site: explain K3 round seven local path audit
This commit is contained in:
@@ -228,7 +228,7 @@ 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 !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || papers.total !== 486 || !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:${exceptions.join(" | ")}`);
|
||||
|
||||
@@ -226,7 +226,7 @@ if (!update.steps[0].includes("Fixed preference")) failures.push("DPO 更新流
|
||||
if (!recipe.family.includes("Multi-effort") || !recipe.regime.includes("9 RL experts") || !recipe.constraints.includes("verbosity")) failures.push("K3 配方合同异常");
|
||||
if (!recipe.path.some((step) => step.includes("3 domains × 3 efforts")) || !recipe.path.some((step) => step.includes("MOPD"))) failures.push("K3 配方路径异常");
|
||||
if (recipe.keyboardSelected !== "recipe" || recipe.keyboardVisible !== "recipe") failures.push("实验 tab 键盘导航异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasAlignmentFilter || papers.alignmentVisible < 35) failures.push("论文库后训练标签或论文总数异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`);
|
||||
|
||||
@@ -234,7 +234,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20)
|
||||
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:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") {
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
|
||||
@@ -1318,7 +1318,7 @@ if (completionDepth.tasks.panel !== "tasks" || completionDepth.tasks.mathCards !
|
||||
if (completionDepth.hidden.panel !== "hidden" || completionDepth.hidden.stages !== 29 || completionDepth.hidden.selected !== "layer_07" || completionDepth.hidden.points !== 29 || completionDepth.hidden.exact === "1,537 / 1,537" || numeric(completionDepth.hidden.relative) <= 0) failures.push("29 阶段隐藏状态曲线或交互异常");
|
||||
if (completionDepth.router.panel !== "router" || completionDepth.router.layers !== 26 || completionDepth.router.selected !== "layer 24" || completionDepth.router.points !== 26 || !completionDepth.router.ordered.includes("%") || !completionDepth.router.setExact.includes("%") || numeric(completionDepth.router.tv) <= 0 || completionDepth.router.reproCards !== 4 || completionDepth.router.links !== 4) failures.push("26 层 MoE 路由曲线或复跑证据异常");
|
||||
if (completionDepth.keyboardSelected !== "tasks" || completionDepth.keyboardVisible !== "tasks") failures.push("完成度与全深度实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/" || home.paperCount !== "486") failures.push("首页 K3 首发入口或论文数异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/" || home.paperCount !== "486") failures.push("首页 K3 首发入口或论文数异常");
|
||||
if (papers.total !== 486 || !papers.hasFilter || papers.visible < 20 || !papers.hasCoder || !papers.hasEngram) failures.push("论文库 DeepSeek 聚光异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 13 || mobile.behaviorTabs !== 4 || mobile.behaviorSources !== 16 || mobile.behaviorEdges !== 10 || mobile.behaviorDeviceCells !== 29 || mobile.completionDepthTabs !== 4 || mobile.completionDepthHiddenStages !== 29 || mobile.completionDepthRouterLayers !== 26 || mobile.artifactHeatCells !== 64 || mobile.corpusCohorts !== 3 || mobile.lengthDeltaCards !== 4 || mobile.templateLayers !== 6 || mobile.templateScopes !== 2 || mobile.templateModes !== 2 || mobile.templateDomainCards !== 4 || mobile.templateDepthCells !== 24 || mobile.historyLayers !== 6 || mobile.historyScopes !== 2 || mobile.historyModes !== 2 || mobile.historyEffects !== 3 || mobile.historyDomainCards !== 4 || mobile.historyDepthCells !== 24 || mobile.distanceLayers !== 6 || mobile.distanceScopes !== 2 || mobile.distanceModes !== 2 || mobile.distanceContrasts !== 2 || mobile.distanceDomainCards !== 4 || mobile.distanceDepthCells !== 24 || mobile.boundaryLayers !== 6 || mobile.boundaryScopes !== 2 || mobile.boundaryModes !== 2 || mobile.boundaryContrasts !== 3 || mobile.boundaryTokenCards !== 4 || mobile.boundaryDomainCards !== 4 || mobile.boundaryDepthCells !== 24 || mobile.roleLayers !== 6 || mobile.roleScopes !== 2 || mobile.roleModes !== 2 || mobile.roleContrasts !== 3 || mobile.roleLevelCards !== 4 || mobile.roleDomainCards !== 4 || mobile.roleDepthCells !== 24 || mobile.specialLayers !== 6 || mobile.specialScopes !== 2 || mobile.specialModes !== 2 || mobile.specialContrasts !== 4 || mobile.specialTokenCards !== 4 || mobile.specialDomainCards !== 4 || mobile.specialDepthCells !== 24 || mobile.roleBlockLayers !== 6 || mobile.roleBlockScopes !== 2 || mobile.roleBlockModes !== 2 || mobile.roleBlockEffects !== 3 || mobile.roleBlockMatrixCards !== 4 || mobile.roleBlockDomainCards !== 4 || mobile.roleBlockDepthCells !== 24) 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:${JSON.stringify(mobile.offenders)}`);
|
||||
|
||||
@@ -277,7 +277,7 @@ if (numeric(system.initial.success) <= numeric(system.initial.model) || numeric(
|
||||
if (numeric(system.cheap.success) >= numeric(system.initial.success) || numeric(system.cheap.cost) !== 4) failures.push("低预算没有降低成功率 / 成本");
|
||||
if (numeric(system.locked.unsafe) !== 0 || numeric(system.locked.overrefusal) <= numeric(system.initial.overrefusal)) failures.push("安全壳没有展现危险服从 / 过拒权衡");
|
||||
if (system.keyboardSelected !== "judge" || system.keyboardVisible !== "judge") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || home.topicCount !== "17" || papers.total !== 486 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`);
|
||||
|
||||
@@ -264,7 +264,7 @@ 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 !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasFilter || papers.visible !== 46) 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:${JSON.stringify(mobile.offenders)}`);
|
||||
|
||||
@@ -0,0 +1,292 @@
|
||||
import { writeFileSync } from "node:fs";
|
||||
|
||||
const cdpPort = process.env.CDP_PORT ?? "9230";
|
||||
const baseUrl = process.env.SITE_URL ?? "http://127.0.0.1:4329";
|
||||
const pages = await fetch(`http://127.0.0.1:${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-local-path-lab]");
|
||||
root.scrollIntoView({ block: "start", behavior: "instant" });
|
||||
window.scrollBy(0, -78);
|
||||
const text = (selector) => root.querySelector(selector)?.textContent.trim();
|
||||
const panel = () => root.querySelector("[data-local-panel]:not([hidden])")?.dataset.localPanel;
|
||||
const setSelect = (selector, value) => {
|
||||
const node = root.querySelector(selector);
|
||||
node.value = value;
|
||||
node.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
};
|
||||
const findMatrix = (needle) => [...root.querySelectorAll(".matrix-bars article")]
|
||||
.find((node) => node.textContent.includes(needle))?.textContent.replace(/\\s+/g, " ").trim();
|
||||
|
||||
const initial = {
|
||||
panel: panel(),
|
||||
tabs: root.querySelectorAll("[data-local-tab]").length,
|
||||
panels: root.querySelectorAll("[data-local-panel]").length,
|
||||
ledger: root.querySelectorAll(".local-ledger article").length,
|
||||
groups: root.querySelectorAll(".group-map article.target").length,
|
||||
spikeLayers: root.querySelectorAll(".group-map i.spike").length,
|
||||
boundary: root.textContent.includes("LOCALIZATION NOT ESTABLISHED") &&
|
||||
root.textContent.includes("不是贡献率") &&
|
||||
root.textContent.includes("不是 K3 checkpoint"),
|
||||
};
|
||||
|
||||
root.querySelector('[data-local-tab="matrix"]').click();
