import test from "node:test";
import assert from "node:assert/strict";
import { mkdtempSync, rmSync } from "node:fs";
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, reviewCompanyIds, validateResearch, type ResearchSnapshot } from "../src/lib/ai-research";
import { consumeCode, initializeStore } from "../src/lib/auth-store";
import { newAuthConfig } from "../src/lib/auth";
import { arrDisclosures, describeIncome, groupIncome, platformIncomeSample } from "../src/lib/research-statistics";

test("ARR ledger preserves historical estimates without promoting targets, run rates or outside-cohort claims", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const rows = arrDisclosures(snapshot);
  const ids = new Set(rows.map((row) => row.observation.id));
  for (const id of ["O064", "O065", "O066", "O069", "O070", "O071", "O046"])
    assert.ok(ids.has(id), `${id}: historical claims, estimates and unknown currencies remain visible`);
  for (const id of ["O050", "O052", "O053", "O055", "SR-O-AI067-runrate", "ROCKET-O-arr", "AQ-O-RUNRATE"])
    assert.ok(!ids.has(id), `${id}: excluded or ambiguous records cannot enter the ARR ledger`);
  assert.equal(rows.find((row) => row.observation.id === "O066")?.observation.selection, "historical-estimate");
  assert.equal(rows.find((row) => row.observation.id === "O046")?.observation.unit, "原文$，币种待核");
  const category = snapshot.companies.find((company) => company.id === "AI055")!.cat;
  const filtered = arrDisclosures(snapshot, { category, foundedYear: 2025 });
  assert.ok(filtered.length > 0);
  assert.ok(filtered.every((row) => row.company.cat === category && row.company.year === 2025));
  // A future mistakenly typed target still must not enter the ledger.
  const target = snapshot.observations.find((item) => item.id === "O052")!;
  target.metric = "arr";
  target.company = "AI055";
  assert.ok(!arrDisclosures(snapshot).some((row) => row.observation.id === target.id));
  const claim = snapshot.observations.find((item) => item.id === "O065")!;
  claim.value = Number.NaN;
  assert.ok(!arrDisclosures(snapshot).some((row) => row.observation.id === claim.id));
});

test("research revisions share the authentication database and preserve replay limits", () => {
  const dir = mkdtempSync(join(tmpdir(), "site-research-"));
  const previous = process.env.AUTH_CONFIG_FILE;
  process.env.AUTH_CONFIG_FILE = join(dir, "config.json");
  try {
    initializeStore();
    const config = newAuthConfig();
    for (let i = 0; i < 20; i++) consumeCode(config, "invalid");
    assert.equal(consumeCode(config, "invalid"), "limited");
    const initial = readResearchSnapshot();
    assert.equal(initial.companies.length, 1187);
    assert.equal(initial.evidence.length, 4340);
    assert.equal(initial.observations.length, 453);
    assert.deepEqual(initial.candidateBatches, seed.candidateBatches, "candidate gaps persist in the same database metadata");
    assert.deepEqual(initial.directoryRechecks, seed.directoryRechecks, "follow-up classifications persist without rewriting the discovery audit");
    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 }[];
    assert.ok(tables.some((r) => r.name === "login_state"));
    assert.ok(tables.some((r) => r.name === "research_companies"));
    assert.equal(db.prepare("PRAGMA foreign_keys").get()?.foreign_keys, 1);
    db.close();
    const next = structuredClone(seed) as ResearchSnapshot;
    next.version += "-revision-test";
    next.companies[0].name = "Revised company";
    assert.equal(readResearchSnapshot(next).companies[0].name, "Revised company");
    assert.deepEqual(readResearchSnapshot(), initial, "old release still reads its original revision");
    assert.equal(consumeCode(config, "invalid"), "limited", "research import must not reset auth limits");
    const collision = structuredClone(seed) as ResearchSnapshot;
    collision.companies[0].name = "Changed without revision";
    assert.throws(() => readResearchSnapshot(collision), /new revision/);
    assert.deepEqual(readResearchSnapshot(), initial, "failed import leaves valid revision intact");
  } finally {
    if (previous === undefined) delete process.env.AUTH_CONFIG_FILE;
    else process.env.AUTH_CONFIG_FILE = previous;
    rmSync(dir, { recursive: true, force: true });
  }
});

test("research validation rejects broken evidence and unsafe source links", () => {
  validateResearch(seed as ResearchSnapshot);
  const invalid = structuredClone(seed) as ResearchSnapshot;
  invalid.observations[0].evidence = "missing";
  assert.throws(() => validateResearch(invalid), /observation/);
  assert.equal(evidenceUrl("javascript:alert(1)"), undefined);
  assert.equal(evidenceUrl("/local-link"), undefined);
  assert.equal(evidenceUrl("https://example.com/evidence"), "https://example.com/evidence");
});

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, 198);
  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 97);
  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 44);
  const review = snapshot.reviews.find((r) => r.id === "R4")!;
  assert.deepEqual(reviewCompanyIds(snapshot, review), ["AI007", "AI013", "AI021", "AI034"]);
  assert.deepEqual(reviewCompanyIds(snapshot, snapshot.reviews.find((r) => r.id === "CN-R-PSI")!), []);
  const oldReview = structuredClone(snapshot.reviews.find((r) => r.id === "TECH-GRAD-R-SCOPE")!);
  delete oldReview.scope;
  delete oldReview.companyIds;
  assert.deepEqual(reviewCompanyIds(snapshot, oldReview), ["AI051"], "old revisions retain evidence-owner fallback");
  review.companyIds = ["unknown-company"];
  assert.throws(() => validateResearch(snapshot), /research review/);
  review.companyIds = ["AI007", "AI007"];
  assert.throws(() => validateResearch(snapshot), /research review/);
  review.companyIds = [];
  assert.throws(() => validateResearch(snapshot), /research review/);
});

