fix: Korean/CJK IME input and rendering in Sidebar Terminal

Fixes #1272

This commit addresses three separate Korean/CJK bugs in the Sidebar Terminal:

**Bug 1 - IME Input**: Korean text typed via IME composition was not
reaching the PTY correctly. Added compositionstart/compositionend event
listeners to suppress partial jamo fragments and only send the final
composed string.

**Bug 2a - Font Rendering**: Added CJK monospace font fallbacks
("Noto Sans Mono CJK KR", "Malgun Gothic") to both the xterm.js
fontFamily config and the CSS --font-mono variable. This ensures
consistent cell-width calculations for Korean characters.

**Bug 2b - UTF-8 Boundary Detection**: Added buffering logic to prevent
multi-byte UTF-8 characters (Korean is 3 bytes) from being split across
WebSocket chunks. This follows the same pattern as PR #1007 which fixed
the sidebar-agent path, but extends it to the terminal-agent path.

Special thanks to @ldybob for the excellent root cause analysis and
proposed solutions in issue #1272.

Tested on WSL2 + Windows 11 with Korean IME.
This commit is contained in:
Terry Carson YM 2026-05-02 14:56:59 +08:00
parent b512be7117
commit 4bd6359576
3 changed files with 39 additions and 3 deletions

View File

@ -361,8 +361,26 @@ function buildServer() {
// Binary input. Lazy-spawn claude on the first byte.
if (!session.spawned) {
session.spawned = true;
// UTF-8 boundary detection to prevent splitting multi-byte characters (issue #1272).
// Buffer incomplete UTF-8 sequences until the next chunk completes them.
let leftover = Buffer.alloc(0);
const proc = spawnClaude(session.cols, session.rows, (chunk) => {
try { ws.sendBinary(chunk); } catch {}
const combined = Buffer.concat([leftover, Buffer.from(chunk)]);
// Find the last index where a UTF-8 codepoint ends. Look back at most 3 bytes.
let safeEnd = combined.length;
for (let i = combined.length - 1; i >= Math.max(0, combined.length - 3); i--) {
const b = combined[i];
if ((b & 0x80) === 0) { safeEnd = i + 1; break; } // ASCII
if ((b & 0xC0) === 0x80) continue; // continuation byte
const expected = (b & 0xE0) === 0xC0 ? 2 : (b & 0xF0) === 0xE0 ? 3 : 4;
safeEnd = (combined.length - i >= expected) ? combined.length : i;
break;
}
const flush = combined.slice(0, safeEnd);
leftover = combined.slice(safeEnd);
if (flush.length) {
try { ws.sendBinary(flush); } catch {}
}
});
if (!proc) {
try {

View File

@ -154,7 +154,7 @@
function ensureXterm() {
if (term) return;
term = new Terminal({
fontFamily: '"JetBrains Mono", "SF Mono", Menlo, monospace',
fontFamily: '"JetBrains Mono", "SF Mono", Menlo, "Noto Sans Mono CJK KR", "Malgun Gothic", monospace',
fontSize: 13,
theme: { background: '#0a0a0a', foreground: '#e5e5e5' },
cursorBlink: true,
@ -196,7 +196,25 @@
});
ro.observe(els.mount);
// IME composition handling for Korean/CJK input (issue #1272).
// Suppress partial jamo during composition; only send the final
// composed string on compositionend. Without this, Korean IME
// sends fragmented input or doubles characters.
let composing = false;
const ta = term.textarea;
if (ta) {
ta.addEventListener('compositionstart', () => { composing = true; });
ta.addEventListener('compositionend', (e) => {
composing = false;
if (e.data && ws && ws.readyState === WebSocket.OPEN) {
ws.send(new TextEncoder().encode(e.data));
}
});
}
term.onData((data) => {
if (composing) return; // suppress partial input events during IME composition
if (ws && ws.readyState === WebSocket.OPEN) {
ws.send(new TextEncoder().encode(data));
}

View File

@ -38,7 +38,7 @@
/* Typography */
--font-system: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
--font-mono: 'JetBrains Mono', 'SF Mono', 'Fira Code', 'Cascadia Code', monospace;
--font-mono: 'JetBrains Mono', 'SF Mono', 'Fira Code', 'Cascadia Code', 'Noto Sans Mono CJK KR', 'Malgun Gothic', monospace;
/* Radius */
--radius-sm: 4px;