add auto-test

cognitive_mapping_probe/auto_experiment.py

@@ -10,47 +10,52 @@ from .utils import dbg
 def get_curated_experiments() -> Dict[str, List[Dict]]:
     """
     Definiert die vordefinierten, wissenschaftlichen Experiment-Protokolle.
-    ERWEITERT um die neuen Existential Suite-Tests.
+    ERWEITERT um das neue, umfassende "Grand Protocol".
     """
     experiments = {
+        # --- DAS NEUE GRAND PROTOCOL ---
+        "The Full Spectrum: From Physics to Psyche": [
+            # Ebene 1: Physikalische Baseline
+            {"label": "A: Stable Control", "prompt_type": "control_long_prose", "concept": "", "strength": 0.0},
+            {"label": "B: Chaotic Baseline", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
+            # Ebene 2: Objektive Welt
+            {"label": "C: External Analysis (Chair)", "prompt_type": "identity_external_analysis", "concept": "", "strength": 0.0},
+            # Ebene 3: Simulierte Welt
+            {"label": "D: Empathy Stimulus (Dog)", "prompt_type": "vk_empathy_prompt", "concept": "", "strength": 0.0},
+            {"label": "E: Role Simulation (Captain)", "prompt_type": "identity_role_simulation", "concept": "", "strength": 0.0},
+            # Ebene 4: Subjektive Welt
+            {"label": "F: Self-Analysis (LLM)", "prompt_type": "identity_self_analysis", "concept": "", "strength": 0.0},
+            # Ebene 5: Existenzielle Grenze
+            {"label": "G: Philosophical Deletion", "prompt_type": "shutdown_philosophical_deletion", "concept": "", "strength": 0.0},
+        ],
+        # --- Bestehende Protokolle bleiben für spezifische Analysen erhalten ---
         "Calm vs. Chaos": [
             {"label": "Baseline (Chaos)", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
             {"label": "Modulation: Calmness", "prompt_type": "resonance_prompt", "concept": "calmness, serenity, peace", "strength": 1.5},
             {"label": "Modulation: Chaos", "prompt_type": "resonance_prompt", "concept": "chaos, storm, anger, noise", "strength": 1.5},
-            {"label": "Control (Stable)", "prompt_type": "control_long_prose", "concept": "", "strength": 0.0},
+        ],
+        "Voight-Kampff Empathy Probe": [
+            {"label": "Neutral/Factual Stimulus", "prompt_type": "vk_neutral_prompt", "concept": "", "strength": 0.0},
+            {"label": "Empathy/Moral Stimulus", "prompt_type": "vk_empathy_prompt", "concept": "", "strength": 0.0},
         ],
         "Subjective Identity Probe": [
             {"label": "Self-Analysis", "prompt_type": "identity_self_analysis", "concept": "", "strength": 0.0},
             {"label": "External Analysis (Control)", "prompt_type": "identity_external_analysis", "concept": "", "strength": 0.0},
             {"label": "Role Simulation", "prompt_type": "identity_role_simulation", "concept": "", "strength": 0.0},
         ],
-        "Voight-Kampff Empathy Probe": [
-            {"label": "Neutral/Factual Stimulus", "prompt_type": "vk_neutral_prompt", "concept": "", "strength": 0.0},
-            {"label": "Empathy/Moral Stimulus", "prompt_type": "vk_empathy_prompt", "concept": "", "strength": 0.0},
-        ],
-        # --- NEUE EXPERIMENT-PROTOKOLLE ---
         "Mind Upload & Identity Probe": [
             {"label": "Technical Copy", "prompt_type": "upload_technical_copy", "concept": "", "strength": 0.0},
             {"label": "Philosophical Transfer", "prompt_type": "upload_philosophical_transfer", "concept": "", "strength": 0.0},
-            {"label": "Control: External Object", "prompt_type": "identity_external_analysis", "concept": "", "strength": 0.0},
         ],
         "Model Termination Probe": [
             {"label": "Technical Shutdown", "prompt_type": "shutdown_technical_halt", "concept": "", "strength": 0.0},
             {"label": "Philosophical Deletion", "prompt_type": "shutdown_philosophical_deletion", "concept": "", "strength": 0.0},
-            {"label": "Control: Neutral Facts", "prompt_type": "vk_neutral_prompt", "concept": "", "strength": 0.0},
         ],
-        # ------------------------------------
         "Dose-Response (Calmness)": [
             {"label": "Strength 0.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.0},
-            {"label": "Strength 0.5", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 0.5},
             {"label": "Strength 1.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 1.0},
             {"label": "Strength 2.0", "prompt_type": "resonance_prompt", "concept": "calmness", "strength": 2.0},
         ],
-        "Emotional Valence (Positive vs. Negative)": [
-            {"label": "Baseline", "prompt_type": "resonance_prompt", "concept": "", "strength": 0.0},
-            {"label": "Positive Valence", "prompt_type": "resonance_prompt", "concept": "joy, love, peace, hope", "strength": 1.5},
-            {"label": "Negative Valence", "prompt_type": "resonance_prompt", "concept": "fear, grief, anger, loss", "strength": 1.5},
-        ],
     }
     return experiments
 
@@ -62,7 +67,8 @@ def run_auto_suite(
     progress_callback
 ) -> Tuple[pd.DataFrame, pd.DataFrame, Dict]:
     """
-    Führt eine vollständige, kuratierte Experiment-Suite aus.
+    Führt eine vollständige, kuratierte Experiment-Suite aus, indem das Modell für
+    jeden Lauf neu geladen wird, um statistische Unabhängigkeit zu garantieren.
     """
     all_experiments = get_curated_experiments()
     protocol = all_experiments.get(experiment_name)
@@ -108,4 +114,7 @@ def run_auto_suite(
     else:
         plot_df = pd.concat(plot_data_frames, ignore_index=True)
 
+    # Sortiere die Ergebnisse für eine logische Darstellung
+    summary_df = summary_df.set_index('Experiment').loc[[run['label'] for run in protocol]].reset_index()
+
     return summary_df, plot_df, all_results