feat: map DeepSeek Chat sampling robustness
This commit is contained in:
@@ -0,0 +1,278 @@
|
||||
import { writeFileSync } from "node:fs";
|
||||
|
||||
const cdpPort = process.env.CDP_PORT ?? "9230";
|
||||
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}${path}` });
|
||||
for (let attempt = 0; attempt < 80; attempt += 1) {
|
||||
await pause(100);
|
||||
if (await evaluate("document.readyState === 'complete'")) return;
|
||||
}
|
||||
throw new Error(`${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"));
|
||||
};
|
||||
const assert = (condition, message) => {
|
||||
if (!condition) throw new Error(message);
|
||||
};
|
||||
|
||||
await command("Page.enable");
|
||||
await command("Runtime.enable");
|
||||
await command("Emulation.setDeviceMetricsOverride", {
|
||||
width: 1440,
|
||||
height: 1100,
|
||||
deviceScaleFactor: 1,
|
||||
mobile: false,
|
||||
});
|
||||
await navigate("/deepseek/");
|
||||
|
||||
const overview = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
document.documentElement.style.scrollBehavior = "auto";
|
||||
window.scrollTo(0, root.getBoundingClientRect().top + window.scrollY);
|
||||
return {
|
||||
tabs: root.querySelectorAll("[data-sp-tab]").length,
|
||||
panels: root.querySelectorAll("[data-sp-panel]").length,
|
||||
seedBars: root.querySelectorAll("[data-sp-seeds] button").length,
|
||||
conditions: root.querySelectorAll(".condition-overview > div").length,
|
||||
edges: root.querySelectorAll(".edge-overview > div").length,
|
||||
heroLabs: [...document.querySelectorAll(".page-facts > div")]
|
||||
.find((node) => node.querySelector("dt")?.textContent.trim() === "LABS")
|
||||
?.querySelector("dd")?.textContent.trim(),
|
||||
activePanel: root.querySelector("[data-sp-panel]:not([hidden])")
|
||||
?.dataset.spPanel,
|
||||
unique: root.querySelector("[data-sp-unique]").textContent.trim(),
|
||||
eos: root.querySelector("[data-sp-eos]").textContent.trim(),
|
||||
greedy: root.querySelector("[data-sp-greedy]").textContent.trim(),
|
||||
documentOverflow: (
|
||||
document.documentElement.scrollWidth
|
||||
- document.documentElement.clientWidth
|
||||
),
|
||||
};
|
||||
})()`);
|
||||
await pause(300);
|
||||
await screenshot("/tmp/llm-atlas-sampling-desktop.png");
|
||||
|
||||
const trajectorySwitch = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
const source = root.querySelector("[data-sp-source]");
|
||||
const condition = root.querySelector("[data-sp-condition]");
|
||||
source.value = "HumanEval/31";
|
||||
source.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
condition.value = "s1_period";
|
||||
condition.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
const buttons = [...root.querySelectorAll("[data-sp-seeds] button")];
|
||||
buttons.at(-1).click();
|
||||
return {
|
||||
unique: root.querySelector("[data-sp-unique]").textContent.trim(),
|
||||
eos: root.querySelector("[data-sp-eos]").textContent.trim(),
|
||||
greedy: root.querySelector("[data-sp-greedy]").textContent.trim(),
|
||||
seedBars: buttons.length,
|
||||
repeats: buttons.filter((button) => button.classList.contains("repeat")).length,
|
||||
selected: buttons.filter((button) => button.classList.contains("selected")).length,
|
||||
focus: root.querySelector("[data-sp-focus-seed]").textContent.trim(),
|
||||
hash: root.querySelector("[data-sp-focus-hash]").textContent.trim(),
|
||||
};
|
||||
})()`);
|
||||
|
||||
const taskSwitch = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
root.querySelector('[data-sp-tab="tasks"]').click();
|
||||
const condition = root.querySelector("[data-sp-task-condition]");
|
||||
const read = () => ({
