Isolated Test Execution Service

from hopx_ai import Sandbox
import os
import json
from typing import Dict, List, Any
from concurrent.futures import ThreadPoolExecutor, as_completed

class IsolatedTestExecutor:
    def __init__(self, api_key: str):
        self.api_key = api_key
    
    def execute_test(self, test_code: str, test_framework: str = "pytest", timeout: int = 60) -> Dict[str, Any]:
        """Execute a single test in isolated sandbox"""
        sandbox = None
        try:
            # Create fresh sandbox for each test
            sandbox = Sandbox.create(
                template="code-interpreter",
                api_key=self.api_key,
                timeout_seconds=timeout + 10
            )
            
            # Write test file
            test_file = "/workspace/test_file.py"
            sandbox.files.write(test_file, test_code)
            
            # Install test framework if needed
            if test_framework == "pytest":
                sandbox.commands.run("pip install pytest", timeout=30)
                # Execute test
                result = sandbox.commands.run(f"pytest {test_file} -v", timeout=timeout)
            elif test_framework == "unittest":
                result = sandbox.commands.run(f"python -m unittest {test_file}", timeout=timeout)
            else:
                result = sandbox.run_code(test_code, timeout=timeout)
            
            # Parse test results
            test_results = self._parse_test_results(result.stdout, test_framework)
            
            return {
                "success": result.exit_code == 0,
                "exit_code": result.exit_code,
                "stdout": result.stdout,
                "stderr": result.stderr,
                "test_results": test_results,
                "execution_time": getattr(result, 'execution_time', 0)
            }
            
        except Exception as e:
            return {
                "success": False,
                "error": str(e),
                "stderr": str(e)
            }
        finally:
            if sandbox:
                sandbox.kill()
    
    def _parse_test_results(self, output: str, framework: str) -> Dict[str, Any]:
        """Parse test framework output"""
        if framework == "pytest":
            # Parse pytest output
            passed = output.count("PASSED")
            failed = output.count("FAILED")
            return {
                "passed": passed,
                "failed": failed,
                "total": passed + failed
            }
        else:
            return {
                "passed": 0,
                "failed": 0,
                "total": 0
            }

# Usage
executor = IsolatedTestExecutor(api_key=os.getenv("HOPX_API_KEY"))

test_code = """
def test_addition():
    assert 1 + 1 == 2

def test_subtraction():
    assert 5 - 3 == 2
"""

result = executor.execute_test(test_code, test_framework="pytest")
print(json.dumps(result, indent=2))

class ParallelTestExecutor(IsolatedTestExecutor):
    def execute_test_suite(self, test_suite: List[Dict], max_workers: int = 5) -> Dict[str, Any]:
        """Execute multiple tests in parallel"""
        results = []
        
        with ThreadPoolExecutor(max_workers=max_workers) as executor:
            # Submit all tests
            future_to_test = {
                executor.submit(
                    self.execute_test,
                    test["code"],
                    test.get("framework", "pytest"),
                    test.get("timeout", 60)
                ): test
                for test in test_suite
            }
            
            # Collect results as they complete
            for future in as_completed(future_to_test):
                test = future_to_test[future]
                try:
                    result = future.result()
                    results.append({
                        "test_name": test.get("name", "unknown"),
                        "result": result
                    })
                except Exception as e:
                    results.append({
                        "test_name": test.get("name", "unknown"),
                        "result": {
                            "success": False,
                            "error": str(e)
                        }
                    })
        
        # Aggregate results
        total_tests = len(results)
        passed_tests = sum(1 for r in results if r["result"].get("success", False))
        failed_tests = total_tests - passed_tests
        
        return {
            "total_tests": total_tests,
            "passed": passed_tests,
            "failed": failed_tests,
            "success_rate": (passed_tests / total_tests * 100) if total_tests > 0 else 0,
            "results": results
        }

# Usage
executor = ParallelTestExecutor(api_key=os.getenv("HOPX_API_KEY"))

test_suite = [
    {
        "name": "test_math",
        "code": """
def test_addition():
    assert 1 + 1 == 2
""",
        "framework": "pytest",
        "timeout": 30
    },
    {
        "name": "test_strings",
        "code": """
def test_concatenation():
    assert "hello" + " " + "world" == "hello world"
""",
        "framework": "pytest",
        "timeout": 30
    }
]

results = executor.execute_test_suite(test_suite, max_workers=2)
print(json.dumps(results, indent=2))

class IsolatedTestRunner:
    def __init__(self, api_key: str):
        self.api_key = api_key
    
    def run_isolated_test(self, test_config: Dict) -> Dict[str, Any]:
        """Run test with complete isolation"""
        sandbox = None
        try:
            # Create sandbox with clean environment
            sandbox = Sandbox.create(
                template="code-interpreter",
                api_key=self.api_key,
                timeout_seconds=test_config.get("timeout", 60) + 10,
                env_vars=test_config.get("env_vars", {})
            )
            
            # Set up test environment
            setup_code = test_config.get("setup", "")
            if setup_code:
                setup_result = sandbox.run_code(setup_code, timeout=30)
                if not setup_result.success:
                    return {
                        "success": False,
                        "error": f"Setup failed: {setup_result.stderr}",
                        "stage": "setup"
                    }
            
            # Write test files
            for file_config in test_config.get("files", []):
                sandbox.files.write(
                    file_config["path"],
                    file_config["content"]
                )
            
            # Execute test
            test_result = sandbox.run_code(
                test_config["test_code"],
                language=test_config.get("language", "python"),
                timeout=test_config.get("timeout", 60)
            )
            
            # Cleanup (teardown)
            teardown_code = test_config.get("teardown", "")
            if teardown_code:
                sandbox.run_code(teardown_code, timeout=30)
            
            return {
                "success": test_result.success,
                "stdout": test_result.stdout,
                "stderr": test_result.stderr,
                "exit_code": test_result.exit_code,
                "execution_time": test_result.execution_time
            }
            
        except Exception as e:
            return {
                "success": False,
                "error": str(e)
            }
        finally:
            # Always cleanup - fresh sandbox for next test
            if sandbox:
                sandbox.kill()

# Usage
runner = IsolatedTestRunner(api_key=os.getenv("HOPX_API_KEY"))

test_config = {
    "test_code": """
import unittest

class TestMath(unittest.TestCase):
    def test_addition(self):
        self.assertEqual(1 + 1, 2)
    
    def test_multiplication(self):
        self.assertEqual(2 * 3, 6)

if __name__ == '__main__':
    unittest.main()
""",
    "setup": "import unittest",
    "timeout": 30,
    "env_vars": {
        "TEST_MODE": "true"
    },
    "files": [
        {
            "path": "/workspace/test_utils.py",
            "content": "def helper(): return 'helper'"
        }
    ]
}

result = runner.run_isolated_test(test_config)
print(json.dumps(result, indent=2))

class TestResultAggregator:
    def __init__(self):
        self.results = []
    
    def add_result(self, test_name: str, result: Dict[str, Any]):
        """Add test result to aggregation"""
        self.results.append({
            "test_name": test_name,
            "result": result,
            "timestamp": self._get_timestamp()
        })
    
    def generate_report(self) -> Dict[str, Any]:
        """Generate aggregated test report"""
        total = len(self.results)
        passed = sum(1 for r in self.results if r["result"].get("success", False))
        failed = total - passed
        
        # Calculate execution times
        execution_times = [
            r["result"].get("execution_time", 0)
            for r in self.results
            if "execution_time" in r["result"]
        ]
        avg_time = sum(execution_times) / len(execution_times) if execution_times else 0
        total_time = sum(execution_times)
        
        # Group by status
        passed_tests = [r for r in self.results if r["result"].get("success", False)]
        failed_tests = [r for r in self.results if not r["result"].get("success", False)]
        
        return {
            "summary": {
                "total": total,
                "passed": passed,
                "failed": failed,
                "success_rate": (passed / total * 100) if total > 0 else 0,
                "average_execution_time": avg_time,
                "total_execution_time": total_time
            },
            "passed_tests": [
                {
                    "name": r["test_name"],
                    "execution_time": r["result"].get("execution_time", 0)
                }
                for r in passed_tests
            ],
            "failed_tests": [
                {
                    "name": r["test_name"],
                    "error": r["result"].get("error") or r["result"].get("stderr", ""),
                    "execution_time": r["result"].get("execution_time", 0)
                }
                for r in failed_tests
            ],
            "all_results": self.results
        }
    
    def _get_timestamp(self) -> str:
        from datetime import datetime
        return datetime.now().isoformat()

# Usage
aggregator = TestResultAggregator()

# Add results
aggregator.add_result("test_1", {"success": True, "execution_time": 1.5})
aggregator.add_result("test_2", {"success": False, "error": "Assertion failed"})
aggregator.add_result("test_3", {"success": True, "execution_time": 2.1})

# Generate report
report = aggregator.generate_report()
print(json.dumps(report, indent=2))