turn run loop, chat.toStreamTextOptions(), the two server actions, typed tools/data parts, and the React transport.
• Docs: the full, version-pinned docs ship bundled at node_modules/@trigger.dev/sdk/docs/ai-chat/; the skill above lists the exact pages it draws from in its sources: frontmatter. Grep for an API, e.g. grep -rl "toStreamTextOptions" 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: forgetting ...chat.toStreamTextOptions().

  // Wrong - compaction / steering / background injection silently no-op
  return streamText({ model, messages, abortSignal: signal });
  // Correct - spread FIRST so explicit overrides win
  return streamText({ ...chat.toStreamTextOptions(), model, messages, abortSignal: signal });
  

  It wires the prepareStep callback behind compaction, mid-turn steering, and background injection, injects the system prompt from chat.prompt(), resolves the registry model, and adds telemetry. Omitting it makes all of those silently no-op with no error.

• Declaring tools only on streamText. Also declare them on chat.agent({ tools }), read them back from run, and pass chat.toStreamTextOptions({ tools }). Otherwise each tool's toModelOutput runs on turn 1 but is dropped when history is re-converted on later turns.

• Not forwarding signal for stop. Without abortSignal: signal, Stop updates the UI but the model keeps generating server-side.