- 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]>
106 lines
3.8 KiB
TypeScript
106 lines
3.8 KiB
TypeScript
import { TaskRegistry } from "@umt/tasks";
|
|
import { createMockMteamApi, type MockMteamApi } from "@umt/testkit";
|
|
import { afterAll, beforeAll, describe, expect, it } from "vitest";
|
|
import { snapshotSite } from "../../src/modules/sources-identity/service/snapshot.ts";
|
|
import { createHarness, type Harness, pgAvailable } from "./harness.ts";
|
|
|
|
const up = await pgAvailable();
|
|
|
|
describe.skipIf(!up)("M-Team 快照与任务注册", () => {
|
|
let h: Harness;
|
|
let api: MockMteamApi;
|
|
let siteId: string;
|
|
|
|
beforeAll(async () => {
|
|
api = await createMockMteamApi();
|
|
h = await createHarness("mteam");
|
|
const site = await h.db
|
|
.insertInto("site")
|
|
.values({
|
|
key: "mteam",
|
|
name: "馒头",
|
|
adapter: "mteam_api",
|
|
base_url: "https://kp.m-team.cc/",
|
|
rate_limit: JSON.stringify({ minIntervalMs: 0 }),
|
|
config: JSON.stringify({ apiBaseUrl: api.baseUrl }),
|
|
})
|
|
.returningAll()
|
|
.executeTakeFirstOrThrow();
|
|
siteId = site.id;
|
|
const ref = await h.secrets.create({ purpose: "site_api_key", plaintext: api.apiKey });
|
|
await h.db
|
|
.insertInto("site_account")
|
|
.values({ site_id: siteId, label: "api", auth_kind: "api_key", secret_ref: ref })
|
|
.execute();
|
|
});
|
|
afterAll(async () => {
|
|
await h?.close();
|
|
await api?.close();
|
|
});
|
|
|
|
it("API Key 站点快照:原始分类保留,促销带观察/过期时间;key 不入库", async () => {
|
|
const r = await snapshotSite(h.rt, { siteId, kind: "periodic" });
|
|
expect(r.status).toBe("ok");
|
|
expect(r.itemCount).toBeGreaterThan(0);
|
|
const rows = await h.db.selectFrom("source_release").selectAll().where("site_id", "=", siteId).execute();
|
|
const sports = rows.find((x) => x.site_release_id === "912237");
|
|
expect(sports?.category_raw).toBe("407");
|
|
const promo = rows.find((x) => x.site_release_id === "912233")!;
|
|
expect((promo.promotion as { observedAt?: string }).observedAt).toBeTruthy();
|
|
expect(JSON.stringify(rows)).not.toContain(api.apiKey);
|
|
});
|
|
|
|
it("key 失效:账号标失效 + 待处理,快照结果 failed", async () => {
|
|
api.setFailMode("banned_key");
|
|
const r = await snapshotSite(h.rt, { siteId, kind: "manual" });
|
|
expect(r.status).toBe("failed");
|
|
const acc = await h.db
|
|
.selectFrom("site_account")
|
|
.select(["status"])
|
|
.where("site_id", "=", siteId)
|
|
.executeTakeFirstOrThrow();
|
|
expect(["invalid", "expired"]).toContain(acc.status);
|
|
const d = await h.db
|
|
.selectFrom("decision")
|
|
.selectAll()
|
|
.where("dedupe_key", "=", `site-auth:${siteId}`)
|
|
.executeTakeFirstOrThrow();
|
|
expect(d.status).toBe("open");
|
|
api.setFailMode(null);
|
|
});
|
|
|
|
it("模块注册 7 个任务与 3 条 outbox 路由;任务处理器经 step.run 调服务", async () => {
|
|
const reg = new TaskRegistry();
|
|
h.module.registerTasks(reg, h.ctx);
|
|
expect(reg.names()).toEqual([
|
|
"enrichPoolEntry",
|
|
"ingestFeed",
|
|
"refreshMetadata",
|
|
"refreshSiteAccount",
|
|
"resolveObservation",
|
|
"searchSubscription",
|
|
"snapshotSite",
|
|
]);
|
|
expect(Object.keys(h.module.outboxRoutes!(h.ctx)).sort()).toEqual([
|
|
"feed.due",
|
|
"feed.gap_suspected",
|
|
"release.observed",
|
|
]);
|
|
const def = reg.latest("resolveObservation");
|
|
expect(def.inputSchema.safeParse({}).success).toBe(false);
|
|
expect(def.inputSchema.safeParse({ observationId: "00000000-0000-4000-8000-000000000000" }).success).toBe(true);
|
|
const steps: string[] = [];
|
|
const out = await reg.latest("snapshotSite").handler({
|
|
input: { siteId, kind: "periodic" },
|
|
step: {
|
|
run: async (name: string, fn: () => unknown) => {
|
|
steps.push(name);
|
|
return fn();
|
|
},
|
|
},
|
|
} as never);
|
|
expect(steps).toEqual(["snapshot"]);
|
|
expect(out).toMatchObject({ status: "skipped", reason: "auth_invalid" });
|
|
});
|
|
});
|