feat: 完善批量可视化测试验证逻辑（仅提交业务代码）

tools/test_api.py

@@ -14,7 +14,8 @@ BASE_URL = "http://127.0.0.1:8000"
 ENDPOINT = "/generate_plan"
 
 # The user prompt we will send for the test
-TEST_PROMPT = "起飞"
+#TEST_PROMPT = "无人机起飞到一米高度后，先移动至搜索区，搜索并锁定任一穿黑色衣服的人，在对其进行跟踪30秒后进行打击操作"
+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"
 
 # 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")

tools/test_validate/batch_visualize.py

@@ -0,0 +1,269 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+从API测试日志中提取JSON响应并批量可视化
+"""
+import json
+import os
+import re
+import logging
+import platform
+import random
+import html
+from typing import Dict, List, Tuple
+from collections import defaultdict
+
+# 配置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+
+def sanitize_filename(text: str) -> str:
+    """将文本转换为安全的文件名"""
+    # 移除或替换不安全的字符
+    text = re.sub(r'[<>:"/\\|?*]', '_', text)
+    # 限制长度
+    if len(text) > 100:
+        text = text[:100]
+    return text
+
+def _pick_zh_font():
+    """选择合适的中文字体"""
+    sys = platform.system()
+    if sys == "Windows":
+        return "Microsoft YaHei"
+    elif sys == "Darwin":
+        return "PingFang SC"
+    else:
+        return "Noto Sans CJK SC"
+
+def _add_nodes_and_edges(node: dict, dot, parent_id: str | None = None) -> str:
+    """递归辅助函数，用于添加节点和边。"""
+    try:
+        from graphviz import Digraph
+    except ImportError:
+        logging.critical("错误：未安装graphviz库。请运行: pip install graphviz")
+        return ""
+    
+    current_id = f"{id(node)}_{random.randint(1000, 9999)}"
+    
+    # 准备节点标签（HTML-like，正确换行与转义）
+    name = html.escape(str(node.get('name', '')))
+    ntype = html.escape(str(node.get('type', '')))
+    label_parts = [f"<B>{name}</B> <FONT POINT-SIZE='10'><I>({ntype})</I></FONT>"]
+    
+    # 格式化参数显示
+    params = node.get('params') or {}
+    if params:
+        params_lines = []
+        for key, value in params.items():
+            k = html.escape(str(key))
+            if isinstance(value, float):
+                value_str = f"{value:.2f}".rstrip('0').rstrip('.')
+            else:
+                value_str = str(value)
+            v = html.escape(value_str)
+            params_lines.append(f"{k}: {v}")
+        params_text = "<BR ALIGN='LEFT'/>".join(params_lines)
+        label_parts.append(f"<FONT POINT-SIZE='9' COLOR='#555555'>{params_text}</FONT>")
+    
+    node_label = f"<{'<BR/>'.join(label_parts)}>"
+    
+    # 根据类型设置节点样式和颜色
+    node_type = (node.get('type') or '').lower()
+    shape = 'ellipse'
+    style = 'filled'
+    fillcolor = '#e6e6e6'   # 默认灰色填充
+    border_color = '#666666' # 默认描边色
+    
+    if node_type == 'action':
+        shape = 'box'
+        style = 'rounded,filled'
+        fillcolor = "#cde4ff"  # 浅蓝
+    elif node_type == 'condition':
+        shape = 'diamond'
+        style = 'filled'
+        fillcolor = "#fff2cc"  # 浅黄
+    elif node_type == 'sequence':
+        shape = 'ellipse'
+        style = 'filled'
+        fillcolor = '#d5e8d4'  # 绿色
+    elif node_type == 'selector':
+        shape = 'ellipse'
+        style = 'filled'
+        fillcolor = '#ffe6cc'  # 橙色
+    elif node_type == 'parallel':
+        shape = 'ellipse'
+        style = 'filled'
+        fillcolor = '#e1d5e7'  # 紫色
+    
+    # 特别标记安全相关节点
+    if node.get('name') in ['battery_above', 'gps_status', 'SafetyMonitor']:
+        border_color = '#ff0000'  # 红色边框突出显示安全节点
+        style = 'filled,bold'  # 加粗
+    
+    dot.node(current_id, label=node_label, shape=shape, style=style, fillcolor=fillcolor, color=border_color)
+    
+    # 连接父节点
+    if parent_id:
+        dot.edge(parent_id, current_id)
+    
+    # 递归处理子节点
+    children = node.get("children", [])
+    if not children:
+        return current_id
+    
+    # 记录所有子节点的ID
+    child_ids = []
+    
+    # 正确的递归连接：每个子节点都连接到当前节点
+    for child in children:
+        child_id = _add_nodes_and_edges(child, dot, current_id)
+        child_ids.append(child_id)
+    
+    # 子节点同级排列（横向排布，更直观地表现同层）
+    if len(child_ids) > 1:
+        with dot.subgraph(name=f"rank_{current_id}") as s:
+            s.attr(rank='same')
+            for cid in child_ids:
+                s.node(cid)
+    
+    return current_id
+
+def _visualize_pytree(node: Dict, file_path: str):
+    """
+    使用Graphviz将Pytree字典可视化，并保存到指定路径。
+    """
+    try:
+        from graphviz import Digraph
+    except ImportError:
+        logging.critical("错误：未安装graphviz库。请运行: pip install graphviz")
+        return
+
