wuyang
304 lines
16 KiB
JavaScript
304 lines
16 KiB
JavaScript
import { writeFileSync } from "node:fs";
|
||
|
||
const cdpPort = process.env.CDP_PORT ?? "9227";
|
||
const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4327";
|
||
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("/deepseek/");
|
||
await screenshot("/tmp/llm-atlas-deepseek-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,
|
||
ledgers: document.querySelectorAll(".ledger-card").length,
|
||
waves: document.querySelectorAll(".wave-grid > article").length,
|
||
paperLinks: document.querySelectorAll("[data-deepseek-paper-chain] a").length,
|
||
labTabs: document.querySelectorAll("[data-ds-tab]").length,
|
||
labPanels: document.querySelectorAll("[data-ds-panel]").length,
|
||
branches: document.querySelectorAll(".branch-grid > a").length,
|
||
followups: document.querySelectorAll(".lineage-row.followup").length,
|
||
navLinks: document.querySelectorAll(".top-nav a").length,
|
||
activeNav: document.querySelector('.top-nav a[aria-current="page"]')?.textContent.trim(),
|
||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||
}))()`);
|
||
|
||
const capacity = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
total: root.querySelector("[data-total-capacity]").textContent.trim(),
|
||
active: root.querySelector("[data-active-compute]").textContent.trim(),
|
||
combinations: root.querySelector("[data-combinations]").textContent.trim(),
|
||
communication: root.querySelector("[data-communication]").textContent.trim(),
|
||
name: root.querySelector("[data-capacity-name]").textContent.trim(),
|
||
explain: root.querySelector("[data-capacity-explain]").textContent.trim(),
|
||
});
|
||
const initial = read();
|
||
root.querySelector('[data-capacity-preset="dense"]').click();
|
||
const dense = read();
|
||
root.querySelector('[data-capacity-preset="deepseekmoe"]').click();
|
||
const fine = read();
|
||
root.querySelector('[data-capacity-preset="v3"]').click();
|
||
const v3 = read();
|
||
return { initial, dense, fine, v3 };
|
||
})()`);
|
||
|
||
const cache = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="cache"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
mha: root.querySelector("[data-mha-elements]").textContent.trim(),
|
||
gqa: root.querySelector("[data-gqa-elements]").textContent.trim(),
|
||
mla: root.querySelector("[data-mla-elements]").textContent.trim(),
|
||
rope: root.querySelector("[data-rope-cache]").textContent.trim(),
|
||
selected: root.querySelector("[data-selected-cache]").textContent.trim(),
|
||
baseline: root.querySelector("[data-mha-cache]").textContent.trim(),
|
||
reduction: root.querySelector("[data-cache-reduction]").textContent.trim(),
|
||
boundary: root.querySelector("[data-cache-boundary]").textContent.trim(),
|
||
});
|
||
const initial = read();
|
||
const rope = root.querySelector("[data-rope-dim]");
|
||
rope.value = "0";
|
||
rope.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const noRope = read();
|
||
const context = root.querySelector("[data-context-length]");
|
||
context.value = "1048576";
|
||
context.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const million = read();
|
||
return { initial, noRope, million };
|
||
})()`);
|
||
|
||
const codesign = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="codesign"]').click();
|
||
const readSchedule = () => ({
|
||
bubble: root.querySelector("[data-bubble]").textContent.trim(),
|
||
exposed: root.querySelector("[data-exposed-comm]").textContent.trim(),
|
||
});
|
||
const oneWay = readSchedule();
|
||
root.querySelector('[data-schedule="dual"]').click();
|
||
const dual = readSchedule();
|
||
root.querySelector('[data-precision="naive"]').click();
|
||
const naive = {
|
||
risk: root.querySelector("[data-risk-label]").textContent.trim(),
|
||
accum: root.querySelector("[data-accum-dtype]").textContent.trim(),
