AIclinicalresearch/backend/scripts/test-unifuncs-clinicaltrials.ts

/**
 * Unifuncs API — ClinicalTrials.gov 专项测试
 * 
 * ClinicalTrials.gov 在上一轮测试中超时，本脚本用多种策略针对性测试
 * 
 * 运行方式：
 *   cd backend
 *   npx tsx scripts/test-unifuncs-clinicaltrials.ts
 */

const API_KEY = 'sk-2fNwqUH73elGq0aDKJEM4ReqP7Ry0iqHo4OXyidDe2WpQ9XQ';
const BASE_URL = 'https://api.unifuncs.com/deepsearch/v1';
const POLL_INTERVAL = 10000;
const MAX_WAIT = 900000; // 15 分钟（上次 10 分钟超时，放宽到 15 分钟）

interface TestStrategy {
  id: string;
  name: string;
  query: string;
  domainScope: string[];
  maxDepth: number;
  introduction: string;
}

const STRATEGIES: TestStrategy[] = [
  {
    id: 'A',
    name: '英文查询 + 限定 clinicaltrials.gov',
    query: 'Statin therapy for cardiovascular disease prevention, randomized controlled trials, recent 5 years',
    domainScope: ['https://clinicaltrials.gov/'],
    maxDepth: 10,
    introduction: 'You are a clinical research expert. Search ClinicalTrials.gov for relevant clinical trials. Return trial NCT numbers, titles, status, and links.',
  },
  {
    id: 'B',
    name: '英文查询 + 不限域名（观察是否自然覆盖 clinicaltrials.gov）',
    query: 'Find clinical trials on statins for cardiovascular disease prevention registered on ClinicalTrials.gov, list NCT numbers and trial details',
    domainScope: [],
    maxDepth: 10,
    introduction: 'You are a clinical research expert. Focus on finding registered clinical trials from ClinicalTrials.gov. Return NCT numbers, trial titles, status, and direct links to clinicaltrials.gov.',
  },
  {
    id: 'C',
    name: '中文查询 + 限定 clinicaltrials.gov + 高深度',
    query: '他汀类药物预防心血管疾病的临床试验，请在 ClinicalTrials.gov 上查找注册的 RCT，返回 NCT 编号和试验详情',
    domainScope: ['https://clinicaltrials.gov/'],
    maxDepth: 15,
    introduction: '你是临床试验检索专家。请在 ClinicalTrials.gov 上搜索相关临床试验，返回 NCT 编号、试验标题、状态、链接。',
  },
  {
    id: 'D',
    name: '简短英文查询 + 限定 clinicaltrials.gov + 低深度',
    query: 'statin cardiovascular RCT',
    domainScope: ['https://clinicaltrials.gov/'],
    maxDepth: 5,
    introduction: 'Search ClinicalTrials.gov for statin cardiovascular trials. Return NCT IDs and links.',
  },
];

async function createTask(strategy: TestStrategy): Promise<{ taskId: string } | { error: string }> {
  const payload: any = {
    model: 's2',
    messages: [{ role: 'user', content: strategy.query }],
    introduction: strategy.introduction,
    max_depth: strategy.maxDepth,
    reference_style: 'link',
    generate_summary: true,
  };
  if (strategy.domainScope.length > 0) {
    payload.domain_scope = strategy.domainScope;
  }

  try {
    const res = await fetch(`${BASE_URL}/create_task`, {
      method: 'POST',
      headers: {
        'Authorization': `Bearer ${API_KEY}`,
        'Content-Type': 'application/json',
      },
      body: JSON.stringify(payload),
    });
    const json = await res.json() as any;
    if (json.code === 0 && json.data?.task_id) {
      return { taskId: json.data.task_id };
    }
    return { error: `API error: ${json.message || JSON.stringify(json)}` };
  } catch (err: any) {
    return { error: `Request failed: ${err.message}` };
  }
}

async function queryTask(taskId: string): Promise<any> {
  const params = new URLSearchParams({ task_id: taskId });
  const res = await fetch(`${BASE_URL}/query_task?${params.toString()}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` },
  });
  return res.json();
}

function sleep(ms: number): Promise<void> {
  return new Promise(resolve => setTimeout(resolve, ms));
}

function extractLinks(content: string): { ctLinks: string[]; nctIds: string[]; otherLinks: string[] } {
  const urlPattern = /https?:\/\/[^\s)\]"'>]+/gi;
  const allUrls = [...new Set(content.match(urlPattern) || [])];
  const ctLinks = allUrls.filter(u => u.includes('clinicaltrials.gov'));
  const otherLinks = allUrls.filter(u => !u.includes('clinicaltrials.gov'));

