feat(ops): production resilience — healthchecks, restart_policy, log-rotation, --wait deploy [skip ci]

compose.yaml

@@ -15,12 +15,24 @@ services:
       interval: 10s
       timeout: 5s
       retries: 5
+      start_period: 30s
     networks: [nexus]
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
 
   api:
     build:
       context: ./backend
     restart: unless-stopped
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 5s
+        max_attempts: 3
+        window: 120s
     environment:
       ASPNETCORE_ENVIRONMENT: Production
       ASPNETCORE_URLS: http://+:8080
@@ -40,6 +52,12 @@ services:
     depends_on:
       postgres:
         condition: service_healthy
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 15s
     volumes:
       - /opt/openclaw/data/openclaw/openclaw.json:/home/node/.openclaw/openclaw.json:ro
       - /opt/openclaw/data/openclaw/workspace-iris:/mnt/workspace-iris
@@ -51,15 +69,37 @@ services:
     networks:
       - nexus
       - openclaw_default
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
 
   web:
     build:
       context: ./frontend
     restart: unless-stopped
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 5s
+        max_attempts: 3
+        window: 120s
     ports:
       - "127.0.0.1:18880:80"
     depends_on: [api]
+    healthcheck:
+      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:80/ || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 10s
     networks: [nexus]
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
 
 networks:
   nexus: