# HarnessAgent

`HarnessAgent` is an AI SDK `Agent` implementation backed by a harness adapter.
It gives you `generate()` and `stream()` methods that return AI SDK-compatible
results while a preconfigured harness powers these results.

## Installation

Install the core harness package, a harness adapter, and a sandbox provider:

<div className="my-4">
  <Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
    <Tab>
      <Snippet
        text="pnpm add @ai-sdk/harness @ai-sdk/harness-claude-code @ai-sdk/sandbox-vercel"
        dark
      />
    </Tab>
    <Tab>
      <Snippet
        text="npm install @ai-sdk/harness @ai-sdk/harness-claude-code @ai-sdk/sandbox-vercel"
        dark
      />
    </Tab>
    <Tab>
      <Snippet
        text="yarn add @ai-sdk/harness @ai-sdk/harness-claude-code @ai-sdk/sandbox-vercel"
        dark
      />
    </Tab>
    <Tab>
      <Snippet
        text="bun add @ai-sdk/harness @ai-sdk/harness-claude-code @ai-sdk/sandbox-vercel"
        dark
      />
    </Tab>
  </Tabs>
</div>

Bridge-backed harnesses such as Claude Code and Codex require using real network sandbox
like `@ai-sdk/sandbox-vercel`. Host-runtime harnesses such as Pi can also run with
`@ai-sdk/sandbox-just-bash` because they do not need a sandbox-exposed port.

## Create an Agent

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

export const agent = new HarnessAgent({
  harness: claudeCode,
  sandbox: createVercelSandbox({
    runtime: 'node24',
    ports: [4000],
  }),
  instructions:
    'You are a careful coding assistant. Prefer small changes and explain tradeoffs.',
});
```

Construct the agent at module scope. It holds configuration, not a live session.
Live state belongs to `HarnessAgentSession`.

To use this agent, ensure environment variables with sandbox and harness credentials
are set.

## Run a Turn

```ts
const session = await agent.createSession();

let exitCode = 0;
try {
  const result = await agent.generate({
    session,
    prompt: 'Create a short TODO.md for this repository.',
  });

  console.log(result.text);
} catch (err) {
  exitCode = 1;
  console.error(err);
} finally {
  await session.destroy();
  process.exit(exitCode);
}
```

`generate()` drains the turn and returns a `GenerateTextResult`.

Use `stream()` for incremental output:

```ts
const session = await agent.createSession();

let exitCode = 0;
try {
  const result = await agent.stream({
    session,
    prompt: 'Create a short TODO.md for this repository.',
  });

  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);
}
```

## Messages and History

A harness session owns its native conversation history. When you pass `messages`
or a message-array `prompt`, `HarnessAgent` takes the latest user message as the
fresh input for the turn. It does not replay the full prior conversation into
the harness.

This is different from model calls, where the application usually sends the full
message history. In chat routes, persist and resume the harness session instead
of relying on message replay.

## Session Lifecycle

End every session explicitly:

- `session.destroy()` stops the runtime and discards resumability.
- `session.detach()` parks the runtime and sandbox, returns resume state, and
  keeps the sandbox warm for a later attach. If the turn is unfinished, the
  resume state includes the continuation state.
- `session.stop()` saves resume state, then stops the runtime and sandbox. If
  the turn is unfinished, the resume state includes the continuation state.
- `session.suspendTurn()` is for advanced active-turn continuation across a
  process boundary.

Use `destroy()` for one-off scripts and tests. Use `detach()` or `stop()` for
HTTP routes that need multi-turn continuity.

```ts
const session = await agent.createSession({ sessionId: chatId });

try {
  const result = await agent.stream({ session, messages });

  for await (const part of result.stream) {
    if (part.type === 'text-delta') {
      process.stdout.write(part.text);
    }
  }

  const resumeState = await session.detach();
  await persistResumeState({ chatId, resumeState });
} catch (error) {
  await session.destroy();
  throw error;
}
```

## Resuming

Persist the opaque resume state and pass it back with the original `sessionId`:

```ts
const resumeState = await loadResumeState({ chatId });

const session = await agent.createSession(
  resumeState
    ? { sessionId: chatId, resumeFrom: resumeState }
    : { sessionId: chatId },
);
```

`HarnessAgent` validates that the resume state was produced by the same harness
adapter before handing it to the runtime. If the resume state includes an
unfinished turn, call `continueStream()` or `continueGenerate()` before sending a
new prompt.

## Continue a Suspended Turn

For advanced workflows that must hand off an active turn across a process
boundary, suspend the turn and persist the continuation state:

