扩展 AI 公司目录覆盖并保留逐条核查台账

Reviewed-on: #7

README.md

@@ -80,6 +80,49 @@ AUTH_CONFIG_FILE=/private/tmp/tabularium-auth/config.json AUTH_COOKIE_SECURE=fal
 
 `pnpm test:auth`运行算法、会话、重放及限流测试。容器验证使用自己的匿名测试卷完成登录/并发重放/CSRF/限流测试，并在重启后检查状态仍存在。生产部署只运行无副作用的 `verify`，不会消耗用户动态码或触发生产限流。
 
+## AI 公司研究
+
+导航入口为 **其他研究 → AI 公司研究**，页面路径是
+`/docs/other-research/ai-company-research/overview`。工作台提供业务分类、公司搜索与筛选、
+公司明细、收入观测、原始证据和数据核查记录。所有页面与
+`GET /api/research/ai-companies` 均使用文档站现有的登录认证。
+
+研究数据与登录状态**共用文档站现有的 SQLite 数据库文件**：
+`AUTH_CONFIG_FILE` 同目录下的 `login-state.sqlite`。该文件名是历史名称，未创建第二个数据库。
+`login_state` 保留登录限流与重放状态，新增的 `research_*` 表保存数据版本、分类、
+公司、经营指标、证据与核查记录。沿用现有 `/auth` 持久挂载，数据库不会写入镜像或公开目录。
+
+`content/research/ai-companies.seed.json` 是可评审的研究导入快照，
+服务端首次读取该版本时将它以事务导入同一数据库，之后从数据库查询记录。
+导入使用外键校验，不删除登录数据，也不覆盖旧研究版本。每次更新快照必须修改 `version`；
+同一版本内容变化会拒绝导入，避免静默读取旧数据。回退代码时继续读取对应旧版本。
+所有修改都经过工作分支和 PR，部署仍等待人工合并主线。
+
+当前资料包含 986 条公司记录、10 类业务及待分类组、1,035 条证据记录和 75 条经营观测。
+其中保留 58 家个案资料，新增 928 条目录基础资料；目录项不等于完成财务和技术核验。
+它是定向试样，收入披露不足且统计时点不统一，不代表全部 AI 公司。
+界面将公司自述、第三方估算、融资、客户收入和履历收入分开，未知收入不记为零。
+保留被撤回的声明作为核查记录，并排除收入比较；并购后业务、管理层预测与历史里程碑单列。
+团队规模下界在列表中显示比较符，商业成熟度展示公开交付证据，不等于技术能力排名。
+当前尚不能可靠计算领域 ARR 均值、离散排名或财务造假概率。
+
+覆盖核查：从 yc-oss 非官方镜像发现 2025—2026 八个 YC 批次的 1,428 条候选，
+逐条读取对应 YC 官方公开页面，以页面中的成立年份、团队字段和业务描述筛选。
+962 条初筛匹配，其中 34 条与原表 URL 重合，实际新增 928 条；268 条年份不符或缺失、
+192 条 AI 业务待确认、6 条成立年份晚于批次年份未纳入本批新增。
+`content/research/ai-companies.coverage.json` 保留逐条筛选结果、来源与响应摘要，
+数据快照中的 `coverage` 也随版本进入同一 SQLite 数据库。只覆盖该候选池，不能称全球全量。
+
+新增业务分类优先匹配主营简介，再参考目录标签；未匹配者进入待分类组。
+初分规则位于 `scripts/classify-ai-profiles.py`，只生成待评审标签，不执行抓取或构建。
+所有新增项均标注规则初分，保留 `classificationBasis` 和 `directoryTags` 供复核。
+AI 关键词可能出现在业务背景中，收入、买家和交付状态仍须逐家深查，不能把目录项的未知收入当作未披露。
+界面支持按资料深度、记录团队规模筛选；证据列表每页 30 条，避免一次渲染全部来源。
+
+`pnpm test:research` 在远程 Runner 上验证同库持久化、重复读取、版本导入与回退、
+登录限流保留、引用完整性及收入排除规则。镜像冒烟检查会验证研究页面与 API 的认证、
+返回记录数量、只读方法和容器重启后的读取结果。页面筛选交互仍需实际浏览器验证。
+
 ## CI/CD 与缓存
 
 `.gitea/workflows/ci-deploy.yml` 使用已有 ces-control Runner，不修改共享 Runner 配置。

apps/docs/package.json

@@ -10,7 +10,8 @@
     "start": "NEXT_TELEMETRY_DISABLED=1 next start --hostname 127.0.0.1",
     "lint": "eslint . --max-warnings=0",
     "typecheck": "NEXT_TELEMETRY_DISABLED=1 next typegen && tsc --noEmit",
-    "test:auth": "node scripts/test-auth.mjs"
+    "test:auth": "node scripts/test-auth.mjs",
+    "test:research": "node scripts/test-research.mjs"
   },
   "dependencies": {
     "next": "16.4.3",

apps/docs/scripts/auth-cli.ts

@@ -160,7 +160,7 @@ async function main() {
       path,
     );
   }
-  for (const path of ["/api/private", "/api/unknown", "/api/search"])
+  for (const path of ["/api/private", "/api/unknown", "/api/search", "/api/research/ai-companies"])
     assert.equal((await request(path)).status, 401, path);
   assert.equal(
     (
@@ -181,6 +181,21 @@ async function main() {
   const headers = {
     Authorization: "Bearer " + signSession(config, undefined, 600),
   };
+  const researchResponse = await request("/api/research/ai-companies", { headers });
+  assert.equal(researchResponse.status, 200, "authenticated research API");
+  assert.ok(researchResponse.headers.get("cache-control")?.includes("no-store"));
+  const research = await researchResponse.json();
+  assert.equal(research.companies.length, 986);
+  assert.equal(research.categories.length, 11);
+  assert.equal(research.evidence.length, 1035);
+  assert.equal(research.observations.length, 75);
+  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);
+  const researchHtml = await researchPage.text();
+  assert.ok(researchHtml.includes('data-category="其他研究"'));
+  assert.ok(researchHtml.includes("AI 公司研究"));
+  assert.ok(researchHtml.includes("正在读取研究数据库"));
   const searchResponse = await request("/api/search", { headers });
   assert.equal(searchResponse.status, 200);
   const searchIndex = await searchResponse.json();

apps/docs/scripts/test-research.mjs

@@ -0,0 +1,14 @@
+import { build } from "esbuild";
+import { mkdtemp, rm } from "node:fs/promises";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { spawnSync } from "node:child_process";
+
+const dir = await mkdtemp(join(tmpdir(), "tabularium-research-tests-"));
+try {
+  const file = join(dir, "research.test.cjs");
+  await build({ entryPoints: ["tests/research.test.ts"], bundle: true,
+    platform: "node", target: "node22", format: "cjs", outfile: file });
+  const result = spawnSync(process.execPath, ["--test", file], { stdio: "inherit" });
+  process.exitCode = result.status ?? 1;
+} finally { await rm(dir, { recursive: true, force: true }); }

apps/docs/src/components/AICompanyResearch.tsx

@@ -0,0 +1,155 @@
+import { useEffect, useMemo, useRef, useState } from "react";
+import {
+  categorySummary, evidenceUrl, type ResearchEvidence, type ResearchSnapshot,
+} from "@/lib/ai-research";
+
+const pageSize = 12;
+const evidencePageSize = 30;
+const revenueLabels = { self: "公司披露，待核口径", estimate: "仅第三方估算", unknown: "暂无可用收入数字" };
+const useLabels: Record<string, string> = {
+  signal: "公司披露信号", estimate: "第三方估算", historical: "历史里程碑",
+  "historical-estimate": "其他时点估算", excluded: "排除收入比较", scale: "团队规模", adoption: "采用规模",
+  funding: "融资", crosscheck: "同一里程碑的其他资料",
+};
+const money = (value: number, unit = "USD") => unit === "USD"
+  ? new Intl.NumberFormat("zh-CN", { style: "currency", currency: "USD", maximumFractionDigits: 0 }).format(value)
+  : `${new Intl.NumberFormat("zh-CN").format(value)} ${unit}`;
+
+function External({ url, children }: { url: string; children: React.ReactNode }) {
+  const safe = evidenceUrl(url);
+  return safe ? <a href={safe} target="_blank" rel="noopener noreferrer">{children} ↗</a> : <span>{children}</span>;
+}
+function Evidence({ item, prefix = "evidence" }: { item: ResearchEvidence; prefix?: string }) {
+  return <li id={`${prefix}-${item.id}`} className="research-evidence">
+    <div><code>{item.id}</code><span className="research-tag">{item.kind}</span></div>
+    <strong><External url={item.url}>{item.title}</External></strong>
+    <p>{item.summary}</p><p className="research-muted">{item.limitation}</p>
+    <small>发布：{item.publishedAt ?? "未注明"}　读取：{item.accessedAt}</small>
+  </li>;
+}
+
+export default function AICompanyResearch() {
+  const [data, setData] = useState<ResearchSnapshot | null>(null);
+  const [error, setError] = useState(false);
+  const [attempt, setAttempt] = useState(0);
+  const [query, setQuery] = useState("");
+  const [category, setCategory] = useState("");
+  const [cohort, setCohort] = useState("");
+  const [income, setIncome] = useState("");
+  const [page, setPage] = useState(0);
+  const [sourcePage, setSourcePage] = useState(0);
+  const [depth, setDepth] = useState("");
+  const [teamBand, setTeamBand] = useState("");
+  const [selected, setSelected] = useState<string | null>(null);
+  const [tab, setTab] = useState<"companies" | "revenue" | "sources" | "reviews">("companies");
+  const companySection = useRef<HTMLElement>(null);
+  const detailSection = useRef<HTMLElement>(null);
+  useEffect(() => {
+    const controller = new AbortController();
+    fetch("/api/research/ai-companies", { signal: controller.signal, cache: "no-store" })
+      .then(async (response) => {
+        if (!response.ok) throw new Error("Research unavailable");
+        const snapshot: ResearchSnapshot = await response.json();
+        setData(snapshot);
+      }).catch(() => { if (!controller.signal.aborted) setError(true); });
+    return () => controller.abort();
+  }, [attempt]);
+  useEffect(() => { if (selected) detailSection.current?.focus(); }, [selected]);
+  const summaries = useMemo(() => data ? categorySummary(data) : [], [data]);
+  const filtered = useMemo(() => data?.companies.filter((c) => {
+    const search = `${c.name} ${c.business} ${c.location ?? ""} ${c.buyer}`.toLocaleLowerCase();
+    const yearMatch = !cohort || (cohort === "other" ? ![2025, 2026].includes(c.year ?? 0) : c.year === Number(cohort));
+    const depthMatch = !depth || (depth === "profile" ? c.profileOnly : !c.profileOnly);
+    const teamMatch = !teamBand || (teamBand === "unknown" ? c.team === null || (!!c.teamBound && c.team < 51)
+      : c.team !== null && (teamBand === "xl" ? c.team >= 51 : !c.teamBound && (teamBand === "small" ? c.team <= 5 : teamBand === "medium" ? c.team >= 6 && c.team <= 20 : c.team >= 21 && c.team <= 50)));
+    return depthMatch && teamMatch && (!category || c.cat === category) && yearMatch && (!income || c.revenueStatus === income)
+      && search.includes(query.trim().toLocaleLowerCase());
+  }) ?? [], [data, query, category, cohort, income, depth, teamBand]);
+  if (error) return <div className="research-message" role="alert">研究数据库暂时不可用。<button onClick={() => { setError(false); setAttempt((n) => n + 1); }}>重新读取</button></div>;
+  if (!data) return <p className="research-message" role="status">正在读取研究数据库…</p>;
+  const categories = new Map(data.categories.map((c) => [c.id, c]));
+  const selectedCompany = data.companies.find((c) => c.id === selected);
+  const observed = data.observations.filter((o) => ["signal", "estimate"].includes(o.selection));
+  const revenueCompanies = new Set(observed.map((o) => o.company)).size;
+  const selectedObservations = data.observations.filter((o) => o.company === selected);
+  const selectedEvidenceIds = new Set([
+    ...(selectedCompany?.evidenceIds ?? []), ...(selectedCompany?.pricingEvidence ? [selectedCompany.pricingEvidence] : []),
+    ...selectedObservations.map((o) => o.evidence),
+  ]);
+  const selectedEvidence = data.evidence.filter((e) => e.companyId === selected || selectedEvidenceIds.has(e.id));
+  function chooseCategory(id: string) {
+    setCategory(id); setPage(0); setTab("companies");
+    companySection.current?.scrollIntoView({ behavior: "smooth", block: "start" });
+  }
+  return <div className="ai-research not-prose">
+    <div className="research-meta"><span>资料截至 {data.asOf}</span><span>首批研究 · 持续补全</span></div>
+    <div className="research-stats">
+      <div><strong>{data.companies.length}</strong><span>已收录公司</span></div>
+      <div><strong>{data.categories.length}</strong><span>业务类别</span></div>
+      <div><strong>{revenueCompanies}</strong><span>找到收入信号的公司</span></div>
+      <div><strong>{data.evidence.length}</strong><span>证据记录</span></div>
+    </div>
+    <div className="research-scope"><p>{data.scope}</p>
+      {data.coverage && <p>YC 候选池 {data.coverage.candidateRecords} 条，官方页面读取 {data.coverage.profilesRead} 条；初筛匹配 {data.coverage.matchingProfiles} 条，新增 {data.coverage.newProfiles} 条目录记录。年份不符或缺失 {data.coverage.otherOrMissingYear} 条、AI 业务待确认 {data.coverage.unclearAI} 条、日期冲突 {data.coverage.dateConflicts} 条。目录基础资料尚未逐家核验收入和交付能力。</p>}
+      <details><summary>数据口径与覆盖限制</summary><ul>{data.limitations.map((note) => <li key={note}>{note}</li>)}</ul>
+        <p>来源以 YC、公司官网、投资机构名录与经营案例为主。同一披露的转载不构成独立验证。团队人数包含公司自报的 Team Size，与正式员工口径可能不同。</p>
+      </details>
+    </div>
+    <section aria-labelledby="research-categories-title" className="research-section">
+      <h2 id="research-categories-title">业务分类</h2><p className="research-muted">点击类别查看对应公司。数量反映本次采集覆盖，不是市场份额。</p>
+      <div className="research-categories">{summaries.map((c) => <button key={c.id} onClick={() => chooseCategory(c.id)} aria-label={`查看${c.name}的${c.count}家公司`}>
+        <div><span>{c.name}</span><strong>{c.count}</strong></div>
+        <span className="research-bar" aria-hidden="true"><i style={{ width: `${c.count / Math.max(1, ...summaries.map((s) => s.count)) * 100}%` }} /></span>
+        <small>{c.description}</small>
+      </button>)}</div>
+    </section>
+    <section ref={companySection} className="research-section" aria-labelledby="research-records-title">
+      <h2 id="research-records-title">研究数据</h2>
+      <div className="research-tabs" role="group" aria-label="研究数据视图">
+        {([['companies','公司数据'],['revenue','收入观测'],['sources','原始证据'],['reviews','核查记录']] as const).map(([id,label]) =>
+          <button key={id} aria-pressed={tab === id} onClick={() => setTab(id)}>{label}</button>)}
+      </div>
+      {tab === "companies" && <>
+        <div className="research-filters">
+          <label className="research-query">搜索公司<input type="search" value={query} placeholder="名称、业务、地区或买家" onChange={(e) => { setQuery(e.target.value); setPage(0); }} /></label>
+          <label>业务类别<select value={category} onChange={(e) => { setCategory(e.target.value); setPage(0); }}><option value="">全部类别</option>{data.categories.map((c) => <option key={c.id} value={c.id}>{c.name}</option>)}</select></label>
+          <label>成立或发布<select value={cohort} onChange={(e) => { setCohort(e.target.value); setPage(0); }}><option value="">全部组别</option><option value="2025">2025 年成立</option><option value="2026">2026 年成立</option><option value="other">公开发布与转型对照</option></select></label>
+          <label>资料深度<select value={depth} onChange={(e) => { setDepth(e.target.value); setPage(0); }}><option value="">全部资料</option><option value="case">原有个案研究</option><option value="profile">目录基础资料</option></select></label>
+          <label>记录团队规模<select value={teamBand} onChange={(e) => { setTeamBand(e.target.value); setPage(0); }}><option value="">全部规模</option><option value="small">1—5 人</option><option value="medium">6—20 人</option><option value="large">21—50 人</option><option value="xl">至少 51 人</option><option value="unknown">未披露或分组不确定</option></select></label>
+          <label>收入资料<select value={income} onChange={(e) => { setIncome(e.target.value); setPage(0); }}><option value="">全部状态</option><option value="self">找到公司披露</option><option value="estimate">仅第三方估算</option><option value="unknown">暂无可用数字</option></select></label>
+        </div>
+        <div className="research-result-count" role="status">{filtered.length} 家匹配公司<button onClick={() => { setCategory(""); setQuery(""); setCohort(""); setIncome(""); setDepth(""); setTeamBand(""); setPage(0); }}>清除筛选</button></div>
+        <div className="research-table-wrap"><table><caption className="sr-only">公司分类与经营资料。选择公司名称查看指标和原始证据。</caption><thead><tr><th>公司 / 地区</th><th>业务与买家</th><th>成立 / 发布组别</th><th>团队规模</th><th>商业成熟度</th><th>收入资料</th></tr></thead><tbody>
+          {filtered.slice(page * pageSize, (page + 1) * pageSize).map((c) => <tr key={c.id} data-selected={selected === c.id || undefined}>
+            <td><button className="research-company-name" aria-expanded={selected === c.id} aria-controls="research-company-detail" onClick={() => setSelected(c.id)}>{c.name}</button><small>{c.location ?? "地区未注明"}</small></td>
+            <td><span className="research-tag">{categories.get(c.cat)?.name}</span>{c.profileOnly && <small>规则初分 · 待复核</small>}<p>{c.business}</p><small>买家：{c.buyer}</small></td>
