Merge pull request '修正动态发布测试使用已归档 Endor 集合的问题' (#54) from codex/current-catalog-smoke into main

Reviewed-on: #54

README.md

@@ -179,6 +179,18 @@ python3 scripts/documents-client.py save "$api_work_dir/document.json"
 
 客户端只自动重试一次临时网络或 `502/503/504` 错误，保持正文和请求 ID 不变；`409` 等业务错误不会自动覆盖。它不跟随 HTTP 重定向，避免将 Bearer 凭据转发到其他地址。正文和 Key 继续保存在数据库或私有文件中，不因使用 API 而进入 Git。
 
+### 上传正文图片
+
+使用前述 HTTPS 或 SSH 隧道配置以及 `read-write` 文档 API Key：
+
+```sh
+python3 scripts/documents-client.py upload-image ./diagram.png
+```
+
+客户端向 `POST /api/documents/images` 发送原始图片字节，`Content-Type` 为 `image/png`、`image/jpeg` 或 `image/webp`。服务端接受最大 8 MiB、2500 万像素的静态图，转换为最大 2000 × 4000 像素、2 MiB 的 WebP，并按处理后内容去重。
+
+把响应中的 `url` 放入 Markdown，例如 `![渲染流程图](/api/documents/images/<id>)`，然后通过章节 API 保存正文。登录读者和文档 API Key 均可读取图片。图片存入现有持久化 SQLite，同步纳入整库备份。仅导出正文的 `docs export` 保留图片引用，迁移时需使用包含图片的整库备份。
+
 ## 研究数据与检查
 
 研究工作台提供公司筛选、经营指标、原始证据、收费与交付模式、技术材料及核查记录。它区分公司披露、支付平台指标、第三方估算、融资和客户收益；未知收入不填零，材料可访问也不代表性能或商业效果已经验证。研究范围、样本限制和个案结论以工作台记录为准。

apps/docs/package.json

@@ -20,7 +20,8 @@
     "react": "19.3.1",
     "react-dom": "19.3.1",
     "react-markdown": "10.1.0",
-    "remark-gfm": "4.0.1"
+    "remark-gfm": "4.0.1",
+    "sharp": "0.35.5"
   },
   "devDependencies": {
     "@tailwindcss/postcss": "4.3.3",
@@ -33,7 +34,6 @@
     "eslint": "^9.39.5",
     "eslint-config-next": "16.4.3",
     "postcss": "8.5.31",
-    "sharp": "0.35.5",
     "tailwindcss": "4.3.3",
     "typescript": "~5.9.3"
   }

