jeo-code 0.8.31 → 0.8.32

package/CHANGELOG.md

@@ -6,6 +6,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 The README mirrors the latest 5 entries — regenerate with `bun run changelog:sync`.
 
+## [0.8.32] - 2026-07-20
+_gjc parity: TUI display-width/wrapping is now grapheme-cluster-aware for emoji sequences (VS16 presentation, skin-tone modifiers, keycaps, ZWJ-joined emoji like family/profession glyphs), fixing box-border and wrap misalignment ("깨짐") that the old per-code-point width summation produced whenever such a sequence appeared in a message — Korean/CJK-only text was already correctly handled and is unaffected._
+
+### Fixed
+- **Display-width no longer over/under-counts emoji sequences, so box borders and hard-wraps never misalign when one appears in a message** (`src/tui/components/width.ts`) — gjc parity (`#1996` "preserve … Unicode grapheme semantics for … VS16 emoji presentation, ZWJ, keycaps, and emoji modifiers"). The old `visibleWidth`/`truncateToWidth` summed `charWidth()` per CODE POINT, which is wrong for any sequence a terminal renders as ONE glyph: `❤️` (heart + VS16) summed to 1 column where terminals render 2; `👍🏽` (thumbs-up + Fitzpatrick skin-tone modifier) summed to 4 where terminals render 2; a 4-person ZWJ family emoji (`👨‍👩‍👧‍👦`) summed to 8 where terminals render 2 — quantified live against the actual old per-code-point path before fixing (not asserted from inference). New `nextGraphemeCluster()` absorbs VS15/VS16, Fitzpatrick modifiers (`U+1F3FB`-`U+1F3FF`), keycap combiners (`U+20E3`), combining marks, and ZWJ-joined chains into one atomic width-2 (or width-1 for VS15 text-presentation) unit; `visibleWidth`/`truncateToWidth` (and therefore `wrapTextWithAnsi`, built on both) now consume it instead of raw per-code-point `charWidth()`, and `truncateToWidth` can no longer split one of these sequences in half at a wrap/truncation boundary (a second corruption vector the old code point-by-point cut was exposed to). Korean/CJK/Hangul-only text (no emoji sequences) was already correct and is byte-identical before/after.
+
+### Verified
+- `test/width.test.ts` — 11 pass (was 9): new `nextGraphemeCluster` unit coverage for the VS15/VS16/Fitzpatrick/keycap/ZWJ cases above, plus a `truncateToWidth` atomicity test proving a 2-wide cluster is dropped whole (never half) at a 1-column budget.
+- Live (unmocked) reproduction: quantified the OLD per-code-point sum against the NEW `visibleWidth` for all 4 sequence classes — heart 1→2, thumbs-up+modifier 4→2, ZWJ family 8→2, keycap 1→2 — confirming this was a real, sometimes-severe (family emoji off by 6 columns) miscount, not a hypothetical.
+- Live (unmocked) box-render smoke test: wrapped a real mixed Korean/emoji message (family emoji, VS16 heart, skin-tone thumbs-up) into a 20-column box via `wrapTextWithAnsi` — every wrapped line's `visibleWidth` fit the declared budget with correct padding, confirming no overflow/misalignment end-to-end (not just at the unit level).
+- Full `bun test` — 3092 pass / 0 fail across 304 files (2 transient parallel-load flakes on the first run — unrelated `/model` pin routing + a Node `--inspect-brk` debug-session test, neither touching `width.ts` — both isolated-pass and a full clean re-run confirmed no regression).
+- `bun run typecheck` — no errors.
+
 ## [0.8.31] - 2026-07-20
 _`web_search` no longer silently degrades every non-Anthropic model to keyless DuckDuckGo scraping — OpenAI and Gemini sessions now get their own native, hosted search tool (matching the same active-model-gated, credential-required design Anthropic already had), with DuckDuckGo remaining the always-on terminal fallback for everyone else._
 

