[BUG] Cyrillic character homoglyph corruption in agent text generation

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?

During a long-running English language session, the agent generated a response that was intended as an English sentence but contained a word with Cyrillic homoglyph corruption:

[...] when combined with --rotate-keys, immediately redeплoys all READY PR preview deployments [...]

What Should Happen?

The generated text should have used Latin characters when representing the English word "redeploys".

Error Messages/Logs

Steps to Reproduce

Unknown - issue appears to have occurred spontaneously in a long-running session.

Claude Model

Sonnet (default)

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.131 (Claude Code)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

VS Code integrated terminal

Additional Information

The agent's self analysis presented the cause as corruption during a compact step:

Cyrillic "п" and "л" visually resemble Latin "p" and "l", so "redeплoys" is a mixed-script homoglyph artifact. It looks like it crept in via the session summary (the compressed context uses the same spelling), and I propagated it into both my text output and the PR description without catching it.

Later:

What we saw was output corruption — Cyrillic "п" and "л" appeared in text Claude generated (specifically in the session context summary, then propagated into my responses).