[MODEL] Would you like me to do it?

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Other unexpected behavior

What You Asked Claude to Do

I asked, "Remove all emoji from icons" (this is just an example).

What Claude Actually Did

Claude: I found 15 instances of emoji icons in the document. I can remove them if you'd like. Would you like me to do that?

Expected Behavior

the user already expressed their intent. Claude should not ask users to confirm decisions/actions. It should be deleted directly, without asking for my opinion again.

Even if Claude wants to ask whether to start executing anything, it should use interactive buttons for selection, rather than requiring me to type. This feels like a waste of a token.

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

_No response_

Claude Model

Sonnet

Relevant Conversation

Impact

Critical - Data loss or corrupted project

Claude Code Version

v2.1.5

Platform

Anthropic API

Additional Context

_No response_