feat: Implement automatic artifact cleanup

examples/circle_packing/evaluator.py

@@ -35,22 +35,22 @@ def validate_packing(centers, radii):
         True if valid, False otherwise
     """
     n = centers.shape[0]
-    
+
     # Check for NaN values
     if np.isnan(centers).any():
         print("NaN values detected in circle centers")
         return False
-    
+
     if np.isnan(radii).any():
         print("NaN values detected in circle radii")
         return False
 
     # Check if radii are nonnegative and not nan
     for i in range(n):
-        if(radii[i] < 0):
+        if radii[i] < 0:
             print(f"Circle {i} has negative radius {radii[i]}")
             return False
-        elif(np.isnan(radii[i])):
+        elif np.isnan(radii[i]):
             print(f"Circle {i} has nan radius")
             return False
 
@@ -214,7 +214,7 @@ def evaluate(program_path):
             centers = np.array(centers)
         if not isinstance(radii, np.ndarray):
             radii = np.array(radii)
-            
+
         # Check for NaN values before validation
         if np.isnan(centers).any() or np.isnan(radii).any():
             print("NaN values detected in solution")

examples/circle_packing_with_artifacts/evaluator.py

@@ -295,9 +295,9 @@ def evaluate(program_path):
         # Add successful packing stats for good solutions
         if valid and target_ratio > 0.95:  # Near-optimal solutions
             artifacts["stdout"] = f"Excellent packing! Achieved {target_ratio:.1%} of target value"
-            artifacts[
-                "radius_stats"
-            ] = f"Min: {validation_details['min_radius']:.6f}, Max: {validation_details['max_radius']:.6f}, Avg: {validation_details['avg_radius']:.6f}"
+            artifacts["radius_stats"] = (
+                f"Min: {validation_details['min_radius']:.6f}, Max: {validation_details['max_radius']:.6f}, Avg: {validation_details['avg_radius']:.6f}"
+            )
 
         return EvaluationResult(
             metrics={
@@ -404,9 +404,9 @@ def evaluate_stage1(program_path):
 
             # Add validation issues if any
             if not valid:
-                artifacts[
-                    "stderr"
-                ] = f"Validation failed: {len(validation_details.get('boundary_violations', []))} boundary violations, {len(validation_details.get('overlaps', []))} overlaps"
+                artifacts["stderr"] = (
+                    f"Validation failed: {len(validation_details.get('boundary_violations', []))} boundary violations, {len(validation_details.get('overlaps', []))} overlaps"
+                )
                 artifacts["failure_stage"] = "stage1_geometric_validation"
                 if validation_details.get("boundary_violations"):
                     artifacts["boundary_issues"] = validation_details["boundary_violations"][