feat: publish representation and depth chapter
This commit is contained in:
@@ -217,7 +217,7 @@ if (!overview.title.includes("可靠行动")) failures.push("章节标题异常"
|
||||
if (overview.sections !== 28 || overview.tocLinks !== 28) failures.push("章节/目录数量异常");
|
||||
if (overview.paperLinks !== 52) failures.push("正式论文链不是 52 个节点");
|
||||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||||
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
|
||||
if (loop.initial.finalState !== "UNVERIFIED" || loop.directSchema.finalState !== "FAILED") failures.push("控制循环终局状态异常");
|
||||
if (!loop.directSchema.observation.includes("ERROR schema") || loop.directSchema.recovery !== "FRAGILE") failures.push("Direct/schema 故障传播异常");
|
||||
@@ -228,8 +228,8 @@ if (numeric(reliability.initial.passAt) <= numeric(reliability.k2.passAt) || num
|
||||
if (reliability.nonIdempotent.sideRisk === "LOW") failures.push("非幂等写操作风险没有提升");
|
||||
if (numeric(rl.wait.utilization) >= numeric(rl.full.utilization) || numeric(rl.wait.lostWork) <= numeric(rl.full.lostWork)) failures.push("wait-all 长尾/重算方向异常");
|
||||
if (!rl.wait.takeaway.includes("wait-all") || rl.keyboardSelected !== "rl" || rl.keyboardVisible !== "rl") failures.push("长程 RL 解释或键盘导航异常");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || papers.total !== 450 || !papers.hasAgentFilter || papers.agentVisible < 52) failures.push("论文库 Agent 标签或论文总数异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || papers.total !== 480 || !papers.hasAgentFilter || papers.agentVisible < 52) failures.push("论文库 Agent 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(" | ")}`);
|
||||
|
||||
|
||||
@@ -216,7 +216,7 @@ if (!overview.title.includes("真正与人协作")) failures.push("章节标题
|
||||
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 !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
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");
|
||||
@@ -226,8 +226,8 @@ if (!update.steps[0].includes("Fixed preference")) failures.push("DPO 更新流
|
||||
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 !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || papers.total !== 450 || !papers.hasAlignmentFilter || papers.alignmentVisible < 35) failures.push("论文库后训练标签或论文总数异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || papers.total !== 480 || !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(" | ")}`);
|
||||
|
||||
|
||||
@@ -230,15 +230,15 @@ if (transform.keyboard.selected !== "transform" || transform.keyboard.visible !=
|
||||
if (layout.articleSections !== 18 || layout.paperLinks !== 31 || layout.labTabs !== 4 || layout.views !== 4) {
|
||||
failures.push("章节、论文或实验数量异常");
|
||||
}
|
||||
if (layout.navLinks !== 19 || mobile.mobileLinks !== 19 || home.navLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
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:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") {
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "450") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (!papers.hasDataFilter || papers.total !== 450 || papers.visible < 25) failures.push("论文库数据标签或论文总数异常");
|
||||
if (home.paperCount !== "480") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (!papers.hasDataFilter || papers.total !== 480 || papers.visible < 25) failures.push("论文库数据标签或论文总数异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -263,7 +263,7 @@ if (overview.sections !== 33 || overview.tocLinks !== 33) failures.push("章节
|
||||
if (overview.paperLinks !== 80) failures.push("正式论文链不是 80 个节点");
|
||||
if (overview.ledgers !== 22) failures.push("二十二张评测账结构异常");
|
||||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||||
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19 || overview.activeNav !== "评测安全") failures.push("全站导航未同步评测专题");
|
||||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20 || overview.activeNav !== "评测安全") failures.push("全站导航未同步评测专题");
|
||||
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 (metric.initial.visible !== "metric" || numeric(metric.initial.one) !== 80 || numeric(metric.initial.atLeast) !== 80 || numeric(metric.initial.all) !== 80) failures.push("指标实验初始值异常");
|
||||
if (numeric(metric.search.atLeast) <= 99 || numeric(metric.search.all) >= 30 || !metric.search.explain.includes("搜索")) failures.push("pass@k / pass^k 方向没有分开");
|
||||
@@ -277,8 +277,8 @@ if (numeric(system.initial.success) <= numeric(system.initial.model) || numeric(
|
||||
if (numeric(system.cheap.success) >= numeric(system.initial.success) || numeric(system.cheap.cost) !== 4) failures.push("低预算没有降低成功率 / 成本");
|
||||
if (numeric(system.locked.unsafe) !== 0 || numeric(system.locked.overrefusal) <= numeric(system.initial.overrefusal)) failures.push("安全壳没有展现危险服从 / 过拒权衡");
|
||||
if (system.keyboardSelected !== "judge" || system.keyboardVisible !== "judge") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || home.topicCount !== "17" || papers.total !== 450 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || home.topicCount !== "17" || papers.total !== 480 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常");
|
||||
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(" | ")}`);
|
||||
|
||||
@@ -251,7 +251,7 @@ if (overview.sections !== 31 || overview.tocLinks !== 31) failures.push("章节/
|
||||
if (overview.paperLinks !== 62) failures.push("正式论文链不是 62 个节点");
|
||||
if (overview.ledgers !== 18) failures.push("十八本服务账结构异常");
|
||||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||||
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
|
||||
if (!memory.initial.weight.includes("32.6") || !memory.initial.perToken.includes("128") || memory.initial.visible !== "memory") failures.push("GQA 默认显存账异常");
|
||||
if (!memory.exploded.status.includes("OOM") || !memory.exploded.fit.includes("over")) failures.push("极端 MHA 配置没有触发 OOM");
|
||||
@@ -264,8 +264,8 @@ if (!fleet.k3.avoided.includes("320K") || fleet.k3.shortSlo !== "PROTECTED") fai
|
||||
if (!fleet.failed.state.includes("SECONDARY RE-PREFILL") || !fleet.failed.recompute.includes("FAILED PRIMARY")) failures.push("缓存故障没有触发原子失效后的重算");
|
||||
if (fleet.bursty.shortSlo !== "VIOLATED") failures.push("平均并发阈值没有暴露长请求突发");
|
||||
if (fleet.keyboardSelected !== "phase" || fleet.keyboardVisible !== "phase") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || papers.total !== 450 || !papers.hasFilter || papers.visible !== 45) failures.push("论文库推理服务标签或总数异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || papers.total !== 480 || !papers.hasFilter || papers.visible !== 45) failures.push("论文库推理服务标签或总数异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (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(" | ")}`);
|
||||
|
||||
@@ -177,7 +177,7 @@ if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentO
|
||||
}
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible) failures.push("移动端菜单按钮未显示");
|
||||
if (home.releaseCards !== 14) failures.push(`首页新章卡数量异常:${home.releaseCards}`);
|
||||
if (home.releaseCards !== 15) failures.push(`首页新章卡数量异常:${home.releaseCards}`);
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -234,7 +234,7 @@ if (!overview.title.includes("第一类输入")) failures.push("章节标题异
|
||||
if (overview.sections !== 30 || overview.tocLinks !== 30) failures.push("章节/目录数量异常");
|
||||
if (overview.paperLinks !== 55) failures.push("正式论文链不是 55 个节点");
|
||||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||||
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在横向溢出");
|
||||
if (numeric(tokens.initial.patches) !== 5476 || numeric(tokens.initial.visual) !== 1369 || tokens.initial.visiblePanel !== "tokens") failures.push("视觉 Token 初始计算异常");
|
||||
if (!tokens.overloaded.status.includes("超预算") || numeric(tokens.overloaded.share) <= 100) failures.push("超大视频没有触发上下文超预算");
|
||||
@@ -246,8 +246,8 @@ if (ocr.unreported.status !== "OUT OF EVIDENCE" || ocr.unreported.accuracy !== "
|
||||
if (loop.toolsStart.state !== "OPEN" || loop.toolsEnd.state !== "VERIFIED" || loop.toolsEnd.evidence !== "97%" || loop.toolsEnd.tools !== "3") failures.push("vision-in-the-loop 终局异常");
|
||||
if (loop.cotEnd.state !== "FAILED" || !loop.cotEnd.takeaway.includes("不能凭空增加")) failures.push("文字 CoT 与新观察没有分开");
|
||||
if (loop.keyboardSelected !== "connector" || loop.keyboardVisible !== "connector") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || papers.total !== 450 || !papers.hasFilter || papers.multimodalVisible < 59) failures.push("论文库多模态标签或总数异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || papers.total !== 480 || !papers.hasFilter || papers.multimodalVisible < 59) failures.push("论文库多模态标签或总数异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (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(" | ")}`);
|
||||
|
||||
@@ -273,15 +273,15 @@ if (stability.keyboard.selected !== "stability" || stability.keyboard.visible !=
|
||||
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 !== 19 || mobile.mobileLinks !== 19 || home.navLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
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:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") {
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "450") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (!papers.hasOptimizerFilter || papers.total !== 450 || papers.visible < 8) failures.push("论文库优化器标签或论文总数异常");
|
||||
if (home.paperCount !== "480") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (!papers.hasOptimizerFilter || papers.total !== 480 || papers.visible < 8) failures.push("论文库优化器标签或论文总数异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -289,7 +289,7 @@ if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentO
|
||||
}
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单")) failures.push("首页评测新章入口异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state")) failures.push("首页评测新章入口异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -0,0 +1,304 @@
|
||||
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("/architecture/representation/");
|
||||
await screenshot("/tmp/llm-atlas-representation-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,
|
||||
ledgers: document.querySelectorAll(".rep-ledgers > article").length,
|
||||
labTabs: document.querySelectorAll("[data-rep-tab]").length,
|
||||
labPanels: document.querySelectorAll("[data-rep-panel]").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 token = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-representation-lab]");
|
||||
const read = () => ({
|
||||
visible: root.querySelector("[data-rep-panel]:not([hidden])").dataset.repPanel,
|
||||
steps: root.querySelector("[data-token-steps]").textContent.trim(),
|
||||
embedding: root.querySelector("[data-embedding-params]").textContent.trim(),
|
||||
io: root.querySelector("[data-io-params]").textContent.trim(),
|
||||
memory: root.querySelector("[data-embedding-memory]").textContent.trim(),
|
||||
vector: root.querySelector("[data-context-vector]").textContent.trim(),
|
||||
shift: root.querySelector("[data-vector-shift]").textContent.trim(),
|
||||
explain: root.querySelector("[data-vector-explain]").textContent.trim(),
|
||||
boundary: root.querySelector("[data-token-boundary]").textContent.trim(),
|
||||
});
|
||||
const initial = read();
|
||||
const unit = root.querySelector("[data-token-unit]");
|
||||
unit.value = "byte";
|
||||
unit.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
const tying = root.querySelector("[data-weight-tying]");
|
||||
tying.checked = false;
|
||||
tying.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
const context = root.querySelector("[data-context]");
|
||||
context.value = "finance";
|
||||
context.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
const changed = read();
|
||||
return { initial, changed };
|
||||
})()`);
|
||||
|
||||
const position = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-representation-lab]");
|
||||
root.querySelector('[data-rep-tab="position"]').click();
|
||||
const read = () => ({
|
||||
visible: root.querySelector("[data-rep-panel]:not([hidden])").dataset.repPanel,
|
||||
regime: root.querySelector("[data-position-regime]").textContent.trim(),
|
||||
term: root.querySelector("[data-explicit-term]").textContent.trim(),
|
||||
mode: root.querySelector("[data-position-mode]").textContent.trim(),
|
||||
equation: root.querySelector("[data-position-equation]").textContent.trim(),
|
||||
score: root.querySelector("[data-position-score]").textContent.trim(),
|
||||
explain: root.querySelector("[data-position-explain]").textContent.trim(),
|
||||
boundary: root.querySelector("[data-position-boundary]").textContent.trim(),
|
||||
});
|
||||
const initial = read();
|
||||
const key = root.querySelector("[data-key-position]");
|
||||
const train = root.querySelector("[data-train-window]");
|
||||
train.value = "64";
|
||||
train.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
key.value = "192";
|
||||
key.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
const ropeOutside = read();
|
||||
root.querySelector('[data-position-scheme="alibi"]').click();
|
||||
const alibi = read();
|
||||
root.querySelector('[data-position-scheme="nope"]').click();
|
||||
const nope = read();
|
||||
return { initial, ropeOutside, alibi, nope };
|
||||
})()`);
|
||||
|
||||
const norm = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-representation-lab]");
|
||||
root.querySelector('[data-rep-tab="norm"]').click();
|
||||
const read = () => ({
|
||||
visible: root.querySelector("[data-rep-panel]:not([hidden])").dataset.repPanel,
|
||||
rms: root.querySelector("[data-final-rms]").textContent.trim(),
|
||||
identity: root.querySelector("[data-identity-gain]").textContent.trim(),
|
||||
peak: root.querySelector("[data-softmax-peak]").textContent.trim(),
|
||||
target: root.querySelector("[data-norm-target]").textContent.trim(),
|
||||
equation: root.querySelector("[data-norm-equation]").textContent.trim(),
|
||||
boundary: root.querySelector("[data-norm-boundary]").textContent.trim(),
|
||||
});
|
||||
const initial = read();
|
||||
const depth = root.querySelector("[data-depth]");
|
||||
const logits = root.querySelector("[data-logit-scale]");
|
||||
depth.value = "192";
|
||||
depth.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
logits.value = "160";
|
||||
logits.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
const unbounded = read();
|
||||
root.querySelector('[data-norm-topology="qk"]').click();
|
||||
const qk = read();
|
||||
root.querySelector('[data-norm-topology="post"]').click();
|
||||
const post = read();
|
||||
return { initial, unbounded, qk, post };
|
||||
})()`);
|
||||
|
||||
const residual = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-representation-lab]");
|
||||
root.querySelector('[data-rep-tab="residual"]').click();
|
||||
const read = () => ({
|
||||
visible: root.querySelector("[data-rep-panel]:not([hidden])").dataset.repPanel,
|
||||
route: root.querySelector("[data-route-name]").textContent.trim(),
|
||||
states: root.querySelector("[data-live-states]").textContent.trim(),
|
||||
choice: root.querySelector("[data-depth-choice]").textContent.trim(),
|
||||
routeExplain: root.querySelector("[data-route-explain]").textContent.trim(),
|
||||
activation: root.querySelector("[data-activation-name]").textContent.trim(),
|
||||
max: root.querySelector("[data-activation-max]").textContent.trim(),
|
||||
bound: root.querySelector("[data-activation-bound]").textContent.trim(),
|
||||
activationExplain: root.querySelector("[data-activation-explain]").textContent.trim(),
|
||||
});
|
||||
const initial = read();
|
||||
root.querySelector('[data-route="mhc"]').click();
|
||||
const mhc = read();
|
||||
root.querySelector('[data-route="attnres"]').click();
|
||||
const attnres = read();
|
||||
root.querySelector('[data-activation="clamp"]').click();
|
||||
