Trigger.dev llms.txt

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Showing the first 18000 characters. Load the complete file to read the remainder.

# Trigger.dev

> Trigger.dev is an open source background jobs framework that lets you write reliable workflows in plain async code. Run long-running AI tasks, handle complex background jobs, and build AI agents with built-in queuing, automatic retries, and real-time monitoring. No timeouts, elastic scaling, and zero infrastructure management required.

- [Trigger.dev docs](https://trigger.dev/docs/introduction.md): Build and run durable AI agents and workflows in TypeScript. Long-running tasks with retries, queues, observability, and elastic scaling. Open source and self-hostable.
- [Quick start: add Trigger.dev to your project](https://trigger.dev/docs/quick-start.md): Set up Trigger.dev in your existing project in under 3 minutes. Install the SDK, create your first background task, and trigger it from your code.
- [Manual setup](https://trigger.dev/docs/manual-setup.md): How to manually setup Trigger.dev in your project.
- [Video walkthrough](https://trigger.dev/docs/video-walkthrough.md): Go from zero to a working task in your Next.js app in 10 minutes.
- [How Trigger.dev works](https://trigger.dev/docs/how-it-works.md): Understand how Trigger.dev works and how it can help you.
- [Limits](https://trigger.dev/docs/limits.md): There are some hard and soft limits that you might hit.
- [Migrating from v3](https://trigger.dev/docs/migrating-from-v3.md): What's new in v4, how to migrate, and breaking changes.
- [Tasks: Overview](https://trigger.dev/docs/tasks/overview.md): Tasks are functions that can run for a long time and provide strong resilience to failure.
- [schemaTask](https://trigger.dev/docs/tasks/schemaTask.md): Define tasks with a runtime payload schema and validate the payload before running the task.
- [Scheduled tasks (cron)](https://trigger.dev/docs/tasks/scheduled.md): A task that is triggered on a recurring schedule using cron syntax.
- [Triggering](https://trigger.dev/docs/triggering.md): Tasks need to be triggered in order to run.
- [Runs](https://trigger.dev/docs/runs.md): Understanding the lifecycle of task run execution in Trigger.dev
- [Using runs.list() efficiently](https://trigger.dev/docs/runs/list-best-practices.md): When to use runs.list(), the patterns to avoid, and what to use instead.
- [API keys](https://trigger.dev/docs/apikeys.md): Authenticate backend requests with environment-specific API keys.
- [Building with AI: overview](https://trigger.dev/docs/building-with-ai.md): Tools and resources for building Trigger.dev projects with AI coding assistants.
- [MCP Introduction](https://trigger.dev/docs/mcp-introduction.md): Learn how to install and configure the Trigger.dev MCP Server
- [MCP Tools](https://trigger.dev/docs/mcp-tools.md): Learn about how to use the tools available in the Trigger.dev MCP Server
- [Skills](https://trigger.dev/docs/skills.md): Install Trigger.dev agent skills to teach any AI coding assistant how to write tasks, realtime frontends, and chat.agent AI agents.
- [Agent rules](https://trigger.dev/docs/mcp-agent-rules.md): Trigger.dev agent rules are now agent skills, installed with the trigger.dev CLI.
- [Writing tasks: Overview](https://trigger.dev/docs/writing-tasks-introduction.md): Tasks are the core of Trigger.dev. They are long-running processes that are triggered by events.
- [Logging, tracing & metrics](https://trigger.dev/docs/logging.md): How to use the built-in logging, tracing, and metrics system.
- [Errors & Retrying](https://trigger.dev/docs/errors-retrying.md): How to deal with errors and write reliable tasks.
- [Wait: Overview](https://trigger.dev/docs/wait.md): During your run you can wait for a period of time or for something to happen.
- [Wait for](https://trigger.dev/docs/wait-for.md): Wait for a period of time, then continue execution.
- [Wait until](https://trigger.dev/docs/wait-until.md): Wait until a date, then continue execution.
- [Wait for token](https://trigger.dev/docs/wait-for-token.md): Wait until a token is completed using waitpoint tokens.
- [Queues](https://trigger.dev/docs/queues.md): Control the order your runs execute in.
- [Concurrency](https://trigger.dev/docs/concurrency.md): Limit how many runs execute at once: per task, per tenant, or shared across tasks.
- [Versioning](https://trigger.dev/docs/versioning.md): We use atomic versioning to ensure that started tasks are not affected by changes to the task code.