+            <td>{c.cohort}</td><td>{c.team !== null && c.teamBound}{c.team ?? "未披露"}{c.team !== null && " 人"}</td><td>{c.stage}</td><td>{c.profileOnly ? "收入尚未逐一核验" : revenueLabels[c.revenueStatus]}</td>
+          </tr>)}
+        </tbody></table></div>
+        {!filtered.length && <p className="research-message">没有匹配公司，请调整筛选条件。</p>}
+        {filtered.length > pageSize && <nav className="research-pagination" aria-label="公司数据分页"><button disabled={page === 0} onClick={() => setPage((n) => n - 1)}>上一页</button><span>{page + 1} / {Math.ceil(filtered.length / pageSize)}</span><button disabled={(page + 1) * pageSize >= filtered.length} onClick={() => setPage((n) => n + 1)}>下一页</button></nav>}
+      </>}
+      {tab === "revenue" && <>
+        <p className="research-notice">目前找到 {revenueCompanies} 家公司的收入信号。大多是缺少日历时点的历史里程碑，且 ARR 与年化收入尚未统一。领域均值和离散度暂不计算。</p>
+        <div className="research-revenue-chart" aria-label="不同时间的公开收入里程碑，线性长度，非同行排名">{observed.map((o) => <div key={o.id}>
+          <div><button onClick={() => setSelected(o.company)}>{o.name}</button><strong>{o.bound !== "=" && o.bound}{money(o.value, o.unit)}</strong></div>
+          <span className="research-bar" data-estimate={o.selection === "estimate" || undefined} aria-hidden="true"><i style={{width: `${o.value / Math.max(...observed.map((v) => v.value)) * 100}%`}} /></span>
+          <small>{o.kind} · {useLabels[o.selection]} · {o.timing}</small>
+        </div>)}</div>
+        <div className="research-table-wrap"><table><caption>当前研究数据中的收入可得性，目录项未逐一检索；未建立同期、同龄、同口径比较组</caption><thead><tr><th>业务分类</th><th>公司披露数</th><th>仅估算数</th><th>暂无可用数字</th><th>同期均值 / 离散度</th></tr></thead><tbody>{summaries.map((c) => <tr key={c.id}><td><button onClick={() => chooseCategory(c.id)}>{c.name}</button></td><td>{c.self}</td><td>{c.estimate}</td><td>{c.unknown}</td><td>条件不足</td></tr>)}</tbody></table></div>
+        <p className="research-muted">离散度用于筛选值得核查的异常，还需排除公司年龄、口径和披露偏差；不能据此认定财务造假。</p>
+      </>}
+      {tab === "sources" && <><p className="research-muted">来源链接保留原始位置。相同 URL 的记录可能属于同一披露，不能按记录数计算独立证据数量。</p><ul className="research-evidence-list">{data.evidence.slice(sourcePage * evidencePageSize, (sourcePage + 1) * evidencePageSize).map((e) => <Evidence key={e.id} item={e} />)}</ul>{data.evidence.length > evidencePageSize && <nav className="research-pagination" aria-label="原始证据分页"><button disabled={sourcePage === 0} onClick={() => setSourcePage((n) => n - 1)}>上一页</button><span>{sourcePage + 1} / {Math.ceil(data.evidence.length / evidencePageSize)}</span><button disabled={(sourcePage + 1) * evidencePageSize >= data.evidence.length} onClick={() => setSourcePage((n) => n + 1)}>下一页</button></nav>}</>}
+      {tab === "reviews" && <ul className="research-review-list">{data.reviews.map((r) => <li key={r.id}><span className="research-tag">{r.type}</span><h3>{r.company}</h3><p>{r.summary}</p><p>{r.handling}</p><div>{r.evidenceIds.map((id) => { const e=data.evidence.find((item) => item.id === id); return e ? <External key={id} url={e.url}>{id}</External> : null; })}</div></li>)}</ul>}
+    </section>
+    {selectedCompany && <section id="research-company-detail" ref={detailSection} tabIndex={-1} className="research-detail research-section" aria-label={`${selectedCompany.name}公司明细`}>
+      <div className="research-detail-heading"><h2>{selectedCompany.name}</h2><button onClick={() => setSelected(null)} aria-label="关闭公司明细">关闭</button></div>
+      <p><External url={selectedCompany.url}>公司资料入口</External>　{selectedCompany.extraUrl && <External url={selectedCompany.extraUrl}>额外核验入口</External>}</p>
+      <dl className="research-company-facts"><div><dt>主营业务</dt><dd>{selectedCompany.business}</dd></div><div><dt>样本组别</dt><dd>{selectedCompany.cohort}</dd></div><div><dt>买家</dt><dd>{selectedCompany.buyer}</dd></div><div><dt>收费方式</dt><dd>{selectedCompany.price}</dd></div><div><dt>交付证据</dt><dd>{selectedCompany.delivery}</dd></div><div><dt>团队口径</dt><dd>{selectedCompany.teamBasis ?? "本轮未核验人数"}</dd></div><div><dt>分类依据</dt><dd>{selectedCompany.classificationBasis ?? "原有个案分类；随研究复核"}</dd></div><div><dt>技术水平</dt><dd>尚未独立测试，不据融资或收入作能力排名。</dd></div><div><dt>身份与限制</dt><dd>{selectedCompany.notes}</dd></div></dl>
+      <h3>经营指标与排除记录</h3>
+      {selectedObservations.length ? <div className="research-table-wrap"><table><thead><tr><th>指标 / 归属</th><th>原始数值</th><th>数据时点</th><th>用途及限制</th><th>证据</th></tr></thead><tbody>{selectedObservations.map((o) => <tr key={o.id}><td>{o.kind}<small>{o.scope}</small></td><td>{o.bound !== "=" && o.bound}{money(o.value,o.unit)}</td><td>{o.timing}</td><td>{useLabels[o.selection] ?? o.selection}<small>{o.reason}</small></td><td><a href={`#detail-evidence-${o.evidence}`}>{o.evidence}</a></td></tr>)}</tbody></table></div> : <p>本轮尚未找到可记录的量化经营指标。收入保持未知。</p>}
+      <h3>原始证据</h3><ul className="research-evidence-list">{selectedEvidence.map((e) => <Evidence key={e.id} prefix="detail-evidence" item={e} />)}</ul>
+    </section>}
+    <p className="research-footnote">数据版本 {data.version}。当前为首批资料，覆盖、收入定义、财务透明度与商业模式评估将随核验补充。</p>
+  </div>;
+}

