[BUG] sending /commands when agent is active doesnt work

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 agent is active and i try to issue a slash command, agent interprets the slash command as a normal message. This used to work in versions before .41

What Should Happen?

/command should still be treated as /command, not just as a normal message to the agent.

Error Messages/Logs

Steps to Reproduce

1. open claude
2. ask it to do something (that will take few seconds so you have time for next step)
3. type /exit
4. claude will finish processing your first request, then it will treat /exit as a message and start doing something weird. i would expect that the session exits.

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

2.0.37

Claude Code Version

2.0.42

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_