```ts
const continuationState = await session.suspendTurn();
await persistContinuationState({ chatId, continuationState });
```

When you only have raw continuation state from `suspendTurn()`, resume with
`continueFrom`, then continue the turn without sending a new prompt:

```ts
const session = await agent.createSession({
  sessionId: chatId,
  continueFrom: continuationState,
});

const result = await agent.continueStream({ session });
```

Use `continueStream()` for incremental output, or `continueGenerate()` to drain
the continued turn and return a `GenerateTextResult`.

## Prepare the Sandbox

Use `sandboxConfig` to prepare the sandbox before the harness starts.

`sandboxConfig.onBootstrap` runs during sandbox template creation, after the
harness adapter's own bootstrap and before snapshot-capable providers publish a
snapshot. Use it for expensive setup that should be reused by future sessions.
When you provide `onBootstrap`, also provide `bootstrapHash`; change the hash
whenever the bootstrap output should invalidate the reusable snapshot.

`sandboxConfig.onSession` runs after each sandbox session is acquired and its
working directory exists, including resumed sessions. Use it for per-session
files or lightweight configuration.

```ts
const agent = new HarnessAgent({
  harness: claudeCode,
  sandbox: createVercelSandbox({
    runtime: 'node24',
    ports: [4000],
  }),
  sandboxConfig: {
    workDir: 'repo',
    bootstrapHash: 'ripgrep-v1',
    onBootstrap: async ({ session, abortSignal }) => {
      const result = await session.run({
        command:
          'command -v rg >/dev/null || (apt-get update && apt-get install -y ripgrep)',
        abortSignal,
      });
      if (result.exitCode !== 0) {
        throw new Error(`Failed to install ripgrep: ${result.stderr}`);
      }
    },
    onSession: async ({ session, sessionWorkDir, abortSignal }) => {
      await session.writeTextFile({
        path: `${sessionWorkDir}/README.md`,
        content: 'Session notes for the harness.',
        abortSignal,
      });
    },
  },
});
```

`workDir` is optional. When provided, it must be relative to the sandbox's
default working directory and is used as the session working directory. When
omitted, regular sessions use the default `<harnessId>-<sessionId>` directory,
while `onBootstrap` receives the sandbox's default working directory.

## Settings

`HarnessAgent` accepts these main settings:

- `harness`: the adapter instance.
- `sandbox`: a `HarnessV1SandboxProvider`.
- `id`: optional stable agent identifier.
- `instructions`: instructions applied once to a fresh session.
- `tools`: AI SDK tools executed by the host when the harness calls them.
- `skills`: instruction bundles surfaced by the adapter.
- `permissionMode`: built-in tool permission mode.
- `toolApproval`: approval status map for host-executed tools.
- `sandboxConfig`: sandbox working-directory and lifecycle hook configuration.
- `telemetry`, `debug`, and `onLog`: observability and diagnostics.

Adapter-specific settings belong on the adapter factory, for example
`createCodex({ reasoningEffort: 'high' })`.

## Next Steps

- [Tools](/docs/ai-sdk-harnesses/tools) for built-in and host-executed tools.
- [Skills](/docs/ai-sdk-harnesses/skills) for reusable instruction bundles.
- [Harness adapters](/docs/ai-sdk-harnesses/harness-adapters) for adapter-specific
  settings.
- [Workflow utilities](/docs/ai-sdk-harnesses/workflow-utilities) for durable
  long-running turns.
- [UI](/docs/ai-sdk-harnesses/ui) for `useChat` integration.


## Navigation

- [Overview](/docs/ai-sdk-harnesses/overview)
- [HarnessAgent](/docs/ai-sdk-harnesses/harness-agent)
- [Tools](/docs/ai-sdk-harnesses/tools)
- [Skills](/docs/ai-sdk-harnesses/skills)
- [Harness Adapters](/docs/ai-sdk-harnesses/harness-adapters)
- [Workflow Utilities](/docs/ai-sdk-harnesses/workflow-utilities)
- [UI](/docs/ai-sdk-harnesses/ui)
- [Terminal UI](/docs/ai-sdk-harnesses/terminal-ui)


[Full Sitemap](/sitemap.md)