Enable sysrq for debugging.

Otherwise, sshd will try and fail to bind on the tailscale IP before
tailscale is up.

.envrc

@@ -0,0 +1 @@
+use flake

.gitignore

@@ -1,3 +1,6 @@
 *.swp
 .tmp
 result
+.aider*
+.claude
+.direnv/

.sops.yaml

@@ -2,9 +2,12 @@ keys:
   - &admin_ppetru age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
   - &server_zippy age1gtyw202hd07hddac9886as2cs8pm07e4exlnrgfm72lync75ng9qc5fjac
   - &server_chilly age16yqffw4yl5jqvsr7tyd883vn98zw0attuv9g5snc329juff6dy3qw2w5wp
+  - &server_sparky age14aml5s3sxksa8qthnt6apl3pu6egxyn0cz7pdzzvp2yl6wncad0q56udyj
+  - &server_stinky age1me78u46409q9ez6fj0qanrfffc5e9kuq7n7uuvlljfwwc2mdaezqmyzxhx
+  - &server_beefy age1cs8uqj243lspyp042ueu5aes4t3azgyuaxl9au70ggrl2meulq4sgqpc7y
   - &server_alo_cloud_1 age1w5w4wfvtul3sge9mt205zvrkjaeh3qs9gsxhmq7df2g4dztnvv6qylup8z
   - &server_c1 age1wwufz86tm3auxn6pn27c47s8rvu7en58rk00nghtaxsdpw0gya6qj6qxdt
-  - &server_c2 age1gekmz8kc8r2lc2x6d4u63s2lnpmres4hu9wulxh29ch74ud7wfksq56xam
+  - &server_c2 age1jy7pe4530s8w904wtvrmpxvteztqy5ewdt92a7y3lq87sg9jce5qxxuydt
   - &server_c3 age1zjgqu3zks5kvlw6hvy6ytyygq7n25lu0uj2435zlf30smpxuy4hshpmfer
 creation_rules:
   - path_regex: secrets/common\.yaml
@@ -13,6 +16,9 @@ creation_rules:
         - *admin_ppetru
         - *server_zippy
         - *server_chilly
+        - *server_sparky
+        - *server_stinky
+        - *server_beefy
         - *server_alo_cloud_1
         - *server_c1
         - *server_c2
@@ -27,6 +33,26 @@ creation_rules:
       - age:
         - *admin_ppetru
         - *server_chilly
+  - path_regex: secrets/sparky\.yaml
+    key_groups:
+      - age:
+        - *admin_ppetru
+        - *server_sparky
+  - path_regex: secrets/stinky\.yaml
+    key_groups:
+      - age:
+        - *admin_ppetru
+        - *server_stinky
+  - path_regex: secrets/beefy\.yaml
+    key_groups:
+      - age:
+        - *admin_ppetru
+        - *server_beefy
+  - path_regex: secrets/wifi\.yaml
+    key_groups:
+      - age:
+        - *admin_ppetru
+        - *server_stinky
   - path_regex: secrets/alo-cloud-1\.yaml
     key_groups:
       - age:

CLAUDE.md

@@ -0,0 +1,116 @@
+# Claude Code Quick Reference
+
+NixOS cluster configuration using flakes. Homelab infrastructure with Nomad/Consul orchestration.
+
+## Project Structure
+
+```
+├── common/
+│   ├── global/                    # Applied to all hosts (backup, sops, users, etc.)
+│   ├── minimal-node.nix           # Base (ssh, user, boot, impermanence)
+│   ├── cluster-member.nix         # Consul agent + storage mounts (NFS/CIFS)
+│   ├── nomad-worker.nix           # Nomad client (runs jobs) + Docker + NFS deps
+│   ├── nomad-server.nix           # Enables Consul + Nomad server mode
+│   ├── cluster-tools.nix          # Just CLI tools (nomad, wander, damon)
+│   ├── workstation-node.nix       # Dev tools (wget, deploy-rs, docker, nix-ld)
+│   ├── desktop-node.nix           # Hyprland + GUI environment
+│   ├── nfs-services-server.nix    # NFS server + btrfs replication
+│   └── nfs-services-standby.nix   # NFS standby + receive replication
+├── hosts/                           # Host configs - check imports for roles
+├── docs/
+│   ├── CLUSTER_REVAMP.md    # Master plan for architecture changes
+│   ├── MIGRATION_TODO.md    # Tracking checklist for migration
+│   ├── NFS_FAILOVER.md      # NFS failover procedures
+│   └── AUTH_SETUP.md        # Authentication (Pocket ID + Traefik OIDC)
+└── services/            # Nomad job specs (.hcl files)
+```
+
+## Current Architecture
+
+### Storage Mounts
+- `/data/services` - NFS from `data-services.service.consul` (check nfs-services-server.nix for primary)
+- `/data/media` - CIFS from fractal
+- `/data/shared` - CIFS from fractal
+
+### Cluster Roles (check hosts/*/default.nix for each host's imports)
+- **Quorum**: hosts importing `nomad-server.nix` (3 expected for consensus)
+- **Workers**: hosts importing `nomad-worker.nix` (run Nomad jobs)
+- **NFS server**: host importing `nfs-services-server.nix` (affinity for direct disk access like DBs)
+- **Standby**: hosts importing `nfs-services-standby.nix` (receive replication)
+
+## Config Architecture
+
+**Modular role-based configs** (compose as needed):
+- `minimal-node.nix` - Base for all systems (SSH, user, boot, impermanence)
+- `cluster-member.nix` - Consul agent + shared storage mounts (no Nomad)
+- `nomad-worker.nix` - Nomad client to run jobs (requires cluster-member)
+- `nomad-server.nix` - Enables Consul + Nomad server mode (for quorum members)
+- `cluster-tools.nix` - Just CLI tools (no services)
+
+**Machine type configs** (via flake profile):
+- `workstation-node.nix` - Dev tools (deploy-rs, docker, nix-ld, emulation)
+- `desktop-node.nix` - Extends workstation + Hyprland/GUI
+
+**Composition patterns**:
+- Quorum member: `cluster-member + nomad-worker + nomad-server`
+- Worker only: `cluster-member + nomad-worker`
+- CLI only: `cluster-member + cluster-tools` (Consul agent, no Nomad service)
+- NFS primary: `cluster-member + nomad-worker + nfs-services-server`
+- Standalone: `minimal-node` only (no cluster membership)
+
+**Key insight**: Profiles (workstation/desktop) don't imply cluster roles. Check imports for actual roles.
+
+## Key Patterns
+
+**NFS Server/Standby**:
+- Primary: imports `nfs-services-server.nix`, sets `standbys = [...]`
+- Standby: imports `nfs-services-standby.nix`, sets `replicationKeys = [...]`
+- Replication: btrfs send/receive every 5min, incremental with fallback to full
+- Check host configs for current primary/standby assignments
+
+**Backups**:
+- Kopia client on all nodes → Kopia server on fractal
+- Backs up `/persist` hourly via btrfs snapshot
+- Excludes: `services@*` and `services-standby/services@*` (replication snapshots)
+
+**Secrets**:
+- SOPS for secrets, files in `secrets/`
+- Keys managed per-host
+
+**Authentication**:
+- Pocket ID (OIDC provider) at `pocket-id.v.paler.net`
+- Traefik uses `traefik-oidc-auth` plugin for SSO
+- Services add `middlewares=oidc-auth@file` tag to protect
+- See `docs/AUTH_SETUP.md` for details
+
+## Migration Status
+
+**Phase 3 & 4**: COMPLETE! GlusterFS removed, all services on NFS
+**Next**: Convert fractal to NixOS (deferred)
+
+See `docs/MIGRATION_TODO.md` for detailed checklist.
+
+## Common Tasks
+
+**Deploy a host**: `deploy -s '.#hostname'`
+**Deploy all**: `deploy`
+**Check replication**: Check NFS primary host, then `ssh <primary> journalctl -u replicate-services-to-*.service -f`
+**NFS failover**: See `docs/NFS_FAILOVER.md`
+**Nomad jobs**: `services/*.hcl` - service data stored at `/data/services/<service-name>`
+
+## Troubleshooting Hints
+
+- Replication errors with "empty stream": SSH key restricted to `btrfs receive`, can't run other commands
+- NFS split-brain protection: nfs-server checks Consul before starting
+- Btrfs snapshots: nested snapshots appear as empty dirs in parent snapshots
+- Kopia: uses temporary snapshot for consistency, doesn't back up nested subvolumes
+
+## Important Files
+
+- `common/global/backup.nix` - Kopia backup configuration
+- `common/nfs-services-server.nix` - NFS server role (check hosts for which imports this)
+- `common/nfs-services-standby.nix` - NFS standby role (check hosts for which imports this)
+- `flake.nix` - Host definitions, nixpkgs inputs
+
+---
+*Auto-generated reference for Claude Code. Keep concise. Update when architecture changes.*

README.md

@@ -0,0 +1,196 @@
+# alo-cluster NixOS Configuration
+
+This repository contains the NixOS configuration for a distributed cluster of machines managed as a unified flake.
+
+## Architecture Overview
+
+The configuration uses a **layered profile system** that enables code reuse while maintaining clear separation of concerns:
+
+```
+minimal-node          # Base system (SSH, users, boot, impermanence)
+    ↓
+cluster-node          # Cluster services (Consul, GlusterFS, CIFS, encryption)
+    ↓
+server-node           # Server workloads (future: MySQL, PostgreSQL)
+    ↓
+workstation-node      # Development tools (Docker, deploy-rs, emulation)
+    ↓
+desktop-node          # GUI environment (Hyprland, Pipewire, fonts)
+```
+
+Each layer extends the previous one, inheriting all configurations. Hosts select a profile level that matches their role.
+
+### Special Node Types
+
+- **compute-node**: Cluster + Nomad worker (container orchestration)
+
+## Directory Structure
+
+```
+.
+├── flake.nix                 # Main flake definition with all hosts
+├── common/
+│   ├── global/               # Global configs applied to all systems
+│   │   ├── console.nix       # Linux console colors (Solarized Dark)
+│   │   ├── locale.nix        # Timezone and locale settings
+│   │   └── nix.nix           # Nix daemon and flake configuration
+│   ├── minimal-node.nix      # Base layer: SSH, users, boot, impermanence
+│   ├── cluster-node.nix      # Cluster layer: Consul, GlusterFS, CIFS
+│   ├── server-node.nix       # Server layer: bare metal services (future)
+│   ├── workstation-node.nix  # Workstation layer: dev tools
+│   ├── desktop-node.nix      # Desktop layer: GUI environment
+│   ├── compute-node.nix      # Nomad worker profile
+│   └── [feature modules]     # Individual feature configs
+├── hosts/
+│   ├── c1/                   # Compute node 1
+│   ├── c2/                   # Compute node 2
+│   ├── c3/                   # Compute node 3
+│   ├── alo-cloud-1/          # Cloud VPS
+│   ├── chilly/               # Server node
+│   ├── zippy/                # Workstation node
+│   └── sparky/               # Desktop node
+├── home/
+│   ├── default.nix           # Home-manager entry point
+│   ├── profiles/             # Per-profile package sets
+│   │   ├── server.nix
+│   │   ├── workstation.nix
+│   │   └── desktop.nix
+│   ├── programs/             # Per-profile program configurations
+│   │   ├── server.nix        # CLI tools (fish, tmux, git, nixvim)
+│   │   ├── workstation.nix   # + dev tools
+│   │   └── desktop.nix       # + Hyprland, wofi
+│   └── common/               # Shared home-manager configs
+└── services/                 # Nomad job definitions (not NixOS)
+```
+
+## Profile System
+
+### System Profiles
+
+Profiles are automatically applied based on the `mkHost` call in `flake.nix`:
+
+```nix
+# Example: Desktop profile includes all layers up to desktop-node
+mkHost "x86_64-linux" "desktop" [
+  ./hosts/sparky
+];
+```
+
+**Available profiles:**
+- `"server"` → minimal + cluster + server
+- `"workstation"` → minimal + cluster + server + workstation
+- `"desktop"` → minimal + cluster + server + workstation + desktop
+
+### Home-Manager Profiles
+
+Home-manager automatically inherits the same profile as the system, configured in `home/default.nix`:
+
+```nix
+imports = [ ./programs/${profile}.nix ];
+home.packages = profilePkgs.${profile};
+```
+
+This ensures system and user configurations stay synchronized.
+
+## Host Definitions
+
+### Current Hosts
+
+| Host | Profile | Role | Hardware |
+|------|---------|------|----------|
+| **c1, c2, c3** | compute-node | Nomad workers | Bare metal servers |
+| **alo-cloud-1** | minimal | Reverse proxy (Traefik) | Cloud VPS |
+| **chilly** | server | Home Assistant in a VM | Bare metal server |
+| **zippy** | workstation | Development machine, server | Bare metal server |
+| **sparky** | desktop | Desktop environment | Bare metal desktop |
+
+### Adding a New Host
+
+1. Create host directory:
+   ```bash
+   mkdir -p hosts/newhost
+   ```
+
+2. Create `hosts/newhost/default.nix`:
+   ```nix
+   { config, pkgs, ... }:
+   {
+     imports = [
+       ../../common/encrypted-btrfs-layout.nix  # or your layout
+       ../../common/global
+       ./hardware.nix
+     ];
+
+     networking.hostName = "newhost";
+     # Host-specific configs here
+   }
+   ```
+
+3. Generate hardware config:
+   ```bash
+   nixos-generate-config --show-hardware-config > hosts/newhost/hardware.nix
+   ```
+
+4. Add to `flake.nix`:
+   ```nix
+   newhost = mkHost "x86_64-linux" "workstation" [
+     ./hosts/newhost
+   ];
+   ```
+
+## Deployment
+
+### Using deploy-rs
+
+Deploy to specific host:
+```bash
+deploy -s '.#sparky'
+```
+
+Deploy to all hosts:
+```bash
+deploy
+```
+
+Deploy with detailed logging:
+```bash
+deploy -s '.#sparky' -- --show-trace
+```
+
+### Manual Deployment
+
+```bash
+nixos-rebuild switch --flake .#sparky --target-host sparky
+```
+
+## Key Features
+
+### Impermanence
+All hosts use tmpfs root with selective persistence. Persistent paths configured per-host in `persistence.directories` and `persistence.files`.
+
+### Unattended Encryption
+Cluster nodes support automatic unlocking via Tailscale network using `common/unattended-encryption.nix`.
+
+### Cluster Services
+- **Consul**: Service discovery and distributed KV store
+- **GlusterFS**: Distributed filesystem client
+- **CIFS/Samba**: Network file sharing
+
+### Desktop Environment (sparky only)
+- **Hyprland**: Wayland compositor with CapsLock→Super remapping
+- **wofi**: Application launcher (Super+D)
+- **foot**: Terminal emulator (Super+Q)
+- **greetd/tuigreet**: Login manager with console option
+
+### Development Tools (workstation/desktop)
+- Docker with rootless mode
+- deploy-rs for NixOS deployments
+- ARM emulation via binfmt
+- Full NixVim configuration
+
+## Future Work
+
+- Migrate Nomad services (MySQL, PostgreSQL) to bare NixOS services under `server-node.nix`
+- Add monitoring stack (Prometheus, Grafana)
+- Document Tailscale key rotation process
+- Add automated testing for configuration changes

common/base-node.nix

@@ -1,13 +0,0 @@
-{ pkgs, ... }:
-{
-  imports = [
-    ./cifs-client.nix
-    ./consul.nix
-    ./glusterfs-client.nix
-    ./impermanence.nix
-    ./sshd.nix
-    ./user-ppetru.nix
-    ./unattended-encryption.nix
-    ./systemd-boot.nix
-  ];
-}

common/binary-cache-server.nix

@@ -0,0 +1,41 @@
+{ config, pkgs, lib, ... }:
+{
+  # Binary cache proxy using ncps (Nix Cache Proxy Server)
+  # Transparently caches packages from cache.nixos.org for faster LAN access
+  #
+  # How it works:
+  # - Acts as HTTP proxy for cache.nixos.org
+  # - Caches packages on first request
+  # - Subsequent requests served from local disk (LAN speed)
+  # - No signing needed (packages already signed by upstream)
+  # - Automatic fallback to cache.nixos.org if this host is down
+  #
+  # Setup:
+  # 1. Deploy this host
+  # 2. Deploy all other hosts (they're already configured to use this)
+  # 3. Cache warms up automatically on first use
+
+  services.ncps = {
+    enable = true;
+    cache = {
+      hostName = config.networking.hostName;
+      # NOTE: These paths are hardcoded to /persist (not using config.custom.impermanence.persistPath)
+      # This is acceptable since this service is only enabled on btrfs-based hosts
+      dataPath = "/persist/ncps/data";
+      tempPath = "/persist/ncps/tmp";
+      databaseURL = "sqlite:/persist/ncps/db/db.sqlite";
+      maxSize = "300G";  # Adjust based on available disk space
+      lru.schedule = "0 3 * * *";  # Clean up daily at 3 AM if over maxSize
+    };
+    server.addr = "0.0.0.0:8501";
+    upstream = {
+      caches = [ "https://cache.nixos.org" ];
+      publicKeys = [
+        "cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
+      ];
+    };
+  };
+
+  # Open firewall for LAN access
+  networking.firewall.allowedTCPPorts = [ 8501 ];
+}

common/cifs-client.nix

@@ -1,7 +1,7 @@
 { pkgs, ... }:
 let
   # this line prevents hanging on network split
-  automount_opts = "x-systemd.automount,noauto,x-systemd.idle-timeout=60,x-systemd.device-timeout=5s,x-systemd.mount-timeout=5s";
+  automount_opts = "x-systemd.automount,noauto,x-systemd.idle-timeout=60,x-systemd.mount-timeout=5s,nobrl";
 in
 {
   environment.systemPackages = [ pkgs.cifs-utils ];
@@ -17,12 +17,12 @@ in
   fileSystems."/data/media" = {
     device = "//fractal/media";
     fsType = "cifs";
-    options = [ "${automount_opts},credentials=/etc/nixos/smb-secrets" ];
+    options = [ "uid=1000,${automount_opts},credentials=/etc/nixos/smb-secrets" ];
   };
 
   fileSystems."/data/shared" = {
     device = "//fractal/shared";
     fsType = "cifs";
-    options = [ "${automount_opts},credentials=/etc/nixos/smb-secrets" ];
+    options = [ "uid=1000,${automount_opts},credentials=/etc/nixos/smb-secrets" ];
   };
 }

common/cloud-node.nix

@@ -1,10 +0,0 @@
-{ pkgs, ... }:
-{
-  imports = [
-    ./consul.nix
-    ./impermanence.nix
-    ./sshd.nix
-    ./user-ppetru.nix
-    ./systemd-boot.nix
-  ];
-}

common/cluster-member.nix

@@ -0,0 +1,24 @@
+{ pkgs, lib, config, ... }:
+{
+  # Cluster node configuration
+  # Extends minimal-node with cluster-specific services (Consul, GlusterFS, CIFS, NFS)
+  # Used by: compute nodes (c1, c2, c3)
+  imports = [
+    ./minimal-node.nix
+    ./unattended-encryption.nix
+    ./cifs-client.nix
+    ./consul.nix
+    ./nfs-services-client.nix  # New: NFS client for /data/services
+  ];
+
+  options.networking.cluster.primaryInterface = lib.mkOption {
+    type = lib.types.str;
+    default = "eno1";
+    description = "Primary network interface for cluster communication (Consul, NFS, etc.)";
+  };
+
+  config = {
+    # Wait for primary interface to be routable before considering network online
+    systemd.network.wait-online.extraArgs = [ "--interface=${config.networking.cluster.primaryInterface}:routable" ];
+  };
+}

common/compute-node.nix

@@ -1,9 +0,0 @@
-{ pkgs, ... }:
-{
-  imports = [
-    ./base-node.nix
-    ./glusterfs.nix
-    ./nomad.nix
-    ./syncthing-data.nix
-  ];
-}

common/consul.nix

@@ -1,44 +1,47 @@
-{ pkgs, config, ... }:
+{ pkgs, config, lib, ... }:
 let
   servers = [
     "c1"
     "c2"
     "c3"
   ];
-  server_enabled = builtins.elem config.networking.hostName servers;
 in
 {
-  services.consul = {
+  options.clusterRole.consulServer = lib.mkEnableOption "Consul server mode";
-    enable = true;
+
-    webUi = true;
+  config = {
-    interface.advertise = "eno1";
+    services.consul = {
-    extraConfig = {
+      enable = true;
-      client_addr = "0.0.0.0";
+      webUi = true;
-      datacenter = "alo";
+      interface.advertise = config.networking.cluster.primaryInterface;
-      server = server_enabled;
+      extraConfig = {
-      bootstrap_expect = if server_enabled then (builtins.length servers + 2) / 2 else null;
+        client_addr = "0.0.0.0";
-      retry_join = builtins.filter (elem: elem != config.networking.hostName) servers;
+        datacenter = "alo";
+        server = config.clusterRole.consulServer;
+        bootstrap_expect = if config.clusterRole.consulServer then (builtins.length servers + 2) / 2 else null;
+        retry_join = builtins.filter (elem: elem != config.networking.hostName) servers;
       telemetry = {
         prometheus_retention_time = "24h";
         disable_hostname = true;
       };
     };
-  };
+    };
 
-  environment.persistence."/persist".directories = [ "/var/lib/consul" ];
+    environment.persistence.${config.custom.impermanence.persistPath}.directories = [ "/var/lib/consul" ];
 
-  networking.firewall = {
+    networking.firewall = {
-    allowedTCPPorts = [
+      allowedTCPPorts = [
-      8600
+        8600
-      8500
+        8500
-      8301
+        8301
-      8302
+        8302
-      8300
+        8300
-    ];
+      ];
-    allowedUDPPorts = [
+      allowedUDPPorts = [
-      8600
+        8600
-      8301
+        8301
-      8302
+        8302
-    ];
+      ];
+    };
   };
 }

common/container-node.nix

@@ -1,11 +0,0 @@
-{ lib, ... }:
-{
-  imports = [
-    ./impermanence.nix # TODO: find a way to avoid needing this here
-  ];
-
-  boot.isContainer = true;
-  custom.impermanence.enable = false;
-  custom.tailscale.enable = false;
-  networking.useDHCP = lib.mkForce false;
-}

common/desktop-node.nix

@@ -0,0 +1,51 @@
+{ pkgs, lib, ... }:
+{
+  # Desktop profile: Graphical desktop with Hyprland
+  # Extends workstation-node with desktop environment
+  imports = [
+    ./workstation-node.nix
+  ];
+
+  # omarchy-nix enables NetworkManager, but we use useDHCP globally
+  networking.networkmanager.enable = lib.mkForce false;
+
+  # Enable Hyprland (Wayland compositor)
+  programs.hyprland = {
+    enable = true;
+    xwayland.enable = true; # For compatibility with X11 apps if needed
+  };
+
+  # Essential desktop services
+  services.dbus.enable = true;
+
+  # polkit for privilege escalation
+  security.polkit.enable = true;
+
+  # Enable sound with pipewire
+  security.rtkit.enable = true;
+  services.pipewire = {
+    enable = true;
+    alsa.enable = true;
+    alsa.support32Bit = true;
+    pulse.enable = true;
+  };
+
+  # Fonts
+  fonts.packages = with pkgs; [
+    noto-fonts
+    noto-fonts-cjk-sans
+    noto-fonts-emoji
+    liberation_ttf
+    fira-code
+    fira-code-symbols
+  ];
+
+  # Environment variables for Wayland
+  environment.sessionVariables = {
+    NIXOS_OZONE_WL = "1"; # Hint electron apps to use Wayland
+  };
+
+  environment.systemPackages = with pkgs; [
+    prusa-slicer
+  ];
+}

common/ethereum.nix

@@ -0,0 +1,18 @@
+{ config, pkgs, ... }:
+{
+  sops.secrets.lighthouse_jwt = {
+    sopsFile = ./../secrets/${config.networking.hostName}.yaml;
+  };
+  services.ethereum.lighthouse-beacon.mainnet = {
+    enable = true;
+    #package = pkgs.unstable.lighthouse;
+    args = {
+      execution-endpoint = "http://eth1:8551";
+      execution-jwt = config.sops.secrets.lighthouse_jwt.path;
+      checkpoint-sync-url = "https://beaconstate.info";
+    };
+  };
+  environment.persistence.${config.custom.impermanence.persistPath}.directories = [
+    "/var/lib/private/lighthouse-mainnet"
+  ];
+}

common/global/backup.nix

@@ -6,8 +6,7 @@ let
   btrfs = "${btrfsPkg}/bin/btrfs";
   snapshotBackup = pkgs.writeScript "kopia-snapshot-backup" (builtins.readFile ./kopia-snapshot-backup.sh);
   backupScript = pkgs.writeShellScript "backup-persist" ''
-      target_path="/persist"
+      target_path="${config.custom.impermanence.persistPath}"
-      snapshot_path="$target_path/kopia-backup-snapshot"
       KOPIA_CHECK_FOR_UPDATES=false
 
       ${kopia} repository connect server \
@@ -16,14 +15,29 @@ let
         -p "$(cat ${config.sops.secrets.kopia.path})" \
       || exit 1
 
