Mumuni review action items: health checks for all containers, version pinning, 503+Retry-After on all-GPU saturation

docker-compose.yml

@@ -27,6 +27,11 @@ services:
       - GPU_MOE_URL=http://192.168.68.15:8080/v1
       - GPU_DENSE_URL=http://192.168.68.8:8080/v1
       - GPU_LIGHT_URL=http://192.168.68.110:8080/v1
+    healthcheck:
+      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/health')"]
+      interval: 15s
+      timeout: 5s
+      retries: 3
     depends_on:
       redis:
         condition: service_healthy
@@ -42,6 +47,11 @@ services:
       - ./litellm_config.yaml:/app/config.yaml
     environment:
       - LITELLM_MASTER_KEY=sk-syslog-local-master-key
+    healthcheck:
+      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9000/health')"]
+      interval: 15s
+      timeout: 5s
+      retries: 3
     depends_on:
       redis:
         condition: service_healthy
@@ -54,6 +64,11 @@ services:
       - "80:80"
     volumes:
       - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://127.0.0.1/health"]
+      interval: 15s
+      timeout: 5s
+      retries: 3
     depends_on:
       - litellm
       - dashboard
@@ -67,6 +82,11 @@ services:
     environment:
       - REDIS_URL=redis://redis:6379
       - GPU_SIDECARS=192.168.68.15:8090,192.168.68.8:8090,192.168.68.110:8090
+    healthcheck:
+      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3000/health')"]
+      interval: 15s
+      timeout: 5s
+      retries: 3
     depends_on:
       - redis