> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ai-stats.phaseo.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Subagent Server Tool

> Let the main model delegate focused work to a worker model.

Use `ai-stats:subagent` when the main model should hand off a self-contained task to a smaller or faster worker model during the same request.

The main model calls the Subagent tool with a task description. AI Stats runs the worker model server-side, returns the worker result as tool context, and lets the main model finish the answer.

## Quick start

```bash theme={null}
curl https://api.phaseo.app/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "messages": [
      { "role": "user", "content": "Compare these release notes and summarize the breaking changes." }
    ],
    "tools": [
      {
        "type": "ai-stats:subagent",
        "parameters": {
          "model": "openai/gpt-5-nano",
          "instructions": "Return concise findings for the main model. Do not address the end user directly.",
          "max_uses": 3,
          "max_completion_tokens": 1200
        }
      }
    ]
  }'
```

## Parameters

```json theme={null}
{
  "type": "ai-stats:subagent",
  "parameters": {
    "model": "openai/gpt-5-nano",
    "instructions": "You are a fast, focused worker. Complete only the delegated task.",
    "max_uses": 3,
    "max_completion_tokens": 1200,
    "reasoning": { "effort": "low" },
    "temperature": 0.2
  }
}
```

| Parameter               | Type    | Default                     | Description                                                   |
| ----------------------- | ------- | --------------------------- | ------------------------------------------------------------- |
| `model`                 | string  | `openai/gpt-5-nano`         | Worker model to call.                                         |
| `instructions`          | string  | focused worker instructions | Extra instructions appended to the default Subagent behavior. |
| `max_uses`              | integer | `10`                        | Maximum Subagent calls during the server-tool loop.           |
| `max_completion_tokens` | integer | Advisor default             | Max output tokens for each worker response.                   |
| `max_tokens`            | integer | Advisor default             | Legacy alias for `max_completion_tokens`.                     |
| `reasoning`             | object  | provider default            | Reasoning config forwarded to the worker call when supported. |
| `temperature`           | number  | provider default            | Sampling temperature for the worker call.                     |

## Tool-call arguments

The model normally calls Subagent with `task_description`:

```json theme={null}
{
  "task_description": "Extract the three highest-risk migration steps from the supplied plan."
}
```

AI Stats also accepts `task`, `prompt`, or `input` as aliases when a model emits a slightly different argument name.

## What the tool returns

Subagent returns JSON as the tool result:

```json theme={null}
{
  "status": "ok",
  "model": "openai/gpt-5-nano",
  "result": "The highest-risk steps are schema migration, traffic cutover, and rollback verification."
}
```

If the worker request cannot run, AI Stats returns a tool error such as `subagent_invalid_request`, `subagent_max_uses_exceeded`, or `subagent_request_failed`.

## Usage and pricing

Subagent calls increment:

```json theme={null}
{
  "usage": {
    "server_tool_use": {
      "subagent_requests": 1
    }
  }
}
```

The worker model's tokens are included in total usage and can be priced at the selected worker model's rates.

## Related

* [Advisor](./advisor)
* [Fusion](./fusion)
* [Server Tools](./index)