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/api.py

@@ -833,11 +833,11 @@ async def send_custom_prompt_dm(user_id: str, req: CustomPromptRequest):
             return {"status": "error", "message": f"User {user_id} not found"}
         
         # Use the LLM query function for DM context
-        from utils.llm import query_ollama
+        from utils.llm import query_llama
         
         async def send_dm_custom_prompt():
             try:
-                response = await query_ollama(req.prompt, user_id=user_id, guild_id=None, response_type="dm_response")
+                response = await query_llama(req.prompt, user_id=user_id, guild_id=None, response_type="dm_response")
                 await user.send(response)
                 print(f"✅ Custom DM prompt sent to user {user_id}: {req.prompt[:50]}...")