|
||||
panel: root.querySelector("[data-sp-panel]:not([hidden])").dataset.spPanel,
|
||||
math: root.querySelector("[data-sp-math-total]").textContent.trim(),
|
||||
code: root.querySelector("[data-sp-code-total]").textContent.trim(),
|
||||
mathCells: root.querySelectorAll("[data-sp-math-cells] article").length,
|
||||
codeCells: root.querySelectorAll("[data-sp-code-cells] article").length,
|
||||
});
|
||||
condition.value = "s1_x";
|
||||
condition.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
const systemX = read();
|
||||
condition.value = "s0_period";
|
||||
condition.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
const period = read();
|
||||
return { systemX, period };
|
||||
})()`);
|
||||
|
||||
const edgeSwitch = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
root.querySelector('[data-sp-tab="edges"]').click();
|
||||
const source = root.querySelector("[data-sp-edge-source]");
|
||||
const edge = root.querySelector("[data-sp-edge]");
|
||||
source.value = "gsm8k/test/1069";
|
||||
source.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
edge.value = "system_eos";
|
||||
edge.dispatchEvent(new Event("change", { bubbles: true }));
|
||||
return {
|
||||
panel: root.querySelector("[data-sp-panel]:not([hidden])").dataset.spPanel,
|
||||
aligned: root.querySelector("[data-sp-edge-aligned]").textContent.trim(),
|
||||
nearest: root.querySelector("[data-sp-edge-nearest]").textContent.trim(),
|
||||
overlap: root.querySelector("[data-sp-edge-overlap]").textContent.trim(),
|
||||
left: root.querySelectorAll("[data-sp-edge-left-set] article").length,
|
||||
right: root.querySelectorAll("[data-sp-edge-right-set] article").length,
|
||||
highlighted: root.querySelectorAll(".two-sets article.overlap").length,
|
||||
};
|
||||
})()`);
|
||||
|
||||
const keyboard = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
const first = root.querySelector('[data-sp-tab="trajectories"]');
|
||||
first.click();
|
||||
first.focus();
|
||||
first.dispatchEvent(new KeyboardEvent("keydown", {
|
||||
key: "ArrowRight",
|
||||
bubbles: true,
|
||||
}));
|
||||
const selected = root.querySelector(
|
||||
'[data-sp-tab][aria-selected="true"]',
|
||||
).dataset.spTab;
|
||||
root.querySelector('[data-sp-tab="reproduction"]').click();
|
||||
return {
|
||||
keyboardSelected: selected,
|
||||
visible: root.querySelector("[data-sp-panel]:not([hidden])")
|
||||
.dataset.spPanel,
|
||||
reproFields: root.querySelectorAll(".repro-fields article").length,
|
||||
};
|
||||
})()`);
|
||||
|
||||
await command("Emulation.setDeviceMetricsOverride", {
|
||||
width: 390,
|
||||
height: 844,
|
||||
deviceScaleFactor: 1,
|
||||
mobile: true,
|
||||
});
|
||||
await navigate("/deepseek/#sampling");
|
||||
const mobile = await evaluate(`(() => {
|
||||
const root = document.querySelector("[data-sampling-lab]");
|
||||
document.documentElement.style.scrollBehavior = "auto";
|
||||
window.scrollTo(0, root.getBoundingClientRect().top + window.scrollY);
|
||||
return {
|
||||
tabs: root.querySelectorAll("[data-sp-tab]").length,
|
||||
seedBars: root.querySelectorAll("[data-sp-seeds] button").length,
|
||||
documentOverflow: (
|
||||
document.documentElement.scrollWidth
|
||||
- document.documentElement.clientWidth
|
||||
),
|
||||
rootOverflow: root.scrollWidth - root.clientWidth,
|
||||
};
|
||||
})()`);
|
||||
await pause(300);
|
||||
await screenshot("/tmp/llm-atlas-sampling-mobile.png");
|
||||
|
||||
assert(overview.tabs === 4, `sampling tabs=${overview.tabs}`);
|
||||
assert(overview.panels === 4, `sampling panels=${overview.panels}`);
|
||||
assert(overview.seedBars === 8, `initial seed bars=${overview.seedBars}`);
