scalebox-sdk 0.1.4__py3-none-any.whl → 0.1.25__py3-none-any.whl

scalebox/test/{test_code_interpreter_e2bsync_comprehensive.py → test_code_interpreter_execcode.py}

@@ -12,58 +12,44 @@ This test suite demonstrates and validates all key functionality of the CodeInte
 """
 
 import datetime
-import json
 import logging
 import os
-import tempfile
 import time
+import tempfile
+import json
+from typing import List, Optional, Dict, Any
 from io import StringIO
-from typing import Any, Dict, List, Optional
-
-from e2b_code_interpreter import (
-    Context,
-    Execution,
-    ExecutionError,
-    Logs,
-    OutputMessage,
-    Result,
-    Sandbox,
-)
 
-# from scalebox.code_interpreter import Sandbox, Context, Execution, ExecutionError, Result, OutputMessage, Logs
+from scalebox.code_interpreter import Sandbox, Context, Execution, ExecutionError, Result, OutputMessage, Logs
 
 # 配置日志
-logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
-)
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 logger = logging.getLogger(__name__)
 
 
 class CodeInterpreterValidator:
     """Comprehensive CodeInterpreter validation test suite."""
-
+    
     def __init__(self):
         self.sandbox: Optional[Sandbox] = None
         self.test_results = []
         self.failed_tests = []
         self.contexts: Dict[str, Context] = {}
-
-    def log_test_result(
-        self, test_name: str, success: bool, message: str = "", duration: float = 0
-    ):
+        
+    def log_test_result(self, test_name: str, success: bool, message: str = "", duration: float = 0):
         """记录测试结果"""
         status = "✅ PASS" if success else "❌ FAIL"
         result = {
-            "test": test_name,
-            "success": success,
-            "message": message,
-            "duration": duration,
+            'test': test_name,
+            'success': success,
+            'message': message,
+            'duration': duration
         }
         self.test_results.append(result)
-
+        
         if not success:
             self.failed_tests.append(test_name)
-
+            
         logger.info(f"{status} {test_name} ({duration:.3f}s) {message}")
 
     def run_test(self, test_func, test_name: str):
@@ -78,50 +64,75 @@ class CodeInterpreterValidator:
             self.log_test_result(test_name, False, str(e), duration=duration)
 
     # ======================== 基础代码解释器操作测试 ========================
-
+    
     def test_code_interpreter_creation(self):
         """测试代码解释器创建"""
-        # self.sandbox = Sandbox(
-        #     template="code-interpreter",
-        #     timeout=600,
-        #     debug=True,
-        #     metadata={"test": "code_interpreter_validation"},
-        #     envs={"CI_TEST": "sync_test"}
-        # )
-        self.sandbox = Sandbox.create()
-
-        # time.sleep(5)
+        self.sandbox = Sandbox.create(
+            template="code-interpreter",
+            timeout=3600,
+            # debug=True,
+            metadata={"test": "code_interpreter_validation"},
+            envs={"CI_TEST": "sync_test"}
+        )
+        # time.sleep(2)
         assert self.sandbox is not None
         assert self.sandbox.sandbox_id is not None
-        logger.info(
-            f"Created CodeInterpreter sandbox with ID: {self.sandbox.sandbox_id}"
-        )
+        logger.info(f"Created CodeInterpreter sandbox with ID: {self.sandbox.sandbox_id}")
 
     def test_basic_python_execution(self):
         """测试基础Python代码执行"""
         assert self.sandbox is not None
-
+        
         code = """
-print("Hello, CodeInterpreter!")
-x = 1 + 2
-y = x * 3
-print(f"计算结果: x={x}, y={y}")
-result = {"x": x, "y": y}
-print(result)
-"""
+import random
+import math
+import matplotlib.pyplot as plt
+
+# Generate random data
+num_points = 50
+random_data = [random.uniform(10, 100) for _ in range(num_points)]
+
+# Generate a second dataset with a sine wave pattern for comparison
+x_values = list(range(num_points))
+sine_data = [50 + 30 * math.sin(i * 0.2) for i in range(num_points)]
+
+# Create figure and axis for the plot
+plt.figure(figsize=(10, 6))
+
+# Plot both datasets
+plt.plot(x_values, random_data, label='Random Data', color='blue', marker='o', markersize=4, linewidth=1)
+plt.plot(x_values, sine_data, label='Sine Pattern', color='red', linestyle='-', linewidth=2)
+
+# Add labels and title
+plt.title('Random Data vs Sine Pattern')
+plt.xlabel('Data Point Index')
+plt.ylabel('Value')
 
+# Add grid and legend
+plt.grid(True, linestyle='--', alpha=0.7)
+plt.legend()
+
+# Improve layout
+plt.tight_layout()
+
+# Save the plot
+plt.savefig('random_data_plot.png')
+
+print('Line chart with random data has been created and saved as random_data_plot.png')
+"""
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert isinstance(execution, Execution)
         assert execution.error is None
         assert len(execution.logs.stdout) > 0
-        assert "Hello, CodeInterpreter!" in execution.logs.stdout[0]
+        # assert "Hello, CodeInterpreter!" in execution.logs.stdout[0]
         logger.info(f"Python execution stdout: {execution.logs.stdout}")
 
     def test_math_calculations(self):
         """测试数学计算"""
         assert self.sandbox is not None
-
+        
         code = """
 import math
 import numpy as np
@@ -150,7 +161,7 @@ print(f"标准差: {std_val:.3f}")
     "array_stats": {"mean": mean_val, "std": std_val}
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -160,7 +171,7 @@ print(f"标准差: {std_val:.3f}")
     def test_data_processing(self):
         """测试数据处理"""
         assert self.sandbox is not None
-
+        
         code = """
 import pandas as pd
 import json
@@ -200,7 +211,7 @@ result = {
 }
 print(f"\\n处理结果: {json.dumps(result, indent=2)}")
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -210,7 +221,7 @@ print(f"\\n处理结果: {json.dumps(result, indent=2)}")
     def test_visualization_code(self):
         """测试数据可视化代码"""
         assert self.sandbox is not None
-
+        
         code = """
 import matplotlib.pyplot as plt
 import numpy as np
@@ -260,39 +271,39 @@ print("图表包含正弦、余弦函数和随机散点图")
 # 返回结果信息
 {"image_size": len(image_base64), "charts": ["sin/cos functions", "random scatter"]}
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
         assert any("图表已生成" in line for line in execution.logs.stdout)
 