const clamp = read();
|
||||
root.querySelector('[data-activation="situ"]').click();
|
||||
const situ = read();
|
||||
const firstTab = root.querySelector('[data-rep-tab="token"]');
|
||||
firstTab.focus();
|
||||
firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||||
return {
|
||||
initial,
|
||||
mhc,
|
||||
attnres,
|
||||
clamp,
|
||||
situ,
|
||||
keyboardSelected: root.querySelector('[data-rep-tab][aria-selected="true"]').dataset.repTab,
|
||||
keyboardVisible: root.querySelector("[data-rep-panel]:not([hidden])").dataset.repPanel,
|
||||
};
|
||||
})()`);
|
||||
|
||||
await evaluate(`(() => {
|
||||
document.querySelector("[data-representation-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||||
window.scrollBy(0, -82);
|
||||
})()`);
|
||||
await pause(180);
|
||||
await screenshot("/tmp/llm-atlas-representation-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(),
|
||||
topicCount: document.querySelector(".hero-stats div:nth-child(1) 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() === "表示");
|
||||
button?.click();
|
||||
return {
|
||||
total: document.querySelectorAll("[data-paper]").length,
|
||||
visible: document.querySelectorAll("[data-paper]:not([hidden])").length,
|
||||
hasFilter: Boolean(button),
|
||||
};
|
||||
})()`);
|
||||
|
||||
await command("Emulation.setDeviceMetricsOverride", {
|
||||
width: 390,
|
||||
height: 844,
|
||||
deviceScaleFactor: 1,
|
||||
mobile: true,
|
||||
});
|
||||
await navigate("/architecture/representation/");
|
||||
const mobile = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-representation-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-rep-tab]").length,
|
||||
offenders: [...document.querySelectorAll("body *")]
|
||||
.filter((node) => !node.closest(".paper-chain, .rep-ledgers, .position-table"))
|
||||
.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-representation-mobile.png");
|
||||
|
||||
const report = { overview, token, position, norm, residual, home, papers, mobile, exceptions };
|
||||
console.log(JSON.stringify(report, null, 2));
|
||||
|
||||
const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
|
||||
const failures = [];
|
||||
if (!overview.title.includes("表示") || !overview.title.includes("残差")) failures.push("章节标题异常");
|
||||
if (overview.sections !== 29 || overview.tocLinks !== 29) failures.push("章节 / 目录数量异常");
|
||||
if (overview.paperLinks !== 66) failures.push("正式论文链不是 66 个节点");
|
||||
if (overview.ledgers !== 20) failures.push("二十张问题账结构异常");
|
||||
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 !== "表示深度") failures.push("全站导航未同步表示专题");
|
||||
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 (token.initial.visible !== "token" || numeric(token.initial.steps) !== 9 || !token.initial.memory.includes("GiB")) failures.push("Token 实验初始状态异常");
|
||||
if (numeric(token.changed.steps) <= numeric(token.initial.steps) || numeric(token.changed.io) <= numeric(token.initial.io) || !token.changed.explain.includes("金融")) failures.push("Byte / untie / context 操作没有改变表示账");
|
||||
if (position.initial.visible !== "position" || position.initial.regime !== "INTERPOLATION") failures.push("位置实验初始状态异常");
|
||||
if (position.ropeOutside.regime !== "EXTRAPOLATION" || !position.ropeOutside.boundary.includes("192")) failures.push("位置外推窗口没有被识别");
|
||||
if (!position.alibi.term.includes("bias") || !position.alibi.explain.includes("logit")) failures.push("ALiBi 机制展示异常");
|
||||
if (!position.nope.mode.includes("NO EXPLICIT") || !position.nope.explain.includes("隐式")) failures.push("NoPE 边界说明异常");
|
||||
if (norm.initial.visible !== "norm" || numeric(norm.unbounded.rms) <= numeric(norm.initial.rms)) failures.push("深度 / RMS 教学曲线异常");
|
||||
if (numeric(norm.qk.peak) >= numeric(norm.unbounded.peak) || !norm.qk.boundary.includes("QK-Norm")) failures.push("QK-Norm 没有压低 toy softmax 峰值");
|
||||
if (numeric(norm.post.rms) !== 1 || numeric(norm.post.identity) >= 1) failures.push("Post-LN 拓扑展示异常");
|
||||
if (residual.initial.visible !== "residual" || !residual.initial.route.includes("ATTENTION")) failures.push("Residual 实验初始状态异常");
|
||||
if (!residual.mhc.route.includes("MANIFOLD") || numeric(residual.mhc.states) !== 4 || !residual.mhc.routeExplain.includes("Birkhoff")) failures.push("mHC 教学状态异常");
|
||||
if (numeric(residual.attnres.states) !== 9 || !residual.attnres.routeExplain.includes("93")) failures.push("K3 Block AttnRes 来源数异常");
|
||||
if (!residual.clamp.activation.includes("V4") || !residual.clamp.bound.includes("100")) failures.push("DeepSeek-V4 clamp 展示异常");
|
||||
if (!residual.situ.activation.includes("KIMI") || !residual.situ.bound.includes("100")) failures.push("K3 SiTU 上界展示异常");
|
||||
if (residual.keyboardSelected !== "position" || residual.keyboardVisible !== "position") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页表示新章入口异常");
|
||||
if (home.paperCount !== "480" || home.topicCount !== "17" || papers.total !== 480 || !papers.hasFilter || papers.visible < 30) failures.push("首页 / 论文库表示索引异常");
|
||||
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- ${failures.join("\n- ")}`);
|
||||
process.exitCode = 1;
|
||||
} else {
|
||||
console.log("\nPASS representation browser regression");
|
||||
}
|
||||
|
||||
socket.close();
|
||||
@@ -269,14 +269,14 @@ if (emergence.paths.some((length) => length < 500)) failures.push("涌现多指
|
||||
if (layout.articleSections !== 16 || layout.paperLinks !== 29 || layout.labTabs !== 4 || layout.views !== 4) {
|
||||
failures.push("章节、论文或实验数量异常");
|
||||
}
|
||||
if (layout.navLinks !== 19 || mobile.mobileLinks !== 19 || home.navLinks !== 19) failures.push("全站导航未同步评测专题");
|
||||
if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) failures.push("全站导航未同步评测专题");
|
||||
if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出");
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") {
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "450") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (home.paperCount !== "480") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -233,7 +233,7 @@ if (layout.articleSections !== 16 || layout.paperLinks !== 37 || layout.labTabs
|
||||
if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出");
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单")) failures.push("首页评测新章入口异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state")) failures.push("首页评测新章入口异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -172,7 +172,7 @@ const home = await evaluate(`(() => ({
|
||||
releaseCards: document.querySelectorAll(".release-card").length,
|
||||
firstRelease: document.querySelector(".release-card h2").textContent,
|
||||
firstHref: document.querySelector(".release-card").getAttribute("href"),
|
||||
paperCount: [...document.querySelectorAll(".hero-stats b")].map((node) => node.textContent.trim()).find((value) => value === "450"),
|
||||
paperCount: [...document.querySelectorAll(".hero-stats b")].map((node) => node.textContent.trim()).find((value) => value === "480"),
|
||||
}))()`);
|
||||
|
||||
await navigate("/papers/");
|
||||
@@ -236,8 +236,8 @@ if (block.family.trim() !== "Hybrid MoE" || !block.kv.includes("3 KDA : 1 Gated
|
||||
if (!block.path.some((step) => step.includes("KDA × 3")) || !block.note.includes("AttnRes")) failures.push("K3 Block 路径异常");
|
||||
if (block.context.trim() !== "128K" || numeric(block.mha) !== 400 || numeric(block.kda) !== 1) failures.push("KV 成本缩放异常");
|
||||
if (block.keyboardSelected !== "block" || block.keyboardVisible !== "block") failures.push("实验 tab 键盘导航异常");
|
||||
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "450" || papers.total !== 450 || papers.transformerVisible < 30) failures.push("论文库或首页论文数量异常");
|
||||
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
|
||||
if (home.paperCount !== "480" || papers.total !== 480 || papers.transformerVisible < 30) failures.push("论文库或首页论文数量异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user