深化20条目录资料并保留发现来源审计

apps/docs/scripts/auth-cli.ts

@@ -188,7 +188,7 @@ async function main() {
   assert.equal(research.companies.length, 1015);
   assert.equal(research.categories.length, 11);
   assert.equal(research.evidence.length, 1086);
-  assert.equal(research.observations.length, 151);
+  assert.equal(research.observations.length, 155);
   assert.equal((await request("/api/research/ai-companies", { method: "POST", headers })).status, 405);
   const researchPage = await request("/docs/other-research/ai-company-research/overview", { headers });
   assert.equal(researchPage.status, 200);

apps/docs/src/lib/ai-research.ts

@@ -14,6 +14,7 @@ export type ResearchCompany = {
   extraUrl?: string; pricingEvidence?: string;
   businessModel?: string; entityBasis?: string;
   profileOnly?: boolean; classificationBasis?: string; directoryTags?: string[];
+  directoryOrigin?: "yc-2025-2026";
   technicalReview?: {
     level: "description" | "public-artifact" | "independent-test";
     reviewedAt: string; summary: string; evidenceIds: string[]; testScope?: string;
@@ -81,6 +82,8 @@ export function validateResearch(snapshot: ResearchSnapshot) {
       throw new Error(`Invalid technical review: ${c.id}`);
     if (c.profileOnly && (c.revenueStatus !== "unknown" || !c.classificationBasis))
       throw new Error(`Invalid profile-only research record: ${c.id}`);
+    if (c.directoryOrigin && (c.directoryOrigin !== "yc-2025-2026" || !/^YC\d+$/.test(c.id)))
+      throw new Error(`Invalid research directory origin: ${c.id}`);
     if (!categories.has(c.cat) || !evidenceUrl(c.url) ||
         c.evidenceIds.some((id) => !evidence.has(id)) ||
         (c.pricingEvidence && !evidence.has(c.pricingEvidence)))
@@ -99,7 +102,7 @@ export function validateResearch(snapshot: ResearchSnapshot) {
   if (coverage && (coverage.profilesRead + coverage.failedProfiles !== coverage.candidateRecords ||
       coverage.matchingProfiles !== coverage.existingProfiles + coverage.newProfiles ||
       coverage.matchingProfiles + coverage.otherOrMissingYear + coverage.unclearAI + coverage.dateConflicts !== coverage.profilesRead ||
-      snapshot.companies.filter((c) => c.profileOnly).length !== coverage.newProfiles || !evidenceUrl(coverage.source)))
+      snapshot.companies.filter((c) => c.profileOnly || c.directoryOrigin === "yc-2025-2026").length !== coverage.newProfiles || !evidenceUrl(coverage.source)))
     throw new Error("Invalid research coverage accounting");
   for (const r of snapshot.reviews)
     if (r.evidenceIds.some((id) => !evidence.has(id)) ||

apps/docs/tests/research.test.ts

@@ -25,7 +25,7 @@ test("research revisions share the authentication database and preserve replay l
     const initial = readResearchSnapshot();
     assert.equal(initial.companies.length, 1015);
     assert.equal(initial.evidence.length, 1086);
-    assert.equal(initial.observations.length, 151);
+    assert.equal(initial.observations.length, 155);
     assert.deepEqual(readResearchSnapshot(), initial, "reopening does not duplicate records");
     const db = openSiteDatabase();
     const tables = db.prepare("SELECT name FROM sqlite_master WHERE type='table'").all() as { name: string }[];
@@ -62,7 +62,7 @@ test("research validation rejects broken evidence and unsafe source links", () =
 
 test("reviews link explicit companies without turning global or excluded cases into companies", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 28);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 29);
   assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 3);
   assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 8);
   const review = snapshot.reviews.find((r) => r.id === "R4")!;
@@ -84,10 +84,10 @@ test("disclosure counts exclude client income, biographies, targets and duplicat
   const snapshot = seed as ResearchSnapshot;
   const summary = categorySummary(snapshot);
   assert.equal(summary.reduce((n, c) => n + c.count, 0), 1015);
-  assert.equal(summary.reduce((n, c) => n + c.self, 0), 17);
+  assert.equal(summary.reduce((n, c) => n + c.self, 0), 18);
   assert.equal(summary.reduce((n, c) => n + c.estimate, 0), 1);
   assert.equal(summary.reduce((n, c) => n + c.platform, 0), 16);
-  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 981);
+  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 980);
   assert.equal(snapshot.companies.find((c) => c.name === "Rork")?.revenueStatus, "unknown");
   assert.equal(snapshot.companies.find((c) => c.name === "Result")?.revenueStatus, "unknown");
   assert.ok(snapshot.observations.filter((o) => o.selection === "signal").every((o) => o.scope === "公司整体"));
@@ -167,15 +167,22 @@ test("directory coverage reconciles every candidate and keeps profile-only incom
   assert.equal(count("ai-unclear"), coverage.unclearAI);
   for (const row of coverageAudit.records.filter((r) => r.status === "imported")) {
     const company = snapshot.companies.find((c) => c.id === `YC${row.ycId}`)!;
-    assert.ok(company.profileOnly);
+    assert.ok(company.profileOnly || company.directoryOrigin === "yc-2025-2026");
     assert.equal(company.url, row.source);
-    assert.equal(company.revenueStatus, "unknown");
+    if (company.profileOnly) assert.equal(company.revenueStatus, "unknown");
     assert.equal(company.year, row.foundedYear);
     assert.ok([2025, 2026].includes(company.year!));
   }
   const invalid = structuredClone(snapshot);
   invalid.coverage!.newProfiles += 1;
   assert.throws(() => validateResearch(invalid), /coverage accounting/);
+  const promoted = snapshot.companies.find((c) => c.id === "YC30215")!;
+  assert.equal(promoted.profileOnly, false);
+  assert.equal(promoted.directoryOrigin, "yc-2025-2026");
+  assert.equal(promoted.revenueStatus, "self");
+  const lostOrigin = structuredClone(snapshot);
+  delete lostOrigin.companies.find((c) => c.id === promoted.id)!.directoryOrigin;
+  assert.throws(() => validateResearch(lostOrigin), /coverage accounting/);
 });
 
 test("income descriptions report sample dispersion and maximum-value sensitivity", () => {