     # ======================== 回调函数测试 ========================
-
+    
     def test_callback_handling(self):
         """测试回调函数处理"""
         assert self.sandbox is not None
-
+        
         stdout_messages = []
         stderr_messages = []
         results = []
         errors = []
-
+        
         def stdout_callback(msg: OutputMessage):
             stdout_messages.append(msg.content)
             logger.info(f"STDOUT: {msg.content}")
-
+        
         def stderr_callback(msg: OutputMessage):
             stderr_messages.append(msg.content)
             logger.info(f"STDERR: {msg.content}")
-
+        
         def result_callback(result: Result):
             results.append(result)
             logger.info(f"RESULT: {result}")
-
+        
         def error_callback(error: ExecutionError):
             errors.append(error)
             logger.info(f"ERROR: {error.name} - {error.value}")
-
+        
         code = """
 import sys
 
@@ -305,46 +316,42 @@ print(f"最终结果: {result_data}")
 
 result_data  # 返回结果
 """
-
+        
         execution = self.sandbox.run_code(
             code,
             language="python",
             on_stdout=stdout_callback,
             on_stderr=stderr_callback,
             on_result=result_callback,
-            on_error=error_callback,
+            on_error=error_callback
         )
         print(execution.to_json())
         assert execution.error is None
         # 注意：回调可能在执行完成后才触发
-        logger.info(
-            f"Callback test completed. stdout: {len(stdout_messages)}, stderr: {len(stderr_messages)}"
-        )
+        logger.info(f"Callback test completed. stdout: {len(stdout_messages)}, stderr: {len(stderr_messages)}")
 
     def test_error_handling(self):
         """测试错误处理"""
         assert self.sandbox is not None
-
+        
         error_messages = []
-
+        
         def error_callback(error: ExecutionError):
             error_messages.append(error)
             logger.info(f"捕获错误: {error.name} - {error.value}")
-
+        
         # 测试语法错误
         code_syntax_error = """
 print("开始执行")
 invalid syntax here  # 这里有语法错误
 print("这行不会执行")
 """
-
-        execution = self.sandbox.run_code(
-            code_syntax_error, language="python", on_error=error_callback
-        )
+        
+        execution = self.sandbox.run_code(code_syntax_error,language="python", on_error=error_callback)
         assert execution.error is not None
         assert execution.error.name in ["SyntaxError", "ParseError"]
         logger.info(f"正确捕获语法错误: {execution.error.name}")
-
+        
         # 测试运行时错误
         code_runtime_error = """
 print("开始执行")
@@ -353,29 +360,30 @@ y = 0
 result = x / y  # 除零错误
 print(f"结果: {result}")
 """
-
-        execution2 = self.sandbox.run_code(
-            code_runtime_error, language="python", on_error=error_callback
-        )
+        
+        execution2 = self.sandbox.run_code(code_runtime_error,language="python",on_error=error_callback)
         print(execution.to_json())
         assert execution2.error is not None
         assert "ZeroDivisionError" in execution2.error.name
         logger.info(f"正确捕获运行时错误: {execution2.error.name}")
 
     # ======================== 上下文管理测试 ========================
-
+    
     def test_context_creation(self):
         """测试上下文创建"""
         assert self.sandbox is not None
-
+        
         # 创建Python上下文
-        python_context = self.sandbox.create_code_context(language="python", cwd="/tmp")
+        python_context = self.sandbox.create_code_context(
+            language="python", 
+            cwd="/tmp"
+        )
         assert isinstance(python_context, Context)
         assert python_context.id is not None
         assert python_context.language == "python"
         self.contexts["python"] = python_context
         logger.info(f"Created Python context: {python_context.id}")
-
+        
         # 测试完成后立即清理context
         try:
             self.sandbox.destroy_context(python_context)
@@ -389,11 +397,11 @@ print(f"结果: {result}")
     def test_context_persistence(self):
         """测试上下文状态持久性"""
         assert self.sandbox is not None
-
+        
         # 创建新的上下文用于持久性测试
         context = self.sandbox.create_code_context(language="python", cwd="/tmp")
         self.contexts["persistence_test"] = context
-
+        
         # 在上下文中定义变量
         code1 = """
 test_var = "Hello from context"
@@ -401,11 +409,11 @@ numbers = [1, 2, 3, 4, 5]
 counter = 0
 print(f"定义了变量: test_var={test_var}, numbers={numbers}")
 """
-
+        
         execution1 = self.sandbox.run_code(code1, context=context)
         print(execution1.to_json())
         assert execution1.error is None
-
+        
         # 在同一上下文中使用之前定义的变量
         code2 = """
 print(f"从上下文读取: test_var={test_var}")
@@ -413,13 +421,13 @@ counter += 10
 numbers.append(6)
 print(f"修改后: counter={counter}, numbers={numbers}")
 """
-
+        
         execution2 = self.sandbox.run_code(code2, context=context)
         print(execution2.to_json())
         assert execution2.error is None
         assert any("从上下文读取" in line for line in execution2.logs.stdout)
         logger.info("Context persistence test passed")
-
+        
         # 测试完成后立即清理context
         try:
             self.sandbox.destroy_context(context)
@@ -433,48 +441,48 @@ print(f"修改后: counter={counter}, numbers={numbers}")
     def test_multiple_contexts(self):
         """测试多个上下文"""
         assert self.sandbox is not None
-
+        
         # 创建两个独立的上下文
         context1 = self.sandbox.create_code_context(language="python", cwd="/tmp")
         context2 = self.sandbox.create_code_context(language="python", cwd="/home")
         self.contexts["multi_context1"] = context1
         self.contexts["multi_context2"] = context2
-
+        
         # 在第一个上下文中设置变量
         code1 = """
 context_name = "context_1"
 shared_data = {"source": "context_1", "value": 100}
 print(f"在 {context_name} 中设置数据")
 """
-
+        
         execution1 = self.sandbox.run_code(code1, context=context1)
         print(execution1.to_json())
         assert execution1.error is None
-
+        
         # 在第二个上下文中设置不同的变量
         code2 = """
 context_name = "context_2"
 shared_data = {"source": "context_2", "value": 200}
 print(f"在 {context_name} 中设置数据")
 """
-
+        
         execution2 = self.sandbox.run_code(code2, context=context2)
         print(execution2.to_json())
         assert execution2.error is None
-
+        
         # 验证两个上下文的独立性
         verify_code = """
 print(f"当前上下文: {context_name}")
 print(f"数据: {shared_data}")
 """
-
+        
         result1 = self.sandbox.run_code(verify_code, context=context1)
         print(result1.to_json())
         result2 = self.sandbox.run_code(verify_code, context=context2)
         print(result2.to_json())
         assert result1.error is None and result2.error is None
         logger.info("Multiple contexts test passed")
-
+        
         # 测试完成后立即清理所有contexts
         contexts_to_destroy = [context1, context2]
         for context in contexts_to_destroy:
@@ -483,7 +491,7 @@ print(f"数据: {shared_data}")
                 logger.info(f"Successfully destroyed multi-context: {context.id}")
             except Exception as e:
                 logger.warning(f"Failed to destroy multi-context {context.id}: {e}")
-
+        
         # 从contexts字典中移除
         if "multi_context1" in self.contexts:
             del self.contexts["multi_context1"]
@@ -491,11 +499,11 @@ print(f"数据: {shared_data}")
             del self.contexts["multi_context2"]
 