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), 1187);
  assert.equal(summary.reduce((n, c) => n + c.self, 0), 58);
  assert.equal(summary.reduce((n, c) => n + c.estimate, 0), 2);
  assert.equal(summary.reduce((n, c) => n + c.platform, 0), 19);
  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1108);
  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"));
  const arena = snapshot.observations.find((o) => o.id === "COARENA-O-CUMULATIVE")!;
  assert.equal(arena.selection, "historical", "cumulative launch revenue is not a recurring company-wide signal");
  assert.equal(arena.comparisonGroup, null);
  assert.ok(arena.metric !== "mrr" && arena.metric !== "arr", "a two-week cumulative figure cannot become MRR or ARR");
});

test("service run rates, legacy freight revenue and paid adoption do not become platform ARR", () => {
  const snapshot = seed as ResearchSnapshot;
  const runRate = snapshot.observations.find((o) => o.id === "INDUSTRY11-O-LOCKE-RUNRATE")!;
  assert.equal(runRate.metric, "annualized-revenue");
  assert.equal(runRate.selection, "historical");
  assert.equal(runRate.observedAt, undefined);
  assert.equal(runRate.comparisonGroup, null);
  assert.equal(snapshot.companies.find((c) => c.id === "YC33283")?.revenueStatus, "self");
  for (const id of ["TRUEMILE-OLD-REV", "VELTHA-DEMO", "LANTERN-OLD-REV"]) {
    const observation = snapshot.observations.find((o) => o.id === `INDUSTRY11-O-${id}`)!;
    assert.equal(observation.selection, "excluded");
    assert.equal(observation.metric, undefined);
    assert.equal(observation.comparisonGroup, null);
  }
  for (const [id, company] of [["VERDANT-DEPLOY", "YC32189"], ["SUTRIX-PAID", "YC36576"]]) {
    const observation = snapshot.observations.find((o) => o.id === `INDUSTRY11-O-${id}`)!;
    assert.equal(observation.selection, "adoption");
    assert.equal(observation.metric, undefined);
    assert.equal(snapshot.companies.find((c) => c.id === company)?.revenueStatus, "unknown");
  }
  assert.ok(platformIncomeSample(snapshot, { windowDays: 90 }).points.every((point) => !point.observation.id.startsWith("INDUSTRY11-")));
});

test("technical reviews keep accessible materials separate from tested capabilities", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 172);
  assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 24);
  assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
  assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
  assert.match(snapshot.companies.find((c) => c.id === "AI051")!.technicalReview!.testScope!, /Sep 2026/);
  assert.ok(snapshot.observations.filter((o) => o.id.startsWith("TECH-GRAD-O-")).every((o) => o.selection === "technical" && o.comparisonGroup === null));
  const company = snapshot.companies.find((c) => c.id === "AI061")!;
  const review = company.technicalReview!;
  review.evidenceIds = ["missing-technical-evidence"];
  assert.throws(() => validateResearch(snapshot), /technical review/);
  review.evidenceIds = ["TECH-NAIVE-HF"];
  review.reviewedAt = "2026-02-30";
  assert.throws(() => validateResearch(snapshot), /technical review/);
  review.reviewedAt = "2099-01-01";
  assert.throws(() => validateResearch(snapshot), /technical review/);
  review.reviewedAt = snapshot.asOf;
  review.level = "independent-test";
  assert.throws(() => validateResearch(snapshot), /technical review/,
    "an accessible artifact cannot become a test record without a stated test scope");
});

