Phase 3: Unified Cheshire Cat integration with WebSocket-based per-user isolation

Key changes:
- CatAdapter (bot/utils/cat_client.py): WebSocket /ws/{user_id} for chat
  queries instead of HTTP POST (fixes per-user memory isolation when no
  API keys are configured — HTTP defaults all users to user_id='user')
- Memory management API: 8 endpoints for status, stats, facts, episodic
  memories, consolidation trigger, multi-step delete with confirmation
- Web UI: Memory tab (tab9) with collection stats, fact/episodic browser,
  manual consolidation trigger, and 3-step delete flow requiring exact
  confirmation string
- Bot integration: Cat-first response path with query_llama fallback for
  both text and embed responses, server mood detection
- Discord bridge plugin: fixed .pop() to .get() (UserMessage is a Pydantic
  BaseModelDict, not a raw dict), metadata extraction via extra attributes
- Unified docker-compose: Cat + Qdrant services merged into main compose,
  bot depends_on Cat healthcheck
- All plugins (discord_bridge, memory_consolidation, miku_personality)
  consolidated into cat-plugins/ for volume mount
- query_llama deprecated but functional for compatibility

docker-compose.yml

@@ -1,6 +1,5 @@
-version: '3.9'
-
 services:
+  # ========== LLM Backends ==========
   llama-swap:
     image: ghcr.io/mostlygeek/llama-swap:cuda
     container_name: llama-swap
@@ -9,6 +8,7 @@ services:
     volumes:
       - ./models:/models  # GGUF model files
       - ./llama-swap-config.yaml:/app/config.yaml  # llama-swap configuration
+      - ./llama31_notool_template.jinja:/app/llama31_notool_template.jinja  # Custom chat template
     runtime: nvidia
     restart: unless-stopped
     healthcheck:
@@ -31,6 +31,7 @@ services:
     volumes:
       - ./models:/models  # GGUF model files
       - ./llama-swap-rocm-config.yaml:/app/config.yaml  # llama-swap configuration for AMD
+      - ./llama31_notool_template.jinja:/app/llama31_notool_template.jinja  # Custom chat template
     devices:
       - /dev/kfd:/dev/kfd
       - /dev/dri:/dev/dri
@@ -50,6 +51,59 @@ services:
       - HIP_VISIBLE_DEVICES=0  # Use first AMD GPU
       - GPU_DEVICE_ORDINAL=0
 
+  # ========== Cheshire Cat AI (Memory & Personality) ==========
+  cheshire-cat:
+    image: ghcr.io/cheshire-cat-ai/core:1.6.2
+    container_name: miku-cheshire-cat
+    depends_on:
+      cheshire-cat-vector-memory:
+        condition: service_started
+      llama-swap-amd:
+        condition: service_healthy
+    environment:
+      - PYTHONUNBUFFERED=1
+      - WATCHFILES_FORCE_POLLING=true
+      - CORE_HOST=localhost
+      - CORE_PORT=1865
+      - QDRANT_HOST=cheshire-cat-vector-memory
+      - QDRANT_PORT=6333
+      - CORE_USE_SECURE_PROTOCOLS=false
+      - API_KEY=
+      - LOG_LEVEL=INFO
+      - DEBUG=true
+      - SAVE_MEMORY_SNAPSHOTS=false
+      - OPENAI_API_BASE=http://llama-swap-amd:8080/v1
+    ports:
+      - "1865:80"  # Cat admin UI on host port 1865
+    volumes:
+      - ./cheshire-cat/cat/static:/app/cat/static
+      - ./cat-plugins:/app/cat/plugins        # Shared plugins directory
+      - ./cheshire-cat/cat/data:/app/cat/data  # Personality data (lore, prompts)
+      - ./cheshire-cat/cat/log.py:/app/cat/log.py  # Patched: fix loguru KeyError for third-party libs
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:80/"]
+      interval: 15s
+      timeout: 10s
+      retries: 8
+      start_period: 45s  # Cat takes a while to load embedder + plugins
+
+  cheshire-cat-vector-memory:
+    image: qdrant/qdrant:v1.9.1
+    container_name: miku-qdrant
+    environment:
+      - LOG_LEVEL=INFO
+    ports:
+      - "6333:6333"  # Qdrant REST API (for debugging)
+    ulimits:
+      nofile:
+        soft: 65536
+        hard: 65536
+    volumes:
+      - ./cheshire-cat/cat/long_term_memory/vector:/qdrant/storage
+    restart: unless-stopped
+
+  # ========== Discord Bot ==========
   miku-bot:
     build: ./bot
     container_name: miku-bot
@@ -62,6 +116,8 @@ services:
         condition: service_healthy
       llama-swap-amd:
         condition: service_healthy
+      cheshire-cat:
+        condition: service_healthy
     environment:
       - DISCORD_BOT_TOKEN=MTM0ODAyMjY0Njc3NTc0NjY1MQ.GXsxML.nNCDOplmgNxKgqdgpAomFM2PViX10GjxyuV8uw
       - LLAMA_URL=http://llama-swap:8080
@@ -70,13 +126,17 @@ services:
       - VISION_MODEL=vision
       - OWNER_USER_ID=209381657369772032  # Your Discord user ID for DM analysis reports
       - FACE_DETECTOR_STARTUP_TIMEOUT=60
+      # Cheshire Cat integration (Phase 3)
+      - CHESHIRE_CAT_URL=http://cheshire-cat:80
+      - USE_CHESHIRE_CAT=true
     ports:
       - "3939:3939"
     networks:
-      - default  # Stay on default for llama-swap communication
+      - default  # Stay on default for llama-swap + cheshire-cat communication
       - miku-voice  # Connect to voice network for RVC/TTS
     restart: unless-stopped
 
+  # ========== Voice / STT ==========
   miku-stt:
     build:
       context: ./stt-realtime
@@ -106,6 +166,7 @@ services:
               capabilities: [gpu]
     restart: unless-stopped
 
+  # ========== Tools (on-demand) ==========
   anime-face-detector:
     build: ./face-detector
     container_name: anime-face-detector