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

@@ -0,0 +1,87 @@
+import seed from "../../../../content/research/ai-companies.seed.json";
+import { createHash } from "node:crypto";
+import { openSiteDatabase } from "./site-database";
+import { validateResearch, type ResearchSnapshot } from "./ai-research";
+
+// Each release selects an immutable research revision. New revisions are added
+// transactionally, preserving both earlier research and all authentication rows.
+export function readResearchSnapshot(snapshot = seed as ResearchSnapshot): ResearchSnapshot {
+  validateResearch(snapshot);
+  const digest = createHash("sha256").update(JSON.stringify(snapshot)).digest("hex");
+  const db = openSiteDatabase();
+  try {
+    db.exec(`
+      CREATE TABLE IF NOT EXISTS research_datasets (
+        id TEXT PRIMARY KEY, as_of TEXT NOT NULL, metadata TEXT NOT NULL, content_hash TEXT NOT NULL
+      );
+      CREATE TABLE IF NOT EXISTS research_categories (
+        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
+        id TEXT NOT NULL, payload TEXT NOT NULL, PRIMARY KEY(dataset_id,id)
+      );
+      CREATE TABLE IF NOT EXISTS research_companies (
+        dataset_id TEXT NOT NULL, id TEXT NOT NULL, category_id TEXT NOT NULL,
+        name TEXT NOT NULL, founded_year INTEGER, team_size INTEGER,
+        revenue_status TEXT NOT NULL, payload TEXT NOT NULL,
+        PRIMARY KEY(dataset_id,id),
+        FOREIGN KEY(dataset_id,category_id) REFERENCES research_categories(dataset_id,id)
+      );
+      CREATE TABLE IF NOT EXISTS research_evidence (
+        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
+        id TEXT NOT NULL, url TEXT NOT NULL, payload TEXT NOT NULL,
+        PRIMARY KEY(dataset_id,id)
+      );
+      CREATE TABLE IF NOT EXISTS research_observations (
+        dataset_id TEXT NOT NULL, id TEXT NOT NULL, company_id TEXT NOT NULL,
+        evidence_id TEXT NOT NULL, kind TEXT NOT NULL, amount REAL NOT NULL,
+        unit TEXT NOT NULL, record_use TEXT NOT NULL, payload TEXT NOT NULL,
+        PRIMARY KEY(dataset_id,id),
+        FOREIGN KEY(dataset_id,company_id) REFERENCES research_companies(dataset_id,id),
+        FOREIGN KEY(dataset_id,evidence_id) REFERENCES research_evidence(dataset_id,id)
+      );
+      CREATE TABLE IF NOT EXISTS research_reviews (
+        dataset_id TEXT NOT NULL REFERENCES research_datasets(id),
+        id TEXT NOT NULL, payload TEXT NOT NULL, PRIMARY KEY(dataset_id,id)
+      );
+    `);
+    // The database transaction also serializes first requests from two workers.
+    db.exec("BEGIN IMMEDIATE");
+    try {
+      const exists = db.prepare("SELECT content_hash FROM research_datasets WHERE id=?")
+        .get(snapshot.version) as { content_hash: string } | undefined;
+      if (exists && exists.content_hash !== digest)
+        throw new Error("Research data changed without a new revision identifier");
+      if (!exists) {
+        const { categories, companies, observations, evidence, reviews, ...metadata } = snapshot;
+        db.prepare("INSERT INTO research_datasets VALUES (?,?,?,?)")
+          .run(snapshot.version, snapshot.asOf, JSON.stringify(metadata), digest);
+        const insertCategory = db.prepare("INSERT INTO research_categories VALUES (?,?,?)");
+        for (const row of categories) insertCategory.run(snapshot.version, row.id, JSON.stringify(row));
+        const insertCompany = db.prepare("INSERT INTO research_companies VALUES (?,?,?,?,?,?,?,?)");
+        for (const row of companies) insertCompany.run(snapshot.version, row.id, row.cat,
+          row.name, row.year, row.team, row.revenueStatus, JSON.stringify(row));
+        const insertEvidence = db.prepare("INSERT INTO research_evidence VALUES (?,?,?,?)");
+        for (const row of evidence) insertEvidence.run(snapshot.version, row.id, row.url, JSON.stringify(row));
+        const insertObservation = db.prepare("INSERT INTO research_observations VALUES (?,?,?,?,?,?,?,?,?)");
+        for (const row of observations) insertObservation.run(snapshot.version, row.id, row.company,
+          row.evidence, row.kind, row.value, row.unit, row.selection, JSON.stringify(row));
+        const insertReview = db.prepare("INSERT INTO research_reviews VALUES (?,?,?)");
+        for (const row of reviews) insertReview.run(snapshot.version, row.id, JSON.stringify(row));
+      }
+      db.exec("COMMIT");
+    } catch (error) {
+      db.exec("ROLLBACK");
+      throw error;
+    }
+    const meta = db.prepare("SELECT metadata FROM research_datasets WHERE id=?").get(snapshot.version) as { metadata: string };
+    // All displayed records come from the site database, not the seed arrays.
+    const rows = (table: string) => (db.prepare(
+      `SELECT payload FROM ${table} WHERE dataset_id=? ORDER BY id`,
+    ).all(snapshot.version) as { payload: string }[]).map((r) => JSON.parse(r.payload));
+    const stored: ResearchSnapshot = { ...JSON.parse(meta.metadata),
+      categories: rows("research_categories"), companies: rows("research_companies"),
+      observations: rows("research_observations"), evidence: rows("research_evidence"),
+      reviews: rows("research_reviews") };
+    validateResearch(stored);
+    return stored;
+  } finally { db.close(); }
+}

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

@@ -0,0 +1,94 @@
+export type ResearchCategory = { id: string; name: string; description: string };
+export type ResearchCompany = {
+  id: string; name: string; url: string; cat: string; year: number | null;
+  team: number | null; teamBound?: ">" | "≥"; location: string | null; business: string; buyer: string;
+  delivery: string; notes: string; cohort: string; teamBasis: string | null;
+  price: string; stage: string; sourceType: string; evidenceIds: string[];
+  revenueStatus: "self" | "estimate" | "unknown";
+  extraUrl?: string; pricingEvidence?: string;
+  profileOnly?: boolean; classificationBasis?: string; directoryTags?: string[];
+};
+export type ResearchObservation = {
+  id: string; company: string; name: string; kind: string; value: number;
+  unit: string; timing: string; evidence: string; scope: string;
+  selection: string; reason: string; bound: string; comparisonGroup: string | null;
+};
+export type ResearchEvidence = {
+  id: string; companyId: string | null; title: string; url: string;
+  publishedAt: string | null; accessedAt: string; kind: string;
+  summary: string; limitation: string;
+};
+export type ResearchReview = {
+  id: string; type: string; company: string; summary: string;
+  evidenceIds: string[]; handling: string;
+};
+export type ResearchCoverage = {
+  source: string; accessedAt: string; candidateRecords: number; profilesRead: number;
+  matchingProfiles: number; existingProfiles: number; newProfiles: number;
+  otherOrMissingYear: number; unclearAI: number; dateConflicts: number; failedProfiles: number;
+  discoverySha256: string;
+};
+export type ResearchSnapshot = {
+  version: string; asOf: string; scope: string; limitations: string[];
+  categories: ResearchCategory[]; companies: ResearchCompany[];
+  observations: ResearchObservation[]; evidence: ResearchEvidence[];
+  reviews: ResearchReview[]; coverage?: ResearchCoverage;
+};
+
+export function evidenceUrl(value: string): string | undefined {
+  try {
+    const url = new URL(value);
+    return ["https:", "http:"].includes(url.protocol) ? url.href : undefined;
+  } catch { return undefined; }
+}
+
+export function validateResearch(snapshot: ResearchSnapshot) {
+  const unique = (values: string[], label: string) => {
+    if (new Set(values).size !== values.length || values.some((v) => !v))
+      throw new Error(`Duplicate or missing research ${label}`);
+    return new Set(values);
+  };
+  if (!snapshot.version || !/^\d{4}-\d{2}-\d{2}$/.test(snapshot.asOf))
+    throw new Error("Invalid research dataset metadata");
+  const categories = unique(snapshot.categories.map((c) => c.id), "categories");
+  const companies = unique(snapshot.companies.map((c) => c.id), "companies");
+  const evidence = unique(snapshot.evidence.map((e) => e.id), "evidence");
+  unique(snapshot.observations.map((o) => o.id), "observations");
+  unique(snapshot.reviews.map((r) => r.id), "reviews");
+  for (const c of snapshot.companies) {
+    if (c.profileOnly && (c.revenueStatus !== "unknown" || !c.classificationBasis))
+      throw new Error(`Invalid profile-only research record: ${c.id}`);
+    if (!categories.has(c.cat) || !evidenceUrl(c.url) ||
+        c.evidenceIds.some((id) => !evidence.has(id)) ||
+        (c.pricingEvidence && !evidence.has(c.pricingEvidence)))
+      throw new Error(`Invalid research company reference: ${c.id}`);
+  }
+  for (const e of snapshot.evidence) {
+    if (!evidenceUrl(e.url) || (e.companyId && !companies.has(e.companyId)))
+      throw new Error(`Invalid research evidence: ${e.id}`);
+  }
+  for (const o of snapshot.observations) {
+    if (!companies.has(o.company) || !evidence.has(o.evidence) ||
+        !Number.isFinite(o.value))
+      throw new Error(`Invalid research observation: ${o.id}`);
+  }
+  const coverage = snapshot.coverage;
+  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)))
+    throw new Error("Invalid research coverage accounting");
+  for (const r of snapshot.reviews)
+    if (r.evidenceIds.some((id) => !evidence.has(id)))
+      throw new Error(`Invalid research review: ${r.id}`);
+}
+
+export function categorySummary(snapshot: ResearchSnapshot) {
+  return snapshot.categories.map((category) => {
+    const companies = snapshot.companies.filter((c) => c.cat === category.id);
+    return { ...category, count: companies.length,
+      self: companies.filter((c) => c.revenueStatus === "self").length,
+      estimate: companies.filter((c) => c.revenueStatus === "estimate").length,
+      unknown: companies.filter((c) => c.revenueStatus === "unknown").length };
+  });
+}

apps/docs/src/lib/auth-store.ts

@@ -1,14 +1,8 @@
-import { chmodSync } from "node:fs";
-import { dirname, join } from "node:path";
-import { DatabaseSync } from "node:sqlite";
 import { authId, matchingStep, type AuthConfig } from "./auth";
+import { openSiteDatabase } from "./site-database";
 
 function database() {
-  const configFile = process.env.AUTH_CONFIG_FILE;
-  if (!configFile) throw new Error("Authentication is not configured");
-  const file = join(dirname(configFile), "login-state.sqlite");
-  const db = new DatabaseSync(file);
-  chmodSync(file, 0o600);
+  const db = openSiteDatabase();
   db.exec(`PRAGMA busy_timeout=5000;
     CREATE TABLE IF NOT EXISTS login_state (
       id TEXT PRIMARY KEY, window_start INTEGER NOT NULL,

apps/docs/src/lib/site-database.ts

@@ -0,0 +1,20 @@
+import { chmodSync } from "node:fs";
+import { dirname, join } from "node:path";
+import { DatabaseSync } from "node:sqlite";
+
+// Keep the historical filename so existing authentication state is preserved.
+// Research and authentication use different tables in this same site database.
+export function openSiteDatabase() {
+  const configFile = process.env.AUTH_CONFIG_FILE;
+  if (!configFile) throw new Error("Authentication is not configured");
+  const file = join(dirname(configFile), "login-state.sqlite");
+  const db = new DatabaseSync(file);
+  try {
+    chmodSync(file, 0o600);
+    db.exec("PRAGMA busy_timeout=5000; PRAGMA foreign_keys=ON;");
+    return db;
+  } catch (error) {
+    db.close();
+    throw error;
+  }
+}

apps/docs/src/pages/api/research/ai-companies.ts

@@ -0,0 +1,13 @@
+import type { NextApiRequest, NextApiResponse } from "next";
+import { readResearchSnapshot } from "@/lib/ai-research-store";
+
+// The site's existing proxy protects this endpoint with the same login session.
+export default function handler(request: NextApiRequest, response: NextApiResponse) {
+  response.setHeader("Cache-Control", "private, no-store");
+  if (request.method !== "GET") {
+    response.setHeader("Allow", "GET");
+    return response.status(405).end();
+  }
+  try { return response.status(200).json(readResearchSnapshot()); }
+  catch { return response.status(503).json({ error: "研究数据库暂时不可用，请稍后重试" }); }
+}

apps/docs/src/pages/docs/[...slug].tsx

@@ -4,6 +4,7 @@ import type {
   InferGetStaticPropsType,
 } from "next";
 import Head from "next/head";
+import dynamic from "next/dynamic";
 import Link from "next/link";
 import {
   Children,
@@ -24,6 +25,7 @@ import { Icon } from "@/components/Icon";
 import { headingsFor } from "@/lib/navigation";
 
 type Props = { doc: Doc; docs: DocLink[] };
+const AICompanyResearch = dynamic(() => import("@/components/AICompanyResearch"));
 export const getStaticPaths: GetStaticPaths = async () => ({
   paths: (await listDocs()).map(({ slug }) => ({ params: { slug: slug.split("/") } })),
   fallback: false,
@@ -88,7 +90,7 @@ export default function DocPage({
         <meta name="description" content={doc.description} />
       </Head>
       <Shell key={doc.slug} docs={docs} current={doc.slug}>
-        <div className="reading-layout">
+        <div className={`reading-layout${doc.collection === "AI 公司研究" ? " research-layout" : ""}`}>
           <aside className="sidebar">
             <Navigation docs={docs} current={doc.slug} />
           </aside>
@@ -225,6 +227,7 @@ export default function DocPage({
                 {doc.content}
               </ReactMarkdown>
             </article>
+            {doc.slug === "other-research/ai-company-research/overview" && <AICompanyResearch />}
             <div className="article-end">
               
               <a

apps/docs/src/styles/globals.css

@@ -1381,3 +1381,92 @@ svg { flex-shrink: 0; }
  .category-menu { position: static; }
  .category-panel, .category-menu:last-child .category-panel { width: auto; left: 0; right: 0; }
 }
+
+/* Research keeps the documentation navigation and uses the remaining reading width. */
+.research-layout { grid-template-columns: 240px minmax(0, 1fr); }
+.research-layout .reading-main { max-width: 1440px; width: 100%; }
+.research-layout > .toc { display: none; }
+.ai-research { margin-top: 28px; font-size: 13px; line-height: 1.65; }
+.ai-research h2 { font-size: 20px; font-weight: 600; margin: 0 0 10px; letter-spacing: -.4px; }
+.ai-research h3 { font-size: 15px; font-weight: 600; margin: 18px 0 8px; }
+.ai-research p { margin: 6px 0 10px; }
+.ai-research a, .research-company-name { color: var(--green); }
+.ai-research a:hover, .research-company-name:hover { text-decoration: underline; }
+.ai-research button { text-align: left; }
+.research-meta { display: flex; flex-wrap: wrap; gap: 12px 24px; color: var(--muted); font-size: 12px; }
+.research-stats { display: grid; grid-template-columns: repeat(4,minmax(0,1fr)); gap: 16px; margin: 22px 0; }
+.research-stats > div { border-top: 1px solid var(--line); padding: 14px 0; }
+.research-stats strong { display: block; font-size: 29px; line-height: 1.3; font-weight: 550; font-variant-numeric: tabular-nums; }
+.research-stats span { color: var(--muted); font-size: 12px; }
+.research-scope { padding: 14px 18px; background: var(--soft); border-radius: 7px; }
+.research-scope summary { color: var(--green); font-weight: 500; }
+.research-scope ul { padding-left: 20px; }
+.research-section { margin: 38px 0; scroll-margin-top: 92px; }
+.research-muted, .research-footnote { color: var(--muted); font-size: 12px; }
+.research-categories { display: grid; grid-template-columns: repeat(2,minmax(0,1fr)); gap: 8px 26px; margin-top: 20px; }
+.research-categories button { padding: 12px 0; background: transparent; border: 0; border-bottom: 1px solid var(--line); }
+.research-categories button:hover { color: var(--green); }
+.research-categories button > div, .research-revenue-chart > div > div { display: flex; justify-content: space-between; gap: 16px; }
+.research-categories strong { font-variant-numeric: tabular-nums; }
+.research-categories small { font-size: 11px; color: var(--muted); }
+.research-bar { display: block; height: 5px; background: #f0f3f1; margin: 8px 0; border-radius: 3px; overflow: hidden; }
+.research-bar i { display: block; height: 100%; background: #47856d; border-radius: 3px; }
+.research-bar[data-estimate] i { background: #b98a40; }
+.research-tabs { display: flex; gap: 18px; border-bottom: 1px solid var(--line); margin: 18px 0; overflow-x: auto; }
+.research-tabs button { padding: 10px 0; white-space: nowrap; background: none; border: 0; border-bottom: 2px solid transparent; color: var(--muted); }
+.research-tabs button[aria-pressed="true"] { border-bottom-color: var(--green); color: var(--green); font-weight: 600; }
+.research-filters { display: flex; flex-wrap: wrap; align-items: end; gap: 12px; }
+.research-filters label { display: flex; flex-direction: column; gap: 5px; color: var(--muted); font-size: 11px; flex: 1 1 140px; }
+.research-filters .research-query { flex: 2 1 210px; }
+.research-filters :is(input,select) { min-width: 0; width: 100%; padding: 8px 10px; font-size: 12px; color: var(--ink); background: #fff; border: 1px solid #dfe6e0; border-radius: 5px; height: 36px; }
+.research-result-count { display: flex; justify-content: space-between; margin: 14px 0 8px; color: var(--muted); font-size: 12px; }
+.research-result-count button { border: 0; background: none; color: var(--green); }
+.research-table-wrap { overflow-x: auto; max-width: 100%; }
+.ai-research table { width: 100%; border-collapse: collapse; min-width: 720px; text-align: left; font-size: 12px; }
+.ai-research caption { text-align: left; color: var(--muted); padding: 12px 0; font-size: 12px; }
+.ai-research th { color: var(--muted); background: #f7f9f7; font-weight: 500; }
+.ai-research :is(th,td) { padding: 12px 14px; border-bottom: 1px solid var(--line); vertical-align: top; }
+.ai-research td:first-child { min-width: 140px; }
+.ai-research td:nth-child(2) { min-width: 220px; }
+.ai-research td p { margin: 6px 0; }
+.ai-research td small { display: block; color: var(--muted); margin-top: 5px; }
+.ai-research tr[data-selected] { background: #f0f8f3; }
+.research-company-name { font-weight: 600; background: none; border: 0; padding: 0; }
+.research-tag { display: inline-block; font-size: 10px; line-height: 1.7; padding: 1px 6px; border-radius: 3px; background: #eef3ef; color: #596e60; }
+.research-pagination { display: flex; justify-content: space-between; align-items: center; gap: 16px; margin-top: 16px; }
+.research-pagination button, .research-message button, .research-detail-heading button { padding: 6px 11px; border-radius: 4px; border: 1px solid var(--line); background: white; }
+.research-pagination button:disabled { color: #a8afa9; cursor: default; }
+.research-message { padding: 24px 0; color: var(--muted); }
+.research-message button { margin-left: 12px; color: var(--green); }
+.research-notice { border-left: 3px solid #c6a063; padding: 10px 16px; background: #faf8f2; }
+.research-revenue-chart { display: grid; gap: 18px; padding: 18px 0 30px; }
+.research-revenue-chart button { padding: 0; border: 0; background: none; color: var(--green); }
+.research-revenue-chart strong { font-variant-numeric: tabular-nums; font-weight: 500; }
+.research-revenue-chart small { color: var(--muted); font-size: 11px; }
+.research-evidence-list, .research-review-list { list-style: none; padding: 0; margin: 0; }
+.research-evidence { padding: 18px 0; border-bottom: 1px solid var(--line); scroll-margin-top: 92px; }
+.research-evidence > div { display: flex; align-items: center; gap: 10px; margin-bottom: 8px; }
+.research-evidence code { font-size: 11px; color: var(--muted); }
+.research-evidence strong { font-weight: 500; }
+.research-evidence small { color: var(--muted); font-size: 11px; }
+.research-review-list > li { padding: 20px 0; border-bottom: 1px solid var(--line); }
+.research-review-list h3 { margin: 8px 0; }
+.research-review-list > li > div { display: flex; gap: 14px; flex-wrap: wrap; }
+.research-detail { padding-top: 24px; border-top: 2px solid #dbe8df; }
+.research-detail-heading { display: flex; align-items: center; justify-content: space-between; gap: 18px; }
+.research-company-facts { margin: 24px 0; }
+.research-company-facts > div { display: grid; grid-template-columns: 90px minmax(0,1fr); gap: 12px; padding: 9px 0; border-bottom: 1px solid var(--line); }
+.research-company-facts dt { color: var(--muted); }
+.research-company-facts dd { margin: 0; }
+.research-footnote { border-top: 1px solid var(--line); padding: 18px 0; }
+@media (max-width: 760px) {
+  .research-layout { grid-template-columns: 1fr; }
+  .research-layout .reading-main { padding: 26px 24px 0; }
+  .research-section, .research-evidence { scroll-margin-top: 176px; }
+}
+@media (max-width: 560px) {
+  .research-stats { grid-template-columns: repeat(2,minmax(0,1fr)); gap: 4px 18px; }
+  .research-categories { grid-template-columns: 1fr; }
+  .research-tabs { gap: 16px; }
+  .research-layout .reading-main { padding: 22px 16px 0; }
+}

apps/docs/tests/research.test.ts

@@ -0,0 +1,112 @@
+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 { 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";
+
+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, 986);
+    assert.equal(initial.evidence.length, 1035);
+    assert.equal(initial.observations.length, 75);
+    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("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.self, 0), 8);
+  assert.equal(summary.reduce((n, c) => n + c.estimate, 0), 1);
+  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");
+  assert.ok(snapshot.observations.filter((o) => o.selection === "signal").every((o) => o.scope === "公司整体"));
+});
+
+// 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.teamBound, ">");
+  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);
+    assert.equal(company.url, row.source);
+    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/);
+});

content/catalog.json

@@ -17,6 +17,14 @@
     }
   ],
   "documents": {
+    "ai-company-research/00-overview": {
+      "collection": "AI 公司研究",
+      "group": "公司与市场",
+      "description": "按业务分类查看 AI 公司、经营指标与原始证据，检查收入定义与数据缺项。",
+      "slug": "other-research/ai-company-research/overview",
+      "category": "其他研究",
+      "featured": true
+    },
     "00-endor-concepts-draft": {
       "group": "架构设计",
       "description": "Endor 的全球入口、区域运行时与对象数据。",

content/docs/ai-company-research/00-overview.md

@@ -0,0 +1,5 @@
+# AI 公司研究
+
+调查 2025—2026 年不同类型 AI 公司的业务、交付能力、规模与商业模式。分类表链接公司数据，公司数据链接经营指标与原始证据。
+
+以下工作台读取研究数据库。首批为公开资料定向试样，成立、公开发布和转型发布分别记录。未披露收入的公司继续保留，避免把收入资料缺失误当成零收入。

package.json

@@ -13,7 +13,8 @@
     "lint": "pnpm --filter @endor/docs run lint",
     "typecheck": "pnpm --filter @endor/docs run typecheck",
     "figures": "uv run --locked --project tools/figures endor-figures",
-    "check": "pnpm run lint && pnpm run typecheck && pnpm run test:auth && pnpm --filter @endor/docs run images && pnpm --filter @endor/docs run test:images && pnpm run figures && pnpm run build",
-    "test:auth": "pnpm --filter @endor/docs run test:auth"
+    "check": "pnpm run lint && pnpm run typecheck && pnpm run test:auth && pnpm run test:research && pnpm --filter @endor/docs run images && pnpm --filter @endor/docs run test:images && pnpm run figures && pnpm run build",
+    "test:auth": "pnpm --filter @endor/docs run test:auth",
+    "test:research": "pnpm --filter @endor/docs run test:research"
   }
 }

scripts/check-container.sh

@@ -6,6 +6,7 @@ uv sync --project tools/figures --locked
 pnpm run lint
 pnpm run typecheck
 pnpm --filter @endor/docs run test:auth
+pnpm --filter @endor/docs run test:research
 pnpm --filter @endor/docs run images
 pnpm --filter @endor/docs run test:images
 cp -R apps/docs/public/figures /tmp/expected-figures

scripts/classify-ai-profiles.py

@@ -0,0 +1,50 @@
+"""Draft business labels for public company profiles, never financial verification.
+
+Input is a directory of JSON records with a `company` object containing
+one_liner and tags, as retained by the official-profile research snapshot.
+Output is for review; unmatched records remain C00 rather than being forced.
+This tool does not fetch sources, modify the site database or run a build.
+"""
+import argparse
+import json
+import re
+from pathlib import Path
+
+def match(pattern,text):return bool(re.search(pattern,text,re.I))
+def classify(c):
+ short=c.get('one_liner') or '';tags=' '.join(c.get('tags') or [])
+ rules=[
+ ('C10',r'\brobot(?:s|ics|ic)?\b|embodied|physical intelligence|autonomous (?:driving|vehicle)|drones?|manufacturing hardware'),
+ ('C02',r'context compression|compression middleware|RNA intelligence|audio data for AI|synthetic data|data quality|\bGPU\b|\bGPUs\b|\bchips?\b|semiconductor|data centers?|datacenters?|inference|compute|training data|data labeling|data labelling|RL environments|reinforcement learning|model training'),
+ ('C07',r'precision medicine|ambulance|clinic|biology|manufacturers|distributors|fabrication|people-intelligence|deskless workers|health|medical|clinical|dental|physician|hospital|veterinar|therap|radiolog|pharma|legal|law firm|lawyer|litigation|accountant|accounting|audit\b|insurance|underwrit|financ|hedge funds?|bank|wealth|investment|investing|real estate|property|properties|construction|building (?:plan|code)|engineering projects|\bCAD\b|\bEDA\b|chip design|architecture|architects|logistics|supply chain|freight|global trade|compliance|government|govtech|lobby|energy|utilities|\bfleets?\b|education|edtech|\btutor|schools?|exam prep|tax\b|recruit|hiring|human resources|procurement|retail|e-commerce|ecommerce|merchants?|industrial'),
+ ('C03',r'AI evaluations|AI governance|voice agents|chat AI agents|harnesses|agent.{0,25}(?:infrastructure|tools|identity|identities|memory|evaluation|eval|observability|browser|payment|communication)|(?:infrastructure|tools|identity|identities|evaluation|eval|observability|browsers?|payments?).{0,25}agents?|\bMCP\b|agentmail|API.{0,20}agents?|developer.{0,15}agents?'),
+ ('C04',r'firmware|internal apps|coding|software engineer|code\b|codebase|developer|programming|app(?:lication)? (?:builder|creation|generation)|(?:build|building|make|create|generat).{0,25}(?:apps|applications|software)|\bDevOps\b|product docs|documentation engineer|\bIDE\b|logs and fix|testing|debug'),
+ ('C06',r'\bsales\b|marketing|customer support|customer service|call center|call centre|\bGTM\b|\bCRM\b|\bSEO\b|\bGEO\b|\bAEO\b|growth engine|outbound|telemarketing|advertis|\bads\b|contact center|customer success'),
+ ('C08',r'\bvideo\b|\bimage\b|\bphoto\b|\bfilm\b|\bdesign\b|animation|creative|creators?|content creation|\bmusic\b|media|audio edit|voiceover'),
+ ('C01',r'foundation models?|frontier models?|large language models?|\bLLMs?\b|voice model|speech model|world model'),
+ ('C09',r'consumer|personal|companions?|\bstor(?:y|ies)\b|entertainment|\bgam(?:e|es|ing)\b|social network|\bphone\b|smartphone|keyboard|your digital life'),
+ ('C05',r'\bB2B\b|enterprise|workflow|workspace|productivity|operations|\bSaaS\b|\bSOP\b|Word editor|spreadsheet|knowledge|company OS|company brain|work\b|teams?|business|employee|meeting|security|cyber|search'),
+ ]
+ for label,text in [('主营简介',short),('目录标签',tags)]:
+  for cat,pattern in rules:
+   if match(pattern,text):return cat,label+'的规则初分'
+ return 'C00','简介不足以确定主业务，待复核'
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--input", required=True, type=Path)
+    parser.add_argument("--output", required=True, type=Path)
+    args = parser.parse_args()
+    result = []
+    for path in sorted(args.input.glob("*.json")):
+        record = json.loads(path.read_text())
+        company = record["company"]
+        category, basis = classify(company)
+        result.append({"ycId": company["id"], "category": category,
+                       "basis": basis, "status": "provisional"})
+    args.output.write_text(json.dumps(result, ensure_ascii=False, indent=2) + "\n")
+
+
+if __name__ == "__main__":
+    main()