Durable workflows (Vercel Workflow)

Long-running assistants and chat backends often need durable execution: if a function restarts, the same logical run should resume, tool calls should retry safely, and each step should be observable. @github-tools/sdk supports this through the Vercel Workflow SDK and the @github-tools/sdk/workflow entry point.

What “durable” means here

• "use workflow" — Your orchestration function is a workflow: the platform can pause, resume, and replay it across failures and deploys.
• "use step" — Each GitHub tool implementation runs inside a named, module-level step. Every tool call is a durable step with retries and full Node.js access in the workflow runtime.
• createDurableGithubAgent — Wraps the same GitHub tools in a DurableAgent so LLM turns and tool invocations participate in that durable model (not just raw generateText in a plain serverless handler).

Together, this is the recommended pattern when you build Nuxt, Next.js, or other apps that expose a chat or agent API and must not lose progress on timeout or cold start.

Install optional workflow dependencies

Durable agents are optional. Add them only when you use @github-tools/sdk/workflow:

pnpm add workflow @workflow/ai

npm install workflow @workflow/ai

yarn add workflow @workflow/ai

bun add workflow @workflow/ai

You still need ai, zod, and @github-tools/sdk as documented in Installation.

Minimal durable workflow

createDurableGithubAgent returns a DurableGithubAgent with two methods:

• .stream() — real-time output to a WritableStream (for chat UIs)
• .generate() — non-streaming, returns the full text response (for bots, background jobs, webhooks)

Both methods execute each tool call as a durable workflow step with automatic retries.

Streaming (chat UI)

import { createDurableGithubAgent } from '@github-tools/sdk/workflow'
import { getWritable } from 'workflow'
import type { ModelMessage, UIMessageChunk } from 'ai'

export async function durableGithubChat(
  messages: ModelMessage[],
  token: string,
  model: string
) {
  'use workflow'

  const writable = getWritable<UIMessageChunk>()

  const agent = createDurableGithubAgent({
    model,
    token,
    preset: 'code-review',
  })

  await agent.stream({ messages, writable })
}

Non-streaming (bot / background job)

For non-streaming use cases (bots, webhooks, background jobs), use createGithubAgent inside a "use step" function. This gives you the full tool loop while keeping the step durable:

import { createGithubAgent } from '@github-tools/sdk'

async function runAgentTurn(prompt: string) {
  'use step'
  const agent = createGithubAgent({
    model: 'anthropic/claude-sonnet-4.6',
    preset: 'code-review',
    requireApproval: false,
  })
  const { text } = await agent.generate({ prompt })
  return text
}

export async function reviewWorkflow(prompt: string) {
  'use workflow'
  await runAgentTurn(prompt)
}

Wire these workflows from an API route or server handler provided by your framework’s Workflow integration (for example a Nuxt server route that starts the run and streams results to the client).

AI assistant prompt (durable workflow)

Integrate a durable GitHub assistant using @github-tools/sdk/workflow and the Vercel Workflow SDK in this repo.

- Add dependencies: workflow, @workflow/ai (and existing @github-tools/sdk, ai, zod)
- Define an async function with "use workflow" using createDurableGithubAgent, getWritable from "workflow", and agent.stream with ModelMessage[] and UIMessageChunk
- Document that requireApproval is ignored by DurableAgent: https://github-tools.com/guide/durable-workflows
- Match this framework’s workflow layout (e.g. server/workflows in Nuxt)

Presets and options

All presets (code-review, issue-triage, repo-explorer, ci-ops, maintainer) work with createDurableGithubAgent. Options mirror createGithubAgent for model, token, preset, instructions, and temperature, with additional pass-through for DurableAgentOptions fields like experimental_telemetry, onStepFinish, onFinish, and prepareStep.

Approval control and durable agents

Standard agents vs durable agents

Durable steps on every tool

Even if you do not use createDurableGithubAgent, spreading createGithubTools() inside a workflow still benefits from per-tool "use step" boundaries when the AI SDK executes tools — each GitHub operation remains a proper workflow step. The durable agent entry point additionally durably wraps the LLM loop itself.

External references

• Vercel Workflow documentation
• AI SDK tools