test("ambiguous ARR claims retain currency, precision and attribution limits", () => {
  const snapshot = seed as ResearchSnapshot;
  const variant = snapshot.observations.filter((o) => o.company === "AI066");
  assert.deepEqual(variant.filter((o) => o.selection === "crosscheck").map((o) => o.value).sort(), [500000, 600000]);
  assert.equal(variant.filter((o) => o.selection === "signal").length, 0);
  assert.ok(variant.filter((o) => [2500000, 40000000].includes(o.value)).every((o) => o.selection === "excluded"));
  const codos = snapshot.observations.find((o) => o.id === "SR-O-AI065-arr")!;
  assert.equal(codos.bound, "≥");
  assert.equal(codos.unit, "币种未注明");
  assert.equal(codos.comparisonGroup, null);
  assert.ok(snapshot.observations.filter((o) => o.id.startsWith("SR-O-")).every((o) => o.comparisonGroup === null && o.unit !== "USD"));
  assert.equal(snapshot.companies.find((c) => c.id === "AI071")?.year, 2021);
  const rocket = snapshot.observations.find((o) => o.id === "ROCKET-O-arr")!;
  assert.equal(rocket.selection, "historical");
  assert.equal(rocket.comparisonGroup, null);
  assert.notEqual(rocket.scope, "公司整体");
  assert.equal(snapshot.companies.find((c) => c.id === "AI070")?.revenueStatus, "unknown");
  assert.equal(snapshot.observations.filter((o) => o.company === "AI070").length, 0,
    "unreadable announcement summaries do not become numeric ARR");
  const waitlist = snapshot.observations.find((o) => o.id === "SR25-O-OMI-WAITLIST")!;
  assert.equal(waitlist.selection, "excluded", "waitlist conversions are not paid recurring revenue");
  assert.equal(snapshot.companies.find((c) => c.id === waitlist.company)?.revenueStatus, "unknown");
  const bluma = snapshot.observations.find((o) => o.id === "BLUMA-O-HISTORICAL-MRR")!;
  assert.equal(bluma.selection, "historical");
  assert.ok(bluma.unit !== "USD" && !bluma.observedAt && bluma.comparisonGroup === null);
  const native = snapshot.observations.find((o) => o.id === "NATIVE-O-ARR-CLAIM")!;
  assert.equal(native.selection, "crosscheck");
  assert.ok(!native.metric && !native.observedAt && native.comparisonGroup === null);
  const marketVolume = snapshot.observations.find((o) => o.id === "PALISADE-O-GMV")!;
  assert.equal(marketVolume.selection, "excluded", "customer GMV must not establish company revenue or ARR");
  assert.equal(snapshot.companies.find((c) => c.id === marketVolume.company)?.revenueStatus, "unknown");
  const pingo = snapshot.observations.find((o) => o.id === "PINGO-O-MRR-JUL25")!;
  assert.equal(pingo.selection, "historical", "a July 2025 self-report is not a current payment-platform sample");
  assert.ok(pingo.unit !== "USD" && !pingo.observedAt && pingo.comparisonGroup === null);
  const designService = snapshot.observations.find((o) => o.id === "SEMIOTIC-O-LAUNCH-REVENUE")!;
  assert.equal(designService.selection, "historical");
  assert.ok(!designService.metric && designService.comparisonGroup === null, "four-week service revenue is not MRR or ARR");
  const restaurantAdoption = snapshot.observations.filter((o) => o.company === "YC32815");
  assert.ok(restaurantAdoption.length > 0 && restaurantAdoption.every((o) => o.selection === "adoption" && !o.metric),
    "restaurant count and list price must not produce an invented MRR observation");
  const fishPilot = snapshot.observations.find((o) => o.id === "OCTAPULSE-O-CONTRACT")!;
  assert.equal(fishPilot.selection, "excluded", "a paid pilot or annual contract does not establish recognized recurring revenue");
  assert.equal(snapshot.companies.find((c) => c.id === fishPilot.company)?.revenueStatus, "unknown");
  assert.equal(fishPilot.comparisonGroup, null);
  assert.notEqual(fishPilot.unit, "USD", "six-figure wording does not establish the currency");
  assert.ok(!fishPilot.metric && !fishPilot.observedAt, "the publication date is not the financial reporting date");
  const cedar = snapshot.observations.filter((o) => o.company === "AI102");
  assert.ok(cedar.every((o) => o.selection !== "signal" && o.comparisonGroup === null),
    "closed and contracted amounts without recognition or period do not establish ARR");
  assert.equal(snapshot.observations.find((o) => o.id === "SR25-O-LOOPS-CUSTOMER-SALES")?.selection, "excluded");
  const portfolio = snapshot.observations.filter((o) => o.company === "AI100");
  assert.deepEqual(portfolio.filter((o) => o.selection === "signal").map((o) => o.id), ["SR25-O-DRS-PORTFOLIO"],
    "a product milestone must not be added to its company portfolio as another company");
  assert.ok(snapshot.observations.filter((o) => o.id.startsWith("SR25-O-")).every((o) =>
    o.unit !== "USD" && !o.metric && !o.observedAt && o.comparisonGroup === null),
  "access dates and dollar symbols must not invent dated USD income samples");
});

// Retractions and forecasts must stay visible for review without becoming revenue signals.
test("retracted ARR and projected margins remain excluded", () => {
  const snapshot = seed as ResearchSnapshot;
  const cluely = snapshot.companies.find((c) => c.name === "Cluely")!;
  assert.equal(cluely.revenueStatus, "unknown");
  assert.ok(snapshot.reviews.some((r) => r.company === "Cluely" && r.evidenceIds.includes("E100")));
  const retracted = snapshot.observations.filter((o) => o.company === cluely.id);
  assert.ok(retracted.length > 0);
  assert.ok(retracted.every((o) => o.selection === "excluded"));
  const forecast = snapshot.observations.find((o) => o.kind === "非GAAP毛利率预期")!;
  assert.equal(forecast.selection, "excluded");
  const peec = snapshot.companies.find((c) => c.name === "Peec AI")!;
  assert.equal(peec.team, 100);
  assert.equal(peec.teamBound, "≥");
  const currentTeam = snapshot.observations.find((o) => o.id === "PEEC-JOB-TEAM")!;
  assert.equal(currentTeam.value, peec.team);
  assert.equal(currentTeam.bound, peec.teamBound);
  const historicalTeam = snapshot.observations.find((o) => o.id === "O067")!;
  assert.equal(historicalTeam.value, 70);
  assert.equal(historicalTeam.bound, ">");
  assert.equal(snapshot.observations.filter((o) => o.company === peec.id && o.selection === "signal").length, 1);
  assert.ok(snapshot.observations.some((o) => o.company === peec.id && o.selection === "historical-estimate"));
});

