feat(ingest): T0.5–T5 純餵食器管線實作（issue #2）

ingest 全管線（採取優先、extract fallback、跨庫織網、POST envelope）： - T0.5 骨架：Hono + zod-openapi，無 D1/Vectorize/AI 綁定（不碰儲存鐵律） - T1 SourceAdapter：GitHub runtime API 拉 + per-file sha256 content-hash + /refresh 受理端 - T2 採取（路徑 A 優先）：harvest template 1.8.0+ 卡（gloss/實體/typed-edge） - T3 extract（路徑 B fallback）：LlmCaller 可選模型 + JSON-fail 升級閘 + 端點對齊硬自檢護欄；第一版不 embed（只打標） - T4 跨庫織網（主職）：匯總多 repo → 偵測跨庫橋/異見，不算 bridge_score（graph 領域） - T5 輸出：buildEnvelope strict + 顯式禁送欄位自檢；graph-client 純 POST（cherry-pick _kbdb_client.py 改不碰 base）；薄 ops CLI（不帶查詢 MCP） envelope 對齊 full contract（embed/id/aliases/predicate_embed）；同步 contract 向量化欄位升格。 gate：vitest 28 passed / tsc clean / wrangler dry-run 乾淨（只 env-var 綁定）。端到端 ingest→graph：graph receiver 已補對齊 → 待 ingest 部署 + GRAPH_BASE_URL → 待部署驗，未假綠。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-26 20:40:53 +08:00
parent dffefdcdc2
commit 16ad1cb208
24 changed files with 4003 additions and 28 deletions
@@ -0,0 +1,117 @@
+#!/usr/bin/env node
+// 薄 ops CLI（T5.2）— 人手動觸發重萃。不帶查詢 MCP（ambient 餵食器沒人「問」它）。
+//
+// 兩種模式：
+//   ingest refresh <github:owner/repo@path>   經部署的 Worker /refresh 重萃單一來源
+//   ingest pull <owner/repo> [root]           本地 dry-run：拉 + 列出會送的 envelope（不 POST）
+//
+// 設定走 env：
+//   KBDB_INGEST_URL   已部署的 ingest Worker base（refresh 模式用）
+//   GRAPH_BASE_URL    graph 寫入端（pull --post 用）
+//   GITHUB_TOKEN      拉私庫用（公庫可空）
+//
+// 鐵律：CLI 不碰儲存；refresh 經 Worker、pull --post 經 graph 寫入端。觸發＝人手動（無排程）。
+
+import process from 'node:process';
+
+const [, , cmd, arg, arg2] = process.argv;
+
+async function sha256hex(text) {
+  const data = new TextEncoder().encode(text);
+  const digest = await crypto.subtle.digest('SHA-256', data);
+  return [...new Uint8Array(digest)].map((b) => b.toString(16).padStart(2, '0')).join('');
+}
+
+function ghHeaders() {
+  const h = { Accept: 'application/vnd.github+json', 'User-Agent': 'kbdb-ingest-cli' };
+  if (process.env.GITHUB_TOKEN) h.Authorization = `Bearer ${process.env.GITHUB_TOKEN}`;
+  return h;
+}
+
+async function ghGetFile(owner, repo, path) {
+  const url = `https://api.github.com/repos/${owner}/${repo}/contents/${path}`;
+  const res = await fetch(url, { headers: ghHeaders() });
+  if (!res.ok) throw new Error(`github ${owner}/${repo}@${path}: ${res.status}`);
+  const body = await res.json();
+  const text = body.encoding === 'base64' ? Buffer.from(body.content, 'base64').toString('utf-8') : body.content;
+  return { text, commit: body.sha };
+}
+
+async function ghListMarkdown(owner, repo, root = '') {
+  const res = await fetch(`https://api.github.com/repos/${owner}/${repo}/git/trees/HEAD?recursive=1`, { headers: ghHeaders() });
+  if (!res.ok) throw new Error(`github list ${owner}/${repo}: ${res.status}`);
+  const body = await res.json();
+  const prefix = root.replace(/^\/+|\/+$/g, '');
+  return (body.tree || [])
+    .filter((e) => e.type === 'blob' && e.path.endsWith('.md'))
+    .map((e) => e.path)
