[BUG] Rust panic: "byte index 2 is not a char boundary" when processing emoji (✅)

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?

Claude Code crashes with a Rust panic error when processing text containing emoji characters.

The panic occurs because the code attempts to slice a UTF-8 string at byte index 2,
which falls inside the multi-byte emoji character '✅' (which occupies bytes 0..3).

This appears to be a string handling issue where byte-based indexing is used instead
of character-boundary-aware slicing for multi-byte UTF-8 characters.

What Should Happen?

Claude Code should handle emoji and other multi-byte UTF-8 characters correctly
without crashing. String operations should use character-boundary-aware methods
instead of raw byte indexing.

Error Messages/Logs

thread '<unnamed>' (1563082) panicked at /rustc/ed61e7d7e242494fb7057f2657300d9e77bb4fcb/library/core/src/str/mod.rs:833:21:            
  byte index 2 is not a char boundary; it is inside '✅' (bytes 0..3) of `✅`                                                             
  note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace                                                           
  fatal runtime error: failed to initiate panic, error 5, aborting

Steps to Reproduce

1. Run Claude Code in terminal
2. [여기에 오류가 발생했을 때 수행하던 작업을 구체적으로 작성하세요]

예: "Send a prompt containing emoji characters like ✅"
또는 "Use a CLAUDE.md file containing emoji markers"

1. The application crashes with the above panic message

Note: The exact trigger is unclear, but the error involves processing
the ✅ emoji character.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.0.72 (Claude Code)

Platform

Other

Operating System

macOS

Terminal/Shell

VS Code integrated terminal

Additional Information

Related Issues

• Possibly related to #6903 (Unicode Codepoint Corruption)
• Similar to openai/codex#3261

## Suggested Fix
Use str.char_indices() or str.chars() for string slicing instead of
direct byte indexing to ensure operations occur at valid UTF-8 character boundaries.