test("directory coverage reconciles every candidate and keeps profile-only income unknown", () => {
  const snapshot = seed as ResearchSnapshot;
  const coverage = snapshot.coverage!;
  assert.equal(coverageAudit.records.length, coverage.candidateRecords);
  assert.equal(new Set(coverageAudit.records.map((r) => r.ycId)).size, coverage.candidateRecords);
  const count = (status: string) => coverageAudit.records.filter((r) => r.status === status).length;
  assert.equal(count("imported"), coverage.newProfiles);
  assert.equal(count("existing"), coverage.existingProfiles);
  assert.equal(count("date-conflict"), coverage.dateConflicts);
  assert.equal(count("year-outside-or-missing"), coverage.otherOrMissingYear);
  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 || company.directoryOrigin === "yc-2025-2026");
    assert.equal(company.url, row.source);
    if (company.profileOnly) assert.equal(company.revenueStatus, "unknown");
    if (company.id === "YC31370") {
      assert.equal(row.foundedYear, 2025, "original discovery remains unchanged");
      assert.equal(company.year, null, "a pivot year cannot settle the company founding year");
      assert.ok(snapshot.reviews.some((review) => review.id === "DAYJOB-R-COHORT" && review.companyIds?.includes(company.id)));
    } else if (company.id === "YC36279") {
      assert.equal(row.foundedYear, 2026, "original Native discovery remains unchanged");
      assert.equal(company.year, null, "a model launch and YC date cannot settle the older business founding year");
      assert.ok(snapshot.reviews.some((review) => review.id === "NATIVE-R-COHORT" && review.companyIds?.includes(company.id)));
    } else if (company.id === "YC31470") {
      assert.equal(row.foundedYear, 2025, "original Tasklet discovery remains unchanged");
      assert.equal(company.year, null, "a new product cannot establish a new company founding year");
      assert.ok(snapshot.reviews.some((review) => review.id === "ENTERPRISE3-R-TASKLET" && review.companyIds?.includes(company.id)));
    } else {
      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("business pivots and procurement volume do not become comparable startup ARR", () => {
  const snapshot = seed as ResearchSnapshot;
  const dayjob = snapshot.companies.find((company) => company.id === "YC31370")!;
  assert.equal(dayjob.year, null);
  assert.equal(dayjob.directoryOrigin, "yc-2025-2026");
  const milestones = snapshot.observations.filter((observation) => observation.company === dayjob.id);
  assert.deepEqual(milestones.filter((observation) => observation.selection === "crosscheck").map((observation) => observation.value).sort(), [496000, 653000]);
  assert.ok(milestones.every((observation) => observation.comparisonGroup === null && !observation.metric && !observation.observedAt));
  assert.ok(milestones.filter((observation) => [150000, 800000].includes(observation.value)).every((observation) => observation.selection === "excluded"));
  const procurement = snapshot.observations.find((observation) => observation.id === "SAUDARA-O-SOURCING")!;
  assert.equal(procurement.selection, "excluded");
  assert.equal(procurement.comparisonGroup, null);
});

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, 16);
  assert.equal(recent.excluded.length, 4);
  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", "MR017"]));
  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, 18);
  assert.ok(older.points.some((p) => p.company.id === "AI016"));
  assert.ok(!recent.points.some((p) => p.company.id === "MR017"));
  assert.ok(older.points.some((p) => p.company.id === "MR017" && p.observation.connectionExpired),
    "an expired connection retains its historical observation date in the wider window");
  assert.equal(recent.points.find((p) => p.company.id === "MR018")?.value, 67864,
    "an older Markdown cache must not replace or duplicate the later web snapshot");
  assert.equal(recent.points.find((p) => p.company.id === "MR019")?.value, 65431,
    "period-table revenue and revenue snapshots must not replace MRR");
  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);
      }
    }
  }
});


test("product launch candidates preserve unresolved years and many launches per company", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const batch = snapshot.candidateBatches![0];
  assert.equal(batch.complete, false);
  assert.equal(batch.records.length, 19);
  const kilo = batch.records.filter((r) => r.companyId === "AI072");
  assert.equal(kilo.length, 2, "IDE and hosted products resolve to one company");
  assert.equal(snapshot.companies.filter((c) => c.id === "AI072").length, 1);
  assert.ok(batch.records.some((r) => r.status === "pending-year" && !r.companyId));
  assert.ok(batch.records.some((r) => r.status === "existing-outside-cohort" && r.companyId === "AI054"));
  kilo[0].companyId = "missing-company";
  assert.throws(() => validateResearch(snapshot), /research candidate/);
});

test("annual launch archives exclude older companies only with evidence and reuse existing records", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "PH-2025-visible-1")!;
  assert.equal(batch.complete, false);
  assert.equal(batch.records.length, 19);
  const older = batch.records.filter((r) => r.status === "outside-cohort");
  assert.equal(older.length, 16);
  assert.ok(older.every((r) => !r.companyId && r.evidenceIds?.length));
  assert.equal(batch.records.find((r) => r.name === "Trace")?.companyId, "YC30687");
  const trace = snapshot.companies.find((c) => c.id === "YC30687")!;
  assert.equal(trace.profileOnly, false);
  assert.equal(trace.directoryOrigin, "yc-2025-2026");
  assert.equal(trace.revenueStatus, "unknown");
  assert.ok(!snapshot.observations.some((o) => o.evidence === "TRACE-HOME"), "demo metrics must not become reported results");
  older[0].evidenceIds = [];
  assert.throws(() => validateResearch(snapshot), /research candidate/);
  older[0].evidenceIds = ["missing-proof"];
  assert.throws(() => validateResearch(snapshot), /research candidate/);
});

test("unreconciled directory financials remain source reviews instead of income observations", () => {
  const snapshot = seed as ResearchSnapshot;
  const review = snapshot.reviews.find((r) => r.id === "PH-R-SOURCE-QUALITY")!;
  assert.equal(review.scope, "dataset");
  assert.ok(review.evidenceIds.includes("PH-TANA-DR"));
  assert.equal(reviewCompanyIds(snapshot, review).length, 0);
  assert.ok(!snapshot.observations.some((o) => o.evidence === "PH-TANA-DR"));
  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).filter((r) => r.status === "pending-year").length, 121);
});

