fix(kbdb): D69 節流世代核對＋標庫共用 D1 額度，補「挑哪一批」的統一 SelectionCriteria（Arcrun#85）
leo 逐行複核 fix/embed-backfill-d68 後點出的破口＋二次裁決（票上全文見 Leo/Arcrun#85）： 一、向量化優先序（今天寫的立刻／本週在跑的先跑／有查詢紀錄的庫優先／半年前慢慢跑）表達 不出來——策略要能從外面（工作流）指定，不能焊死在資料層。新增 embed.ts 的 `SelectionCriteria`（owner_id/source/library/since/until）,backfillEmbeddings 與 reconcileEmbedGeneration 共用同一套形狀；「按庫」那一層現在有資料可用即可運作（見下）。 二、世代核對（reconcileEmbedGeneration）不打 AI 但逐筆寫 D1，47 萬筆候選 ≈ 4.7 倍 D1 100,000 rows/日免費額度，先前零保護。新增 actions/maintenance-quota.ts（單一 entries 列/日的共用計數器，精神同 execution-log.ts／embed.ts 既有慣例，不新增表）。 三、leo 二度裁決：「標庫」與「時間分層」其實是一件事，判定標準要從第一天同時容納兩者， 不能先做一半再回頭改。新增 actions/library-backfill.ts 的 backfillEntryLibraryTags—— 呼叫端（ingest／daemon／Arcrun#87）決定要貼哪個庫、用 page_names（Gitea 原稿卡名精準 點名，leo 定案的正解）或 source_prefix/page_name_prefix 過渡 fallback 篩選候選，base 只負責安全、節流地寫入。owner_id 刻意必填（leo 點出「補錯 owner 等於白做」——實查卡片 掛在 owner_id=bfezv28v，換成 'leo' 查卻是空的）。 D69：reconcile 與標庫 backfill 共用同一顆「今天還剩多少 D1 寫入額度」計數器（不共用的話 其中一個會把另一個的閘繞過去）；新增 POST /entries/backfill-library + GET .../status， 擴充 POST /embed/backfill 與 /embed/reconcile 吃 library/since/until 參數。 測試：92 → 39 個新增/擴充案例覆蓋 since/until/library 篩選、reconcile 額度真的擋 （含「拿掉 cap 會變紅」反向驗證）、標庫 backfill 冪等/owner_id 必填/page_names 精準比對、 以及兩個操作共用同一顆額度計數器的跨模組驗證（雙向：先 reconcile 耗盡再標庫、反之亦然）。 kbdb 全套 192 個測試綠燈，tsc --noEmit 除既有 auth.test.ts 舊缺陷外無新增錯誤。 紅線：未併 main、未部署、未動任何實例的 is_embedded 旗標（只在本地 SQLite 測試治具跑過）。 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
uncle6me-web
@@ -83,7 +83,7 @@ async function countUsageRows(db: D1Database): Promise<{ id: string; entry_type:
|
||||
return res.results;
|
||||
}
|
||||
|
||||
function makeEnv(db: D1Database, opts: { withBindings?: boolean; dailyLimit?: string } = {}): Bindings {
|
||||
function makeEnv(db: D1Database, opts: { withBindings?: boolean; dailyLimit?: string; maintenanceLimit?: string } = {}): Bindings {
|
||||
const withBindings = opts.withBindings ?? true;
|
||||
const upserts: { id: string }[] = [];
|
||||
const aiCalls: string[][] = [];
|
||||
@@ -93,6 +93,7 @@ function makeEnv(db: D1Database, opts: { withBindings?: boolean; dailyLimit?: st
|
||||
DB: db,
|
||||
ENVIRONMENT: 'test',
|
||||
EMBED_BACKFILL_DAILY_LIMIT: opts.dailyLimit,
|
||||
KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: opts.maintenanceLimit,
|
||||
...(withBindings
|
||||
? {
|
||||
AI: {
|
||||
@@ -366,6 +367,102 @@ describe('D68③：leo21c 資料還原情境——is_embedded=1 但對應已退
|
||||
insertEntry(db, { id: 'e1', content: 'x', created_at: 1, is_embedded: 1 });
|
||||
const env = makeEnv(db, { withBindings: false });
|
||||
const r = await reconcileEmbedGeneration(env);
|
||||
expect(r).toEqual({ enabled: false, checked: 0, confirmed_current: 0, reset_to_pending: 0, remaining: 0 });
|
||||
expect(r).toEqual({
|
||||
enabled: false, checked: 0, confirmed_current: 0, reset_to_pending: 0, remaining: 0,
|
||||
scanned: 0, quota_limit: 0, quota_used_today: 0, quota_exceeded: false,
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85 D69：reconcile 的 D1 寫入額度（與標庫 backfill 共用的計數器）', () => {
|
||||
it('額度耗盡後 reconcile 停手：不再寫 D1，quota_exceeded=true', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'r1', content: 'c1', created_at: 1, is_embedded: 1, content_hash: null });
|
||||
insertEntry(db, { id: 'r2', content: 'c2', created_at: 2, is_embedded: 1, content_hash: null });
|
||||
insertEntry(db, { id: 'r3', content: 'c3', created_at: 3, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db, { maintenanceLimit: '2' }); // 上限比候選數（3）小
|
||||
seedVectorized(env, ['r1', 'r2', 'r3']); // 全在現行 index（confirmed_current 路徑，仍是 D1 write）
|
||||
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.scanned).toBe(3); // 掃到 3 筆候選
|
||||
expect(r.checked).toBe(2); // 但只處理了額度允許的 2 筆
|
||||
expect(r.confirmed_current).toBe(2);
|
||||
expect(r.quota_limit).toBe(2);
|
||||
expect(r.quota_used_today).toBe(2);
|
||||
expect(r.quota_exceeded).toBe(true);
|
||||
|
||||
// 只有 2 筆真的被寫回 content_hash（最新的兩筆，ORDER BY created_at DESC）
|
||||
const rows = await listAllRows(db);
|
||||
const byId = Object.fromEntries(rows.map((x) => [x.id, x]));
|
||||
expect(byId.r3.content_hash).toBe(CURRENT_MODEL);
|
||||
expect(byId.r2.content_hash).toBe(CURRENT_MODEL);
|
||||
expect(byId.r1.content_hash).toBe(null); // 額度用完，沒輪到它
|
||||
|
||||
// 再跑一次（同一天）：額度已用完，checked=0
|
||||
const r2 = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r2.checked).toBe(0);
|
||||
expect(r2.quota_exceeded).toBe(true);
|
||||
});
|
||||
|
||||
it('額度上限被拿掉時本測試會變紅（反向驗證，同 D68② 手法）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db, { id: `r${i}`, content: `c${i}`, created_at: i, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db); // 不設 maintenanceLimit → 用預設 20000，遠大於 5，全部應被處理
|
||||
seedVectorized(env, ['r1', 'r2', 'r3', 'r4', 'r5']);
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.checked).toBe(5);
|
||||
expect(r.quota_exceeded).toBe(false);
|
||||
|
||||
const db2 = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db2, { id: `r${i}`, content: `c${i}`, created_at: i, is_embedded: 1, content_hash: null });
|
||||
const env2 = makeEnv(db2, { maintenanceLimit: '2' });
|
||||
seedVectorized(env2, ['r1', 'r2', 'r3', 'r4', 'r5']);
|
||||
const r2 = await reconcileEmbedGeneration(env2, { limit: 100 });
|
||||
expect(r2.checked).toBe(2);
|
||||
expect(r2.checked).not.toBe(r.checked); // 有 cap vs 沒 cap 必須不同，否則 cap 沒在作用
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85：「挑哪一批」可以從外面指定（SelectionCriteria：since/until/library）', () => {
|
||||
it('backfillEmbeddings 帶 since/until 只補時間窗內的候選', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'too-old', content: 'x', created_at: 100 });
|
||||
insertEntry(db, { id: 'in-window-1', content: 'y', created_at: 500 });
|
||||
insertEntry(db, { id: 'in-window-2', content: 'z', created_at: 800 });
|
||||
insertEntry(db, { id: 'too-new', content: 'w', created_at: 1500 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const r = await backfillEmbeddings(env, { limit: 100, since: 400, until: 1000 });
|
||||
expect(r.processed).toBe(2);
|
||||
expect((await listEmbeddedIds(db)).sort()).toEqual(['in-window-1', 'in-window-2']);
|
||||
});
|
||||
|
||||
it('backfillEmbeddings 帶 library 只補該庫的候選（未標記歸 general）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'finance-1', content: 'x', created_at: 1, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'hr-1', content: 'y', created_at: 2, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
insertEntry(db, { id: 'untagged', content: 'z', created_at: 3 }); // 無 library → general
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const r = await backfillEmbeddings(env, { limit: 100, library: 'finance' });
|
||||
expect(r.processed).toBe(1);
|
||||
expect(await listEmbeddedIds(db)).toEqual(['finance-1']);
|
||||
|
||||
const r2 = await backfillEmbeddings(env, { limit: 100, library: 'general' });
|
||||
expect(r2.processed).toBe(1);
|
||||
expect((await listEmbeddedIds(db)).sort()).toEqual(['finance-1', 'untagged']);
|
||||
});
|
||||
|
||||
it('reconcile 帶 since/until/library 同樣受篩選（同一套 SelectionCriteria，非獨立實作）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'old', content: 'x', created_at: 1, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'new', content: 'y', created_at: 100, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'other-lib', content: 'z', created_at: 100, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
const env = makeEnv(db);
|
||||
seedVectorized(env, ['old', 'new', 'other-lib']);
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100, library: 'finance', since: 50 });
|
||||
expect(r.checked).toBe(1);
|
||||
const row = await getRow(db, 'new');
|
||||
expect(row!.content_hash).toBe(CURRENT_MODEL);
|
||||
const oldRow = await getRow(db, 'old');
|
||||
expect(oldRow!.content_hash).toBe(null); // 在時間窗外，沒被動到
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,230 @@
|
||||
// 標庫 backfill（Arcrun#85 二次裁決，2026-08-11）測試。
|
||||
//
|
||||
// 測試策略比照 embed-backfill.test.ts：真 SQLite（node:sqlite）套 migrations/0001_base.sql
|
||||
// 原檔，驗真實 SQL 語意（json_set／WHERE／LIMIT），不是「以為 SQL 長這樣」。
|
||||
//
|
||||
// 覆蓋：
|
||||
// 1. 只補「符合條件、目前未標記 library」的候選；已標記的不動（冪等）
|
||||
// 2. owner_id 必填（缺了要拋錯，防「補錯 owner 等於白做」——2026-08-11 leo 直令）
|
||||
// 3. source_prefix／page_name_prefix／since／until 篩選條件真的在篩
|
||||
// 4. 與 reconcileEmbedGeneration 共用同一顆每日 D1 寫入額度（D69 的核心訴求：
|
||||
// 補標不能把世代核對的閘繞過去，反之亦然）
|
||||
//
|
||||
// 本檔在 kbdb/tests/（牆外），依 D38 kbdb-api-wall-guard 規則，直接對 SQLite 治具下 SQL
|
||||
// 的行集中在 helper（測試治具本身，非牆外業務邏輯繞過 API，每行標 kbdb-sql-ok 留痕）。
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { DatabaseSync } from 'node:sqlite';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { backfillEntryLibraryTags, libraryBackfillStatus } from '../src/actions/library-backfill';
|
||||
import { reconcileEmbedGeneration } from '../src/embed';
|
||||
import type { Bindings, Entry, EntryType } from '../src/types';
|
||||
|
||||
// ── node:sqlite → D1 介面最小 adapter（同 embed-backfill.test.ts 手法）──────────────
|
||||
function makeSqliteD1(): D1Database {
|
||||
const raw = new DatabaseSync(':memory:');
|
||||
raw.exec(readFileSync(new URL('../migrations/0001_base.sql', import.meta.url), 'utf8')); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）套 migration 原檔
|
||||
function stmt(sql: string, params: unknown[]) {
|
||||
const s = {
|
||||
bind(...args: unknown[]) { return stmt(sql, args); },
|
||||
async all<T>() { return { results: raw.prepare(sql).all(...params) as T[] }; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async first<T>() { return (raw.prepare(sql).get(...params) ?? null) as T | null; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async run() {
|
||||
const r = raw.prepare(sql).run(...params); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim），非牆外業務邏輯繞過 API
|
||||
return { success: true, meta: { changes: r.changes } };
|
||||
},
|
||||
};
|
||||
return s;
|
||||
}
|
||||
return { prepare: (sql: string) => stmt(sql, []) } as unknown as D1Database;
|
||||
}
|
||||
|
||||
function insertEntry(db: D1Database, e: Partial<Entry> & { id: string; created_at: number }): void {
|
||||
const sql = `INSERT INTO entries (id, content, entry_type, owner_id, content_hash, is_embedded, metadata_json, page_name, created_at, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`;
|
||||
db.prepare(sql).bind( // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）灌測試資料
|
||||
e.id,
|
||||
e.content === undefined ? 'x' : e.content,
|
||||
(e.entry_type ?? 'block') as EntryType,
|
||||
e.owner_id ?? 'bfezv28v',
|
||||
e.content_hash ?? null,
|
||||
e.is_embedded ?? 0,
|
||||
e.metadata_json === undefined ? null : e.metadata_json,
|
||||
e.page_name ?? null,
|
||||
e.created_at,
|
||||
e.created_at,
|
||||
).run();
|
||||
}
|
||||
|
||||
async function getLibrary(db: D1Database, id: string): Promise<string | null> {
|
||||
const row = await db.prepare("SELECT json_extract(metadata_json, '$.library') AS library FROM entries WHERE id = ?").bind(id).first<{ library: string | null }>(); // kbdb-sql-ok：測試治具讀回斷言用
|
||||
return row?.library ?? null;
|
||||
}
|
||||
|
||||
function makeEnv(db: D1Database, opts: { maintenanceLimit?: string } = {}): Bindings {
|
||||
return {
|
||||
DB: db,
|
||||
ENVIRONMENT: 'test',
|
||||
KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: opts.maintenanceLimit,
|
||||
} as unknown as Bindings;
|
||||
}
|
||||
|
||||
describe('backfillEntryLibraryTags — 基本行為', () => {
|
||||
it('只標記符合條件、目前未標記 library 的候選；已標記的不動', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 }); // 無 metadata_json → 未標記
|
||||
insertEntry(db, { id: 'b', created_at: 2, metadata_json: JSON.stringify({}) }); // 有 metadata_json 但無 library
|
||||
insertEntry(db, { id: 'c', created_at: 3, metadata_json: JSON.stringify({ library: 'hr' }) }); // 已標記，不該被動
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r.tagged).toBe(2);
|
||||
expect(r.remaining).toBe(0);
|
||||
expect(await getLibrary(db, 'a')).toBe('finance');
|
||||
expect(await getLibrary(db, 'b')).toBe('finance');
|
||||
expect(await getLibrary(db, 'c')).toBe('hr'); // 未被覆寫
|
||||
});
|
||||
|
||||
it('冪等：全部標記完後重跑不再處理', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
const env = makeEnv(db);
|
||||
await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
const r2 = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r2.tagged).toBe(0);
|
||||
expect(r2.remaining).toBe(0);
|
||||
});
|
||||
|
||||
it('owner_id 缺了要拋錯（防補錯 owner 等於白做，2026-08-11 leo 直令）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
const env = makeEnv(db);
|
||||
await expect(
|
||||
backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: '' }),
|
||||
).rejects.toThrow(/owner_id/);
|
||||
});
|
||||
|
||||
it('library 缺了要拋錯', async () => {
|
||||
const db = makeSqliteD1();
|
||||
const env = makeEnv(db);
|
||||
await expect(
|
||||
backfillEntryLibraryTags(db, env, { library: '', owner_id: 'bfezv28v' }),
|
||||
).rejects.toThrow(/library/);
|
||||
});
|
||||
|
||||
it('owner_id 篩選：只動指定租戶的資料，其他租戶不受影響（跨租戶隔離）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'mine', created_at: 1, owner_id: 'bfezv28v' });
|
||||
insertEntry(db, { id: 'theirs', created_at: 2, owner_id: 'someone-else' });
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r.tagged).toBe(1);
|
||||
expect(await getLibrary(db, 'mine')).toBe('finance');
|
||||
expect(await getLibrary(db, 'theirs')).toBe(null); // 別的租戶完全沒被動到
|
||||
});
|
||||
|
||||
it('source_prefix／page_name_prefix／since／until 篩選真的在篩', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'match-source', created_at: 500, metadata_json: JSON.stringify({ source: 'gitea://Leo/kb/foo.md' }) });
|
||||
insertEntry(db, { id: 'other-source', created_at: 500, metadata_json: JSON.stringify({ source: 'gitea://Leo/other/bar.md' }) });
|
||||
const r1 = await backfillEntryLibraryTags(db, makeEnv(db), {
|
||||
library: 'kb', owner_id: 'bfezv28v', source_prefix: 'gitea://Leo/kb/',
|
||||
});
|
||||
expect(r1.tagged).toBe(1);
|
||||
expect(await getLibrary(db, 'match-source')).toBe('kb');
|
||||
expect(await getLibrary(db, 'other-source')).toBe(null);
|
||||
|
||||
const db2 = makeSqliteD1();
|
||||
insertEntry(db2, { id: 'in-window', created_at: 500, page_name: 'wiki/foo' });
|
||||
insertEntry(db2, { id: 'out-window', created_at: 5000, page_name: 'wiki/bar' });
|
||||
const r2 = await backfillEntryLibraryTags(db2, makeEnv(db2), {
|
||||
library: 'wiki', owner_id: 'bfezv28v', page_name_prefix: 'wiki/', since: 0, until: 1000,
|
||||
});
|
||||
expect(r2.tagged).toBe(1);
|
||||
expect(await getLibrary(db2, 'in-window')).toBe('wiki');
|
||||
expect(await getLibrary(db2, 'out-window')).toBe(null);
|
||||
});
|
||||
|
||||
it('page_names 精準比對（leo 定案的正解：拿 Gitea 原稿卡名逐批遍歷點名）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1, page_name: 'card-alpha' });
|
||||
insertEntry(db, { id: 'b', created_at: 2, page_name: 'card-beta' });
|
||||
insertEntry(db, { id: 'c', created_at: 3, page_name: 'card-gamma' }); // 不在點名清單內
|
||||
const r = await backfillEntryLibraryTags(db, makeEnv(db), {
|
||||
library: 'kb', owner_id: 'bfezv28v', page_names: ['card-alpha', 'card-beta'],
|
||||
});
|
||||
expect(r.tagged).toBe(2);
|
||||
expect(await getLibrary(db, 'a')).toBe('kb');
|
||||
expect(await getLibrary(db, 'b')).toBe('kb');
|
||||
expect(await getLibrary(db, 'c')).toBe(null); // 沒被點名，不動
|
||||
});
|
||||
|
||||
it('libraryBackfillStatus 回報待補標筆數', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
insertEntry(db, { id: 'b', created_at: 2, metadata_json: JSON.stringify({ library: 'hr' }) });
|
||||
const s = await libraryBackfillStatus(db, { owner_id: 'bfezv28v' });
|
||||
expect(s.pending).toBe(1); // 只有 'a' 未標記
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85 D69：標庫 backfill 與 reconcile 共用同一顆 D1 每日寫入額度', () => {
|
||||
it('reconcile 先消耗額度 → 標庫 backfill 看到的剩餘額度真的變少', async () => {
|
||||
const db = makeSqliteD1();
|
||||
// reconcile 的候選：is_embedded=1 且 content_hash 非現行世代
|
||||
// library 已標記（'hr'）→ 不會被下面的標庫 backfill 選中，讓兩種候選池互不重疊，
|
||||
// 才能單純驗證「額度共用」本身，不被「標庫候選也吃到 reconcile 資料」干擾。
|
||||
insertEntry(db, { id: 'reconcile-1', created_at: 1, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
insertEntry(db, { id: 'reconcile-2', created_at: 2, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
// 標庫的候選：未標記 library
|
||||
insertEntry(db, { id: 'tag-1', created_at: 3 });
|
||||
insertEntry(db, { id: 'tag-2', created_at: 4 });
|
||||
insertEntry(db, { id: 'tag-3', created_at: 5 });
|
||||
|
||||
const maintenanceLimit = '3'; // 5 個候選（2 reconcile + 3 tag），額度只夠 3 個
|
||||
const reconcileEnv = {
|
||||
DB: db, ENVIRONMENT: 'test', KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: maintenanceLimit,
|
||||
AI: { async run() { return { data: [] }; } },
|
||||
VECTORIZE: {
|
||||
async getByIds(ids: string[]) { return ids.map((id) => ({ id, values: [0.1] })); }, // 全部視為現行 index 已有
|
||||
async upsert() { return { count: 0 }; },
|
||||
},
|
||||
} as unknown as Bindings;
|
||||
|
||||
// 先跑 reconcile：吃掉 2 筆額度（3 - 2 = 1 剩）
|
||||
const rc = await reconcileEmbedGeneration(reconcileEnv, { limit: 100 });
|
||||
expect(rc.checked).toBe(2);
|
||||
expect(rc.quota_used_today).toBe(2);
|
||||
|
||||
// 標庫 backfill 用同一顆 DB／同一個每日上限：只剩 1 筆額度可用，即使候選有 3 筆
|
||||
const tagEnv = makeEnv(db, { maintenanceLimit });
|
||||
const tagResult = await backfillEntryLibraryTags(db, tagEnv, { library: 'general', owner_id: 'bfezv28v' });
|
||||
expect(tagResult.scanned).toBe(3); // 3 筆候選都掃到了
|
||||
expect(tagResult.tagged).toBe(1); // 但只剩 1 筆額度，只標了 1 筆
|
||||
expect(tagResult.quota_exceeded).toBe(true);
|
||||
expect(tagResult.quota_used_today).toBe(3); // 2（reconcile）+ 1（本次）＝ 3，額度用滿
|
||||
});
|
||||
|
||||
it('反過來也一樣：標庫 backfill 先消耗額度 → reconcile 看到的剩餘額度真的變少', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'tag-1', created_at: 1 });
|
||||
insertEntry(db, { id: 'tag-2', created_at: 2 });
|
||||
insertEntry(db, { id: 'reconcile-1', created_at: 3, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true }) });
|
||||
|
||||
const maintenanceLimit = '2';
|
||||
const tagEnv = makeEnv(db, { maintenanceLimit });
|
||||
const tagResult = await backfillEntryLibraryTags(db, tagEnv, { library: 'general', owner_id: 'bfezv28v' });
|
||||
expect(tagResult.tagged).toBe(2); // 額度剛好夠標完兩筆
|
||||
|
||||
const reconcileEnv = {
|
||||
DB: db, ENVIRONMENT: 'test', KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: maintenanceLimit,
|
||||
AI: { async run() { return { data: [] }; } },
|
||||
VECTORIZE: {
|
||||
async getByIds(ids: string[]) { return ids.map((id) => ({ id, values: [0.1] })); },
|
||||
async upsert() { return { count: 0 }; },
|
||||
},
|
||||
} as unknown as Bindings;
|
||||
const rc = await reconcileEmbedGeneration(reconcileEnv, { limit: 100 });
|
||||
expect(rc.scanned).toBe(1); // 有 1 筆候選
|
||||
expect(rc.checked).toBe(0); // 但額度已被標庫 backfill 用光，reconcile 一筆都動不了
|
||||
expect(rc.quota_exceeded).toBe(true);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user