LocalAgent/app/metrics_logger.py

"""
度量指标记录和导出模块
用于记录需求分析相关的度量指标
"""

import json
from pathlib import Path
from datetime import datetime
from typing import Dict, Any


class MetricsLogger:
    """度量指标记录器"""
    
    def __init__(self, workspace: Path):
        """
        Args:
            workspace: 工作空间路径
        """
        self.workspace = workspace
        self.metrics_file = workspace / "metrics" / "requirement_analysis.json"
        self.metrics_file.parent.mkdir(exist_ok=True)
        
        # 加载现有指标
        self.metrics = self._load_metrics()
    
    def _load_metrics(self) -> Dict[str, Any]:
        """加载现有指标"""
        if self.metrics_file.exists():
            try:
                with open(self.metrics_file, 'r', encoding='utf-8') as f:
                    return json.load(f)
            except Exception:
                pass
        
        # 返回默认指标结构
        return {
            'total_tasks': 0,
            'clarification_triggered': 0,
            'direct_execution': 0,
            'user_modifications': 0,
            'ambiguity_failures': 0,
            'history': []
        }
    
    def _save_metrics(self):
        """保存指标到文件"""
        try:
            with open(self.metrics_file, 'w', encoding='utf-8') as f:
                json.dump(self.metrics, f, ensure_ascii=False, indent=2)
        except Exception as e:
            print(f"保存度量指标失败: {e}")
    
    def record_task(self, task_type: str, details: Dict[str, Any] = None):
        """
        记录任务
        
        Args:
            task_type: 任务类型 (clarification/direct_execution/modification/failure)
            details: 任务详情
        """
        self.metrics['total_tasks'] += 1
        
        if task_type == 'clarification':
            self.metrics['clarification_triggered'] += 1
        elif task_type == 'direct_execution':
            self.metrics['direct_execution'] += 1
        elif task_type == 'modification':
            self.metrics['user_modifications'] += 1
        elif task_type == 'failure':
            self.metrics['ambiguity_failures'] += 1
        
        # 记录历史
        record = {
            'timestamp': datetime.now().isoformat(),
            'type': task_type,
            'details': details or {}
        }
        self.metrics['history'].append(record)
        
        # 限制历史记录数量
        if len(self.metrics['history']) > 1000:
            self.metrics['history'] = self.metrics['history'][-1000:]
        
        self._save_metrics()
    
    def get_summary(self) -> Dict[str, Any]:
        """获取指标摘要"""
        total = self.metrics['total_tasks']
        if total == 0:
            return {
                'total_tasks': 0,
                'clarification_rate': 0.0,
                'direct_execution_rate': 0.0,
                'modification_rate': 0.0,
                'failure_rate': 0.0
            }
        
        return {
            'total_tasks': total,
            'clarification_triggered': self.metrics['clarification_triggered'],
            'direct_execution': self.metrics['direct_execution'],
            'user_modifications': self.metrics['user_modifications'],
            'ambiguity_failures': self.metrics['ambiguity_failures'],
            'clarification_rate': self.metrics['clarification_triggered'] / total,
            'direct_execution_rate': self.metrics['direct_execution'] / total,
            'modification_rate': self.metrics['user_modifications'] / total,
            'failure_rate': self.metrics['ambiguity_failures'] / total
        }
    
    def export_report(self, output_path: Path = None) -> str:
        """
        导出度量报告
        
        Args:
            output_path: 输出路径，如果为None则返回字符串
            
        Returns:
            报告内容
        """
        summary = self.get_summary()
        
        report = f"""# 需求分析度量报告

生成时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}

## 总体统计

- 总任务数: {summary['total_tasks']}
- 澄清触发次数: {summary['clarification_triggered']}
- 直接执行次数: {summary['direct_execution']}
- 用户二次修改次数: {summary['user_modifications']}
- 需求歧义导致失败次数: {summary['ambiguity_failures']}

## 比率分析

- 澄清触发率: {summary['clarification_rate']:.1%}
- 直接执行率: {summary['direct_execution_rate']:.1%}
- 用户二次修改率: {summary['modification_rate']:.1%}
- 需求歧义失败率: {summary['failure_rate']:.1%}

## 建议

"""
        
        # 根据指标给出建议
        if summary['failure_rate'] > 0.2:
            report += "- ⚠️ 需求歧义失败率较高，建议提高澄清触发阈值\n"
        
        if summary['clarification_rate'] < 0.1:
            report += "- ⚠️ 澄清触发率较低，可能存在模糊需求被直接执行的风险\n"
        
        if summary['modification_rate'] > 0.3:
            report += "- ⚠️ 用户二次修改率较高，说明初次生成的代码质量需要改进\n"
        
        if summary['direct_execution_rate'] > 0.8 and summary['failure_rate'] < 0.1:
            report += "- ✅ 直接执行率高且失败率低，需求分析效果良好\n"
        
        if output_path:
            output_path.parent.mkdir(parents=True, exist_ok=True)
            with open(output_path, 'w', encoding='utf-8') as f:
                f.write(report)
        
        return report