- [Machines](https://trigger.dev/docs/machines.md): Configure the number of vCPUs and GBs of RAM you want the task to use.
- [Idempotency](https://trigger.dev/docs/idempotency.md): An API call or operation is idempotent if it has the same result when called more than once.
- [Max duration](https://trigger.dev/docs/runs/max-duration.md): Set a maximum duration for a task to run.
- [Heartbeats](https://trigger.dev/docs/runs/heartbeats.md): Keep long-running or CPU-heavy tasks from being marked as stalled.
- [Tags](https://trigger.dev/docs/tags.md): Tags allow you to easily filter runs in the dashboard and when using the SDK.
- [Run metadata](https://trigger.dev/docs/runs/metadata.md): Attach structured data to a run and update it as the task progresses. Use metadata for progress tracking, user context, intermediate results, and more.
- [Streaming data from tasks](https://trigger.dev/docs/tasks/streams.md): Pipe continuous data from your Trigger.dev tasks to frontend or backend clients in real time. Stream AI completions, file chunks, progress updates, and more.
- [Usage](https://trigger.dev/docs/run-usage.md): Get compute duration and cost from inside a run, or for a specific block of code.
- [Context](https://trigger.dev/docs/context.md): Get the context of a task run.
- [Priority](https://trigger.dev/docs/runs/priority.md): Specify a priority when triggering a run.
- [Hidden tasks](https://trigger.dev/docs/hidden-tasks.md): Create tasks that are not exported from your trigger files but can still be executed.
- [Bulk actions with the SDK](https://trigger.dev/docs/runs/bulk-actions.md): Cancel or replay many runs from the SDK using run IDs or SDK run-list filters.
- [AI Agents](https://trigger.dev/docs/ai-chat/overview.md): Durable multi-turn AI chats — one Trigger.dev task per conversation, surviving refreshes, deploys, and crashes.
- [Quick Start](https://trigger.dev/docs/ai-chat/quick-start.md): Define an agent, authorize chat sessions on your server, and stream responses into a React frontend.
- [Migrate from an AI SDK route handler](https://trigger.dev/docs/ai-chat/migrating-from-a-route-handler.md): Move an existing useChat + streamText chat app to chat.agent — what stays identical, what you delete, and a prompt you can hand to a coding agent.
- [Anatomy of an agent](https://trigger.dev/docs/ai-chat/anatomy.md): The three parts of a chat agent — the agent task that runs the turn loop, the durable session that carries messages, and the frontend transport — what each does and where it's documented.
- [Backend](https://trigger.dev/docs/ai-chat/backend.md): Three approaches to building your chat backend — chat.agent(), session iterator, or raw task primitives.
- [Lifecycle hooks](https://trigger.dev/docs/ai-chat/lifecycle-hooks.md): Hook into every stage of a chat agent's run: preload, turn start, turn complete, suspend, resume, and more.
- [Tools](https://trigger.dev/docs/ai-chat/tools.md): Declare tools on chat.agent so toModelOutput survives across turns, get them back typed in run(), and type your messages from them.
- [Frontend](https://trigger.dev/docs/ai-chat/frontend.md): Transport setup, session management, client data, and frontend patterns for AI Chat.
- [Server-Side Chat](https://trigger.dev/docs/ai-chat/server-chat.md): Use AgentChat to interact with chat agents from server-side code — tasks, webhooks, scripts, or other agents.
- [Sessions](https://trigger.dev/docs/ai-chat/sessions.md): A Session is a stateful execution of an agent, with two-way streaming and durable compute. A single Session can have multiple runs associated with it.
- [Side channels](https://trigger.dev/docs/ai-chat/side-channels.md): Named, durable stream pairs on a Session, separate from the chat transcript. A side channel outlives a single run, is shared across runs, and its input does not wake a run.
- [chat.local](https://trigger.dev/docs/ai-chat/chat-local.md): Typed, run-scoped data accessible from hooks, run(), tools, and subtasks. Survives across turns, auto-cleared between runs, auto-hydrated into subtasks.
- [Types](https://trigger.dev/docs/ai-chat/types.md): TypeScript types for AI Agents, UI messages, and the frontend transport.
- [Custom agents](https://trigger.dev/docs/ai-chat/custom-agents.md): Build chat agents without chat.agent()'s managed lifecycle: register with chat.customAgent(), then drive turns with the createSession iterator or a hand-rolled loop.
