287 lines
12 KiB
JavaScript
287 lines
12 KiB
JavaScript
import { writeFileSync } from "node:fs";
|
|
|
|
const cdpPort = process.env.CDP_PORT ?? "9225";
|
|
const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4324";
|
|
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("/scaling/");
|
|
await screenshot("/tmp/llm-atlas-scaling-desktop.png");
|
|
|
|
const surface = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-scaling-lab]");
|
|
const initial = {
|
|
model: root.querySelector('[data-surface-metric="model"]').textContent,
|
|
data: root.querySelector('[data-surface-metric="data"]').textContent,
|
|
gap: root.querySelector('[data-surface-metric="gap"]').textContent,
|
|
path: root.querySelector("[data-surface-path]").getAttribute("d").length,
|
|
};
|
|
const tpp = root.querySelector('[data-surface-input="tpp"]');
|
|
tpp.value = "500";
|
|
tpp.dispatchEvent(new Event("input", { bubbles: true }));
|
|
return {
|
|
initial,
|
|
extreme: {
|
|
gap: root.querySelector('[data-surface-metric="gap"]').textContent,
|
|
reading: root.querySelector("[data-surface-reading]").textContent,
|
|
label: root.querySelector("[data-surface-current] text").textContent,
|
|
},
|
|
};
|
|
})()`);
|
|
|
|
const serve = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-scaling-lab]");
|
|
root.querySelector('[data-scaling-tab="serve"]').click();
|
|
root.querySelector('[data-serve-preset="lab"]').click();
|
|
const lab = {
|
|
train: root.querySelector('[data-serve-metric="train"]').textContent,
|
|
total: root.querySelector('[data-serve-metric="total"]').textContent,
|
|
share: root.querySelector('[data-serve-metric="share"]').textContent,
|
|
};
|
|
root.querySelector('[data-serve-preset="mass"]').click();
|
|
return {
|
|
lab,
|
|
mass: {
|
|
train: root.querySelector('[data-serve-metric="train"]').textContent,
|
|
total: root.querySelector('[data-serve-metric="total"]').textContent,
|
|
share: root.querySelector('[data-serve-metric="share"]').textContent,
|
|
reading: root.querySelector("[data-serve-reading]").textContent,
|
|
candidates: root.querySelectorAll(".candidate-row").length,
|
|
},
|
|
};
|
|
})()`);
|
|
|
|
const data = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-scaling-lab]");
|
|
root.querySelector('[data-scaling-tab="data"]').click();
|
|
root.querySelector('[data-data-preset="unique"]').click();
|
|
const unique = {
|
|
seen: root.querySelector('[data-data-metric="seen"]').textContent,
|
|
effective: root.querySelector('[data-data-metric="effective"]').textContent,
|
|
next: root.querySelector('[data-data-metric="next"]').textContent,
|
|
};
|
|
root.querySelector('[data-data-preset="twenty"]').click();
|
|
return {
|
|
unique,
|
|
twenty: {
|
|
seen: root.querySelector('[data-data-metric="seen"]').textContent,
|
|
effective: root.querySelector('[data-data-metric="effective"]').textContent,
|
|
next: root.querySelector('[data-data-metric="next"]').textContent,
|
|
reading: root.querySelector("[data-data-reading]").textContent,
|
|
bars: root.querySelectorAll(".epoch-bars > i").length,
|
|
more: root.querySelector(".epoch-more")?.textContent ?? "",
|
|
},
|
|
};
|
|
})()`);
|
|
|
|
const emergence = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-scaling-lab]");
|
|
root.querySelector('[data-scaling-tab="emergence"]').click();
|
|
const scale = root.querySelector('[data-emergence-input="scale"]');
|
|
const measure = () => ({
|
|
token: root.querySelector('[data-emergence-metric="token"]').textContent,
|
|
threshold: root.querySelector('[data-emergence-metric="threshold"]').textContent,
|
|
exact: root.querySelector('[data-emergence-metric="exact"]').textContent,
|
|
});
|
|
scale.value = "59";
|
|
scale.dispatchEvent(new Event("input", { bubbles: true }));
|
|
const below = measure();
|
|
scale.value = "60";
|
|
scale.dispatchEvent(new Event("input", { bubbles: true }));
|
|
const above = measure();
|
|
const firstTab = root.querySelector('[data-scaling-tab="surface"]');
|
|
firstTab.focus();
|
|
firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "End", bubbles: true }));
|
|
return {
|
|
below,
|
|
above,
|
|
keyboard: {
|
|
selected: root.querySelector('[data-scaling-tab][aria-selected="true"]').dataset.scalingTab,
|
|
visible: root.querySelector("[data-scaling-view]:not([hidden])").dataset.scalingView,
|
|
},
|
|
paths: [...root.querySelectorAll("[data-emergence-line]")].map((path) => path.getAttribute("d").length),
|
|
};
|
|
})()`);
|
|
|
|
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-scaling-tab]").length,
|
|
views: document.querySelectorAll("[data-scaling-view]").length,
|
|
};
|
|
})()`);
|
|
|
|
await evaluate(`(() => {
|
|
document.documentElement.style.scrollBehavior = "auto";
|
|
document.querySelector("[data-scaling-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
|
})()`);
|
|
await pause(150);
|
|
await screenshot("/tmp/llm-atlas-scaling-lab-desktop.png");
|
|
|
|
await command("Emulation.setDeviceMetricsOverride", {
|
|
width: 390,
|
|
height: 844,
|
|
deviceScaleFactor: 1,
|
|
mobile: true,
|
|
});
|
|
await navigate("/scaling/");
|
|
await evaluate(`document.querySelector("[data-scaling-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
|
|
await pause(100);
|
|
await screenshot("/tmp/llm-atlas-scaling-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,
|
|
selectedTab: document.querySelector('[data-scaling-tab][aria-selected="true"]').dataset.scalingTab,
|
|
};
|
|
})()`);
|
|
|
|
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 evaluate(`document.querySelector("#new-chapters").scrollIntoView({ block: "start", behavior: "instant" })`);
|
|
await pause(100);
|
|
await screenshot("/tmp/llm-atlas-home-scaling-release.png");
|
|
|
|
const report = { surface, serve, data, emergence, layout, mobile, home, exceptions };
|
|
console.log(JSON.stringify(report, null, 2));
|
|
|
|
const numeric = (value) => Number.parseFloat(value);
|
|
const modelSize = (value) => Number.parseFloat(value);
|
|
const scaledCount = (value) => {
|
|
const number = Number.parseFloat(value);
|
|
if (value.includes("T")) return number * 1000;
|
|
if (value.includes("M")) return number / 1000;
|
|
return number;
|
|
};
|
|
const failures = [];
|
|
if (!surface.initial.model || !surface.initial.data || surface.initial.path < 1000) failures.push("IsoFLOP 曲线或最优点未渲染");
|
|
if (numeric(surface.extreme.gap) <= numeric(surface.initial.gap) || !surface.extreme.reading.includes("模型偏小")) {
|
|
failures.push("极端 TPP 没有产生预期的 compute-allocation loss gap");
|
|
}
|
|
if (serve.mass.candidates !== 8) failures.push("训练—部署候选模型数量异常");
|
|
if (modelSize(serve.mass.total) >= modelSize(serve.mass.train) || !serve.mass.reading.includes("更小模型")) {
|
|
failures.push("海量调用没有把生命周期最优点推向更小模型");
|
|
}
|
|
if (data.unique.seen !== data.unique.effective) failures.push("单遍数据的 seen 与 effective 不相等");
|
|
if (scaledCount(data.twenty.effective) >= scaledCount(data.twenty.seen) || numeric(data.twenty.next) >= 20) {
|
|
failures.push("数据枯竭预设没有体现复用边际衰减");
|
|
}
|
|
if (data.twenty.bars !== 16 || !data.twenty.more.includes("+4")) failures.push("20 epoch 可视化截断异常");
|
|
if (!emergence.below.threshold.includes("FAIL") || !emergence.above.threshold.includes("PASS")) {
|
|
failures.push("连续能力跨过二值评分线时没有出现离散阶跃");
|
|
}
|
|
if (Math.abs(numeric(emergence.above.token) - numeric(emergence.below.token)) > 2) {
|
|
failures.push("相邻规模的底层连续能力变化异常过大");
|
|
}
|
|
if (emergence.keyboard.selected !== "emergence" || emergence.keyboard.visible !== "emergence") {
|
|
failures.push("实验页签键盘导航异常");
|
|
}
|
|
if (emergence.paths.some((length) => length < 500)) failures.push("涌现多指标曲线未完整渲染");
|
|
if (layout.articleSections !== 16 || layout.paperLinks !== 29 || layout.labTabs !== 4 || layout.views !== 4) {
|
|
failures.push("章节、论文或实验数量异常");
|
|
}
|
|
if (layout.navLinks !== 13 || mobile.mobileLinks !== 13 || home.navLinks !== 13) failures.push("全站导航未同步 Scaling");
|
|
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:${layout.navGap}px`);
|
|
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
|
if (home.releaseCards !== 6 || !home.firstRelease.includes("一万亿 Token") || home.firstHref !== "/pretraining/data/") {
|
|
failures.push("首页数据工程新章入口异常");
|
|
}
|
|
if (home.paperCount !== "202") failures.push(`首页论文总数异常:${home.paperCount}`);
|
|
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);
|
|
}
|