deepagents----/tests/debug_research_v2.py

"""
调试研究流程 V2 - 检查虚拟文件系统

使用方法：
    export PYTHONIOENCODING=utf-8 && python tests/debug_research_v2.py
"""

import sys
import os
import json
from datetime import datetime

# 添加项目根目录到Python路径
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from src.agents.coordinator import create_research_coordinator
from src.config import Config


def debug_research_with_files(question: str, depth: str = "quick"):
    """
    调试研究流程，重点检查虚拟文件系统

    Args:
        question: 研究问题
        depth: 深度模式
    """
    print("\n" + "🔬 " * 40)
    print("智能深度研究系统 - 调试模式 V2")
    print("🔬 " * 40)

    print(f"\n研究问题: {question}")
    print(f"深度模式: {depth}")
    print(f"开始时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")

    # 创建Agent
    print("\n" + "="*80)
    print("创建ResearchCoordinator Agent")
    print("="*80)

    try:
        agent = create_research_coordinator(
            question=question,
            depth=depth,
            format="technical",
            min_tier=3
        )
        print("✅ Agent创建成功")
    except Exception as e:
        print(f"❌ Agent创建失败: {e}")
        import traceback
        traceback.print_exc()
        return

    # 执行研究
    print("\n" + "="*80)
    print("执行研究流程")
    print("="*80)

    try:
        start_time = datetime.now()

        result = agent.invoke({
            "messages": [
                {
                    "role": "user",
                    "content": f"请开始研究这个问题：{question}"
                }
            ]
        })

        end_time = datetime.now()
        duration = (end_time - start_time).total_seconds()

        print(f"\n✅ 执行完成！耗时: {duration:.2f}秒")

        # 分析结果
        print("\n" + "="*80)
        print("结果分析")
        print("="*80)

        print(f"\n结果类型: {type(result)}")
        print(f"结果键: {list(result.keys())}")

        # 检查消息
        if 'messages' in result:
            messages = result['messages']
            print(f"\n📨 消息数量: {len(messages)}")

            print("\n所有消息内容:")
            for i, msg in enumerate(messages, 1):
                print(f"\n{'='*60}")
                print(f"消息 #{i}")
                print('='*60)

                # 检查消息类型
                msg_type = type(msg).__name__
                print(f"类型: {msg_type}")

                # 提取内容
                if hasattr(msg, 'content'):
                    content = msg.content
                    print(f"内容长度: {len(content)} 字符")

                    # 显示内容
                    if len(content) > 500:
                        print(f"\n内容预览:\n{content[:500]}...")
                    else:
                        print(f"\n完整内容:\n{content}")

                # 检查其他属性
                if hasattr(msg, 'additional_kwargs'):
                    kwargs = msg.additional_kwargs
                    if kwargs:
                        print(f"\n额外参数: {kwargs}")

                if hasattr(msg, 'tool_calls'):
                    tool_calls = msg.tool_calls
                    if tool_calls:
                        print(f"\n工具调用: {tool_calls}")

        # 检查文件系统
        if 'files' in result:
            files = result['files']
            print("\n" + "="*80)
            print("虚拟文件系统")
            print("="*80)
            print(f"\n📁 文件数量: {len(files)}")

            for file_path, file_info in files.items():
                print(f"\n{'='*60}")
                print(f"文件: {file_path}")
                print('='*60)

                # 显示文件信息
                if isinstance(file_info, dict):
                    for key, value in file_info.items():
                        if key == 'content':
                            if len(str(value)) > 300:
                                print(f"{key}: {str(value)[:300]}...")
                            else:
                                print(f"{key}: {value}")
                        else:
                            print(f"{key}: {value}")
                else:
                    if len(str(file_info)) > 300:
                        print(f"内容: {str(file_info)[:300]}...")
                    else:
                        print(f"内容: {file_info}")

        # 保存完整结果
        print("\n" + "="*80)
        print("保存调试结果")
        print("="*80)

        output_dir = "outputs/debug"
        os.makedirs(output_dir, exist_ok=True)
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")

        # 保存JSON结果
        output_file = os.path.join(output_dir, f"debug_v2_{timestamp}.json")
        with open(output_file, 'w', encoding='utf-8') as f:
            # 序列化结果
            serialized_result = {
                "question": question,
                "depth": depth,
                "duration_seconds": duration,
                "messages": [
                    {
                        "type": type(msg).__name__,
                        "content": msg.content if hasattr(msg, 'content') else str(msg)
                    }
                    for msg in result.get('messages', [])
                ],
                "files": {
                    path: str(content)
                    for path, content in result.get('files', {}).items()
                }
            }
            json.dump(serialized_result, f, ensure_ascii=False, indent=2)

        print(f"✅ 调试结果已保存到: {output_file}")

    except KeyboardInterrupt:
        print("\n\n⚠️  用户中断执行")
    except Exception as e:
        print(f"\n\n❌ 执行失败: {e}")
        import traceback
        traceback.print_exc()


if __name__ == "__main__":
    question = "Python asyncio最佳实践"
    debug_research_with_files(question, depth="quick")