# EVERY node needs a secret store path; only four take the hub anchor below. Keep this
# anchor separate from that one — folding it in is what crash-looped site-b and site-c on
# 2026-08-11: they merge no secrets anchor, fell back to the shipped default, and were
# rejected at boot.
#
# The value must be absolute AND outside the content root (/app) — Secrets 0.6.2 validates
# both at startup, because a store inside the deployment directory is destroyed by an
# ordinary upgrade (this wiped the MxGateway key store on 2026-08-09). /data is the node's
# own bind mount, the SAME host directory as /app/data, so an existing store is found
# unmoved; only the path used to reach it changes. Do NOT point this back at /app/data —
# absolute is not sufficient, and the boot will fail.
#
# Do NOT delete this key expecting the library's per-user default to take over. Measured on
# this rig: with a Secrets section present but no SqlitePath, the effective value is the
# RELATIVE "secrets.db", which fails both rules. Setting it explicitly is the supported
# posture for a deployment in any case.
x-secrets-store-env: &secrets-store-env
  Secrets__SqlitePath: "/data/scadabridge-secrets.db"

# ── Clustered secret replication: the pull-only gRPC hub (scadaproj#3) ─────────
#
# Central hosts the hub on its EXISTING h2c control-plane listener (CentralGrpcPort
# 8083, alongside CentralControlService); each site node sweeps it on an interval and
# writes what it pulls into its OWN local SQLite store. Nothing but ciphertext crosses
# the wire, so every participating node must resolve the SAME KEK.
#
# ENABLED ON FOUR NODES ONLY: the central pair (hub) and the site-a pair (followers).
# site-b and site-c are deliberately left without it, so the default-OFF posture is
# proven side by side on one rig — exactly as site-a is the rig's only LocalDb-replicated
# pair. A node with no Secrets__* override keeps the shipped appsettings default
# (Replication:Enabled=false, Mode=SqlServer) and composes a plain local store.
#
# ALL VALUES HERE ARE DEV-ONLY and committed under the same exception as the mesh PSKs
# and the ApiKeyPepper above: a local docker rig needs a working credential in source
# control to boot. Production supplies the KEK out of band (ZB_SECRETS_MASTER_KEY, never
# committed) and the hub token from appsettings/env — NEVER as a ${secret:} reference,
# since resolving one is what the hub exists to make possible.
x-secrets-hub-env: &secrets-hub-env
  # DEV-ONLY KEK — NOT a real key. Identical on all four participating nodes: only
  # ciphertext replicates, so a node with a different KEK fails closed on resolve with a
  # kek_id mismatch that reads like corruption but is a deployment error.
  ZB_SECRETS_MASTER_KEY: "zZiBWuoaVMbJmGXToLk9Lakw0iJozXoL/7Gxac3GwJ4="
  Secrets__Replication__Enabled: "true"
  Secrets__Replication__Mode: "Grpc"
  # DEV-ONLY shared bearer token — NOT a real secret. Presented by every follower and
  # verified by the hub's fail-closed SecretsHubAuthInterceptor. Must be IDENTICAL on the
  # hub and every follower; an unset token is a startup failure on both halves.
  Secrets__GrpcHub__BearerToken: "secrets-hub-docker-dev-token"

# Central-only half: the SHARED SQL-Server secret store (scadaproj#4, Secrets 0.5.0).
# In Grpc mode BOTH central nodes read and write ONE copy of every row in this database,
# so the two hub instances serve identical manifests by construction — that is what makes
# the site-side FallbackEndpoints below safe. ZbSecretsHub is a dedicated database on the
# rig's existing scadabridge-mssql container (default zbsecrets schema, created by the
# boot-time SqlServerSecretsStoreMigrator; the database itself + the scadabridge_app grant
# were provisioned once via sqlcmd — see docs/plans/2026-08-07-secrets-central-shared-store-live-gate.md).
# Same DEV-ONLY credentials as the ScadaBridge__Database__* strings above. Must be a
# LITERAL value, never a ${secret:} reference — the pre-host expander needs this string to
# reach the store that would resolve it (bootstrap circularity; registration rejects it).
# Site nodes must NEVER carry this key: sites talk to central, not to central's database.
x-secrets-hub-central-env: &secrets-hub-central-env
  Secrets__SqlServer__ConnectionString: "Server=scadabridge-mssql,1433;Database=ZbSecretsHub;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"

# Site half of the same section. The hub client dials Endpoint first and fails over, per
# call, to FallbackEndpoints in order (sticky on whichever answered last, Secrets 0.5.0).
# Listing central-b is safe ONLY because both centrals serve the one shared SQL store
# above — never list endpoints backed by independent stores: failing over to an emptier
# hub is a silent convergence stop, the exact defect (scadaproj#4) the shared store
# exists to prevent.
x-secrets-hub-site-env: &secrets-hub-site-env
  Secrets__GrpcHub__Endpoint: "http://scadabridge-central-a:8083"
  Secrets__GrpcHub__FallbackEndpoints__0: "http://scadabridge-central-b:8083"

services:
  central-a:
    image: scadabridge:latest
    # An init process (tini) as PID 1, so a crashed dotnet process actually dies.
    # Without it dotnet IS PID 1, Linux ignores the SIGABRT the runtime's crash path
    # raises against PID 1, and any unhandled boot exception left the container
    # `running` with the main thread spinning at 100% CPU — restart policy never
    # fired (ScadaBridge#34). Belt to Program.cs's UnhandledException handler, which
    # covers managed exceptions but not FailFast/runtime-internal aborts.
    init: true
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-central-a
    environment:
      # Hub half of the pull-only gRPC secrets hub + the central-only shared SQL store
      # (anchors at the top of this file).
      <<: [*secrets-store-env, *secrets-hub-env, *secrets-hub-central-env]
      SCADABRIDGE_CONFIG: Central
      ASPNETCORE_ENVIRONMENT: Development
      ASPNETCORE_URLS: "http://+:5000"
      # DEV-ONLY local-cluster value — NOT a real secret. The Auth/Config normalization
      # (2026-06-03) made ScadaBridge:InboundApi:ApiKeyPepper a hard Central startup
      # requirement (>=16 chars, per-environment). Real deployments inject a true secret
      # out-of-band (env/secret store), never from source control — see
      # docs/operations/inbound-api-key-reissue.md. Both Central nodes share one pepper.
      ScadaBridge__InboundApi__ApiKeyPepper: "dev-only-insecure-pepper-docker-cluster-0001"
      # DEV-ONLY local-cluster secrets — NOT real secrets. Relocated out of the mounted
      # appsettings.Central.json (G-4 T5 secrets cleanup) so that app-config file carries no
      # plaintext credentials. Env overrides layer over JSON BEFORE the ${secret:} pre-host
      # expander runs, so the dev cluster boots with no KEK/secret store. The SQL password is
      # the same value already committed for the sibling scadabridge-mssql container
      # (infra/docker-compose.yml MSSQL_SA_PASSWORD) — consolidation, not new exposure. Real
      # deployments use ${secret:} tokens (src/.../appsettings.Central.json) + a seeded store.
      ScadaBridge__Database__ConfigurationDb: "Server=scadabridge-mssql,1433;Database=ScadaBridgeConfig;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"
      ScadaBridge__Database__MachineDataDb: "Server=scadabridge-mssql,1433;Database=ScadaBridgeMachineData;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"
      ScadaBridge__Security__Ldap__ServiceAccountPassword: "serviceaccount123"
      ScadaBridge__Security__JwtSigningKey: "scadabridge-dev-jwt-signing-key-must-be-at-least-32-characters-long"
      # DEV-ONLY gRPC control-plane preshared keys, one per site — NOT real secrets.
      # Central verifies/presents these; each site node carries the same value as
      # ScadaBridge:Communication:GrpcPsk in its mounted appsettings.Site.json. Kept as
      # env overrides (not in the mounted central appsettings) so that file stays free of
      # plaintext credentials. Production instead seeds SB-GRPC-PSK-<siteId> into the
      # secret store, which is also the only source that can serve a site added at runtime.
      ScadaBridge__Communication__SitePsks__site-a: "dev-grpc-psk-docker-site-a"
      ScadaBridge__Communication__SitePsks__site-b: "dev-grpc-psk-docker-site-b"
      ScadaBridge__Communication__SitePsks__site-c: "dev-grpc-psk-docker-site-c"
    ports:
      - "9001:5000"   # Web UI + Inbound API
      - "9011:8081"   # Akka remoting (host access for CLI/debugging)
      - "9013:8083"   # gRPC control plane (CentralControlService, T1A.2)
    volumes:
      - ./central-node-a/appsettings.Central.json:/app/appsettings.Central.json:ro
      # Originally added for the gRPC secrets hub's local SQLite store; since the
      # central store moved to the shared SQL-Server database (Secrets 0.5.0,
      # scadaproj#4) the scadabridge-secrets.db here is a pre-0.5.0 residue, but the
      # volume is still needed (inbound-api-keys.sqlite lives on it).
      - ./central-node-a/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./central-node-a/data:/data
      - ./central-node-a/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  central-b:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-central-b
    environment:
      # Hub half of the pull-only gRPC secrets hub + the central-only shared SQL store
      # (anchors at the top of this file).
      <<: [*secrets-store-env, *secrets-hub-env, *secrets-hub-central-env]
      SCADABRIDGE_CONFIG: Central
      ASPNETCORE_ENVIRONMENT: Development
      ASPNETCORE_URLS: "http://+:5000"
      # DEV-ONLY local-cluster value — NOT a real secret. The Auth/Config normalization
      # (2026-06-03) made ScadaBridge:InboundApi:ApiKeyPepper a hard Central startup
      # requirement (>=16 chars, per-environment). Real deployments inject a true secret
      # out-of-band (env/secret store), never from source control — see
      # docs/operations/inbound-api-key-reissue.md. Both Central nodes share one pepper.
      ScadaBridge__InboundApi__ApiKeyPepper: "dev-only-insecure-pepper-docker-cluster-0001"
      # DEV-ONLY local-cluster secrets — NOT real secrets. Relocated out of the mounted
      # appsettings.Central.json (G-4 T5 secrets cleanup) so that app-config file carries no
      # plaintext credentials. Env overrides layer over JSON BEFORE the ${secret:} pre-host
      # expander runs, so the dev cluster boots with no KEK/secret store. The SQL password is
      # the same value already committed for the sibling scadabridge-mssql container
      # (infra/docker-compose.yml MSSQL_SA_PASSWORD) — consolidation, not new exposure. Real
      # deployments use ${secret:} tokens (src/.../appsettings.Central.json) + a seeded store.
      ScadaBridge__Database__ConfigurationDb: "Server=scadabridge-mssql,1433;Database=ScadaBridgeConfig;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"
      ScadaBridge__Database__MachineDataDb: "Server=scadabridge-mssql,1433;Database=ScadaBridgeMachineData;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"
      ScadaBridge__Security__Ldap__ServiceAccountPassword: "serviceaccount123"
      ScadaBridge__Security__JwtSigningKey: "scadabridge-dev-jwt-signing-key-must-be-at-least-32-characters-long"
      # DEV-ONLY gRPC control-plane preshared keys, one per site — NOT real secrets.
      # Central verifies/presents these; each site node carries the same value as
      # ScadaBridge:Communication:GrpcPsk in its mounted appsettings.Site.json. Kept as
      # env overrides (not in the mounted central appsettings) so that file stays free of
      # plaintext credentials. Production instead seeds SB-GRPC-PSK-<siteId> into the
      # secret store, which is also the only source that can serve a site added at runtime.
      ScadaBridge__Communication__SitePsks__site-a: "dev-grpc-psk-docker-site-a"
      ScadaBridge__Communication__SitePsks__site-b: "dev-grpc-psk-docker-site-b"
      ScadaBridge__Communication__SitePsks__site-c: "dev-grpc-psk-docker-site-c"
    ports:
      - "9002:5000"   # Web UI + Inbound API
      - "9012:8081"   # Akka remoting
      - "9014:8083"   # gRPC control plane (CentralControlService, T1A.2)
    volumes:
