infra: migrate application from Mac mini to GPU server

- Integrate ollama + ai-gateway into root docker-compose.yml
  (NVIDIA GPU runtime, single compose for all services)
- Change NAS mount from SMB (NAS_SMB_PATH) to NFS (NAS_NFS_PATH)
  Default: /mnt/nas/Document_Server (fstab registered on GPU server)
- Update config.yaml AI endpoints:
  primary → Mac mini MLX via Tailscale (100.76.254.116:8800)
  fallback/embedding/vision/rerank → ollama (same Docker network)
  gateway → ai-gateway (same Docker network)
- Update credentials.env.example (remove GPU_SERVER_IP, add NFS path)
- Mark gpu-server/docker-compose.yml as deprecated
- Update CLAUDE.md network diagram and AI model config
- Update architecture.md, deploy.md, devlog.md for GPU server as main
- Caddyfile: auto_https off, HTTP only (TLS at upstream proxy)
- Caddy port: 127.0.0.1:8080:80 (localhost only)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.yml

@@ -22,7 +22,7 @@ services:
     ports:
       - "3100:3100"
     volumes:
-      - ${NAS_SMB_PATH:-/Volumes/Document_Server}:/documents:ro
+      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
     healthcheck:
       test: ["CMD", "node", "-e", "fetch('http://localhost:3100/health').then(r=>{process.exit(r.ok?0:1)}).catch(()=>process.exit(1))"]
       interval: 10s
@@ -30,12 +30,40 @@ services:
       retries: 3
     restart: unless-stopped
 
+  ollama:
+    image: ollama/ollama
+    volumes:
+      - ollama_data:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    ports:
+      - "11434:11434"
+    restart: unless-stopped
+
+  ai-gateway:
+    build: ./gpu-server/services/ai-gateway
+    ports:
+      - "8081:8080"
+    environment:
+      - PRIMARY_ENDPOINT=http://100.76.254.116:8800/v1/chat/completions
+      - FALLBACK_ENDPOINT=http://ollama:11434/v1/chat/completions
+      - CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
+      - DAILY_BUDGET_USD=${DAILY_BUDGET_USD:-5.00}
+    depends_on:
+      - ollama
+    restart: unless-stopped
+
   fastapi:
     build: ./app
     ports:
       - "8000:8000"
     volumes:
-      - ${NAS_SMB_PATH:-/Volumes/Document_Server}:/documents
+      - ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents
       - ./config.yaml:/app/config.yaml:ro
       - ./scripts:/app/scripts:ro
       - ./logs:/app/logs
@@ -62,8 +90,7 @@ services:
   caddy:
     image: caddy:2
     ports:
-      - "8080:80"
-      - "9443:443"
+      - "127.0.0.1:8080:80"
     volumes:
       - ./Caddyfile:/etc/caddy/Caddyfile
       - caddy_data:/data
@@ -75,3 +102,4 @@ services:
 volumes:
   pgdata:
   caddy_data:
+  ollama_data: