Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py (Corrected Version)
+# app.py (Hardened and Debuggable Version)
 import gradio as gr
 import tensorflow as tf
 import pickle
@@ -6,6 +6,7 @@ import numpy as np
 
 # --- 1. CONFIGURATION & MODEL LOADING ---
 MAX_SEQ_LENGTH = 30
+print("--- App Starting Up ---")
 print("Loading models and tokenizers...")
 try:
     successor_model = tf.keras.models.load_model('successor_model.h5')
@@ -21,39 +22,41 @@ except Exception as e:
     print(f"FATAL ERROR loading files: {e}")
     successor_model, predecessor_model = None, None
 
-# --- 2. THE CORE PREDICTION LOGIC ---
-def predict_next_state(direction, current_unit, current_analogy, current_commentary):
-    if not all([successor_model, predecessor_model]):
-        return "Error: Models are not loaded.", "Please check the server logs on Hugging Face.", "---"
+# --- 2. THE CORE PREDICTION LOGIC (MODIFIED) ---
+# This function now receives the actual model and tokenizer objects
+def predict_next_state(model, tokenizers, current_unit, current_analogy, current_commentary):
+    if not model or not tokenizers:
+        return "Error: A required model or tokenizer is not loaded.", "Check server logs.", "---"
 
-    model = successor_model if direction == "larger" else predecessor_model
-    tokenizers = successor_tokenizers if direction == "larger" else predecessor_tokenizers
-    
-    input_data = {
-        'current_unit_name': [current_unit],
-        'current_analogy': [current_analogy],
-        'current_commentary': [current_commentary]
-    }
-    
+    # Prepare input data
+    input_data = {'current_unit_name': [current_unit], 'current_analogy': [current_analogy], 'current_commentary': [current_commentary]}
     processed_input = {}
     for col, text_list in input_data.items():
         sequences = tokenizers[col].texts_to_sequences(text_list)
         padded_sequences = tf.keras.preprocessing.sequence.pad_sequences(sequences, maxlen=MAX_SEQ_LENGTH, padding='post')
         processed_input[col] = padded_sequences
         
+    # Get AI prediction
     predictions = model.predict(processed_input)
     
+    # Decode prediction back to text
     target_texts = {}
     output_cols = ['target_unit_name', 'target_analogy', 'target_commentary']
-    
     for i, col in enumerate(output_cols):
         pred_indices = np.argmax(predictions[i], axis=-1)
         predicted_sequence = tokenizers[col].sequences_to_texts(pred_indices)[0]
-        # More robust cleaning
         clean_text = ' '.join([word for word in predicted_sequence.split() if word not in ['<oov>', 'end']])
         target_texts[col] = clean_text.strip()
     
+    # *** DEBUGGING PRINT ***
+    print(f"--- PREDICTION DECODED ---")
+    print(f"Decoded Unit Name: {target_texts['target_unit_name']}")
+    print(f"Decoded Analogy: {target_texts['target_analogy']}")
+    print("--------------------------")
+    
+    # Handle "Infinity" Sentinel
     if "end of knowledge" in target_texts['target_unit_name'].lower():
+        direction = "larger" if model == successor_model else "smaller"
         prefix = "Giga-" if direction == "larger" else "pico-"
         new_unit = f"{prefix}{current_unit}"
         new_analogy = "A procedurally generated unit beyond the AI's known universe."
@@ -62,42 +65,35 @@ def predict_next_state(direction, current_unit, current_analogy, current_comment
     else:
         return target_texts['target_unit_name'], target_texts['target_analogy'], target_texts['target_commentary']
 
-# Wrapper functions for the buttons
+# --- WRAPPER FUNCTIONS (MODIFIED) ---
+# These wrappers now pass the correct objects explicitly
 def go_larger(unit, analogy, commentary):
-    return predict_next_state("larger", unit, analogy, commentary)
+    print("\n>>> 'Go Larger' button clicked. Using SUCCESSOR model.")
+    return predict_next_state(successor_model, successor_tokenizers, unit, analogy, commentary)
 
 def go_smaller(unit, analogy, commentary):
-    return predict_next_state("smaller", unit, analogy, commentary)
+    print("\n>>> 'Go Smaller' button clicked. Using PREDECESSOR model.")
+    return predict_next_state(predecessor_model, predecessor_tokenizers, unit, analogy, commentary)
 
-# --- 3. THE GRADIO USER INTERFACE ---
+# --- 3. THE GRADIO USER INTERFACE (No changes needed here) ---
 initial_unit = "Byte"
 initial_analogy = "a single character of text, like 'R'"
 initial_commentary = "From binary choices, a building block is formed, ready to hold a single, recognizable symbol."
 
 with gr.Blocks(theme=gr.themes.Soft(primary_hue="sky")) as demo:
     gr.Markdown("# 🤖 Digital Scale Explorer AI")
+    # ... (the rest of the UI code is identical) ...
     gr.Markdown("An AI trained from scratch to explore the infinite ladder of data sizes. Click the buttons to traverse the universe of data!")
-    
     with gr.Row():
         unit_name_out = gr.Textbox(value=initial_unit, label="Unit Name", interactive=False)
         analogy_out = gr.Textbox(value=initial_analogy, label="Analogy", lines=4, interactive=False)
         commentary_out = gr.Textbox(value=initial_commentary, label="AI Commentary", lines=3, interactive=False)
-
     with gr.Row():
         smaller_btn = gr.Button("Go Smaller ⬇️", variant="secondary", size="lg")
         larger_btn = gr.Button("Go Larger ⬆️", variant="primary", size="lg")
     
-    larger_btn.click(
-        fn=go_larger,
-        inputs=[unit_name_out, analogy_out, commentary_out],
-        outputs=[unit_name_out, analogy_out, commentary_out]
-    )
-    
-    smaller_btn.click(
-        fn=go_smaller, # Corrected from go_larger to go_smaller
-        inputs=[unit_name_out, analogy_out, commentary_out],
-        outputs=[unit_name_out, analogy_out, commentary_out]
-    )
+    larger_btn.click(fn=go_larger, inputs=[unit_name_out, analogy_out, commentary_out], outputs=[unit_name_out, analogy_out, commentary_out])
+    smaller_btn.click(fn=go_smaller, inputs=[unit_name_out, analogy_out, commentary_out], outputs=[unit_name_out, analogy_out, commentary_out])
 
 if __name__ == "__main__":
     demo.launch()