package/README.ja.md

@@ -283,11 +283,11 @@ CI は `.github/workflows/npm-publish.yml` で公開します — GitHub リリ
 ## 変更履歴 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.8.32]** (2026-07-20) — gjc parity: TUI display-width/wrapping is now grapheme-cluster-aware for emoji sequences (VS16 presentation, skin-tone modifiers, keycaps, ZWJ-joined emoji like family/profession glyphs), fixing box-border and wrap misalignment ("깨짐") that the old per-code-point width summation produced whenever such a sequence appeared in a message — Korean/CJK-only text was already correctly handled and is unaffected.
 - **[0.8.31]** (2026-07-20) — `web_search` no longer silently degrades every non-Anthropic model to keyless DuckDuckGo scraping — OpenAI and Gemini sessions now get their own native, hosted search tool (matching the same active-model-gated, credential-required design Anthropic already had), with DuckDuckGo remaining the always-on terminal fallback for everyone else.
 - **[0.8.30]** (2026-07-20) — `bun run build` (the host-only dev binary build) has been silently broken for every user who ran it — a drift between the plain `package.json` `build` script and the actual working release-binary build command (`scripts/ci-release-build-binaries.ts`), which had already documented and fixed the exact same crash.
 - **[0.8.29]** (2026-07-20) — gajae-code (gjc) v0.10.2→v0.11.4 gap analysis: most of that range is gjc-specific architecture jeo intentionally does not replicate (SDK broker/session-index recovery, Gajae Pet, coordinator-mcp, Telegram/Discord rich-delivery internals, browser tab workers, worktree-subcommand removal, RPC durable model selection) — one genuinely applicable TUI bug was found and closed; the CLI empty-non-TTY-stdin fix (gjc #2586) was investigated and found already-correct by construction (jeo's one-shot gate forces true whenever stdin isn't a TTY, regardless of args, so the hang gjc fixed cannot occur here).
 - **[0.8.28]** (2026-07-16) — Improved the welcome UI's right-side table to display dynamic sections (What's New, Flow keys, Project pulse, and Session trail) matching gajae-code (gjc) >= 0.8.0 features.
-- **[0.8.27]** (2026-07-16) — Repeat-read recovery now survives both context-overflow and refusal-result elision without reopening mutating-call loops.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.ko.md

@@ -284,11 +284,11 @@ CI는 `.github/workflows/npm-publish.yml`로 배포합니다 — GitHub 릴리
 ## 변경 이력 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.8.32]** (2026-07-20) — gjc parity: TUI display-width/wrapping is now grapheme-cluster-aware for emoji sequences (VS16 presentation, skin-tone modifiers, keycaps, ZWJ-joined emoji like family/profession glyphs), fixing box-border and wrap misalignment ("깨짐") that the old per-code-point width summation produced whenever such a sequence appeared in a message — Korean/CJK-only text was already correctly handled and is unaffected.
 - **[0.8.31]** (2026-07-20) — `web_search` no longer silently degrades every non-Anthropic model to keyless DuckDuckGo scraping — OpenAI and Gemini sessions now get their own native, hosted search tool (matching the same active-model-gated, credential-required design Anthropic already had), with DuckDuckGo remaining the always-on terminal fallback for everyone else.
 - **[0.8.30]** (2026-07-20) — `bun run build` (the host-only dev binary build) has been silently broken for every user who ran it — a drift between the plain `package.json` `build` script and the actual working release-binary build command (`scripts/ci-release-build-binaries.ts`), which had already documented and fixed the exact same crash.
 - **[0.8.29]** (2026-07-20) — gajae-code (gjc) v0.10.2→v0.11.4 gap analysis: most of that range is gjc-specific architecture jeo intentionally does not replicate (SDK broker/session-index recovery, Gajae Pet, coordinator-mcp, Telegram/Discord rich-delivery internals, browser tab workers, worktree-subcommand removal, RPC durable model selection) — one genuinely applicable TUI bug was found and closed; the CLI empty-non-TTY-stdin fix (gjc #2586) was investigated and found already-correct by construction (jeo's one-shot gate forces true whenever stdin isn't a TTY, regardless of args, so the hang gjc fixed cannot occur here).
 - **[0.8.28]** (2026-07-16) — Improved the welcome UI's right-side table to display dynamic sections (What's New, Flow keys, Project pulse, and Session trail) matching gajae-code (gjc) >= 0.8.0 features.
-- **[0.8.27]** (2026-07-16) — Repeat-read recovery now survives both context-overflow and refusal-result elision without reopening mutating-call loops.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.md

