Rust panic: UTF-8 Korean character boundary error

Bug Description

Claude Code panics when processing Korean (Hangul) characters due to incorrect UTF-8 byte boundary handling.

Error Message

thread '<unnamed>' panicked at /rustc/ed61e7d7e242494fb7057f2657300d9e77bb4fcb\library\core\src\str\mod.rs:833:21:
byte index 2 is not a char boundary; it is inside '가' (bytes 0..3) of `가`
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace

Environment

• Platform: Windows (win32)
• Working directory contains Korean characters in file paths or content

Steps to Reproduce

1. Run Claude Code in a directory with Korean text in files or paths
2. Execute any command that processes Korean characters
3. Panic occurs when Rust code tries to slice a Korean character at byte index 2 (Korean '가' occupies bytes 0-3 in UTF-8)

Root Cause

The Rust code is attempting to slice a UTF-8 string at a non-character boundary. Korean characters like '가' are 3 bytes in UTF-8, but the code is trying to access byte index 2 which is in the middle of the character.

Expected Behavior

Claude Code should properly handle multi-byte UTF-8 characters including Korean, Chinese, Japanese, and other non-ASCII scripts.

Workaround

Currently, users must avoid Korean characters in file paths and content, which is not practical for Korean-speaking users.