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]>

packages/contracts/src/settings.ts

@@ -452,6 +452,9 @@ export const DEFAULT_ENRICH_DOMAINS: string[] = [
   "ixigua.com",
   "baike.sogou.com",
   "mydramalist.com",
+  // META-2:快懂百科、河马剧场(短剧平台公开作品页);红果短剧的 /series/ 页 robots 不允许,只读 robots 放行的页面
+  "baike.com",
+  "kuaikaw.cn",
 ];
 
 export const IdentitySettings = z.object({
@@ -475,6 +478,11 @@ export const IdentitySettings = z.object({
         .regex(/^[a-z0-9.-]+\.[a-z]{2,}$/),
     )
     .max(100),
+  /**
+   * META-2 摘要模式:白名单外网站(多为短剧聚合站)的搜索结果摘要也用来抽字段(只读搜索引擎给的摘要,不打开这些网页)。
+   * 缺省开;关掉后只用白名单网站的摘要与网页。旧设置没有这个键,按开处理
+   */
+  enrichSnippetAllSites: z.boolean().optional(),
 });
 export type IdentitySettings = z.infer<typeof IdentitySettings>;
 
@@ -668,6 +676,7 @@ export const DEFAULT_SETTINGS: GlobalSettings = {
     autoEnrich: false,
     enrichDailyBudget: 20,
     enrichDomains: DEFAULT_ENRICH_DOMAINS,
+    enrichSnippetAllSites: true,
   },
   search: { defaultSiteMode: "default", siteIds: [] },
   storage: DEFAULT_STORAGE_SETTINGS,
@@ -960,6 +969,7 @@ export const SETTINGS_SECTIONS: readonly SettingsSectionDef[] = [
       "identity.autoEnrich",
       "identity.enrichDailyBudget",
       "identity.enrichDomains",
+      "identity.enrichSnippetAllSites",
       "cache.globalImageCache",
       "cache.globalImageCacheDays",
     ],