Files
UHD_Media_Tool/apps/server/test/sources-identity/site-capabilities.test.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

166 lines
7.4 KiB
TypeScript

import { randomUUID } from "node:crypto";
import type { CapabilityRegistry, InvokeContext } from "@umt/agent";
import { CAPABILITY_IDS, capabilitySpec } from "@umt/contracts";
import { createMockNexusPhpSite, type MockNexusPhpSite } from "@umt/testkit";
import { afterAll, beforeAll, describe, expect, it } from "vitest";
import { createCapabilityRegistry } from "../../src/modules/agent/capability-registry.ts";
import { registerSourcesCapabilities } from "../../src/modules/sources-identity/capabilities.ts";
import { createHarness, type Harness, pgAvailable } from "./harness.ts";
// W10-pre2 站点能力:site.list / site.health_check / site.refresh_login / site.user_data。
// 规格(类别 / 风险 / 重放)、execute 类要持续授权、输出不含凭证与 Cookie。
const up = await pgAvailable();
const TiB = 1024 ** 4;
const SITE_IDS = ["site.list", "site.health_check", "site.refresh_login", "site.user_data"] as const;
describe("站点能力规格", () => {
it("进入首批能力目录(17 + 3 只读摘要 + 4 站点 + 10 浏览器 + 2 会话交互 + 2 网页搜索 + 1 元数据补全 = 39);类别 / 风险 / 重放按约定", () => {
expect(CAPABILITY_IDS).toHaveLength(39);
for (const id of SITE_IDS) expect(CAPABILITY_IDS).toContain(id);
expect(capabilitySpec("site.list")).toMatchObject({ kind: "read", riskLevel: "low", replay: "safe" });
expect(capabilitySpec("site.user_data")).toMatchObject({ kind: "read", riskLevel: "low", replay: "safe" });
expect(capabilitySpec("site.health_check")).toMatchObject({
kind: "execute",
riskLevel: "low",
replay: "safe",
idempotent: true,
});
expect(capabilitySpec("site.refresh_login")).toMatchObject({
kind: "execute",
riskLevel: "medium",
replay: "never",
});
});
});
describe.skipIf(!up)("站点能力(mock NexusPHP)", () => {
let h: Harness;
let mock: MockNexusPhpSite;
let registry: CapabilityRegistry;
let siteId: string;
const PASSWORD = "cap-s3cret-pw";
const agentCtx = (): InvokeContext => ({
actorId: "agent:site-test",
taskId: randomUUID(),
scopeIds: [],
signal: new AbortController().signal,
source: "agent",
});
/** 输出里不许出现的东西:密码、会话 Cookie、secret 引用 */
const assertRedacted = async (out: unknown) => {
const text = JSON.stringify(out);
expect(text).not.toContain(PASSWORD);
expect(text).not.toMatch(/secretRef|secret_ref|cookie|loginName|userAgent/i);
for (const v of h.secrets.plain.values()) expect(text).not.toContain(v);
for (const ref of h.secrets.plain.keys()) expect(text).not.toContain(ref);
};
beforeAll(async () => {
mock = await createMockNexusPhpSite({ username: "alice", password: PASSWORD });
h = await createHarness("sitecaps");
registry = createCapabilityRegistry({ logger: h.ctx.logger, db: h.db, settings: h.ctx.settings });
registerSourcesCapabilities(registry, () => h.rt);
const r = await h.req("/sites", {
body: {
key: "audiences",
name: "观众",
adapter: "nexusphp",
baseUrl: `${mock.baseUrl}/`,
rateLimit: { minIntervalMs: 0, concurrency: 10 },
},
});
siteId = ((await r.json()) as { data: { id: string } }).data.id;
const c = await h.req(`/sites/${siteId}/credentials`, {
method: "PUT",
body: { kind: "password", username: "alice", password: PASSWORD },
});
expect(c.status).toBe(200);
});
afterAll(async () => {
await h?.close();
await mock?.close();
});
it("四个站点能力都挂上处理器", () => {
const ids = registry.list().map((c) => c.descriptor.id);
for (const id of SITE_IDS) expect(ids).toContain(id);
