workflow

por vercel

Crea flujos de trabajo duraderos y reanudables usando el Workflow DevKit de Vercel. Úsalo al construir flujos de trabajo que necesiten sobrevivir a reinicios, pausarse para eventos externos,…

npx skills add https://github.com/vercel-labs/open-agents --skill workflow

CRITICAL: Always Use Correct workflow Documentation

Your knowledge of workflow is outdated.

The workflow documentation outlined below matches the installed version of the Workflow DevKit. Follow these instructions before starting on any workflow-related tasks:

Search the bundled documentation in node_modules/workflow/docs/:

  1. Find docs: glob "node_modules/workflow/docs/**/*.mdx"
  2. Search content: grep "your query" node_modules/workflow/docs/

Documentation structure in node_modules/workflow/docs/:

  • getting-started/ - Framework setup (next.mdx, express.mdx, hono.mdx, etc.)
  • foundations/ - Core concepts (workflows-and-steps.mdx, hooks.mdx, streaming.mdx, etc.)
  • api-reference/workflow/ - API docs (sleep.mdx, create-hook.mdx, fatal-error.mdx, etc.)
  • api-reference/workflow-api/ - Client API (start.mdx, get-run.mdx, resume-hook.mdx, etc.)
  • ai/ - AI SDK integration docs
  • errors/ - Error code documentation

Related packages also include bundled docs:

  • @workflow/ai: node_modules/@workflow/ai/docs/ - DurableAgent and AI integration
  • @workflow/core: node_modules/@workflow/core/docs/ - Core runtime (foundations, how-it-works)
  • @workflow/next: node_modules/@workflow/next/docs/ - Next.js integration

When in doubt, update to the latest version of the Workflow DevKit.

Official Resources

Quick Reference

Directives:

"use workflow";  // First line - makes async function durable
"use step";      // First line - makes function a cached, retryable unit

Essential imports:

// Workflow primitives
import { sleep, fetch, createHook, createWebhook, getWritable } from "workflow";
import { FatalError, RetryableError } from "workflow";
import { getWorkflowMetadata, getStepMetadata } from "workflow";

// API operations
import { start, getRun, resumeHook, resumeWebhook } from "workflow/api";

// Framework integrations
import { withWorkflow } from "workflow/next";
import { workflow } from "workflow/vite";
import { workflow } from "workflow/astro";
// Or use modules: ["workflow/nitro"] for Nitro/Nuxt

Prefer Step Functions to Avoid Sandbox Errors

"use workflow" functions run in a sandboxed VM. "use step" functions have full Node.js access. Put your logic in steps and use the workflow function purely for orchestration.

// Steps have full Node.js and npm access
async function fetchUserData(userId: string) {
  "use step";
  const response = await fetch(`https://api.example.com/users/${userId}`);
  return response.json();
}

async function processWithAI(data: any) {
  "use step";
  // AI SDK works in steps without workarounds
  return await generateText({
    model: openai("gpt-4"),
    prompt: `Process: ${JSON.stringify(data)}`,
  });
}

// Workflow orchestrates steps - no sandbox issues
export async function dataProcessingWorkflow(userId: string) {
  "use workflow";
  const data = await fetchUserData(userId);
  const processed = await processWithAI(data);
  return { success: true, processed };
}

Benefits: Steps have automatic retry, results are persisted for replay, and no sandbox restrictions.

Workflow Sandbox Limitations

When you need logic directly in a workflow function (not in a step), these restrictions apply:

LimitationWorkaround
No fetch()import { fetch } from "workflow" then globalThis.fetch = fetch
No setTimeout/setIntervalUse sleep("5s") from "workflow"
No Node.js modules (fs, crypto, etc.)Move to a step function

Example - Using fetch in workflow context:

import { fetch } from "workflow";

export async function myWorkflow() {
  "use workflow";
  globalThis.fetch = fetch;  // Required for AI SDK and HTTP libraries
  // Now generateText() and other libraries work
}

Note: DurableAgent from @workflow/ai handles the fetch assignment automatically.

Error Handling

Use FatalError for permanent failures (no retry), RetryableError for transient failures:

import { FatalError, RetryableError } from "workflow";

if (res.status >= 400 && res.status < 500) {
  throw new FatalError(`Client error: ${res.status}`);
}
if (res.status === 429) {
  throw new RetryableError("Rate limited", { retryAfter: "5m" });
}

Serialization

All data passed to/from workflows and steps must be serializable.

Supported types: string, number, boolean, null, undefined, bigint, plain objects, arrays, Date, RegExp, URL, URLSearchParams, Map, Set, Headers, ArrayBuffer, typed arrays, Request, Response, ReadableStream, WritableStream.

Not supported: Functions, class instances, Symbols, WeakMap/WeakSet. Pass data, not callbacks.

Streaming

Use getWritable() in step functions to stream data:

async function streamData() {
  "use step";  // Required - streaming only works in steps
  const writer = getWritable();
  await writer.write(data);
  writer.releaseLock();  // Always release the lock
}

// Close when done
await getWritable().close();

Debugging

# Check workflow endpoints are reachable
npx workflow health
npx workflow health --port 3001  # Non-default port

# Visual dashboard for runs
npx workflow web
npx workflow web --app-url http://localhost:3001

# CLI inspection (for agents)
npx workflow inspect runs
npx workflow inspect run <run_id>

Tip: Only import workflow APIs you actually use. Unused imports can cause 500 errors.

Más skills de vercel

vercel
vercel
API REST de Vercel emulada para desarrollo y pruebas locales. Úsala cuando el usuario necesite interactuar con endpoints de la API de Vercel localmente, probar integraciones de Vercel,…
cron-jobs
vercel
Configuración y mejores prácticas de Vercel Cron Jobs. Úsalo al agregar, editar o depurar tareas programadas en vercel.json.
codegen
vercel
Utilidades de generación de código para json-render. Úselo al generar código a partir de especificaciones de UI, crear exportadores de código personalizados, recorrer especificaciones o serializar propiedades para…
next-best-practice
vercel
Prácticas recomendadas de Next.js: convenciones de archivos, límites de RSC, patrones de datos, APIs asíncronas, metadatos, manejo de errores, manejadores de rutas, optimización de imágenes/fuentes,…
benchmark-sandbox
vercel
Ejecuta escenarios de evaluación de vercel-plugin en Vercel Sandboxes en lugar de paneles locales de WezTerm. Aprovisiona microVMs efímeras con Claude Code y el plugin preinstalado,…
write-guide
vercel
Producir una guía técnica que enseñe un caso de uso del mundo real mediante ejemplos progresivos. Los conceptos se introducen solo cuando el lector los necesita.
benchmark-testing
vercel
Crear y lanzar proyectos de prueba de benchmark para ejercitar la inyección de habilidades de vercel-plugin en escenarios realistas. Configura directorios aislados, instala el…
ai-gateway
vercel
Guía experta de Vercel AI Gateway. Úselo al configurar el enrutamiento de modelos, la conmutación por error de proveedores, el seguimiento de costos o la gestión de múltiples proveedores de IA a través de un...