+    fontname = _pick_zh_font()
+    
+    dot = Digraph('Pytree', comment='Drone Mission Plan')
+    dot.attr(rankdir='TB', label='Drone Mission Plan', fontsize='20', fontname=fontname)
+    dot.attr('node', shape='box', style='rounded,filled', fontname=fontname)
+    dot.attr('edge', fontname=fontname)
+    
+    _add_nodes_and_edges(node, dot)
+    
+    try:
+        # 确保输出目录存在，并避免生成 .png.png
+        base_path, ext = os.path.splitext(file_path)
+        render_path = base_path if ext.lower() == '.png' else file_path
+
+        out_dir = os.path.dirname(render_path)
+        if out_dir and not os.path.exists(out_dir):
+            os.makedirs(out_dir, exist_ok=True)
+
+        # 保存为 .png 文件，并自动删除源码 .gv 文件
+        output_path = dot.render(render_path, format='png', cleanup=True, view=False)
+        logging.info(f"✅ 可视化成功: {output_path}")
+    except Exception as e:
+        logging.error(f"❌ 生成可视化图形失败: {e}")
+
+def parse_log_file(log_file_path: str) -> Dict[str, List[Dict]]:
+    """
+    解析日志文件，提取原始指令和完整API响应JSON
+    返回: {原始指令: [JSON响应列表]}
+    """
+    with open(log_file_path, 'r', encoding='utf-8') as f:
+        content = f.read()
+    
+    # 按分隔符分割条目
+    entries = re.split(r'={80,}', content)
+    
+    results = defaultdict(list)
+    
+    for entry in entries:
+        if not entry.strip():
+            continue
+        
+        # 提取原始指令
+        instruction_match = re.search(r'原始指令:\s*(.+)', entry)
+        if not instruction_match:
+            continue
+        
+        original_instruction = instruction_match.group(1).strip()
+        
+        # 提取完整API响应JSON
+        json_match = re.search(r'完整API响应:\s*\n(\{.*\})', entry, re.DOTALL)
+        if not json_match:
+            logging.warning(f"未找到指令 '{original_instruction}' 的JSON响应")
+            continue
+        
+        json_str = json_match.group(1).strip()
+        
+        try:
+            json_obj = json.loads(json_str)
+            results[original_instruction].append(json_obj)
+            logging.info(f"成功提取指令 '{original_instruction}' 的JSON响应")
+        except json.JSONDecodeError as e:
+            logging.error(f"解析指令 '{original_instruction}' 的JSON失败: {e}")
+            continue
+    
+    return results
+
+def process_and_visualize(log_file_path: str, output_dir: str):
+    """
+    处理日志文件并批量可视化
+    """
+    # 创建输出目录
+    os.makedirs(output_dir, exist_ok=True)
+    
+    # 解析日志文件
+    logging.info(f"开始解析日志文件: {log_file_path}")
+    instruction_responses = parse_log_file(log_file_path)
+    
+    logging.info(f"共找到 {len(instruction_responses)} 个不同的原始指令")
+    
+    # 处理每个指令的所有响应
+    for instruction, responses in instruction_responses.items():
+        logging.info(f"\n处理指令: {instruction} (共 {len(responses)} 个响应)")
+        
+        # 创建指令目录（使用安全的文件名）
+        safe_instruction_name = sanitize_filename(instruction)
+        instruction_dir = os.path.join(output_dir, safe_instruction_name)
+        os.makedirs(instruction_dir, exist_ok=True)
+        
+        # 处理每个响应
+        for idx, response in enumerate(responses, 1):
+            try:
+                # 提取root节点
+                root_node = response.get('root')
+                if not root_node:
+                    logging.warning(f"响应 #{idx} 没有root节点，跳过")
+                    continue
+                
+                # 生成文件名
+                json_filename = f"response_{idx}.json"
+                png_filename = f"response_{idx}.png"
+                
+                json_path = os.path.join(instruction_dir, json_filename)
+                png_path = os.path.join(instruction_dir, png_filename)
+                
+                # 保存JSON文件
+                with open(json_path, 'w', encoding='utf-8') as f:
+                    json.dump(response, f, ensure_ascii=False, indent=2)
+                
+                logging.info(f"  保存JSON: {json_filename}")
+                
+                # 生成可视化
+                _visualize_pytree(root_node, png_path)
+                logging.info(f"  生成可视化: {png_filename}")
+                
+            except Exception as e:
+                logging.error(f"处理响应 #{idx} 时出错: {e}")
+                continue
+    
+    logging.info(f"\n✅ 所有处理完成！结果保存在: {output_dir}")
+
+if __name__ == "__main__":
+    log_file = "/home/iscas/WorkSpace/code/DronePlanning/tools/test_validate/api_test_log.txt"
+    output_directory = "/home/iscas/WorkSpace/code/DronePlanning/tools/test_validate/validation"
+    
+    process_and_visualize(log_file, output_directory)
+

