[BUG] Content filter blocked while working on calculator app

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?

So, the Claude Code is wasting tokens while working on absolutely normal typescript app which is so generic, rudimentary and bland that I don't even need to describe it. Then sub-agent stops with "Content filter blocked. Retrying with a tighter brief." and it goes over again. Apparently, the orchestrating agent is asking sub-agent to perform sex with Hitler, or whatever else Anthropic considers unsafe. I have no other explanation.

From what I see in logs, agent was trying to write typescript file to deal with fonts. Apparently, one of those was homophobic terrorist font. Or whatever Anthropic doesn't like these days.

What Should Happen?

Business as usual

Error Messages/Logs

Steps to Reproduce

Ask Claude to create simple basic rudimentary calculator app using sub-agent.

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.133 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Terminal.app (macOS)

Additional Information

<img width="532" height="46" alt="Image" src="https://github.com/user-attachments/assets/99b69c07-ce37-479c-aff0-0ec6f1f7dfbc" />