Derive classifier dimensions from bicorder.json automatically

Both export_model_for_js.py and bicorder_classifier.py now read
DIMENSIONS and KEY_DIMENSIONS directly from bicorder.json at runtime,
so the model stays in sync whenever gradient terms are renamed or
added. A COLUMN_RENAMES dict handles historical CSV column name
changes. The model now includes bicorder_version so the app's version
check works correctly.

Regenerated bicorder_model.json against bicorder.json v1.2.6 with
correct dimension names, 9 key dimensions from shortform flags, and
updated thresholds.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

analysis/bicorder_classifier.py

@@ -30,58 +30,46 @@ from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 import json
 from pathlib import Path
 
+# Path to bicorder.json (relative to this script)
+_BICORDER_JSON = Path(__file__).parent.parent / 'bicorder.json'
+
+# Historical column renames: maps old CSV column names → current bicorder.json names.
+# Add an entry here whenever gradient terms are renamed in bicorder.json.
+_COLUMN_RENAMES = {
+    'Design_elite_vs_vernacular': 'Design_institutional_vs_vernacular',
+    'Entanglement_exclusive_vs_non-exclusive': 'Entanglement_monopolistic_vs_pluralistic',
+    'Experience_sufficient_vs_insufficient': 'Experience_sufficient_vs_limited',
+    'Experience_Kafka_vs_Whitehead': 'Experience_restraining_vs_liberating',
+}
+
+
+def _load_bicorder_dimensions(bicorder_path=_BICORDER_JSON):
+    """Read DIMENSIONS and KEY_DIMENSIONS from bicorder.json."""
+    with open(bicorder_path) as f:
+        data = json.load(f)
+    dimensions = []
+    key_dimensions = []
+    for category in data['diagnostic']:
+        set_name = category['set_name']
+        for gradient in category['gradients']:
+            dim_name = f"{set_name}_{gradient['term_left']}_vs_{gradient['term_right']}"
+            dimensions.append(dim_name)
+            if gradient.get('shortform', False):
+                key_dimensions.append(dim_name)
+    return dimensions, key_dimensions
+
 
 class BicorderClassifier:
     """
     Classifies protocols into one of two families and recommends form type.
     """
 
-    # Dimension names (in order)
-    DIMENSIONS = [
-        'Design_explicit_vs_implicit',
-        'Design_precise_vs_interpretive',
-        'Design_elite_vs_vernacular',
-        'Design_documenting_vs_enabling',
-        'Design_static_vs_malleable',
-        'Design_technical_vs_social',
-        'Design_universal_vs_particular',
-        'Design_durable_vs_ephemeral',
-        'Entanglement_macro_vs_micro',
-        'Entanglement_sovereign_vs_subsidiary',
-        'Entanglement_self-enforcing_vs_enforced',
-        'Entanglement_abstract_vs_embodied',
-        'Entanglement_obligatory_vs_voluntary',
-        'Entanglement_flocking_vs_swarming',
-        'Entanglement_defensible_vs_exposed',
-        'Entanglement_exclusive_vs_non-exclusive',
-        'Experience_sufficient_vs_insufficient',
-        'Experience_crystallized_vs_contested',
-        'Experience_trust-evading_vs_trust-inducing',
-        'Experience_predictable_vs_emergent',
-        'Experience_exclusion_vs_inclusion',
-        'Experience_Kafka_vs_Whitehead',
-        'Experience_dead_vs_alive',
-    ]
-
     # Cluster names
     CLUSTER_NAMES = {
         1: "Relational/Cultural",
         2: "Institutional/Bureaucratic"
     }
 
-    # Key dimensions for short form (most discriminative)
-    # Based on LDA analysis - top differentiating dimensions
-    KEY_DIMENSIONS = [
-        'Design_elite_vs_vernacular',              # 4.602 difference
-        'Entanglement_flocking_vs_swarming',       # 4.079 difference
-        'Design_static_vs_malleable',              # 3.775 difference
-        'Entanglement_obligatory_vs_voluntary',    # 3.648 difference
-        'Entanglement_self-enforcing_vs_enforced', # 3.628 difference
-        'Design_explicit_vs_implicit',             # High importance
-        'Entanglement_sovereign_vs_subsidiary',    # High importance
-        'Design_technical_vs_social',              # High importance
-    ]
-
     def __init__(self, model_path='analysis_results/data'):
         """Initialize classifier with pre-computed model data."""
         self.model_path = Path(model_path)
@@ -89,6 +77,9 @@ class BicorderClassifier:
         self.lda = None
         self.cluster_centroids = None
 
+        # Derive dimension lists from bicorder.json
+        self.DIMENSIONS, self.KEY_DIMENSIONS = _load_bicorder_dimensions()
+
         # Load training data to fit scaler and LDA
         self._load_model()
 
@@ -98,6 +89,9 @@ class BicorderClassifier:
         df = pd.read_csv('diagnostic_output.csv')
         clusters = pd.read_csv(self.model_path / 'kmeans_clusters.csv')
 
+        # Rename old column names to match current bicorder.json
+        df = df.rename(columns=_COLUMN_RENAMES)
+
         # Remove duplicates
         df = df.drop_duplicates(subset='Descriptor', keep='first')