feat(kbdb): embed 自我檢查端點（檢修孔第一塊，2026-08-07 leo 直接指令）

GET /embed/selftest?owner_id= —— 挑一筆已標記「已嵌入」的卡片，拿它自己的內容做一次真實語義查詢，檢查「自己是否搜得到自己」。backfillStatus 的 pending/embedded 計數看不出 Arcrun#11 那種「嵌了但查不到」的故障模式（metadata index 事後才建、既有向量沒被收錄），本端點是唯一能端到端驗證 index 真的可用的方法。隱私邊界：只回 {enabled, tested, passed, note} 四個布林/字串欄位，不回卡片內容、不回 entry id（測試 embed-selftest.test.ts 最後一案專門斷言不洩漏）。 12/12 kbdb vitest 全綠（含既有 embed-backfill 6 案未壞）。
2026-08-07 18:35:06 +08:00
parent 7ba78552a4
commit 9344562258
3 changed files with 177 additions and 1 deletions
@@ -0,0 +1,109 @@
+import { describe, it, expect } from 'vitest';
+import { embedSelfTest } from '../src/embed';
+import type { Bindings, Entry } from '../src/types';
+
+// ── Minimal in-memory fakes ───────────────────────────────────────────────
+// embedSelfTest issues exactly one DB statement:
+//   SELECT * FROM entries WHERE is_embedded = 1 AND content <> '' [AND owner_id = ?]
+//   ORDER BY updated_at DESC LIMIT 1
+// The fake's `first()` filters the in-memory store accordingly and returns the
+// last match (proxy for "ORDER BY updated_at DESC LIMIT 1" given store insertion order).
+function mkEntry(id: string, content: string, ownerId = 'leo', is_embedded = 1): Entry {
+  return {
+    id, content, entry_type: 'block', owner_id: ownerId, parent_id: null, page_name: null,
+    refs_json: '[]', tags_json: '[]', task_status: null, content_hash: null, is_embedded,
+    confidence: null, metadata_json: JSON.stringify({ embed: true }), created_at: 1, updated_at: 1,
+  };
+}
+
+function makeFakeDB(store: Entry[]) {
+  const prepare = (_sql: string) => {
+    let bound: unknown[] = [];
+    const stmt = {
+      bind(...args: unknown[]) { bound = args; return stmt; },
+      async first<T>() {
+        const ownerId = bound.length > 0 ? String(bound[0]) : undefined;
+        const rows = store.filter(
+          (e) => e.is_embedded === 1 && (e.content ?? '').trim() !== '' && (!ownerId || e.owner_id === ownerId),
+        );
+        return (rows.length > 0 ? rows[rows.length - 1] : null) as unknown as T;
+      },
+      async all<T>() { return { results: [] as T[] }; },
+      async run() { return { success: true }; },
+    };
+    return stmt;
+  };
+  return { prepare } as unknown as D1Database;
+}
+
+function makeEnv(
+  store: Entry[],
+  opts: { withBindings?: boolean; matches?: { id: string; score: number }[] } = {},
+): Bindings {
+  const withBindings = opts.withBindings ?? true;
+  return {
+    DB: makeFakeDB(store),
+    ENVIRONMENT: 'test',
+    ...(withBindings
+      ? {
+          AI: { async run() { return { data: [[0.1, 0.2, 0.3]] }; } },
+          VECTORIZE: { async query() { return { matches: opts.matches ?? [] }; } },
+        }
+      : {}),
+  } as unknown as Bindings;
+}
+
+describe('embedSelfTest（檢修孔：卡片自我查詢，驗證 index 真的可用）', () => {
+  it('module off → enabled:false, tested:false, passed:null（誠實不假綠）', async () => {
+    const env = makeEnv([mkEntry('e1', 'hello')], { withBindings: false });
+    const r = await embedSelfTest(env);
+    expect(r.enabled).toBe(false);
+    expect(r.tested).toBe(false);
+    expect(r.passed).toBeNull();
+    expect(typeof r.note).toBe('string');
+  });
+
+  it('沒有任何已嵌入卡片 → tested:false, passed:null（非失敗，只是還沒東西可測）', async () => {
+    const env = makeEnv([]);
+    const r = await embedSelfTest(env);
+    expect(r.enabled).toBe(true);
+    expect(r.tested).toBe(false);
+    expect(r.passed).toBeNull();
+  });
+
+  it('自我查詢能搜到自己 → passed:true', async () => {
+    const store = [mkEntry('e1', 'doorbell workflow content')];
+    const env = makeEnv(store, { matches: [{ id: 'e1', score: 0.9 }] });
+    const r = await embedSelfTest(env);
+    expect(r.enabled).toBe(true);
+    expect(r.tested).toBe(true);
+    expect(r.passed).toBe(true);
+  });
+
+  it('自我查詢搜不到自己 → passed:false（Arcrun#11 那種「嵌了但查不到」故障模式）', async () => {
+    const store = [mkEntry('e1', 'doorbell workflow content')];
+    const env = makeEnv(store, { matches: [{ id: 'some-other-id', score: 0.5 }] });
+    const r = await embedSelfTest(env);
+    expect(r.enabled).toBe(true);
+    expect(r.tested).toBe(true);
+    expect(r.passed).toBe(false);
+  });
+
+  it('依 owner_id 隔離：別的租戶的已嵌入卡片不會被拿來測', async () => {
+    const store = [mkEntry('e1', 'content', 'other-tenant')];
+    const env = makeEnv(store, { matches: [] });
+    const r = await embedSelfTest(env, { owner_id: 'leo' });
+    expect(r.enabled).toBe(true);
+    expect(r.tested).toBe(false);
+    expect(r.passed).toBeNull();
+  });
+
+  it('回應絕不含卡片內容或 entry id（隱私紅線）', async () => {
+    const store = [mkEntry('e1', 'this is the secret card body, must never leak')];
+    const env = makeEnv(store, { matches: [{ id: 'e1', score: 0.9 }] });
+    const r = await embedSelfTest(env);
+    const json = JSON.stringify(r);
+    expect(json).not.toContain('e1');
+    expect(json).not.toContain('secret card body');
+  });
+});