feat: Implement LLM and scheduler functionalities

This commit finalizes Phase 4 of the project by implementing the
LLM and scheduler integrations.

- Implements `get_smart_response` in `app/llm.py` to generate
  AI-powered responses using the OpenAI API.
- Implements a daily summary scheduler in `app/scheduler.py` using
  the `JobQueue` from `python-telegram-bot` for better integration
  with the application's event loop.
- Adds `get_events_for_day` to `app/calendar.py` to fetch daily
  events for the summary.
- Integrates the scheduler into the main application loop in
  `app/main.py`.
- Improves the date formatting in the daily summary for better
  readability.
- Updates `tasks.md` to reflect the completion of Phase 4.

app/llm.py

@@ -1,15 +1,26 @@
 # app/llm.py
 
-from config import OPENAI_API_KEY
+import openai
+from app.config import OPENAI_API_KEY
 
 def get_smart_response(prompt):
     """
     Generates a smart response using an LLM.
     """
-
     if not OPENAI_API_KEY:
         return "OpenAI API key not configured."
 
-    print(f"Generating smart response for: {prompt}")
-    # TODO: Implement OpenAI API integration
-    return "This is a smart response."
+    openai.api_key = OPENAI_API_KEY
+
+    try:
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": prompt},
+            ],
+        )
+        return response.choices[0].message.content.strip()
+    except Exception as e:
+        print(f"An error occurred with OpenAI: {e}")
+        return "I'm sorry, I couldn't generate a response right now."