[v3.8.50] feat(ci): extend i18n glossary-consistency gate to ko (#8244)

* fix(dashboard): correct machine-translated Korean UI strings in ko.json

Fix 527 mistranslated values in the Korean locale, all verified against
the en.json source:

- Restore protected product/protocol names garbled by machine translation
  (응록→ngrok, 인류/인류학→Anthropic, 쌍둥이자리→Gemini, 반중력→Antigravity,
  꼬리비늘 깔때기→Tailscale Funnel, 진공→VACUUM, 우편번호→ZIP)
- Fix wrong-sense homonym translations (달리기→실행 중 for Running,
  장애인→비활성화됨 for Disabled, 열쇠→키 for Key, 안타→적중 for Hits,
  유물→아티팩트 for Artifacts, 건강검진→상태 확인 for Healthcheck)
- Repair translated identifiers that broke literal values (양말5→socks5,
  볼록-세션-id→convex-session-id, 채팅/완료→chat/completions,
  메시지/보내기→message/send JSON-RPC methods)
- Replace key-name dumps shipped as values ("Table Name", "Overview
  Title", "Cli Tools Redirect Title" etc.) with real Korean translations
- Unify ngrok casing (Ngrok→ngrok) and trailing punctuation with the
  English source; align terminology across fixes (공급자, 폴백, 사용자 정의)

All {placeholder} tokens, markdown, and protected terms preserved
verbatim; i18n UI coverage and ko validation gates pass.

* feat(ci): extend i18n glossary-consistency gate to ko

Follow-up to #8224 (ko.json mistranslation cleanup): the glossary gate
only checked zh-CN, leaving the Korean catalog unguarded against the
next machine-translation run reintroducing the garbage it fixed.

- Add scripts/i18n/glossary/ko.json: 9 canonical concepts (provider,
  fallback, running/disabled states, key, export, healthcheck, port,
  artifacts) plus protectedTermMistranslations for 10 verified garbled
  renderings (응록→ngrok, 인류→Anthropic, 쌍둥이자리→Gemini,
  반중력→Antigravity, 꼬리비늘→Tailscale, 진공→VACUUM, 양말5→socks5,
  우편번호→ZIP, 클로드→Claude, 옴니루트→OmniRoute)
- Extend check-glossary-consistency.mjs to merge per-locale
  protectedTermMistranslations from the glossary file with the legacy
  zh-CN KNOWN_MISTRANSLATIONS map (behavior for zh-CN unchanged)
- Add ngrok/Anthropic/Claude/Gemini/Antigravity/Tailscale/VACUUM/
  socks5/ZIP to protected-terms.json
- Wire --locale=ko into the i18n-glossary CI job and add the
  i18n:check-glossary:ko npm script
- Tests: merge semantics (3 new unit tests), #8224 regression guards
  for src + bin/cli ko catalogs, and real-file pass assertions for ko

Every enforced synonym/mistranslation was verified to have zero
occurrences in both real ko catalogs; collision-prone candidates
(안타 ⊂ 안타깝게도, 배우 ⊂ 배우기) were deliberately excluded.

.github/workflows/ci.yml

@@ -501,11 +501,13 @@ jobs:
           BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
         run: node scripts/i18n/check-ui-value-drift.mjs
 
