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/kindness.py

@@ -2,7 +2,7 @@
 
 import random
 import globals
-from utils.llm import query_ollama  # Adjust path as needed
+from utils.llm import query_llama  # Adjust path as needed
 
 
 async def detect_and_react_to_kindness(message, after_reply=False, server_context=None):
@@ -37,7 +37,7 @@ async def detect_and_react_to_kindness(message, after_reply=False, server_contex
             "Answer with 'yes' or 'no' only.\n\n"
             f"Message: \"{message.content}\""
         )
-        result = await query_ollama(prompt, user_id="kindness-check", guild_id=None, response_type="dm_response")
+        result = await query_llama(prompt, user_id="kindness-check", guild_id=None, response_type="dm_response")
 
         if result.strip().lower().startswith("yes"):
             await message.add_reaction(emoji)