|
||||
const matrixInitial = {
|
||||
panel: panel(),
|
||||
rows: root.querySelectorAll(".matrix-bars article").length,
|
||||
state: text("[data-local-matrix-state]"),
|
||||
group67: findMatrix("仅 Groups 6+7 uniform"),
|
||||
restoration67: findMatrix("恢复 Groups 6+7"),
|
||||
};
|
||||
setSelect("[data-local-matrix-seed]", "2026073002");
|
||||
root.querySelector('[data-local-matrix-metric="peak_normalized"]').click();
|
||||
const matrixChanged = {
|
||||
rows: root.querySelectorAll(".matrix-bars article").length,
|
||||
state: text("[data-local-matrix-state]"),
|
||||
group67: findMatrix("仅 Groups 6+7 uniform"),
|
||||
restoration67: findMatrix("恢复 Groups 6+7"),
|
||||
};
|
||||
|
||||
root.querySelector('[data-local-tab="dual"]').click();
|
||||
const dual = {
|
||||
panel: panel(),
|
||||
rows: root.querySelectorAll(".dual-table tbody tr").length,
|
||||
good: root.querySelectorAll(".dual-table td.good").length,
|
||||
bad: root.querySelectorAll(".dual-table td.bad").length,
|
||||
verdict: text(".verdict-banner"),
|
||||
mean: root.querySelector(".dual-table tr.mean")?.textContent.replace(/\\s+/g, " ").trim(),
|
||||
};
|
||||
|
||||
root.querySelector('[data-local-tab="branch"]').click();
|
||||
const branchInitial = {
|
||||
panel: panel(),
|
||||
state: text("[data-local-branch-state]"),
|
||||
values: [...root.querySelectorAll("[data-local-branch-value]")].map((node) => node.textContent.trim()),
|
||||
passed: root.dataset.branchPassed,
|
||||
};
|
||||
root.querySelector('[data-local-branch-group="7"]').click();
|
||||
const branchChanged = {
|
||||
state: text("[data-local-branch-state]"),
|
||||
values: [...root.querySelectorAll("[data-local-branch-value]")].map((node) => node.textContent.trim()),
|
||||
labels: [...root.querySelectorAll("[data-local-branch-label]")].map((node) => node.textContent.trim()),
|
||||
passed: root.dataset.branchPassed,
|
||||
};
|
||||
|
||||
root.querySelector('[data-local-tab="spectrum"]').click();
|
||||
const spectrumInitial = {
|
||||
panel: panel(),
|
||||
points: root.querySelectorAll("[data-local-spectrum-points] circle").length,
|
||||
line: root.querySelector("[data-local-spectrum-line]").getAttribute("points"),
|
||||
state: text("[data-local-spectrum-state]"),
|
||||
count: text("[data-local-spectrum-count]"),
|
||||
contrast: text("[data-local-spectrum-contrast]"),
|
||||
peak: text("[data-local-spectrum-peak]"),
|
||||
layer: text("[data-local-spectrum-layer]"),
|
||||
};
|
||||
setSelect("[data-local-spectrum-seed]", "2026073002");
|
||||
setSelect("[data-local-spectrum-mode]", "uniform_groups_6_7_only");
|
||||
const spectrumGroup67 = {
|
||||
points: root.querySelectorAll("[data-local-spectrum-points] circle").length,
|
||||
line: root.querySelector("[data-local-spectrum-line]").getAttribute("points"),
|
||||
state: text("[data-local-spectrum-state]"),
|
||||
count: text("[data-local-spectrum-count]"),
|
||||
contrast: text("[data-local-spectrum-contrast]"),
|
||||
peak: text("[data-local-spectrum-peak]"),
|
||||
layer: text("[data-local-spectrum-layer]"),
|
||||
selectedPeakRadius: root.querySelector('[data-local-spectrum-points] circle[data-layer="25"]')?.getAttribute("r"),
|
||||
};
|
||||
setSelect("[data-local-spectrum-seed]", "2026073003");
|
||||
setSelect("[data-local-spectrum-mode]", "uniform_all");
|
||||
const spectrumAll = {
|
||||
points: root.querySelectorAll("[data-local-spectrum-points] circle").length,
|
||||
state: text("[data-local-spectrum-state]"),
|
||||
count: text("[data-local-spectrum-count]"),
|
||||
layer: text("[data-local-spectrum-layer]"),
|
||||
