去除ROS2相关内容，新增一键启动脚本

tools/test_validate/test_validity.py

@@ -17,7 +17,7 @@ SUMMARY_CSV = "test_summary.csv"
 LOG_FILE = "api_test_log.txt"
 
 # 测试参数
-TESTS_PER_INSTRUCTION = 10
+TESTS_PER_INSTRUCTION = 1
 MAX_RETRIES = 3
 RETRY_DELAY = 2
 
@@ -207,20 +207,38 @@ def read_instructions(filename):
         return []
 
 def write_log_entry(log_file, instruction_idx, run_number, prompt, result):
-    """写入详细日志"""
+    """写入详细日志，包含完整的API响应"""
     timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
     
     with open(log_file, 'a', encoding='utf-8') as f:
         f.write(f"\n{'='*80}\n")
         f.write(f"指令 #{instruction_idx} - 运行 #{run_number} - {timestamp}\n")
         f.write(f"HTTP状态: {result.get('http_status', 'N/A')}\n")
-        f.write(f"指令: {prompt}\n")
+        f.write(f"原始指令: {prompt}\n")
         f.write(f"尝试次数: {result['attempts']}\n")
         f.write(f"响应时间: {result['response_time']:.2f}秒\n")
         f.write(f"结果: {'✅ 成功' if result['success'] else '❌ 失败'}\n")
         
-        if result['success']:
-            f.write("验证结果:\n")
+        if result['success'] and result.get('data'):
+            data = result['data']
+            
+            # 提取并记录组织后的prompt（如果存在）
+            organized_prompt = None
+            if isinstance(data, dict):
+                organized_prompt = data.get("organized_prompt") or \
+                                 data.get("processed_prompt") or \
+                                 data.get("final_prompt") or \
+                                 data.get("enhanced_prompt") or \
+                                 data.get("user_prompt_enhanced")
+            
+            if organized_prompt:
+                f.write(f"\n📝 组织后的Prompt:\n")
+                f.write(f"{organized_prompt}\n")
+            else:
+                f.write(f"\n📝 组织后的Prompt: (未在响应中返回)\n")
+            
+            # 记录验证结果
+            f.write("\n验证结果:\n")
             for check_name, check_result in result['validation_checks'].items():
                 f.write(f"  {check_name}: {'✅' if check_result else '❌'}\n")
             
@@ -229,8 +247,27 @@ def write_log_entry(log_file, instruction_idx, run_number, prompt, result):
             
             if result['invalid_conditions']:
                 f.write(f"⚠️  无效条件节点: {result['invalid_conditions']}\n")
+            
+            # 记录完整的API响应
+            f.write(f"\n完整API响应:\n")
+            try:
+                response_json = json.dumps(data, indent=2, ensure_ascii=False)
+                f.write(response_json)
+                f.write("\n")
+            except Exception as e:
+                f.write(f"⚠️  无法序列化响应数据: {e}\n")
+                f.write(f"原始数据: {str(data)}\n")
         else:
             f.write(f"错误信息: {result['error']}\n")
+            # 即使失败也尝试记录响应数据（如果有）
+            if result.get('data'):
+                f.write(f"\n部分响应数据:\n")
+                try:
+                    response_json = json.dumps(result['data'], indent=2, ensure_ascii=False)
+                    f.write(response_json)
+                    f.write("\n")
+                except Exception:
+                    f.write(f"原始数据: {str(result['data'])}\n")
 
 def generate_summary_report(instructions, results_summary):
     """
@@ -311,6 +348,10 @@ def main():
             write_log_entry(LOG_FILE, instruction_idx, run_number, prompt, result)
             
             # 记录结果
+            plan_id = ""
+            if result.get("success") and result.get("data") and isinstance(result["data"], dict):
+                plan_id = result["data"].get("plan_id", "")
+            
             detailed_result = {
                 "instruction_index": instruction_idx,
                 "instruction": prompt,
@@ -318,7 +359,7 @@ def main():
                 "success": result["success"],
                 "attempts": result["attempts"],
                 "response_time": result["response_time"],
-                "http_status": result.get("http_status"),
+                "plan_id": plan_id,
                 "error": result["error"] or "",
                 "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S")
             }
@@ -363,6 +404,10 @@ def main():
     # 生成统计摘要
     generate_summary_report(instructions, results_summary)
     
+    # 计算总统计
+    total_tests = len(instructions) * TESTS_PER_INSTRUCTION
+    total_successful = sum(summary['success_count'] for summary in results_summary)
+    
     # 打印最终统计
     print(f"\n{'='*60}")
     print("📈 最终测试统计")
@@ -370,7 +415,10 @@ def main():
     print(f"总测试次数: {total_tests}")
     print(f"成功次数: {total_successful}")
     print(f"失败次数: {total_tests - total_successful}")
-    print(f"总成功率: {(total_successful / total_tests * 100):.2f}%")
+    if total_tests > 0:
+        print(f"总成功率: {(total_successful / total_tests * 100):.2f}%")
+    else:
+        print(f"总成功率: N/A")
     
     # 打印每个指令的统计
     print(f"\n📋 每个指令的统计:")