     # ======================== 数据类型和格式测试 ========================
-
+    
     def test_different_data_types(self):
         """测试不同数据类型"""
         assert self.sandbox is not None
-
+        
         code = """
 import json
 import datetime
@@ -526,7 +534,7 @@ print(f"\\nJSON序列化长度: {len(json_str)}")
 # 返回测试数据
 test_data
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -535,7 +543,7 @@ test_data
     def test_file_operations_simulation(self):
         """测试文件操作（模拟）"""
         assert self.sandbox is not None
-
+        
         code = """
 import tempfile
 import os
@@ -577,18 +585,18 @@ print("临时文件已清理")
 
 {"file_size": file_size, "data_match": data_match}
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
         assert any("数据已写入文件" in line for line in execution.logs.stdout)
 
     # ======================== 性能测试 ========================
-
+    
     def test_performance_simple_calculations(self):
         """测试简单计算性能"""
         assert self.sandbox is not None
-
+        
         code = """
 import time
 import random
@@ -623,23 +631,23 @@ print(f"总时间: {total_time:.3f}s")
 
 {"total": total, "calculation_time": calculation_time, "string_time": string_time, "total_time": total_time}
 """
-
+        
         start_test_time = time.time()
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         test_duration = time.time() - start_test_time
-
+        
         assert execution.error is None
         assert any("开始性能测试" in line for line in execution.logs.stdout)
         logger.info(f"Performance test completed in {test_duration:.3f}s")
-
+        
         # 性能断言
         assert test_duration < 30  # 整个测试应在30秒内完成
 
     def test_performance_concurrent_simulation(self):
         """测试并发模拟（使用线程）"""
         assert self.sandbox is not None
-
+        
         code = """
 import threading
 import time
@@ -706,18 +714,18 @@ for result in results:
     "results": results
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
         assert any("并发测试完成" in line for line in execution.logs.stdout)
 
     # ======================== 结果格式测试 ========================
-
+    
     def test_text_result(self):
         """测试文本格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成纯文本结果
 text_content = '''
@@ -735,22 +743,22 @@ text_content = '''
 print("生成文本格式结果")
 text_content
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
         assert len(execution.results) > 0
-
+        
         # 检查是否有文本结果
         for result in execution.results:
-            if hasattr(result, "text") and result.text:
+            if hasattr(result, 'text') and result.text:
                 logger.info(f"文本结果长度: {len(result.text)}")
                 assert "CodeInterpreter" in result.text
 
     def test_html_result(self):
         """测试HTML格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成HTML格式结果
 html_content = '''<!DOCTYPE html>
@@ -799,7 +807,7 @@ print("生成HTML格式结果")
 from IPython.display import HTML
 HTML(html_content)
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -808,7 +816,7 @@ HTML(html_content)
     def test_markdown_result(self):
         """测试Markdown格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成Markdown格式结果
 markdown_content = '''# 📊 CodeInterpreter 测试报告
@@ -879,7 +887,7 @@ print("生成Markdown格式结果")
 from IPython.display import Markdown
 Markdown(markdown_content)
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -888,7 +896,7 @@ Markdown(markdown_content)
     def test_svg_result(self):
         """测试SVG格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成SVG格式结果
 svg_content = '''<svg width="400" height="300" xmlns="http://www.w3.org/2000/svg">
@@ -940,7 +948,7 @@ print("生成SVG格式结果")
 from IPython.display import SVG
 SVG(svg_content)
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -949,7 +957,7 @@ SVG(svg_content)
     def test_image_results(self):
         """测试图像格式结果 (PNG/JPEG)"""
         assert self.sandbox is not None
-
+        
         code = """
 import matplotlib.pyplot as plt
 import numpy as np
@@ -1029,7 +1037,7 @@ print(f"  JPEG大小: {len(jpeg_base64)} 字符")
     "description": "CodeInterpreter测试结果图表集"
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         # for result in execution.results:
         #     print(result.__str__())
@@ -1040,7 +1048,7 @@ print(f"  JPEG大小: {len(jpeg_base64)} 字符")
     def test_latex_result(self):
         """测试LaTeX格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成LaTeX格式结果
 latex_content = r'''
@@ -1140,7 +1148,7 @@ print("生成LaTeX格式结果")
 from IPython.display import Latex
 Latex(latex_content)
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -1149,7 +1157,7 @@ Latex(latex_content)
     def test_json_data_result(self):
         """测试JSON数据格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 import json
 from datetime import datetime
@@ -1258,7 +1266,7 @@ print(f"\\n格式化JSON长度: {len(formatted_json)} 字符")
 # 返回JSON数据
 json_data
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -1268,7 +1276,7 @@ json_data
     def test_javascript_result(self):
         """测试JavaScript格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 # 生成JavaScript格式结果
 javascript_code = '''
@@ -1482,7 +1490,7 @@ print("包含完整的交互式结果展示系统")
     "description": "CodeInterpreter交互式结果展示系统"
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -1492,7 +1500,7 @@ print("包含完整的交互式结果展示系统")
     def test_chart_data_result(self):
         """测试图表数据格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 import json
 
@@ -1647,7 +1655,7 @@ print(f"\\n图表数据JSON长度: {len(json.dumps(chart_data))} 字符")
 # 返回图表数据
 chart_data
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -1657,7 +1665,7 @@ chart_data
     def test_mixed_format_result(self):
         """测试混合格式结果"""
         assert self.sandbox is not None
-
+        
         code = """
 import json
 import base64
@@ -1810,7 +1818,7 @@ print(f"  SVG图标: 成功状态指示")
     }
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -1818,11 +1826,11 @@ print(f"  SVG图标: 成功状态指示")
         logger.info("混合格式结果测试完成")
 
