Files
UHD_Media_Tool/packages/db/migrations/0049_enrichment.ts
T
rootandClaude Opus 5.5 f4666a4671 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]>
2026-09-29 15:57:48 +08:00

63 lines
3.0 KiB
TypeScript

import type { Kysely } from "kysely";
import { entityTable, execDdl, oneOf } from "../src/migration-helpers.ts";
// META-1 TMDB 缺失作品的元数据补全(REQ R03 / R10、§7.3、§7.5):
// - metadata_enrichment:一次补全的记录(查询 → 网页搜索 / 读取 → 模型抽取出的建议;应用后指向建出的作品)。
// 每日预算按当天新建的行计数(命中归一化标题缓存不新建行);建议只存这里,应用前不写作品表。
// - metadata_field / field_override 的来源新增 web:值出自网页原文(Agent 改写 / 归纳的字段记 agent,不记 tmdb);
// - metadata_field.evidence:字段证据(来源网页、证据等级、补全记录 id),作品详情"元数据来源"里显示链接。
const OLD_SOURCES = ["tmdb", "user", "agent", "nfo", "site", "import"] as const;
const SOURCES = [...OLD_SOURCES, "web"] as const;
// biome-ignore lint/suspicious/noExplicitAny: 迁移不依赖应用表类型
export async function up(db: Kysely<any>): Promise<void> {
await execDdl(
db,
`
alter table metadata_field drop constraint metadata_field_source_check;
alter table metadata_field add constraint metadata_field_source_check ${oneOf("source", SOURCES)};
alter table field_override drop constraint field_override_source_check;
alter table field_override add constraint field_override_source_check ${oneOf("source", SOURCES)};
alter table metadata_field add column evidence jsonb;
${entityTable(
"metadata_enrichment",
`
identity_candidate_id uuid references identity_candidate (id) on delete set null,
normalized_title text not null,
query jsonb not null,
status text not null default 'suggested' ${oneOf("status", ["suggested", "applied", "failed"])},
trigger text not null default 'manual' ${oneOf("trigger", ["manual", "auto", "agent"])},
suggestion jsonb,
error text,
usage jsonb not null default '{}'::jsonb,
media_entity_id uuid references media_entity (id) on delete set null,
applied_at timestamptz,
applied_by text,
created_by text`,
)}
create index metadata_enrichment_created_idx on metadata_enrichment (created_at);
create index metadata_enrichment_candidate_idx on metadata_enrichment (identity_candidate_id, created_at desc);
create index metadata_enrichment_title_idx on metadata_enrichment (normalized_title);
`,
);
}
// biome-ignore lint/suspicious/noExplicitAny: 同上
export async function down(db: Kysely<any>): Promise<void> {
await execDdl(
db,
`
drop table if exists metadata_enrichment;
alter table metadata_field drop column if exists evidence;
delete from metadata_field where source = 'web';
update field_override set source = 'agent' where source = 'web';
alter table metadata_field drop constraint metadata_field_source_check;
alter table metadata_field add constraint metadata_field_source_check ${oneOf("source", OLD_SOURCES)};
alter table field_override drop constraint field_override_source_check;
alter table field_override add constraint field_override_source_check ${oneOf("source", OLD_SOURCES)};
`,
);
}