      - ./central-node-b/appsettings.Central.json:/app/appsettings.Central.json:ro
      # Originally added for the gRPC secrets hub's local SQLite store; since the
      # central store moved to the shared SQL-Server database (Secrets 0.5.0,
      # scadaproj#4) the scadabridge-secrets.db here is a pre-0.5.0 residue, but the
      # volume is still needed (inbound-api-keys.sqlite lives on it).
      - ./central-node-b/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./central-node-b/data:/data
      - ./central-node-b/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-a-a:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-a-a
    environment:
      # Follower half of the pull-only gRPC secrets hub (anchors at the top of this
      # file). site-b and site-c deliberately carry neither.
      <<: [*secrets-store-env, *secrets-hub-env, *secrets-hub-site-env]
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9021:8082"   # Akka remoting (host access for debugging)
      - "9023:8083"   # gRPC streaming
    volumes:
      - ./site-a-node-a/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-a-node-a/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-a-node-a/data:/data
      - ./site-a-node-a/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-a-b:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-a-b
    environment:
      # Follower half of the pull-only gRPC secrets hub (anchors at the top of this
      # file). site-b and site-c deliberately carry neither.
      <<: [*secrets-store-env, *secrets-hub-env, *secrets-hub-site-env]
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9022:8082"   # Akka remoting
      - "9024:8083"   # gRPC streaming
    volumes:
      - ./site-a-node-b/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-a-node-b/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-a-node-b/data:/data
      - ./site-a-node-b/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-b-a:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-b-a
    environment:
      <<: *secrets-store-env
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9031:8082"   # Akka remoting
      - "9033:8083"   # gRPC streaming
    volumes:
      - ./site-b-node-a/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-b-node-a/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-b-node-a/data:/data
      - ./site-b-node-a/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-b-b:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-b-b
    environment:
      <<: *secrets-store-env
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9032:8082"   # Akka remoting
      - "9034:8083"   # gRPC streaming
    volumes:
      - ./site-b-node-b/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-b-node-b/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-b-node-b/data:/data
      - ./site-b-node-b/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-c-a:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-c-a
    environment:
      <<: *secrets-store-env
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9041:8082"   # Akka remoting
      - "9043:8083"   # gRPC streaming
    volumes:
      - ./site-c-node-a/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-c-node-a/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-c-node-a/data:/data
      - ./site-c-node-a/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  site-c-b:
    image: scadabridge:latest
    init: true  # PID-1 crash wedge, ScadaBridge#34 — see central-a
    # CoordinatedShutdown needs cluster-leave (15s budget) + cluster-exiting +
    # actor-system-terminate + Serilog flush; the 10s SIGTERM default SIGKILLed
    # mid-drain, turning every redeploy into the crash path (review 01 [Medium]).
    stop_grace_period: 30s
    container_name: scadabridge-site-c-b
    environment:
      <<: *secrets-store-env
      SCADABRIDGE_CONFIG: Site
    ports:
      - "9042:8082"   # Akka remoting
      - "9044:8083"   # gRPC streaming
    volumes:
      - ./site-c-node-b/appsettings.Site.json:/app/appsettings.Site.json:ro
      - ./site-c-node-b/data:/app/data
      # Same host directory, mounted a second time OUTSIDE the content root (/app).
      # Secrets 0.6.2 refuses a store path under the content root; this bind mount is
      # not touched by an image rebuild, but the guard is lexical and cannot know that.
      - ./site-c-node-b/data:/data
      - ./site-c-node-b/logs:/app/logs
    networks:
      - scadabridge-net
    restart: unless-stopped

  traefik:
    image: traefik:v3.4
    container_name: scadabridge-traefik
    ports:
      - "9000:80"        # Central load-balanced entrypoint
      - "8180:8080"      # Traefik dashboard
    volumes:
      - ./traefik/traefik.yml:/etc/traefik/traefik.yml:ro
      - ./traefik/dynamic.yml:/etc/traefik/dynamic.yml:ro
    networks:
      - scadabridge-net
    restart: unless-stopped

networks:
  scadabridge-net:
    external: true