feat: add reduced AttnRes trace lab

2026-07-30 07:30:01 +08:00
parent d1d9d22bf3
commit 4ce780dcc9
11 changed files with 1070 additions and 26 deletions
@@ -0,0 +1,200 @@
+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}${path}` });
+  for (let attempt = 0; attempt < 80; attempt += 1) {
+    await pause(100);
+    if (await evaluate("document.readyState === 'complete'")) return;
+  }
+  throw new Error(`${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("/k3/");
+
+const desktop = await evaluate(`(() => {
+  const root = document.querySelector("[data-attnres-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -78);
+  const text = (selector) => root.querySelector(selector)?.textContent.trim();
+  const panel = () => root.querySelector("[data-attnres-panel]:not([hidden])")?.dataset.attnresPanel;
+  const line = (architecture) => root.querySelector(\`[data-curve-series="\${architecture}"] [data-curve-line]\`)?.getAttribute("points");
+
+  const initial = {
+    panel: panel(),
+    tabs: root.querySelectorAll("[data-attnres-tab]").length,
+    panels: root.querySelectorAll("[data-attnres-panel]").length,
+    baseline: text('[data-curve-final="baseline"]'),
+    full: text('[data-curve-final="full"]'),
+    block: text('[data-curve-final="block"]'),
+    baselineLine: line("baseline"),
+    textBoundary: root.textContent.includes("不是 K3 checkpoint forward") &&
+      root.textContent.includes("不能写成论文梯度结果复现"),
+  };
+
+  root.querySelector('[data-curve-seed="0"]').click();
+  const seed = {
+    baseline: text('[data-curve-final="baseline"]'),
+    full: text('[data-curve-final="full"]'),
+    block: text('[data-curve-final="block"]'),
+    baselineLine: line("baseline"),
+  };
+
+  root.querySelector('[data-attnres-tab="rms"]').click();
+  const rmsInitial = {
+    panel: panel(),
+    title: text("[data-rms-title]"),
+    blockLine: root.querySelector('[data-rms-series="block"]').getAttribute("points"),
+    rhythm: root.querySelectorAll(".block-rhythm i").length,
+  };
+  root.querySelector('[data-rms-metric="branch_output_rms"]').click();
+  const rmsChanged = {
+    title: text("[data-rms-title]"),
+    blockLine: root.querySelector('[data-rms-series="block"]').getAttribute("points"),
+  };
+
+  root.querySelector('[data-attnres-tab="mixer"]').click();
+  const mixerInitial = {
+    panel: panel(),
+    fullVisible: !root.querySelector('[data-mixer-view="full"]').hidden,
+    fullRows: root.querySelectorAll('[data-mixer-view="full"] .heat-row').length,
+    spike: root.querySelectorAll(".spikeSource").length,
+  };
+  root.querySelector('[data-mixer-arch="block"]').click();
+  const mixerChanged = {
+    blockVisible: !root.querySelector('[data-mixer-view="block"]').hidden,
+    blockRows: root.querySelectorAll('[data-mixer-view="block"] .heat-row').length,
+  };
+
+  root.querySelector('[data-attnres-tab="gradient"]').click();
+  const gradient = {
+    panel: panel(),
+    cards: root.querySelectorAll(".gradient-cv article").length,
+    blocks: root.querySelectorAll(".gradient-grid article").length,
+    boundary: root.textContent.includes("BASE < FULL < BLOCK") &&
+      root.textContent.includes("不能写成论文梯度结果复现"),
+  };
+
+  root.querySelector('[data-attnres-tab="audit"]').click();
+  const audit = {
+    panel: panel(),
+    costs: root.querySelectorAll(".cost-grid article").length,
+    hashes: root.querySelectorAll(".hash-ledger code").length,
+    exact: root.textContent.includes("2,000 steps · 8 / 8 exact"),
+    claims: root.querySelectorAll(".claim-grid li").length,
+  };
+
+  const first = root.querySelector('[data-attnres-tab="outcome"]');
+  first.focus();
+  first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
+  const keyboard = {
+    selected: root.querySelector('[data-attnres-tab][aria-selected="true"]').dataset.attnresTab,
+    panel: panel(),
+  };
+
+  return {
+    initial, seed, rmsInitial, rmsChanged, mixerInitial, mixerChanged, gradient, audit, keyboard,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-desktop.png");
+
+await command("Emulation.setDeviceMetricsOverride", {
+  width: 390,
+  height: 844,
+  deviceScaleFactor: 1,
+  mobile: true,
+});
+await navigate("/k3/");
+const mobile = await evaluate(`(() => {
+  const root = document.querySelector("[data-attnres-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -64);
+  return {
+    tabs: root.querySelectorAll("[data-attnres-tab]").length,
+    ledger: root.querySelectorAll(".trace-ledger article").length,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+    rootOverflow: root.scrollWidth - root.clientWidth,
+    visiblePanel: root.querySelector("[data-attnres-panel]:not([hidden])")?.dataset.attnresPanel,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-mobile.png");
+
+const report = { desktop, mobile, exceptions };
+console.log(JSON.stringify(report, null, 2));
+
+const numeric = (text) => Number.parseFloat(text.replace("−", "-"));
+const failures = [];
+if (desktop.initial.panel !== "outcome" || desktop.initial.tabs !== 5 || desktop.initial.panels !== 5) failures.push("五视图初始结构异常");
+if (Math.abs(numeric(desktop.initial.baseline) - 1.99913) > 1e-5 || Math.abs(numeric(desktop.initial.full) - 1.98457) > 1e-5 || Math.abs(numeric(desktop.initial.block) - 1.95667) > 1e-5) failures.push("三 seed 均值 BPC 异常");
+if (Math.abs(numeric(desktop.seed.baseline) - 2.00054) > 1e-5 || desktop.seed.baselineLine === desktop.initial.baselineLine) failures.push("seed 切换未更新训练曲线");
+if (!desktop.initial.textBoundary) failures.push("主视区缺少 K3 forward 或梯度反证边界");
+if (desktop.rmsInitial.panel !== "rms" || desktop.rmsInitial.rhythm !== 32 || desktop.rmsInitial.title === desktop.rmsChanged.title || desktop.rmsInitial.blockLine === desktop.rmsChanged.blockLine) failures.push("RMS 指标切换或 32 层节律异常");
+if (desktop.mixerInitial.panel !== "mixer" || !desktop.mixerInitial.fullVisible || desktop.mixerInitial.fullRows !== 32 || desktop.mixerInitial.spike !== 1 || !desktop.mixerChanged.blockVisible || desktop.mixerChanged.blockRows !== 32) failures.push("Full/Block mixer heatmap 异常");
+if (desktop.gradient.panel !== "gradient" || desktop.gradient.cards !== 4 || desktop.gradient.blocks !== 16 || !desktop.gradient.boundary) failures.push("梯度反证视图异常");
+if (desktop.audit.panel !== "audit" || desktop.audit.costs !== 3 || desktop.audit.hashes !== 4 || !desktop.audit.exact || desktop.audit.claims !== 6) failures.push("成本、重放或 claim boundary 异常");
+if (desktop.keyboard.selected !== "rms" || desktop.keyboard.panel !== "rms") failures.push("键盘 tab 导航异常");
+if (desktop.documentOverflow > 1 || mobile.documentOverflow > 1 || mobile.rootOverflow > 1) failures.push("桌面或移动端出现文档级横向溢出");
+if (mobile.tabs !== 5 || mobile.ledger !== 6 || mobile.visiblePanel !== "outcome") failures.push("移动端初始结构异常");
+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 K3 AttnRes browser regression");
+}
+
+socket.close();