Update app.py

app.py

@@ -37,7 +37,7 @@ Este análisis es una herramienta informativa de IA y **NO es un diagnóstico m
 **Si tus síntomas son severos, busca ayuda médica urgente.**
 """
 
-# --- CONFIGURACIÓN GEMINI CON LA VARIABLE GEMINI_API_KEY ---
+# --- CONFIGURACIÓN DE CLIENTE GEMINI CON GEMINI_API_KEY ---
 def get_gemini_client():
     api_key = os.getenv("GEMINI_API_KEY")
     
@@ -60,13 +60,31 @@ def get_gemini_client():
     try:
         return genai.Client(
             api_key=api_key,
-            http_options=types.HttpOptions(timeout=10000) # 10 segundos
+            http_options=types.HttpOptions(timeout=15.0) # 15 segundos
         )
     except Exception as e:
         logger.warning(f"❌ Error instanciando cliente Gemini: {e}")
         return None
 
-# --- CARGA ULTRA-RÁPIDA DE DATOS Y FOODB ---
+# --- CASCADA DE MODELOS DE GEMINI CON FALLBACK ---
+def generate_content_with_fallback(gemini_client, prompt):
+    """Prueba los modelos disponibles en la cuenta de Google AI Studio en cascada."""
+    models_to_try = ['gemini-2.5-flash-lite', 'gemini-2.5-flash', 'gemini-1.5-flash']
+    for model_name in models_to_try:
+        try:
+            response = gemini_client.models.generate_content(
+                model=model_name,
+                contents=prompt
+            )
+            if response and response.text:
+                logger.info(f"✅ Respuesta exitosa generada por el modelo: {model_name}")
+                return response.text
+        except Exception as e:
+            logger.warning(f"⚠️ Modelo {model_name} no disponible ({e}), probando siguiente modelo...")
+            continue
+    raise RuntimeError("Todos los modelos de Gemini fallaron o no están disponibles.")
+
+# --- CARGA ULTRA-RÁPIDA DE DATOS Y FOODB (CERO COPIA EN MEMORIA) ---
 @st.cache_resource
 def load_data():
     try:
@@ -95,6 +113,7 @@ def get_foodb_lower_map(_foodb_index):
 
 foodb_lower_map = get_foodb_lower_map(foodb_index)
 
+# --- CACHÉ GLOBAL DE APRENDIZAJE EN RAM ---
 @st.cache_resource
 def get_global_learned_cache():
     return {}
@@ -220,6 +239,7 @@ FOOD_TO_COMPOUND_MAP = {
     "carne de res": ["histamina", "alfa-gal", "purinas"],
     "res": ["histamina", "alfa-gal", "purinas"],
     "café": ["cafeína", "salicilatos", "oxalatos"],
+    "cafe": ["cafeína", "salicilatos", "oxalatos"],
     "té": ["cafeína", "taninos", "oxalatos", "salicilatos"],
     "té negro": ["cafeína", "taninos", "oxalatos", "salicilatos"],
     "té verde": ["cafeína", "taninos", "oxalatos", "salicilatos"],
@@ -261,7 +281,7 @@ FOOD_NAME_TO_FOODB_KEY = {
     "vino": ["wine"], "vino tinto": ["wine", "red wine"], "cerveza": ["beer"], "chocolate": ["chocolate", "cocoa"],
     "tomate": ["tomato"], "aguacate": ["avocado"], "plátano": ["banana", "plantain"], "banano": ["banana"],
     "naranja": ["orange"], "jugo de naranja": ["orange juice", "orange"], "pan": ["bread", "wheat"],
-    "trigo": ["wheat"], "café": ["coffee"], "té": ["tea"], "manzana": ["apple"], "pera": ["pear"],
+    "trigo": ["wheat"], "café": ["coffee"], "cafe": ["coffee"], "té": ["tea"], "manzana": ["apple"], "pera": ["pear"],
     "fresa": ["strawberry"], "uva": ["grape"], "piña": ["pineapple"], "papaya": ["papaya"],
     "mango": ["mango"], "limón": ["lemon", "lime"], "espinaca": ["spinach"], "cebolla": ["onion"],
     "ajo": ["garlic"], "papa": ["potato"], "patata": ["potato"], "frijol": ["bean", "beans"],
@@ -269,7 +289,7 @@ FOOD_NAME_TO_FOODB_KEY = {
 }
 
 STRICT_COMPOUND_TRIGGERS = {
-    "cafeína": ["cafeína", "caffeine", "café", "coffee", "espresso", "energizante", "guaraná"],
+    "cafeína": ["cafeína", "caffeine", "café", "cafe", "coffee", "espresso", "energizante", "guaraná"],
     "teobromina": ["teobromina", "theobromine", "cacao", "chocolate"],
     "solanina": ["solanina", "solanine", "solanáceas", "nightshades", "tomate", "berenjena", "patata", "papa"],
     "capsaicina": ["capsaicina", "capsaicin", "chile", "ají", "picante", "pimiento"],
@@ -445,7 +465,6 @@ COMPOUND_SYNONYM_MAP = {
     "proteínas": ["protein", "amino acid"]
 }
 
