import { writeFileSync } from "node:fs"; const cdpPort = process.env.CDP_PORT ?? "9225"; const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4323"; const pages = await fetch(`http://127.0.0.1:${cdpPort}/json/list`).then((response) => response.json()); const page = pages.find((entry) => entry.type === "page"); if (!page) throw new Error(`CDP ${cdpPort} 没有可用页面`); const socket = new WebSocket(page.webSocketDebuggerUrl); await new Promise((resolve, reject) => { socket.addEventListener("open", resolve, { once: true }); socket.addEventListener("error", reject, { once: true }); }); let nextId = 0; const pending = new Map(); const exceptions = []; socket.addEventListener("message", (event) => { const message = JSON.parse(event.data); if (message.id && pending.has(message.id)) { const { resolve, reject } = pending.get(message.id); pending.delete(message.id); if (message.error) reject(new Error(message.error.message)); else resolve(message.result); } if (message.method === "Runtime.exceptionThrown") { exceptions.push(message.params.exceptionDetails.exception?.description ?? message.params.exceptionDetails.text); } }); const command = (method, params = {}) => new Promise((resolve, reject) => { const id = ++nextId; pending.set(id, { resolve, reject }); socket.send(JSON.stringify({ id, method, params })); }); const pause = (milliseconds) => new Promise((resolve) => setTimeout(resolve, milliseconds)); const evaluate = async (expression) => { const result = await command("Runtime.evaluate", { expression, returnByValue: true, awaitPromise: true }); if (result.exceptionDetails) throw new Error(result.exceptionDetails.exception?.description ?? result.exceptionDetails.text); return result.result.value; }; const navigate = async (path) => { await command("Page.navigate", { url: `${baseUrl}${path}` }); for (let attempt = 0; attempt < 70; attempt += 1) { await pause(100); if (await evaluate("document.readyState === 'complete'")) return; } throw new Error(`${path} 加载超时`); }; const screenshot = async (path) => { const result = await command("Page.captureScreenshot", { format: "png", captureBeyondViewport: false, }); writeFileSync(path, Buffer.from(result.data, "base64")); }; await command("Page.enable"); await command("Runtime.enable"); await command("Emulation.setDeviceMetricsOverride", { width: 1440, height: 1100, deviceScaleFactor: 1, mobile: false, }); await navigate("/multimodal/"); await screenshot("/tmp/llm-atlas-multimodal-desktop.png"); const overview = await evaluate(`(() => ({ title: document.querySelector("h1")?.textContent.trim(), sections: document.querySelectorAll(".article-section").length, tocLinks: document.querySelectorAll(".side-rail a").length, paperLinks: document.querySelectorAll(".paper-chain a").length, labTabs: document.querySelectorAll("[data-mm-tab]").length, labPanels: document.querySelectorAll("[data-mm-panel]").length, navLinks: document.querySelectorAll(".top-nav a").length, documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth, }))()`); const tokens = await evaluate(`(() => { const root = document.querySelector("[data-mm-lab]"); const read = () => ({ patches: root.querySelector("[data-token-patches]").textContent.trim(), visual: root.querySelector("[data-token-visual]").textContent.trim(), share: root.querySelector("[data-token-share]").textContent.trim(), status: root.querySelector("[data-token-status]").textContent.trim(), visiblePanel: root.querySelector("[data-mm-panel]:not([hidden])").dataset.mmPanel, }); const initial = read(); const resolution = root.querySelector("[data-token-resolution]"); const frames = root.querySelector("[data-token-frames]"); const context = root.querySelector("[data-token-context]"); resolution.value = "7"; resolution.dispatchEvent(new Event("input", { bubbles: true })); frames.value = "32"; frames.dispatchEvent(new Event("input", { bubbles: true })); context.value = "8192"; context.dispatchEvent(new Event("input", { bubbles: true })); root.querySelector('[data-spatial="1"]').click(); const overloaded = read(); return { initial, overloaded }; })()`); const connector = await evaluate(`(() => { const root = document.querySelector("[data-mm-lab]"); root.querySelector('[data-mm-tab="connector"]').click(); const read = () => ({ visual: root.querySelector("[data-connector-visual]").textContent.trim(), alignment: root.querySelector("[data-connector-alignment]").textContent.trim(), score: root.querySelector("[data-native-score]").textContent.trim(), activeNative: root.querySelectorAll("[data-native-item].active").length, visiblePanel: root.querySelector("[data-mm-panel]:not([hidden])").dataset.mmPanel, }); root.querySelector('[data-connector="k3"]').click(); const k3 = read(); root.querySelector('[data-connector="kimivl"]').click(); const kimiVl = read(); return { k3, kimiVl }; })()`); const ocr = await evaluate(`(() => { const root = document.querySelector("[data-mm-lab]"); root.querySelector('[data-mm-tab="ocr"]').click(); const curve = root.querySelector("[data-ocr-curve]"); const read = () => ({ ratio: root.querySelector("[data-ocr-ratio]").textContent.trim(), accuracy: root.querySelector("[data-ocr-accuracy]").textContent.trim(), evidence: root.querySelector("[data-ocr-evidence]").textContent.trim(), status: root.querySelector("[data-ocr-status]").textContent.trim(), }); const boundary = read(); curve.value = "15"; curve.dispatchEvent(new Event("input", { bubbles: true })); const interpolated = read(); curve.value = "23"; curve.dispatchEvent(new Event("input", { bubbles: true })); const unreported = read(); return { boundary, interpolated, unreported }; })()`); const loop = await evaluate(`(() => { const root = document.querySelector("[data-mm-lab]"); root.querySelector('[data-mm-tab="loop"]').click(); const read = () => ({ evidence: root.querySelector("[data-loop-evidence]").textContent.trim(), tools: root.querySelector("[data-loop-tools]").textContent.trim(), state: root.querySelector("[data-loop-state]").textContent.trim(), type: root.querySelector("[data-loop-type]").textContent.trim(), takeaway: root.querySelector("[data-loop-takeaway]").textContent.trim(), }); const toolsStart = read(); const next = root.querySelector("[data-loop-next]"); for (let index = 0; index < 4; index += 1) next.click(); const toolsEnd = read(); root.querySelector('[data-loop-mode="cot"]').click(); next.click(); next.click(); const cotEnd = read(); const firstTab = root.querySelector('[data-mm-tab="tokens"]'); firstTab.focus(); firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true })); return { toolsStart, toolsEnd, cotEnd, keyboardSelected: root.querySelector('[data-mm-tab][aria-selected="true"]').dataset.mmTab, keyboardVisible: root.querySelector("[data-mm-panel]:not([hidden])").dataset.mmPanel, }; })()`); await evaluate(`document.querySelector("[data-mm-lab]").scrollIntoView({ block: "start", behavior: "instant" })`); await pause(180); await screenshot("/tmp/llm-atlas-multimodal-lab-desktop.png"); await navigate("/"); const home = await evaluate(`(() => ({ releaseCards: document.querySelectorAll(".release-card").length, firstRelease: document.querySelector(".release-card h2").textContent.trim(), firstHref: document.querySelector(".release-card").getAttribute("href"), paperCount: document.querySelector(".hero-stats div:nth-child(3) b").textContent.trim(), navLinks: document.querySelectorAll(".top-nav a").length, }))()`); await navigate("/papers/"); const papers = await evaluate(`(() => { const button = [...document.querySelectorAll("[data-filter]")].find((node) => node.textContent.trim() === "多模态"); button?.click(); return { total: document.querySelectorAll("[data-paper]").length, multimodalVisible: document.querySelectorAll("[data-paper]:not([hidden])").length, hasFilter: Boolean(button), }; })()`); await command("Emulation.setDeviceMetricsOverride", { width: 390, height: 844, deviceScaleFactor: 1, mobile: true, }); await navigate("/multimodal/"); const mobile = await evaluate(`(() => { const root = document.querySelector("[data-mm-lab]"); root.scrollIntoView({ block: "start", behavior: "instant" }); const toggle = document.querySelector("#menu-toggle"); toggle?.click(); return { documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth, menuVisible: getComputedStyle(toggle).display !