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/bot.py

@@ -34,7 +34,7 @@ from utils.moods import (
 from utils.media import(
     overlay_username_with_ffmpeg
 )
-from utils.llm import query_ollama
+from utils.llm import query_llama
 from utils.autonomous import (
     setup_autonomous_speaking, 
     load_last_sent_tweets,
@@ -100,7 +100,7 @@ async def on_ready():
 
     # Start server-specific schedulers (includes DM mood rotation)
     server_manager.start_all_schedulers(globals.client)
-
+https://tea.koko210cloud.xyz/Koko210/miku-discord
     # Start the global scheduler for other tasks
     globals.scheduler.start()
 
@@ -367,7 +367,8 @@ async def on_message(message):
                                         print(f"✅ Image downloaded, analyzing with vision model...")
                                         # Analyze image
                                         qwen_description = await analyze_image_with_qwen(base64_img)
-                                        truncated = (qwen_description[:50] + "...") if len(qwen_description) > 50 else qwen_description
+                                        truncated = (qwen_description[:50] + "...") 
+                        if not base64_img:if len(qwen_description) > 50 else qwen_description
                                         print(f"📝 Vision analysis result: {truncated}")
                                         if qwen_description and qwen_description.strip():
                                             embed_context_parts.append(f"[Embedded image shows: {qwen_description}]")
@@ -413,7 +414,7 @@ async def on_message(message):
                             response_type = "dm_response" if is_dm else "server_response"
                             author_name = message.author.display_name
                             
-                            response = await query_ollama(
+                            response = await query_llama(
                                 enhanced_prompt,
                                 user_id=str(message.author.id),
                                 guild_id=guild_id,
@@ -454,7 +455,7 @@ async def on_message(message):
             guild_id = message.guild.id if message.guild else None
             response_type = "dm_response" if is_dm else "server_response"
             author_name = message.author.display_name
-            response = await query_ollama(
+            response = await query_llama(
                 prompt, 
                 user_id=str(message.author.id), 
                 guild_id=guild_id,