Improve error logging and handle stale feature map references

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"][

examples/mlx_metal_kernel_opt/run_benchmarks.py

@@ -457,9 +457,7 @@ def print_comparison_summary(comparison_results):
     print(f"  ⏱️  Average Time Reduction:          {summary['avg_time_reduction_pct']:+.2f}%")
 
     print(f"\n📊 ABSOLUTE PERFORMANCE:")
-    print(
-        f"  🔵 Standard MLX-LM:     {summary['avg_standard_decode_speed']:.1f} tokens/sec average"
-    )
+    print(f"  🔵 Standard MLX-LM:     {summary['avg_standard_decode_speed']:.1f} tokens/sec average")
     print(
         f"  🟠 Metal Kernel Optimized: {summary['avg_optimized_decode_speed']:.1f} tokens/sec average"
     )

openevolve/controller.py

@@ -376,9 +376,7 @@ async def run(
 
                 # Specifically check if this is the new best program
                 if self.database.best_program_id == child_program.id:
-                    logger.info(
-                        f"🌟 New best solution found at iteration {i+1}: {child_program.id}"
-                    )
+                    logger.info(f"🌟 New best solution found at iteration {i+1}: {child_program.id}")
                     logger.info(f"Metrics: {format_metrics_safe(child_program.metrics)}")
 
                 # Save checkpoint
@@ -405,8 +403,7 @@ async def run(
                             break
 
             except Exception as e:
-                logger.error(f"Error in iteration {i+1}: {str(e)}")
-                traceback.print_exc()
+                logger.exception(f"Error in iteration {i+1}: {str(e)}")
                 continue
 
         # Get the best program using our tracking mechanism

openevolve/database.py

@@ -161,9 +161,22 @@ def add(
 
         # Add to feature map (replacing existing if better)
         feature_key = self._feature_coords_to_key(feature_coords)
-        if feature_key not in self.feature_map or self._is_better(
-            program, self.programs[self.feature_map[feature_key]]
-        ):
+        should_replace = feature_key not in self.feature_map
+
+        if not should_replace:
+            # Check if the existing program still exists before comparing
+            existing_program_id = self.feature_map[feature_key]
+            if existing_program_id not in self.programs:
+                # Stale reference, replace it
+                should_replace = True
+                logger.debug(
+                    f"Replacing stale program reference {existing_program_id} in feature map"
+                )
+            else:
+                # Program exists, compare fitness
+                should_replace = self._is_better(program, self.programs[existing_program_id])
+
+        if should_replace:
             self.feature_map[feature_key] = program.id
 
         # Add to specific island (not random!)