feat: add AttnRes gradient scale lab

2026-07-30 10:24:42 +08:00
parent 26fc824409
commit f7670efcdd
9 changed files with 1191 additions and 17 deletions
@@ -0,0 +1,231 @@
+import { writeFileSync } from "node:fs";
+
+const cdpPort = process.env.CDP_PORT ?? "9228";
+const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4328";
+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}${path}` });
+  for (let attempt = 0; attempt < 100; attempt += 1) {
+    await pause(100);
+    if (await evaluate("document.readyState === 'complete'")) return;
+  }
+  throw new Error(`${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-gradient-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -78);
+  const text = (selector) => root.querySelector(selector)?.textContent.trim();
+  const panel = () => root.querySelector("[data-gradient-panel]:not([hidden])")?.dataset.gradientPanel;
+  const points = (selector) => root.querySelector(selector)?.getAttribute("points");
+  const setSelect = (selector, value) => {
+    const node = root.querySelector(selector);
+    node.value = value;
+    node.dispatchEvent(new Event("change", { bubbles: true }));
+  };
+
+  const initial = {
+    panel: panel(),
+    tabs: root.querySelectorAll("[data-gradient-tab]").length,
+    panels: root.querySelectorAll("[data-gradient-panel]").length,
+    ledger: root.querySelectorAll(".gradient-ledger article").length,
+    definition: root.textContent.includes("论文作者就是这样算的") &&
+      root.textContent.includes("activation gradient") &&
+      root.textContent.includes("parameter gradient"),
+  };
+
+  root.querySelector('[data-gradient-tab="spectrum"]').click();
+  const spectrumInitial = {
+    panel: panel(),
+    baseCv: text("[data-spectrum-base-cv]"),
+    blockCv: text("[data-spectrum-block-cv]"),
+    baseRatio: text("[data-spectrum-base-ratio]"),
+    blockRatio: text("[data-spectrum-block-ratio]"),
+    baseLine: points('[data-chart-line="baseline"]'),
+    blockLine: points('[data-chart-line="block"]'),
+    boundaries: root.querySelectorAll("[data-chart-groups] .group-boundary").length,
+  };
+  root.querySelector('[data-spectrum-scale="normalized"]').click();
+  const normalized = {
+    title: text("[data-spectrum-title]"),
+    baseLine: points('[data-chart-line="baseline"]'),
+  };
+  root.querySelector('[data-spectrum-depth="16"]').click();
+  const depth16 = {
+    baseCv: text("[data-spectrum-base-cv]"),
+    blockCv: text("[data-spectrum-block-cv]"),
+    pointCount: points('[data-chart-line="baseline"]').split(" ").length,
+    boundaries: root.querySelectorAll("[data-chart-groups] .group-boundary").length,
+  };
+  setSelect("[data-spectrum-seed]", "2026073001");
+  setSelect("[data-spectrum-step]", "2000");
+  const seedStep = {
+    state: text("[data-spectrum-state]"),
+    baseCv: text("[data-spectrum-base-cv]"),
+    blockCv: text("[data-spectrum-block-cv]"),
+  };
+
+  root.querySelector('[data-gradient-tab="timeline"]').click();
+  const timelineInitial = {
+    panel: panel(),
+    title: text("[data-time-title]"),
+    line: points('[data-time-line="block"]'),
+    pointCount: root.querySelectorAll('[data-time-points="block"] circle').length,
+  };
+  root.querySelector('[data-time-metric="imbalance"]').click();
+  const timelineChanged = {
+    title: text("[data-time-title]"),
+    line: points('[data-time-line="block"]'),
+  };
+
+  root.querySelector('[data-gradient-tab="output"]').click();
+  const outputInitial = {
+    panel: panel(),
+    pointCount: points('[data-output-line="block"]').split(" ").length,
+    bars: root.querySelectorAll("[data-output-bars] i").length,
+    boundaries: root.querySelectorAll("[data-output-groups] .group-boundary").length,
+    copy: text("[data-output-copy]"),
+  };
+  root.querySelector('[data-output-depth="16"]').click();
+  const outputDepth16 = {
+    pointCount: points('[data-output-line="block"]').split(" ").length,
+    bars: root.querySelectorAll("[data-output-bars] i").length,
+    copy: text("[data-output-copy]"),
+  };
+
+  root.querySelector('[data-gradient-tab="verdict"]').click();
+  const verdict = {
+    panel: panel(),
+    rows: root.querySelectorAll(".verdict-table tbody tr").length,
+    metrics: root.querySelectorAll(".metric-pairs article").length,
+    costs: root.querySelectorAll(".cost-compare article").length,
+    hashes: root.querySelectorAll(".hash-ledger code").length,
+    exact: root.textContent.includes("model + optimizer exact") &&
+      root.textContent.includes("all frozen fields exact"),
+    mixed: root.textContent.includes("depth-dependent or inconclusive"),
+  };
+
+  const first = root.querySelector('[data-gradient-tab="definition"]');
+  first.focus();
+  first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
+  const keyboard = {
+    selected: root.querySelector('[data-gradient-tab][aria-selected="true"]').dataset.gradientTab,
+    panel: panel(),
+  };
+
+  return {
+    initial, spectrumInitial, normalized, depth16, seedStep,
+    timelineInitial, timelineChanged, outputInitial, outputDepth16,
+    verdict, keyboard,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+    rootOverflow: root.scrollWidth - root.clientWidth,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-gradient-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-gradient-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -64);
+  root.querySelector('[data-gradient-tab="spectrum"]').click();
+  root.querySelector('[data-spectrum-depth="16"]').click();
+  root.querySelector('[data-gradient-tab="output"]').click();
+  root.querySelector('[data-output-depth="16"]').click();
+  return {
+    tabs: root.querySelectorAll("[data-gradient-tab]").length,
+    ledger: root.querySelectorAll(".gradient-ledger article").length,
+    outputBars: root.querySelectorAll("[data-output-bars] i").length,
+    visiblePanel: root.querySelector("[data-gradient-panel]:not([hidden])")?.dataset.gradientPanel,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+    rootOverflow: root.scrollWidth - root.clientWidth,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-gradient-mobile.png");
+
+const report = { desktop, mobile, exceptions };
+console.log(JSON.stringify(report, null, 2));
+
+const numeric = (value) => Number.parseFloat(value.replace("−", "-"));
+const failures = [];
+if (desktop.initial.panel !== "definition" || desktop.initial.tabs !== 5 || desktop.initial.panels !== 5 || desktop.initial.ledger !== 6) failures.push("五视图初始结构异常");
+if (!desktop.initial.definition) failures.push("定义与对象边界缺失");
+if (desktop.spectrumInitial.panel !== "spectrum" || Math.abs(numeric(desktop.spectrumInitial.baseCv) - 0.3786) > 1e-4 || Math.abs(numeric(desktop.spectrumInitial.blockCv) - 0.5996) > 1e-4) failures.push("depth-32 final spectrum 读数异常");
+if (desktop.spectrumInitial.boundaries !== 7 || desktop.spectrumInitial.baseLine === desktop.normalized.baseLine || !desktop.normalized.title.includes("NORMALIZED")) failures.push("绝对/归一化谱或组边界异常");
+if (desktop.depth16.pointCount !== 16 || desktop.depth16.boundaries !== 7 || Math.abs(numeric(desktop.depth16.baseCv) - 0.4246) > 1e-4 || Math.abs(numeric(desktop.depth16.blockCv) - 0.4678) > 1e-4) failures.push("depth-16 spectrum 切换异常");
+if (!desktop.seedStep.state.includes("2026073001") || !desktop.seedStep.state.includes("2,000") || Math.abs(numeric(desktop.seedStep.baseCv) - 0.4101) > 1e-4 || Math.abs(numeric(desktop.seedStep.blockCv) - 0.3656) > 1e-4) failures.push("seed/checkpoint spectrum 切换异常");
+if (desktop.timelineInitial.panel !== "timeline" || desktop.timelineInitial.pointCount !== 6 || desktop.timelineInitial.line === desktop.timelineChanged.line || !desktop.timelineChanged.title.includes("FIRST / LAST")) failures.push("六时点轨迹指标切换异常");
+if (desktop.outputInitial.panel !== "output" || desktop.outputInitial.pointCount !== 32 || desktop.outputInitial.bars !== 32 || desktop.outputInitial.boundaries !== 7 || desktop.outputDepth16.pointCount !== 16 || desktop.outputDepth16.bars !== 16 || !desktop.outputDepth16.copy.includes("DEPTH 16")) failures.push("Output RMS 深度/组节律切换异常");
+if (desktop.verdict.panel !== "verdict" || desktop.verdict.rows !== 2 || desktop.verdict.metrics !== 4 || desktop.verdict.costs !== 3 || desktop.verdict.hashes !== 4 || !desktop.verdict.exact || !desktop.verdict.mixed) failures.push("联合判定、成本或重放视图异常");
+if (desktop.keyboard.selected !== "spectrum" || desktop.keyboard.panel !== "spectrum") failures.push("键盘 tab 导航异常");
+if (desktop.documentOverflow > 1 || desktop.rootOverflow > 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.outputBars !== 16 || mobile.visiblePanel !== "output") failures.push("移动端交互结构异常");
+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 gradient browser regression");
+}
+
+socket.close();