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

# Advisor Server Tool

> Let one model consult another model mid-generation.

Use `phaseo:advisor` when the main model should be able to ask another model for a review, plan, sanity check, or specialist opinion before it finishes.

The main model calls Advisor like any other tool. Phaseo runs the Advisor model server-side and returns the advice as the tool result. The main model then writes the final response.

<Note>
  Advisor is gateway-managed across supported text models. It is not converted into Anthropic's native Advisor tool unless the client explicitly sends Anthropic's native tool shape.
</Note>

## Quick start

```bash theme={null}
curl https://api.phaseo.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "messages": [
      { "role": "user", "content": "Design a rate limiter for a distributed API gateway." }
    ],
    "tools": [
      {
        "type": "phaseo:advisor",
        "parameters": {
          "model": "anthropic/claude-opus-4-8",
          "max_uses": 1,
          "max_completion_tokens": 1400
        }
      }
    ]
  }'
```

## Choosing the Advisor model

You can pin the Advisor model in the tool definition:

```json theme={null}
{
  "type": "phaseo:advisor",
  "parameters": {
    "model": "anthropic/claude-opus-4-8"
  }
}
```

If `parameters.model` is omitted, the tool call may provide `model`. If neither is set, Phaseo falls back to the outer request model.

## Parameters

```json theme={null}
{
  "type": "phaseo:advisor",
  "parameters": {
    "name": "reviewer",
    "model": "anthropic/claude-opus-4-8",
    "instructions": "Review plans for correctness, missing edge cases, and implementation risk.",
    "forward_transcript": true,
    "max_uses": 2,
    "max_completion_tokens": 1400,
    "reasoning": { "effort": "high" },
    "temperature": 0.2
  }
}
```

| Parameter               | Type    | Default                  | Description                                                                                                                   |
| ----------------------- | ------- | ------------------------ | ----------------------------------------------------------------------------------------------------------------------------- |
| `name`                  | string  | none                     | Optional Advisor name. Names must be unique after trimming and may contain letters, numbers, spaces, underscores, and dashes. |
| `model`                 | string  | outer model              | Advisor model to call. If omitted, the tool call can provide `model`.                                                         |
| `instructions`          | string  | default Advisor behavior | Extra instructions for the Advisor model.                                                                                     |
| `forward_transcript`    | boolean | `false`                  | Include the current conversation transcript in the Advisor request.                                                           |
| `max_uses`              | integer | `1`                      | Maximum calls for this Advisor during the server-tool loop.                                                                   |
| `max_completion_tokens` | integer | `1400`                   | Max output tokens for the Advisor response.                                                                                   |
| `max_tokens`            | integer | `1400`                   | Legacy alias for `max_completion_tokens`.                                                                                     |
| `reasoning`             | object  | provider default         | Reasoning config forwarded to the Advisor call when supported by the selected model/provider.                                 |
| `temperature`           | number  | provider default         | Sampling temperature for the Advisor call.                                                                                    |

## Tool-call arguments

The model normally calls Advisor with a `prompt`:

```json theme={null}
{
  "prompt": "Review this migration plan and identify the riskiest assumptions."
}
```

If the Advisor definition does not pin a model, the tool call may also include `model`:

```json theme={null}
{
  "model": "anthropic/claude-opus-4-8",
  "prompt": "Check this security design for missing controls."
}
```

When `forward_transcript` is `true`, Phaseo can execute a transcript-only Advisor call if the model does not supply a prompt.

## Multiple advisors

Add one `phaseo:advisor` entry per advisor. Each named advisor becomes a distinct internal tool, such as `phaseo_advisor_security_reviewer` or `phaseo_advisor_architect`.

```json theme={null}
{
  "tools": [
    {
      "type": "phaseo:advisor",
      "parameters": {
        "name": "security-reviewer",
        "model": "anthropic/claude-opus-4-8",
        "instructions": "Review for vulnerabilities, abuse cases, and missing mitigations."
      }
    },
    {
      "type": "phaseo:advisor",
      "parameters": {
        "name": "architect",
        "model": "openai/gpt-5",
        "instructions": "Review system design tradeoffs and operational risks."
      }
    }
  ]
}
```

At most one Advisor entry may omit `name`. If you force `tool_choice: "phaseo:advisor"` with multiple advisors, Phaseo maps that alias to the first configured Advisor.

## What the tool returns

Advisor returns JSON as the tool result:

```json theme={null}
{
  "status": "ok",
  "name": "reviewer",
  "model": "anthropic/claude-opus-4-8",
  "advice": "Start with a smaller migration slice and define rollback criteria before changing traffic routing."
}
```

If the Advisor request cannot run, Phaseo returns a tool error such as `advisor_invalid_request`, `advisor_max_uses_exceeded`, or `advisor_request_failed`.

## Conversation memory

Advisor does not keep hidden cross-request state. If you replay prior messages and tool results in the next request, the main model can see the prior consultation. If `forward_transcript` is enabled, the Advisor can also see the forwarded conversation transcript for that request.

## Usage and pricing

Advisor calls increment:

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

The Advisor model's tokens are included in total usage and can be priced at the selected Advisor model's rates. Server-tool pricing can also use `server_tool_advisor_requests`.

## Current limits

* Advisor advice streaming is not enabled yet.
* Recursive Advisor calls are blocked by the server-tool loop limits.

## Related

* [Server Tools](./index)
* [Subagent](./subagent)
* [Tool Calling](../tool-calling)