Vercel's AI SDK 7 Turns Fragile Prototype Agents Into Production-Ready Systems
Vercel's AI SDK 7 lands with durable agents, unified reasoning control, tool approvals, MCP Apps, and a new harness abstraction for Claude Code and Codex
- AI SDK 7 is now in beta — the biggest release yet, focused on production-grade agent infrastructure.
- WorkflowAgent brings durable, resumable agents that survive crashes, restarts, and delayed human approvals without custom queue infrastructure.
- Tool approvals let you gate sensitive operations automatically or with a human in the loop, based on tool input values.
- Unified reasoning control adds a single
reasoningparameter across OpenAI, Anthropic, Google, xAI, Groq, DeepSeek, and more. - HarnessAgent provides a single API to run Claude Code, Codex, and Pi — swap harnesses the same way you swap models.
- MCP Apps extend MCP tools with sandboxed interactive UI, and migration codemods handle the v6-to-v7 upgrade automatically. Read the announcement.
AI SDK 7 is now available in beta, and it's the most agent-focused release the toolkit has shipped. Where earlier versions laid the groundwork for multi-step tool calling and streaming, version 7 tackles the hard problems that show up when you try to run agents in production: state that survives crashes, tools that need human sign-off, secrets that should never reach the model, and harnesses like Claude Code or Codex that you want to swap without rewriting your agent logic.
The durability problem, finally solved
The biggest addition is WorkflowAgent, a native integration between the AI SDK and Vercel's Workflow SDK. The core issue it addresses is simple but painful:
a standard ToolLoopAgent runs entirely in memory, so if the process crashes, all progress is lost. For production agents that make multiple tool calls, this creates problems around statefulness, resumability, human-in-the-loop approvals, and observability.
WorkflowAgent solves these by running inside a Vercel Workflow, where each tool execution is a durable step with automatic retries.
The practical upshot:
durable streams persist agent output, and getWritable() gives you a persistent stream that multiple clients can connect to, disconnect from, and reconnect to later. The workflow keeps running even if the user closes the browser, and when they come back, the client resumes exactly where the stream left off , no Redis or custom pub/sub required.
Because the workflow is durable, approval requests survive process restarts , the user can approve hours later and the agent will resume. This is the kind of guarantee that previously required wiring up your own queue infrastructure.
Tool approvals and context isolation
Agent safety gets a serious upgrade in v7.
By default, tools with an execute function run automatically as the model calls them. You can now require approval before execution by setting