219 lines
10 KiB
JavaScript
219 lines
10 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}${path}` });
|
|
for (let attempt = 0; attempt < 60; attempt += 1) {
|
|
await pause(100);
|
|
if (await evaluate("document.readyState === 'complete'")) return;
|
|
}
|
|
throw new Error(`${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("/foundations/language-models/");
|
|
await screenshot("/tmp/llm-atlas-language-history-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-history-tab]").length,
|
|
labPanels: document.querySelectorAll("[data-history-panel]").length,
|
|
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
|
mainObjective: document.querySelector(".objective-stack .main h3")?.textContent,
|
|
}))()`);
|
|
|
|
const probability = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-history-lab]");
|
|
const read = () => ({
|
|
probability: root.querySelector("[data-sequence-probability]").textContent,
|
|
nll: root.querySelector("[data-sequence-nll]").textContent,
|
|
ppl: root.querySelector("[data-sequence-ppl]").textContent,
|
|
zeroSteps: root.querySelectorAll(".sequence-readout .zero").length,
|
|
});
|
|
const initial = read();
|
|
const slider = root.querySelector("[data-smoothing]");
|
|
slider.value = "20";
|
|
slider.dispatchEvent(new Event("input", { bubbles: true }));
|
|
const smoothed = read();
|
|
root.querySelector("[data-ngram-order]").value = "1";
|
|
root.querySelector("[data-ngram-order]").dispatchEvent(new Event("change", { bubbles: true }));
|
|
const unigram = read();
|
|
return { initial, smoothed, unigram };
|
|
})()`);
|
|
|
|
const embedding = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-history-lab]");
|
|
root.querySelector('[data-history-tab="embedding"]').click();
|
|
root.querySelector('[data-word="dog"]').click();
|
|
return {
|
|
selected: root.querySelector("[data-selected-word]").textContent,
|
|
onehot: [...root.querySelectorAll("[data-onehot-vector] i")].map((node) => node.textContent).join(""),
|
|
activeMap: root.querySelector(".map-point.selected b").textContent,
|
|
visiblePanel: root.querySelector("[data-history-panel]:not([hidden])").dataset.historyPanel,
|
|
};
|
|
})()`);
|
|
|
|
const memory = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-history-lab]");
|
|
root.querySelector('[data-history-tab="memory"]').click();
|
|
const distance = root.querySelector("[data-memory-distance]");
|
|
const retention = root.querySelector("[data-memory-retention]");
|
|
distance.value = "50";
|
|
distance.dispatchEvent(new Event("input", { bubbles: true }));
|
|
retention.value = "0.99";
|
|
retention.dispatchEvent(new Event("change", { bubbles: true }));
|
|
return {
|
|
signal: root.querySelector("[data-memory-signal]").textContent,
|
|
distance: root.querySelector("[data-distance-label]").textContent,
|
|
rnn: root.querySelector("[data-rnn-value]").textContent,
|
|
lstm: root.querySelector("[data-lstm-value]").textContent,
|
|
};
|
|
})()`);
|
|
|
|
const seq2seq = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-history-lab]");
|
|
root.querySelector('[data-history-tab="seq2seq"]').click();
|
|
root.querySelector('[data-seq-mode="attention"]').click();
|
|
root.querySelector('[data-decoder-step="1"]').click();
|
|
const weights = [...root.querySelectorAll("[data-source-value]")].map((node) => node.textContent);
|
|
const firstTab = root.querySelector('[data-history-tab="probability"]');
|
|
firstTab.focus();
|
|
firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "End", bubbles: true }));
|
|
return {
|
|
token: root.querySelector("[data-decoder-token]").textContent,
|
|
weights,
|
|
note: root.querySelector("[data-seq-note]").textContent,
|
|
bridge: root.querySelector("[data-bridge-label]").textContent,
|
|
keyboardSelected: root.querySelector('[data-history-tab][aria-selected="true"]').dataset.historyTab,
|
|
keyboardVisible: root.querySelector("[data-history-panel]:not([hidden])").dataset.historyPanel,
|
|
};
|
|
})()`);
|
|
|
|
await evaluate(`document.querySelector("[data-history-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
|
|
await pause(180);
|
|
await screenshot("/tmp/llm-atlas-language-history-lab-desktop.png");
|
|
|
|
await command("Emulation.setDeviceMetricsOverride", {
|
|
width: 390,
|
|
height: 844,
|
|
deviceScaleFactor: 1,
|
|
mobile: true,
|
|
});
|
|
await navigate("/foundations/language-models/");
|
|
const mobile = await evaluate(`(() => {
|
|
const root = document.querySelector("[data-history-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"),
|
|
tabs: root.querySelectorAll("[data-history-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-language-history-mobile.png");
|
|
|
|
const report = { overview, probability, embedding, memory, seq2seq, mobile, exceptions };
|
|
console.log(JSON.stringify(report, null, 2));
|
|
|
|
const numeric = (value) => Number.parseFloat(value);
|
|
const failures = [];
|
|
if (overview.sections !== 21 || overview.tocLinks !== 21) failures.push("章节/目录数量异常");
|
|
if (overview.paperLinks !== 33) failures.push("正式论文链不是 33 个节点");
|
|
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
|
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
|
|
if (overview.mainObjective?.trim() !== "Next-token NLL") failures.push("当代目标主次标签异常");
|
|
if (probability.initial.ppl !== "∞" || probability.initial.zeroSteps !== 1) failures.push("零概率未击穿初始序列");
|
|
if (!Number.isFinite(numeric(probability.smoothed.ppl)) || numeric(probability.smoothed.probability) <= 0) failures.push("平滑没有救活未见序列");
|
|
if (probability.unigram.zeroSteps !== 0) failures.push("Unigram 不应出现零概率步骤");
|
|
if (embedding.selected.trim() !== "狗" || embedding.onehot !== "0100000" || embedding.activeMap.trim() !== "狗") failures.push("Embedding 选择状态不同步");
|
|
if (memory.distance.trim() !== "50 步" || numeric(memory.signal) < 60 || numeric(memory.signal) > 61) failures.push("记忆指数衰减计算异常");
|
|
if (seq2seq.token.trim() !== "猫" || seq2seq.weights[2] !== "72%" || !seq2seq.note.includes("cat")) failures.push("Attention 对齐状态异常");
|
|
if (seq2seq.bridge.trim() !== "Σ αᵢhᵢ") failures.push("Attention context 标签异常");
|
|
if (seq2seq.keyboardSelected !== "seq2seq" || seq2seq.keyboardVisible !== "seq2seq") failures.push("实验 tab 键盘导航异常");
|
|
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动导航异常");
|
|
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 language-model-history browser regression");
|
|
}
|
|
|
|
socket.close();
|