修改简单模式验证

tools/test_validate/instructions.txt

@@ -1,3 +1,4 @@
+起飞
 起飞后移动到学生宿舍上方降落
 起飞后移动到学生宿舍上方查找蓝色的车
 起飞后移动到学生宿舍上方寻找蓝色的车

tools/test_validate/test_results.csv

@@ -1,12 +1,13 @@
 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
+1,起飞,1,True,1,2.4630444049835205,42903026-b02b-4089-859d-aec5cfa2435e,,2025-12-03 17:09:32
+2,起飞后移动到学生宿舍上方降落,1,True,1,10.017558574676514,86238ad2-e275-4d50-905c-175bd2f26fd0,,2025-12-03 17:09:43
+3,起飞后移动到学生宿舍上方查找蓝色的车,1,True,1,12.420023202896118,d8345bc3-b70f-41d7-b9fc-3e4898d7409e,,2025-12-03 17:09:56
+4,起飞后移动到学生宿舍上方寻找蓝色的车,1,True,1,12.864884614944458,29b5ee20-c809-4511-af08-80a85240c729,,2025-12-03 17:10:10
+5,起飞后移动到学生宿舍上方检测蓝色的车,1,True,1,10.438142538070679,5e7eb8c7-287a-469a-b6c0-a4102c1b0dac,,2025-12-03 17:10:21
+6,飞到学生宿舍上方查找蓝色的车,1,True,1,11.751057386398315,ef3d1981-1d51-433d-b2f4-2e92838075fd,,2025-12-03 17:10:34
+7,飞到学生宿舍上方查找蓝色车辆并进行打击,1,True,1,32.890604972839355,d8fc4658-08af-4910-89c4-b029c9a5daa0,,2025-12-03 17:11:08
+8,起飞后移动到学生宿舍上方搜索蓝色车辆，并进行打击,1,False,1,33.2862343788147,,,2025-12-03 17:11:42
+9,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,1,12.312166213989258,7fbf0091-f7d3-4c3a-a6b7-4c0bfd4df66e,,2025-12-03 17:11:56
+10,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,1,True,1,12.204660892486572,3ae0b258-b7e4-460c-9cfe-4b224266edc4,,2025-12-03 17:12:09
+11,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,1,12.808414936065674,2acb84cf-c89e-460d-a4d9-8d1edb4ee69a,,2025-12-03 17:12:23
+12,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,1,11.071707487106323,c05d46c9-1b1b-4c8d-b64b-86b76d0c4099,,2025-12-03 17:12:35

tools/test_validate/test_summary.csv

@@ -1,12 +1,13 @@
 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,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,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,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,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,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,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,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,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,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,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,1,1,100.00%,14.13s,14.13s,14.13s,14.13s
+1,起飞,1,1,100.00%,2.46s,2.46s,2.46s,2.46s
+2,起飞后移动到学生宿舍上方降落,1,1,100.00%,10.02s,10.02s,10.02s,10.02s
+3,起飞后移动到学生宿舍上方查找蓝色的车,1,1,100.00%,12.42s,12.42s,12.42s,12.42s
+4,起飞后移动到学生宿舍上方寻找蓝色的车,1,1,100.00%,12.86s,12.86s,12.86s,12.86s
+5,起飞后移动到学生宿舍上方检测蓝色的车,1,1,100.00%,10.44s,10.44s,10.44s,10.44s
+6,飞到学生宿舍上方查找蓝色的车,1,1,100.00%,11.75s,11.75s,11.75s,11.75s
+7,飞到学生宿舍上方查找蓝色车辆并进行打击,1,1,100.00%,32.89s,32.89s,32.89s,32.89s
+8,起飞后移动到学生宿舍上方搜索蓝色车辆，并进行打击,1,0,0.00%,N/A,N/A,N/A,0.00s
+9,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%,12.31s,12.31s,12.31s,12.31s
+10,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%,12.20s,12.20s,12.20s,12.20s
+11,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%,12.81s,12.81s,12.81s,12.81s
+12,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%,11.07s,11.07s,11.07s,11.07s

