wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add DeepSeek equal-length history control

Browse Source
This commit is contained in:
wuyang
2026-07-29 19:01:17 +08:00
parent bdd93a5222
commit 8130e3745f
11 changed files with 2854526 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/check-deepseek-browser.mjs
+90 -5
View File
@@ -418,7 +418,7 @@ const artifactHistory = await evaluate(`(() => {
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()),
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(),
@@ -461,6 +461,64 @@ await evaluate(`(() => {
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 artifactEvidence = await evaluate(`(() => {
const root = document.querySelector("[data-dsv2-lab]");
root.querySelector('[data-artifact-tab="evidence"]').click();
@@ -545,6 +603,12 @@ const mobile = await evaluate(`(() => {
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,
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)
@@ -600,8 +664,22 @@ await evaluate(`(() => {
})()`);
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");
const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactEvidence, home, papers, mobile, exceptions };
const report = { overview, capacity, cache, codesign, rl, artifactRoute, artifactLoad, artifactCache, artifactAbsorb, artifactCorpus, artifactTemplate, artifactHistory, artifactDistance, artifactEvidence, home, papers, mobile, exceptions };
console.log(JSON.stringify(report, null, 2));
const numeric = (text) => Number.parseFloat(text.replaceAll(",", ""));
@@ -611,8 +689,8 @@ 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 !== 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.artifactTabs !== 9 || overview.artifactPanels !== 9 || overview.artifactLayers !== 27) failures.push("真实权重九联实验结构异常");
if (overview.heroLabs !== "13 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");
@@ -659,12 +737,19 @@ if (artifactHistory.layer4Interaction.domains[1].cells.map((cell) => cell.value)
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 (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 !== 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.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 9 || 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) 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(" | ")}`);