Files
Arcrun/kbdb/src/routes/entries.ts
T
Claude 65d85eb08f fix(kbdb): search keyword 補 source filter(#66)+semantic 曝 top_k/min_score 帶 score(#67)
#66:/entries/search keyword 路徑 source 解析後丟棄(#5.1 只接了 listEntries 那半)——
searchEntries 尾端加 source?(既有 positional caller 全不用改),conds 補與 listEntries
同款 json_extract(metadata_json,'$.source') 謂詞;route keyword 分支與 semantic 降級
分支兩處傳入。

#67:semantic 固定 topK=20、零分數閾值、低分尾硬湊數——route 曝 top_k(預設 20、封頂
100)與 min_score(預設 0=不過濾)query 參數;semanticSearch 依 min_score 截低分尾;
semantic 回應 entry 附 score 欄(加欄不改形)。壞值(非數字/非正)視同沒帶,不 400。

向後相容:不帶新參數時輸出與現況一致(semantic 僅多 score 資訊);不動表(D6)、
不動 D1 結構(API-as-Wall)。測試:新增 search-source-and-score.test.ts 13 條
(source 謂詞形狀/route 下傳/降級不洩 filter/min_score 截斷/topK 透傳封頂/壞值防呆/
不帶參數行為不變),kbdb vitest 33/33 綠、tsc 0。

關聯 #66 #67。merge 後需 gated redeploy kbdb worker(leo 閘)。

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JUmjwkHLVBHM3ydhT1WSW3
2026-07-19 07:53:46 +00:00

