1335 lines
96 KiB
JavaScript
1335 lines
96 KiB
JavaScript
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}${path}` });
|
||
for (let attempt = 0; attempt < 70; attempt += 1) {
|
||
await pause(100);
|
||
if (await evaluate("document.readyState === 'complete'")) return;
|
||
}
|
||
throw new Error(`${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("/deepseek/");
|
||
await screenshot("/tmp/llm-atlas-deepseek-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,
|
||
ledgers: document.querySelectorAll(".ledger-card").length,
|
||
waves: document.querySelectorAll(".wave-grid > article").length,
|
||
paperLinks: document.querySelectorAll("[data-deepseek-paper-chain] a").length,
|
||
labTabs: document.querySelectorAll("[data-ds-tab]").length,
|
||
labPanels: document.querySelectorAll("[data-ds-panel]").length,
|
||
artifactTabs: document.querySelectorAll("[data-artifact-tab]").length,
|
||
artifactPanels: document.querySelectorAll("[data-artifact-panel]").length,
|
||
artifactLayers: document.querySelectorAll(".layer-evidence > span").length,
|
||
behaviorTabs: document.querySelectorAll("[data-behavior-tab]").length,
|
||
behaviorPanels: document.querySelectorAll("[data-behavior-panel]").length,
|
||
behaviorSources: document.querySelectorAll("[data-behavior-source] option").length,
|
||
behaviorEdges: document.querySelectorAll("[data-behavior-map-edge]").length,
|
||
completionDepthTabs: document.querySelectorAll("[data-cd-tab]").length,
|
||
completionDepthPanels: document.querySelectorAll("[data-cd-panel]").length,
|
||
crossSourceTabs: document.querySelectorAll("[data-cs-tab]").length,
|
||
crossSourcePanels: document.querySelectorAll("[data-cs-panel]").length,
|
||
hiddenStages: document.querySelectorAll("[data-hidden-stage]").length,
|
||
routerLayers: document.querySelectorAll("[data-router-layer]").length,
|
||
branches: document.querySelectorAll(".branch-grid > a").length,
|
||
followups: document.querySelectorAll(".lineage-row.followup").length,
|
||
navLinks: document.querySelectorAll(".top-nav a").length,
|
||
activeNav: document.querySelector('.top-nav a[aria-current="page"]')?.textContent.trim(),
|
||
heroLabs: [...document.querySelectorAll(".page-facts > div")]
|
||
.find((node) => node.querySelector("dt")?.textContent.trim() === "LABS")
|
||
?.querySelector("dd")?.textContent.trim(),
|
||
documentOverflow: document.documentElement.scrollWidth - document.documentElement.clientWidth,
|
||
}))()`);
|
||
|
||
const capacity = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
total: root.querySelector("[data-total-capacity]").textContent.trim(),
|
||
active: root.querySelector("[data-active-compute]").textContent.trim(),
|
||
combinations: root.querySelector("[data-combinations]").textContent.trim(),
|
||
communication: root.querySelector("[data-communication]").textContent.trim(),
|
||
name: root.querySelector("[data-capacity-name]").textContent.trim(),
|
||
explain: root.querySelector("[data-capacity-explain]").textContent.trim(),
|
||
});
|
||
const initial = read();
|
||
root.querySelector('[data-capacity-preset="dense"]').click();
|
||
const dense = read();
|
||
root.querySelector('[data-capacity-preset="deepseekmoe"]').click();
|
||
const fine = read();
|
||
root.querySelector('[data-capacity-preset="v3"]').click();
|
||
const v3 = read();
|
||
return { initial, dense, fine, v3 };
|
||
})()`);
|
||
|
||
const cache = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="cache"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
mha: root.querySelector("[data-mha-elements]").textContent.trim(),
|
||
gqa: root.querySelector("[data-gqa-elements]").textContent.trim(),
|
||
mla: root.querySelector("[data-mla-elements]").textContent.trim(),
|
||
rope: root.querySelector("[data-rope-cache]").textContent.trim(),
|
||
selected: root.querySelector("[data-selected-cache]").textContent.trim(),
|
||
baseline: root.querySelector("[data-mha-cache]").textContent.trim(),
|
||
reduction: root.querySelector("[data-cache-reduction]").textContent.trim(),
|
||
boundary: root.querySelector("[data-cache-boundary]").textContent.trim(),
|
||
});
|
||
const initial = read();
|
||
const rope = root.querySelector("[data-rope-dim]");
|
||
rope.value = "0";
|
||
rope.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const noRope = read();
|
||
const context = root.querySelector("[data-context-length]");
|
||
context.value = "1048576";
|
||
context.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const million = read();
|
||
return { initial, noRope, million };
|
||
})()`);
|
||
|
||
const codesign = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="codesign"]').click();
|
||
const readSchedule = () => ({
|
||
bubble: root.querySelector("[data-bubble]").textContent.trim(),
|
||
exposed: root.querySelector("[data-exposed-comm]").textContent.trim(),
|
||
});
|
||
const oneWay = readSchedule();
|
||
root.querySelector('[data-schedule="dual"]').click();
|
||
const dual = readSchedule();
|
||
root.querySelector('[data-precision="naive"]').click();
|
||
const naive = {
|
||
risk: root.querySelector("[data-risk-label]").textContent.trim(),
|
||
accum: root.querySelector("[data-accum-dtype]").textContent.trim(),
|
||
explain: root.querySelector("[data-precision-explain]").textContent.trim(),
|
||
};
|
||
root.querySelector('[data-precision="mixed"]').click();
|
||
const mixed = {
|
||
risk: root.querySelector("[data-risk-label]").textContent.trim(),
|
||
accum: root.querySelector("[data-accum-dtype]").textContent.trim(),
|
||
sensitive: root.querySelector("[data-sensitive-dtype]").textContent.trim(),
|
||
};
|
||
root.querySelector('[data-mtp-role="off"]').click();
|
||
const off = root.querySelector("[data-mtp-supervision]").textContent.trim();
|
||
root.querySelector('[data-mtp-role="draft"]').click();
|
||
const draft = {
|
||
supervision: root.querySelector("[data-mtp-supervision]").textContent.trim(),
|
||
cost: root.querySelector("[data-mtp-main-cost]").textContent.trim(),
|
||
explain: root.querySelector("[data-mtp-explain]").textContent.trim(),
|
||
};
|
||
return { panel: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel, oneWay, dual, naive, mixed, off, draft };
|
||
})()`);
|
||
|
||
const rl = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
root.querySelector('[data-ds-tab="rl"]').click();
|
||
const read = () => ({
|
||
signal: root.querySelector("[data-signal-state]").textContent.trim(),
|
||
mean: root.querySelector("[data-reward-mean]").textContent.trim(),
|
||
std: root.querySelector("[data-reward-std]").textContent.trim(),
|
||
effective: root.querySelector("[data-effective]").textContent.trim(),
|
||
provenance: root.querySelector("[data-provenance]").textContent.trim(),
|
||
algorithm: root.querySelector("[data-algorithm-name]").textContent.trim(),
|
||
boundary: root.querySelector("[data-rl-boundary]").textContent.trim(),
|
||
weights: [...root.querySelectorAll("[data-advantage-rows] > div span:last-child")].map((node) => node.textContent.trim()),
|
||
});
|
||
const initial = read();
|
||
root.querySelector('[data-reward-preset="same"]').click();
|
||
const same = read();
|
||
root.querySelector('[data-reward-preset="longwrong"]').click();
|
||
root.querySelector('[data-rl-algorithm="dapo"]').click();
|
||
const dapo = read();
|
||
root.querySelector('[data-rl-algorithm="dr"]').click();
|
||
const dr = read();
|
||
root.querySelector('[data-r1-mode="r1"]').click();
|
||
const r1 = root.querySelector("[data-r1-mode-explain]").textContent.trim();
|
||
root.querySelector('[data-r1-mode="distill"]').click();
|
||
const distill = root.querySelector("[data-r1-mode-explain]").textContent.trim();
|
||
const first = root.querySelector('[data-ds-tab="capacity"]');
|
||
first.focus();
|
||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||
return {
|
||
initial, same, dapo, dr, r1, distill,
|
||
keyboardSelected: root.querySelector('[data-ds-tab][aria-selected="true"]').dataset.dsTab,
|
||
keyboardVisible: root.querySelector("[data-ds-panel]:not([hidden])").dataset.dsPanel,
|
||
};
|
||
})()`);
|
||
|
||
const artifactRoute = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
position: root.querySelector("[data-route-position]").textContent.trim(),
|
||
piece: root.querySelector("[data-route-piece]").textContent.trim(),
|
||
tokenId: root.querySelector("[data-route-token-id]").textContent.trim(),
|
||
weightSum: root.querySelector("[data-route-weight-sum]").textContent.trim(),
|
||
chosen: [...root.querySelectorAll("[data-route-experts] article")].map((node) => ({
|
||
expert: node.querySelector("b").textContent.trim(),
|
||
weight: node.querySelector("small").textContent.trim(),
|
||
})),
|
||
heatCells: root.querySelectorAll("[data-route-heatmap] > span").length,
|
||
selectedCells: root.querySelectorAll("[data-route-heatmap] > span.selected").length,
|
||
routes: root.querySelector("[data-route-count]").textContent.trim(),
|
||
used: root.querySelector("[data-route-used]").textContent.trim(),
|
||
cv: root.querySelector("[data-route-cv]").textContent.trim(),
|
||
effective: root.querySelector("[data-route-effective]").textContent.trim(),
|
||
});
|
||
const initial = read();
|
||
const layer = root.querySelector("[data-route-layer]");
|
||
const prompt = root.querySelector("[data-route-prompt]");
|
||
const token = root.querySelector("[data-route-token]");
|
||
layer.value = "4";
|
||
layer.dispatchEvent(new Event("change", { bubbles: true }));
|
||
prompt.value = "en_architecture";
|
||
prompt.dispatchEvent(new Event("change", { bubbles: true }));
|
||
token.value = String(token.options.length - 1);
|
||
token.dispatchEvent(new Event("change", { bubbles: true }));
|
||
const switched = read();
|
||
return { initial, switched, tokenOptions: token.options.length };
|
||
})()`);
|
||
|
||
const artifactLoad = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="load"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
used: root.querySelector("[data-load-used]").textContent.trim(),
|
||
zero: root.querySelector("[data-load-zero]").textContent.trim(),
|
||
cv: root.querySelector("[data-load-cv]").textContent.trim(),
|
||
gini: root.querySelector("[data-load-gini]").textContent.trim(),
|
||
effective: root.querySelector("[data-load-effective]").textContent.trim(),