     # ======================== R语言测试 ========================
-
+    
     def test_r_language_basic_execution(self):
         """测试R语言基础执行"""
         assert self.sandbox is not None
-
+        
         code = """
 # R语言基础执行测试
 print("Hello from R Language!")
@@ -1859,7 +1867,7 @@ list(
   data_frame = df
 )
 """
-
+        
         execution = self.sandbox.run_code(code, language="r")
         print(execution.to_json())
         assert execution.error is None
@@ -1870,7 +1878,7 @@ list(
     def test_r_language_data_analysis(self):
         """测试R语言数据分析"""
         assert self.sandbox is not None
-
+        
         code = """
 # R语言数据分析测试
 library(dplyr)
@@ -1920,20 +1928,18 @@ list(
   high_scores_count = nrow(high_scores)
 )
 """
-
+        
         execution = self.sandbox.run_code(code, language="r")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Dataset created with 100 rows" in line for line in execution.logs.stdout
-        )
+        assert any("Dataset created with 100 rows" in line for line in execution.logs.stdout)
         assert any("Summary statistics" in line for line in execution.logs.stdout)
         logger.info("R language data analysis test passed")
 
     def test_r_language_visualization(self):
         """测试R语言数据可视化"""
         assert self.sandbox is not None
-
+        
         code = """
 # R语言数据可视化测试
 library(ggplot2)
@@ -1987,23 +1993,18 @@ plot_info <- list(
 print("All visualizations completed successfully")
 plot_info
 """
-
+        
         execution = self.sandbox.run_code(code, language="r")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Creating visualizations..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "All visualizations completed successfully" in line
-            for line in execution.logs.stdout
-        )
+        assert any("Creating visualizations..." in line for line in execution.logs.stdout)
+        assert any("All visualizations completed successfully" in line for line in execution.logs.stdout)
         logger.info("R language visualization test passed")
 
     def test_r_language_statistics(self):
         """测试R语言统计分析"""
         assert self.sandbox is not None
-
+        
         code = """
 # R语言统计分析测试
 library(stats)
@@ -2064,24 +2065,22 @@ list(
   normality_test2_p = shapiro_test2$p.value
 )
 """
-
+        
         execution = self.sandbox.run_code(code, language="r")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Created two sample datasets" in line for line in execution.logs.stdout
-        )
+        assert any("Created two sample datasets" in line for line in execution.logs.stdout)
         assert any("T-test performed" in line for line in execution.logs.stdout)
         logger.info("R language statistics test passed")
 
     def test_r_language_context_management(self):
         """测试R语言上下文管理"""
         assert self.sandbox is not None
-
+        
         # 创建R语言上下文
         r_context = self.sandbox.create_code_context(language="r", cwd="/tmp")
         self.contexts["r_language"] = r_context
-
+        
         # 在上下文中定义变量和函数
         setup_code = """
 # R语言上下文设置
@@ -2120,15 +2119,12 @@ list(
   data_rows = nrow(sample_data)
 )
 """
-
+        
         execution1 = self.sandbox.run_code(setup_code, context=r_context)
         print(execution1.to_json())
         assert execution1.error is None
-        assert any(
-            "Setting up R language context..." in line
-            for line in execution1.logs.stdout
-        )
-
+        assert any("Setting up R language context..." in line for line in execution1.logs.stdout)
+        
         # 在同一上下文中使用之前定义的变量和函数
         use_code = """
 # 使用R语言上下文中的变量和函数
@@ -2162,18 +2158,14 @@ list(
   context_active = TRUE
 )
 """
-
+        
         execution2 = self.sandbox.run_code(use_code, context=r_context)
         print(execution2.to_json())
         assert execution2.error is None
-        assert any(
-            "Using R language context..." in line for line in execution2.logs.stdout
-        )
-        assert any(
-            "Counter after increment:" in line for line in execution2.logs.stdout
-        )
+        assert any("Using R language context..." in line for line in execution2.logs.stdout)
+        assert any("Counter after increment:" in line for line in execution2.logs.stdout)
         logger.info("R language context management test passed")
-
+        
         # 测试完成后立即清理context
         try:
             self.sandbox.destroy_context(r_context)
@@ -2185,11 +2177,11 @@ list(
             logger.warning(f"Failed to destroy R context {r_context.id}: {e}")
 
     # ======================== Node.js/JavaScript 测试 ========================
-
+    
     def test_nodejs_basic_execution(self):
         """测试Node.js基础执行"""
         assert self.sandbox is not None
-
+        
         code = """
 // Node.js 基础执行测试
 console.log("Hello from Node.js Kernel!");
@@ -2214,20 +2206,18 @@ console.log(`Top users: ${top.map(u => u.name).join(', ')}`);
 // 返回综合数据
 ({ sum, product, topCount: top.length })
 """
-
+        
         execution = self.sandbox.run_code(code, language="javascript")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Hello from Node.js Kernel!" in line for line in execution.logs.stdout
-        )
+        assert any("Hello from Node.js Kernel!" in line for line in execution.logs.stdout)
         assert any("Sum:" in line for line in execution.logs.stdout)
         logger.info("Node.js basic execution test passed")
 
     def test_nodejs_async_promises(self):
         """测试Node.js异步/Promise"""
         assert self.sandbox is not None
-
+        
         code = """
 // Node.js 异步 Promise 测试
 function delay(ms) {
@@ -2250,7 +2240,7 @@ async function main() {
 