-      [ -e "$snapshot_path" ] && ${btrfs} subvolume delete "$snapshot_path"
+      # Check if target_path is on btrfs filesystem
+      fs_type=$(stat -f -c %T "$target_path")
 
-      ${btrfs} subvolume snapshot -r "$target_path" "$snapshot_path"
+      if [ "$fs_type" = "btrfs" ]; then
+        # On btrfs: use snapshot for consistency
+        snapshot_path="$target_path/kopia-backup-snapshot"
+        [ -e "$snapshot_path" ] && ${btrfs} subvolume delete "$snapshot_path"
+        ${btrfs} subvolume snapshot -r "$target_path" "$snapshot_path"
 
-      # --no-send-snapshot-path due to https://github.com/kopia/kopia/issues/4402
+        # --no-send-snapshot-path due to https://github.com/kopia/kopia/issues/4402
-      ${kopia} snapshot create --no-send-snapshot-report --override-source "$target_path" -- "$snapshot_path"
+        # Exclude btrfs replication snapshots (they appear as empty dirs in the snapshot anyway)
+        ${kopia} snapshot create --no-send-snapshot-report --override-source "$target_path" \
+          --ignore "services@*" \
+          --ignore "services-standby/services@*" \
+          -- "$snapshot_path"
+
+        ${btrfs} subvolume delete "$snapshot_path"
+      else
+        # On non-btrfs (e.g., ext4): backup directly without snapshot
+        ${kopia} snapshot create --no-send-snapshot-report --override-source "$target_path" \
+          -- "$target_path"
+      fi
 
-      ${btrfs} subvolume delete "$snapshot_path"
       ${kopia} repository disconnect
   '';
 in
@@ -37,7 +51,7 @@ in
     services."backup-persist" = {
       description = "Backup persistent data with Kopia";
       serviceConfig = {
-        type = "oneshot";
+        Type = "oneshot";
         User = "root";
         ExecStart = "${backupScript}";
       };

common/global/console.nix

@@ -0,0 +1,44 @@
+{
+  # Configure Linux console (VT/framebuffer) colors to use Solarized Dark theme
+  # This affects the text-mode console accessed via Ctrl+Alt+F1-F6 or when booting without graphics
+  #
+  # Solarized Dark color scheme by Ethan Schoonover
+  # https://ethanschoonover.com/solarized/
+  #
+  # Color mapping:
+  # 0  = black        -> base02  (#073642)
+  # 1  = red          -> red     (#dc322f)
+  # 2  = green        -> green   (#859900)
+  # 3  = yellow       -> yellow  (#b58900)
+  # 4  = blue         -> blue    (#268bd2)
+  # 5  = magenta      -> magenta (#d33682)
+  # 6  = cyan         -> cyan    (#2aa198)
+  # 7  = white        -> base2   (#eee8d5)
+  # 8  = br_black     -> base03  (#002b36) - background
+  # 9  = br_red       -> orange  (#cb4b16)
+  # 10 = br_green     -> base01  (#586e75)
+  # 11 = br_yellow    -> base00  (#657b83)
+  # 12 = br_blue      -> base0   (#839496)
+  # 13 = br_magenta   -> violet  (#6c71c4)
+  # 14 = br_cyan      -> base1   (#93a1a1)
+  # 15 = br_white     -> base3   (#fdf6e3)
+
+  console.colors = [
+    "073642" # 0:  black (base02)
+    "dc322f" # 1:  red
+    "859900" # 2:  green
+    "b58900" # 3:  yellow
+    "268bd2" # 4:  blue
+    "d33682" # 5:  magenta
+    "2aa198" # 6:  cyan
+    "eee8d5" # 7:  white (base2)
+    "002b36" # 8:  bright black (base03 - Solarized Dark background)
+    "cb4b16" # 9:  bright red (orange)
+    "586e75" # 10: bright green (base01)
+    "657b83" # 11: bright yellow (base00)
+    "839496" # 12: bright blue (base0)
+    "6c71c4" # 13: bright magenta (violet)
+    "93a1a1" # 14: bright cyan (base1)
+    "fdf6e3" # 15: bright white (base3)
+  ];
+}

common/global/default.nix

@@ -2,8 +2,10 @@
 {
   imports = [
     ./backup.nix
+    ./console.nix
     ./cpufreq.nix
     ./flakes.nix
+    ./impermanence-options.nix
     ./kernel.nix
     ./locale.nix
     ./network.nix

common/global/impermanence-options.nix

@@ -0,0 +1,14 @@
+{
+  lib,
+  ...
+}:
+{
+  # Define impermanence options that need to be available to all modules
+  # The actual impermanence implementation is in common/impermanence.nix or common/impermanence-tmpfs.nix
+
+  options.custom.impermanence.persistPath = lib.mkOption {
+    type = lib.types.str;
+    default = "/persist";
+    description = "Path where persistent data is stored (e.g., /persist for btrfs, /nix/persist for tmpfs)";
+  };
+}

common/global/network.nix

@@ -1,3 +1,4 @@
+{ lib, config, ... }:
 {
   networking = {
     useDHCP = true;
@@ -9,7 +10,7 @@
     '';
   };
 
-  environment.persistence."/persist" = {
+  environment.persistence.${config.custom.impermanence.persistPath} = {
     directories = [ "/var/db/dhcpcd" ];
   };
 }

common/global/nix.nix

@@ -1,8 +1,30 @@
 {
-  nix.settings.trusted-users = [
+  nix.settings = {
-    "root"
+    trusted-users = [
-    "@wheel"
+      "root"
-  ];
+      "@wheel"
+    ];
+
+    # Binary cache configuration
+    # c3 runs ncps (Nix Cache Proxy Server) that caches cache.nixos.org
+    # Falls back to cache.nixos.org if c3 is unreachable
+    substituters = [
+      "http://c3.mule-stork.ts.net:8501"  # Local ncps cache proxy on c3
+      "https://cache.nixos.org"
+    ];
+    trusted-public-keys = [
+      "cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
+      "c3:sI3l1RN80xdehzXLA8u2P6352B0SyRPs2XiYy/YWYro="
+    ];
+
+    # Performance tuning
+    max-jobs = "auto";           # Use all cores for parallel builds
+    cores = 0;                   # Each build can use all cores
+    max-substitution-jobs = 16;  # Faster fetching from caches
+    http-connections = 25;       # More parallel downloads
+    download-attempts = 3;       # Retry failed downloads
+  };
+
   nix.gc = {
     automatic = true;
     dates = "weekly";

common/global/packages.nix

@@ -3,6 +3,7 @@
   environment.systemPackages = with pkgs; [
     age
     file
+    killall
     lm_sensors # TODO: this shouldn't be installed on cloud nodes
     nodejs_20 # TODO: this is for one job on nomad, it should just be a dependency there
     neovim

common/global/sops.nix

@@ -3,8 +3,7 @@
   sops = {
     # sometimes the impermanence bind mount is stopped when sops needs these
     age.sshKeyPaths = [
-      "/persist/etc/ssh/ssh_host_ed25519_key"
+      "${config.custom.impermanence.persistPath}/etc/ssh/ssh_host_ed25519_key"
-      "/persist/etc/ssh/ssh_host_rsa_key"
     ];
     defaultSopsFile = ./../../secrets/common.yaml;
     secrets = {

common/global/tailscale.nix

@@ -22,6 +22,6 @@ in
   config = mkIf cfg.enable {
     services.tailscaleAutoconnect.enable = true;
     services.tailscale.package = pkgs.unstable.tailscale;
-    environment.persistence."/persist".directories = [ "/var/lib/tailscale" ];
+    environment.persistence.${config.custom.impermanence.persistPath}.directories = [ "/var/lib/tailscale" ];
   };
 }

common/glusterfs-client.nix

@@ -1,13 +0,0 @@
-{ pkgs, ... }:
-{
-  environment.systemPackages = [ pkgs.glusterfs ];
-
-  fileSystems."/data/compute" = {
-    device = "192.168.1.71:/compute";
-    fsType = "glusterfs";
-    options = [
-      "backup-volfile-servers=192.168.1.72:192.168.1.73"
-      "_netdev"
-    ];
-  };
-}

common/glusterfs.nix

@@ -1,24 +0,0 @@
-{
-  pkgs,
-  config,
-  lib,
-  ...
-}:
-{
-  services.glusterfs = {
-    enable = true;
-  };
-
-  environment.persistence."/persist".directories = [ "/var/lib/glusterd" ];
-
-  # TODO: each volume needs its own port starting at 49152
-  networking.firewall.allowedTCPPorts = [
-    24007
-    24008
-    24009
-    49152
-    49153
-    49154
-    49155
-  ];
-}

common/impermanence-common.nix

@@ -0,0 +1,30 @@
+{
+  lib,
+  config,
+  ...
+}:
+{
+  # Common impermanence configuration shared by both btrfs and tmpfs variants
+  # This module should be imported by impermanence.nix or impermanence-tmpfs.nix
+  # The option custom.impermanence.persistPath is defined in common/global/impermanence-options.nix
+
+  environment.persistence.${config.custom.impermanence.persistPath} = {
+    directories = [
+      "/var/lib/nixos"
+      "/home"
+    ];
+    files = [
+      "/etc/machine-id"
+      "/etc/ssh/ssh_host_ed25519_key"
+      "/etc/ssh/ssh_host_ed25519_key.pub"
+      "/etc/ssh/ssh_host_rsa_key"
+      "/etc/ssh/ssh_host_rsa_key.pub"
+    ];
+  };
+
+  users.mutableUsers = false;
+
+  security.sudo.extraConfig = ''
+    Defaults lecture = never
+  '';
+}

common/impermanence-tmpfs.nix

@@ -0,0 +1,30 @@
+{
+  lib,
+  config,
+  ...
+}:
+{
+  # Impermanence configuration for tmpfs root filesystem
+  # Used for systems with tmpfs root (e.g., Raspberry Pi with SD card)
+  # Root is in-memory and wiped on every boot
+  # Persistent data is stored in /nix/persist (directory on the /nix partition)
+
+  # Import common impermanence configuration
+  imports = [ ./impermanence-common.nix ];
+
+  config = {
+    # Use /nix/persist for tmpfs-based impermanence
+    custom.impermanence.persistPath = "/nix/persist";
+
+    # tmpfs root filesystem
+    fileSystems."/" = {
+      device = "none";
+      fsType = "tmpfs";
+      options = [
+        "defaults"
+        "size=2G"
+        "mode=755"
+      ];
+    };
+  };
+}

common/impermanence.nix

@@ -1,6 +1,5 @@
 {
   pkgs,
-  inputs,
   lib,
   config,
   ...
@@ -9,28 +8,22 @@ let
   cfg = config.custom.impermanence;
 in
 {
+  # Import common impermanence configuration
+  imports = [ ./impermanence-common.nix ];
+
   options.custom.impermanence = {
     enable = lib.mkOption {
       type = lib.types.bool;
       default = true;
-      description = "Enable impermanent root fs";
+      description = "Enable impermanent root fs with btrfs subvolume rollback";
     };
   };
 
   config = lib.mkIf cfg.enable {
-    environment.persistence = {
+    # Use /persist for btrfs-based impermanence
-      "/persist" = {
+    custom.impermanence.persistPath = "/persist";
-        directories = [ "/var/lib/nixos" ];
-        files = [
-          "/etc/machine-id"
-          "/etc/ssh/ssh_host_ed25519_key"
-          "/etc/ssh/ssh_host_ed25519_key.pub"
-          "/etc/ssh/ssh_host_rsa_key"
-          "/etc/ssh/ssh_host_rsa_key.pub"
-        ];
-      };
-    };
 
+    # Btrfs-specific filesystem options
     fileSystems."/".options = [
       "compress=zstd"
       "noatime"
@@ -50,21 +43,11 @@ in
     ];
     fileSystems."/var/log".neededForBoot = true;
 
-    users.mutableUsers = false;
+    # Btrfs subvolume rollback at each boot
-
-    # rollback results in sudo lectures after each reboot
-    security.sudo.extraConfig = ''
-      Defaults lecture = never
-    '';
-
-    # needed for allowOther in the home-manager impermanence config
-    programs.fuse.userAllowOther = true;
-
-    # reset / at each boot
     # Note `lib.mkBefore` is used instead of `lib.mkAfter` here.
     boot.initrd.postDeviceCommands = pkgs.lib.mkBefore ''
       mkdir /mnt
-      mount /dev/mapper/luksroot /mnt
+      mount ${config.fileSystems."/".device} /mnt
       if [[ -e /mnt/root ]]; then
           mkdir -p /mnt/old_roots
           timestamp=$(date --date="@$(stat -c %Y /mnt/root)" "+%Y-%m-%-d_%H:%M:%S")

common/minimal-node.nix

@@ -0,0 +1,13 @@
+{ pkgs, ... }:
+{
+  # Minimal base configuration for all NixOS systems
+  # Provides: SSH access, user management, boot, impermanence
+  # Note: unattended-encryption is NOT included by default - add it explicitly where needed
+  imports = [
+    ./impermanence.nix
+    ./resource-limits.nix
+    ./sshd.nix
+    ./user-ppetru.nix
+    ./systemd-boot.nix
+  ];
+}

common/nfs-services-client.nix

@@ -0,0 +1,29 @@
+{ pkgs, ... }:
+{
+  # NFS client for /data/services
+  # Mounts from data-services.service.consul (Consul DNS for automatic failover)
+  # The NFS server registers itself in Consul, so this will automatically
+  # point to whichever host is currently running the NFS server
+  #
+  # Uses persistent mount (not automount) with nofail to prevent blocking boot.
+  # The mount is established at boot time and persists - no auto-unmount.
+  # This prevents issues with Docker bind mounts seeing empty automount stubs.
+
+  imports = [
+    ./wait-for-dns-ready.nix
+  ];
+
+  fileSystems."/data/services" = {
+    device = "data-services.service.consul:/persist/services";
+    fsType = "nfs";
+    options = [
+      "nofail"                      # Don't block boot if mount fails
+      "x-systemd.mount-timeout=30s" # Timeout for mount attempts
+      "x-systemd.after=wait-for-dns-ready.service" # Wait for DNS to actually work
+      "_netdev"                     # Network filesystem (wait for network)
+    ];
+  };
+
+  # Ensure NFS client packages are available
+  environment.systemPackages = [ pkgs.nfs-utils ];
+}