- [How the AI Agents SDK works](https://trigger.dev/docs/ai-chat/how-it-works.md): End-to-end mechanics of a chat.agent turn: the two durable channels per session, the long-lived task that reads and writes them, and how a chat survives refreshes, deploys, and idle gaps.
- [Prompts](https://trigger.dev/docs/ai/prompts.md): Define prompt templates as code, version them on deploy, and override from the dashboard without redeploying.
- [LLM observability](https://trigger.dev/docs/ai/observability.md): Capture Vercel AI SDK calls in a task as spans in the run trace, with model, token usage, cost, and latency. Opt in per call, link calls to prompt versions, and query usage across runs.
- [Fast starts](https://trigger.dev/docs/ai-chat/fast-starts.md): Two ways to cut first-turn TTFC: Preload eagerly triggers the run before the first message; Head Start runs step 1 in your warm server while the agent boots in parallel.
- [Compaction](https://trigger.dev/docs/ai-chat/compaction.md): Automatic context compaction to keep long conversations within token limits.
- [Prompt caching](https://trigger.dev/docs/ai-chat/prompt-caching.md): Cache the stable prefix of your agent's prompt with Anthropic prompt caching to cut token cost and latency on every turn.
- [Pending Messages](https://trigger.dev/docs/ai-chat/pending-messages.md): Inject user messages mid-execution to steer agents between tool-call steps.
- [Background injection](https://trigger.dev/docs/ai-chat/background-injection.md): Inject context from background work into the agent's conversation: self-review, RAG augmentation, or any async analysis.
- [Actions](https://trigger.dev/docs/ai-chat/actions.md): Custom commands sent from the frontend that mutate chat state without consuming a turn: undo, rollback, edit, regenerate.
- [Transcript storage](https://trigger.dev/docs/ai-chat/transcript-storage.md): Where a chat.agent conversation is kept: the UIMessages the runtime saves, the platform default, reading history back, and bringing your own database through the TranscriptStorage adapter.
- [Migrate from hydrateMessages to transcript storage](https://trigger.dev/docs/ai-chat/migrating-from-hydrate-messages.md): Move a chat.agent that persists its own history through hydrateMessages onto a TranscriptStorage: map your tables, implement load and save, decide whether you need loadContext, and delete the recovery and compaction code you no longer own.
- [Error handling](https://trigger.dev/docs/ai-chat/error-handling.md): How errors flow through chat.agent — stream errors, hook errors, run failures — and how to recover.
- [Sub-Agents](https://trigger.dev/docs/ai-chat/patterns/sub-agents.md): Delegate work to durable sub-agents from within a parent agent's tool calls, with streaming preliminary results.
- [Version upgrades](https://trigger.dev/docs/ai-chat/patterns/version-upgrades.md): Gracefully migrate chat agents to a new deployment using chat.requestUpgrade(), chat.endAndContinue(), and the continuation mechanism.
- [Database persistence for chat](https://trigger.dev/docs/ai-chat/patterns/database-persistence.md): Split conversation state and live session metadata across hooks — preload, turn start, turn complete — without tying the pattern to a specific ORM or schema.
- [Persistence and replay](https://trigger.dev/docs/ai-chat/patterns/persistence-and-replay.md): How chat.agent rebuilds conversation history at run boot — the transcript storage's persisted conversation plus session.out replay, and what changes when your app owns the model's context.
- [Branching conversations](https://trigger.dev/docs/ai-chat/patterns/branching-conversations.md): Persist an active conversation branch and use transcript storage and actions to switch the agent's context.
- [Code execution sandbox](https://trigger.dev/docs/ai-chat/patterns/code-sandbox.md): Warm an isolated sandbox on each chat turn, run an AI SDK executeCode tool, and tear down right before the run suspends — using chat.agent hooks and chat.local.
- [Human-in-the-loop](https://trigger.dev/docs/ai-chat/patterns/human-in-the-loop.md): Ask users to choose an option or approve a tool call, then continue the agent with their response.
- [Tool result auditing](https://trigger.dev/docs/ai-chat/patterns/tool-result-auditing.md): Find new tool results before they merge into chat history, and deduplicate audit writes with a durable idempotency key.
- [Large payloads in chat.agent](https://trigger.dev/docs/ai-chat/patterns/large-payloads.md): Why a single chunk on the chat stream is capped at ~1 MiB, what error you'll see, and how to work around it with ID references.
