homelab-codex-ws/inventory/topology.yaml

topology:
  mesh: tailscale
  git_provider: forgejo

deployment:
  # Every deploy script SSH-pushes from saturn to the target node (recon
  # F20.10); "pull" never matched reality.
  mode: push
  orchestrator: saturn

# Ingress dla usług domowych przez NPM @ PIHA + wildcard cert kapala.org.
# Od 2026-06-30. Poprzednia ścieżka (add-on Tailscale na ha-ken) PORZUCONA.
# DNS kapala.org: Cloudflare, wildcard *.kapala.org via DNS-01 (auto-renew).
# Mail: Fastmail (MX/DKIM/SPF na CF, DNS only).
# Subdomeny mesh: A → 100.108.208.3 (Tailscale PIHA), DNS only.
ingress:
  dns_provider: cloudflare          # kapala.org od 2026-06-30
  wildcard_cert:
    domain: "*.kapala.org"
    method: dns-01                  # Cloudflare DNS-01, auto-renew
    proxy: npm-piha                 # Nginx Proxy Manager @ PIHA
  services:
    home_assistant:
      host: 192.168.31.7
      port: 8123
      ingress: ha.kapala.org        # NPM @ PIHA, cert *.kapala.org, mesh-only
      access: tailscale             # 100.108.208.3
      cert: wildcard-kapala         # DNS-01 Cloudflare, auto-renew
    immich:
      host: 192.168.31.5
      port: 2283
      ingress: immich.kapala.org    # NPM @ PIHA, cert *.kapala.org, mesh-only
      access: tailscale
      cert: wildcard-kapala

# Node-level truth ONLY. Per-node service lists live in hosts/<node>/services.yaml
# (authoritative — the lists formerly duplicated here contradicted them, recon F20.1).
#
# status:
#   active  — node is monitored and remediated normally.
#   dormant — node exists but is expected offline: the observer keeps its
#             last-known world state and emits NO liveness events for it; the
#             supervisor generates NO actions for it. See ARCHITEKTURA.md.
nodes:

  saturn:
    status: active
    roles:
      - control
      - development

  piha:
    status: active
    roles:
      - infra
      - monitoring

  solaria:
    # Powered off ~16 h/day BY DESIGN (on-demand compute desktop): one daily
    # offline/online liveness cycle is expected, not a fault. Nothing that
    # must run 24/7 may live here.
    status: active
    roles:
      - compute
      - ai

  vps:
    status: active
    roles:
      - edge
      - ingress
      - control-plane

  lustro:
    # MagicMirror Raspberry Pi — full monitored node: runs node-agent and
    # ships events to the control plane (recon F20.11).
    # Duty cycle (checked 2026-07-30 in the vps event store): node_offline
    # fires once a day, ~24 h apart, around 23:30 local — a scheduled nightly
    # display power-off like solaria's. Daily stale/offline/online liveness
    # cycles are expected here, not faults.
    status: active
    roles:
      - edge
      - display

  chelsty-infra:
    status: dormant
    dormant_reason: "site hardware down since ~2026-06-01; will be revived later"
    dormant_since: "2026-06-01"
    site: chelsty
    roles:
      - remote
      - hypervisor
      - infra
      - staging
    connectivity:
      uplink: lte
      intermittent: true
    home_automation:
      offline_operation_required: true
      coordinator:
        model: SLZB-06U
        connection: network
        usb: false

  chelsty-ha:
    status: dormant
    dormant_reason: "site hardware down since ~2026-06-01; will be revived later"
    dormant_since: "2026-06-01"
    site: chelsty
    roles:
      - remote
      - homeassistant
    connectivity:
      uplink: lte
      intermittent: true
    home_automation:
      offline_operation_required: true