fx Harness

The fx harness adapter connects HarnessAgent to fx through the Agent Client Protocol (ACP). The adapter delegates installation, sessions, streaming, tools, and lifecycle management to @ai-sdk/harness-acp.

Setup

pnpm add @ai-sdk/harness @ai-sdk/harness-fx @ai-sdk/sandbox-vercel

The ACP harness runs the canonical fx installer inside the sandbox when the first session starts. The installer tracks the latest fx release and installs the executable into the ACP implementation's private home directory.

Import

1
import { createFx, fx } from '@ai-sdk/harness-fx';

fx is equivalent to createFx() with its default configuration.

Basic Usage

1
import { HarnessAgent } from '@ai-sdk/harness/agent';
2
import { fx } from '@ai-sdk/harness-fx';
3
import { createVercelSandbox } from '@ai-sdk/sandbox-vercel';
4

5
const agent = new HarnessAgent({
6
  harness: fx,
7
  model: 'openai/gpt-5.6-luna',
8
  sandbox: createVercelSandbox({
9
    runtime: 'node24',
10
    ports: [4000],
11
  }),
12
});
13

14
const session = await agent.createSession();
15

16
let exitCode = 0;
17
try {
18
  const result = await agent.stream({
19
    session,
20
    prompt: 'Check the test failures and fix the production code.',
21
  });
22

23
  for await (const part of result.stream) {
24
    if (part.type === 'text-delta') {
25
      process.stdout.write(part.text);
26
    }
27
  }
28
} catch (err) {
29
  exitCode = 1;
30
  console.error(err);
31
} finally {
32
  await session.destroy();
33
  process.exit(exitCode);
34
}

Adapter Settings

Use createFx() to configure the runtime:

1
const harness = createFx({
2
  auth: 'ai-gateway',
3
  port: 4001,
4
  startupTimeoutMs: 180_000,
5
});

Settings:

• auth: selects auto, direct, or ai-gateway authentication, or accepts an authentication environment for programmatically resolved credentials. fx always sends model requests through Vercel AI Gateway, so direct and ai-gateway differ only in how the harness passes the Gateway credential into the sandbox.
• credentialForwarding: optional synchronous or asynchronous callback that customizes each credential immediately before the harness adapter forwards it into a sandbox process. It receives the credential value that would otherwise be forwarded (either the real credential or a masked value) and the environment variable name used to expose it. This callback only controls the value forwarded into the sandbox process. It does not restrict which credentials the harness adapter can discover, read, or otherwise access in the host process.
• mcpServers: MCP server definitions keyed by server name. fx ACP sessions use only the servers supplied by the ACP client.
• port: ACP bridge port override.
• portEndpoint: host endpoint for the ACP bridge when the sandbox session cannot expose ports directly.
• startupTimeoutMs: maximum time to wait for the ACP bridge to start.
• mintBridgeToken: synchronous function that receives the sandbox id and returns the ACP bridge authentication token. By default, the adapter generates a random 32-byte token.

The adapter fixes the installation source, executable, launch command, and ACP version. These implementation details cannot be overridden through createFx().

Authentication

fx uses Vercel AI Gateway authentication. Set one of these environment variables:

• VERCEL_OIDC_TOKEN
• AI_GATEWAY_API_KEY

If no applicable credential environment variable is set, the adapter attempts to resolve a native subscription from the host system unless AI Gateway authentication is selected.

fx prefers VERCEL_OIDC_TOKEN when both are available. The adapter brokers the selected credential only to the configured Gateway origin when the sandbox supports request transformations. Other sandboxes retain direct credential forwarding.

Pass an authentication environment when the host resolves credentials at runtime instead of exposing them through process.env:

1
const gatewayHarness = createFx({
2
  auth: {
3
    AI_GATEWAY_API_KEY: await resolveGatewayToken(),
4
    AI_GATEWAY_BASE_URL: 'https://ai-gateway.vercel.sh',
5
  },
6
});

The supplied record replaces the host environment for authentication discovery. The adapter does not add its credentials to process.env or include their values in persisted ACP lifecycle identity.

Both authentication configurations reach AI Gateway:

1
const directHarness = createFx({ auth: 'direct' });
2
const gatewayHarness = createFx({ auth: 'ai-gateway' });

Sandbox

fx runs inside the sandbox through @ai-sdk/harness-acp. It requires a network sandbox with at least one exposed port:

1
const sandbox = createVercelSandbox({
2
  runtime: 'node24',
3
  ports: [4000],
4
});

The first session requires network egress to download fx. Subsequent model and web requests also require network access.

Built-in Tools

The adapter maps glob_files, grep_files, and web_search to the common glob, grep, and webSearch harness tool names.

Other tools remain available under their native fx names, including list_files, read_file, write_file, edit_file, file mutation and metadata tools, terminal, semantic_search, web_fetch, skill tools, subagents, MCP discovery tools, ask_user_question, vision, and read_tool_result.

The adapter maps allow-reads and allow-edits to fx's ask ACP mode. allow-all maps to fx's code ACP mode. The allow-edits mapping is conservative because fx does not provide a mode that allows file edits while still requiring approval for terminal commands. fx may resolve safe operations or apply its own permission policy without sending an ACP permission request.

Known Limitations

• fx's ACP v1 tool updates omit the programmatic tool name and raw input except when requesting permission. Native tools still execute, but ordinary native tool events cannot always be associated with a typed built-in tool name.
• ACP v1 does not expose model-step boundaries or per-step usage. The adapter infers boundaries and reports unknown per-step usage when fx does not provide totals.
• ACP v1 has no portable manual compaction or mid-turn steering API.
• ACP v1 has no portable built-in tool filtering API. Filtering host tools is supported, but filtering fx built-ins throws an unsupported-capability error.
• fx ACP does not expose a structured-output metadata mapping, so schema-backed structured output is unsupported.
• Custom headers are not natively supported and only applied via sandbox-external request transformations. When a sandbox without that capability is provided, custom headers therefore cannot be passed and are ignored.

Related

• HarnessAgent
• Harness tools
• Harness adapters
• Agent Client Protocol