});
it("site.refresh_login:没有持续授权 → 拒绝,账号不动", async () => {
await expect(registry.invoke("site.refresh_login", { siteId }, agentCtx())).rejects.toThrow();
const acc = await h.db.selectFrom("site_account").select(["status"]).where("site_id", "=", siteId).execute();
expect(acc.map((a) => a.status)).toEqual(["unknown"]);
});
it("site.refresh_login:有持续授权 → 登录成功并拉用户数据;输出脱敏", async () => {
await h.db.insertInto("automation_grant").values({ action: "site.refresh_login", granted_by: "test" }).execute();
const out = (await registry.invoke("site.refresh_login", { siteId }, agentCtx())) as {
ok: boolean;
status: string;
userData: { upload: number } | null;
};
expect(out).toMatchObject({ ok: true, status: "active", reason: null });
expect(out.userData?.upload).toBe(12.5 * TiB);
await assertRedacted(out);
const audits = await h.db
.selectFrom("audit_event")
.select(["action"])
.where("target_id", "=", "site.refresh_login")
.execute();
expect(audits.map((a) => a.action)).toEqual(expect.arrayContaining(["capability.denied", "capability.invoke"]));
});
it("site.list:健康、账号状态与凭证有无;不含凭证、Cookie、secret 引用", async () => {
const out = (await registry.invoke("site.list", {}, agentCtx())) as {
items: { id: string; accountStatus: string; accounts: { hasSession: boolean; status: string }[] }[];
};
const item = out.items.find((s) => s.id === siteId);
expect(item).toMatchObject({ key: "audiences", enabled: true, accountStatus: "active" });
expect(item?.accounts[0]).toMatchObject({ status: "active", hasSession: true, authKind: "password" });
await assertRedacted(out);
// 停用站点缺省不列
await h.db.updateTable("site").set({ enabled: false }).where("id", "=", siteId).execute();
const hidden = (await registry.invoke("site.list", {}, agentCtx())) as { items: unknown[] };
expect(hidden.items).toHaveLength(0);
const all = (await registry.invoke("site.list", { includeDisabled: true }, agentCtx())) as { items: unknown[] };
expect(all.items).toHaveLength(1);
await h.db.updateTable("site").set({ enabled: true }).where("id", "=", siteId).execute();
});
it("site.user_data:最新用户数据 + 按天历史", async () => {
const out = (await registry.invoke("site.user_data", { siteId }, agentCtx())) as {
accounts: { userData: { seeding: number } | null }[];
history: { upload: number }[];
};
expect(out.accounts).toHaveLength(1);
expect(out.accounts[0]?.userData?.seeding).toBe(31);
expect(out.history).toHaveLength(1);
expect(out.history[0]?.upload).toBe(12.5 * TiB);
await assertRedacted(out);
});
it("site.health_check:execute 同样要授权;授权后写回健康列", async () => {
await expect(registry.invoke("site.health_check", { siteId }, agentCtx())).rejects.toThrow();
await h.db.insertInto("automation_grant").values({ action: "site.health_check", granted_by: "test" }).execute();
const out = (await registry.invoke("site.health_check", { siteId }, agentCtx())) as {
ok: boolean;
healthStatus: string;
};
expect(out).toMatchObject({ siteId, ok: true, loggedIn: true, healthStatus: "healthy" });
await assertRedacted(out);
const s = await h.db
.selectFrom("site")
.select(["health_status", "last_health_at"])
.where("id", "=", siteId)
.executeTakeFirstOrThrow();
expect(s.health_status).toBe("healthy");
expect(s.last_health_at).toBeTruthy();
});
it("不存在的站点:明确报错", async () => {
await expect(registry.invoke("site.user_data", { siteId: randomUUID() }, agentCtx())).rejects.toThrow(/站点不存在/);
});
});