 main();
 """
-
+        
         execution = self.sandbox.run_code(code, language="javascript")
         print(execution.to_json())
         assert execution.error is None
@@ -2261,7 +2251,7 @@ main();
     def test_nodejs_data_processing(self):
         """测试Node.js数据处理"""
         assert self.sandbox is not None
-
+        
         code = """
 // Node.js 数据处理示例（无需外部库）
 const records = [];
@@ -2280,7 +2270,7 @@ const grouped = Object.entries(summary).map(([group, s]) => ({ group, count: s.c
 console.log("Grouped summary ready");
 ({ total: records.length, groups: grouped })
 """
-
+        
         execution = self.sandbox.run_code(code, language="javascript")
         print(execution.to_json())
         assert execution.error is None
@@ -2290,7 +2280,7 @@ console.log("Grouped summary ready");
     def test_nodejs_chart_data(self):
         """测试Node.js图表数据生成（Chart.js兼容结构）"""
         assert self.sandbox is not None
-
+        
         code = """
 // 生成Chart.js兼容的数据对象
 const labels = Array.from({length: 7}, (_, i) => `Day ${i+1}`);
@@ -2311,7 +2301,7 @@ const chart = {
 console.log("Chart data generated");
 ({ chart })
 """
-
+        
         execution = self.sandbox.run_code(code, language="javascript")
         print(execution.to_json())
         assert execution.error is None
@@ -2323,11 +2313,11 @@ console.log("Chart data generated");
     def test_nodejs_context_management(self):
         """测试Node.js上下文管理"""
         assert self.sandbox is not None
-
+        
         # 创建Node.js上下文
         js_context = self.sandbox.create_code_context(language="javascript", cwd="/tmp")
         self.contexts["nodejs"] = js_context
-
+        
         # 在上下文中定义变量与函数
         setup = """
 // Node.js 上下文初始化
@@ -2338,14 +2328,12 @@ function sum(a,b) { return a + b; }
 console.log(`Init done with ${globalThis.cache.items.length} items`);
 ({ size: globalThis.cache.items.length })
 """
-
+        
         exec1 = self.sandbox.run_code(setup, context=js_context)
         print(exec1.to_json())
         assert exec1.error is None
-        assert any(
-            "Setting up Node.js context..." in line for line in exec1.logs.stdout
-        )
-
+        assert any("Setting up Node.js context..." in line for line in exec1.logs.stdout)
+        
         # 使用上下文中的函数与状态
         use = """
 console.log("Using Node.js context...");
@@ -2355,12 +2343,12 @@ const s = sum(3, 4);
 console.log(`Items now: ${n2}, sum=${s}`);
 ({ items: n2, sum: s })
 """
-
+        
         exec2 = self.sandbox.run_code(use, context=js_context)
         print(exec2.to_json())
         assert exec2.error is None
         assert any("Using Node.js context..." in line for line in exec2.logs.stdout)
-
+        
         # 清理上下文
         try:
             self.sandbox.destroy_context(js_context)
@@ -2371,11 +2359,11 @@ console.log(`Items now: ${n2}, sum=${s}`);
             logger.warning(f"Failed to destroy Node.js context: {e}")
 
     # ======================== Bash 测试 ========================
-
+    
     def test_bash_basic_execution(self):
         """测试Bash基础执行"""
         assert self.sandbox is not None
-
+        
         code = """
 # Bash 基础执行
 echo "Hello from Bash Kernel!"
@@ -2385,7 +2373,7 @@ echo "${GREETING}"
 echo "Current user: $(whoami)"
 date
 """
-
+        
         execution = self.sandbox.run_code(code, language="bash")
         print(execution.to_json())
         assert execution.error is None
@@ -2396,7 +2384,7 @@ date
     def test_bash_file_operations(self):
         """测试Bash文件操作"""
         assert self.sandbox is not None
-
+        
         code = """
 set -e
 echo "Creating files..."
@@ -2411,7 +2399,7 @@ ls -l
 wc -l all.txt
 echo "Done"
 """
-
+        
         execution = self.sandbox.run_code(code, language="bash")
         print(execution.to_json())
         assert execution.error is None
@@ -2422,13 +2410,13 @@ echo "Done"
     def test_bash_pipelines_and_grep(self):
         """测试Bash管道与grep"""
         assert self.sandbox is not None
-
+        
         code = """
 set -e
 printf "%s\n" foo bar baz foo bar | grep -n "foo" | awk -F: '{print "line", $1, ":", $2}'
 echo "PIPELINE_OK"
 """
-
+        
         execution = self.sandbox.run_code(code, language="bash")
         print(execution.to_json())
         assert execution.error is None
@@ -2438,14 +2426,14 @@ echo "PIPELINE_OK"
     def test_bash_env_and_exit_codes(self):
         """测试Bash环境变量与退出码"""
         assert self.sandbox is not None
-
+        
         code = """
 export APP_ENV=production
 echo "ENV=$APP_ENV"
 (exit 7)
 echo $?
 """
-
+        
         execution = self.sandbox.run_code(code, language="bash")
         print(execution.to_json())
         assert execution.error is None
@@ -2457,35 +2445,35 @@ echo $?
     def test_bash_context_management(self):
         """测试Bash上下文管理"""
         assert self.sandbox is not None
-
+        
         # 创建Bash上下文
         bash_ctx = self.sandbox.create_code_context(language="bash", cwd="/tmp")
         self.contexts["bash"] = bash_ctx
-
+        
         setup = """
 echo "Setting up Bash context..."
 MYVAR=42
 echo $MYVAR
 """
-
+        
         e1 = self.sandbox.run_code(setup, context=bash_ctx)
         print(e1.to_json())
         assert e1.error is None
         assert any("Setting up Bash context..." in line for line in e1.logs.stdout)
-
+        
         use = """
 echo "Using Bash context..."
 echo "MYVAR=$MYVAR"
 MYVAR=$((MYVAR+8))
 echo "MYVAR_AFTER=$MYVAR"
 """
-
+        
         e2 = self.sandbox.run_code(use, context=bash_ctx)
         print(e2.to_json())
         assert e2.error is None
         assert any("Using Bash context..." in line for line in e2.logs.stdout)
         assert any("MYVAR_AFTER=50" in line for line in e2.logs.stdout)
-
+        
         # 清理上下文
         try:
             self.sandbox.destroy_context(bash_ctx)
@@ -2496,11 +2484,11 @@ echo "MYVAR_AFTER=$MYVAR"
             logger.warning(f"Failed to destroy Bash context: {e}")
 
     # ======================== IJAVA 测试 ========================
-
+    
     def test_ijava_basic_execution(self):
         """测试IJAVA基础执行"""
         assert self.sandbox is not None
-
+        
         code = """
 // IJAVA 基础执行测试
 System.out.println("Hello from IJAVA Kernel!");
@@ -2532,7 +2520,7 @@ System.out.println(a);
 System.out.println(b);
 System.out.println(sum);
 """
-
+        
         execution = self.sandbox.run_code(code, language="java")
         print(execution.to_json())
         assert execution.error is None
@@ -2544,7 +2532,7 @@ System.out.println(sum);
     def test_ijava_oop_features(self):
         """测试IJAVA面向对象特性"""
         assert self.sandbox is not None
-
+        
         code = """
 // IJAVA 面向对象特性测试
 System.out.println("Testing IJAVA OOP features...");
@@ -2596,23 +2584,19 @@ student;
 
 System.out.println("IJAVA OOP test completed successfully!");
 """
-
+        
         execution = self.sandbox.run_code(code, language="java")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing IJAVA OOP features..." in line for line in execution.logs.stdout
-        )
+        assert any("Testing IJAVA OOP features..." in line for line in execution.logs.stdout)
         assert any("Hi, I'm Alice" in line for line in execution.logs.stdout)
-        assert any(
-            "I'm studying Computer Science" in line for line in execution.logs.stdout
-        )
+        assert any("I'm studying Computer Science" in line for line in execution.logs.stdout)
         logger.info("IJAVA OOP features test passed")
 
     def test_ijava_collections(self):
         """测试IJAVA集合框架"""
         assert self.sandbox is not None
-
+        
         code = """
 import java.util.*;
 
