feat: add DeepSeek chat-template routing probe
This commit is contained in:
@@ -80,6 +80,9 @@ const overview = await evaluate(`(() => ({
|
||||
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,
|
||||
}))()`);
|
||||
|
||||
@@ -344,6 +347,57 @@ await evaluate(`(() => {
|
||||
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 artifactEvidence = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-dsv2-lab]");
|
||||
root.querySelector('[data-artifact-tab="evidence"]').click();
|
||||
@@ -417,6 +471,11 @@ const mobile = await evaluate(`(() => {
|
||||
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,
|
||||
offenders: [...document.querySelectorAll("body *")]
|
||||
.filter((node) => !node.closest(".paper-chain, .advantage-table, .precision-table, .mapping-table, [data-deepseek-lab], [data-dsv2-lab]"))
|
||||
.filter((node) => node.getBoundingClientRect().right > document.documentElement.clientWidth + 1)
|
||||
@@ -444,8 +503,22 @@ await evaluate(`(() => {
|
||||
})()`);
|
||||
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");
|
||||
|
||||
const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactEvidence, home, papers, mobile, exceptions };
|
||||
const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactEvidence, home, papers, mobile, exceptions };
|
||||
console.log(JSON.stringify(report, null, 2));
|
||||
|
||||
const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
|
||||
@@ -455,7 +528,8 @@ if (overview.sections !== 26 || overview.tocLinks !== 26) failures.push("二十
|
||||
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 !== 6 || overview.artifactPanels !== 6 || overview.artifactLayers !== 27) failures.push("真实权重六联实验结构异常");
|
||||
if (overview.artifactTabs !== 7 || overview.artifactPanels !== 7 || overview.artifactLayers !== 27) failures.push("真实权重七联实验结构异常");
|
||||
if (overview.heroLabs !== "11 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");
|
||||
@@ -489,12 +563,18 @@ if (!artifactCorpus.matched16.highest.includes("Python 代码 · 0.969") || arti
|
||||
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 (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 (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 !== 6 || mobile.artifactHeatCells !== 64 || mobile.corpusCohorts !== 3 || mobile.lengthDeltaCards !== 4) failures.push("移动端导航或实验异常");
|
||||
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 7 || mobile.artifactHeatCells !== 64 || mobile.corpusCohorts !== 3 || mobile.lengthDeltaCards !== 4 || mobile.templateLayers !== 6 || mobile.templateScopes !== 2 || mobile.templateModes !== 2 || mobile.templateDomainCards !== 4 || mobile.templateDepthCells !== 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(" | ")}`);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user