Eliminar pasos intermedios del historial de ejecución y limpiar mensajes de depuración en la función de chat.

app.py

@@ -10,7 +10,7 @@ from dotenv import load_dotenv
 import os
 import json
 from datetime import datetime
-from typing import Dict, List, Any
+from typing import List, Any
 
 load_dotenv()
 
@@ -64,8 +64,6 @@ def format_execution_history():
             formatted_history.append(f"**[{timestamp}] 🔧 Llamada a Herramienta**\n\n**Herramienta**: {tool_data['name']}\n\n**Argumentos**: \n\n```json\n{json.dumps(tool_data.get('args', {}), indent=2)}\n```\n\n")
         elif step_type == "tool_result":
             formatted_history.append(f"**[{timestamp}] ✅ Resultado de Herramienta**\n\n```\n{entry['data']}\n```\n\n")
-        elif step_type == "intermediate_step":
-            formatted_history.append(f"**[{timestamp}] 🧠 Paso Intermedio**\n\n{entry['data']}\n\n")
         elif step_type == "error":
             formatted_history.append(f"**[{timestamp}] ❌ Error**\n\n{entry['data']}\n\n")
         
@@ -124,15 +122,11 @@ async def chat(history: list, tab_id: str=None, anthropic_api_key: str=None):
     if tab_id:
         history[-1]["content"] += f"\nThis is your tab_id: {tab_id}"
 
-    print(f"Received message: {history[-1]['content']}")
-    print(f"Complete chat history: {history}")
-
     llm_provider = os.getenv("LLM_PROVIDER", "ollama").lower()
     ollama_model = os.getenv("OLLAMA_MODEL", "qwen3:8b")
 
     try:
         agent = await create_agent_with_llm(llm_provider, anthropic_api_key, ollama_model, tools)
-        add_to_execution_history("intermediate_step", f"Agente creado con provider: {llm_provider}", tab_id)
     except ValueError as e:
         error_msg = str(e)
         add_to_execution_history("error", error_msg, tab_id)
@@ -161,8 +155,6 @@ async def chat(history: list, tab_id: str=None, anthropic_api_key: str=None):
         cleaned = re.sub(r'<think>.*?</think>', '', output, flags=re.DOTALL).strip()
         
         add_to_execution_history("agent_response", cleaned, tab_id)
-        
-        print(f"Processed output: {cleaned}")
         return cleaned
         
     except Exception as e:
@@ -193,15 +185,11 @@ async def chat_with_history_tracking(message: str, history: List, tab_id: str =
     if tab_id:
         messages[-1]["content"] += f"\nThis is your tab_id: {tab_id}"
 
-    print(f"Received message: {message}")
-    print(f"Complete chat history: {messages}")
-
     llm_provider = os.getenv("LLM_PROVIDER", "ollama").lower()
     ollama_model = os.getenv("OLLAMA_MODEL", "qwen3:8b")
 
     try:
         agent = await create_agent_with_llm(llm_provider, anthropic_api_key, ollama_model, tools)
-        add_to_execution_history("intermediate_step", f"Agente creado con provider: {llm_provider}", tab_id)
     except ValueError as e:
         error_msg = str(e)
         add_to_execution_history("error", error_msg, tab_id)
@@ -233,8 +221,6 @@ async def chat_with_history_tracking(message: str, history: List, tab_id: str =
         cleaned = re.sub(r'<think>.*?</think>', '', output, flags=re.DOTALL).strip()
         
         add_to_execution_history("agent_response", cleaned, tab_id)
-        
-        print(f"Processed output: {cleaned}")
         history.append([message, cleaned])
         
         return history, format_execution_history()