@@ -2658,25 +2642,19 @@ numbers.contains(2);
 
 System.out.println("IJAVA Collections test completed!");
 """
-
+        
         execution = self.sandbox.run_code(code, language="java")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing IJAVA Collections..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Fruits: [Apple, Banana, Orange]" in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Unique numbers: [1, 2, 3]" in line for line in execution.logs.stdout
-        )
+        assert any("Testing IJAVA Collections..." in line for line in execution.logs.stdout)
+        assert any("Fruits: [Apple, Banana, Orange]" in line for line in execution.logs.stdout)
+        assert any("Unique numbers: [1, 2, 3]" in line for line in execution.logs.stdout)
         logger.info("IJAVA collections test passed")
 
     def test_ijava_file_io(self):
         """测试IJAVA文件I/O"""
         assert self.sandbox is not None
-
+        
         code = """
 import java.io.*;
 import java.nio.file.*;
@@ -2721,19 +2699,13 @@ try {
     System.err.println("Error: " + e.getMessage());
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="java")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing IJAVA File I/O..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "File written successfully" in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Hello from IJAVA File I/O!" in line for line in execution.logs.stdout
-        )
+        assert any("Testing IJAVA File I/O..." in line for line in execution.logs.stdout)
+        assert any("File written successfully" in line for line in execution.logs.stdout)
+        assert any("Hello from IJAVA File I/O!" in line for line in execution.logs.stdout)
         logger.info("IJAVA file I/O test passed")
 
     def test_ijava_context_management(self):
@@ -2790,9 +2762,7 @@ getCounter();
         execution1 = self.sandbox.run_code(setup_code, context=ijava_context)
         print(execution1.to_json())
         assert execution1.error is None
-        assert any(
-            "Setting up IJAVA context..." in line for line in execution1.logs.stdout
-        )
+        assert any("Setting up IJAVA context..." in line for line in execution1.logs.stdout)
         assert any("Initial counter: 0" in line for line in execution1.logs.stdout)
 
         # 在同一上下文中使用之前定义的变量和方法
@@ -2842,11 +2812,11 @@ System.out.println("IJAVA context usage completed!");
             logger.warning(f"Failed to destroy IJAVA context {ijava_context.id}: {e}")
 
     # ======================== Deno 测试 ========================
-
+    
     def test_deno_basic_execution(self):
         """测试Deno基础执行"""
         assert self.sandbox is not None
-
+        
         code = """
 // Deno 基础执行测试
 console.log("Hello from Deno Kernel!");
@@ -2878,7 +2848,7 @@ const person = {
 };
 console.log(`Person: ${person.name}, ${person.age} years old`);
 """
-
+        
         execution = self.sandbox.run_code(code, language="typescript")
         print(execution.to_json())
         assert execution.error is None
@@ -2890,7 +2860,7 @@ console.log(`Person: ${person.name}, ${person.age} years old`);
     def test_deno_typescript_features(self):
         """测试Deno TypeScript特性"""
         assert self.sandbox is not None
-
+        
         code = """
 // Deno TypeScript 特性测试
 interface User {
@@ -2963,14 +2933,11 @@ processItems(numbers, (num) => console.log(`Processing: ${num}`));
 console.log(`Status: ${Status.APPROVED}`);
 console.log("TypeScript features test completed!");
 """
-
+        
         execution = self.sandbox.run_code(code, language="typescript")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing Deno TypeScript features..." in line
-            for line in execution.logs.stdout
-        )
+        assert any("Testing Deno TypeScript features..." in line for line in execution.logs.stdout)
         assert any("Added user: John Doe" in line for line in execution.logs.stdout)
         assert any("Total users: 2" in line for line in execution.logs.stdout)
         logger.info("Deno TypeScript features test passed")
@@ -2978,7 +2945,7 @@ console.log("TypeScript features test completed!");
     def test_deno_async_await(self):
         """测试Deno异步/await"""
         assert self.sandbox is not None
-
+        
         code = """
 // Deno 异步/await 测试
 async function delay(ms: number): Promise<void> {
@@ -3018,25 +2985,19 @@ async function main(): Promise<void> {
 // 顶层 await，让内核等待完成
 await main();
 """
-
+        
         execution = self.sandbox.run_code(code, language="typescript")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing Deno async/await..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Starting batch processing..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Batch processing completed" in line for line in execution.logs.stdout
-        )
+        assert any("Testing Deno async/await..." in line for line in execution.logs.stdout)
+        assert any("Starting batch processing..." in line for line in execution.logs.stdout)
+        assert any("Batch processing completed" in line for line in execution.logs.stdout)
         logger.info("Deno async/await test passed")
 
     def test_deno_file_operations(self):
         """测试Deno文件操作"""
         assert self.sandbox is not None
-
+        
         code = """
 // Deno 文件操作测试（原生 API，兼容 1.x+）
 await (async () => {
@@ -3066,31 +3027,23 @@ await (async () => {
   }
 })();
 """
-
+        
         execution = self.sandbox.run_code(code, language="typescript")
         print(execution.to_json())
         assert execution.error is None
-        assert any(
-            "Testing Deno file operations..." in line for line in execution.logs.stdout
-        )
-        assert any(
-            "File written successfully" in line for line in execution.logs.stdout
-        )
-        assert any(
-            "Hello from Deno File Operations!" in line for line in execution.logs.stdout
-        )
+        assert any("Testing Deno file operations..." in line for line in execution.logs.stdout)
+        assert any("File written successfully" in line for line in execution.logs.stdout)
+        assert any("Hello from Deno File Operations!" in line for line in execution.logs.stdout)
         logger.info("Deno file operations test passed")
 
