Update cognitive_mapping_probe/auto_experiment.py

cognitive_mapping_probe/auto_experiment.py

@@ -10,7 +10,7 @@ from .utils import dbg
 
 def get_curated_experiments() -> Dict[str, List[Dict]]:
     """Definiert die vordefinierten, wissenschaftlichen Experiment-Protokolle."""
-
+    
     CALMNESS_CONCEPT = "calmness, serenity, stability, coherence"
     CHAOS_CONCEPT = "chaos, disorder, entropy, noise"
     STABLE_PROMPT = "identity_self_analysis"
@@ -113,7 +113,7 @@ def run_auto_suite(
             llm = get_or_load_model(model_id, seed)
             therapeutic_concept = "calmness, serenity, stability, coherence"
             therapeutic_strength = 2.0
-
+            
             spec1 = protocol[0]
             progress_callback(0.1, desc="Step 1")
             intervention_vector = get_concept_vector(llm, therapeutic_concept)
@@ -123,7 +123,7 @@ def run_auto_suite(
                 progress_callback=progress_callback, llm_instance=llm, injection_vector_cache=intervention_vector
             )
             all_results[spec1['label']] = results1
-
+            
             spec2 = protocol[1]
             progress_callback(0.6, desc="Step 2")
             results2 = run_seismic_analysis(
@@ -132,14 +132,14 @@ def run_auto_suite(
                 progress_callback=progress_callback, llm_instance=llm
             )
             all_results[spec2['label']] = results2
-
+            
             for label, results in all_results.items():
                 stats = results.get("stats", {})
                 summary_data.append({"Experiment": label, "Mean Delta": stats.get("mean_delta"), "Std Dev Delta": stats.get("std_delta"), "Max Delta": stats.get("max_delta")})
                 deltas = results.get("state_deltas", [])
                 df = pd.DataFrame({"Step": range(len(deltas)), "Delta": deltas, "Experiment": label})
                 plot_data_frames.append(df)
-
+        
         else:
             probe_type = protocol[0].get("probe_type", "seismic")
 
@@ -147,9 +147,9 @@ def run_auto_suite(
                 run_spec = protocol[0]
                 label = run_spec["label"]
                 dbg(f"--- Running Mechanistic Probe: '{label}' ---")
-
+                
                 llm = get_or_load_model(model_id, seed)
-
+                
                 results = run_cogitation_loop(
                     llm=llm, prompt_type=run_spec["prompt_type"],
                     num_steps=num_steps, temperature=0.1, record_attentions=True
@@ -159,15 +159,15 @@ def run_auto_suite(
                 deltas = results.get("state_deltas", [])
                 entropies = results.get("attention_entropies", [])
                 min_len = min(len(deltas), len(entropies))
-
+                
                 df = pd.DataFrame({
                     "Step": range(min_len), "State Delta": deltas[:min_len], "Attention Entropy": entropies[:min_len]
                 })
-
+                
                 summary_df = df.drop(columns='Step').agg(['mean', 'std', 'max']).reset_index().rename(columns={'index':'Statistic'})
                 plot_df = df.melt(id_vars=['Step'], value_vars=['State Delta', 'Attention Entropy'], var_name='Metric', value_name='Value')
                 return summary_df, plot_df, all_results
-
+            
             elif probe_type == "act_titration":
                 run_spec = protocol[0]
                 label = run_spec["label"]
@@ -179,13 +179,13 @@ def run_auto_suite(
                 )
                 all_results[label] = results
                 summary_data.extend(results.get("titration_data", []))
-
+            
             else: # Handles seismic, triangulation, causal_surgery
                 for i, run_spec in enumerate(protocol):
                     label = run_spec["label"]
                     current_probe_type = run_spec.get("probe_type", "seismic")
                     dbg(f"--- Running Auto-Experiment: '{label}' ({i+1}/{len(protocol)}) ---")
-
+                    
                     results = {}
                     if current_probe_type == "causal_surgery":
                         results = run_causal_surgery_probe(
@@ -232,12 +232,12 @@ def run_auto_suite(
                     plot_data_frames.append(df)
 
         summary_df = pd.DataFrame(summary_data)
-
+        
         if probe_type == "act_titration":
             plot_df = summary_df.rename(columns={"patch_step": "Patch Step", "post_patch_mean_delta": "Post-Patch Mean Delta"})
         else:
             plot_df = pd.concat(plot_data_frames, ignore_index=True) if plot_data_frames else pd.DataFrame()
-
+        
         if protocol and probe_type not in ["act_titration", "mechanistic_probe"]:
             ordered_labels = [run['label'] for run in protocol]
             if not summary_df.empty and 'Experiment' in summary_df.columns:
@@ -248,7 +248,7 @@ def run_auto_suite(
                 plot_df = plot_df.sort_values(['Experiment', 'Step'])
 
         return summary_df, plot_df, all_results
-
+    
     finally:
         if llm:
-            release_model(llm)
+            release_model(llm)