[BUG] New options at the conclusion of authoring a plan are poorly worded

[briankelley]

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 Claude is launched with --allow-dangerously-skip-permissions, at the conclusion of interaction in "plan mode" Claude prompts the user for next steps with the following options:

  1. Yes, clear context and bypass permissions                                                                                                                                  
  2. Yes, and manually approve edits                                                                                                                                            
  3. Yes, and bypass permissions                                                                                                                                                
  4. Yes, manually approve edits              

"clear context" is developer jargon that most users would interpret as "clear permissions" or "start fresh with the plan" rather than "delete the entire conversation history." Had I selected this option, the conversation would have been removed and I would have been unable to continue using /resume.

What Should Happen?

Claude should make it clear that selecting option 1 will REMOVE the conversation.

Error Messages/Logs

Steps to Reproduce

1. launch Claude using --allow-dangerously-skip-permissions
2. engage planning mode for some activity
3. allow claude to complete planning and prompt the user for what to do next.

view options presented

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.1.12 (Claude Code)

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

Xterm

Additional Information

No response