thermograph/infra/docker-compose.yml

# Thermograph production stack: backend (FastAPI/API + TestClient(app.py)),
# frontend (the SSR content service), and TimescaleDB (PostgreSQL 18).
#
# FE/BE CI-CD split (finishes repo-split Stage 6/7): backend and frontend are
# two containers, each running its OWN image published by its OWN repo's
# build-push.yml -- backend = ${BACKEND_IMAGE_PATH}, frontend =
# ${FRONTEND_IMAGE_PATH}, tagged independently by BACKEND_IMAGE_TAG /
# FRONTEND_IMAGE_TAG. This replaces the earlier Stage-4 model where both
# containers shared the single emi/thermograph/app image and
# THERMOGRAPH_SERVICE_ROLE picked the process; the split Dockerfiles now start
# the right process directly (frontend the thermograph-frontend Go binary,
# backend entrypoint.sh), so a backend deploy and a frontend deploy are fully
# independent -- deploy.sh rolls one service without touching the other's tag.
# Both get their own loopback-published port since prod/beta's host Caddy
# path-splits directly to each; backend also gets a reverse-proxy fallback to
# frontend (THERMOGRAPH_FRONTEND_BASE_INTERNAL) for any environment with no
# Caddy in front (LAN dev, bare-metal run.sh) -- see backend/web/app.py's
# _proxy_to_frontend.
#
#   docker compose up -d --build      # or: make up
#
# POSTGRES_PASSWORD must be set at `docker compose` time — compose reads it from
# the repo-root .env for local runs (copy .env.example -> .env), and in prod the
# systemd unit's EnvironmentFile=/etc/thermograph.env puts it in the environment
# so `docker compose up` can interpolate it. It is used BOTH to initialize the db
# container and to build backend's THERMOGRAPH_DATABASE_URL below.

# Pin the compose project name: the monorepo layout runs compose from
# /opt/thermograph/infra, and without an explicit name the project would be
# derived from that directory ("infra") -- silently a NEW project, recreating
# the whole stack beside the running one. LAN dev overrides this via
# COMPOSE_PROJECT_NAME=thermograph-dev (the env var always wins over this key).
name: thermograph

services:
  db:
    # TimescaleDB on PostgreSQL 18 (the stock image already sets
    # shared_preload_libraries=timescaledb). The app's climate record — the full
    # daily archive and the hourly recent+forecast bundle — lives in hypertables
    # here (see backend/data/climate_store.py), so the DB, not the filesystem, is the
    # source of truth. The init script CREATE EXTENSIONs timescaledb on a fresh volume
    # (Alembic also does, idempotently, at app boot).
    #
    # TIMESCALEDB_TAG defaults to the floating latest-pg18 tag (today's behavior,
    # unchanged) so a plain `docker compose up` keeps working with no setup. Pin it
    # to an exact minor (e.g. 2.17.2-pg18) before any host of this stack could ever
    # replicate with another — a floating tag risks two hosts landing on different
    # extension minors, which blocks a physical replica and risks compressed-chunk
    # corruption on restore. The Swarm path (deploy/stack/) enforces this a
    # different way: deploy-stack.sh resolves TIMESCALEDB_IMAGE to the digest of
    # whatever db is ALREADY running -- including this compose stack's
    # thermograph-db-1 -- so the image under an existing volume can never drift.
    image: timescale/timescaledb:${TIMESCALEDB_TAG:-latest-pg18}
    environment:
      POSTGRES_USER: thermograph
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?set POSTGRES_PASSWORD}
      POSTGRES_DB: thermograph
      # The init tuning script (deploy/db/init/20-tuning.sh) scales the Postgres +
      # DuckDB memory GUCs from this budget, matching the mem_limit below. One knob
      # per host: Terraform sets DB_MEMORY (prod 16g), local/beta default 8g.
      DB_MEMORY: ${DB_MEMORY:-8g}
    volumes:
      # Mount the volume at the PARENT of the data dir and let the image pick its own
      # PGDATA subdir under it (the timescaledb image defaults to
      # /var/lib/postgresql/data). Pinning PGDATA directly at the mountpoint trips an
      # initdb chmod on some Docker setups; the whole tree still persists this way.
      - pgdata:/var/lib/postgresql
      - ./deploy/db/init:/docker-entrypoint-initdb.d
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U thermograph -d thermograph"]
      interval: 5s
      timeout: 5s
      retries: 10
    # Give Postgres room to cache + process. mem_limit is the hard ceiling; the actual
    # budget is tuned in deploy/db/init/20-tuning.sh, which scales shared_buffers (25%),
    # effective_cache_size (75%), work_mem and maintenance_work_mem from DB_MEMORY — so
    # raising DB_MEMORY raises both the cap and the tuning together. shm_size backs
    # parallel-query shared memory (the 64MB docker default is
    # too small once shared_buffers/parallelism grow).
    # Sized via env (Terraform sets DB_CPUS/DB_MEMORY per host); defaults match the
    # historical 2 CPU / 8 GB budget so a plain `docker compose up` is unchanged.
    mem_limit: ${DB_MEMORY:-8g}
    shm_size: 1gb
    # Cap the DB at DB_CPUS CPUs. Compose v2 honors the top-level `cpus:`; the
    # deploy.resources block is the Swarm-style equivalent, kept for parity.
    cpus: ${DB_CPUS:-2}
    deploy:
      resources:
        limits:
          cpus: "${DB_CPUS:-2}"
          # Must match mem_limit above (compose rejects distinct values).
          memory: ${DB_MEMORY:-8g}
    restart: unless-stopped
    # No host port on purpose: the app reaches Postgres as db:5432 on the
    # compose network. Nothing outside the stack should touch the database.

