homelab/hosts/jupiter/configuration.nix

{ config, pkgs, lib, ... }:

# ZimaBlade NAS host: hardware + disk + the services it runs.
{
  imports = [
    ./hardware-configuration.nix
    ./disk-config.nix          # disko: OS-disk partitions + filesystems
    ./secrets.nix              # sops-nix: samba password, tailscale key, ...
    ../../common.nix              # shared base: user / ssh / nix / firewall
    ../../services/network/samba.nix
    ../../services/network/avahi.nix
    ../../services/media/audiobookshelf.nix
    ../../services/containers.nix
    ../../services/network/caddy.nix
    ../../services/vpn/tailscale.nix
    ../../services/monitoring/node-exporter.nix
    ../../services/monitoring/victoriametrics.nix
    ../../services/media/jellyfin.nix
    ../../services/media/sabnzbd.nix
    ../../services/media/prowlarr.nix
    ../../services/media/sonarr.nix
    ../../services/media/radarr.nix
    ../../services/media/clonarr.nix
    ../../services/media/seerr.nix
    ../../services/media/immich.nix
    ../../services/dev/gitea.nix
    ../../services/dev/obsidian-livesync.nix
  ];

  # sabnzbd's unrar dependency is unfree; scope the allowance to just that
  # package rather than blanket-allowing unfree across the host.
  nixpkgs.config.allowUnfreePredicate = pkg: builtins.elem (lib.getName pkg) [ "unrar" ];

  # ---- Host identity ----
  networking.hostName = "jupiter";
  networking.networkmanager.enable = true;
  users.users.darman.extraGroups = [ "docker" ];   # merges with common.nix

  # ---- Boot ----
  # systemd-boot for UEFI. If ZimaBlade boots legacy/BIOS, switch to grub.
  boot.loader.systemd-boot.enable = true;
  boot.loader.efi.canTouchEfiVariables = true;
  # common.nix's default of 5 is still too many boot entries for a 29G eMMC — override down to 2.
  boot.loader.systemd-boot.configurationLimit = lib.mkForce 2;

  # A `switch` pins the old generation as a GC root until reboot; common.nix's weekly
  # nix.gc is too slow for a 29G eMMC, so collect garbage on every boot instead.
  systemd.services.gc-on-boot = {
    description = "Full nix-collect-garbage on every boot";
    wantedBy = [ "multi-user.target" ];
    serviceConfig = {
      Type = "oneshot";
      ExecStart = "${pkgs.nix}/bin/nix-collect-garbage -d";
    };
  };

  # Root lives on the ZimaBlade eMMC (mmcblk0). nixos-generate-config runs in
  # the RAM installer and does NOT detect these, so pin them here (merged with
  # hardware-configuration.nix) or stage-1 can't mount root and the box panics.
  boot.initrd.availableKernelModules = [ "mmc_block" "sdhci_pci" "sdhci_acpi" ];

  # Warm reboot hangs at firmware reset on this board (cold power-cycle works).
  # Force the PCI-chipset reset method. If a warm `reboot` still hangs, try the
  # next value: acpi -> bios -> cold -> efi.
  boot.kernelParams = [ "reboot=pci" ];

  # ---- GPU (jellyfin hardware transcoding) ----
  # Apollo Lake N3450 / HD Graphics 500 (Gen9). i915 binds on its own, but VAAPI needs
  # the iHD userspace driver (Gen9; i965 is Gen8-only) or jellyfin-ffmpeg exits 251 on
  # every transcode with no clearer error than "FFmpeg exited with code 251" in the log.
  hardware.graphics = {
    enable = true;
    extraPackages = [ pkgs.intel-media-driver ];
  };
  # ⚠️ Use VAAPI, not QSV, in jellyfin's UI — QSV needs an MFX runtime not safely
  # available for this Gen9 chip (only insecure/EOL options) and fails with exit 171.
  # 4K HDR remuxes also can't be tone-mapped here (needs OpenCL or Gen11+); keep those
  # as 1080p SDR or let them direct-play.

  # ---- NAS data array ----
  # Existing ext4 on mdadm RAID0 (sda+sdb, md0, 29.1T) — mounted, not formatted, kept
  # out of disko. ⚠️ RAID0 has no redundancy: either disk failing loses ALL data.
  boot.swraid.enable = true;
  # Silences the "mdmon service will crash" eval warning — mdmon never actually runs
  # here (native superblocks, not external-metadata) but the module warns regardless.
  boot.swraid.mdadmConf = "MAILADDR root";
  fileSystems."/mnt/data" = {
    # fs UUID (stable) — the array may enumerate as /dev/md127, so avoid /dev/md0.
    device = "/dev/disk/by-uuid/dadbff6f-652e-49b2-bfed-eb1308ab8b78";
    fsType = "ext4";
    options = [ "nofail" ];  # don't block boot if the array is degraded/absent
  };

  # `nofail` alone isn't enough — mounts layered on the array (prowlarr/seerr binds)
  # are RequiredBy local-fs.target and can still trip Emergency Mode, which is a dead
  # end here (root locked, no ssh). Boot as far as possible instead; the array-backed
  # services carry RequiresMountsFor=/mnt/data so they still won't write to the eMMC.
  systemd.enableEmergencyMode = false;

  # ---- Heavy state moved off the eMMC ----
  # A deploy holds two full closures (~9G each) on this 29G disk at once, so state
  # that grows on its own can't live there — moved under /mnt/data/AppData like every
  # other service's state. Settings below are jupiter-only; services/containers.nix
  # stays engine/host-agnostic (mercury runs podman with no array).

  # runroot stays on /run (per-boot tmpfs, doesn't grow); graphroot moves to the array
  # since the gitea runner's CI images alone run several GB.
  virtualisation.containers.storage.settings.storage = {
    driver = "overlay";
    graphroot = "/mnt/data/AppData/containers/storage";
    runroot = "/run/containers/storage";
  };

  # immich's postgres cluster. Version-qualified path (matches upstream default) so a
  # major bump gets a fresh dir instead of reusing the old cluster's files.
  # ⚠️ Puts the DB in the same RAID0 failure domain as the photos it indexes —
  # deliberate (the two are useless apart) but neither is backed up.
  services.postgresql.dataDir =
    "/mnt/data/AppData/postgresql/${config.services.postgresql.package.psqlSchema}";

  # /mnt/data/AppData is drwx--x--- darman:users, so postgres needs the "users" group
  # just to traverse into its dataDir (same reason immich needs it) — postgres itself
  # refuses to start unless the cluster dir is 0700 or 0750.
  users.users.postgres.extraGroups = [ "users" ];

  # Neither path is under /var/lib, so no module creates it automatically — same
  # reason immich needs its own mediaLocation tmpfiles rule.
  systemd.tmpfiles.rules = [
    "d /mnt/data/AppData/postgresql 0750 postgres postgres -"
    "d /mnt/data/AppData/containers 0700 root root -"
  ];

  # Without this, podman would recreate an empty store on the eMMC if the array mounts
  # late or is absent, and the runner would re-pull every image.
  # (podman-clonarr already sets this in services/media/clonarr.nix.)
  systemd.services.podman.unitConfig.RequiresMountsFor = [ "/mnt/data" ];
  systemd.services.gitea-runner-jupiter.unitConfig.RequiresMountsFor = [ "/mnt/data" ];

  # ---- Caddy vhosts (LAN) ----
  # Reached via pihole local-DNS names -> jupiter IP.
  services.caddy.virtualHosts = {
    "http://audiobookshelf.jupiter.sol".extraConfig = "reverse_proxy localhost:8000";
    "http://jellyfin.jupiter.sol".extraConfig = "reverse_proxy localhost:8096";
    "http://sabnzbd.jupiter.sol".extraConfig = "reverse_proxy localhost:8085";
    "http://prowlarr.jupiter.sol".extraConfig = "reverse_proxy localhost:9696";
    "http://sonarr.jupiter.sol".extraConfig = "reverse_proxy localhost:8989";
    "http://radarr.jupiter.sol".extraConfig = "reverse_proxy localhost:7878";
    "http://clonarr.jupiter.sol".extraConfig = "reverse_proxy localhost:6060";
    "http://seerr.jupiter.sol".extraConfig = "reverse_proxy localhost:5055";
    "http://gitea.jupiter.sol".extraConfig = "reverse_proxy localhost:3000";
    # Immich uploads are large: raise the body limit off caddy's default and
    # give slow phone uploads room before the proxy gives up.
    "http://immich.jupiter.sol".extraConfig = ''
      request_body {
        max_size 50GB
      }
      reverse_proxy localhost:2283
    '';
  };

  system.stateVersion = "26.05";
}