去除ROS2相关内容，新增一键启动脚本

tools/response.json

@@ -1,149 +0,0 @@
-{
-    "plan_id": "9f743b03-8ba7-4a06-9260-337463887fc2",
-    "root": {
-        "children": [
-            {
-                "children": [
-                    {
-                        "name": "preflight_checks",
-                        "params": {
-                            "check_level": "comprehensive"
-                        },
-                        "type": "action"
-                    },
-                    {
-                        "name": "takeoff",
-                        "params": {
-                            "altitude": 2
-                        },
-                        "type": "action"
-                    },
-                    {
-                        "name": "fly_to_waypoint",
-                        "params": {
-                            "acceptance_radius": 2,
-                            "x": 5,
-                            "y": 3,
-                            "z": 2
-                        },
-                        "type": "action"
-                    },
-                    {
-                        "children": [
-                            {
-                                "children": [
-                                    {
-                                        "name": "loiter",
-                                        "params": {
-                                            "duration": 10
-                                        },
-                                        "type": "action"
-                                    },
-                                    {
-                                        "name": "object_detect",
-                                        "params": {
-                                            "count": 1,
-                                            "description": "学生",
-                                            "target_class": "person"
-                                        },
-                                        "type": "action"
-                                    }
-                                ],
-                                "name": "DirectDetectionSequence",
-                                "type": "Sequence"
-                            },
-                            {
-                                "name": "search_pattern",
-                                "params": {
-                                    "center_x": 5,
-                                    "center_y": 3,
-                                    "center_z": 2,
-                                    "count": 1,
-                                    "description": "学生",
-                                    "pattern_type": "spiral",
-                                    "radius": 50,
-                                    "target_class": "person"
-                                },
-                                "type": "action"
-                            }
-                        ],
-                        "name": "TargetAcquisitionSelector",
-                        "params": {
-                            "memory": true
-                        },
-                        "type": "Selector"
-                    },
-                    {
-                        "name": "track_object",
-                        "params": {
-                            "description": "学生",
-                            "min_confidence": 0.7,
-                            "safe_distance": 10,
-                            "target_class": "person",
-                            "track_time": 20
-                        },
-                        "type": "action"
-                    },
-                    {
-                        "name": "land",
-                        "params": {
-                            "mode": "home"
-                        },
-                        "type": "action"
-                    }
-                ],
-                "name": "MainTrackingTask",
-                "type": "Sequence"
-            },
-            {
-                "children": [
-                    {
-                        "name": "battery_above",
-                        "params": {
-                            "threshold": 0.35
-                        },
-                        "type": "condition"
-                    },
-                    {
-                        "name": "gps_status",
-                        "params": {
-                            "min_satellites": 8
-                        },
-                        "type": "condition"
-                    },
-                    {
-                        "children": [
-                            {
-                                "name": "emergency_return",
-                                "params": {
-                                    "reason": "safety_breach"
-                                },
-                                "type": "action"
-                            },
-                            {
-                                "name": "land",
-                                "params": {
-                                    "mode": "home"
-                                },
-                                "type": "action"
-                            }
-                        ],
-                        "name": "EmergencyHandler",
-                        "type": "Sequence"
-                    }
-                ],
-                "name": "SafetyMonitor",
-                "params": {
-                    "memory": true
-                },
-                "type": "Selector"
-            }
-        ],
-        "name": "TrackingMission",
-        "params": {
-            "policy": "all_success"
-        },
-        "type": "Parallel"
-    },
-    "visualization_url": "/static/py_tree.png"
-}

tools/test_api.py

@@ -3,6 +3,8 @@
 
 import requests
 import json
+import os
+from datetime import datetime
 
 # --- Configuration ---
 # The base URL of your running FastAPI service
@@ -14,17 +16,49 @@ ENDPOINT = "/generate_plan"
 # The user prompt we will send for the test
 TEST_PROMPT = "已知目标检测红色气球危险性高于蓝色气球高于绿色气球，飞往搜索区搜索并锁定危险性最高的气球，对其跟踪30秒后进行打击操作"
 
+# Log file path (will be created in the same directory as this script)
+LOG_FILE = os.path.join(os.path.dirname(__file__), "api_test.log")
+
+def write_log(message, print_to_console=True):
+    """
+    Write a message to the log file in append mode.
+    Supports multi-line messages - only the first line gets timestamp.
+    
+    Args:
+        message: The message to write (can be multi-line)
+        print_to_console: Whether to also print to console (default: True)
+    """
+    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    
+    # Split message into lines and add timestamp to first line only
+    lines = message.split('\n')
+    log_entries = [f"[{timestamp}] {lines[0]}\n"]
+    for line in lines[1:]:
+        log_entries.append(f"{' ' * (len(timestamp) + 3)}{line}\n")  # Indent continuation lines
+    
+    try:
+        with open(LOG_FILE, "a", encoding="utf-8") as f:
+            f.writelines(log_entries)
+    except Exception as e:
+        print(f"⚠️  Warning: Failed to write to log file: {e}")
+    
+    if print_to_console:
+        print(message)
+
 def test_generate_plan():
     """
     Sends a request to the /generate_plan endpoint and validates the response.
+    All results are logged to the log file for continuous tracking.
     """
     url = BASE_URL + ENDPOINT
     payload = {"user_prompt": TEST_PROMPT}
     headers = {"Content-Type": "application/json"}
 
-    print("--- API Test: Generate Plan ---")
+    # Write separator and test start info to log
-    print(f"✅ URL: {url}")
+    write_log("=" * 80, print_to_console=False)
-    print(f"✅ Sending Prompt: \"{TEST_PROMPT}\"")
+    write_log("--- API Test: Generate Plan ---")
+    write_log(f"URL: {url}")
+    write_log(f"Sending Prompt: \"{TEST_PROMPT}\"")
 
     try:
         # Send the POST request
@@ -36,40 +70,85 @@ def test_generate_plan():
         # Parse the JSON response
         data = response.json()
 
-        print("✅ Received Response:")
+        # Extract and log organized prompt if available in response
-        print(json.dumps(data, indent=2, ensure_ascii=False))
+        organized_prompt = None
+        if isinstance(data, dict):
+            # Check for various possible field names for organized prompt
+            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")
+        
+        write_log("✅ Received Response:")
+        
+        # Log organized prompt if found
+        if organized_prompt:
+            write_log("\n📝 组织后的Prompt:")
+            write_log(organized_prompt)
+        else:
+            # If not in response, log the original prompt for reference
+            write_log("\n📝 原始Prompt:")
+            write_log(f"   {TEST_PROMPT}")
+            write_log("   (注: 组织后的prompt未在API响应中返回，如需查看请检查后端日志)")
+        
+        response_json = json.dumps(data, indent=2, ensure_ascii=False)
+        write_log("\n完整响应内容:")
+        write_log(response_json)
 
         # --- Validation ---
-        print("\n--- Validation Checks ---")
+        write_log("\n--- Validation Checks ---")
+        
+        validation_results = []
         
         # 1. Check if the response is a dictionary
         if isinstance(data, dict):
-            print("PASS: Response is a valid JSON object.")
+            validation_results.append("PASS: Response is a valid JSON object.")
         else:
-            print("FAIL: Response is not a valid JSON object.")
+            validation_results.append("FAIL: Response is not a valid JSON object.")
+            # Write all validation results to log before returning
+            for result in validation_results:
+                write_log(result)
+            write_log("=" * 80, print_to_console=False)
+            write_log("", print_to_console=False)  # Empty line for readability
             return
 
         # 2. Check for the existence of the 'root' key
         if "root" in data and isinstance(data['root'], dict):
-            print("PASS: Response contains a valid 'root' key.")
+            validation_results.append("PASS: Response contains a valid 'root' key.")
         else:
-            print("FAIL: Response does not contain a valid 'root' key.")
+            validation_results.append("FAIL: Response does not contain a valid 'root' key.")
 
         # 3. Check for the existence and format of the 'visualization_url' key
         if "visualization_url" in data and data["visualization_url"].endswith(".png"):
-            print(f"PASS: Response contains a valid 'visualization_url': {data['visualization_url']}")
+            validation_results.append(f"PASS: Response contains a valid 'visualization_url': {data['visualization_url']}")
         else:
-            print("FAIL: Response does not contain a valid 'visualization_url'.")
+            validation_results.append("FAIL: Response does not contain a valid 'visualization_url'.")
+
+        # Write all validation results to log
+        for result in validation_results:
+            write_log(result)
+
+        # Write test completion marker
+        write_log("✅ Test completed successfully")
+        write_log("=" * 80, print_to_console=False)
+        write_log("", print_to_console=False)  # Empty line for readability
 
     except requests.exceptions.RequestException as e:
-        print(f"\n❌ TEST FAILED: Could not connect to the server.")
+        error_msg = f"❌ TEST FAILED: Could not connect to the server.\n   Please make sure the backend service is running.\n   Error details: {e}"
-        print("   Please make sure the backend service is running.")
+        write_log(error_msg)
-        print(f"   Error details: {e}")
+        write_log("=" * 80, print_to_console=False)
+        write_log("", print_to_console=False)  # Empty line for readability
     except json.JSONDecodeError:
-        print(f"\n❌ TEST FAILED: The server response was not valid JSON.")
+        error_msg = f"❌ TEST FAILED: The server response was not valid JSON.\n   Response text: {response.text}"
-        print(f"   Response text: {response.text}")
+        write_log(error_msg)
+        write_log("=" * 80, print_to_console=False)
+        write_log("", print_to_console=False)  # Empty line for readability
     except Exception as e:
-        print(f"\n❌ TEST FAILED: An unexpected error occurred: {e}")
+        error_msg = f"❌ TEST FAILED: An unexpected error occurred: {e}"
+        write_log(error_msg)
+        write_log("=" * 80, print_to_console=False)
+        write_log("", print_to_console=False)  # Empty line for readability
 
 if __name__ == "__main__":
     test_generate_plan()

tools/test_validate/test_results.csv

@@ -1 +1,12 @@
 instruction_index,instruction,run_number,success,attempts,response_time,plan_id,error,timestamp
+1,起飞后移动到学生宿舍上方降落,1,False,1,2.048215866088867,,,2025-12-02 20:44:56
+2,起飞后移动到学生宿舍上方查找蓝色的车,1,True,1,14.806509971618652,8a6f282e-c306-4249-962c-d47d48c31bad,,2025-12-02 20:45:12
+3,起飞后移动到学生宿舍上方寻找蓝色的车,1,True,1,15.240672826766968,f298e2f4-9295-4ffd-8fff-0d0eb9a0ee6c,,2025-12-02 20:45:28
+4,起飞后移动到学生宿舍上方检测蓝色的车,1,True,1,13.8105788230896,31733491-2030-43b1-a5e4-eb1300b8d23f,,2025-12-02 20:45:43
+5,飞到学生宿舍上方查找蓝色的车,1,True,1,12.74257755279541,4c855ef4-c251-48cd-b464-4816bc62fbb5,,2025-12-02 20:45:57
+6,飞到学生宿舍上方查找蓝色车辆并进行打击,1,True,1,16.117226600646973,63d0e7c3-dcbb-40f0-b76b-6f0191c6512f,,2025-12-02 20:46:14
+7,起飞后移动到学生宿舍上方搜索蓝色车辆，并进行打击,1,True,1,16.25989079475403,1b4a537e-c1be-4abf-897e-c21b677b83b7,,2025-12-02 20:46:31
+8,起飞到学生宿舍上方搜索被困人员，并为被困人员投递救援物资,1,True,1,16.014280796051025,f88ea46f-5e0b-48fb-b1da-326d287af3d6,,2025-12-02 20:46:48
+9,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,1,True,1,15.530286073684692,f56c811a-8304-4c68-8260-01643928bf3e,,2025-12-02 20:47:05
+10,飞到学生宿舍上方搜索半径为10米区域范围内的蓝色车辆,1,True,1,16.660754919052124,07a13346-3026-4dce-a976-4e0faa132248,,2025-12-02 20:47:23
+11,起飞到学生宿舍搜索有没有被困人员，然后抛洒救援物资,1,True,1,14.128317832946777,16426d41-4f02-4e27-a05e-f4eb84d6c935,,2025-12-02 20:47:38

tools/test_validate/test_summary.csv

@@ -1,12 +1,12 @@
 instruction_index,instruction,total_runs,successful_runs,success_rate,avg_response_time,min_response_time,max_response_time,total_response_time
-1,起飞后移动到学生宿舍上方降落,10,10,100.00%,7.91s,7.73s,8.96s,79.07s
+1,起飞后移动到学生宿舍上方降落,1,0,0.00%,N/A,N/A,N/A,0.00s
-2,起飞后移动到学生宿舍上方查找蓝色的车,10,9,90.00%,14.18s,9.40s,25.44s,127.59s
+2,起飞后移动到学生宿舍上方查找蓝色的车,1,1,100.00%,14.81s,14.81s,14.81s,14.81s
-3,起飞后移动到学生宿舍上方寻找蓝色的车,10,10,100.00%,11.95s,7.00s,13.08s,119.49s
+3,起飞后移动到学生宿舍上方寻找蓝色的车,1,1,100.00%,15.24s,15.24s,15.24s,15.24s
-4,起飞后移动到学生宿舍上方检测蓝色的车,10,10,100.00%,12.21s,9.09s,13.09s,122.08s
+4,起飞后移动到学生宿舍上方检测蓝色的车,1,1,100.00%,13.81s,13.81s,13.81s,13.81s
-5,飞到学生宿舍上方查找蓝色的车,10,10,100.00%,12.99s,12.79s,13.07s,129.90s
+5,飞到学生宿舍上方查找蓝色的车,1,1,100.00%,12.74s,12.74s,12.74s,12.74s
-6,飞到学生宿舍上方查找蓝色车辆并进行打击,10,10,100.00%,19.17s,19.08s,19.38s,191.70s
+6,飞到学生宿舍上方查找蓝色车辆并进行打击,1,1,100.00%,16.12s,16.12s,16.12s,16.12s
-7,起飞后移动到学生宿舍上方搜索蓝色车辆，并进行打击,10,10,100.00%,19.18s,19.07s,19.25s,191.85s
+7,起飞后移动到学生宿舍上方搜索蓝色车辆，并进行打击,1,1,100.00%,16.26s,16.26s,16.26s,16.26s
-8,起飞到学生宿舍上方搜索被困人员，并为被困人员投递救援物资,10,10,100.00%,15.65s,14.89s,15.91s,156.47s
+8,起飞到学生宿舍上方搜索被困人员，并为被困人员投递救援物资,1,1,100.00%,16.01s,16.01s,16.01s,16.01s
-9,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,10,10,100.00%,14.04s,13.97s,14.15s,140.40s
+9,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,1,1,100.00%,15.53s,15.53s,15.53s,15.53s
-10,飞到学生宿舍上方搜索半径为10米区域范围内的蓝色车辆,10,10,100.00%,11.64s,11.29s,14.16s,116.39s
+10,飞到学生宿舍上方搜索半径为10米区域范围内的蓝色车辆,1,1,100.00%,16.66s,16.66s,16.66s,16.66s
-11,起飞到学生宿舍搜索有没有被困人员，然后抛洒救援物资,10,10,100.00%,16.02s,14.96s,24.95s,160.19s
+11,起飞到学生宿舍搜索有没有被困人员，然后抛洒救援物资,1,1,100.00%,14.13s,14.13s,14.13s,14.13s

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']:
+        if result['success'] and result.get('data'):
-            f.write("验证结果:\n")
+            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:")