test("product pivots and founder histories do not become new company years or current revenue", () => {
  const snapshot = seed as ResearchSnapshot;
  const pivot = snapshot.companies.find((c) => c.id === "AI073")!;
  assert.equal(pivot.year, null, "CRM launch is not a verified company founding year");
  assert.equal(pivot.revenueStatus, "unknown");
  const candidate = snapshot.candidateBatches!.flatMap((b) => b.records).find((r) => r.id === "PH26-11")!;
  assert.equal(candidate.status, "existing-outside-cohort");
  assert.equal(candidate.companyId, pivot.id);
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((point) => point.company.id === pivot.id));
  assert.ok(!snapshot.observations.some((o) => ["PH-FUNDRAISLY-ABOUT", "LF-PIVOT", "LF-HISTORY"].includes(o.evidence)), "other ventures' ARR, users and funding must not transfer");
  const candidates = snapshot.candidateBatches!.flatMap((b) => b.records);
  assert.equal(candidates.find((r) => r.id === "PH26-12")?.status, "outside-cohort",
    "a brand iteration with an earlier business chain is not a new company");
  const happycapy = candidates.find((r) => r.id === "PH26-04")!;
  assert.ok(happycapy.evidenceIds?.includes("FOLLOWUP-CAPY-ACRA"));
  assert.equal(happycapy.status, "pending-year", "a seller's registration does not establish a new global business");
  assert.equal(happycapy.companyId, undefined);
  assert.ok(!snapshot.observations.some((o) => o.evidence.startsWith("FOLLOWUP-")),
    "registration, funding, app-store prices and client amounts are not company income");
});

test("follow-up evidence can admit an uncertain directory candidate without rewriting its original status", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const followup = snapshot.directoryRechecks!.find((row) => row.ycId === 36088)!;
  const original = coverageAudit.records.find((row) => row.ycId === followup.ycId)!;
  assert.equal(original.status, "ai-unclear");
  assert.equal(followup.originalStatus, original.status);
  assert.equal(snapshot.companies.find((c) => c.id === followup.companyId)?.year, 2026);
  assert.equal(snapshot.candidateBatches!.flatMap((b) => b.records).find((r) => r.name === "OpenSEO")?.companyId, followup.companyId);
  assert.ok(!snapshot.observations.some((o) => ["SEO-PRICE", "UP-YC", "PAZI-PRICE"].includes(o.evidence)), "pricing, other ventures' ARR and prepaid balances stay outside income observations");
  followup.companyId = "missing-company";
  assert.throws(() => validateResearch(snapshot), /directory recheck/);
});

test("AI relevance follow-ups retain unresolved businesses and reuse existing company identities", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-1")!;
  assert.equal(batch.complete, false);
  assert.equal(batch.records.length, 24);
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(0, 24);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  const linked = batch.records.filter((r) => r.status === "linked");
  assert.equal(linked.length, 17);
  assert.equal(linked.filter((r) => r.companyId!.startsWith("YC")).length, 14);
  for (const [name, id] of [["Bud", "AI070"], ["Prism", "AI030"], ["Parametric", "AI014"]]) {
    assert.equal(linked.find((r) => r.name === name)?.companyId, id);
  }
  assert.equal(snapshot.companies.filter((c) => c.profileOnly || c.directoryOrigin === "yc-2025-2026").length, 928);
  for (const row of linked) {
    const ycId = Number(row.id.replace("YC-AI1-", ""));
    assert.equal(snapshot.directoryRechecks!.find((r) => r.ycId === ycId)?.companyId, row.companyId);
  }
  const pending = batch.records.filter((r) => r.status === "pending-ai");
  assert.equal(pending.length, 7);
  assert.ok(pending.every((r) => !r.companyId && r.evidenceIds!.length && /2025/.test(r.note)));
  assert.match(pending.find((r) => r.name === "Better Auth")!.note, /AI.*模块/);
  validateResearch(snapshot);
  pending[0].companyId = "AI014";
  assert.throws(() => validateResearch(snapshot), /research candidate/);
  delete pending[0].companyId;
  pending[0].evidenceIds = [];
  assert.throws(() => validateResearch(snapshot), /research candidate/);
});

test("historical monthly revenue and customer examples do not enter recurring platform comparisons", () => {
  const snapshot = seed as ResearchSnapshot;
  const monthly = snapshot.observations.find((o) => o.id === "UNCLEAR1-O-SCALAR-MONTHLY")!;
  assert.equal(monthly.value, 74000);
  assert.equal(monthly.selection, "historical");
  assert.equal(monthly.metric, undefined, "monthly revenue alone does not establish MRR or ARR");
  assert.equal(monthly.comparisonGroup, null);
  assert.equal(snapshot.companies.find((c) => c.id === "YC30514")!.revenueStatus, "self");
  for (const id of ["AMBY-CLIENT", "NIXO-EXAMPLE", "AUTOSTEP-WASTE"]) {
    assert.equal(snapshot.observations.find((o) => o.id === `UNCLEAR1-O-${id}`)!.selection, "excluded");
  }
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR1-")));
  const cua = snapshot.companies.find((c) => c.id === "YC30420")!;
  assert.equal(cua.cat, "C03");
  assert.equal(cua.revenueStatus, "unknown");
  assert.match(cua.businessModel!, /自备计算机/);
  assert.equal(cua.technicalReview!.level, "public-artifact");
});

test("a second uncertain cohort admits evidenced AI tasks while preserving autonomy and finance gaps", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-2")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(24, 48);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 13);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 11);
  for (const name of ["Albacore Inc.", "Perseus Defense", "Munify", "Ruvo", "DeepGrove"]) {
    const row = batch.records.find((r) => r.name === name)!;
    assert.equal(row.status, "pending-ai");
    assert.equal(row.companyId, undefined, "autonomy, a domain or finance automation alone is insufficient");
    assert.ok(row.evidenceIds!.length);
  }
  const signals = snapshot.companies.find((c) => c.id === "YC30639")!;
  assert.equal(signals.year, 2026, "retain the company year instead of assigning the batch's majority year");
  assert.equal(signals.cat, "C06");
  assert.equal(snapshot.companies.find((c) => c.id === "YC30846")!.cat, "C03");
  assert.match(snapshot.companies.find((c) => c.id === "YC30821")!.business, /远端推理/);
  assert.equal(snapshot.companies.find((c) => c.id === "YC30933")!.technicalReview!.level, "description",
    "vendor clinical agreement is not an independent validation");
  const amounts = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR2-"));
  assert.equal(amounts.length, 8);
  assert.ok(amounts.every((o) => ["excluded", "adoption"].includes(o.selection) && !o.metric && o.comparisonGroup === null));
  assert.equal(amounts.find((o) => o.id.endsWith("WARDSTONE-GRANT"))!.selection, "excluded");
  assert.equal(amounts.find((o) => o.id.endsWith("SOLVA-OLD-PREMIUM"))!.selection, "excluded");
  assert.ok(batch.records.filter((r) => r.companyId).every((r) => snapshot.companies.find((c) => c.id === r.companyId)!.revenueStatus === "unknown"));
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR2-")));
});