tools/test_validate/instructions.txt

@@ -10,5 +10,6 @@
 飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆
 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
 起飞到学生宿舍搜索有没有被困人员，然后抛洒救援物资
-
+无人机起飞到一米高度后，先移动至搜索区，搜索并锁定任一穿黑色衣服的人，在对其进行跟踪30秒后进行打击操作
+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
 

tools/test_validate/test_results.csv

@@ -1,13 +1,15 @@
 instruction_index,instruction,run_number,success,attempts,response_time,plan_id,error,timestamp
-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
+1,起飞,1,True,1,0.3463160991668701,0ffa333d-574d-453d-99cd-f8852411b7be,,2025-12-08 16:08:41
+2,起飞后移动到学生宿舍上方降落,1,True,1,0.1823880672454834,46c5741f-1e51-4cbe-bd5a-1e099d0d53f5,,2025-12-08 16:08:42
+3,起飞后移动到学生宿舍上方查找蓝色的车,1,True,1,0.24654889106750488,636bfbb8-c3be-42b6-93cf-caf87ac6424c,,2025-12-08 16:08:43
+4,起飞后移动到学生宿舍上方寻找蓝色的车,1,True,1,0.23946380615234375,744d6e87-5067-4f91-9f73-7f65432e1b83,,2025-12-08 16:08:45
+5,起飞后移动到学生宿舍上方检测蓝色的车,1,True,1,3.5440704822540283,1bf6820d-0c04-4961-b624-49e9d919ac56,,2025-12-08 16:08:49
+6,飞到学生宿舍上方查找蓝色的车,1,False,1,3.451496124267578,,,2025-12-08 16:08:54
+7,飞到学生宿舍上方查找蓝色车辆并进行打击,1,False,1,3.321821689605713,,,2025-12-08 16:08:58
+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,1,18.552793502807617,,,2025-12-08 16:09:17
+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,1,1.5930235385894775,1ae38dbd-4e25-4a51-ac4f-8ed851fe8b1f,,2025-12-08 16:09:20
+10,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,1,False,1,17.402809381484985,,,2025-12-08 16:09:38
+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,1,1.269315481185913,24b02e2d-291d-4213-9e0f-acdd1165a1f1,,2025-12-08 16:09:41
+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,1,3.885636329650879,685b1d6d-8a82-463c-ab68-051348403c89,,2025-12-08 16:09:46
+13,无人机起飞到一米高度后，先移动至搜索区，搜索并锁定任一穿黑色衣服的人，在对其进行跟踪30秒后进行打击操作,1,False,1,16.88854742050171,,,2025-12-08 16:10:04
+14,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,1,False,1,3.594463586807251,,,2025-12-08 16:10:08

tools/test_validate/test_summary.csv

@@ -1,13 +1,15 @@
 instruction_index,instruction,total_runs,successful_runs,success_rate,avg_response_time,min_response_time,max_response_time,total_response_time
-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
+1,起飞,1,1,100.00%,0.35s,0.35s,0.35s,0.35s
+2,起飞后移动到学生宿舍上方降落,1,1,100.00%,0.18s,0.18s,0.18s,0.18s
+3,起飞后移动到学生宿舍上方查找蓝色的车,1,1,100.00%,0.25s,0.25s,0.25s,0.25s
+4,起飞后移动到学生宿舍上方寻找蓝色的车,1,1,100.00%,0.24s,0.24s,0.24s,0.24s
+5,起飞后移动到学生宿舍上方检测蓝色的车,1,1,100.00%,3.54s,3.54s,3.54s,3.54s
+6,飞到学生宿舍上方查找蓝色的车,1,0,0.00%,N/A,N/A,N/A,0.00s
+7,飞到学生宿舍上方查找蓝色车辆并进行打击,1,0,0.00%,N/A,N/A,N/A,0.00s
 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
+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%,1.59s,1.59s,1.59s,1.59s
+10,飞到学生宿舍上方搜索方圆10米范围内的蓝色车辆,1,0,0.00%,N/A,N/A,N/A,0.00s
+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%,1.27s,1.27s,1.27s,1.27s
+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%,3.89s,3.89s,3.89s,3.89s
+13,无人机起飞到一米高度后，先移动至搜索区，搜索并锁定任一穿黑色衣服的人，在对其进行跟踪30秒后进行打击操作,1,0,0.00%,N/A,N/A,N/A,0.00s
+14,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,1,0,0.00%,N/A,N/A,N/A,0.00s

tools/test_validate/test_validity.py

@@ -505,4 +505,4 @@ def main():
     print(f"统计摘要: {SUMMARY_CSV}")
 
 if __name__ == "__main__":
-    main()
+    main()