apps/docs/scripts/auth-cli.ts

@@ -182,10 +182,10 @@ async function main() {
   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, 1302);
+  assert.equal(research.companies.length, 1312);
   assert.equal(research.categories.length, 11);
-  assert.equal(research.evidence.length, 5310);
-  assert.equal(research.observations.length, 493);
+  assert.equal(research.evidence.length, 5354);
+  assert.equal(research.observations.length, 495);
   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);
@@ -196,15 +196,20 @@ async function main() {
   const searchResponse = await request("/api/search", { headers });
   assert.equal(searchResponse.status, 200);
   const searchIndex = await searchResponse.json();
+  assert.ok(!searchIndex.some((doc: { collection: string }) => doc.collection === "Endor 文档"), "Retired Endor documents stay out of search");
   assert.ok(searchIndex.some((doc: { slug: string; searchText: string }) => doc.slug === "source-studies/pretext/measurement-cache" && doc.searchText.includes("getSegmentMetrics")));
   for (const doc of searchIndex as { slug: string; sourceSlug: string }[]) {
     assert.ok(!doc.slug.split("/").some((part) => /^\d+-/.test(part)), doc.slug);
     const legacy = await request(`/docs/${doc.sourceSlug}?from=legacy`, { headers });
-    assert.equal(legacy.status, 308, doc.sourceSlug);
-    const destination = new URL(legacy.headers.get("location")!, base);
-    assert.equal(destination.pathname, `/docs/${doc.slug}`);
-    assert.equal(destination.searchParams.get("from"), "legacy");
     assert.ok(legacy.headers.get("cache-control")?.includes("no-store"));
+    if (doc.sourceSlug === doc.slug) {
+      assert.equal(legacy.status, 200, doc.sourceSlug);
+    } else {
+      assert.equal(legacy.status, 308, doc.sourceSlug);
+      const destination = new URL(legacy.headers.get("location")!, base);
+      assert.equal(destination.pathname, `/docs/${doc.slug}`);
+      assert.equal(destination.searchParams.get("from"), "legacy");
+    }
   }
   const routes = ["/", ...searchIndex.map((doc: { slug: string }) => `/docs/${doc.slug}`)];
   const raw = await request("/api/documents/source?slug=endor/endor-purpose-draft", { headers });
@@ -215,12 +220,13 @@ async function main() {
     const sourceSlug = "ci-live-document";
     const previous = readDocument(sourceSlug);
     if (command === "exercise") {
-      const first = saveDocument({ slug: "endor/ci-live-document", sourceSlug,
-        title: "Runtime document", category: "Endor", collection: "Endor 文档", group: "CI",
+      // Publication is tested in a current collection; Endor is intentionally retired.
+      const first = saveDocument({ slug: "runtime-tests/ci-live-document", sourceSlug,
+        title: "Runtime document", category: "语言与运行时", collection: "运行时验证", group: "CI",
         description: "Isolated smoke test", draft: true, featured: false,
         content: "# Runtime document\n\nInitial body" }, previous?.revision ?? 0);
       assert.equal((await request(`/docs/${first.slug}`, { headers })).status, 200);
-      saveDocument({ ...first, slug: "endor/ci-live-document-renamed", content: "# Runtime document\n\nUpdated without rebuilding" }, first.revision);
+      saveDocument({ ...first, slug: "runtime-tests/ci-live-document-renamed", content: "# Runtime document\n\nUpdated without rebuilding" }, first.revision);
     }
     const stored = readDocument(sourceSlug);
     assert.ok(stored, "Smoke document must exist after creation or restart");
@@ -228,11 +234,11 @@ async function main() {
     const live = await request(`/docs/${stored.slug}`, { headers });
     assert.equal(live.status, 200);
     assert.ok((await live.text()).includes("Updated without rebuilding"));
-    const alias = await request("/docs/endor/ci-live-document?live=1", { headers });
+    const alias = await request("/docs/runtime-tests/ci-live-document?live=1", { headers });
     assert.equal(alias.status, 308);
     assert.ok(alias.headers.get("location")?.includes("ci-live-document-renamed?live=1"));
     const updatedIndex = await (await request("/api/search", { headers })).json();
-    assert.ok(updatedIndex.some((doc: { searchText: string }) => doc.searchText.includes("Updated without rebuilding")));
+    assert.ok(updatedIndex.some((doc: { slug: string; searchText: string }) => doc.slug === stored.slug && doc.searchText.includes("Updated without rebuilding")));
   }
   let home = "";
   let purpose = "";
@@ -254,6 +260,17 @@ async function main() {
       for (const id of ids) assert.ok(html.includes(`href="#${id}"`), `TOC anchor: ${route}#${id}`);
     }
   }
+  assert.ok(!home.includes('data-category="Endor"'), "Superseded Endor collection is absent from navigation");
+  if (searchIndex.some((doc: { collection: string }) => doc.collection === "Endorphin")) {
+    assert.equal([...home.matchAll(/data-category="([^"]+)"/g)][0]?.[1], "Endorphin", "Endorphin is the first category");
+    assert.ok(home.includes('/docs/endorphin/value-proposition'), "Endorphin opens at its value proposition");
+  }
+  // Retired documents remain reachable for historical links and gallery checks.
+  if (!purpose) {
+    const archived = await request("/docs/endor/endor-purpose-draft", { headers });
+    assert.equal(archived.status, 200);
+    purpose = await archived.text();
+  }
   assert.ok(home.includes("资料库"));
   assert.ok(home.includes("/docs/source-studies/pretext/overview"));
   // Inline preview and zoom dialog must both use the compressed browser asset.

apps/docs/src/lib/collections.ts

@@ -1,5 +1,11 @@
 import type { DocLink } from "@/lib/docs";
 
+// Keep superseded Endor pages addressable without offering them as current material.
+export function catalogDocuments<T extends DocLink>(docs: T[]): T[] {
+  return docs.filter((doc) => doc.collection !== "Endor 文档")
+    .sort((a, b) => Number(b.collection === "Endorphin") - Number(a.collection === "Endorphin"));
+}
+
 export function collectionLabel(name: string) {
   return name.replace(/ 文档$| 源码教程$|问题集$/g, "");
 }
@@ -15,10 +21,13 @@ export function collectionIcon(name?: string): "book" | "code" | "layers" | "nod
   if (name?.includes("垃圾回收")) return "nodes";
   return "book";
 }
-export function collectionEntries(docs: DocLink[]) {
+export function collectionEntries(documents: DocLink[]) {
+  const docs = catalogDocuments(documents);
   return [...new Set(docs.map((doc) => doc.collection))].map((name) => {
     const items = docs.filter((doc) => doc.collection === name);
-    const entry = items.find((doc) => doc.slug.endsWith("/overview")) ?? items[0];
+    const entry = items.find((doc) => doc.slug.endsWith("/overview"))
+      ?? (name === "Endorphin" ? items.find((doc) => doc.featured) : undefined)
+      ?? items[0];
     return { name, entry, count: items.length };
   });
 }

apps/docs/src/lib/docs.ts

@@ -1,4 +1,5 @@
 import { randomUUID, createHash } from "node:crypto";
+import { catalogDocuments } from "./collections";
 import { openSiteDatabase } from "./site-database";
 import { DocumentValidationError, DocumentConflictError } from "./document-errors";
 import { sectionSchema, loadSections, reconcileSections, persistSections, splitSections, outline,
@@ -188,7 +189,7 @@ export async function readDoc(slug: string): Promise<Doc> {
 }
 
 export async function listDocs(): Promise<DocLink[]> {
-  return allDocuments().map(({ content: _, ...doc }) => { void _; return doc; });
+  return catalogDocuments(allDocuments()).map(({ content: _, ...doc }) => { void _; return doc; });
 }
 
 // Explicit, atomic bootstrap only. Runtime reads never import repository data.

apps/docs/src/lib/document-images.ts

@@ -0,0 +1,39 @@
+import { createHash } from "node:crypto";
+import { openSiteDatabase } from "./site-database";
+
+function openImages() {
+  const db = openSiteDatabase();
+  try {
+    db.exec(`CREATE TABLE IF NOT EXISTS document_images (
+      id TEXT PRIMARY KEY,
+      bytes BLOB NOT NULL
+    )`);
+    return db;
+  } catch (error) {
+    db.close();
+    throw error;
+  }
+}
+
+export function saveDocumentImage(bytes: Buffer) {
+  const id = createHash("sha256").update(bytes).digest("hex");
+  const db = openImages();
+  try {
+    db.prepare("INSERT INTO document_images (id, bytes) VALUES (?, ?) ON CONFLICT(id) DO NOTHING").run(id, bytes);
+    return id;
+  } finally {
+    db.close();
+  }
+}
+
+export function readDocumentImage(id: string) {
+  const db = openImages();
+  try {
+    const row = db.prepare("SELECT bytes FROM document_images WHERE id = ?").get(id) as
+      | { bytes: Uint8Array }
+      | undefined;
+    return row ? Buffer.from(row.bytes) : undefined;
+  } finally {
+    db.close();
+  }
+}

apps/docs/src/pages/api/documents/images/[id].ts

@@ -0,0 +1,24 @@
+import type { NextApiRequest, NextApiResponse } from "next";
+import { documentApiError } from "@/lib/documents-api";
+import { readDocumentImage } from "@/lib/document-images";
+
+// The site proxy accepts a logged-in reader or a document API key on this route.
+export default function handler(request: NextApiRequest, response: NextApiResponse) {
+  try {
+    response.setHeader("Cache-Control", "private, no-store");
+    response.setHeader("X-Content-Type-Options", "nosniff");
+    if (request.method !== "GET" && request.method !== "HEAD") {
+      response.setHeader("Allow", "GET, HEAD");
+      return response.status(405).end();
+    }
+    const id = request.query.id;
+    if (typeof id !== "string" || !/^[a-f0-9]{64}$/.test(id)) return response.status(404).end();
+    const bytes = readDocumentImage(id);
+    if (!bytes) return response.status(404).end();
+    response.setHeader("Content-Type", "image/webp");
+    response.setHeader("Content-Length", bytes.length);
+    return request.method === "HEAD" ? response.status(200).end() : response.status(200).send(bytes);
+  } catch (error) {
+    return documentApiError(response, error);
+  }
+}

apps/docs/src/pages/api/documents/images/index.ts

@@ -0,0 +1,64 @@
+import type { NextApiRequest, NextApiResponse } from "next";
+import sharp from "sharp";
+import { authorizeDocuments, documentApiError } from "@/lib/documents-api";
+import { saveDocumentImage } from "@/lib/document-images";
+
+const maxUploadBytes = 8 * 1024 * 1024;
+const maxStoredBytes = 2 * 1024 * 1024;
+const imageTypes = new Set(["image/png", "image/jpeg", "image/webp"]);
+const imageFormats = new Set(["png", "jpeg", "webp"]);
+
+export const config = { api: { bodyParser: false } };
+
+export default async function handler(request: NextApiRequest, response: NextApiResponse) {
+  try {
+    if (request.method !== "POST") {
+      response.setHeader("Allow", "POST");
+      return response.status(405).end();
+    }
+    if (!authorizeDocuments(request, response, true)) return;
+
+    const type = request.headers["content-type"]?.split(";")[0].trim().toLowerCase();
+    if (!type || !imageTypes.has(type)) {
+      return response.status(415).json({ error: "请上传 PNG、JPEG 或 WebP 图片" });
+    }
+    if (Number(request.headers["content-length"]) > maxUploadBytes) {
+      return response.status(413).json({ error: "图片上传上限为 8 MiB" });
+    }
+
+    const chunks: Buffer[] = [];
+    let length = 0;
+    for await (const chunk of request.iterator({ destroyOnReturn: false })) {
+      const bytes = Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk);
+      length += bytes.length;
+      if (length > maxUploadBytes) {
+        return response.status(413).json({ error: "图片上传上限为 8 MiB" });
+      }
+      chunks.push(bytes);
+    }
+
+    let encoded: Buffer;
+    try {
+      const input = sharp(Buffer.concat(chunks), { limitInputPixels: 25_000_000 });
+      const { format, pages } = await input.metadata();
+      if (!format || !imageFormats.has(format) || type !== `image/${format}` || (pages ?? 1) > 1) {
+        return response.status(415).json({ error: "图片格式需与声明一致，且只支持静态图片" });
+      }
+      encoded = await input.rotate()
+        .resize({ width: 2000, height: 4000, fit: "inside", withoutEnlargement: true })
+        .webp({ quality: 85 })
+        .toBuffer();
+    } catch {
+      return response.status(400).json({ error: "无法解码图片，或像素数量超过限制" });
+    }
+    if (encoded.length > maxStoredBytes) {
+      return response.status(413).json({ error: "处理后的图片超过 2 MiB，请缩小后重试" });
+    }
+
+    const id = saveDocumentImage(encoded);
+    const url = `/api/documents/images/${id}`;
+    return response.status(200).json({ id, url, contentType: "image/webp", size: encoded.length });
+  } catch (error) {
+    return documentApiError(response, error);
+  }
+}

apps/docs/src/pages/api/search.ts

@@ -1,4 +1,5 @@
 import type { NextApiRequest, NextApiResponse } from "next";
+import { catalogDocuments } from "@/lib/collections";
 import { allDocuments } from "@/lib/docs";
 
 // The proxy authenticates this endpoint, including index content.
@@ -9,7 +10,7 @@ export default async function handler(request: NextApiRequest, response: NextApi
     return response.status(405).end();
   }
   try {
-    const index = allDocuments().map(({ content, ...doc }) => ({ ...doc, searchText: content }));
+    const index = catalogDocuments(allDocuments()).map(({ content, ...doc }) => ({ ...doc, searchText: content }));
     return response.status(200).json(index);
   } catch {
     return response.status(503).json({ error: "文档数据库暂时不可用" });

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

@@ -23,6 +23,10 @@ import { collectionEntries, collectionLabel } from "@/lib/collections";
 import { Icon } from "@/components/Icon";
 import { headingsFor } from "@/lib/navigation";
 
+function isZoomableFigure(source: string) {
+  return source.startsWith("/figures/endor-") || /^\/api\/documents\/images\/[a-f0-9]{64}$/.test(source);
+}
+
 type Props = { doc: Doc; docs: DocLink[] };
 const AICompanyResearch = dynamic(() => import("@/components/AICompanyResearch"));
 export const getServerSideProps: GetServerSideProps<Props> = async ({ params, res, resolvedUrl }) => {
@@ -54,7 +58,8 @@ export default function DocPage({
   const [active, setActive] = useState("");
   
   const siblings = docs.filter((d) => d.collection === doc.collection);
-  const collectionEntry = collectionEntries(docs).find((c) => c.name === doc.collection)!.entry;
+  // Historical pages remain readable even when their collection is outside the catalog.
+  const collectionEntry = collectionEntries(docs).find((c) => c.name === doc.collection)?.entry ?? doc;
   const index = siblings.findIndex((d) => d.slug === doc.slug);
   useEffect(() => {
     const observer = new IntersectionObserver(
@@ -120,14 +125,14 @@ export default function DocPage({
                     const slides = node?.children.flatMap((child) =>
                       child.type === "element" && child.tagName === "img" &&
                       typeof child.properties.src === "string" &&
-                      child.properties.src.startsWith("/figures/endor-")
+                      isZoomableFigure(child.properties.src)
                         ? [{ source: child.properties.src, alt: String(child.properties.alt ?? "") }]
                         : [],
                     ) ?? [];
                     const onlyImages = node?.children.every((child) =>
                       (child.type === "element" && child.tagName === "img" &&
                         typeof child.properties.src === "string" &&
-                        child.properties.src.startsWith("/figures/endor-")) ||
+                        isZoomableFigure(child.properties.src)) ||
                       (child.type === "text" && child.value.trim() === ""),
                     );
                     if (slides.length > 1 && onlyImages) return <FigureGallery slides={slides} />;
@@ -141,7 +146,7 @@ export default function DocPage({
                     );
                   },
                   img: ({ src, alt }) =>
-                    typeof src === "string" && src.startsWith("/figures/endor-") ? (
+                    typeof src === "string" && isZoomableFigure(src) ? (
                       <ArchitectureFigure source={src} alt={alt ?? "Endor 架构图"} />
                     ) : (
                       // eslint-disable-next-line @next/next/no-img-element

apps/docs/tests/research.test.ts

@@ -92,7 +92,8 @@ test("ARR ledger preserves historical estimates without promoting targets, run r
   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), `${id}: historical claims, estimates and unknown currencies remain visible`);
-  for (const id of ["O050", "O052", "O053", "O055", "SR-O-AI067-runrate", "ROCKET-O-arr", "AQ-O-RUNRATE"])
+  for (const id of ["O050", "O052", "O053", "O055", "SR-O-AI067-runrate", "ROCKET-O-arr", "AQ-O-RUNRATE",
+    "SRLEARN1-O-CLAIR-D2C", "SRLEARN1-O-CLAIR-B2B"])
     assert.ok(!ids.has(id), `${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");
@@ -123,11 +124,11 @@ test("research revisions share the authentication database and preserve replay l
     for (let i = 0; i < 20; i++) consumeCode(config, "invalid");
     assert.equal(consumeCode(config, "invalid"), "limited");
     const initial = readResearchSnapshot();
-    assert.equal(initial.companies.length, 1302);
-    assert.equal(initial.evidence.length, 5310);
-    assert.equal(initial.observations.length, 493);
+    assert.equal(initial.companies.length, 1312);
+    assert.equal(initial.evidence.length, 5354);
+    assert.equal(initial.observations.length, 495);
     const businessReviews = initial.reviews.filter((review) => review.type === businessModelReviewType);
-    assert.equal(businessReviews.length, 22);
+    assert.equal(businessReviews.length, 26);
     assert.deepEqual(businessReviews, seed.reviews.filter((review) => review.type === businessModelReviewType)
       .sort((a, b) => a.id.localeCompare(b.id)),
       "business model assessments and company/evidence links persist in the shared database");
@@ -169,9 +170,9 @@ test("research validation rejects broken evidence and unsafe source links", () =
 
 test("reviews link explicit companies without turning global or excluded cases into companies", () => {
   const snapshot = structuredClone(seed) as ResearchSnapshot;
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 291);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 157);
-  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 62);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "companies").length, 299);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "dataset").length, 159);
+  assert.equal(snapshot.reviews.filter((r) => r.scope === "excluded-candidate").length, 65);
   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")!), []);
@@ -190,11 +191,11 @@ test("reviews link explicit companies without turning global or excluded cases i
 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), 1302);
+  assert.equal(summary.reduce((n, c) => n + c.count, 0), 1312);
   assert.equal(summary.reduce((n, c) => n + c.self, 0), 63);
   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), 1218);
+  assert.equal(summary.reduce((n, c) => n + c.unknown, 0), 1228);
   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"));
@@ -229,7 +230,7 @@ test("service run rates, legacy freight revenue and paid adoption do not become
 
 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, 293);
+  assert.equal(snapshot.companies.filter((c) => c.technicalReview).length, 303);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "public-artifact").length, 29);
   assert.equal(snapshot.companies.filter((c) => c.technicalReview?.level === "independent-test").length, 1);
   assert.equal(snapshot.companies.find((c) => c.id === "AI051")?.revenueStatus, "unknown");
@@ -645,10 +646,10 @@ test("public Speedrun cohort rosters preserve the finite boundary without invent
   const newlyRegistered = rosters.filter((batch) => !batch.id.startsWith("SR007-")).flatMap((batch) => batch.records);
   assert.equal(newlyRegistered.length, 242);
   assert.equal(newlyRegistered.filter((row) => row.status === "pending-year").length, 5);
-  assert.equal(newlyRegistered.filter((row) => row.status === "linked").length, 58);
+  assert.equal(newlyRegistered.filter((row) => row.status === "linked").length, 68);
   assert.equal(newlyRegistered.filter((row) => row.status === "existing-outside-cohort").length, 1);
   assert.equal(newlyRegistered.filter((row) => row.status === "outside-cohort").length, 144);
-  assert.equal(newlyRegistered.filter((row) => row.status === "pending-ai").length, 34,
+  assert.equal(newlyRegistered.filter((row) => row.status === "pending-ai").length, 24,
     "a known self-reported founding year does not by itself establish the current AI business");
   assert.equal(newlyRegistered.filter((row) => row.profileStatus === "readable").length, 232);
   assert.ok(newlyRegistered.filter((row) => row.status === "outside-cohort").every((row) =>

content/research/ai-companies.sources.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-11-01-sr-robot-evals-1",
+  "version": "2026-11-01-source-closeout-1",
   "scopeConfirmedAt": "2026-10-30",
   "acceptance": "以确认的公开来源清单为边界，逐条核对并标明缺项。",
   "provenance": "S01—S12恢复自已提交用户的《AI公司研究_来源与分类模板》来源清单；S13—S16单列后续已使用的补充证据渠道，不将使用次数当作全量覆盖。",
@@ -3040,8 +3040,8 @@
         "speedrun.a16z.com"
       ],
       "initialAccess": "见具体证据访问记录",
-      "boundary": "公开七批321唯一位置及原HTML/GET审计保留；226补读档案中138旧年、88自报两年：49已补官网关联、34当前AI/主体待核、5品牌/年份待核。本系列311独立档案已读，10复用未本轮重读。七批129关联、1既有超年、145旧年、6品牌/年份、40当前AI/交付待核。新增SafeWorld/Sparta/Syncere/ThirdBrain/Dispatcher/Sonatic并保留封闭beta、邀请预订/候补、法律页和当前版本缺项。新增20证据，不增经营观测；原493、ARR/MRR和YC覆盖保留。厂商历史20/20含4已知差异，不当当前/独立验收；未来月费/候补不作ARR。",
-      "nextCheck": "继续34个新批次及SR007六个主营待核、10复用变化；核品牌/注册及实际合同/付费。Sparta当前候选/连接器验收和额度成本、Syncere制造/交付/保修/未来费率、ThirdBrain权重IP及专家训练成本、SafeWorld实际评估协议、Dispatcher实体运营及Sonatic权限/本域条款缺项需补。不以历史厂商报告、演示/候补或未来报价推当前性能、ARR/造假概率。",
+      "boundary": "公开七批321唯一位置及原HTML/GET审计保留；226补读档案中138旧年、88自报两年：59已补官网关联、24当前AI/主体待核、5品牌/年份待核。本系列311独立档案已读，10复用未冒充本轮重读。七批139关联、1既有超年、145旧年、6品牌/年份、30当前AI/交付待核。最后20个初始备注已逐项核对14官网和6缺有效网址，替换具体缺项；5新关联，15留未决，不继续扩池。新增23证据，原495经营记录/ARR/MRR和YC保留。有限来源逐条核对并保留未决，不证明未公开公司覆盖或全部注册/技术/财务审计。",
+      "nextCheck": "本轮有限公开来源首轮核对已落实具体记录/缺项；24新批次及SR007六项AI/身份、六项年份未决保留，不用标签强填。后续只有新增公司原件、可访问产品、注册/品牌链或真实合同/净费/财务日出现时补证；不无限重试同一空页/权限失败，也不由采用/请求/未来全上线预测推ARR/造假。",
       "limitation": "来源可读不等于声明已独立验证。",
       "rosterAudit": {
         "url": "https://speedrun.a16z.com/companies",
@@ -3189,8 +3189,8 @@
         },
         "outsideTargetYears": 138,
         "targetYearSelfReports": 88,
-        "newLinkedCompanies": 49,
-        "pendingCurrentAIOrIdentity": 34,
+        "newLinkedCompanies": 59,
+        "pendingCurrentAIOrIdentity": 24,
         "records": [
           {
             "candidateId": "SR001R-C01",

