feat(monitoring): observability stack + app instrumentation

- /health/ready (DB+MinIO+Casdoor checks, webhook post-deploy gate),
  /metrics via prometheus-fastapi-instrumentator, Sentry/GlitchTip capture,
  X-Request-ID middleware + JSON access logging (PROCUREMENT_LOG_FORMAT)
- server-side analytics (OpenPanel Track API): login, quote lifecycle,
  receipts — fire-and-forget, disabled without env config
- monitoring/ compose project: GlitchTip(+pg), Prometheus(+alerts),
  Grafana(provisioned ERP dashboard), Loki+Promtail, node/postgres
  exporters, cAdvisor — mem-limited (~2.2GB), loopback admin UIs,
  separate from app deploys; erp_shared network for scraping
- frontend: @openpanel/web + @sentry/react (build-arg gated, no-op when
  unset), funnel events (login, wizard steps, quote submitted)
- compose: api healthcheck, observability env wiring, .env.example keys
This commit is contained in:
MMD
2026-09-18 22:18:02 +03:30
parent f7b1f7f751
commit e17d1f0883
26 changed files with 1106 additions and 3 deletions
+31
View File
@@ -13,6 +13,10 @@ services:
ports:
- "5433:5432"
networks:
- default
- shared # monitoring stack scrapes it (postgres-exporter)
volumes:
- postgres_data:/var/lib/postgresql
- ./sql/migration.sql:/docker-entrypoint-initdb.d/01-migration.sql:ro
@@ -196,10 +200,28 @@ services:
# Console admin used by POST /users/sync (identity mirroring).
PROCUREMENT_CASDOOR_ADMIN_USER: admin
PROCUREMENT_CASDOOR_ADMIN_PASSWORD: ${CASDOOR_ADMIN_PASSWORD:-123}
# Observability (Phase 2) — see monitoring/README.md
PROCUREMENT_LOG_FORMAT: ${LOG_FORMAT:-text}
PROCUREMENT_SENTRY_DSN: ${SENTRY_DSN_BACKEND:-}
PROCUREMENT_OPENPANEL_API_URL: ${OPENPANEL_API_URL:-}
PROCUREMENT_OPENPANEL_CLIENT_ID: ${OPENPANEL_CLIENT_ID:-}
PROCUREMENT_OPENPANEL_CLIENT_SECRET: ${OPENPANEL_CLIENT_SECRET:-}
ports:
- "8000:8000"
networks:
- traefik_network
- default
- shared # monitoring stack scrapes api:8000/metrics
healthcheck:
test: ["CMD-SHELL", "python -c \"import urllib.request as u; u.urlopen('http://127.0.0.1:8000/health', timeout=3)\""]
interval: 30s
timeout: 5s
retries: 5
start_period: 40s
labels:
- traefik.enable=true
- traefik.http.routers.api.rule=Host(`${API_HOST:-api.localhost}`)
@@ -225,6 +247,10 @@ services:
# Developer Mode panel on the login page — dev-only aid. Production
# builds MUST leave this false (identity comes from Casdoor tokens).
DEV_LOGIN_ENABLED: ${DEV_LOGIN_ENABLED:-false}
# Observability (build-time baked; empty = disabled)
VITE_OPENPANEL_URL: ${OPENPANEL_PUBLIC_URL:-}
VITE_OPENPANEL_CLIENT_ID: ${OPENPANEL_CLIENT_ID:-}
VITE_SENTRY_DSN: ${SENTRY_DSN_FRONTEND:-}
container_name: procurement-frontend
labels:
@@ -248,6 +274,11 @@ networks:
traefik_network:
name: traefik_network
driver: bridge
# Fixed-name network shared with the monitoring stack (monitoring compose
# joins it as external) — carries /metrics scrapes and postgres-exporter.
shared:
name: erp_shared
driver: bridge
volumes:
postgres_data: