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]>
This commit is contained in:
1 parent
081db4651c
commit
9489e40e0c
23 files changed
+2615
-323
No files matched your search
@@ -581,7 +581,7 @@ export const CAPABILITY_CATALOG: Record<KnownCapabilityId, CapabilityDescriptor>
|
||||
"metadata.enrich": d(
|
||||
"metadata.enrich",
|
||||
"补全元数据",
|
||||
"TMDB 查不到的作品(短剧、平台独播剧)按标题查网页:搜索后只读白名单网站(平台、百科),抽取标题、别名、年份、平台、集数、简介、海报、类型,每个字段带出处和证据等级。只给建议,不改作品;同一标题 7 天内直接返回上次结果",
|
||||
"TMDB 查不到的作品(短剧、平台独播剧)按标题查网页:搜索后读白名单网站(平台、百科,遵守 robots.txt),豆瓣和其它网站只用搜索摘要,抽取标题、别名、年份、平台、集数、主演、简介、海报、类型,每个字段带出处、置信度和证据等级。只给建议,不改作品;同一标题 7 天内直接返回上次结果",
|
||||
"propose",
|
||||
"MetadataEnrich",
|
||||
"organize.execute",
|
||||
|
||||
Reference in new issue
Block a user