|
||
rows: root.querySelectorAll("[data-load-rows] > div").length,
|
||
jaccards: root.querySelectorAll("[data-load-jaccard] > article").length,
|
||
});
|
||
const layer1 = read();
|
||
root.querySelector('[data-load-layer="2"]').click();
|
||
const layer2 = read();
|
||
root.querySelector('[data-load-layer="4"]').click();
|
||
const layer4 = read();
|
||
return { layer1, layer2, layer4 };
|
||
})()`);
|
||
|
||
const artifactCache = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="cache"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
latent: root.querySelector("[data-cache-latent-bytes]").textContent.trim(),
|
||
eager: root.querySelector("[data-cache-eager-bytes]").textContent.trim(),
|
||
ratio: root.querySelector("[data-cache-ratio]").textContent.trim(),
|
||
reduction: root.querySelector("[data-cache-reduction]").textContent.trim(),
|
||
});
|
||
const trace = read();
|
||
const context = root.querySelector("[data-cache-context]");
|
||
const batch = root.querySelector("[data-cache-batch]");
|
||
const layers = root.querySelector("[data-cache-layers]");
|
||
context.value = "1048576";
|
||
context.dispatchEvent(new Event("change", { bubbles: true }));
|
||
batch.value = "8";
|
||
batch.dispatchEvent(new Event("input", { bubbles: true }));
|
||
layers.value = "27";
|
||
layers.dispatchEvent(new Event("input", { bubbles: true }));
|
||
const million = read();
|
||
return { trace, million };
|
||
})()`);
|
||
|
||
const artifactAbsorb = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="absorb"]').click();
|
||
return {
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
algebra: root.querySelectorAll(".absorb-algebra article").length,
|
||
naive: root.querySelector(".absorb-cache-flow .naive header b").textContent.trim(),
|
||
absorbed: root.querySelector(".absorb-cache-flow .absorbed header b").textContent.trim(),
|
||
metrics: [...root.querySelectorAll(".absorb-metrics article b")].map((node) => node.textContent.trim()),
|
||
precisionRows: root.querySelectorAll(".precision-lens > div").length,
|
||
matrixRows: root.querySelectorAll(".kernel-matrix > div").length,
|
||
localUnsupported: root.querySelectorAll(".kernel-matrix i.no").length,
|
||
executionCards: root.querySelectorAll(".execution-split article").length,
|
||
boundary: root.querySelector('[data-artifact-panel="absorb"] .artifact-boundary').textContent.replaceAll(/\\s+/g, " ").trim(),
|
||
};
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-absorb-desktop.png");
|
||
|
||
const artifactCorpus = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="corpus"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
rows: root.querySelectorAll("[data-corpus-domain-rows] > div").length,
|
||
tokens: [...root.querySelectorAll("[data-corpus-domain-rows] > div > span:first-child > small")].map((node) => node.textContent.trim()),
|
||
heatRows: root.querySelectorAll("[data-corpus-heatmap] > div").length,
|
||
heatCells: root.querySelectorAll("[data-corpus-heatmap] > div > span").length,
|
||
jsdCells: root.querySelectorAll("[data-corpus-jsd] > *").length,
|
||
highest: root.querySelector("[data-corpus-highest-cv]").textContent.trim(),
|
||
largest: root.querySelector("[data-corpus-largest-jsd]").textContent.trim(),
|
||
heatTitle: root.querySelector("[data-corpus-heat-title]").textContent.trim(),
|
||
cohortTitle: root.querySelector("[data-corpus-cohort-title]").textContent.trim(),
|
||
exact: root.querySelector(".corpus-ledger .exact b").textContent.trim(),
|
||
modeNote: root.querySelector("[data-corpus-mode-note]").textContent.trim(),
|
||
deltaCards: root.querySelectorAll("[data-length-delta-grid] > article").length,
|
||
lengthJsd: root.querySelector("[data-length-jsd]").textContent.trim(),
|
||
lengthLargest: root.querySelector("[data-length-largest]").textContent.trim(),
|
||
});
|
||
const layer1 = read();
|
||
root.querySelector('[data-corpus-layer="4"]').click();
|
||
const layer4 = read();
|
||
root.querySelector('[data-corpus-cohort="matched16"]').click();
|
||
root.querySelector('[data-corpus-layer="2"]').click();
|
||
const matched16 = read();
|
||
root.querySelector('[data-corpus-cohort="matched24"]').click();
|
||
const matched24 = read();
|
||
root.querySelector('[data-corpus-mode="token_weighted"]').click();
|
||
const tokenWeighted = read();
|
||
return { layer1, layer4, matched16, matched24, tokenWeighted };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-corpus-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".length-sensitivity").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-length-sensitivity-desktop.png");
|
||
|
||
const artifactTemplate = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="template"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
domainCards: root.querySelectorAll("[data-template-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-template-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector("span").textContent.trim(),
|
||
values: node.querySelector("b").textContent.trim(),
|
||
delta: node.querySelector("strong").textContent.trim(),
|
||
className: node.querySelector("strong").className,
|
||
ci: node.querySelector("p").textContent.trim(),
|
||
distance: node.querySelector("small").textContent.trim(),
|
||
stability: node.querySelector("em").textContent.trim(),
|
||
})),
|
||
prefixExact: root.querySelector("[data-template-prefix-exact]").textContent.trim(),
|
||
contentZero: root.querySelector("[data-template-content-zero]").textContent.trim(),
|
||
suffixTv: root.querySelector("[data-template-suffix-tv]").textContent.trim(),
|
||
note: root.querySelector("[data-template-note]").textContent.trim(),
|
||
depthRows: root.querySelectorAll("[data-template-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-template-depth-map] > div > span").length,
|
||
exact: root.querySelector(".template-ledger .exact b").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-template-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-template-scope][aria-pressed="true"]').dataset.templateScope,
|
||
activeMode: root.querySelector('[data-template-mode][aria-pressed="true"]').dataset.templateMode,
|
||
});
|
||
const layer1Content = read();
|
||
root.querySelector('[data-template-layer="6"]').click();
|
||
const layer6Content = read();
|
||
root.querySelector('[data-template-scope="full_input"]').click();
|
||
const layer6Full = read();
|
||
root.querySelector('[data-template-mode="token_weighted"]').click();
|
||
const layer6FullToken = read();
|
||
root.querySelector('[data-template-scope="content_only"]').click();
|
||
root.querySelector('[data-template-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-template-layer="2"]').click();
|
||
const layer2Content = read();
|
||
return { layer1Content, layer6Content, layer6Full, layer6FullToken, layer2Content };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-template-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".template-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-template-results-desktop.png");
|
||
|
||
const artifactHistory = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="history"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
matrixRows: root.querySelectorAll(".history-row").length,
|
||
matrixCells: root.querySelectorAll(".history-row > article").length,
|
||
domainCards: root.querySelectorAll("[data-history-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-history-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector("span").textContent.trim(),
|
||
cells: [...node.querySelectorAll(".history-cell-values i")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("b").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector("strong").textContent.trim(),
|
||
className: node.querySelector("strong").className,
|
||
ci: node.querySelector("p").textContent.trim(),
|
||
allEffects: node.querySelector(":scope > small").textContent.trim(),
|
||
edges: node.querySelector("em").textContent.trim(),
|
||
})),
|
||
bufferSummary: [...root.querySelectorAll('[data-artifact-panel="history"] .history-buffer-summary article b')].map((node) => node.textContent.trim()),
|
||
bufferCards: [...root.querySelectorAll("[data-history-buffer-grid] > article")].map((node) => ({
|
||
label: node.querySelector("span").textContent.trim(),
|
||
tv: node.querySelector("b").textContent.trim(),
|
||
reduction: node.querySelector("strong").textContent.trim(),
|
||
stability: node.querySelector("p").textContent.trim(),
|
||
})),
|
||
depthRows: root.querySelectorAll("[data-history-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-history-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-history-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".history-ledger .exact b").textContent.trim(),
|
||
note: root.querySelector("[data-history-note]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-history-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-history-scope][aria-pressed="true"]').dataset.historyScope,
|
||
activeMode: root.querySelector('[data-history-mode][aria-pressed="true"]').dataset.historyMode,
|
||
activeEffect: root.querySelector('[data-history-effect][aria-pressed="true"]').dataset.historyEffect,
|
||
});
|
||
const layer1Interaction = read();
|
||
root.querySelector('[data-history-layer="4"]').click();
|
||
const layer4Interaction = read();
|
||
root.querySelector('[data-history-effect="system_main"]').click();
|
||
const layer4System = read();
|
||
root.querySelector('[data-history-scope="full_input"]').click();
|
||
const layer4FullSystem = read();
|
||
root.querySelector('[data-history-mode="token_weighted"]').click();
|
||
const layer4FullToken = read();
|
||
root.querySelector('[data-history-scope="target_content"]').click();
|
||
root.querySelector('[data-history-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-history-effect="interaction"]').click();
|
||
return { layer1Interaction, layer4Interaction, layer4System, layer4FullSystem, layer4FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-history-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".history-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-history-results-desktop.png");
|
||
|
||
const artifactDistance = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="distance"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
matrixRows: root.querySelectorAll(".distance-row:not(.head)").length,
|
||
matrixCells: root.querySelectorAll(".distance-row:not(.head) > article").length,
|
||
domainCards: root.querySelectorAll("[data-distance-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-distance-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector(":scope > span").textContent.trim(),
|
||
values: [...node.querySelectorAll(".distance-tv-ladder i")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("b").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector("strong").textContent.trim(),
|
||
className: node.querySelector("strong").className,
|
||
ci: node.querySelector(":scope > p").textContent.trim(),
|
||
stability: node.querySelector(":scope > small").textContent.trim(),
|
||
lexical: node.querySelector(":scope > em").textContent.trim(),
|
||
cv: node.querySelector(":scope > u").textContent.trim(),
|
||
})),
|
||
summary: [...root.querySelectorAll(".distance-summary article b")].map((node) => node.textContent.trim()),
|
||
depthRows: root.querySelectorAll("[data-distance-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-distance-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-distance-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".distance-ledger .exact b").textContent.trim(),
|
||
note: root.querySelector("[data-distance-note]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-distance-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-distance-scope][aria-pressed="true"]').dataset.distanceScope,
|
||
activeMode: root.querySelector('[data-distance-mode][aria-pressed="true"]').dataset.distanceMode,
|
||
activeContrast: root.querySelector('[data-distance-contrast][aria-pressed="true"]').dataset.distanceContrast,
|
||
});
|
||
const layer1Filler = read();
|
||
root.querySelector('[data-distance-layer="4"]').click();
|
||
const layer4Filler = read();
|
||
root.querySelector('[data-distance-contrast="demo_minus_filler"]').click();
|
||
const layer4Demo = read();
|
||
root.querySelector('[data-distance-scope="full_input"]').click();
|
||
const layer4FullDemo = read();
|
||
root.querySelector('[data-distance-mode="token_weighted"]').click();
|
||
const layer4FullToken = read();
|
||
root.querySelector('[data-distance-scope="target_content"]').click();
|
||
root.querySelector('[data-distance-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-distance-contrast="filler_minus_none"]').click();
|
||
return { layer1Filler, layer4Filler, layer4Demo, layer4FullDemo, layer4FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-distance-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".distance-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-distance-results-desktop.png");
|
||
|
||
const artifactBoundary = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="boundary"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
tokenCards: root.querySelectorAll(".boundary-token-grid > article").length,
|
||
domainCards: root.querySelectorAll("[data-boundary-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-boundary-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector(":scope > span").textContent.trim(),
|
||
values: [...node.querySelectorAll(".boundary-tv-ladder > b")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("strong").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector(":scope > strong").textContent.trim(),
|
||
className: node.querySelector(":scope > strong").className,
|
||
ci: node.querySelector(":scope > p").textContent.trim(),
|
||
stability: node.querySelector(":scope > small").textContent.trim(),
|
||
substitution: node.querySelector(":scope > em").textContent.trim(),
|
||
interaction: node.querySelector(":scope > u").textContent.trim(),
|
||
cv: node.querySelector(":scope > i").textContent.trim(),
|
||
})),
|
||
summary: [...root.querySelectorAll('[data-artifact-panel="boundary"] .boundary-summary article b')].map((node) => node.textContent.trim()),
|
||
depthRows: root.querySelectorAll("[data-boundary-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-boundary-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-boundary-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".boundary-ledger .exact b").textContent.trim(),
|
||
note: root.querySelector("[data-boundary-note]").textContent.trim(),
|
||
trackToken: root.querySelector("[data-boundary-track-token]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-boundary-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-boundary-scope][aria-pressed="true"]').dataset.boundaryScope,
|
||
activeMode: root.querySelector('[data-boundary-mode][aria-pressed="true"]').dataset.boundaryMode,
|
||
activeContrast: root.querySelector('[data-boundary-contrast][aria-pressed="true"]').dataset.boundaryContrast,
|
||
});
|
||
const layer1X = read();
|
||
root.querySelector('[data-boundary-layer="4"]').click();
|
||
const layer4X = read();
|
||
root.querySelector('[data-boundary-contrast="period_minus_eos"]').click();
|
||
const layer4Period = read();
|
||
root.querySelector('[data-boundary-contrast="newline_minus_eos"]').click();
|
||
const layer4Newline = read();
|
||
root.querySelector('[data-boundary-scope="full_input"]').click();
|
||
const layer4Full = read();
|
||
root.querySelector('[data-boundary-mode="token_weighted"]').click();
|
||
const layer4FullToken = read();
|
||
root.querySelector('[data-boundary-layer="1"]').click();
|
||
root.querySelector('[data-boundary-scope="target_content"]').click();
|
||
root.querySelector('[data-boundary-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-boundary-contrast="x_minus_eos"]').click();
|
||
return { layer1X, layer4X, layer4Period, layer4Newline, layer4Full, layer4FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-boundary-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".boundary-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-boundary-results-desktop.png");
|
||
|
||
const artifactRole = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="role"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
levelCards: root.querySelectorAll(".role-level-grid > article").length,
|
||
domainCards: root.querySelectorAll("[data-role-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-role-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector(":scope > span").textContent.trim(),
|
||
values: [...node.querySelectorAll(".role-tv-ladder > b")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("strong").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector(":scope > strong").textContent.trim(),
|
||
className: node.querySelector(":scope > strong").className,
|
||
ci: node.querySelector(":scope > p").textContent.trim(),
|
||
stability: node.querySelector(":scope > small").textContent.trim(),
|
||
direct: node.querySelector(":scope > em").textContent.trim(),
|
||
interaction: node.querySelector(":scope > u").textContent.trim(),
|
||
cv: node.querySelector(":scope > i").textContent.trim(),
|
||
})),
|
||
summary: [...root.querySelectorAll('[data-artifact-panel="role"] .role-summary article b')].map((node) => node.textContent.trim()),
|
||
depthRows: root.querySelectorAll("[data-role-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-role-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-role-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".role-ledger .exact b").textContent.trim(),
|
||
causalCards: root.querySelectorAll(".role-causal-ledger > article").length,
|
||
batchCells: root.querySelectorAll('[data-artifact-panel="role"] .role-batch-audit > div:last-child > span').length,
|
||
batchValues: [...root.querySelectorAll('[data-artifact-panel="role"] .role-batch-audit > div:last-child > span i')].map((node) => node.textContent.trim()),
|
||
note: root.querySelector("[data-role-note]").textContent.trim(),
|
||
targetHead: root.querySelector("[data-role-target-head]").textContent.trim(),
|
||
suffixHead: root.querySelector("[data-role-suffix-head]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-role-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-role-scope][aria-pressed="true"]').dataset.roleScope,
|
||
activeMode: root.querySelector('[data-role-mode][aria-pressed="true"]').dataset.roleMode,
|
||
activeContrast: root.querySelector('[data-role-contrast][aria-pressed="true"]').dataset.roleContrast,
|
||
});
|
||
const layer1Assistant = read();
|
||
root.querySelector('[data-role-layer="5"]').click();
|
||
root.querySelector('[data-role-contrast="target_x_minus_official"]').click();
|
||
const layer5X = read();
|
||
root.querySelector('[data-role-contrast="suffix_user_minus_official"]').click();
|
||
const layer5Suffix = read();
|
||
root.querySelector('[data-role-scope="full_input"]').click();
|
||
const layer5FullSuffix = read();
|
||
root.querySelector('[data-role-mode="token_weighted"]').click();
|
||
const layer5FullToken = read();
|
||
root.querySelector('[data-role-layer="1"]').click();
|
||
root.querySelector('[data-role-scope="target_content"]').click();
|
||
root.querySelector('[data-role-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-role-contrast="target_assistant_minus_official"]').click();
|
||
return { layer1Assistant, layer5X, layer5Suffix, layer5FullSuffix, layer5FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".role-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-results-desktop.png");
|
||
|
||
const artifactSpecial = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="special"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
tokenCards: root.querySelectorAll(".special-token-grid > article").length,
|
||
domainCards: root.querySelectorAll("[data-special-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-special-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector(":scope > span").textContent.trim(),
|
||
values: [...node.querySelectorAll(".special-tv-ladder > b")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("strong").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector(":scope > strong").textContent.trim(),
|
||
className: node.querySelector(":scope > strong").className,
|
||
ci: node.querySelector(":scope > p").textContent.trim(),
|
||