selectedPeakRadius: root.querySelector('[data-local-spectrum-points] circle[data-layer="2"]')?.getAttribute("r"),
|
||||
};
|
||||
|
||||
const first = root.querySelector('[data-local-tab="scope"]');
|
||||
first.focus();
|
||||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||||
const keyboard = {
|
||||
selected: root.querySelector('[data-local-tab][aria-selected="true"]').dataset.localTab,
|
||||
panel: panel(),
|
||||
};
|
||||
|
||||
return {
|
||||
initial, matrixInitial, matrixChanged, dual, branchInitial, branchChanged,
|
||||
spectrumInitial, spectrumGroup67, spectrumAll, keyboard,
|
||||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||||
rootOverflow: root.scrollWidth - root.clientWidth,
|
||||
};
|
||||
})()`);
|
||||
await pause(180);
|
||||
await screenshot("/tmp/llm-atlas-k3-attnres-local-path-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-local-path-lab]");
|
||||
root.scrollIntoView({ block: "start", behavior: "instant" });
|
||||
window.scrollBy(0, -64);
|
||||
root.querySelector('[data-local-tab="dual"]').click();
|
||||
const dual = {
|
||||
panel: root.querySelector("[data-local-panel]:not([hidden])")?.dataset.localPanel,
|
||||
rows: root.querySelectorAll(".dual-table tbody tr").length,
|
||||
wrapperOverflow: root.querySelector(".dual-table-wrap").scrollWidth -
|
||||
root.querySelector(".dual-table-wrap").clientWidth,
|
||||
};
|
||||
root.querySelector('[data-local-tab="spectrum"]').click();
|
||||
return {
|
||||
tabs: root.querySelectorAll("[data-local-tab]").length,
|
||||
ledger: root.querySelectorAll(".local-ledger article").length,
|
||||
visiblePanel: root.querySelector("[data-local-panel]:not([hidden])")?.dataset.localPanel,
|
||||
points: root.querySelectorAll("[data-local-spectrum-points] circle").length,
|
||||
dual,
|
||||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||||
rootOverflow: root.scrollWidth - root.clientWidth,
|
||||
};
|
||||
})()`);
|
||||
await pause(180);
|
||||
await screenshot("/tmp/llm-atlas-k3-attnres-local-path-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 !== "scope" || desktop.initial.tabs !== 5 || desktop.initial.panels !== 5 ||
|
||||
desktop.initial.ledger !== 6 || desktop.initial.groups !== 2 || desktop.initial.spikeLayers !== 5) {
|
||||
failures.push("五视图、六项账本或预注册路径地图结构异常");
|
||||
}
|
||||
if (!desktop.initial.boundary) failures.push("localization / contribution / reduced-model claim boundary 缺失");
|
||||
if (desktop.matrixInitial.panel !== "matrix" || desktop.matrixInitial.rows !== 14 ||
|
||||
!desktop.matrixInitial.state.includes("3-SEED MEAN") ||
|
||||
!desktop.matrixInitial.group67.includes("+0.677") ||
|
||||
!desktop.matrixInitial.restoration67.includes("+0.650")) {
|
||||
failures.push("14-mask mean contrast 矩阵异常");
|
||||
}
|
||||
if (desktop.matrixChanged.rows !== 14 || !desktop.matrixChanged.state.includes("2026073002") ||
|
||||
!desktop.matrixChanged.state.includes("PEAK / MEAN") ||
|
||||
!desktop.matrixChanged.group67.includes("+1.783") ||
|
||||
!desktop.matrixChanged.restoration67.includes("+0.355")) {
|
||||
failures.push("matrix seed / metric 切换异常");
|
||||
}
|
||||
if (desktop.dual.panel !== "dual" || desktop.dual.rows !== 4 || desktop.dual.good !== 9 ||
|
||||
desktop.dual.bad !== 6 || !desktop.dual.verdict.includes("LOCALIZATION NOT ESTABLISHED") ||
|
||||
!desktop.dual.mean.includes("0.677") || !desktop.dual.mean.includes("0.380") ||
|
||||
!desktop.dual.mean.includes("3 / 6")) {
|
||||
failures.push("双向主门表格或冻结判定异常");
|
||||
}
|
||||
if (desktop.branchInitial.panel !== "branch" || desktop.branchInitial.passed !== "false" ||
|
||||
!desktop.branchInitial.state.includes("5 / 6") ||
