Files
manage/docker-compose.yml
T
Developer d4f95b64d4 chore(observability): externalize stack from root compose files
Manage now connects to existing Grafana/Prometheus/Alertmanager instances
and never deploys its own stack.

- docker-compose.yml / docker-compose.dev.yml: removed prometheus, loki,
  alloy, grafana, alertmanager, node-exporter services, the monitoring
  network, and observability named volumes; they now ship only backend +
  frontend. Dev frontend now joins the web network so the Vite dev proxy
  can reach the backend.
- backend: alertmanager_url default is now empty; /api/monitoring/alerts
  and /alertmanager-status return graceful "not configured" responses
  when ALERTMANAGER_URL is unset. Added not-configured tests.
- docker-compose.observability.yml: kept as the optional standalone
  example; header clarifies Manage does not deploy it.
- Removed orphaned combined monitoring/prometheus/prometheus.yml
  (standalone stack uses prometheus.standalone.yml).
- Docs (README, REQUIREMENTS decision log, monitoring-logging-design,
  observability-runbooks, context.md, MIGRATION_PLAN, frontend/README,
  CHANGELOG) updated to the connect-to-existing model.

VITE_GRAFANA_URL / VITE_PROMETHEUS_URL remain as optional frontend
deep-link overrides. .env.example still needs a manual update (safety
policy blocks assistant edits): set ALERTMANAGER_URL empty/optional and
move standalone-only vars out of the root file.
2026-06-23 21:20:07 +00:00

103 lines
4.3 KiB
YAML

# Manage production stack — backend + frontend only.
#
# Manage does NOT deploy its own Grafana/Prometheus/Loki/Alertmanager stack.
# It exposes a /metrics endpoint and optional Alertmanager proxy endpoints so
# an *existing* observability deployment can scrape/consume them.
#
# For a ready-to-use example observability stack, see
# docker-compose.observability.yml and docs/observability-runbooks.md.
services:
backend:
build:
context: .
dockerfile: backend/Dockerfile
args:
APP_VERSION: ${APP_VERSION:-0.1.0}
APP_BUILD_INFO: ${APP_BUILD_INFO:-dev}
environment:
AUTH_ENABLED: ${AUTH_ENABLED:-true}
OIDC_ISSUER_URL: ${OIDC_ISSUER_URL:?set OIDC_ISSUER_URL}
OIDC_AUDIENCE: ${OIDC_AUDIENCE:?set OIDC_AUDIENCE}
OIDC_JWKS_URL: ${OIDC_JWKS_URL:-}
OIDC_CLOCK_SKEW_SECONDS: ${OIDC_CLOCK_SKEW_SECONDS:-30}
LOG_LEVEL: ${LOG_LEVEL:-INFO}
LOG_FORMAT: ${LOG_FORMAT:-text}
PROMETHEUS_ENABLED: "true"
SMTP_HOST: ${SMTP_HOST:-}
SMTP_PORT: ${SMTP_PORT:-587}
SMTP_USERNAME: ${SMTP_USERNAME:-}
SMTP_PASSWORD: ${SMTP_PASSWORD:-}
SMTP_FROM_ADDRESS: ${SMTP_FROM_ADDRESS:-}
SMTP_FROM_NAME: ${SMTP_FROM_NAME:-Manage}
SMTP_USE_TLS: ${SMTP_USE_TLS:-true}
SMTP_USE_SSL: ${SMTP_USE_SSL:-false}
SMTP_TIMEOUT: ${SMTP_TIMEOUT:-30}
SSH_KNOWN_HOSTS_PATH: /app/backend/.cache/known_hosts
PROMETHEUS_FILE_SD_DIR: ${PROMETHEUS_FILE_SD_DIR:-/app/backend/.cache/prometheus-file-sd}
ALERTMANAGER_URL: ${ALERTMANAGER_URL:-}
ALERTMANAGER_WEBHOOK_URL: ${ALERTMANAGER_WEBHOOK_URL:-}
MANAGE_ENCRYPTION_KEY: ${MANAGE_ENCRYPTION_KEY:?generate one with python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"}
volumes:
- ${BACKEND_CACHE_DIR:-./backend-cache}:/app/backend/.cache
restart: unless-stopped
networks:
- web
expose:
- "8000"
labels:
- "traefik.enable=true"
- "traefik.http.routers.${BACKEND_APP_NAME:-manage-backend}.rule=Host(`${BACKEND_APP_HOST:?set BACKEND_APP_HOST}`)"
- "traefik.http.routers.${BACKEND_APP_NAME:-manage-backend}.entrypoints=websecure"
- "traefik.http.routers.${BACKEND_APP_NAME:-manage-backend}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
- "traefik.http.services.${BACKEND_APP_NAME:-manage-backend}.loadbalancer.server.port=${BACKEND_APP_PORT:-8000}"
healthcheck:
test:
[
"CMD",
"python",
"-c",
"import json, urllib.request; print(json.load(urllib.request.urlopen('http://127.0.0.1:8000/api/health'))['status'])",
]
interval: 30s
timeout: 5s
retries: 3
start_period: 20s
frontend:
build:
context: .
dockerfile: frontend/Dockerfile
target: prod
args:
VITE_API_URL: ${VITE_API_URL:-/api}
VITE_OIDC_ENABLED: ${VITE_OIDC_ENABLED:-true}
VITE_OIDC_ISSUER: ${VITE_OIDC_ISSUER:?set VITE_OIDC_ISSUER}
VITE_OIDC_CLIENT_ID: ${VITE_OIDC_CLIENT_ID:?set VITE_OIDC_CLIENT_ID}
VITE_OIDC_SCOPE: ${VITE_OIDC_SCOPE:-openid profile email}
VITE_OIDC_REDIRECT_URI: ${VITE_OIDC_REDIRECT_URI:?set VITE_OIDC_REDIRECT_URI}
VITE_OIDC_POST_LOGOUT_REDIRECT_URI: ${VITE_OIDC_POST_LOGOUT_REDIRECT_URI:?set VITE_OIDC_POST_LOGOUT_REDIRECT_URI}
VITE_DEV_API_PROXY_TARGET: ${VITE_DEV_API_PROXY_TARGET:-http://backend:8000}
VITE_GRAFANA_URL: ${VITE_GRAFANA_URL:-https://grafana.example.com}
VITE_PROMETHEUS_URL: ${VITE_PROMETHEUS_URL:-http://prometheus.example.com}
VITE_APP_VERSION: ${APP_VERSION:-0.1.0}
VITE_APP_BUILD_INFO: ${APP_BUILD_INFO:-dev}
depends_on:
backend:
condition: service_healthy
networks:
- web
labels:
- "traefik.enable=true"
- "traefik.http.routers.${FRONTEND_APP_NAME:-manage-frontend}.rule=Host(`${FRONTEND_APP_HOST:?set FRONTEND_APP_HOST}`)"
- "traefik.http.routers.${FRONTEND_APP_NAME:-manage-frontend}.entrypoints=websecure"
- "traefik.http.routers.${FRONTEND_APP_NAME:-manage-frontend}.tls.certresolver=${CERT_RESOLVER:?set CERT_RESOLVER}"
- "traefik.http.services.${FRONTEND_APP_NAME:-manage-frontend}.loadbalancer.server.port=${FRONTEND_APP_PORT:-80}"
ports:
- "8080:80"
restart: unless-stopped
networks:
web:
external: true