  backend:
    # Backend's OWN image, published by thermograph-backend's build-push.yml.
    # No `build:` here -- infra holds no Dockerfile; each service's Dockerfile
    # lives in its own app repo. deploy.sh sets BACKEND_IMAGE_TAG to the SHA
    # build-push.yml pushed for the backend commit being deployed; local dev
    # builds `emi/thermograph/backend:local` from the backend repo (see
    # infra Makefile) and this pulls/uses it. BACKEND_IMAGE_PATH/TAG are
    # independent of the frontend's, so the two services deploy separately.
    image: ${REGISTRY_HOST:-git.thermograph.org}/${BACKEND_IMAGE_PATH:-emi/thermograph/backend}:${BACKEND_IMAGE_TAG:-local}
    depends_on:
      db:
        condition: service_healthy
    environment:
      # Built from POSTGRES_PASSWORD; this `environment` value wins over anything
      # in env_file, so the URL always matches the db container's password.
      THERMOGRAPH_DATABASE_URL: postgresql+asyncpg://thermograph:${POSTGRES_PASSWORD}@db:5432/thermograph
      THERMOGRAPH_BASE: /
      PORT: 8137
      THERMOGRAPH_SERVICE_ROLE: backend
      # Docker's built-in service-name DNS -- reachable only inside the compose
      # network. See backend/web/app.py's _proxy_to_frontend.
      THERMOGRAPH_FRONTEND_BASE_INTERNAL: http://frontend:8080
      # Worker count is env-driven so Terraform can raise it on a bigger host;
      # defaults to 4 to keep a plain `docker compose up` identical to before.
      WORKERS: ${WORKERS:-4}
      # One worker wins this lock and runs the subscription notifier / homepage
      # sweep; it lives on the appdata volume so it's shared across workers.
      THERMOGRAPH_DATA_DIR: /state
      # notifier.lock lives in the state volume, which is now mounted at /state
      # (NOT /app/data) so it never shadows the Python `data/` package -- see the
      # volumes: note below and thermograph-backend paths.py.
      THERMOGRAPH_SINGLETON_LOCK: /state/notifier.lock
      # History reads ask the lake service before any third-party source; if
      # the lake has no bucket creds (LAN without them exported) it answers
      # 503 and climate.py falls straight through to NASA — an accelerator,
      # never a dependency.
      THERMOGRAPH_LAKE_URL: http://lake:8141
      # Shared secret for the /internal/* routes the daemon service calls.
      # Interpolated (like POSTGRES_PASSWORD) so local runs get it from the
      # repo-root .env; prod/beta have it in /etc/thermograph.env, which
      # deploy.sh sources before compose so this resolves there too. Empty =>
      # the backend disables the routes and the daemon refuses to start -- fail
      # closed on both ends.
      THERMOGRAPH_INTERNAL_TOKEN: ${THERMOGRAPH_INTERNAL_TOKEN:-}
    # Prod secrets live in /etc/thermograph.env: POSTGRES_PASSWORD,
    # THERMOGRAPH_AUTH_SECRET, THERMOGRAPH_VAPID_PRIVATE_KEY/_PUBLIC_KEY,
    # THERMOGRAPH_COOKIE_SECURE=1, mail/Discord keys, ... (see
    # deploy/thermograph.env.example). `required: false` so local `docker compose
    # up` works without that file — it reads POSTGRES_PASSWORD from repo-root .env.
    env_file:
      - path: /etc/thermograph.env
        required: false
    volumes:
      # Parquet cache, notifier.lock, homepage.json, vapid.json persist here.
      # /state, NOT /app/data: after the repo split the backend's Python package
      # `data/` sits at /app/data, so mounting the runtime volume there erased
      # data/*.py and broke `import data.climate` at boot. THERMOGRAPH_DATA_DIR=/state
      # (above) points runtime state here instead, clear of the code.
      - appdata:/state
      - applogs:/app/logs
    # No compose-level healthcheck override -- the image's own Dockerfile
    # HEALTHCHECK (port-aware via ${PORT}) already covers this, and frontend's
    # depends_on below reads it the same way.
    # Sized via env (Terraform sets APP_CPUS per host); defaults to 4 CPUs. The
    # deploy.resources block mirrors the top-level `cpus:` for Swarm parity; the
    # dev overlay drops both so dev runs uncapped.
    cpus: ${APP_CPUS:-4}
    deploy:
      resources:
        limits:
          cpus: "${APP_CPUS:-4}"
    ports:
      # Loopback only — host Caddy terminates TLS and reverse-proxies to this
      # (and, in prod/beta, directly to frontend's own port below too).
      - "127.0.0.1:8137:8137"
    restart: unless-stopped

  # The ERA5 lake service: partition-pruned reads over the era5-thermograph
  # bucket with a local parquet cache, same backend image with
  # THERMOGRAPH_ROLE=lake (the entrypoint starts lake_app — no database, no
  # migrations, so no depends_on: db). Bucket creds come from
  # /etc/thermograph.env where the vault renders them (beta/prod) or from the
  # deploy environment (LAN — deploy-dev.yml injects the Actions S3 secrets);
  # without them the service stays healthy and every read falls through to
  # NASA. Never published on a host port: only the backend talks to it.
  lake:
    image: ${REGISTRY_HOST:-git.thermograph.org}/${BACKEND_IMAGE_PATH:-emi/thermograph/backend}:${BACKEND_IMAGE_TAG:-local}
    environment:
      THERMOGRAPH_ROLE: lake
      PORT: 8141
      THERMOGRAPH_SERVICE_ROLE: backend
      WORKERS: "1"
      THERMOGRAPH_LAKE_CACHE: /state/lake-cache
      THERMOGRAPH_LAKE_S3_ACCESS_KEY: ${THERMOGRAPH_LAKE_S3_ACCESS_KEY:-}
      THERMOGRAPH_LAKE_S3_SECRET_KEY: ${THERMOGRAPH_LAKE_S3_SECRET_KEY:-}
    env_file:
      - path: /etc/thermograph.env
        required: false
    volumes:
      - lakecache:/state
    cpus: ${LAKE_CPUS:-2}
    deploy:
      resources:
        limits:
          cpus: "${LAKE_CPUS:-2}"
    restart: unless-stopped

  daemon:
    # The SAME image and tag as backend, on purpose: the daemon (Go, built into
    # the backend image as /usr/local/bin/thermograph-daemon) and the backend
    # share the /internal/* API contract, so they must roll together — a
    # separate tag could skew them. It owns the Discord gateway websocket and
    # the recurring-job timers; anything needing data calls back into backend.
    image: ${REGISTRY_HOST:-git.thermograph.org}/${BACKEND_IMAGE_PATH:-emi/thermograph/backend}:${BACKEND_IMAGE_TAG:-local}
    # Bypass deploy/entrypoint.sh entirely: that script runs Alembic, and the
    # backend service's boot already owns migrations — two containers racing
    # `alembic upgrade head` against one database is a real hazard, not a
    # nicety. The daemon binary never touches the DB.
    entrypoint: ["/usr/local/bin/thermograph-daemon"]
    # Its first acts are calls to backend's /internal/* routes, so wait for a
    # genuinely healthy backend, not just a started container.
    depends_on:
      backend:
        condition: service_healthy
    environment:
      # Same var the frontend uses for the same purpose: the backend's URL on
      # the compose-internal network.
      THERMOGRAPH_API_BASE_INTERNAL: http://backend:8137
      # See the backend service's note on this var — same interpolation, same
      # fail-closed-when-empty behavior on both ends. Normally EMPTY: with no
      # explicit value both ends derive the same token from
      # THERMOGRAPH_AUTH_SECRET, which arrives via the env_file below. That is
      # why this service must keep reading that file even though it serves
      # nothing — without the auth secret it has nothing to derive from and
      # refuses to start.
      THERMOGRAPH_INTERNAL_TOKEN: ${THERMOGRAPH_INTERNAL_TOKEN:-}
    # THERMOGRAPH_AUTH_SECRET (derivation input, see above), the bot token/flag
    # and the job intervals (THERMOGRAPH_DISCORD_BOT[_TOKEN],
    # THERMOGRAPH_*_INTERVAL_HOURS) all arrive via the host env file, same as
    # the backend's secrets do — so both processes read one source of truth and
    # cannot disagree about the derived token.
    env_file:
      - path: /etc/thermograph.env
        required: false
    # The image's HEALTHCHECK curls /healthz on ${PORT} — right for the backend
    # process, meaningless for the daemon, which serves nothing. Without this
    # the container would sit permanently "unhealthy".
    healthcheck:
      disable: true
    # No volumes: warm-cities/IndexNow work executes inside the BACKEND process
    # (the daemon only fires the internal endpoints on a timer), the parquet
    # cache and locks stay on backend's appdata volume, and the daemon logs to
    # stdout. It holds no state a volume would protect.
    #
    # No ports: outbound-only (Discord gateway + calls to backend). Publishing
    # anything here would only widen the surface for no benefit.
    cpus: 0.5
    deploy:
      resources:
        limits:
          cpus: "0.5"
    restart: unless-stopped

  frontend:
    # Frontend's OWN image, published by build-push.yml (frontend leg) from
    # frontend/Dockerfile (which starts the thermograph-frontend Go binary
    # directly -- no THERMOGRAPH_SERVICE_ROLE process-picking). Independent
    # FRONTEND_IMAGE_TAG so a frontend deploy never disturbs the backend's tag.
    image: ${REGISTRY_HOST:-git.thermograph.org}/${FRONTEND_IMAGE_PATH:-emi/thermograph/frontend}:${FRONTEND_IMAGE_TAG:-local}
    # Its own register() fetches the IndexNow key from backend at boot -- must
    # wait for a real, healthy backend, not just a started container.
    depends_on:
      backend:
        condition: service_healthy
    environment:
      THERMOGRAPH_BASE: /
      PORT: 8080
      THERMOGRAPH_SERVICE_ROLE: frontend
      THERMOGRAPH_API_BASE_INTERNAL: http://backend:8137
    # No volumes -- stateless, holds no data of its own.
    cpus: ${FRONTEND_CPUS:-2}
    deploy:
      resources:
        limits:
          cpus: "${FRONTEND_CPUS:-2}"
    ports:
      - "127.0.0.1:8080:8080"
    restart: unless-stopped

volumes:
  pgdata: {}
  appdata: {}
  applogs: {}
  lakecache: {}

networks:
  # Pin the default network's subnet + gateway so the host Postfix can rely on a
  # stable address. The app sends verification email by speaking SMTP to the
  # gateway (172.19.0.1), where the host Postfix listens and relays out (see
  # deploy/provision-mail.sh + THERMOGRAPH_SMTP_HOST in thermograph.env). Without
  # the pin, Docker picks a subnet from its pool and the gateway could move.
  # 172.19.0.0/16 matches what prod and beta are live on today, so applying this
  # is a no-op there.
  default:
    ipam:
      config:
        - subnet: 172.19.0.0/16
          gateway: 172.19.0.1