-  # #8038: cheap single-locale glossary/protected-terms consistency gate —
+  # #8038: cheap glossary/protected-terms consistency gate —
   # complements i18n-ui-coverage (key parity) and the ICU `i18n` job below
   # without needing app-boot/Playwright infra. Same gating as i18n-ui-coverage.
+  # ko added after the #8224 ko.json mistranslation cleanup so the fixed
+  # terminology cannot silently regress on the next machine-translation run.
   i18n-glossary-zhcn:
-    name: i18n Glossary (zh-CN)
+    name: i18n Glossary (zh-CN, ko)
     runs-on: ubuntu-latest
     needs: changes
     if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && (needs.changes.outputs.i18n == 'true' || needs.changes.outputs.code == 'true')) }}
@@ -1334,7 +1336,7 @@ jobs:
           echo "| Lint | $(status '${{ needs.lint.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| Docs Sync (Strict) | $(status '${{ needs.docs-sync-strict.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| i18n UI Coverage | $(status '${{ needs.i18n-ui-coverage.result }}') |" >> "$GITHUB_STEP_SUMMARY"
-          echo "| i18n Glossary (zh-CN) | $(status '${{ needs.i18n-glossary-zhcn.result }}') |" >> "$GITHUB_STEP_SUMMARY"
+          echo "| i18n Glossary (zh-CN, ko) | $(status '${{ needs.i18n-glossary-zhcn.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| PR Test Policy | $(status '${{ needs.pr-test-policy.result }}') |" >> "$GITHUB_STEP_SUMMARY"
           echo "| SonarQube | $(status '${{ needs.sonarqube.result }}') |" >> "$GITHUB_STEP_SUMMARY"
 

package.json

@@ -147,6 +147,7 @@
     "i18n:check-value-drift": "node scripts/i18n/check-ui-value-drift.mjs",
     "i18n:check-value-drift:warn": "node scripts/i18n/check-ui-value-drift.mjs --warn",
     "i18n:check-glossary": "node scripts/i18n/check-glossary-consistency.mjs",
+    "i18n:check-glossary:ko": "node scripts/i18n/check-glossary-consistency.mjs --locale=ko",
     "check:node-runtime": "node --import tsx scripts/check/check-supported-node-runtime.ts",
     "check:pack-artifact": "node --import tsx scripts/build/validate-pack-artifact.ts",
     "check:pack-boot": "node scripts/check/check-pack-boot.mjs",

scripts/i18n/check-glossary-consistency.mjs

@@ -10,10 +10,13 @@
  *   - protected-term-altered: a value renders a protected product/provider/
  *     protocol/CLI/env identifier (scripts/i18n/glossary/protected-terms.json)
  *     using a known incorrect translation instead of leaving it verbatim.
+ *     Known incorrect renderings come from the legacy KNOWN_MISTRANSLATIONS
+ *     map below (zh-CN) merged with the optional per-locale
+ *     `protectedTermMistranslations` object in the locale's glossary file (ko).
  *
  * Usage:
  *   node scripts/i18n/check-glossary-consistency.mjs                 # zh-CN, exit 1 on drift
- *   node scripts/i18n/check-glossary-consistency.mjs --locale=zh-CN
+ *   node scripts/i18n/check-glossary-consistency.mjs --locale=ko
  *   node scripts/i18n/check-glossary-consistency.mjs --json
  *   node scripts/i18n/check-glossary-consistency.mjs --report        # print, always exit 0
  */
@@ -30,6 +33,9 @@ const MESSAGES_DIR = path.join(ROOT, "src", "i18n", "messages");
 const GLOSSARY_DIR = path.join(SCRIPT_DIR, "glossary");
 const LOG_PREFIX = "[i18n-glossary]";
 
+// Legacy zh-CN map of known incorrect renderings for protected terms — newer
+// locales (ko) keep theirs in `protectedTermMistranslations` inside their
+// scripts/i18n/glossary/<locale>.json instead of growing this constant.
 // Small, maintained map of known incorrect renderings for protected terms —
 // identifiers that must survive translation verbatim. NOT exhaustive by
 // design (a full back-translation model is out of scope for a static gate),
@@ -97,10 +103,16 @@ export function checkGlossaryConsistency(localeMessages, glossary, protectedTerm
     }
   }
 
