[BUG] Advisor status message says the advisor applies the feedback, but the main agent does

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

When the main agent consults the advisor, Claude Code shows:

Advisor has reviewed the conversation and will apply the feedback

The subject of "will apply" is the advisor, but as far as I understand it, that's not how the tool works. The advisor only returns text to the main agent as a tool result, and the main agent decides whether to execute the changes through its own tool calls. The advisor doesn't apply anything, so the message gets the orchestration model backwards, which is confusing.

What Should Happen?

The message should name the main agent as the actor, for example:

Advisor has reviewed the conversation, and the agent will apply the feedback

Error Messages/Logs

Steps to Reproduce

1. Start a session with the advisor enabled.
2. Give the agent a task where it consults the advisor (or ask explicitly)
3. Read the status message shown after the advisor call returns.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.285

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

iTerm2

Additional Information

_No response_