common/nfs-services-server.nix

@@ -0,0 +1,201 @@
+{ config, lib, pkgs, ... }:
+
+let
+  cfg = config.nfsServicesServer;
+in
+{
+  options.nfsServicesServer = {
+    enable = lib.mkEnableOption "NFS services server" // { default = true; };
+
+    standbys = lib.mkOption {
+      type = lib.types.listOf lib.types.str;
+      default = [];
+      description = ''
+        List of standby hostnames to replicate to (e.g. ["c1"]).
+
+        Requires one-time setup on the NFS server:
+          sudo mkdir -p /persist/root/.ssh
+          sudo ssh-keygen -t ed25519 -f /persist/root/.ssh/btrfs-replication -N "" -C "root@$(hostname)-replication"
+
+        Then add the public key to each standby's nfsServicesStandby.replicationKeys option.
+      '';
+    };
+  };
+
+  config = lib.mkIf cfg.enable {
+    # Persist root SSH directory for replication key
+    environment.persistence.${config.custom.impermanence.persistPath} = {
+      directories = [
+        "/root/.ssh"
+      ];
+    };
+
+    # Bind mount /persist/services to /data/services for local access
+    # This makes the path consistent with NFS clients
+    # Use mkForce to override the NFS client mount from cluster-node.nix
+    fileSystems."/data/services" = lib.mkForce {
+      device = "/persist/services";
+      fsType = "none";
+      options = [ "bind" ];
+    };
+
+    # Nomad node metadata: mark this as the primary storage node
+    # Jobs can constrain to ${meta.storage_role} = "primary"
+    services.nomad.settings.client.meta = {
+      storage_role = "primary";
+    };
+
+    # NFS server configuration
+    services.nfs.server = {
+      enable = true;
+      exports = ''
+        /persist/services 192.168.1.0/24(rw,sync,no_subtree_check,no_root_squash)
+      '';
+    };
+
+    # Consul service registration for NFS
+    services.consul.extraConfig.services = [{
+      name = "data-services";
+      port = 2049;
+      checks = [{
+        tcp = "localhost:2049";
+        interval = "30s";
+      }];
+    }];
+
+    # Firewall for NFS
+    networking.firewall.allowedTCPPorts = [ 2049 111 20048 ];
+    networking.firewall.allowedUDPPorts = [ 2049 111 20048 ];
+
+    # systemd services: NFS server split-brain check + replication services
+    systemd.services = lib.mkMerge ([
+      # Safety check: prevent split-brain by ensuring no other NFS server is active
+      {
+        nfs-server = {
+          preStart = ''
+            # Wait for Consul to be available
+            for i in {1..30}; do
+              if ${pkgs.netcat}/bin/nc -z localhost 8600; then
+                break
+              fi
+              echo "Waiting for Consul DNS... ($i/30)"
+              sleep 1
+            done
+
+            # Check if another NFS server is already registered in Consul
+            CURRENT_SERVER=$(${pkgs.dnsutils}/bin/dig +short @localhost -p 8600 data-services.service.consul | head -1 || true)
+            MY_IP=$(${pkgs.iproute2}/bin/ip -4 addr show | ${pkgs.gnugrep}/bin/grep -oP '(?<=inet\s)\d+(\.\d+){3}' | ${pkgs.gnugrep}/bin/grep -v '^127\.' | head -1)
+
+            if [ -n "$CURRENT_SERVER" ] && [ "$CURRENT_SERVER" != "$MY_IP" ]; then
+              echo "ERROR: Another NFS server is already active at $CURRENT_SERVER"
+              echo "This host ($MY_IP) is configured as NFS server but should be standby."
+              echo "To fix:"
+              echo "  1. If this is intentional (failback), first demote the other server"
+              echo "  2. Update this host's config to use nfs-services-standby.nix instead"
+              echo "  3. Sync data from active server before promoting this host"
+              exit 1
+            fi
+
+            echo "NFS server startup check passed (no other active server found)"
+          '';
+        };
+      }
+    ] ++ (lib.forEach cfg.standbys (standby: {
+        "replicate-services-to-${standby}" = {
+          description = "Replicate /persist/services to ${standby}";
+          path = [ pkgs.btrfs-progs pkgs.openssh pkgs.coreutils pkgs.findutils pkgs.gnugrep pkgs.curl ];
+
+          script = ''
+            set -euo pipefail
+
+            START_TIME=$(date +%s)
+            REPLICATION_SUCCESS=0
+
+            SSH_KEY="/persist/root/.ssh/btrfs-replication"
+            if [ ! -f "$SSH_KEY" ]; then
+              echo "ERROR: SSH key not found at $SSH_KEY"
+              echo "Run: sudo ssh-keygen -t ed25519 -f $SSH_KEY -N \"\" -C \"root@$(hostname)-replication\""
+              exit 1
+            fi
+
+            SNAPSHOT_NAME="services@$(date +%Y%m%d-%H%M%S)"
+            SNAPSHOT_PATH="/persist/$SNAPSHOT_NAME"
+
+            # Create readonly snapshot
+            btrfs subvolume snapshot -r /persist/services "$SNAPSHOT_PATH"
+
+            # Find previous snapshot on sender (sort by name since readonly snapshots have same mtime)
+            # Use -d to list directories only, not their contents
+            PREV_LOCAL=$(ls -1d /persist/services@* 2>/dev/null | grep -v "^$SNAPSHOT_PATH$" | sort -r | head -1 || true)
+
+            # Try incremental send if we have a parent, fall back to full send if it fails
+            if [ -n "$PREV_LOCAL" ]; then
+              echo "Attempting incremental send from $(basename $PREV_LOCAL) to ${standby}"
+
+              # Try incremental send, if it fails (e.g., parent missing on receiver), fall back to full
+              # Use -c to help with broken Received UUID chains
+              if btrfs send -p "$PREV_LOCAL" -c "$PREV_LOCAL" "$SNAPSHOT_PATH" | \
+                 ssh -i "$SSH_KEY" -o StrictHostKeyChecking=accept-new root@${standby} \
+                 "btrfs receive /persist/services-standby"; then
+                echo "Incremental send completed successfully"
+                REPLICATION_SUCCESS=1
+              else
+                echo "Incremental send failed (likely missing parent on receiver), falling back to full send"
+                # Plain full send without clone source (receiver may have no snapshots)
+                btrfs send "$SNAPSHOT_PATH" | \
+                  ssh -i "$SSH_KEY" -o StrictHostKeyChecking=accept-new root@${standby} \
+                  "btrfs receive /persist/services-standby"
+                REPLICATION_SUCCESS=1
+              fi
+            else
+              # First snapshot, do full send
+              echo "Full send to ${standby} (first snapshot)"
+              btrfs send "$SNAPSHOT_PATH" | \
+                ssh -i "$SSH_KEY" -o StrictHostKeyChecking=accept-new root@${standby} \
+                "btrfs receive /persist/services-standby"
+              REPLICATION_SUCCESS=1
+            fi
+
+            # Cleanup old snapshots on sender (keep last 10 snapshots, sorted by name/timestamp)
+            ls -1d /persist/services@* 2>/dev/null | sort | head -n -10 | xargs -r btrfs subvolume delete
+
+            # Calculate metrics
+            END_TIME=$(date +%s)
+            DURATION=$((END_TIME - START_TIME))
+            SNAPSHOT_COUNT=$(ls -1d /persist/services@* 2>/dev/null | wc -l)
+
+            # Push metrics to Prometheus pushgateway
+            cat <<METRICS | curl -s --data-binary @- http://pushgateway.service.consul:9091/metrics/job/nfs_replication/instance/${standby} || true
+            # TYPE nfs_replication_last_success_timestamp gauge
+            nfs_replication_last_success_timestamp $END_TIME
+            # TYPE nfs_replication_duration_seconds gauge
+            nfs_replication_duration_seconds $DURATION
+            # TYPE nfs_replication_snapshot_count gauge
+            nfs_replication_snapshot_count $SNAPSHOT_COUNT
+            # TYPE nfs_replication_success gauge
+            nfs_replication_success $REPLICATION_SUCCESS
+            METRICS
+          '';
+
+          serviceConfig = {
+            Type = "oneshot";
+            User = "root";
+          };
+        };
+      }))
+    );
+
+    systemd.timers = lib.mkMerge (
+      lib.forEach cfg.standbys (standby: {
+        "replicate-services-to-${standby}" = {
+          description = "Timer for replicating /persist/services to ${standby}";
+          wantedBy = [ "timers.target" ];
+          timerConfig = {
+            OnCalendar = "*:0/5";  # Every 5 minutes
+            Persistent = true;
+          };
+        };
+      })
+    );
+  };
+}

common/nfs-services-standby.nix

@@ -0,0 +1,79 @@
+{ config, lib, pkgs, ... }:
+
+let
+  cfg = config.nfsServicesStandby;
+in
+{
+  options.nfsServicesStandby = {
+    enable = lib.mkEnableOption "NFS services standby" // { default = true; };
+
+    replicationKeys = lib.mkOption {
+      type = lib.types.listOf lib.types.str;
+      default = [];
+      description = ''
+        SSH public keys authorized to replicate btrfs snapshots to this standby.
+        These keys are restricted to only run 'btrfs receive /persist/services-standby'.
+
+        Get the public key from the NFS server:
+          ssh <nfs-server> sudo cat /persist/root/.ssh/btrfs-replication.pub
+      '';
+    };
+  };
+
+  config = lib.mkIf cfg.enable {
+    # Allow root SSH login for replication (restricted by command= in authorized_keys)
+    # This is configured in common/sshd.nix
+
+    # Restricted SSH keys for btrfs replication
+    users.users.root.openssh.authorizedKeys.keys =
+      map (key: ''command="btrfs receive /persist/services-standby",restrict ${key}'') cfg.replicationKeys;
+
+    # Mount point for services-standby subvolume
+    # This is just declarative documentation - the subvolume must be created manually once:
+    #   sudo btrfs subvolume create /persist/services-standby
+    # After that, it will persist across reboots (it's under /persist)
+    fileSystems."/persist/services-standby" = {
+      device = "/persist/services-standby";
+      fsType = "none";
+      options = [ "bind" ];
+      noCheck = true;
+    };
+
+    # Cleanup old snapshots on standby (keep last 10 snapshots)
+    systemd.services.cleanup-services-standby-snapshots = {
+      description = "Cleanup old btrfs snapshots in services-standby";
+      path = [ pkgs.btrfs-progs pkgs.findutils pkgs.coreutils pkgs.curl ];
+      script = ''
+        set -euo pipefail
+
+        # Cleanup old snapshots on standby (keep last 10 snapshots, sorted by name/timestamp)
+        ls -1d /persist/services-standby/services@* 2>/dev/null | sort | head -n -10 | xargs -r btrfs subvolume delete || true
+
+        # Calculate metrics
+        CLEANUP_TIME=$(date +%s)
+        SNAPSHOT_COUNT=$(ls -1d /persist/services-standby/services@* 2>/dev/null | wc -l)
+
+        # Push metrics to Prometheus pushgateway
+        cat <<METRICS | curl -s --data-binary @- http://pushgateway.service.consul:9091/metrics/job/nfs_standby_cleanup/instance/$(hostname) || true
+        # TYPE nfs_standby_snapshot_count gauge
+        nfs_standby_snapshot_count $SNAPSHOT_COUNT
+        # TYPE nfs_standby_cleanup_last_run_timestamp gauge
+        nfs_standby_cleanup_last_run_timestamp $CLEANUP_TIME
+        METRICS
+      '';
+      serviceConfig = {
+        Type = "oneshot";
+        User = "root";
+      };
+    };
+
+    systemd.timers.cleanup-services-standby-snapshots = {
+      description = "Timer for cleaning up old snapshots on standby";
+      wantedBy = [ "timers.target" ];
+      timerConfig = {
+        OnCalendar = "hourly";
+        Persistent = true;
+      };
+    };
+  };
+}

