feat: add DeepSeek message-history factorial probe

2026-07-29 18:05:59 +08:00
parent 28f8066626
commit efe3ffcb4e
11 changed files with 1890088 additions and 33 deletions
@@ -398,6 +398,69 @@ await evaluate(`(() => {
 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(".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 artifactEvidence = await evaluate(`(() => {
  const root = document.querySelector("[data-dsv2-lab]");
  root.querySelector('[data-artifact-tab="evidence"]').click();
@@ -476,6 +539,12 @@ const mobile = await evaluate(`(() => {
    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,
    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)
@@ -517,8 +586,22 @@ await evaluate(`(() => {
 })()`);
 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");

-const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactEvidence, home, papers, mobile, exceptions };
+const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactEvidence, home, papers, mobile, exceptions };
 console.log(JSON.stringify(report, null, 2));

 const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
@@ -528,8 +611,8 @@ 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 !== 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.artifactTabs !== 8 || overview.artifactPanels !== 8 || overview.artifactLayers !== 27) failures.push("真实权重八联实验结构异常");
+if (overview.heroLabs !== "12 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");
@@ -569,12 +652,19 @@ if (artifactTemplate.layer1Content.prefixExact !== "3,642 / 3,642 EXACT · L1" |
 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 (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 !== 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.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 8 || 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) 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(" | ")}`);