detail: node.querySelector(":scope > em").textContent.trim(),
|
||
stability: node.querySelector(":scope > small").textContent.trim(),
|
||
cv: node.querySelector(":scope > i").textContent.trim(),
|
||
})),
|
||
summary: [...root.querySelectorAll('[data-artifact-panel="special"] .special-summary article b')].map((node) => node.textContent.trim()),
|
||
depthRows: root.querySelectorAll("[data-special-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-special-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-special-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".special-ledger .exact b").textContent.trim(),
|
||
scopeCards: root.querySelectorAll('[data-artifact-panel="special"] .special-scope-ledger > article').length,
|
||
batchCells: root.querySelectorAll(".special-batch-audit > div:last-child > span").length,
|
||
batchValues: [...root.querySelectorAll(".special-batch-audit > div:last-child > span i")].map((node) => node.textContent.trim()),
|
||
note: root.querySelector("[data-special-note]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-special-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-special-scope][aria-pressed="true"]').dataset.specialScope,
|
||
activeMode: root.querySelector('[data-special-mode][aria-pressed="true"]').dataset.specialMode,
|
||
activeContrast: root.querySelector('[data-special-contrast][aria-pressed="true"]').dataset.specialContrast,
|
||
});
|
||
const layer1Bos = read();
|
||
root.querySelector('[data-special-layer="4"]').click();
|
||
root.querySelector('[data-special-contrast="x_minus_eos"]').click();
|
||
const layer4X = read();
|
||
root.querySelector('[data-special-contrast="period_minus_eos"]').click();
|
||
const layer4Period = read();
|
||
root.querySelector('[data-special-contrast="family"]').click();
|
||
const layer4Family = read();
|
||
root.querySelector('[data-special-scope="full_input"]').click();
|
||
const layer4FullFamily = read();
|
||
root.querySelector('[data-special-mode="token_weighted"]').click();
|
||
const layer4FullToken = read();
|
||
root.querySelector('[data-special-layer="1"]').click();
|
||
root.querySelector('[data-special-scope="target_content"]').click();
|
||
root.querySelector('[data-special-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-special-contrast="bos_minus_eos"]').click();
|
||
return { layer1Bos, layer4X, layer4Period, layer4Family, layer4FullFamily, layer4FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-special-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".special-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-special-results-desktop.png");
|
||
|
||
const artifactRoleBlock = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="role-block"]').click();
|
||
const read = () => ({
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
matrixCards: root.querySelectorAll(".role-block-matrix > article").length,
|
||
domainCards: root.querySelectorAll("[data-role-block-domain-grid] > article").length,
|
||
domains: [...root.querySelectorAll("[data-role-block-domain-grid] > article")].map((node) => ({
|
||
label: node.querySelector(":scope > span").textContent.trim(),
|
||
values: [...node.querySelectorAll(".role-block-tv-ladder > b")].map((cell) => ({
|
||
name: cell.querySelector("small").textContent.trim(),
|
||
value: cell.querySelector("strong").textContent.trim(),
|
||
})),
|
||
effect: node.querySelector(":scope > strong").textContent.trim(),
|
||
className: node.querySelector(":scope > strong").className,
|
||
ci: node.querySelector(":scope > p").textContent.trim(),
|
||
direct: node.querySelector(":scope > em").textContent.trim(),
|
||
dependency: node.querySelector(":scope > u").textContent.trim(),
|
||
stability: node.querySelector(":scope > small").textContent.trim(),
|
||
cv: node.querySelector(":scope > i").textContent.trim(),
|
||
})),
|
||
summary: [...root.querySelectorAll('[data-artifact-panel="role-block"] .role-block-summary article b')].map((node) => node.textContent.trim()),
|
||
directCards: root.querySelectorAll(".role-block-direct > article").length,
|
||
depthRows: root.querySelectorAll("[data-role-block-depth-map] > div").length,
|
||
depthCells: root.querySelectorAll("[data-role-block-depth-map] > div > span").length,
|
||
depthTitle: root.querySelector("[data-role-block-depth-title]").textContent.trim(),
|
||
exact: root.querySelector(".role-block-ledger .exact b").textContent.trim(),
|
||
boundaryCards: root.querySelectorAll(".role-block-boundaries > article").length,
|
||
batchCells: root.querySelectorAll(".role-block-batch-audit > div:last-child > span").length,
|
||
batchValues: [...root.querySelectorAll(".role-block-batch-audit > div:last-child > span i")].map((node) => node.textContent.trim()),
|
||
note: root.querySelector("[data-role-block-note]").textContent.trim(),
|
||
activeLayer: root.querySelector("[data-role-block-layer].active").textContent.trim(),
|
||
activeScope: root.querySelector('[data-role-block-scope][aria-pressed="true"]').dataset.roleBlockScope,
|
||
activeMode: root.querySelector('[data-role-block-mode][aria-pressed="true"]').dataset.roleBlockMode,
|
||
activeEffect: root.querySelector('[data-role-block-effect][aria-pressed="true"]').dataset.roleBlockEffect,
|
||
});
|
||
const layer1Head = read();
|
||
root.querySelector('[data-role-block-layer="4"]').click();
|
||
root.querySelector('[data-role-block-effect="delimiter_main"]').click();
|
||
const layer4Delimiter = read();
|
||
root.querySelector('[data-role-block-layer="5"]').click();
|
||
root.querySelector('[data-role-block-effect="head_by_delimiter"]').click();
|
||
const layer5Interaction = read();
|
||
root.querySelector('[data-role-block-scope="full_input"]').click();
|
||
const layer5FullInteraction = read();
|
||
root.querySelector('[data-role-block-mode="token_weighted"]').click();
|
||
const layer5FullToken = read();
|
||
root.querySelector('[data-role-block-layer="1"]').click();
|
||
root.querySelector('[data-role-block-scope="target_content"]').click();
|
||
root.querySelector('[data-role-block-mode="prompt_balanced"]').click();
|
||
root.querySelector('[data-role-block-effect="head_main"]').click();
|
||
return { layer1Head, layer4Delimiter, layer5Interaction, layer5FullInteraction, layer5FullToken, restored: read() };
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-block-desktop.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".role-block-domain-grid").scrollIntoView({ block: "center", behavior: "instant" });
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-block-results-desktop.png");
|
||
|
||
const artifactEvidence = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-dsv2-lab]");
|
||
root.querySelector('[data-artifact-tab="evidence"]').click();
|
||
const result = {
|
||
panel: root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel,
|
||
layers: root.querySelectorAll(".layer-evidence > span").length,
|
||
executed: root.querySelectorAll(".layer-evidence > span.executed").length,
|
||
split: root.querySelectorAll(".layer-evidence > span.split").length,
|
||
unloaded: root.querySelectorAll(".layer-evidence > span.unloaded").length,
|
||
exact: root.querySelector(".repro-gate strong").textContent.trim(),
|
||
dependency: root.querySelector(".dependency-split").textContent.replaceAll(/\\s+/g, " ").trim(),
|
||
boundary: root.querySelector('[data-artifact-panel="evidence"] .artifact-boundary').textContent.replaceAll(/\\s+/g, " ").trim(),
|
||
};
|
||
const first = root.querySelector('[data-artifact-tab="route"]');
|
||
first.focus();
|
||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||
result.keyboardSelected = root.querySelector('[data-artifact-tab][aria-selected="true"]').dataset.artifactTab;
|
||
result.keyboardVisible = root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel;
|
||
return result;
|
||
})()`);
|
||
|
||
await evaluate(`(() => {
|
||
document.querySelector("[data-dsv2-lab]").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-artifact-desktop.png");
|
||
|
||
const behavior = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-behavior-lab]");
|
||
const readPair = () => ({
|
||
panel: root.querySelector("[data-behavior-panel]:not([hidden])").dataset.behaviorPanel,
|
||
source: root.querySelector("[data-behavior-source-id]").textContent.trim(),
|
||
domain: root.querySelector("[data-behavior-domain]").textContent.trim(),
|
||
exact: root.querySelector("[data-behavior-exact]").textContent.trim(),
|
||
prefix: root.querySelector("[data-behavior-prefix]").textContent.trim(),
|
||
edit: root.querySelector("[data-behavior-edit]").textContent.trim(),
|
||
similarity: root.querySelector("[data-behavior-similarity]").textContent.trim(),
|
||
conditions: [...root.querySelectorAll("[data-output-condition]")].map((node) => node.textContent.trim()),
|
||
statuses: [...root.querySelectorAll("[data-output-status]")].map((node) => node.textContent.trim()),
|
||
outputCharacters: [...root.querySelectorAll("[data-output-text]")].map((node) => node.textContent.length),
|
||
});
|
||
const initial = readPair();
|
||
const source = root.querySelector("[data-behavior-source]");
|
||
const edge = root.querySelector("[data-behavior-edge]");
|
||
source.value = "gsm8k/test/1069";
|
||
source.dispatchEvent(new Event("change", { bubbles: true }));
|
||
edge.value = "x_at_s1";
|
||
edge.dispatchEvent(new Event("change", { bubbles: true }));
|
||
const switched = readPair();
|
||
root.querySelector('[data-behavior-tab="map"]').click();
|
||
const map = root.querySelector("[data-behavior-map-domain]");
|
||
map.value = "math";
|
||
map.dispatchEvent(new Event("change", { bubbles: true }));
|
||
const mathMap = {
|
||
panel: root.querySelector("[data-behavior-panel]:not([hidden])").dataset.behaviorPanel,
|
||
rows: root.querySelectorAll("[data-behavior-map-edge]").length,
|
||
note: root.querySelector("[data-behavior-map-note]").textContent.trim(),
|
||
firstExact: root.querySelector("[data-behavior-map-edge] [data-map-exact]").textContent.trim(),
|
||
firstSimilarity: root.querySelector("[data-behavior-map-edge] [data-map-similarity]").textContent.trim(),
|
||
};
|
||
root.querySelector('[data-behavior-tab="execution"]').click();
|
||
const execution = {
|
||
panel: root.querySelector("[data-behavior-panel]:not([hidden])").dataset.behaviorPanel,
