wuyang
293 lines
13 KiB
JavaScript
293 lines
13 KiB
JavaScript
import { writeFileSync } from "node:fs";
|
||
|
||
const cdpPort = process.env.CDP_PORT ?? "9227";
|
||
const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4326";
|
||
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}${path}` });
|
||
for (let attempt = 0; attempt < 50; attempt += 1) {
|
||
await pause(100);
|
||
if (await evaluate("document.readyState === 'complete'")) return;
|
||
}
|
||
throw new Error(`${path} 加载超时`);
|
||
};
|
||
const screenshot = async (path, full = false) => {
|
||
const params = { format: "png", captureBeyondViewport: full };
|
||
if (full) {
|
||
const metrics = await command("Page.getLayoutMetrics");
|
||
params.clip = {
|
||
x: 0,
|
||
y: 0,
|
||
width: metrics.cssContentSize.width,
|
||
height: metrics.cssContentSize.height,
|
||
scale: 1,
|
||
};
|
||
}
|
||
const result = await command("Page.captureScreenshot", params);
|
||
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("/systems/numerics/");
|
||
await screenshot("/tmp/llm-atlas-numerics-desktop.png");
|
||
|
||
const format = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-numerics-lab]");
|
||
const metric = (name) => root.querySelector('[data-format-metric="' + name + '"]').textContent;
|
||
const initial = {
|
||
storage: metric("storage"),
|
||
status: metric("status"),
|
||
error: metric("absolute"),
|
||
};
|
||
root.querySelector('[data-format-choice="fp16"]').click();
|
||
root.querySelector('[data-format-preset="tiny"]').click();
|
||
const tinyFp16 = { status: metric("status"), encoded: metric("encoded") };
|
||
root.querySelector('[data-format-choice="e4m3"]').click();
|
||
root.querySelector('[data-format-preset="large"]').click();
|
||
const largeE4M3 = { status: metric("status"), encoded: metric("encoded") };
|
||
root.querySelector('[data-format-choice="mxfp4"]').click();
|
||
root.querySelector('[data-format-preset="one"]').click();
|
||
const outlier = root.querySelector('[data-format-input="outlier"]');
|
||
const local = { error: metric("absolute"), encoded: metric("encoded") };
|
||
outlier.value = "64";
|
||
outlier.dispatchEvent(new Event("input", { bubbles: true }));
|
||
return {
|
||
initial,
|
||
tinyFp16,
|
||
largeE4M3,
|
||
local,
|
||
shared: {
|
||
error: metric("absolute"),
|
||
encoded: metric("encoded"),
|
||
note: root.querySelector("[data-format-scale-note]").textContent,
|
||
},
|
||
};
|
||
})()`);
|
||
|
||
const ledger = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-numerics-lab]");
|
||
root.querySelector('[data-num-tab="ledger"]').click();
|
||
const read = () => ({
|
||
total: root.querySelector('[data-ledger-metric="total"]').textContent,
|
||
saving: root.querySelector('[data-ledger-metric="saving"]').textContent,
|
||
activation: root.querySelector('[data-ledger-metric="activation"]').textContent,
|
||
communication: root.querySelector('[data-ledger-metric="communication"]').textContent,
|
||
risks: root.querySelector("[data-ledger-risks]").textContent,
|
||
rows: root.querySelectorAll("[data-state-stack] > div").length,
|
||
});
|
||
root.querySelector('[data-precision-preset="bf16"]').click();
|
||
const bf16 = read();
|
||
root.querySelector('[data-precision-preset="v3"]').click();
|
||
const v3 = read();
|
||
root.querySelector('[data-precision-preset="k3"]').click();
|
||
const k3 = read();
|
||
return { bf16, v3, k3 };
|
||
})()`);
|
||
|
||
const optimizer = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-numerics-lab]");
|
||
root.querySelector('[data-num-tab="optimizer"]').click();
|
||
const ratio = root.querySelector('[data-optimizer-input="ratio"]');
|
||
ratio.value = "24";
|
||
ratio.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const read = () => ({
