Response structure

Successful advisor call

When the advisor is called, a server_tool_use block is followed by an advisor_tool_result block in the assistant's content. The following example shows the plaintext advisor_result variant returned by a Claude Opus 4.8 advisor. The Quick start uses Claude Opus 5, which returns the encrypted advisor_redacted_result variant instead; see Result variants for both shapes side by side.

{
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Let me consult the advisor on this."
    },
    {
      "type": "server_tool_use",
      "id": "srvtoolu_abc123",
      "name": "advisor",
      "input": {}
    },
    {
      "type": "advisor_tool_result",
      "tool_use_id": "srvtoolu_abc123",
      "content": {
        "type": "advisor_result",
        "text": "Use a channel-based coordination pattern. The tricky part is draining in-flight work during shutdown: close the input channel first, then wait on a WaitGroup..."
      }
    },
    {
      "type": "text",
      "text": "Here's the implementation. I'm using a channel-based coordination pattern to avoid writer starvation..."
    }
  ]
}

The server_tool_use.input is always empty. The server constructs the advisor's view from the full transcript automatically. Nothing the executor puts in input reaches the advisor.

Result variants

The advisor_tool_result.content field is a discriminated union. For successful calls, the variant depends on the advisor model:

Variant	Fields	Returned when
advisor_result	text, stop_reason	The advisor model returns plaintext (for example, Claude Opus 4.8).
advisor_redacted_result	encrypted_content, stop_reason	The advisor model returns encrypted output.

Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 advisors return the encrypted advisor_redacted_result. Every other advisor model in the compatibility table returns the plaintext advisor_result. To read the advice text in your own responses, use an advisor that returns plaintext, such as claude-opus-4-8, where your executor's row in the compatibility table lists one. Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5, Claude Fable 5, and Claude Mythos 5 executors pair only with advisors that return the encrypted form, so on those executors the advice text isn't readable in the response.

Here is the same request sent twice, identical except for the advisor model in the tool definition, showing both variants.

With "model": "claude-opus-4-8", the advice is plaintext:

{
  "type": "advisor_tool_result",
  "tool_use_id": "srvtoolu_abc123",
  "content": {
    "type": "advisor_result",
    "text": "Use a channel-based coordination pattern. The tricky part is draining in-flight work during shutdown: close the input channel first, then wait on a WaitGroup..."
  }
}

With "model": "claude-opus-5", the advice is encrypted:

{
  "type": "advisor_tool_result",
  "tool_use_id": "srvtoolu_abc123",
  "content": {
    "type": "advisor_redacted_result",
    "encrypted_content": "EqQBCkYIBRgCIiQ5ZjE0N2M2OC0yYWIxLTRkZTktYjA3ZC1hZTUyMzkxYjhkMmU..."
  }
}

Both result variants carry a stop_reason field when you set max_tokens on the tool definition, and omit it when you do not. It holds the advisor sub-call's stop reason, typically "end_turn", or "max_tokens" when the cap is hit. The values match the top-level Messages API stop_reason.

With advisor_result, the text field contains human-readable advice. With advisor_redacted_result, the encrypted_content field contains an opaque blob that you cannot read. On the next turn, the server decrypts it and renders the plaintext into the executor's prompt.

In both cases, round-trip the content verbatim on subsequent turns. If you switch advisor models mid-conversation, branch on content.type to handle both shapes.

Error results

If the advisor call fails, the result carries an error:

{
  "type": "advisor_tool_result",
  "tool_use_id": "srvtoolu_abc123",
  "content": {
    "type": "advisor_tool_result_error",
    "error_code": "overloaded"
  }
}

The executor sees the error and continues without further advice. The request itself does not fail.

error_code	Meaning
max_uses_exceeded	The request reached the max_uses cap set on the tool definition. Further advisor calls in the same request return this error.
too_many_requests	The advisor sub-inference was rate-limited.
overloaded	The advisor sub-inference hit capacity limits.
prompt_too_long	The transcript exceeded the advisor model's context window.
execution_time_exceeded	The advisor sub-inference timed out.
model_not_found	The configured advisor model is not available.
unavailable	Any other advisor failure.

Advisor rate limits draw from the same per-model bucket as direct calls to the advisor model. A rate limit on the advisor appears as too_many_requests inside the tool result. A rate limit on the executor fails the whole request with HTTP 429.