|
||
layers: root.querySelectorAll(".layer-device-map > span").length,
|
||
gpu: root.querySelectorAll(".layer-device-map > span.gpu").length,
|
||
cpu: root.querySelectorAll(".layer-device-map > span.cpu").length,
|
||
runtimeCards: root.querySelectorAll(".runtime-grid > article").length,
|
||
};
|
||
root.querySelector('[data-behavior-tab="boundary"]').click();
|
||
const boundary = {
|
||
panel: root.querySelector("[data-behavior-panel]:not([hidden])").dataset.behaviorPanel,
|
||
ladder: root.querySelectorAll(".evidence-ladder > article").length,
|
||
tokenCards: root.querySelectorAll(".token-contract > article").length,
|
||
reproCards: root.querySelectorAll(".repro-grid > article").length,
|
||
links: root.querySelectorAll(".artifact-links > a").length,
|
||
forbidden: root.querySelector(".forbidden-claims").textContent.replaceAll(/\\s+/g, " ").trim(),
|
||
};
|
||
const first = root.querySelector('[data-behavior-tab="pair"]');
|
||
first.focus();
|
||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||
return {
|
||
initial,
|
||
switched,
|
||
mathMap,
|
||
execution,
|
||
boundary,
|
||
keyboardSelected: root.querySelector('[data-behavior-tab][aria-selected="true"]').dataset.behaviorTab,
|
||
keyboardVisible: root.querySelector("[data-behavior-panel]:not([hidden])").dataset.behaviorPanel,
|
||
};
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
const root = document.querySelector("[data-behavior-lab]");
|
||
root.querySelector('[data-behavior-tab="pair"]').click();
|
||
root.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-behavior-desktop.png");
|
||
|
||
const completionDepth = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-completion-depth-lab]");
|
||
const initial = {
|
||
panel: root.querySelector("[data-cd-panel]:not([hidden])").dataset.cdPanel,
|
||
conditionRows: root.querySelectorAll("[data-completion-condition]").length,
|
||
incompleteRows: root.querySelectorAll(".incomplete-ledger article").length,
|
||
prefixCards: root.querySelectorAll(".prefix-gate > article").length,
|
||
};
|
||
root.querySelector('[data-cd-tab="tasks"]').click();
|
||
const condition = root.querySelector("[data-task-condition]");
|
||
condition.value = "s1_eos";
|
||
condition.dispatchEvent(new Event("change", { bubbles: true }));
|
||
const tasks = {
|
||
panel: root.querySelector("[data-cd-panel]:not([hidden])").dataset.cdPanel,
|
||
mathCards: root.querySelectorAll("[data-math-task-grid] > article").length,
|
||
codeCards: root.querySelectorAll("[data-code-task-grid] > article").length,
|
||
mathTotal: root.querySelector("[data-math-condition-total]").textContent.trim(),
|
||
codeTotal: root.querySelector("[data-code-condition-total]").textContent.trim(),
|
||
sandboxSteps: root.querySelectorAll(".sandbox-flow > article").length,
|
||
};
|
||
root.querySelector('[data-cd-tab="hidden"]').click();
|
||
const hiddenEdge = root.querySelector("[data-hidden-edge]");
|
||
const hiddenDomain = root.querySelector("[data-hidden-domain]");
|
||
const hiddenMetric = root.querySelector("[data-hidden-metric]");
|
||
hiddenEdge.value = "period_at_s1";
|
||
hiddenEdge.dispatchEvent(new Event("change", { bubbles: true }));
|
||
hiddenDomain.value = "code";
|
||
hiddenDomain.dispatchEvent(new Event("change", { bubbles: true }));
|
||
hiddenMetric.value = "relative";
|
||
hiddenMetric.dispatchEvent(new Event("change", { bubbles: true }));
|
||
root.querySelector('[data-hidden-stage="8"]').click();
|
||
const hidden = {
|
||
panel: root.querySelector("[data-cd-panel]:not([hidden])").dataset.cdPanel,
|
||
stages: root.querySelectorAll("[data-hidden-stage]").length,
|
||
selected: root.querySelector("[data-hidden-stage-name]").textContent.trim(),
|
||
cosine: root.querySelector("[data-hidden-cosine]").textContent.trim(),
|
||
relative: root.querySelector("[data-hidden-relative]").textContent.trim(),
|
||
exact: root.querySelector("[data-hidden-exact]").textContent.trim(),
|
||
points: root.querySelector("[data-hidden-line]").getAttribute("points").split(" ").length,
|
||
};
|
||
root.querySelector('[data-cd-tab="router"]').click();
|
||
const routerEdge = root.querySelector("[data-router-edge]");
|
||
const routerDomain = root.querySelector("[data-router-domain]");
|
||
routerEdge.value = "period_at_s1";
|
||
routerEdge.dispatchEvent(new Event("change", { bubbles: true }));
|
||
routerDomain.value = "math";
|
||
routerDomain.dispatchEvent(new Event("change", { bubbles: true }));
|
||
root.querySelector('[data-router-layer="23"]').click();
|
||
const router = {
|
||
panel: root.querySelector("[data-cd-panel]:not([hidden])").dataset.cdPanel,
|
||
layers: root.querySelectorAll("[data-router-layer]").length,
|
||
selected: root.querySelector("[data-router-layer-name]").textContent.trim(),
|
||
ordered: root.querySelector("[data-router-ordered]").textContent.trim(),
|
||
setExact: root.querySelector("[data-router-set]").textContent.trim(),
|
||
tv: root.querySelector("[data-router-tv]").textContent.trim(),
|
||
points: root.querySelector("[data-router-line]").getAttribute("points").split(" ").length,
|
||
reproCards: root.querySelectorAll(".repro-proof > article").length,
|
||
links: root.querySelectorAll('[data-cd-panel="router"] .artifact-links > a').length,
|
||
};
|
||
const first = root.querySelector('[data-cd-tab="completion"]');
|
||
first.focus();
|
||
first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
|
||
return {
|
||
initial,
|
||
tasks,
|
||
hidden,
|
||
router,
|
||
keyboardSelected: root.querySelector('[data-cd-tab][aria-selected="true"]').dataset.cdTab,
|
||
keyboardVisible: root.querySelector("[data-cd-panel]:not([hidden])").dataset.cdPanel,
|
||
};
|
||
})()`);
|
||
await evaluate(`(() => {
|
||
const root = document.querySelector("[data-completion-depth-lab]");
|
||
root.querySelector('[data-cd-tab="hidden"]').click();
|
||
root.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-completion-depth-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() === "DeepSeek");
|
||
button?.click();
|
||
return {
|
||
total: document.querySelectorAll("[data-paper]").length,
|
||
visible: document.querySelectorAll("[data-paper]:not([hidden])").length,
|
||
hasFilter: Boolean(button),
|
||
hasCoder: document.body.textContent.includes("DeepSeek-Coder-V2"),
|
||
hasEngram: document.body.textContent.includes("Conditional Memory via Scalable Lookup"),
|
||
};
|
||
})()`);
|
||
|
||
await command("Emulation.setDeviceMetricsOverride", {
|
||
width: 390,
|
||
height: 844,
|
||
deviceScaleFactor: 1,
|
||
mobile: true,
|
||
});
|
||
await navigate("/deepseek/");
|
||
const mobile = await evaluate(`(() => {
|
||
const root = document.querySelector("[data-deepseek-lab]");
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
const behavior = document.querySelector("[data-behavior-lab]");
|
||
const completionDepth = document.querySelector("[data-completion-depth-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-ds-tab]").length,
|
||
artifactTabs: artifact.querySelectorAll("[data-artifact-tab]").length,
|
||
behaviorTabs: behavior.querySelectorAll("[data-behavior-tab]").length,
|
||
behaviorSources: behavior.querySelectorAll("[data-behavior-source] option").length,
|
||
behaviorEdges: behavior.querySelectorAll("[data-behavior-map-edge]").length,
|
||
behaviorDeviceCells: behavior.querySelectorAll(".layer-device-map > span").length,
|
||
completionDepthTabs: completionDepth.querySelectorAll("[data-cd-tab]").length,
|
||
completionDepthHiddenStages: completionDepth.querySelectorAll("[data-hidden-stage]").length,
|
||
completionDepthRouterLayers: completionDepth.querySelectorAll("[data-router-layer]").length,
|
||
artifactHeatCells: artifact.querySelectorAll("[data-route-heatmap] > span").length,
|
||
corpusCohorts: artifact.querySelectorAll("[data-corpus-cohort]").length,
|
||
lengthDeltaCards: artifact.querySelectorAll("[data-length-delta-grid] > article").length,
|
||
templateLayers: artifact.querySelectorAll("[data-template-layer]").length,
|
||
templateScopes: artifact.querySelectorAll("[data-template-scope]").length,
|
||
templateModes: artifact.querySelectorAll("[data-template-mode]").length,
|
||
templateDomainCards: artifact.querySelectorAll("[data-template-domain-grid] > article").length,
|
||
templateDepthCells: artifact.querySelectorAll("[data-template-depth-map] > div > span").length,
|
||
historyLayers: artifact.querySelectorAll("[data-history-layer]").length,
|
||
historyScopes: artifact.querySelectorAll("[data-history-scope]").length,
|
||
historyModes: artifact.querySelectorAll("[data-history-mode]").length,
|
||
historyEffects: artifact.querySelectorAll("[data-history-effect]").length,
|
||
historyDomainCards: artifact.querySelectorAll("[data-history-domain-grid] > article").length,
|
||
historyDepthCells: artifact.querySelectorAll("[data-history-depth-map] > div > span").length,
|
||
distanceLayers: artifact.querySelectorAll("[data-distance-layer]").length,
|
||
distanceScopes: artifact.querySelectorAll("[data-distance-scope]").length,
|
||
distanceModes: artifact.querySelectorAll("[data-distance-mode]").length,
|
||
distanceContrasts: artifact.querySelectorAll("[data-distance-contrast]").length,
|
||
distanceDomainCards: artifact.querySelectorAll("[data-distance-domain-grid] > article").length,
|
||
distanceDepthCells: artifact.querySelectorAll("[data-distance-depth-map] > div > span").length,
|
||
boundaryLayers: artifact.querySelectorAll("[data-boundary-layer]").length,
|
||
boundaryScopes: artifact.querySelectorAll("[data-boundary-scope]").length,
|
||
boundaryModes: artifact.querySelectorAll("[data-boundary-mode]").length,
|
||
boundaryContrasts: artifact.querySelectorAll("[data-boundary-contrast]").length,
|
||
boundaryTokenCards: artifact.querySelectorAll(".boundary-token-grid > article").length,
|
||
boundaryDomainCards: artifact.querySelectorAll("[data-boundary-domain-grid] > article").length,
|
||
boundaryDepthCells: artifact.querySelectorAll("[data-boundary-depth-map] > div > span").length,
|
||
roleLayers: artifact.querySelectorAll("[data-role-layer]").length,
|
||
roleScopes: artifact.querySelectorAll("[data-role-scope]").length,
|
||
roleModes: artifact.querySelectorAll("[data-role-mode]").length,
|
||
roleContrasts: artifact.querySelectorAll("[data-role-contrast]").length,
|
||
roleLevelCards: artifact.querySelectorAll(".role-level-grid > article").length,
|
||
roleDomainCards: artifact.querySelectorAll("[data-role-domain-grid] > article").length,
|
||
roleDepthCells: artifact.querySelectorAll("[data-role-depth-map] > div > span").length,
|
||
specialLayers: artifact.querySelectorAll("[data-special-layer]").length,
|
||
specialScopes: artifact.querySelectorAll("[data-special-scope]").length,
|
||
specialModes: artifact.querySelectorAll("[data-special-mode]").length,
|
||
specialContrasts: artifact.querySelectorAll("[data-special-contrast]").length,
|
||
specialTokenCards: artifact.querySelectorAll(".special-token-grid > article").length,
|
||
specialDomainCards: artifact.querySelectorAll("[data-special-domain-grid] > article").length,
|
||
specialDepthCells: artifact.querySelectorAll("[data-special-depth-map] > div > span").length,
|
||
roleBlockLayers: artifact.querySelectorAll("[data-role-block-layer]").length,
|
||
roleBlockScopes: artifact.querySelectorAll("[data-role-block-scope]").length,
|
||
roleBlockModes: artifact.querySelectorAll("[data-role-block-mode]").length,
|
||
roleBlockEffects: artifact.querySelectorAll("[data-role-block-effect]").length,
|
||
roleBlockMatrixCards: artifact.querySelectorAll(".role-block-matrix > article").length,
|
||
roleBlockDomainCards: artifact.querySelectorAll("[data-role-block-domain-grid] > article").length,
|
||
roleBlockDepthCells: artifact.querySelectorAll("[data-role-block-depth-map] > div > span").length,
|
||
offenders: [...document.querySelectorAll("body *")]
|
||
.filter((node) => !node.closest(".paper-chain, .advantage-table, .precision-table, .mapping-table, [data-deepseek-lab], [data-dsv2-lab], [data-behavior-lab], [data-completion-depth-lab]"))
|
||
.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 evaluate(`(() => {
|
||
document.querySelector("#menu-toggle")?.click();
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="corpus"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -82);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-corpus-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".length-sensitivity").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-length-sensitivity-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="template"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-template-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".template-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-template-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="history"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-history-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".history-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-history-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="distance"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-distance-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".distance-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-distance-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="boundary"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-boundary-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".boundary-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-boundary-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="role"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".role-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="special"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-special-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".special-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-special-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const artifact = document.querySelector("[data-dsv2-lab]");
|
||
artifact.querySelector('[data-artifact-tab="role-block"]').click();
|
||
artifact.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-block-mobile.png");
|
||
await evaluate(`(() => {
|
||
document.querySelector(".role-block-domain-grid").scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -72);
|
||
})()`);
|
||
await pause(120);
|
||
await screenshot("/tmp/llm-atlas-deepseek-role-block-results-mobile.png");
|
||
await evaluate(`(() => {
|
||
const behavior = document.querySelector("[data-behavior-lab]");
|
||
behavior.querySelector('[data-behavior-tab="pair"]').click();
|
||
behavior.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-behavior-mobile.png");
|
||
await evaluate(`(() => {
|
||
const completionDepth = document.querySelector("[data-completion-depth-lab]");
|
||
completionDepth.querySelector('[data-cd-tab="router"]').click();
|
||
completionDepth.scrollIntoView({ block: "start", behavior: "instant" });
|
||
window.scrollBy(0, -70);
|
||
})()`);
|
||
await pause(180);
|
||
await screenshot("/tmp/llm-atlas-deepseek-completion-depth-mobile.png");
|
||
|
||
const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactDistance, artifactBoundary, artifactRole, artifactSpecial, artifactRoleBlock, artifactEvidence, behavior, completionDepth, home, papers, mobile, exceptions };
|
||
console.log(JSON.stringify(report, null, 2));
|
||
|
||
const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
|
||
const failures = [];
|
||
if (!overview.title.includes("为什么转向")) failures.push("专题标题异常");
|
||
if (overview.sections !== 31 || overview.tocLinks !== 31) failures.push("三十个编号专题加阅读链的目录结构异常");
|
||
if (overview.ledgers !== 24 || overview.waves !== 10) failures.push("二十四张问题账或十次转向结构异常");
|
||
if (overview.paperLinks !== 60 || overview.branches !== 5 || overview.followups !== 1) failures.push("论文链、旁支或公开后续标记异常");
|
||
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
|
||
if (overview.artifactTabs !== 13 || overview.artifactPanels !== 13 || overview.artifactLayers !== 27) failures.push("真实权重十三联实验结构异常");
|
||
if (overview.behaviorTabs !== 4 || overview.behaviorPanels !== 4 || overview.behaviorSources !== 16 || overview.behaviorEdges !== 10) failures.push("Chat 行为实验结构异常");
|
||
if (overview.completionDepthTabs !== 4 || overview.completionDepthPanels !== 4 || overview.hiddenStages !== 29 || overview.routerLayers !== 26) failures.push("Chat 完成度与全深度实验结构异常");
|
||
if (overview.crossSourceTabs !== 4 || overview.crossSourcePanels !== 4) failures.push("跨来源采样实验结构异常");
|
||
if (overview.heroLabs !== "22 个可操作实验") failures.push("DeepSeek 实验总数账异常");
|
||
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20 || overview.activeNav !== "DeepSeek") failures.push("全站导航未同步 DeepSeek");
|
||
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 (capacity.initial.panel !== "capacity" || capacity.initial.total !== "32.1× FFN" || capacity.initial.active !== "1.13× FFN") failures.push("V3 稀疏容量初始账异常");
|
||
if (!capacity.dense.name.includes("DENSE") || capacity.dense.communication !== "NONE" || numeric(capacity.dense.total) !== numeric(capacity.dense.active)) failures.push("Dense 容量预设异常");
|
||
if (!capacity.fine.name.includes("FINE-GRAINED") || !capacity.fine.explain.includes("shared")) failures.push("DeepSeekMoE 预设异常");
|
||
if (!capacity.v3.combinations.includes("10^") || capacity.v3.communication !== "HIGH") failures.push("V3 路由组合或通信方向异常");
|
||
if (cache.initial.panel !== "cache" || numeric(cache.initial.mha) !== 32768 || numeric(cache.initial.gqa) !== 2048 || numeric(cache.initial.mla) !== 576 || numeric(cache.initial.rope) !== 64) failures.push("MLA 精确元素账异常");
|
||
if (numeric(cache.initial.reduction) !== 98.2 || numeric(cache.noRope.mla) !== 512 || numeric(cache.noRope.reduction) <= numeric(cache.initial.reduction)) failures.push("RoPE cache 或 MLA reduction 异常");
|
||
if (!cache.million.selected.includes("GiB") || !cache.million.boundary.includes("1,048,576")) failures.push("百万 Token 缓存账异常");
|
||
if (numeric(codesign.dual.bubble) >= numeric(codesign.oneWay.bubble) || numeric(codesign.dual.exposed) >= numeric(codesign.oneWay.exposed)) failures.push("Dual-ended toy 没有减少空泡或暴露通信");
|
||
if (codesign.naive.risk !== "CRITICAL" || codesign.naive.accum !== "FP8" || codesign.mixed.risk !== "MANAGED" || !codesign.mixed.accum.includes("FP32")) failures.push("FP8 角色合同异常");
|
||
if (!codesign.off.includes("1 token") || !codesign.draft.supervision.includes("draft") || !codesign.draft.explain.includes("验收率")) failures.push("MTP 生命周期异常");
|
||
if (rl.initial.signal !== "GROUP-RELATIVE SIGNAL" || rl.same.signal !== "ZERO GROUP SIGNAL" || !rl.same.boundary.includes("优势为零")) failures.push("GRPO 零方差信号异常");
|
||
if (!rl.dapo.provenance.includes("2503.14476") || !rl.dapo.algorithm.includes("FOLLOW-UP") || !rl.dr.provenance.includes("2503.20783")) failures.push("DAPO / Dr.GRPO 来源边界异常");
|
||
if (!rl.r1.includes("cold start") || !rl.distill.includes("没有重演")) failures.push("R1 / distill 身份切换异常");
|
||
if (rl.keyboardSelected !== "cache" || rl.keyboardVisible !== "cache") failures.push("实验键盘 tab 导航异常");
|
||
if (artifactRoute.initial.panel !== "route" || artifactRoute.initial.chosen.length !== 6 || artifactRoute.initial.heatCells !== 64 || artifactRoute.initial.selectedCells !== 6) failures.push("真实 top-6 路由结构异常");
|
||
if (artifactRoute.initial.routes !== "156" || artifactRoute.initial.used !== "54 / 64" || artifactRoute.initial.weightSum !== "0.4540") failures.push("Layer 1 中文 token 路由初值异常");
|
||
if (artifactRoute.switched.chosen.length !== 6 || artifactRoute.switched.heatCells !== 64 || artifactRoute.tokenOptions !== 18 || numeric(artifactRoute.switched.weightSum) >= 1) failures.push("路由层 / prompt / token 切换异常");
|
||
if (artifactLoad.layer1.panel !== "load" || artifactLoad.layer1.used !== "63" || artifactLoad.layer1.cv !== "0.925" || artifactLoad.layer1.rows !== 5 || artifactLoad.layer1.jaccards !== 6) failures.push("Layer 1 聚合负载账异常");
|
||
if (artifactLoad.layer2.used !== "64" || artifactLoad.layer2.cv !== "0.549" || artifactLoad.layer4.used !== "62" || artifactLoad.layer4.gini !== "0.417") failures.push("跨层负载统计切换异常");
|
||
if (artifactCache.trace.panel !== "cache" || artifactCache.trace.latent !== "850.50 KiB" || artifactCache.trace.eager !== "7.38 MiB" || artifactCache.trace.ratio !== "8.89×" || artifactCache.trace.reduction !== "88.75%") failures.push("V2-Lite trace 缓存实现账异常");
|
||
if (!artifactCache.million.latent.includes("GiB") || !artifactCache.million.eager.includes("TiB")) failures.push("V2-Lite 百万 Token 缓存外推异常");
|
||
if (artifactAbsorb.panel !== "absorb" || artifactAbsorb.algebra !== 2 || artifactAbsorb.naive !== "260.00 KiB" || artifactAbsorb.absorbed !== "29.25 KiB") failures.push("真实 absorb 缓存执行账异常");
|
||
if (artifactAbsorb.metrics[0] !== "8.8889×" || artifactAbsorb.metrics[1] !== "0.00390625" || artifactAbsorb.metrics[2] !== "1.19e-7" || artifactAbsorb.metrics[3] !== "BYTE-EXACT") failures.push("absorb 数值正确性或复跑闸门异常");
|
||
if (artifactAbsorb.precisionRows !== 3 || artifactAbsorb.matrixRows !== 5 || artifactAbsorb.localUnsupported !== 4 || artifactAbsorb.executionCards !== 3 || !artifactAbsorb.boundary.includes("不是 FlashMLA 性能")) failures.push("FlashMLA SM120 边界结构异常");
|
||
if (artifactCorpus.layer1.panel !== "corpus" || artifactCorpus.layer1.rows !== 4 || artifactCorpus.layer1.heatRows !== 4 || artifactCorpus.layer1.heatCells !== 256 || artifactCorpus.layer1.jsdCells !== 25) failures.push("128 样本路由区间结构异常");
|
||
if (!artifactCorpus.layer1.highest.includes("中文新闻 · 0.754") || !artifactCorpus.layer1.largest.includes("中文新闻 ↔ Python 代码 · 0.059") || artifactCorpus.layer1.exact !== "3 / 3 EXACT") failures.push("Layer 1 多域统计或三 cohort 复跑闸门异常");
|
||
if (!artifactCorpus.layer4.highest.includes("中文新闻 · 0.910") || !artifactCorpus.layer4.largest.includes("中文新闻 ↔ Python 代码 · 0.150") || !artifactCorpus.layer4.heatTitle.includes("layer 4")) failures.push("Layer 4 多域路由切换异常");
|
||
if (!artifactCorpus.matched16.highest.includes("Python 代码 · 0.969") || artifactCorpus.matched16.cohortTitle !== "同样本 · 16 tokens" || !artifactCorpus.matched16.tokens.every((value) => value.includes("512 tokens"))) failures.push("16-token 同源 cohort 切换异常");
|
||
if (!artifactCorpus.matched24.highest.includes("Python 代码 · 0.718") || artifactCorpus.matched24.cohortTitle !== "同样本 · 24 tokens" || !artifactCorpus.matched24.tokens.every((value) => value.includes("768 tokens"))) failures.push("24-token 同源 cohort 切换异常");
|
||
if (artifactCorpus.matched24.deltaCards !== 4 || artifactCorpus.matched24.lengthLargest !== "Python 代码 · Δ -0.251" || artifactCorpus.matched24.lengthJsd !== "0.091 → 0.065 · Δ -0.026") failures.push("16→24 token 成对敏感性结论异常");
|
||
if (!artifactCorpus.tokenWeighted.heatTitle.includes("token 加权") || !artifactCorpus.tokenWeighted.modeNote.includes("理论上重合")) failures.push("等长 cohort 聚合口径切换异常");
|
||
if (artifactTemplate.layer1Content.panel !== "template" || artifactTemplate.layer1Content.domainCards !== 4 || artifactTemplate.layer1Content.depthRows !== 4 || artifactTemplate.layer1Content.depthCells !== 24 || artifactTemplate.layer1Content.exact !== "BYTE-EXACT") failures.push("官方模板扰动结构或独立复跑闸门异常");
|
||
if (artifactTemplate.layer1Content.domains[0].values !== "0.633 → 0.593" || artifactTemplate.layer1Content.domains[0].delta !== "Δ -0.040" || artifactTemplate.layer1Content.domains[1].delta !== "Δ -0.049") failures.push("L1 对齐内容模板敏感性统计异常");
|
||
if (artifactTemplate.layer1Content.prefixExact !== "3,642 / 3,642 EXACT · L1" || artifactTemplate.layer1Content.contentZero !== "4 / 4 DOMAINS · Δ 0") failures.push("L1 causal suffix 负对照异常");
|
||
if (artifactTemplate.layer6Content.domains.some((domain) => domain.className !== "up") || artifactTemplate.layer6Content.domains[0].delta !== "Δ +0.060" || artifactTemplate.layer6Content.domains[2].delta !== "Δ +0.058") failures.push("L6 对齐内容跨域方向异常");
|
||
if (artifactTemplate.layer6Full.domains[0].delta !== "Δ +0.134" || !artifactTemplate.layer6Full.note.includes("完整输入") || artifactTemplate.layer6Full.activeScope !== "full_input") failures.push("模板完整输入 scope 切换异常");
|
||
if (artifactTemplate.layer6FullToken.activeMode !== "token_weighted" || artifactTemplate.layer2Content.activeLayer !== "L2" || artifactTemplate.layer2Content.domains[2].delta !== "Δ -0.067") failures.push("模板层或聚合口径切换异常");
|
||
if (artifactHistory.layer1Interaction.panel !== "history" || artifactHistory.layer1Interaction.matrixRows !== 2 || artifactHistory.layer1Interaction.matrixCells !== 4 || artifactHistory.layer1Interaction.domainCards !== 4 || artifactHistory.layer1Interaction.depthRows !== 4 || artifactHistory.layer1Interaction.depthCells !== 24 || artifactHistory.layer1Interaction.exact !== "BYTE-EXACT") failures.push("消息历史 2×2 结构或独立复跑闸门异常");
|
||
if (artifactHistory.layer1Interaction.domains[0].cells.map((cell) => cell.value).join("/") !== "0.596/0.810/0.779/0.737" || artifactHistory.layer1Interaction.domains[0].effect !== "INTERACTION · Δ -0.256" || artifactHistory.layer1Interaction.domains[1].effect !== "INTERACTION · Δ +0.150") failures.push("L1 消息历史四格或 interaction 统计异常");
|
||
if (artifactHistory.layer1Interaction.bufferSummary.join("|") !== "24 / 24 ↓|.073 → .019|21 / 24 ↓|HISTORY BUFFER" || artifactHistory.layer1Interaction.bufferCards.length !== 4 || !artifactHistory.layer1Interaction.bufferCards[0].tv.startsWith("TV ") || !artifactHistory.layer1Interaction.bufferCards[0].stability.includes("top-6 set exact")) failures.push("消息历史缓冲总账或逐 token 稳定性异常");
|
||
if (artifactHistory.layer4Interaction.domains[1].cells.map((cell) => cell.value).join("/") !== "0.851/0.611/0.719/0.683" || artifactHistory.layer4Interaction.domains[1].effect !== "INTERACTION · Δ +0.204") failures.push("L4 中文消息历史 interaction 异常");
|
||
if (artifactHistory.layer4System.domains[0].effect !== "SYSTEM MAIN · Δ -0.082" || artifactHistory.layer4System.activeEffect !== "system_main" || !artifactHistory.layer4System.depthTitle.includes("System main")) failures.push("消息历史 effect 切换异常");
|
||
if (artifactHistory.layer4FullSystem.domains[0].effect !== "SYSTEM MAIN · Δ -0.057" || artifactHistory.layer4FullSystem.activeScope !== "full_input" || !artifactHistory.layer4FullSystem.note.includes("完整输入")) failures.push("消息历史完整输入 scope 异常");
|
||
if (artifactHistory.layer4FullToken.activeMode !== "token_weighted" || artifactHistory.restored.activeScope !== "target_content" || artifactHistory.restored.activeMode !== "prompt_balanced" || artifactHistory.restored.activeEffect !== "interaction") failures.push("消息历史聚合口径或恢复状态异常");
|
||
if (artifactDistance.layer1Filler.panel !== "distance" || artifactDistance.layer1Filler.matrixRows !== 2 || artifactDistance.layer1Filler.matrixCells !== 6 || artifactDistance.layer1Filler.domainCards !== 4 || artifactDistance.layer1Filler.depthRows !== 4 || artifactDistance.layer1Filler.depthCells !== 24 || artifactDistance.layer1Filler.exact !== "BYTE-EXACT") failures.push("等长历史 2×3 结构或独立复跑闸门异常");
|
||
if (artifactDistance.layer1Filler.domains[0].values.map((cell) => cell.value).join("/") !== "0.106/0.056/0.024" || artifactDistance.layer1Filler.domains[0].effect !== "FILLER − NONE · ΔTV -0.050" || artifactDistance.layer1Filler.domains[1].effect !== "FILLER − NONE · ΔTV -0.050") failures.push("L1 等长 filler 阶梯统计异常");
|
||
if (artifactDistance.layer1Filler.summary.join("|") !== "24 / 24 ↓|24 / 24 ↓|.074 → .038 → .019|NOT PURE DISTANCE" || !artifactDistance.layer1Filler.domains[0].stability.includes("target top-6 set exact") || !artifactDistance.layer1Filler.domains[0].lexical.includes("filler↔demo TV")) failures.push("等长历史双台阶总账或逐 token 稳定性异常");
|
||
if (artifactDistance.layer4Filler.domains[1].values.map((cell) => cell.value).join("/") !== "0.071/0.029/0.015" || artifactDistance.layer4Filler.domains[1].effect !== "FILLER − NONE · ΔTV -0.043") failures.push("L4 中文 filler 阶梯异常");
|
||
if (artifactDistance.layer4Demo.domains[1].effect !== "DEMO − FILLER · ΔTV -0.014" || artifactDistance.layer4Demo.activeContrast !== "demo_minus_filler" || !artifactDistance.layer4Demo.depthTitle.includes("文本替换")) failures.push("等长历史文本替换 contrast 异常");
|
||
if (artifactDistance.layer4FullDemo.domains[1].effect !== "DEMO − FILLER · ΔTV -0.023" || artifactDistance.layer4FullDemo.activeScope !== "full_input" || !artifactDistance.layer4FullDemo.note.includes("完整输入")) failures.push("等长历史完整输入 scope 异常");
|
||
if (artifactDistance.layer4FullToken.activeMode !== "token_weighted" || artifactDistance.restored.activeScope !== "target_content" || artifactDistance.restored.activeMode !== "prompt_balanced" || artifactDistance.restored.activeContrast !== "filler_minus_none") failures.push("等长历史聚合口径或恢复状态异常");
|
||
if (artifactBoundary.layer1X.panel !== "boundary" || artifactBoundary.layer1X.tokenCards !== 4 || artifactBoundary.layer1X.domainCards !== 4 || artifactBoundary.layer1X.depthRows !== 4 || artifactBoundary.layer1X.depthCells !== 24 || artifactBoundary.layer1X.exact !== "BYTE-EXACT") failures.push("单 token 边界控制结构或独立复跑闸门异常");
|
||
if (artifactBoundary.layer1X.domains[0].values.map((cell) => cell.value).join("/") !== "0.056/0.084/0.081/0.080" || artifactBoundary.layer1X.domains[0].effect !== "X − EOS · ΔTV +0.028" || !artifactBoundary.layer1X.domains[0].ci.includes("+0.019, +0.035")) failures.push("L1 英文边界替换统计异常");
|
||
if (artifactBoundary.layer1X.summary.join("|") !== "24 / 24 ↑|24 / 24 ↑|23 / 24 ↑|.037 → .054 / .055 / .049" || artifactBoundary.layer1X.trackToken !== "X" || !artifactBoundary.layer1X.domains[0].stability.includes("EOS 50.7%")) failures.push("边界控制总账、协议轨或逐 token 稳定性异常");
|
||
if (artifactBoundary.layer4X.domains[0].values.map((cell) => cell.value).join("/") !== "0.032/0.051/0.051/0.045" || artifactBoundary.layer4X.domains[0].effect !== "X − EOS · ΔTV +0.019") failures.push("L4 英文 x 边界替换异常");
|
||
if (artifactBoundary.layer4Period.domains[2].effect !== "PERIOD − EOS · ΔTV +0.034" || artifactBoundary.layer4Period.activeContrast !== "period_minus_eos" || artifactBoundary.layer4Period.trackToken !== ".") failures.push("L4 代码句点边界替换异常");
|
||
if (artifactBoundary.layer4Newline.activeContrast !== "newline_minus_eos" || artifactBoundary.layer4Newline.trackToken !== "↵" || !artifactBoundary.layer4Newline.depthTitle.includes("换行")) failures.push("换行边界替换切换异常");
|
||
if (artifactBoundary.layer4Full.activeScope !== "full_input" || !artifactBoundary.layer4Full.note.includes("完整输入") || artifactBoundary.layer4Full.domains[0].values[0].value === artifactBoundary.layer4Newline.domains[0].values[0].value) failures.push("边界控制完整输入 scope 异常");
|
||
if (artifactBoundary.layer4FullToken.activeMode !== "token_weighted" || artifactBoundary.restored.activeLayer !== "L1" || artifactBoundary.restored.activeScope !== "target_content" || artifactBoundary.restored.activeMode !== "prompt_balanced" || artifactBoundary.restored.activeContrast !== "x_minus_eos") failures.push("边界控制聚合口径或恢复状态异常");