|
||
label: root.querySelector("[data-optimizer-label]").textContent,
|
||
imbalance: root.querySelector('[data-optimizer-metric="imbalance"]').textContent,
|
||
unit: root.querySelector('[data-optimizer-metric="unit"]').textContent,
|
||
note: root.querySelector("[data-optimizer-note]").textContent,
|
||
cells: root.querySelectorAll('[data-matrix="output"] i').length,
|
||
});
|
||
root.querySelector('[data-optimizer-choice="muon"]').click();
|
||
const full = read();
|
||
root.querySelector('[data-optimizer-choice="perhead"]').click();
|
||
const perHead = read();
|
||
return { full, perHead };
|
||
})()`);
|
||
|
||
const stability = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-numerics-lab]");
|
||
root.querySelector('[data-num-tab="stability"]').click();
|
||
const read = () => ({
|
||
summary: root.querySelector("[data-stability-summary]").textContent,
|
||
levels: [...root.querySelectorAll("[data-gauge] b")].map((node) => node.textContent),
|
||
defenses: [...root.querySelectorAll("[data-defense]:checked")].map((node) => node.dataset.defense),
|
||
timeline: root.querySelectorAll("[data-risk-timeline] i").length,
|
||
});
|
||
root.querySelector('[data-stability-preset="k2"]').click();
|
||
const k2 = read();
|
||
root.querySelector('[data-stability-preset="v4"]').click();
|
||
const v4 = read();
|
||
const firstTab = root.querySelector('[data-num-tab="format"]');
|
||
firstTab.focus();
|
||
firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "End", bubbles: true }));
|
||
return {
|
||
k2,
|
||
v4,
|
||
keyboard: {
|
||
selected: root.querySelector('[data-num-tab][aria-selected="true"]').dataset.numTab,
|
||
visible: root.querySelector("[data-num-view]:not([hidden])").dataset.numView,
|
||
},
|
||
};
|
||
})()`);
|
||
|
||
const layout = await evaluate(`(() => {
|
||
const nav = document.querySelector(".top-nav");
|
||
const meta = document.querySelector(".header-meta");
|
||
return {
|
||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||
navGap: Number((meta.getBoundingClientRect().left - nav.getBoundingClientRect().right).toFixed(1)),
|
||
navLinks: document.querySelectorAll(".top-nav a").length,
|
||
articleSections: document.querySelectorAll(".article-section").length,
|
||
paperLinks: document.querySelectorAll(".paper-chain a").length,
|
||
labTabs: document.querySelectorAll("[data-num-tab]").length,
|
||
views: document.querySelectorAll("[data-num-view]").length,
|
||
};
|
||
})()`);
|
||
|
||
await evaluate(`document.querySelector("[data-numerics-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
|
||
await pause(150);
|
||
await screenshot("/tmp/llm-atlas-numerics-lab-desktop.png");
|
||
|
||
await command("Emulation.setDeviceMetricsOverride", {
|
||
width: 390,
|
||
height: 844,
|
||
deviceScaleFactor: 1,
|
||
mobile: true,
|
||
});
|
||
await navigate("/systems/numerics/");
|
||
await evaluate(`document.querySelector("[data-numerics-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
|
||
await pause(100);
|
||
await screenshot("/tmp/llm-atlas-numerics-lab-mobile.png");
|
||
const mobile = await evaluate(`(() => {
|
||
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,
|
||
};
|
||
})()`);
|
||
|
||
await command("Emulation.setDeviceMetricsOverride", {
|
||
width: 1440,
|
||
height: 1100,
|
||
deviceScaleFactor: 1,
|
||
mobile: false,
|
||
});
|
||
await navigate("/");
|
||
const home = await evaluate(`({
|
||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||
releaseCards: document.querySelectorAll(".release-card").length,
|
||
firstRelease: document.querySelector(".release-card h2").textContent,
|
||
firstHref: document.querySelector(".release-card").getAttribute("href"),
|
||
paperCount: document.querySelector(".hero-stats div:nth-child(3) b").textContent,
|
||
navLinks: document.querySelectorAll(".top-nav a").length,
|
||
})`);
|
||
|
||
await navigate("/papers/");
|
||
const papers = await evaluate(`(() => {
|
||
const optimizer = [...document.querySelectorAll("[data-filter]")].find((node) => node.dataset.filter === "优化器");
|
||
optimizer?.click();
|
||
return {
|
||
hasOptimizerFilter: Boolean(optimizer),
|
||
total: document.querySelectorAll("[data-paper]").length,
|
||
visible: [...document.querySelectorAll("[data-paper]")].filter((node) => !node.hidden).length,
|
||
};
|
||
})()`);
|
||
|
||
const report = { format, ledger, optimizer, stability, layout, mobile, home, papers, exceptions };
|
||
console.log(JSON.stringify(report, null, 2));
|
||
|
||
const numeric = (value) => Number.parseFloat(value.replaceAll(",", ""));
|
||
const failures = [];
|
||
if (format.initial.storage !== "2.000 B/value") failures.push("BF16 初始字节口径异常");
|
||
if (!["SUBNORMAL", "ROUNDED"].includes(format.tinyFp16.status)) failures.push("FP16 微小梯度未进入 subnormal/rounding 边界");
|
||
if (format.largeE4M3.status !== "OVERFLOW") failures.push("E4M3 大激活未触发 overflow");
|
||
if (numeric(format.shared.error) <= numeric(format.local.error) || !format.shared.note.includes("teaching scale")) {
|
||
failures.push("MXFP4 block outlier 没有压缩普通值格点");
|
||
}
|
||
if (ledger.bf16.rows !== 6 || ledger.v3.rows !== 6 || ledger.k3.rows !== 6) failures.push("混合精度状态栈数量异常");
|
||
if (numeric(ledger.v3.total) >= numeric(ledger.bf16.total) || numeric(ledger.k3.total) >= numeric(ledger.bf16.total)) {
|
||
failures.push("低精度预设没有降低教学状态字节");
|
||
}
|
||
if (!ledger.v3.risks.includes("1×128") || !ledger.k3.risks.includes("post-training")) failures.push("V3/K3 证据边界缺失");
|
||
if (optimizer.full.cells !== 8 || optimizer.perHead.cells !== 8) failures.push("更新矩阵没有完整渲染");
|
||
if (optimizer.perHead.unit.trim() !== "attention head" || !optimizer.perHead.label.includes("Per-Head")) {
|
||
failures.push("Per-Head Muon 逻辑单位异常");
|
||
}
|
||
if (
|
||
numeric(optimizer.perHead.imbalance) > 1.25
|
||
|| numeric(optimizer.perHead.imbalance) >= numeric(optimizer.full.imbalance) * 0.1
|
||
) failures.push("Per-Head Muon 没有显著降低两个 head 的更新失衡");
|
||
if (stability.v4.timeline !== 24 || stability.k2.timeline !== 24) failures.push("稳定性时间线数量异常");
|
||
if (!stability.v4.summary.includes("均低于 HIGH") || stability.v4.defenses.length !== 5) {
|
||
failures.push("DeepSeek-V4 防线预设没有压低四条教学风险");
|
||
}
|
||
if (stability.keyboard.selected !== "stability" || stability.keyboard.visible !== "stability") {
|
||
failures.push("实验页签键盘导航异常");
|
||
}
|
||
if (layout.articleSections !== 19 || layout.paperLinks !== 36 || layout.labTabs !== 4 || layout.views !== 4) {
|
||
failures.push("章节、论文或实验数量异常");
|
||
}
|
||
if (layout.navLinks !== 15 || mobile.mobileLinks !== 15 || home.navLinks !== 15) failures.push("全站导航未同步数值专题");
|
||
if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出");
|
||
if (layout.navGap < 0) failures.push(`桌面导航碰撞：${layout.navGap}px`);
|
||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||
if (home.releaseCards !== 10 || !home.firstRelease.includes("DPO 没有") || home.firstHref !== "/post-training/alignment/") {
|
||
failures.push("首页 Transformer 新章入口异常");
|
||
}
|
||
if (home.paperCount !== "280") failures.push(`首页论文总数异常：${home.paperCount}`);
|
||
if (!papers.hasOptimizerFilter || papers.total !== 280 || papers.visible < 8) failures.push("论文库优化器标签或论文总数异常");
|
||
if (exceptions.length) failures.push(`浏览器脚本异常：${exceptions.join("; ")}`);
|
||
|
||
socket.close();
|
||
if (failures.length) {
|
||
failures.forEach((failure) => console.error(`- ${failure}`));
|
||
process.exit(1);
|
||
}
|
||
console.log("数值精度、优化器与稳定性专题真实 Chrome 断言通过。");
|