- [Agent Skills](https://trigger.dev/docs/ai-chat/patterns/skills.md): Ship reusable capabilities (folders with SKILL.md + scripts) that a chat agent discovers and invokes on demand.
- [OOM resilience](https://trigger.dev/docs/ai-chat/patterns/oom-resilience.md): Recover from out-of-memory errors mid-turn by automatically retrying the failed turn on a larger machine — without losing the in-flight user message or re-processing completed turns.
- [Recovery boot](https://trigger.dev/docs/ai-chat/patterns/recovery-boot.md): Recover from cancel-mid-stream, crashes, and OOM kills with full conversational context. The smart default Just Works; the onRecoveryBoot hook is the override path for advanced policies.
- [Trusted edge signals](https://trigger.dev/docs/ai-chat/patterns/trusted-edge-signals.md): How to safely deliver server-trusted signals (bot scores, JA4, ASN, ReCAPTCHA verdicts) to a chat.agent run via an edge proxy.
- [Redact chat content from traces](https://trigger.dev/docs/ai-chat/patterns/redacting-telemetry.md): Stop a chat agent recording user messages and clientData on its spans, turn off AI SDK prompt and response recording, or redact span content with a span processor before it leaves the worker.
- [Native compaction & provider fallback](https://trigger.dev/docs/ai-chat/patterns/native-compaction.md): Persist provider-native compaction (Anthropic context editing, OpenAI stored responses) across chat.agent turns so history is never re-sent, and fall back between providers without losing the conversation.
- [API Reference](https://trigger.dev/docs/ai-chat/reference.md): Complete API reference for the AI Agents SDK — backend options, events, frontend transport, and hooks.
- [Client Protocol](https://trigger.dev/docs/ai-chat/client-protocol.md): The wire protocol for building custom chat transports — how clients communicate with chat agents over Sessions and SSE.
- [Testing](https://trigger.dev/docs/ai-chat/testing.md): Drive a chat.agent through real turns in unit tests — no network, no task runtime, no mocking the SDK.
- [MCP Server](https://trigger.dev/docs/ai-chat/mcp.md): Chat with your agents from any AI coding tool using the Trigger.dev MCP server.
- [Upgrade Guide: prerelease → Sessions-as-run-manager](https://trigger.dev/docs/ai-chat/upgrade-guide.md): Migrating chat.agent code from the prerelease API to the Sessions-as-run-manager release.
- [AI Agents SDK changelog](https://trigger.dev/docs/ai-chat/changelog.md): Changelog for the AI Agents SDK.
- [Webhooks overview](https://trigger.dev/docs/webhooks/overview.md): Receive provider webhooks on hosted, verified endpoints and route each event to tasks, agents, and waiting runs.
- [Sources and verification](https://trigger.dev/docs/webhooks/sources.md): Choose an endpoint's source, configure verification, and type the event its subscribers receive.
- [Connect a webhook provider](https://trigger.dev/docs/webhooks/connect.md): Register an endpoint's URL and signing secret with the provider, by hand or with an AI coding agent, then check that events arrive.
- [Deliveries and endpoints](https://trigger.dev/docs/webhooks/deliveries.md): Inspect webhook payloads, where each delivery went, and the runs it started or resumed.
- [Filtering deliveries](https://trigger.dev/docs/webhooks/filters.md): Choose which verified webhook events reach each subscriber, by payload fields, request headers, or endpoint metadata.
- [Waiting for a webhook](https://trigger.dev/docs/webhooks/waiters.md): Pause a run until a matching webhook arrives on an endpoint, then resume it with the verified event.
- [Routing to a session](https://trigger.dev/docs/webhooks/session-routing.md): Route verified webhook deliveries to a durable per-key session instead of a fresh run.
- [Channels (chat frontends)](https://trigger.dev/docs/webhooks/channels.md): Point Slack (or any chat surface) at an agent: messages become turns and replies post back.
- [Slack agents](https://trigger.dev/docs/webhooks/slack.md): Turn a chat.agent into a Slack agent: users message it in Slack, it shows its status while it works, streams its reply with its tool calls as a plan, asks for approvals, and stops on Slack's stop button.
- [Linear agents](https://trigger.dev/docs/webhooks/linear.md): Turn a chat.agent into a Linear agent: assign it an issue or @mention it, and it works the issue inside Linear's agent session UI.
- [Human-in-the-loop](https://trigger.dev/docs/webhooks/human-in-the-loop.md): Pause an agent mid-turn to get a human decision from the channel