OliviaCandClaude Opus 4.7
ede70a21b3
Sostituisce il healthcheck banale (urlopen /api/health) con uno che fallisce quando camera_open != true, e aggiunge il container willfarrell/autoheal che restarta il backend quando Docker lo marca unhealthy. Recovery <1min da SDK stuck senza intervento SSH. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
92 lines
2.5 KiB
YAML
92 lines
2.5 KiB
YAML
services:
|
||
|
||
# -- NATS Server ----------------------------
|
||
nats:
|
||
image: nats:latest
|
||
profiles: ["nats"]
|
||
ports:
|
||
- "4222:4222"
|
||
- "8222:8222"
|
||
command: >
|
||
--auth ${NATS_TOKEN:-realsense-dev-token}
|
||
--http_port 8222
|
||
restart: unless-stopped
|
||
healthcheck:
|
||
test: ["CMD", "nats-server", "--help"]
|
||
interval: 5s
|
||
timeout: 3s
|
||
retries: 3
|
||
start_period: 5s
|
||
|
||
# -- Backend --------------------------------
|
||
backend:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
# network: host so that build-time apt/git/pip can reach the
|
||
# tinyproxy running on the host at localhost:8888.
|
||
network: host
|
||
privileged: true
|
||
ports:
|
||
- "${API_PORT:-8878}:8878"
|
||
devices:
|
||
- "/dev/bus/usb:/dev/bus/usb"
|
||
volumes:
|
||
- ./images:/app/images
|
||
- ./models:/app/models:ro
|
||
env_file: .env
|
||
depends_on:
|
||
nats:
|
||
condition: service_healthy
|
||
required: false
|
||
restart: unless-stopped
|
||
labels:
|
||
# autoheal monitora SOLO i container con questa label = true
|
||
autoheal: "true"
|
||
healthcheck:
|
||
# Healthcheck "vero": fallisce se camera_open != true.
|
||
# Usa /api/health (pubblico, no API key) che già ritorna camera_open.
|
||
# 4 retry × 15s ⇒ ~1 min di stato cattivo prima dell'autoheal restart.
|
||
test:
|
||
- CMD
|
||
- python3
|
||
- -c
|
||
- |
|
||
import urllib.request, json, sys
|
||
try:
|
||
r = urllib.request.urlopen('http://localhost:8878/api/health', timeout=3)
|
||
d = json.loads(r.read())
|
||
sys.exit(0 if d.get('data', {}).get('camera_open') else 1)
|
||
except Exception:
|
||
sys.exit(1)
|
||
interval: 15s
|
||
timeout: 5s
|
||
retries: 4
|
||
start_period: 30s
|
||
|
||
# -- Autoheal -------------------------------
|
||
# Monitora i container con label `autoheal=true` e li restarta automaticamente
|
||
# quando Docker li marca "unhealthy". Risolve il caso "pyrealsense2 SDK stuck".
|
||
autoheal:
|
||
image: willfarrell/autoheal:latest
|
||
container_name: autoheal-d435
|
||
restart: always
|
||
environment:
|
||
AUTOHEAL_CONTAINER_LABEL: autoheal
|
||
AUTOHEAL_INTERVAL: 10
|
||
AUTOHEAL_START_PERIOD: 30
|
||
volumes:
|
||
- /var/run/docker.sock:/var/run/docker.sock:ro
|
||
|
||
# -- Frontend React Dev (hot reload) --------
|
||
frontend-dev:
|
||
image: node:20-alpine
|
||
working_dir: /app
|
||
volumes:
|
||
- ./src/frontend/react:/app
|
||
- /app/node_modules
|
||
command: sh -c "npm ci && npm run dev -- --host 0.0.0.0"
|
||
ports:
|
||
- "5173:5173"
|
||
profiles: [dev]
|