feat: publish long-horizon agent chapter

2026-07-29 06:54:31 +08:00
parent 6c8c0fb90f
commit 25982cbbb4
25 changed files with 5122 additions and 39 deletions
@@ -0,0 +1,243 @@
+import { writeFileSync } from "node:fs";
+
+const cdpPort = process.env.CDP_PORT ?? "9225";
+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}${path}` });
+  for (let attempt = 0; attempt < 70; attempt += 1) {
+    await pause(100);
+    if (await evaluate("document.readyState === 'complete'")) return;
+  }
+  throw new Error(`${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("/agents/");
+await screenshot("/tmp/llm-atlas-agents-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-agent-tab]").length,
+  labPanels: document.querySelectorAll("[data-agent-panel]").length,
+  navLinks: document.querySelectorAll(".top-nav a").length,
+  documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
+}))()`);
+
+const loop = await evaluate(`(() => {
+  const root = document.querySelector("[data-agent-lab]");
+  const read = () => ({
+    status: root.querySelector("[data-loop-status]").textContent.trim(),
+    observation: root.querySelector("[data-loop-observation]").textContent.trim(),
+    recovery: root.querySelector("[data-loop-recovery]").textContent.trim(),
+    finalState: root.querySelector("[data-loop-final]").textContent.trim(),
+    takeaway: root.querySelector("[data-loop-takeaway]").textContent.trim(),
+  });
+  const initial = read();
+  root.querySelector('[data-loop-mode="direct"]').click();
+  root.querySelector('[data-loop-fault="schema"]').click();
+  root.querySelector("[data-loop-next]").click();
+  root.querySelector("[data-loop-next]").click();
+  return { initial, directSchema: read() };
+})()`);
+
+const contract = await evaluate(`(() => {
+  const root = document.querySelector("[data-agent-lab]");
+  root.querySelector('[data-agent-tab="contract"]').click();
+  root.querySelector('[data-contract-case="wrongstate"]').click();
+  return {
+    syntax: root.querySelector('[data-contract-score="syntax"]').textContent.trim(),
+    execution: root.querySelector('[data-contract-score="execution"]').textContent.trim(),
+    finalState: root.querySelector('[data-contract-score="final"]').textContent.trim(),
+    takeaway: root.querySelector("[data-contract-takeaway]").textContent.trim(),
+    visiblePanel: root.querySelector("[data-agent-panel]:not([hidden])").dataset.agentPanel,
+  };
+})()`);
+
+const reliability = await evaluate(`(() => {
+  const root = document.querySelector("[data-agent-lab]");
+  root.querySelector('[data-agent-tab="reliability"]').click();
+  const k = root.querySelector("[data-rel-k]");
+  const read = () => ({
+    passAt: root.querySelector("[data-rel-pass-at]").textContent.trim(),
+    passHat: root.querySelector("[data-rel-pass-hat]").textContent.trim(),
+    sideRisk: root.querySelector("[data-rel-side]").textContent.trim(),
+    takeaway: root.querySelector("[data-rel-takeaway]").textContent.trim(),
+  });
+  const initial = read();
+  k.value = "2";
+  k.dispatchEvent(new Event("input", { bubbles: true }));
+  const k2 = read();
+  k.value = "8";
+  k.dispatchEvent(new Event("input", { bubbles: true }));
+  root.querySelector('[data-rel-idempotent="false"]').click();
+  const nonIdempotent = read();
+  return { initial, k2, nonIdempotent };
+})()`);
+
+const rl = await evaluate(`(() => {
+  const root = document.querySelector("[data-agent-lab]");
+  root.querySelector('[data-agent-tab="rl"]').click();
+  const read = () => ({
+    utilization: root.querySelector("[data-rl-util]").textContent.trim(),
+    lostWork: root.querySelector("[data-rl-lost]").textContent.trim(),
+    modelState: root.querySelector("[data-rl-model-state]").textContent.trim(),
+    worldState: root.querySelector("[data-rl-world-state]").textContent.trim(),
+    takeaway: root.querySelector("[data-rl-takeaway]").textContent.trim(),
+  });
+  const full = read();
+  root.querySelector('[data-rl-mode="wait"]').click();
+  const wait = read();
+  const firstTab = root.querySelector('[data-agent-tab="loop"]');
+  firstTab.focus();
+  firstTab.dispatchEvent(new KeyboardEvent("keydown", { key: "End", bubbles: true }));
+  return {
+    full,
+    wait,
+    keyboardSelected: root.querySelector('[data-agent-tab][aria-selected="true"]').dataset.agentTab,
+    keyboardVisible: root.querySelector("[data-agent-panel]:not([hidden])").dataset.agentPanel,
+  };
+})()`);
+
+await evaluate(`document.querySelector("[data-agent-lab]").scrollIntoView({ block: "start", behavior: "instant" })`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-agents-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(),
+  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() === "Agent");
+  button?.click();
+  return {
+    total: document.querySelectorAll("[data-paper]").length,
+    agentVisible: document.querySelectorAll("[data-paper]:not([hidden])").length,
+    hasAgentFilter: Boolean(button),
+  };
+})()`);
+
+await command("Emulation.setDeviceMetricsOverride", {
+  width: 390,
+  height: 844,
+  deviceScaleFactor: 1,
+  mobile: true,
+});
+await navigate("/agents/");
+const mobile = await evaluate(`(() => {
+  const root = document.querySelector("[data-agent-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-agent-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-agents-mobile.png");
+
+const report = { overview, loop, contract, reliability, rl, home, papers, mobile, exceptions };
+console.log(JSON.stringify(report, null, 2));
+
+const numeric = (value) => Number.parseFloat(value);
+const failures = [];
+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 !== 16 || home.navLinks !== 16 || mobile.mobileLinks !== 16) failures.push("全站导航未同步 Agent 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");
+if (contract.syntax !== "100%" || contract.execution !== "100%" || contract.finalState !== "0%") failures.push("工具契约三层评分异常");
+if (!contract.takeaway.includes("final-state") || contract.visiblePanel !== "contract") failures.push("工具契约终局验证解释异常");
+if (numeric(reliability.initial.passAt) < 99.9 || Math.abs(numeric(reliability.initial.passHat) - 16.78) > 0.02) failures.push("pass@k / pass^k 初始计算异常");
+if (numeric(reliability.initial.passAt) <= numeric(reliability.k2.passAt) || numeric(reliability.initial.passHat) >= numeric(reliability.k2.passHat)) failures.push("k 增长时两类可靠性没有反向变化");
+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 !== 11 || !home.firstRelease.includes("Agent 不是一个循环") || home.firstHref !== "/agents/") failures.push("首页 Agent 首发入口异常");
+if (home.paperCount !== "314" || papers.total !== 314 || !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(" | ")}`);
+
+if (failures.length) {
+  console.error(`\nFAIL\n- ${failures.join("\n- ")}`);
+  process.exitCode = 1;
+} else {
+  console.log("\nPASS agents browser regression");
+}
+
+socket.close();