content/research/ai-income-analysis.json

@@ -1,5 +1,5 @@
 {
-  "sourceVersion": "2026-11-01-sr-robot-evals-1",
+  "sourceVersion": "2026-11-01-source-closeout-1",
   "asOf": "2026-11-01",
   "metric": "platform-mrr-usd",
   "sampleUnit": "product-or-business",

pnpm-lock.yaml

@@ -28,6 +28,9 @@ importers:
       remark-gfm:
         specifier: 4.0.1
         version: 4.0.1(supports-color@7.2.0)
+      sharp:
+        specifier: 0.35.5
+        version: 0.35.5(@types/node@22.20.5)
     devDependencies:
       '@tailwindcss/postcss':
         specifier: 4.3.3
@@ -59,9 +62,6 @@ importers:
       postcss:
         specifier: 8.5.31
         version: 8.5.31
-      sharp:
-        specifier: 0.35.5
-        version: 0.35.5(@types/node@22.20.5)
       tailwindcss:
         specifier: 4.3.3
         version: 4.3.3

scripts/documents-client.py

@@ -45,14 +45,15 @@ def read_token(filename):
     return value
 
 
-def request(base, token, method, path, payload=None, request_id=None):
-    data = None if payload is None else json.dumps(payload, ensure_ascii=False).encode()
+def request(base, token, method, path, payload=None, request_id=None, *, image_type=None):
+    data = payload if image_type else (None if payload is None else json.dumps(payload, ensure_ascii=False).encode())
     if data is not None and len(data) > 8 * 1024 * 1024:
         raise ValueError('Request exceeds 8 MiB; split into smaller atomic batches')
     headers = {'Authorization': 'Bearer ' + token, 'Accept': 'application/json'}
     if data is not None:
-        headers['Content-Type'] = 'application/json'
-        headers['Idempotency-Key'] = request_id
+        headers['Content-Type'] = image_type or 'application/json'
+        if request_id is not None:
+            headers['Idempotency-Key'] = request_id
     opener = urllib.request.build_opener(NoRedirect())
     for attempt in range(2):
         req = urllib.request.Request(base + path, data=data, method=method, headers=headers)
@@ -127,6 +128,8 @@ def main():
     editing.add_argument('slug')
     editing.add_argument('file')
     editing.add_argument('--request-id')
+    upload = sub.add_parser('upload-image', help='Upload a static image and print its Markdown URL')
+    upload.add_argument('file')
     saving = sub.add_parser('save')
     saving.add_argument('file', help='Private JSON file or - for stdin; one document or {documents: [...]}')
     saving.add_argument('--request-id', help='Reuse this id only with the same input when retrying')
@@ -136,7 +139,18 @@ def main():
     try:
         base = server_url(args.url)
         token = read_token(args.key_file)
-        if args.command == 'list':
+        if args.command == 'upload-image':
+            image = Path(args.file)
+            image_types = {'.png': 'image/png', '.jpg': 'image/jpeg', '.jpeg': 'image/jpeg', '.webp': 'image/webp'}
+            image_type = image_types.get(image.suffix.lower())
+            if not image_type:
+                raise ValueError('Use a PNG, JPEG or WebP image')
+            with image.open('rb') as source:
+                data = source.read(8 * 1024 * 1024 + 1)
+            if len(data) > 8 * 1024 * 1024:
+                raise ValueError('Image exceeds 8 MiB')
+            result = request(base, token, 'POST', '/api/documents/images', data, image_type=image_type)
+        elif args.command == 'list':
             result = request(base, token, 'GET', '/api/documents?' + urllib.parse.urlencode(
                 {'limit': args.limit, 'offset': args.offset}))
         elif args.command == 'get':