test("the third uncertain cohort retains shutdowns, unknown scale and mixed data-service economics", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-3")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(48, 72);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 12);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 12);
  for (const name of ["Voltair", "Mirabelle", "ZeroSettle", "Kyten Technologies"]) {
    assert.equal(batch.records.find((r) => r.name === name)!.companyId, undefined);
  }
  const klaus = snapshot.companies.find((c) => c.id === "YC31084")!;
  assert.equal(klaus.revenueStatus, "unknown", "a shutdown must not manufacture a zero revenue report");
  assert.match(klaus.stage, /2026-09-01停服/);
  assert.ok(!snapshot.observations.some((o) => o.company === klaus.id));
  const openspec = snapshot.companies.find((c) => c.id === "YC31116")!;
  assert.equal(openspec.team, null, "missing staff count stays unknown");
  assert.equal(openspec.year, 2025, "a license copyright line alone is not a company founding date");
  assert.equal(openspec.technicalReview!.level, "public-artifact");
  assert.match(snapshot.companies.find((c) => c.id === "YC31095")!.businessModel!, /清洁/);
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR3-"));
  assert.equal(figures.length, 8);
  assert.ok(figures.every((o) => ["excluded", "adoption"].includes(o.selection) && !o.metric && o.comparisonGroup === null));
  assert.equal(figures.find((o) => o.id.endsWith("SHORTKIT-OLD-ARR"))!.selection, "excluded");
  assert.equal(figures.find((o) => o.id.endsWith("KALPA-TRAIN-COST"))!.selection, "excluded");
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR3-")));
});

test("the fourth uncertain cohort distinguishes product pivots, managed labor and pass-through money", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-4")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(72, 96);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 13);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 11);
  assert.equal(batch.records.find((r) => r.name === "Orthogonal")!.companyId, "AI036");
  assert.equal(snapshot.companies.filter((c) => c.url.endsWith("/companies/orthogonal")).length, 1);
  const fern = snapshot.companies.find((c) => c.id === "YC31152")!;
  assert.equal(fern.cat, "C02");
  assert.match(fern.notes, /会议/);
  const mocha = snapshot.companies.find((c) => c.id === "YC31269")!;
  assert.equal(mocha.year, 2026);
  assert.match(mocha.businessModel!, /人工/);
  assert.match(mocha.price, /Platform.*Managed/);
  assert.match(mocha.notes, /Coming soon/);
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR4-"));
  assert.equal(figures.length, 7);
  assert.ok(figures.every((o) => ["excluded", "adoption"].includes(o.selection) && !o.metric && o.comparisonGroup === null));
  for (const suffix of ["LAURENCE-ADSPEND", "EKPA-CONNECTED-ASSETS", "REGBASE-CLIENT-GRANTS", "MOCHA-FUNDING"]) {
    assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
  }
  assert.equal(snapshot.companies.find((c) => c.id === "YC31199")!.technicalReview!.level, "public-artifact");
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR4-")));
});

test("the fifth uncertain cohort separates dated ARR, service run rates, bookings and previous ventures", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-5")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(96, 120);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 15);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 9);
  assert.equal(batch.records.find((r) => r.name === "primitive")!.companyId, "AI002");
  assert.equal(batch.records.find((r) => r.name === "Result")!.companyId, "AI001");
  const result = snapshot.companies.find((c) => c.id === "AI001")!;
  assert.equal(result.cat, "C09");
  assert.equal(result.revenueStatus, "unknown");
  assert.match(result.notes, /280万美元ARR属于用户/);
  assert.ok(result.evidenceIds.includes("UNCLEAR5-31438-TERMS"));
  const andco = snapshot.companies.find((c) => c.id === "YC31411")!;
  assert.equal(andco.year, 2026, "a founder's previous venture must not replace the new company's stated year");
  assert.match(andco.notes, /Layup/);
  assert.equal(snapshot.evidence.find((e) => e.id === "UNCLEAR5-31411-LAUNCH6")!.companyId, null);
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR5-"));
  assert.equal(figures.length, 18);
  const dated = figures.find((o) => o.id.endsWith("TRELLIS-ARR-AUG"))!;
  assert.equal(dated.metric, "arr");
  assert.equal(dated.observedAt, "2026-08-24");
  assert.equal(dated.bound, "≥");
  assert.equal(figures.find((o) => o.id.endsWith("INSTA-RUNRATE"))!.metric, "annualized-revenue");
  assert.equal(figures.find((o) => o.id.endsWith("INSTA-LAUNCH-ARR"))!.metric, "arr");
  for (const suffix of ["PARROT-CONTRACT", "KINRO-OLD-CONTRACT", "BENTO-OLD-EMPLOYER", "TRELLIS-OLD-MGMT"]) {
    assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
  }
  assert.equal(snapshot.companies.find((c) => c.id === "YC31423")!.technicalReview!.level, "description",
    "an internal benchmark subset is not an independent leaderboard result");
  assert.ok(figures.every((o) => o.comparisonGroup === null));
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR5-")));
});