common/nomad-server.nix

@@ -0,0 +1,9 @@
+{ ... }:
+{
+  # Enable server mode for both Consul and Nomad
+  # Used by: c1, c2, c3 (quorum members)
+  clusterRole = {
+    consulServer = true;
+    nomadServer = true;
+  };
+}

common/nomad-worker.nix

@@ -0,0 +1,9 @@
+{ ... }:
+{
+  # Enable Nomad client to run workloads
+  # Includes: Nomad client, Docker plugin, host volumes, NFS mount dependencies
+  # Used by: c1, c2, c3, zippy (all nodes that run Nomad jobs)
+  imports = [
+    ./nomad.nix
+  ];
+}

common/nomad.nix

@@ -1,109 +1,177 @@
 # inspiration: https://github.com/astro/skyflake/blob/main/nixos-modules/nomad.nix
-{ pkgs, config, ... }:
+{ pkgs, config, lib, ... }:
 let
   servers = [
     "c1"
     "c2"
     "c3"
   ];
-  server_enabled = builtins.elem config.networking.hostName servers;
 in
 {
-  services.nomad = {
+  options.clusterRole.nomadServer = lib.mkEnableOption "Nomad server mode";
-    enable = true;
-    # true breaks at least CSI volumes
-    # TODO: consider fixing
-    dropPrivileges = false;
 
-    settings = {
+  config = {
-      datacenter = "alo";
+    services.nomad = {
+      enable = true;
+      # true breaks at least CSI volumes
+      # TODO: consider fixing
+      dropPrivileges = false;
 
-      client = {
+      settings = {
-        enabled = true;
+        datacenter = "alo";
-        server_join.retry_join = servers;
+
-        host_network.tailscale = {
+        client = {
-          interface = "tailscale0";
+          enabled = true;
-          cidr = "100.64.0.0/10";
+          server_join.retry_join = servers;
+          host_network.tailscale = {
+            interface = "tailscale0";
+            cidr = "100.64.0.0/10";
+          };
+          host_volume = {
+            services = {
+              path = "/data/services";
+              read_only = false;
+            };
+            nix-store = {
+              path = "/nix/store";
+              read_only = true;
+            };
+            sw = {
+              path = "/run/current-system/sw";
+              read_only = true;
+            };
+          };
         };
-        host_volume = {
+
-          code = {
+        server = {
-            path = "/data/compute/code";
+          enabled = config.clusterRole.nomadServer;
-            read_only = true;
+          bootstrap_expect = (builtins.length servers + 2) / 2;
-          };
+          server_join.retry_join = servers;
-          appdata = {
+        };
-            path = "/data/compute/appdata";
+
-            read_only = false;
+        telemetry = {
-          };
+          collection_interval = "1s";
-          nix-store = {
+          disable_hostname = true;
-            path = "/nix/store";
+          prometheus_metrics = true;
-            read_only = true;
+          publish_allocation_metrics = true;
-          };
+          publish_node_metrics = true;
-          sw = {
-            path = "/run/current-system/sw";
-            read_only = true;
-          };
         };
       };
 
-      server = {
+      extraSettingsPaths = [ "/etc/nomad-alo.json" ];
-        enabled = server_enabled;
+    };
-        bootstrap_expect = (builtins.length servers + 2) / 2;
-        server_join.retry_join = servers;
-      };
 
-      telemetry = {
+    # NFS mount dependency configuration for Nomad:
-        collection_interval = "1s";
+    #
-        disable_hostname = true;
+    # Problem: Docker bind mounts need the real NFS mount, not an empty stub.
-        prometheus_metrics = true;
+    # If Nomad starts before NFS is mounted, containers get empty directories.
-        publish_allocation_metrics = true;
+    #
-        publish_node_metrics = true;
+    # Solution: Use soft dependencies (wants/after) with health-checking recovery.
+    # - wants: Nomad wants the mount, but won't be killed if it goes away
+    # - after: Nomad waits for mount to be attempted before starting
+    # - ExecStartPre with findmnt: Blocks Nomad start until mount is actually active
+    #
+    # This prevents Docker race conditions while allowing:
+    # - Boot to proceed if NFS unavailable (Nomad fails to start, systemd retries)
+    # - Nomad to keep running if NFS temporarily fails (containers may error)
+    # - Recovery service to auto-restart Nomad when NFS comes back or becomes stale
+    #
+    # Note: Mount uses Consul DNS which resolves at mount time. If NFS server
+    #       moves to different IP, mount becomes stale and needs remount.
+    #       The recovery service handles this by detecting stale mounts and restarting Nomad.
+    systemd.services.nomad = {
+      wants = [ "network-online.target" "data-services.mount" ];
+      after = [ "data-services.mount" ];
+      serviceConfig.ExecStartPre = "${pkgs.util-linux}/bin/findmnt --mountpoint /data/services";
+    };
+
+    # Recovery service: automatically restart Nomad when NFS mount needs attention
+    # This handles scenarios where:
+    # - NFS server was down during boot (mount failed, Nomad hit start-limit)
+    # - NFS server failed over to different host with new IP (mount went stale)
+    # - Network outage temporarily broke the mount
+    #
+    # The timer runs every 30s and checks:
+    # 1. Is mount healthy (exists and accessible)?
+    # 2. If mount is stale/inaccessible → restart Nomad (triggers remount)
+    # 3. If mount is healthy but Nomad failed → restart Nomad (normal recovery)
+    systemd.services.nomad-mount-watcher = {
+      description = "Restart Nomad when NFS mount needs attention";
+      serviceConfig = {
+        Type = "oneshot";
+        ExecStart = pkgs.writeShellScript "nomad-mount-watcher" ''
+          # Check if mount point exists
+          if ! ${pkgs.util-linux}/bin/findmnt --mountpoint /data/services >/dev/null 2>&1; then
+            exit 0  # Mount not present, nothing to do
+          fi
+
+          # Check if mount is actually accessible (not stale)
+          # Use timeout to avoid hanging on stale NFS mounts
+          if ! ${pkgs.coreutils}/bin/timeout 5s ${pkgs.coreutils}/bin/stat /data/services >/dev/null 2>&1; then
+            echo "NFS mount is stale or inaccessible. Restarting Nomad to trigger remount..."
+            ${pkgs.systemd}/bin/systemctl restart nomad.service
+            exit 0
+          fi
+
+          # Mount is healthy - check if Nomad needs recovery
+          if ${pkgs.systemd}/bin/systemctl is-failed nomad.service >/dev/null 2>&1; then
+            echo "NFS mount is healthy but Nomad is failed. Restarting Nomad..."
+            ${pkgs.systemd}/bin/systemctl restart nomad.service
+          fi
+        '';
       };
     };
 
-    extraSettingsPaths = [ "/etc/nomad-alo.json" ];
+    systemd.timers.nomad-mount-watcher = {
-  };
+      description = "Timer for Nomad mount watcher";
-
+      wantedBy = [ "timers.target" ];
-  systemd.services.nomad.wants = [ "network-online.target" ];
+      timerConfig = {
-
+        OnBootSec = "1min";       # First run 1min after boot
-  environment.etc."nomad-alo.json".text = builtins.toJSON {
+        OnUnitActiveSec = "30s";  # Then every 30s
-    plugin.docker.config = {
+        Unit = "nomad-mount-watcher.service";
-      allow_privileged = true;
+      };
-      # for keepalived, though only really needing "NET_ADMIN","NET_BROADCAST","NET_RAW" on top of default
-      # TODO: trim this down
-      allow_caps = [ "all" ];
-      volumes.enabled = true;
-      extra_labels = [
-        "job_name"
-        "task_group_name"
-        "task_name"
-        "node_name"
-      ];
     };
 
