Testing the Agent with Examples › Analyzing Test Results

def summarize_results(results):
    """
    Generate a summary of test results.
    """
    total = len(results)
    passed = sum(1 for r in results if r["passed"])
    failed = total - passed

    print(f"\n{'=' * 50}")
    print("Test Summary")
    print(f"{'=' * 50}")
    print(f"Total tests: {total}")
    print(f"Passed: {passed} ({passed / total * 100:.1f}%)")
    print(f"Failed: {failed} ({failed / total * 100:.1f}%)")

    # Break down by category
    categories = {}
    for result in results:
        # Find the test case to get its category
        test_case = next(
            (tc for tc in test_suite if tc["id"] == result["test_id"]), None
        )
        if test_case:
            cat = test_case["category"]
            if cat not in categories:
                categories[cat] = {"total": 0, "passed": 0}
            categories[cat]["total"] += 1
            if result["passed"]:
                categories[cat]["passed"] += 1

    print("\nBy Category:")
    for cat, stats in categories.items():
        success_rate = stats["passed"] / stats["total"] * 100
        print(
            f"  {cat}: {stats['passed']}/{stats['total']} ({success_rate:.1f}%)"
        )

    # List failed tests
    if failed > 0:
        print("\nFailed Tests:")
        for result in results:
            if not result["passed"]:
                print(f"  {result['test_id']}: {result['input'][:50]}...")