|
||||
desktop.branchChanged.passed !== "true" || !desktop.branchChanged.state.includes("6 / 6 PASS") ||
|
||||
desktop.branchChanged.labels.some((value) => value !== "GROUP 7") ||
|
||||
Math.abs(numeric(desktop.branchChanged.values[0]) - .015) > .001 ||
|
||||
Math.abs(numeric(desktop.branchChanged.values[1]) - .026) > .001 ||
|
||||
Math.abs(numeric(desktop.branchChanged.values[2]) - .426) > .001 ||
|
||||
Math.abs(numeric(desktop.branchChanged.values[3]) - .823) > .001) {
|
||||
failures.push("group 6 / 7 branch gate 切换异常");
|
||||
}
|
||||
if (desktop.spectrumInitial.panel !== "spectrum" || desktop.spectrumInitial.points !== 32 ||
|
||||
desktop.spectrumInitial.count !== "0 / 65" || numeric(desktop.spectrumInitial.contrast) !== 3.093 ||
|
||||
numeric(desktop.spectrumInitial.peak) !== 3.241 || desktop.spectrumInitial.layer !== "21") {
|
||||
failures.push("reference 32 层谱异常");
|
||||
}
|
||||
if (desktop.spectrumGroup67.points !== 32 || desktop.spectrumGroup67.line === desktop.spectrumInitial.line ||
|
||||
!desktop.spectrumGroup67.state.includes("2026073002") ||
|
||||
desktop.spectrumGroup67.count !== "16 / 65" ||
|
||||
numeric(desktop.spectrumGroup67.contrast) !== 1.263 ||
|
||||
numeric(desktop.spectrumGroup67.peak) !== 1.326 ||
|
||||
desktop.spectrumGroup67.layer !== "25" || desktop.spectrumGroup67.selectedPeakRadius !== "4.5") {
|
||||
failures.push("groups 6+7 spectrum seed / mode / peak 切换异常");
|
||||
}
|
||||
if (desktop.spectrumAll.points !== 32 || desktop.spectrumAll.count !== "65 / 65" ||
|
||||
desktop.spectrumAll.layer !== "2" || desktop.spectrumAll.selectedPeakRadius !== "4.5") {
|
||||
failures.push("all-uniform spectrum selector census 或 peak 异常");
|
||||
}
|
||||
if (desktop.keyboard.selected !== "matrix" || desktop.keyboard.panel !== "matrix") {
|
||||
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 !== "spectrum" ||
|
||||
mobile.points !== 32 || mobile.dual.panel !== "dual" || mobile.dual.rows !== 4 ||
|
||||
mobile.dual.wrapperOverflow <= 0) {
|
||||
failures.push("移动端交互结构或局部可滚动表格异常");
|
||||
}
|
||||
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 local-path browser regression");
|
||||
}
|
||||
|
||||
socket.close();
|
||||
@@ -85,6 +85,9 @@ const overview = await evaluate(`(() => ({
|
||||
gradientPanels: document.querySelectorAll("[data-gradient-panel]").length,
|
||||
spikeTabs: document.querySelectorAll("[data-spike-tab]").length,
|
||||
spikePanels: document.querySelectorAll("[data-spike-panel]").length,
|
||||
localPathTabs: document.querySelectorAll("[data-local-tab]").length,
|
||||
localPathPanels: document.querySelectorAll("[data-local-panel]").length,
|
||||
localPathVerdict: document.querySelector("#attnres-local-path")?.textContent.includes("localization 未建立"),
|
||||
nativeVisionCorrected: document.body.textContent.includes("MoonViT‑V2 从头训练") &&
|
||||
document.body.textContent.includes("同一个 next-token prediction objective"),
|
||||
staleVisionClaim: document.body.textContent.includes("先固定语言模型训练视觉组件"),
|
||||
@@ -296,8 +299,9 @@ const mobile = await evaluate(`(() => {
|
||||
attnresTabs: document.querySelectorAll("[data-attnres-tab]").length,
|
||||
gradientTabs: document.querySelectorAll("[data-gradient-tab]").length,
|
||||
spikeTabs: document.querySelectorAll("[data-spike-tab]").length,
|
||||
localPathTabs: document.querySelectorAll("[data-local-tab]").length,
|
||||
offenders: [...document.querySelectorAll("body *")]
|
||||
.filter((node) => !node.closest(".paper-chain, .spec-table-wrap, .cache-strip, .architecture-explorer, [data-k3-lab], [data-k3-artifact-lab], [data-attnres-lab], [data-gradient-lab], [data-spike-lab]"))