  const nctPattern = /NCT\d{6,}/gi;
  const nctIds = [...new Set(content.match(nctPattern) || [])];

  return { ctLinks, nctIds, otherLinks };
}

async function testStrategy(strategy: TestStrategy): Promise<void> {
  const startTime = Date.now();
  console.log(`\n${'━'.repeat(80)}`);
  console.log(`策略 ${strategy.id}: ${strategy.name}`);
  console.log(`查询: "${strategy.query}"`);
  console.log(`domain_scope: ${strategy.domainScope.length > 0 ? strategy.domainScope.join(', ') : '不限'}`);
  console.log(`max_depth: ${strategy.maxDepth}`);
  console.log(`${'━'.repeat(80)}`);

  const createResult = await createTask(strategy);
  if ('error' in createResult) {
    console.log(`  ❌ 创建失败: ${createResult.error}`);
    return;
  }

  console.log(`  → task_id: ${createResult.taskId}`);

  const deadline = Date.now() + MAX_WAIT;
  let lastProgress = '';

  while (Date.now() < deadline) {
    await sleep(POLL_INTERVAL);

    try {
      const json = await queryTask(createResult.taskId) as any;
      const data = json.data;
      if (!data) continue;

      const progress = data.progress ? `${data.progress.current}/${data.progress.total}` : '?';
      const stats = data.statistics || {};
      const statusLine = `${data.status} (${progress}) 搜索${stats.search_count || 0} 阅读${stats.read_count || 0} 迭代${stats.iterations || 0}`;

      if (statusLine !== lastProgress) {
        const elapsed = ((Date.now() - startTime) / 1000).toFixed(0);
        console.log(`  [${elapsed}s] ${statusLine}`);
        lastProgress = statusLine;
      }

      if (data.status === 'completed') {
        const content = data.result?.content || '';
        const reasoning = data.result?.reasoning_content || '';
        const elapsed = ((Date.now() - startTime) / 1000).toFixed(0);

        const { ctLinks, nctIds, otherLinks } = extractLinks(content);
        const { ctLinks: rCtLinks, nctIds: rNctIds } = extractLinks(reasoning);

        console.log(`\n  ✅ 完成 (${elapsed}s)`);
        console.log(`  ├─ 内容长度: ${content.length} 字符`);
        console.log(`  ├─ 推理长度: ${reasoning.length} 字符`);
        console.log(`  ├─ 搜索/阅读: ${stats.search_count || 0}/${stats.read_count || 0}`);
        console.log(`  ├─ ClinicalTrials 链接 (content): ${ctLinks.length} 个`);
        console.log(`  ├─ ClinicalTrials 链接 (reasoning): ${rCtLinks.length} 个`);
        console.log(`  ├─ NCT 编号 (content): ${nctIds.length} 个 → ${nctIds.slice(0, 10).join(', ')}${nctIds.length > 10 ? '...' : ''}`);
        console.log(`  ├─ NCT 编号 (reasoning): ${rNctIds.length} 个`);
        console.log(`  ├─ 其他链接: ${otherLinks.length} 个`);
        console.log(`  └─ Token: ${JSON.stringify(stats.token_usage || {})}`);

        if (ctLinks.length > 0) {
          console.log(`\n  📎 ClinicalTrials.gov 链接示例:`);
          ctLinks.slice(0, 8).forEach((link, i) => console.log(`     ${i + 1}. ${link}`));
        }

        if (ctLinks.length === 0 && nctIds.length === 0) {
          console.log(`\n  ⚠️ 内容预览 (前 500 字):`);
          console.log(`  ${content.slice(0, 500).replace(/\n/g, '\n  ')}`);
        }

        return;
      }

      if (data.status === 'failed') {
        console.log(`  ❌ 失败: ${data.result?.content || '未知错误'}`);
        return;
      }
    } catch (err: any) {
      // 轮询网络错误，继续重试
    }
  }

  console.log(`  ⏰ 超时 (${MAX_WAIT / 1000}s)`);
}

async function main() {
  console.log('╔════════════════════════════════════════════════════════════╗');
  console.log('║   ClinicalTrials.gov 专项测试 — 4 种策略并行              ║');
  console.log('╚════════════════════════════════════════════════════════════╝');
  console.log(`超时: ${MAX_WAIT / 1000}s | 轮询: ${POLL_INTERVAL / 1000}s`);

  // 并行执行所有策略
  await Promise.all(STRATEGIES.map(s => testStrategy(s)));

  console.log(`\n${'═'.repeat(80)}`);
  console.log('所有策略测试完成！');
  console.log(`${'═'.repeat(80)}`);
}

main().catch(err => {
  console.error('脚本执行失败:', err);
  process.exit(1);
});