feat: Implement LLM and scheduler modules

- Implement `llm.py` with OpenAI API integration for smart responses.
- Implement `scheduler.py` to send a daily summary to the bot owner using `python-telegram-bot`'s `JobQueue`.
- Integrate the scheduler into the main application.
- Add `pytz` as a new dependency.
- Update `tasks.md` to mark all tasks as complete.

app/main.py

@@ -29,6 +29,7 @@ from modules.aprobaciones import view_pending, handle_approval_action
 from modules.servicios import get_service_info
 from modules.admin import get_system_status
 from modules.print import print_handler
+from app.scheduler import schedule_daily_summary
 
 # Enable logging
 logging.basicConfig(
@@ -89,6 +90,9 @@ def main() -> None:
 
     application = Application.builder().token(TELEGRAM_BOT_TOKEN).build()
 
+    # Schedule daily summary
+    schedule_daily_summary(application)
+
     # Conversation handler for proposing activities
     conv_handler = ConversationHandler(
         entry_points=[CallbackQueryHandler(propose_activity_start, pattern='^propose_activity$')],