tools/test_validate/test_validity.py

@@ -84,10 +84,15 @@ def send_api_request(prompt, instruction_idx, run_number):
     for attempt in range(MAX_RETRIES):
         try:
             debug_print(f"指令 {instruction_idx}-{run_number} 尝试 {attempt + 1}")
+            debug_print(f"请求URL: {url}")
+            debug_print(f"请求Payload: {json.dumps(payload, ensure_ascii=False)}")
             start_time = time.time()
             response = requests.post(url, data=json.dumps(payload), headers=headers, timeout=60)  # 增加超时
             response_time = time.time() - start_time
             
+            debug_print(f"HTTP状态码: {response.status_code}")
+            debug_print(f"响应时间: {response_time:.2f}秒")
+            
             # 首先检查HTTP状态
             response.raise_for_status()
             
@@ -98,27 +103,51 @@ def send_api_request(prompt, instruction_idx, run_number):
                 debug_print(f"JSON解析失败: {e}, 响应文本: {response.text[:200]}")
                 raise
             
+            # 判断是简单模式还是复杂模式
+            # 简单模式和复杂模式都使用root字段，区别是：
+            # - 简单模式：root是单个action节点，没有children
+            # - 复杂模式：root是控制流节点或有children的节点
             root_node = data.get('root', {})
+            root_type = root_node.get('type', '')
+            root_has_children = bool(root_node.get('children'))
             
-            # 基本验证 - 放宽要求
+            # 简单模式：root是action类型且没有children
+            is_simple_mode = (root_type == 'action' and not root_has_children)
+            # 复杂模式：有root字段且不是简单模式
+            is_complex_mode = ("root" in data and not is_simple_mode)
+            
+            # 基本验证 - 支持简单模式和复杂模式
             validation_checks = {
                 "is_dict": isinstance(data, dict),
                 "has_root": "root" in data,
-                "root_has_children": bool(root_node.get('children')),
                 "has_plan_id": "plan_id" in data,
                 "has_visualization_url": "visualization_url" in data,
             }
             
+            # 模式特定的验证
+            if is_simple_mode:
+                # 简单模式：root必须是action类型，且没有children
+                validation_checks.update({
+                    "root_is_action": root_type == 'action',
+                    "root_no_children": not root_has_children,
+                    "root_has_name": bool(root_node.get('name')),
+                })
+                # 简单模式和复杂模式都不应该有mode字段
+                validation_checks["no_mode_field"] = "mode" not in data
+            elif is_complex_mode:
+                # 复杂模式：root应该有children（控制流节点）
+                validation_checks.update({
+                    "root_has_children": root_has_children,
+                })
+                # 复杂模式不应该有mode字段
+                validation_checks["no_mode_field"] = "mode" not in data
+            else:
+                # 既不是简单模式也不是复杂模式，这是错误
+                validation_checks["valid_mode"] = False
+                debug_print(f"⚠️  响应既不是简单模式也不是复杂模式: root_type={root_type}, has_children={root_has_children}")
+            
             # 可选的高级验证
-            advanced_checks = {
-                "leaf_nodes_valid": check_leaf_nodes(root_node),
-                "has_safety": check_safety_monitoring(root_node)
-            }
-            
-            # 合并验证结果
-            validation_checks.update(advanced_checks)
-            
-            # 统计无效节点但不作为失败条件
+            advanced_checks = {}
             invalid_actions = []
             invalid_conditions = []
             
@@ -139,13 +168,41 @@ def send_api_request(prompt, instruction_idx, run_number):
                 for child in current_node.get('children', []):
                     collect_nodes(child)
             
