feat: Refactor LLM router and integrate health check endpoint

- Simplified LLM call logic in llm_router.py, removing tool adapter complexity and enhancing error handling.
- Added health check endpoint to main.py for system status verification.
- Cleaned up router.py by removing unused imports and commented-out code, streamlining the structure.
- Updated docker-compose.yml to unify services under a single Lyra container, enhancing deployment simplicity.
- Created Dockerfile for unified container setup, including both Relay and Cortex services.
- Added QUICKSTART.md for improved onboarding and usage instructions.
- Implemented start.sh script to manage service startup and health checks.

docker-compose.yml

@@ -3,101 +3,40 @@ networks:
     driver: bridge
 
 volumes:
-  postgres_data:
+  nebula_fallback:
     driver: local
-  neo4j_data:
-    driver: local
-  code_executions:
+  relay_sessions:
     driver: local
 
 services:
 
-  # # ============================================================
-  # # NeoMem: Postgres
-  # # ============================================================
-  # neomem-postgres:
-  #   image: ankane/pgvector:v0.5.1
-  #   container_name: neomem-postgres
-  #   restart: unless-stopped
-  #   environment:
-  #     POSTGRES_USER: neomem
-  #     POSTGRES_PASSWORD: neomempass
-  #     POSTGRES_DB: neomem
-  #   volumes:
-  #     - ./volumes/postgres_data:/var/lib/postgresql/data
-  #   ports:
-  #     - "5432:5432"
-  #   healthcheck:
-  #     test: ["CMD-SHELL", "pg_isready -U neomem -d neomem || exit 1"]
-  #     interval: 5s
-  #     timeout: 5s
-  #     retries: 10
-  #   networks:
-  #     - lyra_net
-
-  # # ============================================================
-  # # NeoMem: Neo4j Graph
-  # # ============================================================
-  # neomem-neo4j:
-  #   image: neo4j:5
-  #   container_name: neomem-neo4j
-  #   restart: unless-stopped
-  #   environment:
-  #     NEO4J_AUTH: "neo4j/neomemgraph"
-  #     NEO4JLABS_PLUGINS: '["graph-data-science"]'
-  #   volumes:
-  #     - ./volumes/neo4j_data:/data
-  #   ports:
-  #     - "7474:7474"
-  #     - "7687:7687"
-  #   healthcheck:
-  #     test: ["CMD-SHELL", "cypher-shell -u neo4j -p neomemgraph 'RETURN 1' || exit 1"]
-  #     interval: 10s
-  #     timeout: 10s
-  #     retries: 10
-  #   networks:
-  #     - lyra_net
-
   # ============================================================
-  # NeoMem API
+  # Lyra (Unified: Relay + Cortex + Intake)
   # ============================================================
-  # neomem-api:
-  #   build:
-  #     context: ./neomem
-  #   image: lyra-neomem:latest
-  #   container_name: neomem-api
-  #   restart: unless-stopped
-  #   env_file:
-  #     - ./neomem/.env
-  #     - ./.env
-  #   volumes:
-  #     - ./neomem_history:/app/history
-  #   ports:
-  #     - "7077:7077"
-  #   depends_on:
-  #     neomem-postgres:
-  #       condition: service_healthy
-  #     neomem-neo4j:
-  #       condition: service_healthy
-  #   networks:
-  #     - lyra_net
-
-  # ============================================================
-  # Relay  (host mode)
-  # ============================================================
-  relay:
+  lyra:
     build:
-      context: ./core/relay
-    container_name: relay
+      context: .
+      dockerfile: Dockerfile
+    container_name: lyra
     restart: unless-stopped
     env_file:
       - ./.env
     volumes:
-      - ./core/relay/sessions:/app/sessions
+      - relay_sessions:/app/relay/sessions
+      - nebula_fallback:/app/.nebula_fallback
+      - ./cortex:/app/cortex  # Mount for hot reload during development
+      - /var/run/docker.sock:/var/run/docker.sock:ro
     ports:
-      - "7078:7078"
+      - "7078:7078"  # Relay API (user-facing)
+      - "7081:7081"  # Cortex API (internal/debug)
     networks:
       - lyra_net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:7078/_health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
 
   # ============================================================
   # UI Server
@@ -112,84 +51,6 @@ services:
       - ./core/ui:/usr/share/nginx/html:ro
     networks:
       - lyra_net
-
-
-  # ============================================================
-  # Cortex
-  # ============================================================
-  cortex:
-    build:
-      context: ./cortex
-    container_name: cortex
-    restart: unless-stopped
-    env_file:
-      - ./cortex/.env
-      - ./.env
-    volumes:
-      - ./cortex:/app
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-    ports:
-      - "7081:7081"
-    networks:
-      - lyra_net
-
-  # ============================================================
-  # Code Sandbox (for tool execution)
-  # ============================================================
-  code-sandbox:
-    build:
-      context: ./sandbox
-    container_name: lyra-code-sandbox
-    restart: unless-stopped
-    security_opt:
-      - no-new-privileges:true
-    cap_drop:
-      - ALL
-    cap_add:
-      - CHOWN
-      - SETUID
-      - SETGID
-    network_mode: "none"
-    volumes:
-      - code_executions:/executions
-    mem_limit: 512m
-    cpus: 1.0
-    pids_limit: 100
-    user: sandbox
-    command: tail -f /dev/null
-
-  # ============================================================
-  # Intake
-  # ============================================================
-#  intake:
-#   build:
-#      context: ./intake
-#    container_name: intake
-#    restart: unless-stopped
-#    env_file:
-#      - ./intake/.env
-#      - ./.env
-#    ports:
-#      - "7080:7080"
-#    volumes:
-#      - ./intake:/app
-#      - ./intake-logs:/app/logs
-#    depends_on:
-#      - cortex
-#    networks:
-#      - lyra_net
-
-  # ============================================================
-  # RAG Service
-  # ============================================================
-  # rag:
-  #   build:
-  #     context: ./rag
-  #   container_name: rag
-  #   restart: unless-stopped
-  #   environment:
-  #     NEOMEM_URL: http://neomem-api:7077
-  #   ports:
-  #     - "7090:7090"
-  #   networks:
-  #     - lyra_net  
+    depends_on:
+      lyra:
+        condition: service_healthy