|
||
explain: root.querySelector("[data-precision-explain]").textContent.trim(),
|
||
};
|
||
root.querySelector('[data-precision="mixed"]').click();
|
||
const mixed = {
|
||
risk: root.querySelector("[data-risk-label]").textContent.trim(),
|
||
accum: root.querySelector("[data-accum-dtype]").textContent.trim(),
|
||
sensitive: root.querySelector("[data-sensitive-dtype]").textContent.trim(),
|
||
};
|
||
root.querySelector('[data-mtp-role="off"]').click();
|
||
const off = root.querySelector("[data-mtp-supervision]").textContent.trim();
|
||
root.querySelector('[data-mtp-role="draft"]').click();
|
||
const draft = {
|
||
supervision: root.querySelector("[data-mtp-supervision]").textContent.trim(),
|
||
cost: root.querySelector("[data-mtp-main-cost]").textContent.trim(),
|
||
explain: root.querySelector("[data-mtp-explain]").textContent.trim(),
|
||
};
|
||
return { panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel, oneWay, dual, naive, mixed, off, draft };
|
||
})()`);
|
||
|
||
const rl = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="rl"]').click();
|
||
const read = () => ({
|
||
signal: root.querySelector("[data-signal-state]").textContent.trim(),
|
||
mean: root.querySelector("[data-reward-mean]").textContent.trim(),
|
||
std: root.querySelector("[data-reward-std]").textContent.trim(),
|
||
effective: root.querySelector("[data-effective]").textContent.trim(),
|
||
provenance: root.querySelector("[data-provenance]").textContent.trim(),
|
||
algorithm: root.querySelector("[data-algorithm-name]").textContent.trim(),
|
||
boundary: root.querySelector("[data-rl-boundary]").textContent.trim(),
|
||
weights: [...root.querySelectorAll("[data-advantage-rows] > div span:last-child")].map((node) => node.textContent.trim()),
|
||
});
|
||
const initial = read();
|
||
root.querySelector('[data-reward-preset="same"]').click();
|
||
const same = read();
|
||
root.querySelector('[data-reward-preset="longwrong"]').click();
|
||
root.querySelector('[data-rl-algorithm="dapo"]').click();
|
||
const dapo = read();
|
||
root.querySelector('[data-rl-algorithm="dr"]').click();
|
||
const dr = read();
|
||
root.querySelector('[data-r1-mode="r1"]').click();
|
||
const r1 = root.querySelector("[data-r1-mode-explain]").textContent.trim();
|
||
root.querySelector('[data-r1-mode="distill"]').click();
|
||
const distill = root.querySelector("[data-r1-mode-explain]").textContent.trim();
|
||
const first = root.querySelector('[data-ds-tab="capacity"]');
|
||
first.focus();
|
||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||
return {
|
||
initial, same, dapo, dr, r1, distill,
|
||
keyboardSelected: root.querySelector('[data-ds-tab][aria-selected="true"]').dataset.dsTab,
|
||
keyboardVisible: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
};
|
||
})()`);
|
||
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-deepseek-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-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() === "DeepSeek");
|
||
button?.click();
|
||
return {
|
||
total: document.querySelectorAll("[data-paper]").length,
|
||
visible: document.querySelectorAll("[data-paper]:not([hidden])").length,
|
||
hasFilter: Boolean(button),
|
||
hasCoder: document.body.textContent.includes("DeepSeek-Coder-V2"),
|
||
hasEngram: document.body.textContent.includes("Conditional Memory via Scalable Lookup"),
|
||
};
|
||
})()`);
|
||
|
||
await command("Emulation.setDeviceMetricsOverride", {
|
||
width: 390,
|
||
height: 844,
|
||
deviceScaleFactor: 1,
|
||
mobile: true,
|
||
});
|
||
await navigate("/deepseek/");
|
||
const mobile = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-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-ds-tab]").length,
|
||
offenders: [...document.querySelectorAll("body *")]
|
||
.filter((node) => !node.closest(".paper-chain, .advantage-table, .precision-table, .mapping-table, [data-deepseek-lab]"))
|
||
.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 evaluate(`(() => {
|
||
document.querySelector("#menu-toggle")?.click();
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-mobile.png");
|
||
|
||
const report = { overview, capacity, cache, codesign, rl, home, papers, mobile, exceptions };
|
||
console.log(JSON.stringify(report, null, 2));
|
||
|
||
const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
|
||
const failures = [];
|
||
if (!overview.title.includes("为什么转向")) failures.push("专题标题异常");
|
||
if (overview.sections !== 25 || overview.tocLinks !== 25) failures.push("二十四个编号专题加阅读链的目录结构异常");
|
||
if (overview.ledgers !== 24 || overview.waves !== 10) failures.push("二十四张问题账或十次转向结构异常");
|
||
if (overview.paperLinks !== 60 || overview.branches !== 5 || overview.followups !== 1) failures.push("论文链、旁支或公开后续标记异常");
|
||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20 || overview.activeNav !== "DeepSeek") failures.push("全站导航未同步 DeepSeek");
|
||
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在文档级横向溢出");
|
||
if (capacity.initial.panel !== "capacity" || capacity.initial.total !== "32.1× FFN" || capacity.initial.active !== "1.13× FFN") failures.push("V3 稀疏容量初始账异常");
|
||
if (!capacity.dense.name.includes("DENSE") || capacity.dense.communication !== "NONE" || numeric(capacity.dense.total) !== numeric(capacity.dense.active)) failures.push("Dense 容量预设异常");
|
||
if (!capacity.fine.name.includes("FINE-GRAINED") || !capacity.fine.explain.includes("shared")) failures.push("DeepSeekMoE 预设异常");
|
||
if (!capacity.v3.combinations.includes("10^") || capacity.v3.communication !== "HIGH") failures.push("V3 路由组合或通信方向异常");
|
||
if (cache.initial.panel !== "cache" || numeric(cache.initial.mha) !== 32768 || numeric(cache.initial.gqa) !== 2048 || numeric(cache.initial.mla) !== 576 || numeric(cache.initial.rope) !== 64) failures.push("MLA 精确元素账异常");
|
||
if (numeric(cache.initial.reduction) !== 98.2 || numeric(cache.noRope.mla) !== 512 || numeric(cache.noRope.reduction) <= numeric(cache.initial.reduction)) failures.push("RoPE cache 或 MLA reduction 异常");
|
||
if (!cache.million.selected.includes("GiB") || !cache.million.boundary.includes("1,048,576")) failures.push("百万 Token 缓存账异常");
|
||
if (numeric(codesign.dual.bubble) >= numeric(codesign.oneWay.bubble) || numeric(codesign.dual.exposed) >= numeric(codesign.oneWay.exposed)) failures.push("Dual-ended toy 没有减少空泡或暴露通信");
|
||
if (codesign.naive.risk !== "CRITICAL" || codesign.naive.accum !== "FP8" || codesign.mixed.risk !== "MANAGED" || !codesign.mixed.accum.includes("FP32")) failures.push("FP8 角色合同异常");
|
||
if (!codesign.off.includes("1 token") || !codesign.draft.supervision.includes("draft") || !codesign.draft.explain.includes("验收率")) failures.push("MTP 生命周期异常");
|
||
if (rl.initial.signal !== "GROUP-RELATIVE SIGNAL" || rl.same.signal !== "ZERO GROUP SIGNAL" || !rl.same.boundary.includes("优势为零")) failures.push("GRPO 零方差信号异常");
|
||
if (!rl.dapo.provenance.includes("2503.14476") || !rl.dapo.algorithm.includes("FOLLOW-UP") || !rl.dr.provenance.includes("2503.20783")) failures.push("DAPO / Dr.GRPO 来源边界异常");
|
||
if (!rl.r1.includes("cold start") || !rl.distill.includes("没有重演")) failures.push("R1 / distill 身份切换异常");
|
||
if (rl.keyboardSelected !== "cache" || rl.keyboardVisible !== "cache") failures.push("实验键盘 tab 导航异常");
|
||
if (home.releaseCards !== 16 || !home.firstRelease.includes("从 Dense 到百万上下文") || home.firstHref !== "/deepseek/" || home.paperCount !== "486") failures.push("首页 DeepSeek 首发入口或论文数异常");
|
||
if (papers.total !== 486 || !papers.hasFilter || papers.visible < 20 || !papers.hasCoder || !papers.hasEngram) failures.push("论文库 DeepSeek 聚光异常");
|
||
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 DeepSeek browser regression");
|
||
}
|
||
|
||
socket.close();
|