|
||
if (artifactRole.layer1Assistant.panel !== "role" || artifactRole.layer1Assistant.levelCards !== 4 || artifactRole.layer1Assistant.domainCards !== 4 || artifactRole.layer1Assistant.depthRows !== 4 || artifactRole.layer1Assistant.depthCells !== 24 || artifactRole.layer1Assistant.exact !== "BYTE-EXACT" || artifactRole.layer1Assistant.causalCards !== 3 || artifactRole.layer1Assistant.batchCells !== 6) failures.push("角色词头单 ID 控制结构或独立复跑闸门异常");
|
||
if (artifactRole.layer1Assistant.domains[0].values.map((cell) => cell.value).join("/") !== "0.056/0.059/0.062/0.056" || artifactRole.layer1Assistant.domains[0].effect !== "U→A − OFFICIAL · ΔTV +0.003" || !artifactRole.layer1Assistant.domains[0].ci.includes("-0.003, +0.007")) failures.push("L1 英文角色词头 system-edge 统计异常");
|
||
if (!artifactRole.layer1Assistant.domains[0].stability.includes("S0 79.7% · S1 84.6%") || !artifactRole.layer1Assistant.domains[0].direct.includes("S0 0.024 · S1 0.021") || artifactRole.layer1Assistant.summary.join("|") !== ".0222 / .0218|.0263 / .0253|34,488 / 34,488|12↑12↓ / 13↑11↓") failures.push("角色词头直接效应、对齐率或总账异常");
|
||
if (artifactRole.layer5X.activeContrast !== "target_x_minus_official" || artifactRole.layer5X.targetHead !== "x" || !artifactRole.layer5X.depthTitle.includes("普通 token")) failures.push("角色词头 U→x 层或 contrast 切换异常");
|
||
if (artifactRole.layer5Suffix.domains.some((domain) => domain.effect !== "SUFFIX A→U − OFFICIAL · ΔTV +0.000") || artifactRole.layer5Suffix.targetHead !== "User" || artifactRole.layer5Suffix.suffixHead !== "User" || !artifactRole.layer5Suffix.domains.every((domain) => domain.direct.includes("S0 0.000 · S1 0.000"))) failures.push("后置角色词头 causal suffix 负对照异常");
|
||
if (artifactRole.layer5FullSuffix.activeScope !== "full_input" || !artifactRole.layer5FullSuffix.note.includes("suffix 自身") || artifactRole.layer5FullSuffix.domains[0].values[0].value === artifactRole.layer5Suffix.domains[0].values[0].value) failures.push("角色词头完整输入 scope 异常");
|
||
if (artifactRole.layer5FullToken.activeMode !== "token_weighted" || artifactRole.restored.activeLayer !== "L1" || artifactRole.restored.activeScope !== "target_content" || artifactRole.restored.activeMode !== "prompt_balanced" || artifactRole.restored.activeContrast !== "target_assistant_minus_official" || artifactRole.restored.targetHead !== "Assistant" || artifactRole.restored.suffixHead !== "Assistant") failures.push("角色词头聚合口径或恢复状态异常");
|
||
if (artifactRole.layer1Assistant.batchValues.join("|") !== "256 / 256|180 / 256|149 / 256|102 / 256|72 / 256|73 / 256") failures.push("角色词头 BF16 batch-content 审计异常");
|
||
if (artifactSpecial.layer1Bos.panel !== "special" || artifactSpecial.layer1Bos.tokenCards !== 4 || artifactSpecial.layer1Bos.domainCards !== 4 || artifactSpecial.layer1Bos.depthRows !== 4 || artifactSpecial.layer1Bos.depthCells !== 24 || artifactSpecial.layer1Bos.exact !== "BYTE-EXACT" || artifactSpecial.layer1Bos.scopeCards !== 3 || artifactSpecial.layer1Bos.batchCells !== 6) failures.push("特殊词元家族控制结构或独立复跑闸门异常");
|
||
if (artifactSpecial.layer1Bos.domains[0].values.map((cell) => cell.value).join("/") !== "0.056/0.108/0.084/0.081" || artifactSpecial.layer1Bos.domains[0].effect !== "BOS − EOS · ΔTV +0.052" || !artifactSpecial.layer1Bos.domains[0].ci.includes("+0.040, +0.061")) failures.push("L1 英文特殊词元家族统计异常");
|
||
if (!artifactSpecial.layer1Bos.domains[0].detail.includes("S0 0.087 · S1 0.064") || !artifactSpecial.layer1Bos.domains[0].stability.includes("S0 37.4%") || artifactSpecial.layer1Bos.summary.join("|") !== ".037518|+.010500|24↑ / 24↑|+.011864") failures.push("特殊词元直接效应、对齐率或总账异常");
|
||
if (artifactSpecial.layer4X.activeContrast !== "x_minus_eos" || !artifactSpecial.layer4X.depthTitle.includes("普通内容 token") || artifactSpecial.layer4Period.activeContrast !== "period_minus_eos" || !artifactSpecial.layer4Period.depthTitle.includes("句点")) failures.push("特殊词元单 ID contrast 切换异常");
|
||
if (artifactSpecial.layer4Family.activeContrast !== "family" || !artifactSpecial.layer4Family.note.includes("四个 ID") || !artifactSpecial.layer4Family.domains.every((domain) => domain.stability.includes("2-vs-2"))) failures.push("特殊词元描述性 family 汇总异常");
|
||
if (artifactSpecial.layer4FullFamily.activeScope !== "full_input" || !artifactSpecial.layer4FullFamily.note.includes("完整输入") || artifactSpecial.layer4FullToken.activeMode !== "token_weighted") failures.push("特殊词元完整输入或聚合口径切换异常");
|
||
if (artifactSpecial.restored.activeLayer !== "L1" || artifactSpecial.restored.activeScope !== "target_content" || artifactSpecial.restored.activeMode !== "prompt_balanced" || artifactSpecial.restored.activeContrast !== "bos_minus_eos") failures.push("特殊词元控制恢复状态异常");
|
||
if (artifactSpecial.layer1Bos.batchValues.join("|") !== "768 / 768|610 / 768|477 / 768|368 / 768|269 / 768|244 / 768") failures.push("特殊词元 BF16 batch-content 审计异常");
|
||
if (artifactRoleBlock.layer1Head.panel !== "role-block" || artifactRoleBlock.layer1Head.matrixCards !== 4 || artifactRoleBlock.layer1Head.domainCards !== 4 || artifactRoleBlock.layer1Head.depthRows !== 4 || artifactRoleBlock.layer1Head.depthCells !== 24 || artifactRoleBlock.layer1Head.exact !== "BYTE-EXACT" || artifactRoleBlock.layer1Head.directCards !== 4 || artifactRoleBlock.layer1Head.boundaryCards !== 3 || artifactRoleBlock.layer1Head.batchCells !== 6) failures.push("完整角色块 2×2 结构或独立复跑闸门异常");
|
||
if (artifactRoleBlock.layer1Head.domains[0].values.map((cell) => cell.value).join("/") !== "0.056/0.059/0.056/0.058" || artifactRoleBlock.layer1Head.domains[0].effect !== "HEAD MAIN · ΔTV +0.002" || !artifactRoleBlock.layer1Head.domains[0].ci.includes("-0.002, +0.004")) failures.push("L1 英文完整角色块 head 统计异常");
|
||
if (!artifactRoleBlock.layer1Head.domains[0].direct.includes("head @ colon") || !artifactRoleBlock.layer1Head.domains[0].dependency.includes("head @ x") || artifactRoleBlock.layer1Head.summary.join("|") !== ".037304 → .036220|−.000654|−.000430|−.000729") failures.push("完整角色块直接边或总账异常");
|
||
if (artifactRoleBlock.layer4Delimiter.activeEffect !== "delimiter_main" || !artifactRoleBlock.layer4Delimiter.depthTitle.includes("冒号→x") || artifactRoleBlock.layer5Interaction.activeEffect !== "head_by_delimiter" || !artifactRoleBlock.layer5Interaction.depthTitle.includes("依赖 delimiter") || !artifactRoleBlock.layer5Interaction.domains[0].direct.includes("head@x − head@colon")) failures.push("完整角色块因子或 interaction 切换异常");
|
||
if (artifactRoleBlock.layer5FullInteraction.activeScope !== "full_input" || artifactRoleBlock.layer5FullToken.activeMode !== "token_weighted" || artifactRoleBlock.restored.activeLayer !== "L1" || artifactRoleBlock.restored.activeScope !== "target_content" || artifactRoleBlock.restored.activeMode !== "prompt_balanced" || artifactRoleBlock.restored.activeEffect !== "head_main") failures.push("完整角色块 scope、聚合口径或恢复状态异常");
|
||
if (artifactRoleBlock.layer1Head.batchValues.join("|") !== "512 / 512|368 / 512|279 / 512|230 / 512|178 / 512|156 / 512") failures.push("完整角色块 BF16 batch-content 审计异常");
|
||
if (artifactEvidence.panel !== "evidence" || artifactEvidence.layers !== 27 || artifactEvidence.executed !== 7 || artifactEvidence.split !== 1 || artifactEvidence.unloaded !== 19 || artifactEvidence.exact !== "31 / 31") failures.push("真实工件执行边界或复跑闸门异常");
|
||
if (!artifactEvidence.dependency.includes("Transformers 5.5") || !artifactEvidence.dependency.includes("4.41.2") || !artifactEvidence.boundary.includes("完整 27 层生成")) failures.push("依赖版本或未覆盖边界异常");
|
||
if (artifactEvidence.keyboardSelected !== "load" || artifactEvidence.keyboardVisible !== "load") failures.push("真实工件实验键盘 tab 导航异常");
|
||
if (behavior.initial.panel !== "pair" || behavior.initial.source !== "wikitext2/raw-validation/0443" || behavior.initial.conditions.join("|") !== "S0 · EOS|S1 · EOS" || behavior.initial.exact !== "DIVERGED" || behavior.initial.prefix !== "63" || behavior.initial.edit !== "33" || behavior.initial.similarity !== "74.2%") failures.push("Chat 行为逐格输出初值异常");
|
||
if (behavior.switched.domain !== "Grade-school math" || behavior.switched.conditions.join("|") !== "S1 · EOS|S1 · x" || behavior.switched.exact !== "DIVERGED" || behavior.switched.outputCharacters.some((value) => value < 100)) failures.push("Chat 行为 source / contrast 切换异常");
|
||
if (behavior.mathMap.panel !== "map" || behavior.mathMap.rows !== 10 || !behavior.mathMap.note.includes("GSM8K") || behavior.mathMap.firstExact !== "2 / 4" || behavior.mathMap.firstSimilarity !== "84.0%") failures.push("Chat 行为分域分叉地图异常");
|
||
if (behavior.execution.panel !== "execution" || behavior.execution.layers !== 29 || behavior.execution.gpu !== 25 || behavior.execution.cpu !== 4 || behavior.execution.runtimeCards !== 4) failures.push("Chat BF16 GPU / CPU offload 设备图异常");
|
||
if (behavior.boundary.panel !== "boundary" || behavior.boundary.ladder !== 3 || behavior.boundary.tokenCards !== 4 || behavior.boundary.reproCards !== 4 || behavior.boundary.links !== 3 || !behavior.boundary.forbidden.includes("route TV")) failures.push("Chat 行为证据阶梯或限制异常");
|
||
if (behavior.keyboardSelected !== "map" || behavior.keyboardVisible !== "map") failures.push("Chat 行为实验键盘 tab 导航异常");
|
||
if (completionDepth.initial.panel !== "completion" || completionDepth.initial.conditionRows !== 8 || completionDepth.initial.incompleteRows !== 7 || completionDepth.initial.prefixCards !== 3) failures.push("512-token 完成度阶梯结构异常");
|
||
if (completionDepth.tasks.panel !== "tasks" || completionDepth.tasks.mathCards !== 4 || completionDepth.tasks.codeCards !== 4 || completionDepth.tasks.mathTotal !== "3 / 4 PASS" || completionDepth.tasks.codeTotal !== "2 / 4 PASS" || completionDepth.tasks.sandboxSteps !== 4) failures.push("Math / HumanEval 完成感知评测切换异常");
|
||
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("47 页不再压成摘要") || home.firstHref !== "/k3/" || home.paperCount !== "486") failures.push("首页 DeepSeek 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:${JSON.stringify(mobile.offenders)}`);
|
||
if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`);
|
||
|
||
if (failures.length) {
|
||
console.error(`\nFAIL\n- ${failures.join("\n- ")}`);
|
||
process.exitCode = 1;
|
||
} else {
|
||
console.log("\nPASS DeepSeek browser regression");
|
||
}
|
||
|
||
socket.close();
|