feat: add DeepSeek Chat behavior evidence

scripts/check-deepseek-browser.mjs

@@ -76,6 +76,10 @@ const overview = await evaluate(`(() => ({
   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,
   branches: document.querySelectorAll(".branch-grid > a").length,
   followups: document.querySelectorAll(".lineage-row.followup").length,
   navLinks: document.querySelectorAll(".top-nav a").length,
@@ -803,6 +807,78 @@ await evaluate(`(() => {
 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");
+
 await navigate("/");
 const home = await evaluate(`(() => ({
   releaseCards: document.querySelectorAll(".release-card").length,
@@ -835,6 +911,7 @@ 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]");
   root.scrollIntoView({ block: "start", behavior: "instant" });
   const toggle = document.querySelector("#menu-toggle");
   toggle?.click();
@@ -845,6 +922,10 @@ const mobile = await evaluate(`(() => {
     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,
     artifactHeatCells: artifact.querySelectorAll("[data-route-heatmap] > span").length,
     corpusCohorts: artifact.querySelectorAll("[data-corpus-cohort]").length,
     lengthDeltaCards: artifact.querySelectorAll("[data-length-delta-grid] > article").length,
@@ -894,7 +975,7 @@ const mobile = await evaluate(`(() => {
     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]"))
+      .filter((node) => !node.closest(".paper-chain, .advantage-table, .precision-table, .mapping-table, [data-deepseek-lab], [data-dsv2-lab], [data-behavior-lab]"))
       .filter((node) => node.getBoundingClientRect().right > document.documentElement.clientWidth + 1)
       .slice(0, 12)
       .map((node) => ({
@@ -1018,19 +1099,28 @@ await evaluate(`(() => {
 })()`);
 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");
 
-const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactDistance, artifactBoundary, artifactRole, artifactSpecial, artifactRoleBlock, artifactEvidence, home, papers, mobile, exceptions };
+const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactDistance, artifactBoundary, artifactRole, artifactSpecial, artifactRoleBlock, artifactEvidence, behavior, 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 !== 26 || overview.tocLinks !== 26) failures.push("二十五个编号专题加阅读链的目录结构异常");
+if (overview.sections !== 27 || overview.tocLinks !== 27) failures.push("二十六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.heroLabs !== "17 个可操作实验") failures.push("DeepSeek 实验总数账异常");
+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.heroLabs !== "18 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");
@@ -1117,9 +1207,15 @@ if (artifactRoleBlock.layer1Head.batchValues.join("|") !== "512 / 512|368 / 512|
 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 (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.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.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 13 || mobile.behaviorTabs !== 4 || mobile.behaviorSources !== 16 || mobile.behaviorEdges !== 10 || mobile.behaviorDeviceCells !== 29 || 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(" | ")}`);