test("the sixth uncertain cohort preserves namesakes, churn and historical robotics MRR", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-6")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(120, 144);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 13);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 11);
  const hera = snapshot.companies.find((c) => c.id === "YC32123")!;
  const videoHera = snapshot.companies.find((c) => c.id === "AI025")!;
  assert.equal(hera.cat, "C07");
  assert.equal(hera.year, 2026);
  assert.equal(videoHera.cat, "C08");
  assert.equal(videoHera.year, 2025);
  assert.notEqual(hera.url, videoHera.url, "same-name products with different YC pages must not be merged");
  for (const name of ["Aernata", "Maquoketa Research", "Fire Wallet", "Eden Robotics", "Edgerun"]) {
    const row = batch.records.find((r) => r.name === name)!;
    assert.equal(row.status, "pending-ai");
    assert.equal(row.companyId, undefined, "historical AI products, agent features and autonomous hardware need current-core evidence");
  }
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR6-"));
  assert.equal(figures.length, 13);
  const churn = figures.find((o) => o.id.endsWith("ARDENT-CHURN"))!;
  assert.equal(churn.selection, "excluded");
  assert.equal(churn.metric, undefined, "lost ARR is not a positive current ARR observation");
  assert.equal(snapshot.companies.find((c) => c.id === "YC31475")!.revenueStatus, "unknown");
  const mrr = figures.find((o) => o.id.endsWith("AVEA-MRR"))!;
  assert.equal(mrr.value, 18000);
  assert.equal(mrr.metric, "mrr");
  assert.equal(mrr.selection, "historical");
  assert.match(mrr.unit, /无币种/);
  assert.match(snapshot.companies.find((c) => c.id === "YC31530")!.notes, /Acquired/);
  for (const suffix of ["PLAN0-PROJECTS-YC", "PLAN0-PROJECTS-LAUNCH", "SILMARIL-DAMAGE-YC", "SILMARIL-DAMAGE-CASE1", "SILMARIL-DAMAGE-CASE2", "EXPANSE-WASTE"]) {
    assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
  }
  const openwork = snapshot.companies.find((c) => c.id === "YC31505")!;
  assert.equal(openwork.technicalReview!.level, "public-artifact");
  assert.ok(openwork.technicalReview!.evidenceIds.includes("UNCLEAR6-31505-EE-LICENSE"));
  assert.match(openwork.notes, /桌面MIT与ee目录/);
  assert.ok(figures.every((o) => o.comparisonGroup === null));
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR6-")));
});

test("the seventh uncertain cohort separates hardware sales, prepayments and bounded verification", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-7")!;
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear").slice(144, 168);
  assert.equal(batch.complete, false);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 16);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 8);
  const robotNori = snapshot.companies.find((c) => c.id === "YC32553")!;
  const healthNori = snapshot.companies.find((c) => c.id === "YC30657")!;
  assert.equal(robotNori.cat, "C10");
  assert.equal(healthNori.cat, "C09");
  assert.notEqual(robotNori.url, healthNori.url, "same-name hardware and health companies retain distinct identities");
  assert.equal(batch.records.find((r) => r.name === "Nori")!.companyId, robotNori.id);
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR7-"));
  assert.equal(figures.length, 18);
  const sales = figures.find((o) => o.id.endsWith("NORI-SALES"))!;
  assert.equal(sales.value, 440000);
  assert.equal(sales.selection, "historical");
  assert.equal(sales.metric, undefined, "hardware sales with unverified preorder/delivery mix must not become ARR");
  assert.match(snapshot.companies.find((c) => c.id === "YC32164")!.price!, /额度/);
  for (const suffix of ["GUT-PHARMACY", "MANIFOLD-PICKS", "ATC-CLIENT-FLEET", "OPERON-CLIENT-SAVE", "ANYALPHA-OLD-APPS", "LETTER-DEMO"]) {
    assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
  }
  assert.match(figures.find((o) => o.id.endsWith("LETTER-DEMO"))!.scope, /fictional/);
  assert.equal(snapshot.companies.find((c) => c.id === "YC34899")!.cat, "C06");
  const kailash = snapshot.companies.find((c) => c.id === "YC34828")!;
  assert.equal(kailash.cat, "C10");
  assert.equal(kailash.technicalReview!.level, "description", "an open-weights claim without readable weights or a model card is not a reviewed public artifact");
  const graphify = snapshot.companies.find((c) => c.id === "YC32583")!;
  assert.equal(graphify.technicalReview!.level, "public-artifact");
  const proof = snapshot.evidence.find((e) => e.id === "UNCLEAR7-32583-PROOF")!;
  assert.match(proof.summary, /unknown/);
  assert.match(proof.summary, /函数/);
  assert.match(proof.limitation, /整库正确/);
  assert.match(snapshot.companies.find((c) => c.id === "YC32518")!.notes, /Build标Coming soon/);
  for (const name of ["Kara", "Molagri", "TareBio", "Atomarine", "Vernius Systems, Inc."]) {
    const row = batch.records.find((r) => r.name === name)!;
    assert.equal(row.status, "pending-ai");
    assert.equal(row.companyId, undefined);
  }
  assert.ok(figures.every((o) => o.comparisonGroup === null));
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR7-")));
});

