Remove all Ollama remnants and complete migration to llama.cpp

- Remove Ollama-specific files (Dockerfile.ollama, entrypoint.sh)
- Replace all query_ollama imports and calls with query_llama
- Remove langchain-ollama dependency from requirements.txt
- Update all utility files (autonomous, kindness, image_generation, etc.)
- Update README.md documentation references
- Maintain backward compatibility alias in llm.py

bot/utils/scheduled.py

@@ -11,7 +11,7 @@ from discord import Status, ActivityType
 
 import globals
 from server_manager import server_manager
-from utils.llm import query_ollama
+from utils.llm import query_llama
 from utils.dm_interaction_analyzer import dm_analyzer
 
 BEDTIME_TRACKING_FILE = "last_bedtime_targets.json"
@@ -27,7 +27,7 @@ async def send_monday_video_for_server(guild_id: int):
 
     # Generate a motivational message
     prompt = "It's Miku Monday! Give me an energetic and heartfelt Miku Monday morning message to inspire someone for the week ahead."
-    response = await query_ollama(prompt, user_id=f"weekly-motivation-{guild_id}", guild_id=guild_id)
+    response = await query_llama(prompt, user_id=f"weekly-motivation-{guild_id}", guild_id=guild_id)
 
     video_url = "http://zip.koko210cloud.xyz/u/zEgU7Z.mp4"
 
@@ -158,7 +158,7 @@ async def send_bedtime_reminder_for_server(guild_id: int, client=None):
             f"Miku is currently feeling: {server_config.current_mood_description or 'neutral'}\nPlease word in a way that reflects this emotional tone."
         )
         
-        bedtime_message = await query_ollama(prompt, user_id=f"bedtime-{guild_id}", guild_id=guild_id)
+        bedtime_message = await query_llama(prompt, user_id=f"bedtime-{guild_id}", guild_id=guild_id)
 
         try:
             await channel.send(f"{chosen_one.mention} {bedtime_message}")