feat(identity): source-aware short-drama enrichment with snippet mode and hit rate (META-2)

- classify enrich sources: encyclopedia, platform pages (hongguo, kuaikaw, video
  platforms), douban (search snippet only) and other sites' search snippets
  (snippet mode, pages never opened); one extractor per source, fields carry
  source kind and confidence, merged by noisy-OR across hosts
- new cast field (applied as MediaCredit with placeholder ids)
- robots.txt check (cached per host 1 day) and login-wall/captcha give-up
- per-enrichment source attempts + GET /identity/enrich-stats, 30-day hit-rate
  table under settings -> metadata -> identity
- setting identity.enrichSnippetAllSites (default on); default domains add
  baike.com and kuaikaw.cn
- replay fixtures from the real run on the 4 user-library short dramas
  (sanitized Brave responses, hongguo page, robots.txt)

Co-Authored-By: Claude Opus 5.5 <[email protected]>

apps/web/app/components/settings/metadata.tsx

@@ -1,6 +1,9 @@
 import { DEFAULT_SETTINGS } from "@umt/contracts";
 import { toast } from "sonner";
 import { useClearImageCache, useClearTmdbCache, useImageCache, useTmdbCache } from "~/api/cache.ts";
+import { useEnrichStats } from "~/api/identity.ts";
+import { DataTable } from "~/components/console/data-table.tsx";
+import { ENRICH_SOURCE_KIND } from "~/components/library/labels.ts";
 import { Button } from "~/components/ui/button.tsx";
 import { errorMessage } from "~/lib/api.ts";
 import { secretPatch } from "~/lib/secret.ts";
@@ -212,7 +215,14 @@ const IDENTITY_CARD: CardSpec = {
       name: "identity.enrichDomains",
       label: "补全可读取的网站",
       kind: "textarea",
-      hint: "每行一个域名，含子域名；只放平台和百科类网站。已登记站点的域名一律不读",
+      hint: "每行一个域名，含子域名；只放平台和百科类网站。豆瓣只用搜索摘要，不读页面；robots.txt 不允许的页面不读。已登记站点的域名一律不读",
+      wide: true,
+    },
+    {
+      name: "identity.enrichSnippetAllSites",
+      label: "也用其它网站的搜索摘要",
+      kind: "switch",
+      hint: "短剧多半只有聚合站收录。打开后，白名单以外网站的搜索摘要也用来抽年份、集数、主演、简介（只看搜索引擎给的摘要，不打开这些网页）",
       wide: true,
     },
   ],
@@ -221,6 +231,7 @@ const IDENTITY_CARD: CardSpec = {
     "identity.autoEnrich": s.identity.autoEnrich,
     "identity.enrichDailyBudget": n(s.identity.enrichDailyBudget),
     "identity.enrichDomains": s.identity.enrichDomains.join("\n"),
+    "identity.enrichSnippetAllSites": s.identity.enrichSnippetAllSites ?? true,
   }),
   toPatch: (v) => ({
     identity: {
@@ -231,10 +242,59 @@ const IDENTITY_CARD: CardSpec = {
         .split(/[\s,，]+/)
         .map((d) => d.trim().toLowerCase())
         .filter(Boolean),
+      enrichSnippetAllSites: v["identity.enrichSnippetAllSites"] === true,
     },
   }),
+  extra: () => <EnrichStatsTable />,
 };
 
+type StatRow = { kind: string; withResults: number; hits: number; rate: number | null };
+
+/** 最近 30 天补全命中率(按来源类别,META-2) */
+function EnrichStatsTable() {
+  const q = useEnrichStats(30);
+  const d = q.data;
+  return (
+    <div className="mb-3 space-y-2">
+      <p className="text-meta text-muted-foreground tabular-nums">
+        {d
+          ? `最近 ${d.days} 天元数据补全 ${d.total} 次，出了建议 ${d.suggested} 次${d.tracked < d.total ? `；有来源明细的 ${d.tracked} 次` : ""}`
+          : "读取补全命中率…"}
+      </p>
+      {d && d.tracked > 0 ? (
+        <DataTable<StatRow>
+          rows={d.sources}
+          rowKey={(r) => r.kind}
+          empty={{ title: "还没有补全记录" }}
+          columns={[
+            { key: "kind", header: "来源", cell: (r) => ENRICH_SOURCE_KIND[r.kind] ?? r.kind },
+            {
+              key: "withResults",
+              header: "有结果",
+              align: "right",
+              cell: (r) => <span className="tabular-nums">{r.withResults}</span>,
+            },
+            {
+              key: "hits",
+              header: "命中",
+              align: "right",
+              cell: (r) => <span className="tabular-nums">{r.hits}</span>,
+            },
+            {
+              key: "rate",
+              header: "命中率",
+              align: "right",
+              cell: (r) => (
+                <span className="tabular-nums">{r.rate === null ? "—" : `${Math.round(r.rate * 100)}%`}</span>
+              ),
+            },
+          ]}
+        />
+      ) : null}
+    </div>
+  );
+}
+
 export function MetadataSection() {
   return (
     <SettingsGate>