== "none", menuOpen: toggle.getAttribute("aria-expanded"), mobileLinks: document.querySelectorAll("#mobile-nav a").length, tabs: root.querySelectorAll("[data-mm-tab]").length, offenders: [...document.querySelectorAll("body *")] .filter((node) => !node.closest(".eval-matrix")) .filter((node) => node.getBoundingClientRect().right > document.documentElement.clientWidth + 1) .slice(0, 12) .map((node) => ({ tag: node.tagName, className: typeof node.className === "string" ? node.className : "", right: Math.round(node.getBoundingClientRect().right), width: Math.round(node.getBoundingClientRect().width), })), }; })()`); await pause(180); await screenshot("/tmp/llm-atlas-multimodal-mobile.png"); const report = { overview, tokens, connector, ocr, loop, home, papers, mobile, exceptions }; console.log(JSON.stringify(report, null, 2)); const numeric = (value) => Number.parseFloat(value.replaceAll(",", "")); const failures = []; if (!overview.title.includes("第一类输入")) failures.push("章节标题异常"); if (overview.sections !== 30 || overview.tocLinks !== 30) failures.push("章节/目录数量异常"); if (overview.paperLinks !== 55) failures.push("正式论文链不是 55 个节点"); if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常"); if (overview.navLinks !== 17 || home.navLinks !== 17 || mobile.mobileLinks !== 17) failures.push("全站导航未同步多模态专题"); if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出"); if (numeric(tokens.initial.patches) !== 5476 || numeric(tokens.initial.visual) !== 1369 || tokens.initial.visiblePanel !== "tokens") failures.push("视觉 Token 初始计算异常"); if (!tokens.overloaded.status.includes("超预算") || numeric(tokens.overloaded.share) <= 100) failures.push("超大视频没有触发上下文超预算"); if (!connector.k3.visual.includes("从头") || !connector.k3.alignment.includes("无 post-hoc") || connector.k3.score !== "5 / 5" || connector.k3.activeNative !== 5) failures.push("K3 训练制度预设异常"); if (connector.kimiVl.score !== "4 / 5" || connector.kimiVl.activeNative !== 4 || connector.k3.visiblePanel !== "connector") failures.push("Kimi-VL 原生五维预设异常"); if (ocr.boundary.status !== "BOUNDARY" || Math.abs(numeric(ocr.boundary.ratio) - 7.81) > 0.01) failures.push("OCR 初始压缩边界异常"); if (ocr.interpolated.status !== "TEACHING INTERPOLATION" || !ocr.interpolated.evidence.includes("教学插值")) failures.push("OCR 教学插值没有显式标记"); if (ocr.unreported.status !== "OUT OF EVIDENCE" || ocr.unreported.accuracy !== "未报告") failures.push("OCR 超证据区仍在外推"); if (loop.toolsStart.state !== "OPEN" || loop.toolsEnd.state !== "VERIFIED" || loop.toolsEnd.evidence !== "97%" || loop.toolsEnd.tools !== "3") failures.push("vision-in-the-loop 终局异常"); if (loop.cotEnd.state !== "FAILED" || !loop.cotEnd.takeaway.includes("不能凭空增加")) failures.push("文字 CoT 与新观察没有分开"); if (loop.keyboardSelected !== "connector" || loop.keyboardVisible !== "connector") failures.push("实验键盘 tab 导航异常"); if (home.releaseCards !== 12 || !home.firstRelease.includes("原生多模态") || home.firstHref !== "/multimodal/") failures.push("首页多模态首发入口异常"); if (home.paperCount !== "355" || papers.total !== 355 || !papers.hasFilter || papers.multimodalVisible < 59) failures.push("论文库多模态标签或总数异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`); if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`); if (failures.length) { console.error(`\nFAIL\n- ${failures.join("\n- ")}`); process.exitCode = 1; } else { console.log("\nPASS multimodal browser regression"); } socket.close();