+    .filter((p) => (prefix ? p === prefix || p.startsWith(prefix + '/') : true));
+}
+
+// 極簡採取（鏡射 src/lib/harvest.ts；CLI dry-run 用，不引 TS）。
+function harvest(md) {
+  const fm = /^---\n([\s\S]*?)\n---\n?([\s\S]*)$/.exec(md);
+  const body = fm ? fm[2] : md;
+  const gloss = fm && /^gloss:\s*(.+)$/m.exec(fm[1]) ? /^gloss:\s*(.+)$/m.exec(fm[1])[1].trim() : undefined;
+  const title = /^#\s+(.+)$/m.exec(body)?.[1]?.trim();
+  const sec = (h) => new RegExp(`^##\\s+${h}[^\\n]*\\n([\\s\\S]*?)(?=\\n##\\s|$)`, 'm').exec(body)?.[1] || '';
+  const nodes = [];
+  if (title) nodes.push({ name: title, gloss, embed: true });
+  for (const line of sec('實體').split('\n')) {
+    const m = /^-\s*\*\*(.+?)\*\*\s*(?:（(.+?)）)?\s*(?:[—-]\s*(.+))?$/.exec(line.trim());
+    if (m) nodes.push({ name: m[1].trim(), gloss: m[3]?.trim() || undefined, embed: true });
+  }
+  const triplets = [];
+  for (const line of sec('關聯').split('\n')) {
+    const m = /^(.+?)\s*>>\s*(.+?)\s*>>\s*(.+?)$/.exec(line.replace(/^-\s*/, '').trim());
+    if (m) {
+      const clean = (s) => s.replace(/\[\[|\]\]|\*\*/g, '').trim();
+      triplets.push({ subject: clean(m[1]), predicate: m[2].trim(), object: clean(m[3]), predicate_embed: true });
+    }
+  }
+  return { nodes, triplets };
+}
+
+async function doRefresh(uri) {
+  const base = process.env.KBDB_INGEST_URL;
+  if (!base) throw new Error('KBDB_INGEST_URL 未設（指向已部署的 ingest Worker）');
+  const res = await fetch(base.replace(/\/$/, '') + '/refresh', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ uri }),
+  });
+  console.log(JSON.stringify(await res.json(), null, 2));
+}
+
+async function doPull(ownerRepo, root) {
+  const [owner, repo] = ownerRepo.split('/');
+  if (!owner || !repo) throw new Error('用法：ingest pull <owner/repo> [root]');
+  const paths = await ghListMarkdown(owner, repo, root || '');
+  console.error(`[ingest] ${owner}/${repo}: ${paths.length} 個 MD`);
+  const envelopes = [];
+  for (const path of paths) {
+    const { text, commit } = await ghGetFile(owner, repo, path);
+    const { nodes, triplets } = harvest(text);
+    if (!triplets.length) continue; // 採不到（非 template 卡）→ dry-run 跳過（CLI 不做 extract）
+    envelopes.push({
+      source: { uri: `github:${owner}/${repo}@${path}`, content_hash: await sha256hex(text), commit },
+      extractor: { model: 'local-harvest', tier: 'shallow' },
+      nodes,
+      triplets,
+    });
+  }
+  console.error(`[ingest] 採取出 ${envelopes.length} 個 envelope（共 ${envelopes.reduce((n, e) => n + e.triplets.length, 0)} 三元組）`);
+  console.log(JSON.stringify(envelopes, null, 2));
+}
+
+try {
+  if (cmd === 'refresh' && arg) await doRefresh(arg);
+  else if (cmd === 'pull' && arg) await doPull(arg, arg2);
+  else {
+    console.error('用法：\n  ingest refresh <github:owner/repo@path>\n  ingest pull <owner/repo> [root]');
+    process.exit(2);
+  }
+} catch (e) {
+  console.error('[ingest] 錯誤:', e.message);
+  process.exit(1);
+}