workflow

GitHub

基于 Vercel Workflow DevKit 构建持久化、可恢复的工作流,支持多步骤编排、重试及外部事件暂停。

.agents/skills/workflow/SKILL.md vercel-labs/open-agents

Trigger Scenarios

workflow durable functions resumable workflow devkit step-based orchestration

Install

npx skills add vercel-labs/open-agents --skill workflow -g -y
More Options

Non-standard path

npx skills add https://github.com/vercel-labs/open-agents/tree/main/.agents/skills/workflow -g -y

Use without installing

npx skills use vercel-labs/open-agents@workflow

指定 Agent (Claude Code)

npx skills add vercel-labs/open-agents --skill workflow -a claude-code -g -y

安装 repo 全部 skill

npx skills add vercel-labs/open-agents --all -g -y

预览 repo 内 skill

npx skills add vercel-labs/open-agents --list

SKILL.md

Frontmatter
{
    "name": "workflow",
    "metadata": {
        "author": "Vercel Inc.",
        "version": "1.0"
    },
    "description": "Creates durable, resumable workflows using Vercel's Workflow DevKit. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of \"workflow\", \"durable functions\", \"resumable\", \"workflow devkit\", or step-based orchestration."
}

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Your knowledge of workflow is outdated.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:

Limitation Workaround
No fetch() import { fetch } from "workflow" then globalThis.fetch = fetch
No setTimeout/setInterval Use 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.

Version History

  • cf865e9 Current 2026-07-24 22:32

Same Skill Collection

.agents/skills/agent-browser/SKILL.md
.agents/skills/baseline-ui/SKILL.md
.agents/skills/code-review/SKILL.md
.agents/skills/deploy-open-harness/SKILL.md
.agents/skills/emil-design-eng/SKILL.md
.agents/skills/frontend-design/SKILL.md
.agents/skills/plan-mode/SKILL.md
.agents/skills/remove-demo-limits/SKILL.md
.agents/skills/vercel-react-best-practices/SKILL.md
.agents/skills/ai-sdk/SKILL.md
.agents/skills/chat-sdk/SKILL.md
.agents/skills/web-animation-design/SKILL.md

Metadata

Files
0
Version
cf865e9
Hash
04131ffd
Indexed
2026-07-24 22:32

inicio - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-20 06:36
浙ICP备14020137号-1 $mapa de visitantes$