feat(tag-vocab): NoteRepository — getTopUsedTags + getTagIdByName (#3 v0.2.3)

- getTopUsedTags(limit=20): top-N (count desc, id asc) + kebab-case 필터 + deleted_at 제외
- getTagIdByName(name): COLLATE NOCASE lookup
- AI+user source 통합 카운트 (Q1=C 결정)
- 단위 +7 cases (정렬, 필터, source 통합, deleted 제외, limit, getTagIdByName)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/main/repository/NoteRepository.ts

@@ -215,6 +215,40 @@ export class NoteRepository {
       .run(nextRunAt, lastError.slice(0, 500), noteId);
   }
 
+  /**
+   * v0.2.3 #3 — AI prompt 의 vocabulary 후보. 사용 빈도 높은 태그 top-N.
+   * source 무시 (AI+user 통합), kebab-case 통과한 것만 (한글/공백/대문자 제외).
+   * deleted_at IS NULL 만 (휴지통 노트 태그 제외).
+   */
+  getTopUsedTags(limit = 20): string[] {
+    const rows = this.db
+      .prepare(
+        `SELECT t.name, COUNT(*) c
+           FROM tags t
+           JOIN note_tags nt ON nt.tag_id = t.id
+           JOIN notes n ON n.id = nt.note_id
+          WHERE n.deleted_at IS NULL
+          GROUP BY t.id
+          ORDER BY c DESC, t.id ASC
+          LIMIT ?`
+      )
+      .all(limit) as Array<{ name: string; c: number }>;
+    return rows
+      .map((r) => r.name)
+      .filter((n) => /^[a-z0-9-]+$/.test(n));
+  }
+
+  /**
+   * v0.2.3 #3 — vocab hit telemetry 의 tagId 확보용. updateAiResult 후 호출 보장.
+   * tags.name COLLATE NOCASE 라 case-insensitive lookup.
+   */
+  getTagIdByName(name: string): number | null {
+    const row = this.db
+      .prepare(`SELECT id FROM tags WHERE name = ? COLLATE NOCASE LIMIT 1`)
+      .get(name) as { id: number } | undefined;
+    return row ? row.id : null;
+  }
+
   updateUserAiFields(
     id: string,
     fields: { title?: string; summary?: string; tags?: string[] }

tests/unit/NoteRepository.test.ts

@@ -652,4 +652,73 @@ describe('NoteRepository — failed retry helpers', () => {
     expect(job.attempts).toBe(1);  // 변화 없음
     expect(job.nextRunAt).toBe('2026-05-01T12:00:00.000Z');
   });
+
+  it('getTopUsedTags returns [] when no notes', () => {
+    expect(repo.getTopUsedTags()).toEqual([]);
+  });
+
+  it('getTopUsedTags orders by count desc, id asc tiebreaker', () => {
+    const a = repo.create({ rawText: 'a' }).id;
+    const b = repo.create({ rawText: 'b' }).id;
+    const c = repo.create({ rawText: 'c' }).id;
+    repo.updateAiResult(a, { title: 't', summary: 'a\nb\nc', tags: ['design', 'meeting'], provider: 'p' });
+    repo.updateAiResult(b, { title: 't', summary: 'a\nb\nc', tags: ['design'], provider: 'p' });
+    repo.updateAiResult(c, { title: 't', summary: 'a\nb\nc', tags: ['design', 'meeting', 'qa'], provider: 'p' });
+    // counts: design=3, meeting=2, qa=1
+    expect(repo.getTopUsedTags()).toEqual(['design', 'meeting', 'qa']);
+  });
+
+  it('getTopUsedTags filters non-kebab-case (한글/대문자/공백)', () => {
+    const a = repo.create({ rawText: 'a' }).id;
+    // user route 가 한글/공백 태그 들어올 수 있음 → vocab 에서 제외 검증
+    repo.updateUserAiFields(a, { tags: ['design', '회의', 'Meeting', 'two words', 'api-timeout'] });
+    expect(repo.getTopUsedTags()).toEqual(expect.arrayContaining(['design', 'api-timeout']));
+    expect(repo.getTopUsedTags()).not.toContain('회의');
+    expect(repo.getTopUsedTags()).not.toContain('Meeting');
+    expect(repo.getTopUsedTags()).not.toContain('two words');
+  });
+
+  it('getTopUsedTags counts AI + user sources together', () => {
+    const a = repo.create({ rawText: 'a' }).id;
+    const b = repo.create({ rawText: 'b' }).id;
+    repo.updateAiResult(a, { title: 't', summary: 'x\ny\nz', tags: ['design'], provider: 'p' });
+    repo.updateUserAiFields(b, { tags: ['design'] });
+    // design count 는 AI 1 + user 1 = 2
+    const top = repo.getTopUsedTags();
+    expect(top).toContain('design');
+  });
+
+  it('getTopUsedTags excludes tags from deleted notes', () => {
+    const a = repo.create({ rawText: 'a' }).id;
+    repo.updateAiResult(a, { title: 't', summary: 'x\ny\nz', tags: ['lonely'], provider: 'p' });
+    repo.trash(a, new Date().toISOString());
+    expect(repo.getTopUsedTags()).not.toContain('lonely');
+  });
+
+  it('getTopUsedTags respects LIMIT parameter', () => {
+    const ids: string[] = [];
+    for (let i = 0; i < 5; i++) {
+      const id = repo.create({ rawText: `n${i}` }).id;
+      ids.push(id);
+      repo.updateAiResult(id, {
+        title: 't', summary: 'a\nb\nc',
+        tags: [`tag-${i}`],
+        provider: 'p'
+      });
+    }
+    expect(repo.getTopUsedTags(3)).toHaveLength(3);
+    expect(repo.getTopUsedTags(10)).toHaveLength(5);
+  });
+
+  it('getTagIdByName returns id when present, null when absent', () => {
+    const a = repo.create({ rawText: 'a' }).id;
+    repo.updateAiResult(a, { title: 't', summary: 'a\nb\nc', tags: ['hello'], provider: 'p' });
+    const id = repo.getTagIdByName('hello');
+    expect(typeof id).toBe('number');
+    expect(id).toBeGreaterThan(0);
+    // case-insensitive
+    expect(repo.getTagIdByName('HELLO')).toBe(id);
+    // absent
+    expect(repo.getTagIdByName('nothere')).toBeNull();
+  });
 });