@@ -291,11 +291,11 @@ Huge thanks to [gajae-code](https://github.com/Yeachan-Heo/gajae-code) for the i
 ## Changelog
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.8.32]** (2026-07-20) — gjc parity: TUI display-width/wrapping is now grapheme-cluster-aware for emoji sequences (VS16 presentation, skin-tone modifiers, keycaps, ZWJ-joined emoji like family/profession glyphs), fixing box-border and wrap misalignment ("깨짐") that the old per-code-point width summation produced whenever such a sequence appeared in a message — Korean/CJK-only text was already correctly handled and is unaffected.
 - **[0.8.31]** (2026-07-20) — `web_search` no longer silently degrades every non-Anthropic model to keyless DuckDuckGo scraping — OpenAI and Gemini sessions now get their own native, hosted search tool (matching the same active-model-gated, credential-required design Anthropic already had), with DuckDuckGo remaining the always-on terminal fallback for everyone else.
 - **[0.8.30]** (2026-07-20) — `bun run build` (the host-only dev binary build) has been silently broken for every user who ran it — a drift between the plain `package.json` `build` script and the actual working release-binary build command (`scripts/ci-release-build-binaries.ts`), which had already documented and fixed the exact same crash.
 - **[0.8.29]** (2026-07-20) — gajae-code (gjc) v0.10.2→v0.11.4 gap analysis: most of that range is gjc-specific architecture jeo intentionally does not replicate (SDK broker/session-index recovery, Gajae Pet, coordinator-mcp, Telegram/Discord rich-delivery internals, browser tab workers, worktree-subcommand removal, RPC durable model selection) — one genuinely applicable TUI bug was found and closed; the CLI empty-non-TTY-stdin fix (gjc #2586) was investigated and found already-correct by construction (jeo's one-shot gate forces true whenever stdin isn't a TTY, regardless of args, so the hang gjc fixed cannot occur here).
 - **[0.8.28]** (2026-07-16) — Improved the welcome UI's right-side table to display dynamic sections (What's New, Flow keys, Project pulse, and Session trail) matching gajae-code (gjc) >= 0.8.0 features.
-- **[0.8.27]** (2026-07-16) — Repeat-read recovery now survives both context-overflow and refusal-result elision without reopening mutating-call loops.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/README.zh.md

@@ -283,11 +283,11 @@ CI 通过 `.github/workflows/npm-publish.yml` 发布 — GitHub 发布 release
 ## 更新日志 (Changelog)
 
 <!-- CHANGELOG:START (auto-generated from CHANGELOG.md — run `bun run changelog:sync`) -->
+- **[0.8.32]** (2026-07-20) — gjc parity: TUI display-width/wrapping is now grapheme-cluster-aware for emoji sequences (VS16 presentation, skin-tone modifiers, keycaps, ZWJ-joined emoji like family/profession glyphs), fixing box-border and wrap misalignment ("깨짐") that the old per-code-point width summation produced whenever such a sequence appeared in a message — Korean/CJK-only text was already correctly handled and is unaffected.
 - **[0.8.31]** (2026-07-20) — `web_search` no longer silently degrades every non-Anthropic model to keyless DuckDuckGo scraping — OpenAI and Gemini sessions now get their own native, hosted search tool (matching the same active-model-gated, credential-required design Anthropic already had), with DuckDuckGo remaining the always-on terminal fallback for everyone else.
 - **[0.8.30]** (2026-07-20) — `bun run build` (the host-only dev binary build) has been silently broken for every user who ran it — a drift between the plain `package.json` `build` script and the actual working release-binary build command (`scripts/ci-release-build-binaries.ts`), which had already documented and fixed the exact same crash.
 - **[0.8.29]** (2026-07-20) — gajae-code (gjc) v0.10.2→v0.11.4 gap analysis: most of that range is gjc-specific architecture jeo intentionally does not replicate (SDK broker/session-index recovery, Gajae Pet, coordinator-mcp, Telegram/Discord rich-delivery internals, browser tab workers, worktree-subcommand removal, RPC durable model selection) — one genuinely applicable TUI bug was found and closed; the CLI empty-non-TTY-stdin fix (gjc #2586) was investigated and found already-correct by construction (jeo's one-shot gate forces true whenever stdin isn't a TTY, regardless of args, so the hang gjc fixed cannot occur here).
 - **[0.8.28]** (2026-07-16) — Improved the welcome UI's right-side table to display dynamic sections (What's New, Flow keys, Project pulse, and Session trail) matching gajae-code (gjc) >= 0.8.0 features.
-- **[0.8.27]** (2026-07-16) — Repeat-read recovery now survives both context-overflow and refusal-result elision without reopening mutating-call loops.
 
 See [CHANGELOG.md](CHANGELOG.md) for the full history.
 <!-- CHANGELOG:END -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jeo-code",
-  "version": "0.8.31",
+  "version": "0.8.32",
   "description": "Clean, highly optimized AI coding agent using spec-first loop",
   "type": "module",
   "main": "src/cli.ts",

