From 1d42be98826fcc07be4811a44f2cf22d437e6211 Mon Sep 17 00:00:00 2001 From: Marcel Date: Fri, 15 May 2026 01:23:03 +0200 Subject: [PATCH] devops(observability): scaffold docker-compose.observability.yml and infra/observability/ structure Creates the skeleton observability stack (no running services yet) that all subsequent Grafana LGTM + GlitchTip issues depend on: - docker-compose.observability.yml: external archiv-net join, obs-net bridge, named volumes for all five services, placeholder comments for each service group (Metrics/Logs/Traces/Dashboards/Error Tracking), startup-order note - infra/observability/{prometheus,loki,promtail,tempo,grafana/provisioning/{datasources,dashboards}}/.gitkeep - .env.example: new # --- Observability --- section with PORT_GRAFANA, PORT_GLITCHTIP, PORT_PROMETHEUS, GLITCHTIP_DOMAIN, GLITCHTIP_SECRET_KEY (with generation hint), SENTRY_DSN, VITE_SENTRY_DSN Verified: docker compose -f docker-compose.observability.yml config exits 0 Co-Authored-By: Claude Sonnet 4.6 --- .env.example | 24 ++++++++++ docker-compose.observability.yml | 48 +++++++++++++++++++ .../grafana/provisioning/dashboards/.gitkeep | 0 .../grafana/provisioning/datasources/.gitkeep | 0 infra/observability/loki/.gitkeep | 0 infra/observability/prometheus/.gitkeep | 0 infra/observability/promtail/.gitkeep | 0 infra/observability/tempo/.gitkeep | 0 8 files changed, 72 insertions(+) create mode 100644 docker-compose.observability.yml create mode 100644 infra/observability/grafana/provisioning/dashboards/.gitkeep create mode 100644 infra/observability/grafana/provisioning/datasources/.gitkeep create mode 100644 infra/observability/loki/.gitkeep create mode 100644 infra/observability/prometheus/.gitkeep create mode 100644 infra/observability/promtail/.gitkeep create mode 100644 infra/observability/tempo/.gitkeep diff --git a/.env.example b/.env.example index 5b928337..3d8ebb00 100644 --- a/.env.example +++ b/.env.example @@ -26,6 +26,30 @@ PORT_MAILPIT_SMTP=1025 # Generate with: python3 -c "import secrets; print(secrets.token_hex(32))" OCR_TRAINING_TOKEN=change-me-in-production +# --- Observability --- +# Optional stack — start with: docker compose -f docker-compose.observability.yml up -d +# Requires the main stack to already be running (docker compose up -d creates archiv-net). + +# Ports for host access +PORT_GRAFANA=3001 +PORT_GLITCHTIP=3002 +PORT_PROMETHEUS=9090 + +# GlitchTip domain — production: use https://grafana.raddatz.cloud (must match Caddy vhost) +GLITCHTIP_DOMAIN=http://localhost:3002 + +# GlitchTip secret key — Django SECRET_KEY equivalent, used to sign sessions and tokens. +# REQUIRED in production — must not be empty or 'changeme'. Fail-closed: GlitchTip will +# refuse to start with an invalid key. +# Generate with: python3 -c "import secrets; print(secrets.token_hex(50))" +GLITCHTIP_SECRET_KEY=changeme-generate-a-real-secret + +# Error reporting DSNs — leave empty to disable the SDK (safe default). +# SENTRY_DSN: backend (Spring Boot) — used by the GlitchTip/Sentry Java SDK +SENTRY_DSN= +# VITE_SENTRY_DSN: frontend (SvelteKit) — injected at build time via Vite +VITE_SENTRY_DSN= + # Production SMTP — uncomment and fill in to send real emails instead of catching them # APP_BASE_URL=https://your-domain.example.com # MAIL_HOST=smtp.example.com diff --git a/docker-compose.observability.yml b/docker-compose.observability.yml new file mode 100644 index 00000000..461f2905 --- /dev/null +++ b/docker-compose.observability.yml @@ -0,0 +1,48 @@ +# Observability stack — Grafana LGTM + GlitchTip +# +# Requires the main stack to be running first: +# docker compose up -d # creates archiv-net +# docker compose -f docker-compose.observability.yml up -d +# +# To validate without starting: +# docker compose -f docker-compose.observability.yml config + +# No services defined yet — added in subsequent issues: +# +# --- Metrics: Prometheus --- +# prometheus: (see issue #573) +# +# --- Logs: Loki + Promtail --- +# loki: (see issue #574) +# promtail: (see issue #575) +# +# --- Traces: Tempo --- +# tempo: (see future issue) +# +# --- Dashboards: Grafana --- +# grafana: (see future issue) +# +# --- Error Tracking: GlitchTip --- +# glitchtip: (see future issue) +services: {} + +networks: + # Shared network created by the main docker-compose.yml. + # The observability stack joins as a peer so Prometheus can scrape + # archive-backend by container name. The observability stack must NOT + # attempt to create this network — it will fail with a clear error if + # the main stack is not running yet. + archiv-net: + external: true + + # Internal network for observability-service-to-service traffic + # (e.g. Grafana → Prometheus, Grafana → Loki, Grafana → Tempo). + obs-net: + driver: bridge + +volumes: + prometheus_data: + loki_data: + tempo_data: + grafana_data: + glitchtip_data: diff --git a/infra/observability/grafana/provisioning/dashboards/.gitkeep b/infra/observability/grafana/provisioning/dashboards/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/infra/observability/grafana/provisioning/datasources/.gitkeep b/infra/observability/grafana/provisioning/datasources/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/infra/observability/loki/.gitkeep b/infra/observability/loki/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/infra/observability/prometheus/.gitkeep b/infra/observability/prometheus/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/infra/observability/promtail/.gitkeep b/infra/observability/promtail/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/infra/observability/tempo/.gitkeep b/infra/observability/tempo/.gitkeep new file mode 100644 index 00000000..e69de29b