144 lines
7.6 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
// Entries route — atomic data + tree (project/workflow). Base; embed is OPTIONAL (issue #7).
import { Hono } from 'hono';
import type { Bindings } from '../types';
import {
createEntry,
getEntry,
listEntries,
updateEntry,
deleteEntry,
searchEntries,
} from '../actions/entry-crud';
import { embedEnabled, embedOnWrite, semanticSearch } from '../embed';
export const entryRoutes = new Hono<{ Bindings: Bindings }>();
// library 多值參數(逗號分隔,portal-auth P1design §3.3)。空值/全空白 → undefined(=不過濾,
// 行為與未帶參數一字不變——向後相容硬驗收)。
function parseLibraryParam(raw: string | undefined): string[] | undefined {
if (!raw) return undefined;
const libs = raw.split(',').map((s) => s.trim()).filter(Boolean);
return libs.length > 0 ? libs : undefined;
}
// POST /entries — create (entry_type=block/value/project/workflow/...)
entryRoutes.post('/', async (c) => {
const body = await c.req.json().catch(() => null);
if (!body || !body.entry_type) return c.json({ success: false, error: 'entry_type required' }, 400);
const entry = await createEntry(c.env.DB, body);
// embed-on-write (#7 / #5 第4點):模組開 + entry 標 embed:true 才做;fire-and-forget,不阻塞回應、失敗不致命。
if (embedEnabled(c.env)) c.executionCtx.waitUntil(embedOnWrite(c.env, entry).catch(() => {}));
return c.json({ success: true, entry });
});
// GET /entries — list with filters (entry_type, owner_id, parent_id, page_name, source, q/search)
// e.g. list workflows under a project: ?parent_id=PROJECT&entry_type=workflow
// e.g. get one by idempotency key: ?page_name=skill-rag_with_arcrun
// e.g. filter by ingest source: ?source=logseq://vault/foo.md (issue #5.1)
// e.g. filter by library(多值逗號分隔,portal-auth P1: ?library=finance,hr(未標記舊資料歸 general
// e.g. keyword filter: ?q=遷移 或 ?search=遷移(別名,Arcrun#3 發現①:caller 實測時打的是 search=
// 舊版完全不接這個 filter;q 與 search 兩個名字都認,避免同一個坑再踩一次)。
// count = 本頁筆數(受 limit 影響);total = 符合條件全部筆數(不受 limit 影響,見 total 欄位)。
entryRoutes.get('/', async (c) => {
const { entries, total } = await listEntries(c.env.DB, {
entry_type: c.req.query('entry_type') || undefined,
owner_id: c.req.query('owner_id') || undefined,
parent_id: c.req.query('parent_id') || undefined,
page_name: c.req.query('page_name') || undefined,
source: c.req.query('source') || undefined,
library: parseLibraryParam(c.req.query('library')),
q: c.req.query('q') || c.req.query('search') || undefined,
limit: c.req.query('limit') ? Number(c.req.query('limit')) : undefined,
offset: c.req.query('offset') ? Number(c.req.query('offset')) : undefined,
});
return c.json({ success: true, entries, count: entries.length, total });
});
// GET /entries/search?q=...&owner_id=...&source=...&entry_type=...&library=...&mode=keyword|semantic
// - mode=keyword(預設):D1 LIKEbase,永遠可用)。
// - mode=semantic:需 embed 模組開(Vectorize+AI binding)。未開 → 降級 keyword + capability_hint 告知缺能力(#7 發現閉環)。
// - entry_typebase 通用 filtercaller 傳任意 type,如 workflowbase 不寫死語意,workflow-discovery Q4)。
// - library:多值庫 filter(逗號分隔,portal-auth P1)。keyword 走 json_extractNULL→general
// semantic 走 Vectorize $in。未帶=全庫(行為不變)。
// - sourcekeyword 走 json_extract 謂詞(#66——#5.1 只接了 list 那半,這裡原本解析完即丟);
// semantic 走 Vectorize metadata filter(原本就有)。
// - top_k / min_score#67semantic 專用):topK 可調(預設 20、上限 100)+分數閾值
// (預設 0=不過濾)。未帶=行為與舊版一致(向後相容);semantic 回應的 entry 另附 score
// 欄讓 caller 自裁(加欄不改形,keyword 路徑不受影響)。
entryRoutes.get('/search', async (c) => {
const q = c.req.query('q');
if (!q) return c.json({ success: false, error: 'q required' }, 400);
const owner_id = c.req.query('owner_id') || undefined;
const source = c.req.query('source') || undefined;
const entry_type = c.req.query('entry_type') || undefined;
const library = parseLibraryParam(c.req.query('library'));
const mode = c.req.query('mode') === 'semantic' ? 'semantic' : 'keyword';
// 數字參數防呆:非數字/非正 → 當沒帶(回預設),不 400——與其他 filter「壞值靜默忽略」一致。
const topKNum = Number(c.req.query('top_k'));
const top_k = Number.isFinite(topKNum) && topKNum > 0 ? Math.floor(topKNum) : undefined;
const minScoreNum = Number(c.req.query('min_score'));
const min_score = Number.isFinite(minScoreNum) && minScoreNum > 0 ? minScoreNum : undefined;
if (mode === 'semantic') {
const hits = await semanticSearch(c.env, q, {
owner_id, source, entry_type, library, topK: top_k, min_score,
});
if (hits === null) {
// 模組沒開:誠實降級 keyword + 告知「叫 CC 幫你開 vectorize」(不假裝有語義)。
const entries = await searchEntries(c.env.DB, q, owner_id, entry_type, undefined, library, source);
return c.json({
success: true,
entries,
count: entries.length,
mode: 'keyword',
requested_mode: 'semantic',
capability_hint:
'語義查詢需先開 vectorizeembed 模組)。叫 CC「幫我開語義查詢」即可(設 kbdb_embed:true + redeploy)。本次已降級關鍵字搜尋。',
});
}
// hydrate vector hits → 完整 entry(保持回應形狀與 keyword 一致)。
// #67entry 附 score(相似分數)——加欄不改形,既有 caller 不解析多的欄位不受影響。
const entries = (
await Promise.all(
hits.map(async (h) => {
const e = await getEntry(c.env.DB, h.id);
return e ? { ...e, score: h.score } : null;
}),
)
).filter((e): e is NonNullable<typeof e> => e !== null);
return c.json({ success: true, entries, count: entries.length, mode: 'semantic' });
}
const entries = await searchEntries(c.env.DB, q, owner_id, entry_type, undefined, library, source);
return c.json({ success: true, entries, count: entries.length, mode: 'keyword' });
});
// GET /entries/:id
entryRoutes.get('/:id', async (c) => {
const entry = await getEntry(c.env.DB, c.req.param('id'));
if (!entry) return c.json({ success: false, error: 'not found' }, 404);
return c.json({ success: true, entry });
});
// PATCH /entries/:id
entryRoutes.patch('/:id', async (c) => {
const body = await c.req.json().catch(() => ({}));
const entry = await updateEntry(c.env.DB, c.req.param('id'), body);
if (!entry) return c.json({ success: false, error: 'not found' }, 404);
// 內容改了 → 重 embed(保持向量新鮮)。embedOnWrite 內部自會檢查模組開 + entry 是否 embeddable。
if (embedEnabled(c.env) && body.content !== undefined) {
c.executionCtx.waitUntil(embedOnWrite(c.env, entry).catch(() => {}));
}
return c.json({ success: true, entry });
});
// DELETE /entries/:id
entryRoutes.delete('/:id', async (c) => {
// 模組開 → 連帶刪向量(避免孤兒向量)。失敗不致命。
if (embedEnabled(c.env)) {
c.executionCtx.waitUntil(c.env.VECTORIZE!.deleteByIds([c.req.param('id')]).then(() => {}).catch(() => {}));
}
await deleteEntry(c.env.DB, c.req.param('id'));
return c.json({ success: true });
});