Claude Code Harness

The Claude Code harness adapter connects HarnessAgent to Claude Code through @anthropic-ai/claude-agent-sdk. The adapter runs a bridge inside the sandbox and streams Claude Code events back to the host over a sandbox-exposed WebSocket.

Harness packages are experimental. Expect breaking changes between releases as this early API gets further refined.

Setup 

pnpm add @ai-sdk/harness @ai-sdk/harness-claude-code @ai-sdk/sandbox-vercel

The adapter bootstraps the Claude Code bridge dependencies inside the sandbox when the first session starts.

Import 

import { claudeCode, createClaudeCode } from '@ai-sdk/harness-claude-code';

claudeCode is equivalent to createClaudeCode() with its default configuration.

Basic Usage 

import { HarnessAgent } from '@ai-sdk/harness/agent';
import { claudeCode } from '@ai-sdk/harness-claude-code';
import { createVercelSandbox } from '@ai-sdk/sandbox-vercel';


const agent = new HarnessAgent({
  harness: claudeCode,
  sandbox: createVercelSandbox({
    runtime: 'node24',
    ports: [4000],
  }),
});


const session = await agent.createSession();


let exitCode = 0;
try {
  const result = await agent.stream({
    session,
    prompt: 'Check the test failures and fix the production code.',
  });


  for await (const part of result.stream) {
    if (part.type === 'text-delta') {
      process.stdout.write(part.text);
    }
  }
} catch (err) {
  exitCode = 1;
  console.error(err);
} finally {
  await session.destroy();
  process.exit(exitCode);
}

To use this agent, ensure environment variables include VERCEL_OIDC_TOKEN for Vercel Sandbox, and one of the variables listed under authentication for Claude Code.

Adapter Settings

Use createClaudeCode() to configure the runtime:

const harness = createClaudeCode({
  model: 'claude-sonnet-4-6',
  maxTurns: 10,
  thinking: {
    type: 'adaptive',
    display: 'summarized',
  },
});

Settings:

  • auth: direct Anthropic or AI Gateway authentication settings.
  • model: Anthropic model id passed to the underlying Claude Code runtime.
  • maxTurns: maximum internal turns before yielding.
  • thinking: extended-thinking configuration. type can be enabled, disabled, or adaptive. For enabled or adaptive thinking, display can be summarized or omitted. Defaults to { type: 'adaptive', display: 'summarized' }.
  • port: bridge port override.
  • startupTimeoutMs: maximum time to wait for the bridge to start.

Authentication

By default, authentication is resolved from the host environment and forwarded to the sandbox bridge. The adapter checks for AI Gateway and Anthropic credentials.

Supported environment variables:

  • VERCEL_OIDC_TOKEN
  • AI_GATEWAY_API_KEY
  • AI_GATEWAY_BASE_URL
  • ANTHROPIC_API_KEY
  • ANTHROPIC_AUTH_TOKEN
  • ANTHROPIC_BASE_URL

You can also pass explicit auth settings:

const harness = createClaudeCode({
  auth: {
    gateway: {
      apiKey: process.env.AI_GATEWAY_API_KEY,
    },
  },
});

Sandbox

Claude Code requires a network sandbox with at least one exposed port, e.g. @ai-sdk/sandbox-vercel:

const sandbox = createVercelSandbox({
  runtime: 'node24',
  ports: [4000],
});

Built-in Tools

The adapter exposes these common Claude Code built-ins through agent.tools:

  • read
  • write
  • edit
  • bash
  • glob
  • grep
  • webSearch

Additional Claude Code built-ins may also appear in agent.tools when they do not fit a common tool shape.

Claude Code supports built-in tool approval requests when permissionMode is allow-reads or allow-edits.