feat(identity): web metadata enrichment for titles missing on TMDB (META-1)

- metadata.enrich (propose, low, replay safe): normalized-title cache (kv_cache
  region enrich, 7 days) -> daily budget -> web.search (title + 短剧 / 电视剧 平台,
  second query limited to whitelist via site:) -> web.fetch of up to 3 relevant
  whitelisted pages (registered site domains never read, redirects out of the
  whitelist dropped) -> upstream model extraction with rule fallback -> server-side
  evidence check (rule_confirmed / multi_evidence / needs_review). Suggestion only.
- POST /identity-pool/{id}/enrich (suggest) and /enrich/apply (console session):
  provisional entity or same-title merge, season/episode units, field-level
  metadata with source web/agent + evidence, aliases, release assignment.
  Poster proxy GET /img/enrich/{id} (og:image from whitelisted pages only).
- Auto-enrich once per pool entry when subscription/rule lookups find nothing on
  TMDB (identity.autoEnrich, off by default); identity.enrichDailyBudget,
  identity.enrichDomains settings; web.fetch now returns og:image.
- Pool sheet "元数据补全" section; entity detail shows evidence links.
- Migration 0049_enrichment (metadata_enrichment, metadata_field.evidence, source
  web). Requires image rebuild / api + worker restart to take effect.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
rootandClaude Opus 5.5 committed 2026-09-29 15:57:48 +08:00
1 parent 18a5cf1de7
commit f4666a4671
36 files changed
+2514 -25

No files matched your search

@@ -2,6 +2,7 @@ import { defineTask, type OutboxRouteFn, type TaskRegistry } from "@umt/tasks";
import { z } from "zod";
import type { SourcesRuntime } from "./runtime.ts";
import { refreshSiteAccount } from "./service/account.ts";
import { AUTO_ENRICH_TASK, runAutoEnrich } from "./service/enrich.ts";
import { ingestFeed } from "./service/feeds.ts";
import { refreshMetadata } from "./service/metadata.ts";
import { resolveRelease } from "./service/resolve.ts";
@@ -55,6 +56,14 @@ export function registerSourcesTasks(registry: TaskRegistry, rt: () => SourcesRu
}),
),
}),
// META-1 自动元数据补全(每个池条目一次,只出建议):经能力注册中心调用 metadata.enrich
defineTask({
name: AUTO_ENRICH_TASK,
version: 1,
inputSchema: z.object({ poolEntryId: id }),
retryPolicy: { maximumAttempts: 1 },
handler: (t) => t.step.run("enrich", () => runAutoEnrich(rt().ctx, t.input.poolEntryId, t.runId, t.abortSignal)),
}),
defineTask({
name: "refreshMetadata",
version: 1,