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/autonomous_wip.py

@@ -10,7 +10,7 @@ from discord import Status
 from discord import TextChannel
 from difflib import SequenceMatcher
 import globals
-from utils.llm import query_ollama
+from utils.llm import query_llama
 from utils.moods import MOOD_EMOJIS
 from utils.twitter_fetcher import fetch_miku_tweets
 from utils.image_handling import analyze_image_with_qwen, download_and_encode_image
@@ -95,7 +95,7 @@ async def miku_say_something_general(guild_id, settings):
     )
 
     for attempt in range(3):  # retry up to 3 times if message is too similar
-        message = await query_ollama(prompt, user_id=f"miku-general-{int(time.time())}", guild_id=guild_id, response_type="autonomous_general")
+        message = await query_llama(prompt, user_id=f"miku-general-{int(time.time())}", guild_id=guild_id, response_type="autonomous_general")
         if not is_too_similar(message, _last_autonomous_messages):
             break
         print("🔁 Response was too similar to past messages, retrying...")
@@ -183,7 +183,7 @@ async def miku_engage_random_user(guild_id, settings):
     )
 
     try:
-        message = await query_ollama(prompt, user_id=f"miku-engage-{int(time.time())}", guild_id=guild_id, response_type="autonomous_general")
+        message = await query_llama(prompt, user_id=f"miku-engage-{int(time.time())}", guild_id=guild_id, response_type="autonomous_general")
         await channel.send(f"{target.mention} {message}")
         print(f"👤 Miku engaged {display_name}")
         _last_user_engagements[target.id] = time.time()
@@ -236,7 +236,7 @@ async def miku_detect_and_join_conversation():
     )
 
     try:
-        reply = await query_ollama(prompt, user_id=f"miku-chat-{int(time.time())}", guild_id=guild_id, response_type="conversation_join")
+        reply = await query_llama(prompt, user_id=f"miku-chat-{int(time.time())}", guild_id=guild_id, response_type="conversation_join")
         await channel.send(reply)
         print(f"💬 Miku joined an ongoing conversation.")
     except Exception as e:
@@ -275,7 +275,7 @@ async def share_miku_tweet(guild_id, settings):
         img_desc = await analyze_image_with_qwen(base64_img)
         base_prompt += f"\n\nThe image looks like this: {img_desc}"
 
-    miku_comment = await query_ollama(base_prompt, user_id="autonomous", guild_id=guild_id, response_type="autonomous_tweet")
+    miku_comment = await query_llama(base_prompt, user_id="autonomous", guild_id=guild_id, response_type="autonomous_tweet")
 
     # Post to Discord
     # Convert to fxtwitter for better embeds
@@ -302,7 +302,7 @@ async def handle_custom_prompt(user_prompt: str):
     )
 
     try:
-        message = await query_ollama(prompt, user_id=f"manual-{int(time.time())}", guild_id=None, response_type="autonomous_general")
+        message = await query_llama(prompt, user_id=f"manual-{int(time.time())}", guild_id=None, response_type="autonomous_general")
         await channel.send(message)
         print("🎤 Miku responded to custom prompt.")
         _last_autonomous_messages.append(message)