Panic: UTF-8 byte boundary error when processing Japanese text

Bug Description

Claude Code crashes with a Rust panic when processing files containing Japanese text.

Error Message

thread '<unnamed>' panicked at /rustc/ed61e7d7e242494fb7057f2657300d9e77bb4fcb/library/core/src/str/mod.rs:833:21:
byte index 24 is not a char boundary; it is inside 'す' (bytes 22..25) of `下の3段階で定義する`
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
fatal runtime error: failed to initiate panic, error 5, aborting
[1]    3413453 IOT instruction (core dumped)  claude

Root Cause

The code is attempting to slice a UTF-8 string at a byte index (24) that falls in the middle of a multi-byte character ('す', which occupies bytes 22-25). In Rust, string slicing at non-character boundaries causes a panic.

Steps to Reproduce

1. Open a file containing Japanese text in the IDE (the file was docs/research_plan/05_definitions.md)
2. The file contains the text 下の3段階で定義する
3. Claude Code crashes when processing this file

Environment

• Platform: Linux 6.1.0-25-amd64
• Claude Code version: (latest as of 2026-01-01)

Expected Behavior

Claude Code should correctly handle multi-byte UTF-8 characters (Japanese, Chinese, Korean, emoji, etc.) without crashing.

Suggested Fix

Ensure all string slicing operations use character boundaries (.char_indices()) rather than raw byte indices, or use safe slicing methods that account for UTF-8 encoding.