[BUG] False-positive general_harm flag has me completely unable to use Claude Code. I cannot work. I pay$100/month for this?

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?

False-positive [general_harms]. I am completely locked.

<img width="1288" height="420" alt="Image" src="https://github.com/user-attachments/assets/8598563d-90ab-4fdc-9b73-ae83db6b422c" />

What Should Happen?

[general_harms] False Positive. I am completely locked.

<img width="1288" height="420" alt="Image" src="https://github.com/user-attachments/assets/8f2a32e8-7318-4b00-888f-1b847640ba32" />

Error Messages/Logs

Steps to Reproduce

I type "what is 2 + 2?". I get API Error: Sonnet 5 can't help with this. Start a new session to continue.

Learn more: https://www.anthropic.com/legal/aup

Details: [general_harms]

Request ID: req_011CeTJrHXGLS877JcpuFoRQ

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.247 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

_No response_