+  const localeMistranslations = isPlainObject(glossary?.protectedTermMistranslations)
+    ? glossary.protectedTermMistranslations
+    : {};
   const protectedList = Array.isArray(protectedTerms) ? protectedTerms : [];
   for (const term of protectedList) {
-    const badRenderings = KNOWN_MISTRANSLATIONS[term];
-    if (!badRenderings || badRenderings.length === 0) continue;
+    const fromGlossary = Array.isArray(localeMistranslations[term])
+      ? localeMistranslations[term]
+      : [];
+    const badRenderings = [...(KNOWN_MISTRANSLATIONS[term] || []), ...fromGlossary];
+    if (badRenderings.length === 0) continue;
     for (const bad of badRenderings) {
       for (const leaf of leaves) {
         if (leaf.value.includes(bad)) {

scripts/i18n/glossary/ko.json

@@ -0,0 +1,55 @@
+{
+  "version": 1,
+  "locale": "ko",
+  "description": "Canonical ko terminology for recurring OmniRoute concepts. Consumed by scripts/i18n/check-glossary-consistency.mjs. Each concept lists the canonical translation plus any non-canonical synonym that is actively normalized (drift enforced by the consistency gate). Concepts whose `synonyms` array is empty are seeded for documentation only — the catalog still uses more than one legitimate rendering for them today (e.g. 공급자/제공자, 폴백/대체), so enforcement is deferred to a follow-up normalization pass. Every enforced synonym and mistranslation below was verified to have zero legitimate occurrences in the real src + bin/cli ko catalogs before being added (collision policy mirrors the KNOWN_MISTRANSLATIONS note in the checker script — e.g. 안타 (Hits) is deliberately NOT enforced because it is a substring of the legitimate 안타깝게도).",
+  "terms": {
+    "provider": {
+      "canonical": "공급자",
+      "synonyms": []
+    },
+    "fallback": {
+      "canonical": "폴백",
+      "synonyms": []
+    },
+    "running (status)": {
+      "canonical": "실행 중",
+      "synonyms": ["달리기"]
+    },
+    "disabled (status)": {
+      "canonical": "비활성화됨",
+      "synonyms": ["장애인"]
+    },
+    "key (credential)": {
+      "canonical": "키",
+      "synonyms": ["열쇠"]
+    },
+    "export (action)": {
+      "canonical": "내보내기",
+      "synonyms": ["수출"]
+    },
+    "healthcheck": {
+      "canonical": "상태 확인",
+      "synonyms": ["건강검진"]
+    },
+    "port (network)": {
+      "canonical": "포트",
+      "synonyms": ["항구"]
+    },
+    "artifacts": {
+      "canonical": "아티팩트",
+      "synonyms": ["유물"]
+    }
+  },
+  "protectedTermMistranslations": {
+    "ngrok": ["응록"],
+    "Anthropic": ["인류", "앤트로픽"],
+    "Claude": ["클로드"],
+    "Gemini": ["쌍둥이자리"],
+    "Antigravity": ["반중력"],
+    "OmniRoute": ["옴니루트"],
+    "Tailscale": ["꼬리비늘"],
+    "VACUUM": ["진공"],
+    "socks5": ["양말5"],
+    "ZIP": ["우편번호"]
+  }
+}

scripts/i18n/glossary/protected-terms.json

@@ -1,5 +1,5 @@
 {
-  "description": "Product/provider/model/protocol/header/CLI/env/identifier names that must appear verbatim (untranslated) inside any zh-CN localized string that mentions them. Distinct from untranslatable-keys.json, which excludes whole KEYS from drift checks at key-granularity; this list is consumed by scripts/i18n/check-glossary-consistency.mjs to flag a VALUE that mentions the concept but altered/translated the protected term itself.",
+  "description": "Product/provider/model/protocol/header/CLI/env/identifier names that must appear verbatim (untranslated) inside any localized string that mentions them (gated locales: zh-CN, ko). Distinct from untranslatable-keys.json, which excludes whole KEYS from drift checks at key-granularity; this list is consumed by scripts/i18n/check-glossary-consistency.mjs to flag a VALUE that mentions the concept but altered/translated the protected term itself. Known incorrect renderings live per-locale: legacy zh-CN entries in the checker's KNOWN_MISTRANSLATIONS map, newer locales in `protectedTermMistranslations` inside scripts/i18n/glossary/<locale>.json.",
   "terms": [
     "OmniRoute",
     "OAuth",
@@ -20,6 +20,15 @@
     "CLI",
     "Docker",
     "Electron",
-    "Playwright"
+    "Playwright",
+    "ngrok",
+    "Anthropic",
+    "Claude",
+    "Gemini",
+    "Antigravity",
+    "Tailscale",
+    "VACUUM",
+    "socks5",
+    "ZIP"
   ]
 }

tests/unit/i18n-glossary-consistency-check.test.ts

@@ -97,6 +97,78 @@ test("regression: bin/cli/locales/zh-CN.json no longer contains 提供商", () =
   assert.equal(raw.includes("提供商"), false);
 });
 