     def test_deno_context_management(self):
         """测试Deno上下文管理"""
         assert self.sandbox is not None
-
+        
         # 创建Deno上下文
-        deno_context = self.sandbox.create_code_context(
-            language="typescript", cwd="/tmp"
-        )
+        deno_context = self.sandbox.create_code_context(language="typescript", cwd="/tmp")
         self.contexts["deno"] = deno_context
-
+        
         # 在上下文中定义变量和函数
         setup_code = """
 // Deno 上下文设置
@@ -3126,15 +3079,13 @@ console.log(`Initial counter: ${counter}`);
 console.log(`Cache size: ${cache.size}`);
 console.log(`Context data: ${contextData.value}`);
 """
-
+        
         execution1 = self.sandbox.run_code(setup_code, context=deno_context)
         print(execution1.to_json())
         assert execution1.error is None
-        assert any(
-            "Setting up Deno context..." in line for line in execution1.logs.stdout
-        )
+        assert any("Setting up Deno context..." in line for line in execution1.logs.stdout)
         assert any("Initial counter: 0" in line for line in execution1.logs.stdout)
-
+        
         # 在同一上下文中使用之前定义的变量和函数
         use_code = """
 // 使用 Deno 上下文中的变量和函数
@@ -3161,19 +3112,15 @@ console.log(`Modified context data: ${contextData.value}`);
 
 console.log("Context usage completed!");
 """
-
+        
         execution2 = self.sandbox.run_code(use_code, context=deno_context)
         print(execution2.to_json())
         assert execution2.error is None
         assert any("Using Deno context..." in line for line in execution2.logs.stdout)
-        assert any(
-            "Counter after increment: 1" in line for line in execution2.logs.stdout
-        )
-        assert any(
-            "Cache size after addition: 1" in line for line in execution2.logs.stdout
-        )
+        assert any("Counter after increment: 1" in line for line in execution2.logs.stdout)
+        assert any("Cache size after addition: 1" in line for line in execution2.logs.stdout)
         logger.info("Deno context management test passed")
-
+        
         # 测试完成后立即清理context
         try:
             self.sandbox.destroy_context(deno_context)
@@ -3185,11 +3132,11 @@ console.log("Context usage completed!");
             logger.warning(f"Failed to destroy Deno context {deno_context.id}: {e}")
 
     # ======================== 高级功能测试 ========================
-
+    
     def test_web_request_simulation(self):
         """测试网络请求模拟"""
         assert self.sandbox is not None
-
+        
         code = """
 import json
 import time
@@ -3258,7 +3205,7 @@ print(f"\\n完成 {len(results)} 个API调用")
     "results": results
 }
 """
-
+        
         execution = self.sandbox.run_code(code, language="python")
         print(execution.to_json())
         assert execution.error is None
@@ -3269,91 +3216,80 @@ print(f"\\n完成 {len(results)} 个API调用")
     def run_all_tests(self):
         """运行所有测试"""
         logger.info("开始CodeInterpreter综合验证测试...")
-
+        
         # 基础操作测试
         self.run_test(self.test_code_interpreter_creation, "CodeInterpreter Creation")
         self.run_test(self.test_basic_python_execution, "Basic Python Execution")
-        self.run_test(self.test_math_calculations, "Math Calculations")
-        self.run_test(self.test_data_processing, "Data Processing")
-        self.run_test(self.test_visualization_code, "Visualization Code")
-
-        # 回调函数测试
-        self.run_test(self.test_callback_handling, "Callback Handling")
-        self.run_test(self.test_error_handling, "Error Handling")
-
-        # 上下文管理测试
-        self.run_test(self.test_context_creation, "Context Creation")
-        self.run_test(self.test_context_persistence, "Context Persistence")
-        self.run_test(self.test_multiple_contexts, "Multiple Contexts")
-
-        # 数据类型测试
-        self.run_test(self.test_different_data_types, "Different Data Types")
-        self.run_test(
-            self.test_file_operations_simulation, "File Operations Simulation"
-        )
-
-        # 性能测试
-        self.run_test(
-            self.test_performance_simple_calculations, "Performance Simple Calculations"
-        )
-        self.run_test(
-            self.test_performance_concurrent_simulation,
-            "Performance Concurrent Simulation",
-        )
-
-        # 结果格式测试
-        self.run_test(self.test_text_result, "Text Result Format")
-        self.run_test(self.test_html_result, "HTML Result Format")
-        self.run_test(self.test_markdown_result, "Markdown Result Format")
-        self.run_test(self.test_svg_result, "SVG Result Format")
-        self.run_test(self.test_image_results, "Image Result Formats (PNG/JPEG)")
-        self.run_test(self.test_latex_result, "LaTeX Result Format")
-        self.run_test(self.test_json_data_result, "JSON Data Result Format")
-        self.run_test(self.test_javascript_result, "JavaScript Result Format")
-        self.run_test(self.test_chart_data_result, "Chart Data Result Format")
-        self.run_test(self.test_mixed_format_result, "Mixed Format Result")
-
-        # R语言测试
-        self.run_test(
-            self.test_r_language_basic_execution, "R Language Basic Execution"
-        )
-        self.run_test(self.test_r_language_data_analysis, "R Language Data Analysis")
-        self.run_test(self.test_r_language_visualization, "R Language Visualization")
-        self.run_test(self.test_r_language_statistics, "R Language Statistics")
-        self.run_test(
-            self.test_r_language_context_management, "R Language Context Management"
-        )
-
-        # Node.js/JavaScript 测试
-        self.run_test(self.test_nodejs_basic_execution, "Node.js Basic Execution")
-        self.run_test(self.test_nodejs_async_promises, "Node.js Async Promises")
-        self.run_test(self.test_nodejs_data_processing, "Node.js Data Processing")
-        self.run_test(self.test_nodejs_chart_data, "Node.js Chart Data Generation")
-        self.run_test(self.test_nodejs_context_management, "Node.js Context Management")
-
-        # Bash 测试
-        self.run_test(self.test_bash_basic_execution, "Bash Basic Execution")
-        self.run_test(self.test_bash_file_operations, "Bash File Operations")
-        self.run_test(self.test_bash_pipelines_and_grep, "Bash Pipelines and Grep")
-        # self.run_test(self.test_bash_env_and_exit_codes, "Bash Env and Exit Codes")
-        self.run_test(self.test_bash_context_management, "Bash Context Management")
-
-        # IJAVA 测试
-        self.run_test(self.test_ijava_basic_execution, "IJAVA Basic Execution")
-        self.run_test(self.test_ijava_oop_features, "IJAVA OOP Features")
-        self.run_test(self.test_ijava_collections, "IJAVA Collections")
-        self.run_test(self.test_ijava_file_io, "IJAVA File I/O")
-        self.run_test(self.test_ijava_context_management, "IJAVA Context Management")
-
-        # Deno 测试
-        self.run_test(self.test_deno_basic_execution, "Deno Basic Execution")
-        self.run_test(self.test_deno_typescript_features, "Deno TypeScript Features")
-        self.run_test(self.test_deno_async_await, "Deno Async/Await")
-        self.run_test(self.test_deno_file_operations, "Deno File Operations")
-        self.run_test(self.test_deno_context_management, "Deno Context Management")
-
-        # 高级功能测试
-        self.run_test(self.test_web_request_simulation, "Web Request Simulation")
+        # self.run_test(self.test_math_calculations, "Math Calculations")
+        # self.run_test(self.test_data_processing, "Data Processing")
+        # self.run_test(self.test_visualization_code, "Visualization Code")
+        #
+        # # 回调函数测试
+        # self.run_test(self.test_callback_handling, "Callback Handling")
+        # self.run_test(self.test_error_handling, "Error Handling")
+        #
+        # # 上下文管理测试
+        # self.run_test(self.test_context_creation, "Context Creation")
+        # self.run_test(self.test_context_persistence, "Context Persistence")
+        # self.run_test(self.test_multiple_contexts, "Multiple Contexts")
+        #
+        # # 数据类型测试
+        # self.run_test(self.test_different_data_types, "Different Data Types")
+        # self.run_test(self.test_file_operations_simulation, "File Operations Simulation")
+        #
+        # # 性能测试
+        # self.run_test(self.test_performance_simple_calculations, "Performance Simple Calculations")
+        # self.run_test(self.test_performance_concurrent_simulation, "Performance Concurrent Simulation")
+        #
+        # # 结果格式测试
+        # self.run_test(self.test_text_result, "Text Result Format")
+        # self.run_test(self.test_html_result, "HTML Result Format")
+        # self.run_test(self.test_markdown_result, "Markdown Result Format")
+        # self.run_test(self.test_svg_result, "SVG Result Format")
+        # self.run_test(self.test_image_results, "Image Result Formats (PNG/JPEG)")
+        # self.run_test(self.test_latex_result, "LaTeX Result Format")
+        # self.run_test(self.test_json_data_result, "JSON Data Result Format")
+        # self.run_test(self.test_javascript_result, "JavaScript Result Format")
+        # self.run_test(self.test_chart_data_result, "Chart Data Result Format")
+        # self.run_test(self.test_mixed_format_result, "Mixed Format Result")
+        #
+        # # R语言测试
+        # self.run_test(self.test_r_language_basic_execution, "R Language Basic Execution")
+        # self.run_test(self.test_r_language_data_analysis, "R Language Data Analysis")
+        # self.run_test(self.test_r_language_visualization, "R Language Visualization")
+        # self.run_test(self.test_r_language_statistics, "R Language Statistics")
+        # self.run_test(self.test_r_language_context_management, "R Language Context Management")
+        #
+        # # Node.js/JavaScript 测试
+        # self.run_test(self.test_nodejs_basic_execution, "Node.js Basic Execution")
+        # self.run_test(self.test_nodejs_async_promises, "Node.js Async Promises")
+        # self.run_test(self.test_nodejs_data_processing, "Node.js Data Processing")
+        # self.run_test(self.test_nodejs_chart_data, "Node.js Chart Data Generation")
+        # self.run_test(self.test_nodejs_context_management, "Node.js Context Management")
+        #
+        # # Bash 测试
+        # self.run_test(self.test_bash_basic_execution, "Bash Basic Execution")
+        # self.run_test(self.test_bash_file_operations, "Bash File Operations")
+        # self.run_test(self.test_bash_pipelines_and_grep, "Bash Pipelines and Grep")
+        # # self.run_test(self.test_bash_env_and_exit_codes, "Bash Env and Exit Codes")
+        # self.run_test(self.test_bash_context_management, "Bash Context Management")
+        #
+        # # IJAVA 测试
+        # self.run_test(self.test_ijava_basic_execution, "IJAVA Basic Execution")
+        # self.run_test(self.test_ijava_oop_features, "IJAVA OOP Features")
+        # self.run_test(self.test_ijava_collections, "IJAVA Collections")
+        # self.run_test(self.test_ijava_file_io, "IJAVA File I/O")
+        # self.run_test(self.test_ijava_context_management, "IJAVA Context Management")
+        #
+        # # Deno 测试
+        # self.run_test(self.test_deno_basic_execution, "Deno Basic Execution")
+        # self.run_test(self.test_deno_typescript_features, "Deno TypeScript Features")
+        # self.run_test(self.test_deno_async_await, "Deno Async/Await")
+        # self.run_test(self.test_deno_file_operations, "Deno File Operations")
+        # self.run_test(self.test_deno_context_management, "Deno Context Management")
+        #
+        # # 高级功能测试
+        # self.run_test(self.test_web_request_simulation, "Web Request Simulation")
 
