feat: KBDB self-hosted 查詢 + embed 模組 + thin-shell 收窄 + search_workflow(code done 待端到端)

按 issue 分段標明(檔 #5/#8 改動交疊處無法乾淨拆檔,故併一個 commit):

#4 thin-shell §3.1 自力救濟階梯 + code-node 規則(純文檔/規則,code-node 零件未實作)
#5 KBDB source filter(json_extract metadata_json 零建表)+ 能力對照;documents 聚合與
   DELETE proxy 部分擱置等頂層 T8
#7 base embed 模組(kbdb/src/embed.ts)+ vectorize 開關(deploy/config/wrangler.toml 註解範本)
   + 語義查詢降級閉環(mode=semantic 未開→LIKE+capability_hint)
#8 部分(workflow-discovery):
   - KBDB /entries/search 加 base 通用 entry_type filter(entry-crud/embed/route/kbdb-proxy 透傳)
   - /webhooks/named 強制 description(空→400,訊息要求操盤 AI 據實寫一句)
   - 部署雙寫 entry_type=workflow embeddable entry(waitUntil 非阻塞,供 search)
   - cypher GET /workflows/search + MCP u6u_search_workflows(優先語意、降級 hint)
   - cypher POST /workflows/backfill-search-entries(無 desc 列出不編造)
   - GET /webhooks/named 補回 description/created_at 欄位(為 list 來源收斂備)

⚠️ tsc 綠 = code done,非完成(mindset §7 禁假綠):
- #7/#8 端到端待 leo21c 部署驗(Vectorize 需官方憑證、CC 跑不了)
- #8 ①-a(MCP deploy 改打 /webhooks/named)未做、MCP deploy 那半仍 404
- #8 端到端(強制填擋空/語義命中/租戶隔離/降級 hint)未驗

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
uncle6me-web
2026-06-27 17:52:52 +08:00
parent 013b55e97e
commit 934b9265d9
16 changed files with 610 additions and 33 deletions
+13 -1
View File
@@ -57,6 +57,7 @@ export interface ListEntriesFilter {
owner_id?: string;
parent_id?: string;
page_name?: string; // exact-match lookup (e.g. skill-/example- idempotency key)
source?: string; // filter by metadata_json.$.source (ingest envelope source.uri). issue #5.1
limit?: number;
offset?: number;
}
@@ -68,6 +69,9 @@ export async function listEntries(db: D1Database, f: ListEntriesFilter = {}): Pr
if (f.owner_id) { conds.push('owner_id = ?'); params.push(f.owner_id); }
if (f.parent_id) { conds.push('parent_id = ?'); params.push(f.parent_id); }
if (f.page_name) { conds.push('page_name = ?'); params.push(f.page_name); }
// source is queryable via SQLite json_extract on the existing metadata_json TEXT column —
// no new column / no migration (表不變鐵律). Per issue #5.1 (頂層化 source 成可查 filter).
if (f.source) { conds.push("json_extract(metadata_json, '$.source') = ?"); params.push(f.source); }
const where = conds.length ? `WHERE ${conds.join(' AND ')}` : '';
const limit = Math.min(f.limit ?? 100, 1000);
const offset = f.offset ?? 0;
@@ -107,10 +111,18 @@ export async function deleteEntry(db: D1Database, id: string): Promise<void> {
}
// D1 LIKE keyword search (base; semantic search is the optional embed module).
export async function searchEntries(db: D1Database, q: string, owner_id?: string, limit = 50): Promise<Entry[]> {
// entry_type: optional base filter (generic — caller passes any type, base stays type-agnostic).
export async function searchEntries(
db: D1Database,
q: string,
owner_id?: string,
entry_type?: string,
limit = 50,
): Promise<Entry[]> {
const conds = ['content LIKE ?'];
const params: unknown[] = [`%${q}%`];
if (owner_id) { conds.push('owner_id = ?'); params.push(owner_id); }
if (entry_type) { conds.push('entry_type = ?'); params.push(entry_type); }
const res = await db
.prepare(`SELECT * FROM entries WHERE ${conds.join(' AND ')} ORDER BY updated_at DESC LIMIT ?`)
.bind(...params, Math.min(limit, 200))