|
||||
assert(overview.conditions === 8, `condition rows=${overview.conditions}`);
|
||||
assert(overview.edges === 10, `edge rows=${overview.edges}`);
|
||||
assert(overview.heroLabs?.startsWith("20"), `hero labs=${overview.heroLabs}`);
|
||||
assert(overview.activePanel === "trajectories", `active=${overview.activePanel}`);
|
||||
assert(overview.unique === "8 / 8", `initial unique=${overview.unique}`);
|
||||
assert(overview.eos === "5 / 8", `initial eos=${overview.eos}`);
|
||||
assert(overview.greedy === "NO", `initial greedy=${overview.greedy}`);
|
||||
assert(overview.documentOverflow === 0, `desktop overflow=${overview.documentOverflow}`);
|
||||
|
||||
assert(trajectorySwitch.unique === "2 / 8", `switched unique=${trajectorySwitch.unique}`);
|
||||
assert(trajectorySwitch.eos === "8 / 8", `switched eos=${trajectorySwitch.eos}`);
|
||||
assert(trajectorySwitch.greedy === "YES", `switched greedy=${trajectorySwitch.greedy}`);
|
||||
assert(trajectorySwitch.seedBars === 8, `switched seeds=${trajectorySwitch.seedBars}`);
|
||||
assert(trajectorySwitch.repeats >= 2, `repeat markers=${trajectorySwitch.repeats}`);
|
||||
assert(trajectorySwitch.selected === 1, `selected seeds=${trajectorySwitch.selected}`);
|
||||
assert(trajectorySwitch.focus.startsWith("R7"), `focus=${trajectorySwitch.focus}`);
|
||||
assert(trajectorySwitch.hash.includes("sha256"), `focus hash=${trajectorySwitch.hash}`);
|
||||
|
||||
assert(taskSwitch.systemX.panel === "tasks", `task panel=${taskSwitch.systemX.panel}`);
|
||||
assert(taskSwitch.systemX.math === "7 / 8 PASS", `system x math=${taskSwitch.systemX.math}`);
|
||||
assert(taskSwitch.systemX.code === "8 / 8 PASS", `system x code=${taskSwitch.systemX.code}`);
|
||||
assert(taskSwitch.period.code === "7 / 8 PASS", `period code=${taskSwitch.period.code}`);
|
||||
assert(taskSwitch.period.mathCells === 8, `math cells=${taskSwitch.period.mathCells}`);
|
||||
assert(taskSwitch.period.codeCells === 8, `code cells=${taskSwitch.period.codeCells}`);
|
||||
|
||||
assert(edgeSwitch.panel === "edges", `edge panel=${edgeSwitch.panel}`);
|
||||
assert(edgeSwitch.aligned === "77.3%", `edge aligned=${edgeSwitch.aligned}`);
|
||||
assert(edgeSwitch.nearest === "89.4%", `edge nearest=${edgeSwitch.nearest}`);
|
||||
assert(edgeSwitch.overlap === "1 / 14", `edge overlap=${edgeSwitch.overlap}`);
|
||||
assert(edgeSwitch.left === 8 && edgeSwitch.right === 8, `edge sets=${edgeSwitch.left}/${edgeSwitch.right}`);
|
||||
assert(edgeSwitch.highlighted >= 2, `edge highlights=${edgeSwitch.highlighted}`);
|
||||
|
||||
assert(keyboard.keyboardSelected === "tasks", `keyboard selected=${keyboard.keyboardSelected}`);
|
||||
assert(keyboard.visible === "reproduction", `repro visible=${keyboard.visible}`);
|
||||
assert(keyboard.reproFields === 8, `repro fields=${keyboard.reproFields}`);
|
||||
assert(mobile.tabs === 4 && mobile.seedBars === 8, `mobile controls=${mobile.tabs}/${mobile.seedBars}`);
|
||||
assert(mobile.documentOverflow === 0, `mobile document overflow=${mobile.documentOverflow}`);
|
||||
assert(mobile.rootOverflow === 0, `mobile root overflow=${mobile.rootOverflow}`);
|
||||
assert(exceptions.length === 0, `runtime exceptions: ${exceptions.join(" | ")}`);
|
||||
|
||||
console.log(JSON.stringify({
|
||||
overview,
|
||||
trajectorySwitch,
|
||||
taskSwitch,
|
||||
edgeSwitch,
|
||||
keyboard,
|
||||
mobile,
|
||||
exceptions,
|
||||
screenshots: [
|
||||
"/tmp/llm-atlas-sampling-desktop.png",
|
||||
"/tmp/llm-atlas-sampling-mobile.png",
|
||||
],
|
||||
}, null, 2));
|
||||
|
||||
socket.close();
|
||||
Reference in New Issue
Block a user