-            collect_nodes(root_node)
+            if is_complex_mode:
+                # 复杂模式的高级验证
+                advanced_checks = {
+                    "leaf_nodes_valid": check_leaf_nodes(root_node),
+                    "has_safety": check_safety_monitoring(root_node)
+                }
+                collect_nodes(root_node)
+            elif is_simple_mode:
+                # 简单模式：检查action名称是否有效
+                action_name = root_node.get('name', '')
+                if action_name and action_name not in ['deliver_payload', 'emergency_return', 'fly_to_waypoint', 
+                                                       'land', 'loiter', 'object_detect', 'preflight_checks', 
+                                                       'search_pattern', 'strike_target', 'battle_damage_assessment', 'takeoff']:
+                    invalid_actions.append(action_name)
             
-            # 主要检查基本验证，高级验证作为警告
-            success = all(validation_checks[k] for k in ["is_dict", "has_root", "root_has_children", 
-                                                       "has_plan_id", "has_visualization_url"])
+            # 合并验证结果
+            validation_checks.update(advanced_checks)
             
-            debug_print(f"验证结果: 成功={success}, 基本验证通过={all(validation_checks.values())}")
+            # 根据模式确定成功条件
+            if is_simple_mode:
+                # 简单模式：必须有的字段
+                required_checks = ["is_dict", "has_root", "has_plan_id", "has_visualization_url", 
+                                 "root_is_action", "root_no_children", "root_has_name", "no_mode_field"]
+                success = all(validation_checks.get(k, False) for k in required_checks)
+            elif is_complex_mode:
+                # 复杂模式：必须有的字段
+                required_checks = ["is_dict", "has_root", "has_plan_id", "has_visualization_url", 
+                                 "root_has_children", "no_mode_field"]
+                success = all(validation_checks.get(k, False) for k in required_checks)
+            else:
+                # 无效模式
+                success = False
+            
+            mode_type = "简单模式" if is_simple_mode else ("复杂模式" if is_complex_mode else "未知模式")
+            debug_print(f"验证结果: 模式={mode_type}, 成功={success}, 基本验证通过={all(validation_checks.values())}")
             
             return {
                 "success": success,
@@ -156,13 +213,22 @@ def send_api_request(prompt, instruction_idx, run_number):
                 "invalid_conditions": invalid_conditions,
                 "error": None,
                 "attempts": attempt + 1,
-                "http_status": response.status_code
+                "http_status": response.status_code,
+                "mode_type": mode_type
             }
             
         except requests.exceptions.RequestException as e:
             error_msg = f"请求失败: {e}"
+            http_status = getattr(e.response, 'status_code', None) if hasattr(e, 'response') else None
             debug_print(f"请求异常: {error_msg}")
+            debug_print(f"HTTP状态码: {http_status}")
+            if hasattr(e, 'response') and e.response is not None:
+                try:
+                    debug_print(f"响应内容: {e.response.text[:500]}")
+                except:
+                    pass
             if attempt < MAX_RETRIES - 1:
+                debug_print(f"等待 {RETRY_DELAY} 秒后重试...")
                 time.sleep(RETRY_DELAY)
                 continue
             return {
@@ -174,12 +240,15 @@ def send_api_request(prompt, instruction_idx, run_number):
                 "invalid_conditions": [],
                 "error": error_msg,
                 "attempts": attempt + 1,
-                "http_status": getattr(e.response, 'status_code', None) if hasattr(e, 'response') else None
+                "http_status": http_status,
+                "mode_type": "未知"
             }
             
         except Exception as e:
             error_msg = f"未知错误: {e}"
             debug_print(f"未知错误: {error_msg}")
+            import traceback
+            debug_print(f"错误堆栈: {traceback.format_exc()}")
             return {
                 "success": False,
                 "data": None,
@@ -189,7 +258,8 @@ def send_api_request(prompt, instruction_idx, run_number):
                 "invalid_conditions": [],
                 "error": error_msg,
                 "attempts": attempt + 1,
-                "http_status": None
+                "http_status": None,
+                "mode_type": "未知"
             }
 
 def read_instructions(filename):
@@ -215,6 +285,7 @@ def write_log_entry(log_file, instruction_idx, run_number, prompt, result):
         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"原始指令: {prompt}\n")
+        f.write(f"模式类型: {result.get('mode_type', '未知')}\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")