package/src/tui/components/width.ts

@@ -58,6 +58,85 @@ export function charWidth(cp: number): number {
   }
   return 1;
 }
+const ZWJ = 0x200d;
+const VS15 = 0xfe0e; // variation selector: force TEXT (narrow) presentation
+const VS16 = 0xfe0f; // variation selector: force EMOJI (wide) presentation
+const FITZPATRICK_MIN = 0x1f3fb; // Emoji Modifier Fitzpatrick Type-1-2 .. Type-6
+const FITZPATRICK_MAX = 0x1f3ff;
+const KEYCAP_COMBINING = 0x20e3; // combining enclosing keycap (1️⃣, #️⃣, *️⃣)
+
+function isFitzpatrick(cp: number): boolean {
+  return cp >= FITZPATRICK_MIN && cp <= FITZPATRICK_MAX;
+}
+
+/** True for combining/zero-width marks that attach to a preceding base rather than
+ *  starting a new cluster on their own (diacritics etc.) — the zero-width branch of
+ *  `charWidth` MINUS variation selectors (VS15/VS16 are handled explicitly above,
+ *  since they change the CLUSTER's width rather than merely contributing 0 to it). */
+function isAttachableCombining(cp: number): boolean {
+  return (cp >= 0x0300 && cp <= 0x036f)
+    || (cp >= 0x1ab0 && cp <= 0x1aff)
+    || (cp >= 0x1dc0 && cp <= 0x1dff)
+    || (cp >= 0x20d0 && cp <= 0x20ff)
+    || cp === 0xfeff;
+}
+
+function codePointAndLength(s: string, i: number): { cp: number; length: number } {
+  const cp = s.codePointAt(i)!;
+  return { cp, length: cp > 0xffff ? 2 : 1 };
+}
+
+/**
+ * Resolve the visual CLUSTER starting at `s[i]` (not an SGR escape or tab — callers
+ * handle those separately) into its total consumed UTF-16 length and DISPLAY width,
+ * absorbing variation selectors, skin-tone modifiers, keycap combiners, combining
+ * marks, and ZWJ-joined sequences into ONE atomic unit (gjc parity: "preserve …
+ * Unicode grapheme semantics for … Korean tone marks, VS16 emoji presentation, ZWJ,
+ * keycaps, and emoji modifiers").
+ *
+ * Per-code-point summing (the old behavior) over- or under-counts every one of these:
+ * 👍🏽 (thumbs-up + Fitzpatrick modifier) summed to 4 columns where a terminal renders
+ * ONE 2-wide glyph; ❤️ (heart + VS16) summed to 1 where a terminal renders 2; a 4-person
+ * ZWJ family emoji summed to 8 where a terminal renders 2. Every one of those is a real,
+ * visible box-border/wrap misalignment ("깨짐") the instant such a sequence appears in a
+ * message — this collapses each sequence to the width a terminal ACTUALLY renders it at,
+ * atomically, so `truncateToWidth`/`wrapTextWithAnsi` also never split one in half at a
+ * boundary (this is a pragmatic subset of UAX #29 grapheme-cluster breaking scoped to
+ * the sequences a chat/coding TUI actually sees — not a general script-shaping engine).
+ */
+export function nextGraphemeCluster(s: string, i: number): { length: number; width: number } {
+  const base = codePointAndLength(s, i);
+  let width = charWidth(base.cp);
+  let len = base.length;
+  let j = i + base.length;
+  const peek = (): number => s.codePointAt(j) ?? -1;
+
+  if (peek() === VS15) { width = 1; len += 1; j += 1; }
+  else if (peek() === VS16) { width = 2; len += 1; j += 1; }
+
+  while (isFitzpatrick(peek())) {
+    const mod = codePointAndLength(s, j);
+    len += mod.length;
+    j += mod.length;
+    width = 2;
+  }
+
+  if (peek() === KEYCAP_COMBINING) { len += 1; j += 1; width = 2; }
+
+  while (isAttachableCombining(peek())) {
+    const mark = codePointAndLength(s, j);
+    len += mark.length;
+    j += mark.length;
+  }
+
+  if (peek() === ZWJ && j + 1 < s.length) {
+    const joined = nextGraphemeCluster(s, j + 1);
+    len += 1 + joined.length;
+    width = 2;
+  }
+
+  return { length: len, width };
+}
 
 /**
  * Visible display width of a string: SGR escapes count 0, tabs advance to the
@@ -81,9 +160,9 @@ export function visibleWidth(s: string): number {
       i += 1;
       continue;
     }
-    const cp = s.codePointAt(i)!;
-    w += charWidth(cp);
-    i += cp > 0xffff ? 2 : 1;
+    const cluster = nextGraphemeCluster(s, i);
+    w += cluster.width;
+    i += cluster.length;
   }
   return w;
 }
@@ -130,9 +209,9 @@ export function truncateToWidth(s: string, cols: number): string {
       cw = TAB_STOP - (w % TAB_STOP);
       chunk = "\t";
     } else {
-      const cp = s.codePointAt(i)!;
-      cw = charWidth(cp);
-      chunk = cp > 0xffff ? s.slice(i, i + 2) : s[i]!;
+      const cluster = nextGraphemeCluster(s, i);
+      cw = cluster.width;
+      chunk = s.slice(i, i + cluster.length);
     }
     if (w + cw > limit) break;
     out += chunk;