新增支付平台收入样本与分布分析

apps/docs/tests/research.test.ts

@@ -5,11 +5,13 @@ import { join } from "node:path";
 import { tmpdir } from "node:os";
 import seed from "../../../content/research/ai-companies.seed.json";
 import coverageAudit from "../../../content/research/ai-companies.coverage.json";
+import incomeReference from "../../../content/research/ai-income-analysis.json";
 import { readResearchSnapshot } from "../src/lib/ai-research-store";
 import { openSiteDatabase } from "../src/lib/site-database";
 import { categorySummary, evidenceUrl, validateResearch, type ResearchSnapshot } from "../src/lib/ai-research";
 import { consumeCode, initializeStore } from "../src/lib/auth-store";
 import { newAuthConfig } from "../src/lib/auth";
+import { describeIncome, groupIncome, platformIncomeSample } from "../src/lib/research-statistics";
 
 test("research revisions share the authentication database and preserve replay limits", () => {
   const dir = mkdtempSync(join(tmpdir(), "site-research-"));
@@ -21,9 +23,9 @@ test("research revisions share the authentication database and preserve replay l
     for (let i = 0; i < 20; i++) consumeCode(config, "invalid");
     assert.equal(consumeCode(config, "invalid"), "limited");
     const initial = readResearchSnapshot();
-    assert.equal(initial.companies.length, 986);
-    assert.equal(initial.evidence.length, 1035);
-    assert.equal(initial.observations.length, 75);
+    assert.equal(initial.companies.length, 1002);
+    assert.equal(initial.evidence.length, 1055);
+    assert.equal(initial.observations.length, 126);
     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 }[];
@@ -61,9 +63,10 @@ test("research validation rejects broken evidence and unsafe source links", () =
 test("disclosure counts exclude client income, biographies, targets and duplicate milestones", () => {
   const snapshot = seed as ResearchSnapshot;
   const summary = categorySummary(snapshot);
-  assert.equal(summary.reduce((n, c) => n + c.count, 0), 986);
+  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1002);
   assert.equal(summary.reduce((n, c) => n + c.self, 0), 8);
   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), 977);
   assert.equal(snapshot.companies.find((c) => c.name === "Rork")?.revenueStatus, "unknown");
   assert.equal(snapshot.companies.find((c) => c.name === "Result")?.revenueStatus, "unknown");
@@ -110,3 +113,74 @@ test("directory coverage reconciles every candidate and keeps profile-only incom
   invalid.coverage!.newProfiles += 1;
   assert.throws(() => validateResearch(invalid), /coverage accounting/);
 });
+
+test("income descriptions report sample dispersion and maximum-value sensitivity", () => {
+  const stats = describeIncome([100, 200, 300])!;
+  assert.equal(stats.mean, 200);
+  assert.equal(stats.median, 200);
+  assert.equal(stats.sampleDeviation, 100);
+  assert.equal(stats.cv, .5);
+  assert.equal(stats.largestShare, .5);
+  assert.equal(stats.meanWithoutLargest, 150);
+  assert.equal(stats.largestRemovalDrop, .25);
+  assert.equal(describeIncome([5])!.cv, null);
+  assert.equal(describeIncome([0, 0])!.mean, 0, "observed zero is distinct from missing");
+  assert.equal(describeIncome([0, 0])!.cv, null);
+  assert.equal(describeIncome([]), null);
+  assert.equal(describeIncome([100, NaN]), null);
+  assert.equal(describeIncome([-1]), null);
+  assert.ok(describeIncome([1, 2, 100])!.largestRemovalDrop! > .95);
+});
+
+test("platform samples exclude stale data and keep ARR, estimates and collections separate", () => {
+  const snapshot = seed as ResearchSnapshot;
+  const recent = platformIncomeSample(snapshot, { windowDays: 7 });
+  assert.equal(recent.points.length, 14);
+  assert.equal(recent.excluded.length, 3);
+  assert.ok(recent.points.every((p) => p.observation.metric === "mrr" && p.observation.selection === "platform"));
+  assert.deepEqual(new Set(recent.excluded.map((p) => p.observation.company)), new Set(["AI016", "MR013", "MR014"]));
+  assert.ok(recent.points.some((p) => p.company.name === "TrackAI" && p.observation.connectionExpired), "dated recent value is not a claim of active connection");
+  const older = platformIncomeSample(snapshot, { windowDays: 90 });
+  assert.equal(older.points.length, 15);
+  assert.ok(older.points.some((p) => p.company.id === "AI016"));
+  const scaled = platformIncomeSample(snapshot, { windowDays: 7, annualize: true });
+  const monthlyGroups = groupIncome(recent.points);
+  const annualGroups = groupIncome(scaled.points);
+  for (const group of monthlyGroups) {
+    const annual = annualGroups.find((g) => g.key === group.key)!;
+    assert.ok(Math.abs(annual.stats.mean - group.stats.mean * 12) < 1e-6);
+    if (group.stats.cv !== null) assert.ok(Math.abs(annual.stats.cv! - group.stats.cv) < 1e-10);
+  }
+  const invalid = structuredClone(snapshot);
+  invalid.observations = invalid.observations.filter((o) => o.company === "MR001" && o.metric === "mrr");
+  const first = invalid.observations[0];
+  invalid.observations.push({ ...first, id: "future", observedAt: "2026-11-01", value: 999999 });
+  invalid.observations.push({ ...first, id: "bad-date", observedAt: "2026-02-30", value: 999999 });
+  invalid.observations.push({ ...first, id: "currency", unit: "EUR", value: 999999 });
+  invalid.observations.push({ ...first, id: "older", observedAt: "2026-10-28", value: 1 });
+  const selected = platformIncomeSample(invalid, { windowDays: 7 });
+  assert.equal(selected.points.length, 1);
+  assert.equal(selected.points[0].observation.id, first.id, "bad newer data and older duplicate must not replace latest valid point");
+  assert.equal(selected.excluded.length, 4);
+  assert.throws(() => platformIncomeSample(snapshot, { windowDays: -1 }), /window/);
+});
+
+test("distribution statistics match independently calculated snapshot references", () => {
+  const snapshot = seed as ResearchSnapshot;
+  assert.equal(incomeReference.sourceVersion, snapshot.version);
+  for (const reference of incomeReference.windows) {
+    const sample = platformIncomeSample(snapshot, { windowDays: reference.days });
+    assert.deepEqual(new Set(sample.points.map((p) => p.company.id)), new Set(reference.products));
+    const groups = groupIncome(sample.points);
+    assert.equal(groups.length, reference.groups.length);
+    for (const expected of reference.groups) {
+      const actual = groups.find((g) => g.category === expected.category && g.provider === expected.provider && g.model === expected.model)!;
+      assert.equal(actual.stats.n, expected.n);
+      for (const metric of ["mean", "median", "sampleDeviation", "cv", "meanWithoutLargest", "largestRemovalDrop"] as const) {
+        const value = expected[metric];
+        if (value === null) assert.equal(actual.stats[metric], null);
+        else assert.ok(Math.abs(actual.stats[metric]! - value) < 1e-6, metric);
+      }
+    }
+  }
+});