|
||||
.filter((node) => !node.closest(".paper-chain, .spec-table-wrap, .cache-strip, .architecture-explorer, [data-k3-lab], [data-k3-artifact-lab], [data-attnres-lab], [data-gradient-lab], [data-spike-lab], [data-local-path-lab]"))
|
||||
.filter((node) => node.getBoundingClientRect().right > document.documentElement.clientWidth + 1)
|
||||
.slice(0, 15)
|
||||
.map((node) => ({
|
||||
@@ -328,7 +332,7 @@ console.log(JSON.stringify(report, null, 2));
|
||||
const numeric = (text) => Number.parseFloat(text.replaceAll(",", "").replace("−", "-"));
|
||||
const failures = [];
|
||||
if (!overview.title.includes("因果环节")) failures.push("K3 二轮标题异常");
|
||||
if (overview.sections !== 35 || overview.tocLinks !== 35) failures.push("34 个编号专题加阅读链的目录结构异常");
|
||||
if (overview.sections !== 36 || overview.tocLinks !== 36) failures.push("35 个编号专题加阅读链的目录结构异常");
|
||||
if (overview.ledgers !== 32 || overview.reportMap !== 9) failures.push("32 张问题账或报告地图异常");
|
||||
if (overview.figureAtlas !== 21 || overview.paperLinks !== 100 || overview.paperGroups < 12) failures.push("图表审计或 100 节点阅读链异常");
|
||||
if (overview.labTabs !== 8 || overview.labPanels !== 8) failures.push("八联实验结构异常");
|
||||
@@ -336,6 +340,7 @@ if (overview.artifactTabs !== 4 || overview.artifactPanels !== 4 || overview.art
|
||||
if (overview.attnresTabs !== 5 || overview.attnresPanels !== 5) failures.push("AttnRes 独立实验五视图异常");
|
||||
if (overview.gradientTabs !== 5 || overview.gradientPanels !== 5) failures.push("AttnRes 梯度定义扩展五视图异常");
|
||||
if (overview.spikeTabs !== 5 || overview.spikePanels !== 5) failures.push("AttnRes 尖峰路径五视图异常");
|
||||
if (overview.localPathTabs !== 5 || overview.localPathPanels !== 5 || !overview.localPathVerdict) failures.push("AttnRes 局部路径五视图或冻结判定异常");
|
||||
if (!overview.nativeVisionCorrected || overview.staleVisionClaim) failures.push("原生多模态纠错未生效或旧错误残留");
|
||||
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 (labs.memoryInitial.panel !== "memory" || numeric(labs.memoryInitial.additiveError) <= numeric(labs.memoryInitial.deltaError)) failures.push("Delta memory 初始递推异常");
|
||||
@@ -360,7 +365,7 @@ if (artifacts.parameterChanged.shape !== "[96,128] F32" || !artifacts.parameterC
|
||||
if (artifacts.reproductionInitial.panel !== "reproduction" || numeric(artifacts.reproductionInitial.speedup) !== 1.85 || numeric(artifacts.reproductionInitial.localMean) < 2.6 || !artifacts.reproductionInitial.exactSuite || numeric(artifacts.reproductionInitial.cv) < 2) failures.push("FlashKDA H20、本机 exact suite 或 router 初始探针异常");
|
||||
if (numeric(artifacts.reproductionChanged.speedup) !== 3.27 || numeric(artifacts.reproductionChanged.flash) !== 0.7064 || numeric(artifacts.reproductionChanged.localMean) >= numeric(artifacts.reproductionInitial.localMean) || !artifacts.reproductionChanged.localMode.includes("FP32 state") || numeric(artifacts.reproductionChanged.cv) <= numeric(artifacts.reproductionInitial.cv) || numeric(artifacts.reproductionChanged.zero) <= numeric(artifacts.reproductionInitial.zero)) failures.push("GB200 benchmark、本机 varlen/state 或 synthetic router counterexample 未更新");
|
||||
if (artifacts.keyboardSelected !== "tensors" || artifacts.keyboardVisible !== "tensors") failures.push("开放工件键盘 tab 导航异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 8 || mobile.artifactTabs !== 4 || mobile.artifactLayers !== 93 || mobile.attnresTabs !== 5 || mobile.gradientTabs !== 5 || mobile.spikeTabs !== 5) failures.push("移动端导航或实验异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 8 || mobile.artifactTabs !== 4 || mobile.artifactLayers !== 93 || mobile.attnresTabs !== 5 || mobile.gradientTabs !== 5 || mobile.spikeTabs !== 5 || mobile.localPathTabs !== 5) 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:${exceptions.join(" | ")}`);
