fix: release v1.0.3 预设渲染与语言搬运监督修复

web_platform/e2e/website.live.spec.ts

@@ -1,9 +1,12 @@
 import { expect, test } from '@playwright/test';
 import { writeFile } from 'node:fs/promises';
-import { loadWebsiteRobot, runWebsiteCommand } from './website.helpers';
+import { collectRobotResults, loadWebsiteRobot, runWebsiteCommand } from './website.helpers';
 
 test('显式授权：公网内置模型，前进/转向/抓放，无手填密钥或自动重试', async ({ page }, info) => {
-  test.skip(process.env.CADWORLD_LIVE_API !== '1', '仅经用户授权后运行，会消耗服务器公共额度');
+  test.skip(
+    process.env.CADWORLD_LIVE_API !== '1' || process.env.CADWORLD_LIVE_PRESET === '1',
+    '仅经用户授权后运行；预设专项测试不重复执行运动测试',
+  );
   test.setTimeout(360000);
   const calls = { command: 0, plan: 0, decide: 0, blocked: 0 };
   let csrf = '',
@@ -86,3 +89,87 @@ test('显式授权：公网内置模型，前进/转向/抓放，无手填密钥
   }
   expect(cleanup).toBe(true);
 });
+
+test('显式授权：空工作台默认预设指令完成真实模型抓放', async ({ page }, info) => {
+  test.skip(
+    process.env.CADWORLD_LIVE_API !== '1' || process.env.CADWORLD_LIVE_PRESET !== '1',
+    '仅在显式选择预设专项实测时调用付费 API',
+  );
+  test.setTimeout(360000);
+  const calls = { command: 0, plan: 0, decide: 0, blocked: 0 };
+  let csrf = '',
+    cleanup = false;
+  const captures: Promise<void>[] = [];
+  page.on('response', (response) => {
+    if (response.url().endsWith('/session') && response.request().method() === 'POST')
+      captures.push(
+        response.json().then((value) => {
+          csrf = value.csrfToken;
+        }),
+      );
+  });
+  await page.route('**/api/decision/v1/**', async (route) => {
+    const endpoint = new URL(route.request().url()).pathname.split('/').at(-1);
+    if (endpoint === 'command' || endpoint === 'plan' || endpoint === 'decide') {
+      if (calls[endpoint] >= { command: 1, plan: 1, decide: 13 }[endpoint]) {
+        calls.blocked++;
+        await route.abort();
+        return;
+      }
+      calls[endpoint]++;
+    } else if (endpoint === 'test') {
+      calls.blocked++;
+      await route.abort();
+      return;
+    }
+    await route.continue();
+  });
+  try {
+    await collectRobotResults(page);
+    await page.goto('/');
+    await page.getByRole('tab', { name: '控制台', exact: true }).click();
+    await page.getByRole('button', { name: '机器人语言控制', exact: true }).click();
+    const panel = page.getByLabel('机器人语言控制', { exact: true });
+    await panel.getByRole('button', { name: '载入预设场景' }).click();
+    await expect(panel.getByRole('status')).toContainText('预设已载入并暂停', { timeout: 120000 });
+    await expect(panel.getByRole('textbox', { name: '机器人指令' })).toHaveValue('把方块搬到 B 区');
+    const result = await runWebsiteCommand(page, '把方块搬到 B 区', info, 'live-default-preset');
+    expect(result.goal).toEqual([0.257, 0.75, 0.128]);
+    expect(result.transported).toBeGreaterThan(0.7);
+    expect(result.sample.onGoalSupport).toBe(true);
+    expect(result.llmCalls).toBe(2);
+    expect(result.jevCalls).toBe(14);
+    expect(calls).toEqual({ command: 1, plan: 1, decide: 13, blocked: 0 });
+    await page.screenshot({ path: info.outputPath('live-default-preset.png') });
+  } finally {
+    await Promise.all(captures);
+    if (csrf)
+      cleanup = await page
+        .evaluate(
+          async (token) =>
+            (
+              await fetch('/api/decision/v1/session', {
+                method: 'DELETE',
+                headers: { 'Content-Type': 'application/json', 'X-CSRF-Token': token },
+                body: '{}',
+              })
+            ).status === 200,
+          csrf,
+        )
+        .catch(() => false);
+    await writeFile(
+      info.outputPath('live-default-summary.json'),
+      JSON.stringify(
+        {
+          calls,
+          sessionDestroyed: cleanup,
+          maximumUpstreamCalls: { llm: 2, jev: 14 },
+          retries: 0,
+        },
+        null,
+        2,
+      ),
+    );
+  }
+  expect(cleanup).toBe(true);
+});