test("all original AI-unclear candidates retain a unique follow-up without counting EveryApp twice", () => {
  const snapshot = seed as ResearchSnapshot;
  const rows = snapshot.candidateBatches!.filter((b) => b.id.startsWith("YC-AI-UNCLEAR-")).flatMap((b) => b.records);
  const original = coverageAudit.records.filter((r) => r.status === "ai-unclear");
  assert.equal(rows.length, 192);
  assert.equal(new Set(rows.map((r) => r.url)).size, 192);
  assert.deepEqual(rows.map((r) => r.url), original.map((r) => r.source));
  assert.equal(rows.filter((r) => r.status === "linked").length, 110);
  assert.equal(rows.filter((r) => r.status === "pending-ai").length, 82);
  assert.equal(snapshot.directoryRechecks!.filter((r) => r.ycId === 36088).length, 1);
  const everyapp = rows.find((r) => r.name === "EveryApp")!;
  assert.equal(everyapp.companyId, "AI074");
  assert.equal(snapshot.companies.filter((c) => c.id === "AI074").length, 1);
  for (const row of rows.filter((r) => r.status === "pending-ai")) {
    assert.equal(row.companyId, undefined);
    assert.ok(row.evidenceIds!.length > 0, "unresolved AI relevance has explicit evidence and gaps");
  }
  assert.equal(snapshot.coverage!.newProfiles, 928, "later evidence does not rewrite the original discovery accounting");
});

test("the final uncertain cohort separates delivery-start rentals, reservations and upstream costs", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-AI-UNCLEAR-8")!;
  assert.equal(batch.complete, false, "reading the full pool does not resolve all AI, year or financial gaps");
  assert.equal(batch.records.filter((r) => r.status === "linked").length, 11);
  assert.equal(batch.records.filter((r) => r.status === "pending-ai").length, 13);
  const rhem = snapshot.companies.find((c) => c.id === "YC35127")!;
  assert.match(rhem.price!, /确认交付后/);
  assert.match(rhem.price!, /99 USD/);
  assert.equal(rhem.revenueStatus, "unknown");
  assert.match(snapshot.companies.find((c) => c.id === "YC37272")!.price!, /预约/);
  assert.match(snapshot.companies.find((c) => c.id === "AI074")!.price!, /有效订阅/);
  assert.match(snapshot.companies.find((c) => c.id === "YC35396")!.notes, /Coming next/);
  assert.match(snapshot.companies.find((c) => c.id === "YC36774")!.notes, /Early access/);
  const figures = snapshot.observations.filter((o) => o.id.startsWith("UNCLEAR8-"));
  assert.equal(figures.length, 9);
  assert.ok(figures.every((o) => ["excluded", "adoption"].includes(o.selection) && !o.metric && o.comparisonGroup === null));
  for (const suffix of ["OASIVE-OLD-WELLS", "OASIVE-OLD-GOOGLE", "OBSESSION-CALCULATOR", "EVERYAPP-UPSTREAM"]) {
    assert.equal(figures.find((o) => o.id.endsWith(suffix))!.selection, "excluded");
  }
  for (const name of ["Clean", "STASIS", "RATLOG", "Inflection Space Systems", "twentyfour26"]) {
    assert.equal(batch.records.find((r) => r.name === name)!.status, "pending-ai");
  }
  assert.ok(!platformIncomeSample(snapshot, { windowDays: null }).points.some((p) => p.observation.id.startsWith("UNCLEAR8-")));
});

test("founding conflicts preserve old product history without creating new companies or revenue", () => {
  const snapshot = seed as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "YC-DATE-CONFLICT-1")!;
  const original = coverageAudit.records.filter((r) => r.status === "date-conflict");
  assert.equal(batch.complete, false);
  assert.equal(batch.records.length, 6);
  assert.deepEqual(batch.records.map((r) => r.url), original.map((r) => r.source));
  assert.equal(new Set(batch.records.map((r) => r.url)).size, original.length);
  for (const row of batch.records) {
    assert.equal(row.status, "pending-year");
    assert.equal(row.companyId, undefined);
    const evidence = snapshot.evidence.filter((e) => row.evidenceIds!.includes(e.id));
    assert.equal(evidence.length, row.evidenceIds!.length);
    assert.ok(evidence.every((e) => e.companyId === null));
    assert.ok(evidence.some((e) => e.publishedAt?.startsWith("2025-")), "old product launch remains explicit");
    assert.ok(!snapshot.companies.some((c) => c.evidenceIds.some((eid) => row.evidenceIds!.includes(eid))));
  }
  assert.match(batch.records.find((r) => r.name === "Layers")!.note, /未确认当前AI核心/);
  assert.ok(!snapshot.observations.some((o) => o.evidence.startsWith("YEARCONFLICT1-")));
  const excluded = coverageAudit.records.filter((r) => r.status === "year-outside-or-missing");
  assert.equal(excluded.filter((r) => r.foundedYear === null).length, 54);
  assert.equal(excluded.filter((r) => r.foundedYear !== null).length, 214);
  assert.ok(excluded.filter((r) => r.foundedYear !== null).every((r) => ![2025, 2026].includes(r.foundedYear!)));
});

test("Chinese discovery entries preserve unread articles and use separate primary evidence", () => {
  const snapshot = structuredClone(seed) as ResearchSnapshot;
  const batch = snapshot.candidateBatches!.find((b) => b.id === "JQ-2026-targeted-1")!;
  assert.equal(batch.complete, false);
  assert.equal(batch.records.length, 4);
  assert.ok(batch.records.every((row) => row.kind === "company" && row.profileStatus === "unavailable"));
  assert.equal(batch.records.filter((row) => row.status === "linked").length, 2);
  assert.equal(batch.records.find((row) => row.name === "Utopai")?.status, "outside-cohort");
  assert.ok(!snapshot.observations.some((o) => ["PS-CODE", "SG-START", "SG-APR", "SSI-HISTORY"].includes(o.evidence)), "task costs, investment, capacity and financing are not revenue");
  const prism = snapshot.companies.find((c) => c.id === "AI075")!;
  assert.equal(prism.team, null, "a team range or linked employees must not become exact headcount");
  batch.records[0].url = null;
  assert.throws(() => validateResearch(snapshot), /research candidate/);
});