|
||||
|
||||
|
||||
@@ -246,7 +246,7 @@ if (ocr.unreported.status !== "OUT OF EVIDENCE" || ocr.unreported.accuracy !== "
|
||||
if (loop.toolsStart.state !== "OPEN" || loop.toolsEnd.state !== "VERIFIED" || loop.toolsEnd.evidence !== "97%" || loop.toolsEnd.tools !== "3") failures.push("vision-in-the-loop 终局异常");
|
||||
if (loop.cotEnd.state !== "FAILED" || !loop.cotEnd.takeaway.includes("不能凭空增加")) failures.push("文字 CoT 与新观察没有分开");
|
||||
if (loop.keyboardSelected !== "connector" || loop.keyboardVisible !== "connector") failures.push("实验键盘 tab 导航异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasFilter || papers.multimodalVisible < 59) failures.push("论文库多模态标签或总数异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`);
|
||||
|
||||
@@ -277,7 +277,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20)
|
||||
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:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") {
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
|
||||
@@ -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:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有")) failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强")) failures.push("首页 K3 首发入口异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -288,7 +288,7 @@ if (numeric(residual.attnres.states) !== 9 || !residual.attnres.routeExplain.inc
|
||||
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 !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || home.topicCount !== "17" || papers.total !== 486 || !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:${JSON.stringify(mobile.offenders)}`);
|
||||
|
||||
@@ -273,7 +273,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20)
|
||||
if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出");
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") {
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") {
|
||||
failures.push("首页 Transformer 新章入口异常");
|
||||
}
|
||||
if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`);
|
||||
|
||||
@@ -233,7 +233,7 @@ if (layout.articleSections !== 16 || layout.paperLinks !== 37 || layout.labTabs
|
||||
if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出");
|
||||
if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`);
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有")) failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强")) failures.push("首页 K3 首发入口异常");
|
||||
if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`);
|
||||
|
||||
socket.close();
|
||||
|
||||
@@ -236,7 +236,7 @@ if (block.family.trim() !== "Hybrid MoE" || !block.kv.includes("3 KDA : 1 Gated
|
||||
if (!block.path.some((step) => step.includes("KDA × 3")) || !block.note.includes("AttnRes")) failures.push("K3 Block 路径异常");
|
||||
if (block.context.trim() !== "128K" || numeric(block.mha) !== 400 || numeric(block.kda) !== 1) failures.push("KV 成本缩放异常");
|
||||
if (block.keyboardSelected !== "block" || block.keyboardVisible !== "block") failures.push("实验 tab 键盘导航异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.releaseCards !== 17 || !home.firstRelease.includes("16 个局部 mixer 单侧证据很强") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常");
|
||||
if (home.paperCount !== "486" || papers.total !== 486 || papers.transformerVisible < 30) failures.push("论文库或首页论文数量异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
|
||||
if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`);
|
||||
|
||||
Reference in New Issue
Block a user