-# MAPA COMPLETO DE SÍNTOMAS (NUNCA DEJA VACÍA LA EXTRACCIÓN LOCAL)
 MASTER_SYMPTOM_MAP = {
     "dolor abdominal": {
         "frases_es": ["dolor de estómago", "dolor de panza", "dolor abdominal", "retortijones", "cólicos", "calambres abdominales", "gastritis", "acidez", "reflujo", "pesadez"],
@@ -504,7 +523,6 @@ MASTER_SYMPTOM_MAP = {
 def sanitize_text(text):
     if not text:
         return ""
-    # Normaliza puntuación y colapsa múltiples espacios a un solo espacio simple
     text_clean = re.sub(r'[.,;()¿?¡!:"\'\-]', ' ', text).lower()
     text_clean = re.sub(r'\s+', ' ', text_clean).strip()
     return text_clean
@@ -543,7 +561,7 @@ def get_compounds_for_food(food_name, food_map):
             if norm in food_map:
                 return food_map[norm]
 
-    # 3. Corrección difusa de erratas de tipeo (difflib)
+    # 3. Corrección difusa de erratas de tipeo
     fuzzy_matches = difflib.get_close_matches(food_clean, list(food_map.keys()), n=1, cutoff=0.6)
     if fuzzy_matches:
         logger.info(f"💡 Errata corregida automáticamente: '{food_clean}' -> '{fuzzy_matches[0]}'")
@@ -558,7 +576,7 @@ def get_compounds_for_food(food_name, food_map):
     if matched_compounds:
         return list(matched_compounds)
 
-    # 5. Inferencia difusa por palabras individuales en nombres compuestos
+    # 5. Inferencia difusa por palabras individuales
     inferred = set()
     words = food_clean.split()
     for word in words:
@@ -570,7 +588,7 @@ def get_compounds_for_food(food_name, food_map):
     if inferred:
         return list(inferred)
 
-    # 6. INFERENCIA UNIVERSAL POR FAMILIA BIOLÓGICA (Para alimentos no registrados)
+    # 6. INFERENCIA UNIVERSAL POR FAMILIA BIOLÓGICA
     if any(w in food_clean for w in ["carne", "cerdo", "res", "pollo", "pavo", "cordero", "pato", "chicharrón", "tocino"]):
         inferred.update(["histamina", "purinas", "proteínas"])
     elif any(w in food_clean for w in ["pescado", "atún", "marisco", "camarón", "sardina", "langostino", "pulpo"]):
@@ -681,9 +699,9 @@ def reinforce_entities_with_keywords(entities, query, food_map, master_symptom_m
                 current_symptoms.add(main_symptom)
                 break
                 
-    # EXTRAER SÍNTOMAS ADICIONALES POR PALABRAS CLAVE DIRECTAS
+    # EXTRAER SÍNTOMAS ADICIONALES POR PALABRAS CLAVE DIRECTAS EN CASO DE FALLO
     if not current_symptoms:
-        if any(w in query_sanitized for w in ["diarrea", "diarreas", "soltura", "líquida"]):
+        if any(w in query_sanitized for w in ["diarrea", "diarreas", "soltura", "líquida", "suelto"]):
             current_symptoms.add("diarrea")
         elif any(w in query_sanitized for w in ["hinchazón", "hinchazon", "gases", "inflamado"]):
             current_symptoms.add("hinchazón")
@@ -767,7 +785,7 @@ def build_local_hypothesis(entities, food_compound_map, neuro_map):
     es_psicologico = any(k in symptom_text for k in ["ansiedad", "angustia", "nerviosismo", "depresión", "depresion", "irritabilidad", "desrealización", "desrealizacion", "agitación", "agitacion"])
     es_insomnio = any(k in symptom_text for k in ["insomnio", "no puedo dormir", "sueño", "desvelado", "desvelo", "despierto", "dormir"])
     es_gastrointestinal = any(k in symptom_text for k in ["diarrea", "diarreas", "hinchazón", "hinchazon", "gases", "dolor abdominal", "retortijón", "retortijon", "cólico", "colico", "inflamado", "inflama", "pesadez", "estómago", "estomago", "náuseas", "nausea", "acidez", "reflujo"])
-    es_dermatologico = any(k in symptom_text for k in ["piel", "rasca", "picazón", "picazon", "manchas", "urticaria", "erupción", "erupcion", "alergia", "ronchas", "granitos", "eccema"])
+    es_dermatologico = any(k in symptom_text for k in ["piel", "rasca", "picazón", "picazon", "manchas", "urticaria", "erupción", "erupcion", "alergia", "ronchas", "granitos"])
     es_respiratorio = any(k in symptom_text for k in ["asma", "tos", "respirar", "pecho", "sibilancia", "ahogo", "falta de aire", "congestión nasal", "congestion nasal", "estornudo", "rinitis"])
     es_cardiovascular = any(k in symptom_text for k in ["palpitaciones", "taquicardia", "ritmo cardíaco", "presión", "presion", "rubor", "sofoco", "frío"])
     es_articular = any(k in symptom_text for k in ["articulación", "articulacion", "rodilla", "coyuntura", "rigidez", "calambre", "gota", "espalda", "músculo", "musculo"])