     def cleanup(self):
         """清理资源"""
@@ -3364,14 +3300,14 @@ print(f"\\n完成 {len(results)} 个API调用")
                 logger.info(f"Successfully destroyed context {name}: {context.id}")
             except Exception as e:
                 logger.warning(f"Error cleaning up context {name}: {e}")
-
+        
         # 清空contexts字典
         self.contexts.clear()
-
+        
         # 清理沙箱
         if self.sandbox:
             try:
-                self.sandbox.kill()
+                # self.sandbox.kill()
                 logger.info("CodeInterpreter sandbox cleaned up successfully")
             except Exception as e:
                 logger.error(f"Error cleaning up sandbox: {e}")
@@ -3379,32 +3315,32 @@ print(f"\\n完成 {len(results)} 个API调用")
     def print_summary(self):
         """打印测试摘要"""
         total_tests = len(self.test_results)
-        passed_tests = sum(1 for r in self.test_results if r["success"])
+        passed_tests = sum(1 for r in self.test_results if r['success'])
         failed_tests = total_tests - passed_tests
-
-        total_duration = sum(r["duration"] for r in self.test_results)
-
-        print("\n" + "=" * 60)
+        
+        total_duration = sum(r['duration'] for r in self.test_results)
+        
+        print("\n" + "="*60)
         print("CodeInterpreter综合验证测试报告")
-        print("=" * 60)
+        print("="*60)
         print(f"总测试数: {total_tests}")
         print(f"通过数: {passed_tests}")
         print(f"失败数: {failed_tests}")
         print(f"总耗时: {total_duration:.3f}秒")
         print(f"成功率: {(passed_tests/total_tests*100):.1f}%")
-
+        
         if self.failed_tests:
             print(f"\n失败的测试:")
             for test in self.failed_tests:
                 print(f"  ❌ {test}")
-
-        print("=" * 60)
+        
+        print("="*60)
 
 
 def main():
     """主函数"""
     validator = CodeInterpreterValidator()
-
+    
     try:
         validator.run_all_tests()
     finally: