Next-step suggestion text mixes Hanja/foreign characters instead of pure Korean (Hangul)

Description

Claude Code occasionally pre-fills the terminal input box with a "next step" suggestion after a task finishes. When the suggestion is in Korean, it sometimes substitutes a Hanja (Chinese character with the same Sino-Korean reading) for a word that should be written in Hangul.

Example

After a task completed (~2m 19s run), the input box was pre-filled with:

進行 상황 확인해줘

Expected pure Korean (Hangul):

진행 상황 확인해줘

"進行" is the Hanja for "진행" (progress) — same pronunciation, wrong script. This does not look like an IME/OS input issue; the text appears to be auto-generated by Claude Code's next-step suggestion feature and inserted directly into the composer.

Environment

• OS: Windows 11 Home 10.0.26200
• Claude Code running in VS Code integrated terminal

Expected behavior

Auto-generated Korean suggestion text should use pure Hangul, consistent with normal Sino-Korean word usage, rather than substituting Hanja characters.

Additional context

This appears to be a CJK text-generation quirk (Hanja/Hangul are homophonous for Sino-Korean vocabulary) possibly specific to the lightweight/fast generation path used for these inline suggestions, since normal chat responses in the same session did not exhibit this substitution.