wuyang
242 lines
12 KiB
JavaScript
242 lines
12 KiB
JavaScript
import { writeFileSync } from "node:fs";
|
||
|
||
const cdpPort = process.env.CDP_PORT ?? "9224";
|
||
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, 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("/post-training/alignment/");
|
||
await screenshot("/tmp/llm-atlas-alignment-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-alignment-tab]").length,
|
||
labPanels: document.querySelectorAll("[data-alignment-panel]").length,
|
||
navLinks: document.querySelectorAll(".top-nav a").length,
|
||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||
}))()`);
|
||
|
||
const sft = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-alignment-lab]");
|
||
const read = () => ({
|
||
active: root.querySelector("[data-sft-active]").textContent.trim(),
|
||
nll: root.querySelector("[data-sft-nll]").textContent.trim(),
|
||
reading: root.querySelector("[data-sft-reading]").textContent.trim(),
|
||
lossStates: [...root.querySelectorAll("[data-sft-loss]")].map((node) => node.textContent.trim()),
|
||
});
|
||
const initial = read();
|
||
root.querySelector('[data-sft-mask="all"]').click();
|
||
const quality = root.querySelector("[data-sft-quality]");
|
||
quality.value = "unsafe";
|
||
quality.dispatchEvent(new Event("change", { bubbles: true }));
|
||
return { initial, unsafeAll: read() };
|
||
})()`);
|
||
|
||
const preference = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-alignment-lab]");
|
||
root.querySelector('[data-alignment-tab="preference"]').click();
|
||
root.querySelector('[data-pref-preset="bothbad"]').click();
|
||
return {
|
||
rewardA: root.querySelector('[data-reward="a"]').textContent.trim(),
|
||
rewardB: root.querySelector('[data-reward="b"]').textContent.trim(),
|
||
probability: root.querySelector("[data-pref-probability]").textContent.trim(),
|
||
reading: root.querySelector("[data-pref-reading]").textContent.trim(),
|
||
visiblePanel: root.querySelector("[data-alignment-panel]:not([hidden])").dataset.alignmentPanel,
|
||
};
|
||
})()`);
|
||
|
||
const update = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-alignment-lab]");
|
||
root.querySelector('[data-alignment-tab="update"]').click();
|
||
root.querySelector('[data-update-method="dpo"]').click();
|
||
const stale = root.querySelector("[data-update-stale]");
|
||
stale.value = "85";
|
||
stale.dispatchEvent(new Event("input", { bubbles: true }));
|
||
return {
|
||
models: root.querySelector("[data-update-models]").textContent.trim(),
|
||
regime: root.querySelector("[data-update-regime]").textContent.trim(),
|
||
equation: root.querySelector("[data-update-equation]").textContent.trim(),
|
||
reading: root.querySelector("[data-update-reading]").textContent.trim(),
|
||
steps: [...root.querySelectorAll("[data-update-step]")].map((node) => node.textContent.trim()),
|
||
};
|
||
})()`);
|
||
|
||
const recipe = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-alignment-lab]");
|
||
root.querySelector('[data-alignment-tab="recipe"]').click();
|
||
root.querySelector('[data-recipe-id="k3"]').click();
|
||
const selected = {
|
||
family: root.querySelector("[data-recipe-family]").textContent.trim(),
|
||
regime: root.querySelector("[data-recipe-regime]").textContent.trim(),
|
||
constraints: root.querySelector("[data-recipe-constraints]").textContent.trim(),
|
||
path: [...root.querySelectorAll("[data-recipe-step]")].map((node) => node.textContent.trim()),
|
||
risk: root.querySelector("[data-recipe-risk]").textContent.trim(),
|
||
};
|
||
const firstTab = root.querySelector('[data-alignment-tab="sft"]');
|
||
firstTab.focus();
|
||
firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "End", bubbles: true }));
|
||
return {
|
||
...selected,
|
||
keyboardSelected: root.querySelector('[data-alignment-tab][aria-selected="true"]').dataset.alignmentTab,
|
||
keyboardVisible: root.querySelector("[data-alignment-panel]:not([hidden])").dataset.alignmentPanel,
|
||
};
|
||
})()`);
|
||
|
||
await evaluate(`document.querySelector("[data-alignment-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-alignment-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.includes("后训练"));
|
||
button?.click();
|
||
return {
|
||
total: document.querySelectorAll("[data-paper]").length,
|
||
alignmentVisible: document.querySelectorAll("[data-paper]:not([hidden])").length,
|
||
hasAlignmentFilter: Boolean(button),
|
||
};
|
||
})()`);
|
||
|
||
await command("Emulation.setDeviceMetricsOverride", {
|
||
width: 390,
|
||
height: 844,
|
||
deviceScaleFactor: 1,
|
||
mobile: true,
|
||
});
|
||
await navigate("/post-training/alignment/");
|
||
const mobile = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-alignment-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-alignment-tab]").length,
|
||
offenders: [...document.querySelectorAll("body *")]
|
||
.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-alignment-mobile.png");
|
||
|
||
const report = { overview, sft, preference, update, recipe, home, papers, mobile, exceptions };
|
||
console.log(JSON.stringify(report, null, 2));
|
||
|
||
const numeric = (value) => Number.parseFloat(value);
|
||
const failures = [];
|
||
if (!overview.title.includes("真正与人协作")) failures.push("章节标题异常");
|
||
if (overview.sections !== 22 || overview.tocLinks !== 22) failures.push("章节/目录数量异常");
|
||
if (overview.paperLinks !== 44) failures.push("正式论文链不是 44 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("全站导航未同步后训练专题");
|
||
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
|
||
if (sft.initial.active !== "6 / 10" || !sft.initial.lossStates.slice(0, 4).every((value) => value === "MASKED")) failures.push("SFT response-only mask 异常");
|
||
if (sft.unsafeAll.active !== "10 / 10" || numeric(sft.unsafeAll.nll) <= numeric(sft.initial.nll) || !sft.unsafeAll.reading.includes("错误")) failures.push("SFT 全序列/坏示范交互异常");
|
||
if (numeric(preference.rewardA) >= 0 || numeric(preference.rewardB) >= 0 || !preference.reading.includes("两坏") || preference.visiblePanel !== "preference") failures.push("both-bad 偏好实验异常");
|
||
if (update.models !== "2" || update.regime !== "OFFLINE" || !update.equation.includes("Δlog") || !update.reading.includes("旧候选")) failures.push("DPO / 陈旧分布实验异常");
|
||
if (!update.steps[0].includes("Fixed preference")) failures.push("DPO 更新流程没有切换");
|
||
if (!recipe.family.includes("Multi-effort") || !recipe.regime.includes("9 RL experts") || !recipe.constraints.includes("verbosity")) failures.push("K3 配方合同异常");
|
||
if (!recipe.path.some((step) => step.includes("3 domains × 3 efforts")) || !recipe.path.some((step) => step.includes("MOPD"))) failures.push("K3 配方路径异常");
|
||
if (recipe.keyboardSelected !== "recipe" || recipe.keyboardVisible !== "recipe") failures.push("实验 tab 键盘导航异常");
|
||
if (home.releaseCards !== 12 || !home.firstRelease.includes("原生多模态") || home.firstHref !== "/multimodal/") failures.push("首页 Alignment 首发入口异常");
|
||
if (home.paperCount !== "355" || papers.total !== 355 || !papers.hasAlignmentFilter || papers.alignmentVisible < 35) failures.push("论文库后训练标签或论文总数异常");
|
||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||
if (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 alignment browser regression");
|
||
}
|
||
|
||
socket.close();
|