site: explain AttnRes spike path study

2026-07-30 12:20:47 +08:00
parent 3cbb163715
commit a1a52d4280
8 changed files with 1190 additions and 17 deletions
@@ -0,0 +1,216 @@
+import { writeFileSync } from "node:fs";
+
+const cdpPort = process.env.CDP_PORT ?? "9229";
+const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4329";
+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-spike-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -78);
+  const text = (selector) => root.querySelector(selector)?.textContent.trim();
+  const panel = () => root.querySelector("[data-spike-panel]:not([hidden])")?.dataset.spikePanel;
+  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-spike-tab]").length,
+    panels: root.querySelectorAll("[data-spike-panel]").length,
+    ledger: root.querySelectorAll(".spike-ledger article").length,
+    trajectoryPoints: root.querySelectorAll("[data-spike-time-points] circle").length,
+    trajectoryLine: points("[data-spike-time-line]"),
+    boundary: root.textContent.includes("不是训练出的 uniform 模型") &&
+      root.textContent.includes("不是 70.2% 因果贡献"),
+  };
+  root.querySelector('[data-spike-time-metric="population_cv"]').click();
+  setSelect("[data-spike-time-seed]", "2026073003");
+  const trajectoryChanged = {
+    title: text("[data-spike-time-title]"),
+    state: text("[data-spike-time-state]"),
+    line: points("[data-spike-time-line]"),
+    thresholdHidden: getComputedStyle(root.querySelector("[data-spike-time-threshold]")).display === "none",
+  };
+
+  root.querySelector('[data-spike-tab="positions"]').click();
+  root.querySelector('[data-spike-position="pre_mlp_input"]').click();
+  setSelect("[data-spike-position-seed]", "2026073002");
+  const positions = {
+    panel: panel(),
+    buttons: root.querySelectorAll("[data-spike-position]").length,
+    state: text("[data-spike-position-state]"),
+    contrast: text("[data-spike-position-contrast]"),
+    peak: text("[data-spike-position-peak]"),
+    peakValue: text("[data-spike-position-peak-value]"),
+    pointCount: root.querySelectorAll("[data-spike-position-points] circle").length,
+  };
+
+  root.querySelector('[data-spike-tab="reductions"]').click();
+  setSelect("[data-spike-reduction-seed]", "2026073003");
+  setSelect("[data-spike-reduction]", "token_rms_median");
+  const reductions = {
+    panel: panel(),
+    rows: root.querySelectorAll(".reduction-table tbody tr").length,
+    state: text("[data-spike-reduction-state]"),
+    contrast: text("[data-spike-reduction-contrast]"),
+    overlap: text("[data-spike-reduction-overlap]"),
+    rho: text("[data-spike-reduction-rho]"),
+    pointCount: root.querySelectorAll("[data-spike-reduction-points] circle").length,
+  };
+
+  root.querySelector('[data-spike-tab="intervention"]').click();
+  setSelect("[data-spike-intervention-seed]", "2026073002");
+  const intervention = {
+    panel: panel(),
+    lines: root.querySelectorAll("[data-spike-intervention-line]").length,
+    keyDrop: text("[data-spike-key-drop]"),
+    valueDrop: text("[data-spike-value-drop]"),
+    peakShift: text("[data-spike-peak-shift]"),
+    linePoints: [...root.querySelectorAll("[data-spike-intervention-line]")].map((node) => node.getAttribute("points").split(" ").length),
+    forwardIdentity: root.textContent.includes("same logits · same loss"),
+  };
+
+  root.querySelector('[data-spike-tab="mixer"]').click();
+  const mixerInitial = {
+    panel: panel(),
+    points: root.querySelectorAll("[data-spike-mixer-points] circle").length,
+    pearson: text("[data-spike-mixer-pearson]"),
+    spearman: text("[data-spike-mixer-spearman]"),
+    title: text("[data-spike-mixer-title]"),
+  };
+  root.querySelector('[data-spike-mixer-metric="mlp_entropy"]').click();
+  const mixerChanged = {
+    points: root.querySelectorAll("[data-spike-mixer-points] circle").length,
+    pearson: text("[data-spike-mixer-pearson]"),
+    spearman: text("[data-spike-mixer-spearman]"),
+    title: text("[data-spike-mixer-title]"),
+  };
+
+  const first = root.querySelector('[data-spike-tab="trajectory"]');
+  first.focus();
+  first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
+  const keyboard = {
+    selected: root.querySelector('[data-spike-tab][aria-selected="true"]').dataset.spikeTab,
+    panel: panel(),
+  };
+
+  return {
+    initial, trajectoryChanged, positions, reductions, intervention, mixerInitial, mixerChanged, keyboard,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+    rootOverflow: root.scrollWidth - root.clientWidth,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-spike-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-spike-lab]");
+  root.scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -64);
+  root.querySelector('[data-spike-tab="intervention"]').click();
+  return {
+    tabs: root.querySelectorAll("[data-spike-tab]").length,
+    ledger: root.querySelectorAll(".spike-ledger article").length,
+    visiblePanel: root.querySelector("[data-spike-panel]:not([hidden])")?.dataset.spikePanel,
+    lines: root.querySelectorAll("[data-spike-intervention-line]").length,
+    documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+    rootOverflow: root.scrollWidth - root.clientWidth,
+  };
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-attnres-spike-mobile.png");
+
+const report = { desktop, mobile, exceptions };
+console.log(JSON.stringify(report, null, 2));
+
+const numeric = (value) => Number.parseFloat(value.replace("−", "-").replace("%", ""));
+const failures = [];
+if (desktop.initial.panel !== "trajectory" || desktop.initial.tabs !== 5 || desktop.initial.panels !== 5 || desktop.initial.ledger !== 6 || desktop.initial.trajectoryPoints !== 6) failures.push("五视图或六点轨迹初始结构异常");
+if (!desktop.initial.boundary) failures.push("因果与训练变体边界缺失");
+if (!desktop.trajectoryChanged.title.includes("POPULATION CV") || !desktop.trajectoryChanged.state.includes("2026073003") || desktop.trajectoryChanged.line === desktop.initial.trajectoryLine || !desktop.trajectoryChanged.thresholdHidden) failures.push("轨迹 seed / metric 切换异常");
+if (desktop.positions.panel !== "positions" || desktop.positions.buttons !== 6 || !desktop.positions.state.includes("MLP 前输入") || Math.abs(numeric(desktop.positions.contrast) - 4.527) > .001 || numeric(desktop.positions.peak) !== 21 || desktop.positions.pointCount !== 32) failures.push("六位置谱或 seed 切换异常");
+if (desktop.reductions.panel !== "reductions" || desktop.reductions.rows !== 12 || !desktop.reductions.state.includes("Token RMS 中位数") || Math.abs(numeric(desktop.reductions.contrast) - 1.666) > .001 || desktop.reductions.overlap !== "3 / 5" || Math.abs(numeric(desktop.reductions.rho) - .934) > .001 || desktop.reductions.pointCount !== 32) failures.push("reduction robustness 视图异常");
+if (desktop.intervention.panel !== "intervention" || desktop.intervention.lines !== 3 || Math.abs(numeric(desktop.intervention.keyDrop) + 1.93) > .01 || Math.abs(numeric(desktop.intervention.valueDrop) - 76.87) > .01 || desktop.intervention.peakShift !== "21 → 2" || desktop.intervention.linePoints.some((count) => count !== 32) || !desktop.intervention.forwardIdentity) failures.push("same-forward backward 干预视图异常");
+if (desktop.mixerInitial.panel !== "mixer" || desktop.mixerInitial.points !== 30 || Math.abs(numeric(desktop.mixerInitial.pearson) - .690) > .001 || Math.abs(numeric(desktop.mixerInitial.spearman) - .693) > .001 || desktop.mixerChanged.points !== 30 || Math.abs(numeric(desktop.mixerChanged.pearson) + .636) > .001 || Math.abs(numeric(desktop.mixerChanged.spearman) + .640) > .001 || desktop.mixerInitial.title === desktop.mixerChanged.title) failures.push("mixer association 散点或指标切换异常");
+if (desktop.keyboard.selected !== "positions" || desktop.keyboard.panel !== "positions") 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.visiblePanel !== "intervention" || mobile.lines !== 3) 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 spike browser regression");
+}
+
+socket.close();