[BUG] 1/2/3 approval is terribly designed

Resolved 💬 3 comments Opened Apr 28, 2026 by shaps776 Closed May 2, 2026

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?

1 should always be YES, 2 should always be NO and 3 should always be ALWAYS. The fact that 2 goes from meaning NO to meaning SUPER YES depending on what question is asked is about the worst design that I could think of. Either this was an oversight or it was driven by the misguided goal of adding friction here so force attention. Either way, it's not the right design.

What Should Happen?

1 should always be YES, 2 should always be NO and 3 should always be ALWAYS. Or some other order. That part doesn't matter. It's the consistency that matters for muscle memory.

Error Messages/Logs

Steps to Reproduce

Use Claude Code

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

All AFAIK

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