AIclinicalresearch/backend/src/scripts/test-closeai.ts

/**
 * CloseAI集成测试脚本
 * 
 * 测试通过CloseAI代理访问GPT-5和Claude-4.5模型
 * 
 * 运行方式：
 * ```bash
 * cd backend
 * npx tsx src/scripts/test-closeai.ts
 * ```
 * 
 * 环境变量要求：
 * - CLOSEAI_API_KEY: CloseAI API密钥
 * - CLOSEAI_OPENAI_BASE_URL: OpenAI端点
 * - CLOSEAI_CLAUDE_BASE_URL: Claude端点
 * 
 * 参考文档：docs/02-通用能力层/01-LLM大模型网关/03-CloseAI集成指南.md
 */

import { LLMFactory } from '../common/llm/adapters/LLMFactory.js';
import { config } from '../config/env.js';

/**
 * 测试配置验证
 */
function validateConfig() {
  console.log('🔍 验证环境配置...\n');
  
  const checks = [
    {
      name: 'CLOSEAI_API_KEY',
      value: config.closeaiApiKey,
      required: true,
    },
    {
      name: 'CLOSEAI_OPENAI_BASE_URL',
      value: config.closeaiOpenaiBaseUrl,
      required: true,
    },
    {
      name: 'CLOSEAI_CLAUDE_BASE_URL',
      value: config.closeaiClaudeBaseUrl,
      required: true,
    },
  ];

  let allValid = true;

  for (const check of checks) {
    const status = check.value ? '✅' : '❌';
    console.log(`${status} ${check.name}: ${check.value ? '已配置' : '未配置'}`);
    
    if (check.required && !check.value) {
      allValid = false;
    }
  }

  console.log('');

  if (!allValid) {
    throw new Error('环境配置不完整，请检查 .env 文件');
  }

  console.log('✅ 环境配置验证通过\n');
}

/**
 * 测试GPT-5-Pro
 */
async function testGPT5() {
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
  console.log('1️⃣  测试 GPT-5-Pro');
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  try {
    const gpt5 = LLMFactory.getAdapter('gpt-5');
    
    console.log('📤 发送测试请求...');
    console.log('提示词: "你好，请用一句话介绍你自己。"\n');

    const startTime = Date.now();
    
    const response = await gpt5.chat([
      {
        role: 'user',
        content: '你好，请用一句话介绍你自己。',
      },
    ]);

    const duration = Date.now() - startTime;

    console.log('📥 收到响应:\n');
    console.log(`模型: ${response.model}`);
    console.log(`内容: ${response.content}`);
    console.log(`耗时: ${duration}ms`);
    
    if (response.usage) {
      console.log(`Token使用: ${response.usage.totalTokens} (输入: ${response.usage.promptTokens}, 输出: ${response.usage.completionTokens})`);
    }
    
    console.log('\n✅ GPT-5测试通过\n');
    return true;
  } catch (error) {
    console.error('\n❌ GPT-5测试失败:', error);
    return false;
  }
}

/**
 * 测试Claude-4.5-Sonnet
 */
async function testClaude() {
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
  console.log('2️⃣  测试 Claude-4.5-Sonnet');
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  try {
    const claude = LLMFactory.getAdapter('claude-4.5');
    
    console.log('📤 发送测试请求...');
    console.log('提示词: "你好，请用一句话介绍你自己。"\n');

    const startTime = Date.now();
    
    const response = await claude.chat([
      {
        role: 'user',
        content: '你好，请用一句话介绍你自己。',
      },
    ]);

    const duration = Date.now() - startTime;

    console.log('📥 收到响应:\n');
    console.log(`模型: ${response.model}`);
    console.log(`内容: ${response.content}`);
    console.log(`耗时: ${duration}ms`);
    
    if (response.usage) {
      console.log(`Token使用: ${response.usage.totalTokens} (输入: ${response.usage.promptTokens}, 输出: ${response.usage.completionTokens})`);
    }
    
    console.log('\n✅ Claude测试通过\n');
    return true;
  } catch (error) {
    console.error('\n❌ Claude测试失败:', error);
    return false;
  }
}

/**
 * 测试文献筛选场景（实际应用）
 */
async function testLiteratureScreening() {
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
  console.log('3️⃣  测试文献筛选场景（双模型对比）');
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  const testLiterature = {
    title: 'Deep learning in medical imaging: A systematic review',
    abstract: 'Background: Deep learning has shown remarkable performance in various medical imaging tasks. Methods: We systematically reviewed 150 studies on deep learning applications in radiology, pathology, and ophthalmology. Results: Deep learning models achieved high accuracy (>90%) in most tasks. Conclusion: Deep learning is a promising tool for medical image analysis.',
  };

  const picoPrompt = `
请根据以下PICO标准，判断这篇文献是否应该纳入系统评价：

**PICO标准：**
- Population: 成年患者
- Intervention: 深度学习模型
- Comparison: 传统机器学习方法
- Outcome: 诊断准确率

**文献信息：**
标题：${testLiterature.title}
摘要：${testLiterature.abstract}

请输出JSON格式：
{
  "decision": "include/exclude/uncertain",
  "reason": "判断理由",
  "confidence": 0.0-1.0
}
`;

  try {
    console.log('📤 使用DeepSeek和GPT-5进行双模型对比筛选...\n');

    // 并行调用两个模型
    const [deepseekAdapter, gpt5Adapter] = [
      LLMFactory.getAdapter('deepseek-v3'),
      LLMFactory.getAdapter('gpt-5'),
    ];

    const startTime = Date.now();

    const [deepseekResponse, gpt5Response] = await Promise.all([
      deepseekAdapter.chat([{ role: 'user', content: picoPrompt }]),
      gpt5Adapter.chat([{ role: 'user', content: picoPrompt }]),
    ]);

    const duration = Date.now() - startTime;

    console.log('📥 DeepSeek响应:');
    console.log(deepseekResponse.content);
    console.log('');

    console.log('📥 GPT-5响应:');
    console.log(gpt5Response.content);
    console.log('');

    console.log(`⏱️  总耗时: ${duration}ms（并行）`);
    console.log(`💰 总Token: ${(deepseekResponse.usage?.totalTokens || 0) + (gpt5Response.usage?.totalTokens || 0)}`);

    // 尝试解析JSON结果（简单验证）
    try {
      const deepseekDecision = JSON.parse(deepseekResponse.content);
      const gpt5Decision = JSON.parse(gpt5Response.content);

      console.log('\n✅ 双模型筛选结果:');
      console.log(`DeepSeek决策: ${deepseekDecision.decision} (置信度: ${deepseekDecision.confidence})`);
      console.log(`GPT-5决策: ${gpt5Decision.decision} (置信度: ${gpt5Decision.confidence})`);

      if (deepseekDecision.decision === gpt5Decision.decision) {
        console.log('✅ 两个模型一致，共识度高');
      } else {
        console.log('⚠️  两个模型不一致，建议人工复核或启用第三方仲裁（Claude）');
      }
    } catch (parseError) {
      console.log('⚠️  JSON解析失败（测试环境，实际应用需要优化提示词）');
    }

    console.log('\n✅ 文献筛选场景测试通过\n');
    return true;
  } catch (error) {
    console.error('\n❌ 文献筛选场景测试失败:', error);
    return false;
  }
}

/**
 * 测试流式调用（可选）
 */
async function testStreamMode() {
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
  console.log('4️⃣  测试流式调用（GPT-5）');
  console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

  try {
    const gpt5 = LLMFactory.getAdapter('gpt-5');
    
    console.log('📤 发送流式请求...');
    console.log('提示词: "请写一首关于人工智能的短诗（4行）"\n');
    console.log('📥 流式响应:\n');

    const startTime = Date.now();
    let fullContent = '';
    let chunkCount = 0;

    for await (const chunk of gpt5.chatStream([
      {
        role: 'user',
        content: '请写一首关于人工智能的短诗（4行）',
      },
    ])) {
      if (chunk.content) {
        process.stdout.write(chunk.content);
        fullContent += chunk.content;
        chunkCount++;
      }

      if (chunk.done) {
        const duration = Date.now() - startTime;
        console.log('\n');
        console.log(`\n⏱️  耗时: ${duration}ms`);
        console.log(`📦 Chunk数: ${chunkCount}`);
        console.log(`📝 总字符数: ${fullContent.length}`);
        
        if (chunk.usage) {
          console.log(`💰 Token使用: ${chunk.usage.totalTokens}`);
        }
      }
    }

    console.log('\n✅ 流式调用测试通过\n');
    return true;
  } catch (error) {
    console.error('\n❌ 流式调用测试失败:', error);
    return false;
  }
}

/**
 * 主测试函数
 */
async function main() {
  console.log('╔═══════════════════════════════════════════════════╗');
  console.log('║   🧪 CloseAI集成测试                              ║');
  console.log('║   测试GPT-5和Claude-4.5通过CloseAI代理访问        ║');
  console.log('╚═══════════════════════════════════════════════════╝\n');

  try {
    // 验证配置
    validateConfig();

    // 测试结果
    const results = {
      gpt5: false,
      claude: false,
      literatureScreening: false,
      stream: false,
    };

    // 1. 测试GPT-5
    results.gpt5 = await testGPT5();

    // 2. 测试Claude-4.5
    results.claude = await testClaude();

    // 3. 测试文献筛选场景
    results.literatureScreening = await testLiteratureScreening();

    // 4. 测试流式调用（可选）
    results.stream = await testStreamMode();

    // 总结
    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
    console.log('📊 测试总结');
    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

    const allPassed = Object.values(results).every((r) => r === true);

    console.log(`GPT-5测试:          ${results.gpt5 ? '✅ 通过' : '❌ 失败'}`);
    console.log(`Claude测试:         ${results.claude ? '✅ 通过' : '❌ 失败'}`);
    console.log(`文献筛选场景:       ${results.literatureScreening ? '✅ 通过' : '❌ 失败'}`);
    console.log(`流式调用测试:       ${results.stream ? '✅ 通过' : '❌ 失败'}`);

    console.log('\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

    if (allPassed) {
      console.log('🎉 所有测试通过！CloseAI集成成功！');
      console.log('\n✅ 可以在ASL模块中使用GPT-5和Claude-4.5进行双模型对比筛选');
      console.log('✅ 支持三模型共识仲裁（DeepSeek + GPT-5 + Claude）');
      console.log('✅ 支持流式调用，适用于实时响应场景\n');
      process.exit(0);
    } else {
      console.error('⚠️  部分测试失败，请检查配置和网络连接\n');
      process.exit(1);
    }
  } catch (error) {
    console.error('❌ 测试执行失败:', error);
    process.exit(1);
  }
}

// 运行测试
main();