OpenCode Harness

The OpenCode harness adapter connects HarnessAgent to OpenCode through @opencode-ai/sdk. The adapter runs a bridge inside the sandbox, starts an OpenCode server in that sandbox, and streams OpenCode session 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-opencode @ai-sdk/sandbox-vercel

The adapter bootstraps the OpenCode bridge dependencies inside the sandbox when the first session starts. The bridge package depends on @opencode-ai/sdk and opencode-ai.

Import 

import { openCode, createOpenCode } from '@ai-sdk/harness-opencode';

openCode is equivalent to createOpenCode() with its default configuration.

Basic Usage 

import { HarnessAgent } from '@ai-sdk/harness/agent';
import { openCode } from '@ai-sdk/harness-opencode';
import { createVercelSandbox } from '@ai-sdk/sandbox-vercel';


const agent = new HarnessAgent({
  harness: openCode,
  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 OpenCode.

Adapter Settings

Use createOpenCode() to configure the runtime:

const harness = createOpenCode({
  model: 'anthropic/claude-sonnet-4-6',
  reasoningVariant: 'high',
});

Settings:

  • auth: Anthropic, OpenAI, OpenAI-compatible, or AI Gateway authentication settings.
  • model: OpenCode model id. Provider-prefixed values such as anthropic/claude-sonnet-4-6 are passed through to OpenCode.
  • provider: provider id to use with an unprefixed model.
  • reasoningVariant: OpenCode reasoning/thinking variant for supported models, such as low, medium, or high.
  • 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, Anthropic, and OpenAI credentials.

Supported environment variables:

  • AI_GATEWAY_API_KEY
  • AI_GATEWAY_BASE_URL
  • VERCEL_OIDC_TOKEN
  • ANTHROPIC_API_KEY
  • ANTHROPIC_AUTH_TOKEN
  • ANTHROPIC_BASE_URL
  • OPENAI_API_KEY
  • OPENAI_BASE_URL
  • OPENAI_ORGANIZATION
  • OPENAI_PROJECT

You can also pass explicit auth settings:

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

For OpenAI-compatible endpoints, use auth.openaiCompatible and set name to the OpenCode provider id.

Sandbox

OpenCode 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 OpenCode built-ins through agent.tools:

  • read
  • write
  • edit
  • bash
  • glob
  • grep
  • ls
  • webfetch
  • skill
  • todowrite
  • agent

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

OpenCode supports built-in tool approval requests when permissionMode is allow-reads or allow-edits. Host-executed AI SDK tool approvals also work.