+test("glossary-file protectedTermMistranslations are merged into the protected-term check", () => {
+  const koGlossary = {
+    version: 1,
+    locale: "ko",
+    terms: {},
+    protectedTermMistranslations: {
+      ngrok: ["응록"],
+    },
+  };
+  const messages = { endpoint: { ngrokTitle: "응록 터널" } };
+  const { violations } = checkGlossaryConsistency(messages, koGlossary, ["ngrok"]);
+  assert.equal(violations.length, 1);
+  assert.equal(violations[0].type, "protected-term-altered");
+  assert.equal(violations[0].term, "ngrok");
+  assert.equal(violations[0].found, "응록");
+});
+
+test("protectedTermMistranslations for a term absent from protected-terms.json are inert", () => {
+  const koGlossary = {
+    version: 1,
+    locale: "ko",
+    terms: {},
+    protectedTermMistranslations: {
+      ngrok: ["응록"],
+    },
+  };
+  const messages = { endpoint: { ngrokTitle: "응록 터널" } };
+  // "ngrok" not in the protected list → the glossary entry alone must not fire.
+  const { violations } = checkGlossaryConsistency(messages, koGlossary, ["DATA_DIR"]);
+  assert.deepEqual(violations, []);
+});
+
+test("legacy KNOWN_MISTRANSLATIONS still fire when the glossary has no mistranslation map", () => {
+  const messages = { settings: { dataDirHint: "存储在 数据目录 中" } };
+  const { violations } = checkGlossaryConsistency(messages, glossary, ["DATA_DIR"]);
+  assert.equal(violations.length, 1);
+  assert.equal(violations[0].term, "DATA_DIR");
+});
+
+// Regression guard for the #8224 ko.json mistranslation cleanup: the garbled
+// product names and wrong-sense homonyms must not reappear in either ko catalog
+// (e.g. via a future machine-translation run).
+for (const badTerm of ["응록", "인류", "쌍둥이자리", "반중력", "달리기", "장애인"]) {
+  test(`regression: src/i18n/messages/ko.json no longer contains ${badTerm}`, () => {
+    const raw = readFileSync(path.join(ROOT, "src/i18n/messages/ko.json"), "utf8");
+    assert.equal(raw.includes(badTerm), false);
+  });
+
+  test(`regression: bin/cli/locales/ko.json no longer contains ${badTerm}`, () => {
+    const raw = readFileSync(path.join(ROOT, "bin/cli/locales/ko.json"), "utf8");
+    assert.equal(raw.includes(badTerm), false);
+  });
+}
+
+test("real ko.json + real ko glossary + real protected terms pass the gate", () => {
+  const realMessages = JSON.parse(
+    readFileSync(path.join(ROOT, "src/i18n/messages/ko.json"), "utf8")
+  );
+  const realGlossary = JSON.parse(
+    readFileSync(path.join(ROOT, "scripts/i18n/glossary/ko.json"), "utf8")
+  );
+  const realProtected = JSON.parse(
+    readFileSync(path.join(ROOT, "scripts/i18n/glossary/protected-terms.json"), "utf8")
+  );
+  const { violations } = checkGlossaryConsistency(
+    realMessages,
+    realGlossary,
+    realProtected.terms
+  );
+  assert.deepEqual(violations, []);
+});
+
 test("real zh-CN.json + real glossary + real protected terms pass the gate", () => {
   const realMessages = JSON.parse(
     readFileSync(path.join(ROOT, "src/i18n/messages/zh-CN.json"), "utf8")