-    plugin.raw_exec.config.enabled = true;
+    environment.etc."nomad-alo.json".text = builtins.toJSON {
-  };
+      plugin.docker.config = {
+        allow_privileged = true;
+        # for keepalived, though only really needing "NET_ADMIN","NET_BROADCAST","NET_RAW" on top of default
+        # TODO: trim this down
+        allow_caps = [ "all" ];
+        volumes.enabled = true;
+        extra_labels = [
+          "job_name"
+          "task_group_name"
+          "task_name"
+          "node_name"
+        ];
+      };
 
-  environment.persistence."/persist".directories = [
+      plugin.raw_exec.config.enabled = true;
-    "/var/lib/docker"
+    };
-    "/var/lib/nomad"
-  ];
 
-  environment.systemPackages = with pkgs; [
+    environment.persistence.${config.custom.impermanence.persistPath}.directories = [
-    nomad
+      "/var/lib/docker"
-    wander
+      "/var/lib/nomad"
-    damon
+    ];
-  ];
 
-  networking.firewall = {
+    environment.systemPackages = with pkgs; [
-    allowedTCPPorts =
+      nomad
-      if server_enabled then
+      wander
-        [
+      damon
-          4646
+    ];
-          4647
+
-          4648
+    networking.firewall = {
-        ]
+      allowedTCPPorts =
-      else
+        if config.clusterRole.nomadServer then
-        [ 4646 ];
+          [
-    allowedUDPPorts = if server_enabled then [ 4648 ] else [ ];
+            4646
+            4647
+            4648
+          ]
+        else
+          [ 4646 ];
+      allowedUDPPorts = if config.clusterRole.nomadServer then [ 4648 ] else [ ];
+    };
   };
 }

common/resource-limits.nix

@@ -0,0 +1,44 @@
+{ ... }:
+{
+  # Resource limits for user sessions to prevent system wedging
+  #
+  # Modern systemd/cgroups v2 approach to resource control (replaces ulimits).
+  # Limits apply to all user sessions (SSH, GUI, etc.) but NOT to system services.
+  #
+  # Rationale:
+  # - Prevents runaway user processes (nix builds, compiles, etc.) from consuming
+  #   all resources and making the system unresponsive
+  # - System services (Nomad jobs, Consul, NFS, etc.) run outside user.slice and
+  #   are unaffected by these limits
+  # - Ensures SSH access remains responsive even under heavy load
+  #
+  # CPU: Uses CPUWeight (not CPUQuota) so user sessions can use 100% when idle,
+  #      but system services get priority (1.25x) during contention
+  # Memory: Soft limit at 90% (triggers pressure/reclaim), hard limit at 95%
+  #         Gives 5% warning buffer before OOM kills
+
+  systemd.slices.user = {
+    sliceConfig = {
+      # CPU weight: 80 vs default 100 for system services
+      # When idle: user sessions use all available CPU
+      # Under contention: system services get 1.25x CPU share
+      CPUWeight = "80";
+
+      # Memory soft limit: triggers reclaim and memory pressure
+      # User will notice slowdown but processes keep running
+      MemoryHigh = "90%";
+
+      # Memory hard limit: OOM killer targets user.slice
+      # 5% buffer between MemoryHigh and MemoryMax provides warning
+      MemoryMax = "95%";
+
+      # Limit number of tasks (processes/threads)
+      # Prevents fork bombs while still allowing nix builds
+      TasksMax = "4096";
+
+      # Lower I/O priority slightly
+      # System services get preference during I/O contention
+      IOWeight = "90";
+    };
+  };
+}

common/sshd.nix

@@ -3,8 +3,7 @@
     enable = true;
     allowSFTP = true;
     settings = {
-      PasswordAuthentication = false;
+      PermitRootLogin = "prohibit-password";  # Allow root login with SSH keys only
-      KbdInteractiveAuthentication = false;
     };
   };
 

common/syncthing-data.nix

@@ -1,53 +0,0 @@
-{
-  # TODO: when deploying this to a new machine for the first time, first
-  # comment this out to get /data/sync created with the right owner and
-  # permissions. then, do it again with persistence enabled.
-  # This could list the owner user but I'm not sure if it's already created at
-  # the time impermanence setup runs.
-  # Note: chown syncthing:syncthing /data/sync && chmod 700 /data/sync also seems to work
-  environment.persistence."/persist".directories = [ "/data/sync" ];
-
-  services.syncthing = {
-    enable = true;
-    dataDir = "/data/sync";
-    openDefaultPorts = true;
-    #guiAddress = "0.0.0.0:8384";
-    overrideDevices = true;
-    overrideFolders = true;
-    settings = {
-      devices = {
-        "c1" = {
-          id = "XJECP3R-AZHCAYX-UIQKHIT-AHBK5UM-KM7T4OV-B7SEUCW-ZE2UFPG-7BNAIQZ";
-        };
-        "c2" = {
-          id = "Z3D476N-PUV6WAD-DSJWVBO-TWEOD4I-KDDMNRB-QEBOP6T-BYPGYTX-RAAYGAW";
-        };
-        "c3" = {
-          id = "D3C3YII-A3QGUNF-LHOGZNX-GJ4ZF3X-VVLMNY5-BBKF3BO-KNHKJMD-EA5QYQJ";
-        };
-        "zippy" = {
-          id = "WXDYZWN-JG2OBQH-CC42RMM-LPJGTS6-Y2BV37J-TYSLHL4-VHGYL5M-URI42QJ";
-        };
-      };
-      folders = {
-        "wordpress" = {
-          path = "/data/sync/wordpress";
-          devices = [
-            "c1"
-            "c2"
-            "c3"
-            "zippy"
-          ];
-          ignorePerms = false;
-          versioning = {
-            type = "staggered";
-            params = {
-              cleanInterval = "3600";
-              maxAge = "15768000";
-            };
-          };
-        };
-      };
-    };
-  };
-}

common/systemd-boot.nix

@@ -1,7 +1,9 @@
+{ pkgs, lib, ... }:
 {
   boot.loader.systemd-boot = {
     enable = true;
     configurationLimit = 5;
+    memtest86.enable = lib.mkIf (pkgs.system == "x86_64-linux") true;
   };
   boot.loader.efi.canTouchEfiVariables = true;
 }

common/user-ppetru.nix

@@ -15,8 +15,9 @@
     openssh.authorizedKeys.keys = [
       "ssh-rsa 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 petru@paler.net"
       "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIH+QbeQG/gTPJ2sIMPgZ3ZPEirVo5qX/carbZMKt50YN petru@happy"
-      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDZjL47pUIks2caErnbFYv+McJcWd+GSydzAXHZEtL8s JuiceSSH"
+      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOOQ2EcJ+T+7BItZl89oDYhq7ZW4B9KuQVCy2DuQaPKR ppetru@sparky"
-      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINqULSU2VWUXSrHzFhs9pdXWZPtP/RS9gx7zz/zD/GDG petru@Workshop"
+      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFRYVOfrqk2nFSyiu7TzU23ql8D6TfXICFpMIEvPbNsc JuiceSSH"
+      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINBIqK6+aPIbmviJPWP8PI/k8GmaC7RO8v2ENnsK8sJx ppetru@beefy"
     ];
   };
 }

common/wait-for-dns-ready.nix

@@ -0,0 +1,55 @@
+{ pkgs, ... }:
+{
+  # Service to wait for DNS resolution to be actually functional
+  # This is needed because network-online.target and wait-online.service
+  # don't guarantee DNS works - they only check that interfaces are configured.
+  #
+  # Problem: NFS mounts using Consul DNS names (data-services.service.consul)
+  # fail at boot because DNS resolution isn't ready even though network is "online"
+  #
+  # Solution: Actively test DNS resolution before considering network truly ready
+
+  systemd.services.wait-for-dns-ready = {
+    description = "Wait for DNS resolution to be functional";
+    after = [
+      "systemd-networkd-wait-online.service"
+      "systemd-resolved.service"
+      "network-online.target"
+    ];
+    wants = [ "network-online.target" ];
+    wantedBy = [ "multi-user.target" ];
+
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+      ExecStart = pkgs.writeShellScript "wait-for-dns-ready" ''
+        # Test DNS resolution by attempting to resolve data-services.service.consul
+        # This ensures the full DNS path works: interface → gateway → Consul DNS
+
+        echo "Waiting for DNS resolution to be ready..."
+
+        for i in {1..30}; do
+          # Use getent which respects /etc/nsswitch.conf and systemd-resolved
+          if ${pkgs.glibc.bin}/bin/getent hosts data-services.service.consul >/dev/null 2>&1; then
+            echo "DNS ready: data-services.service.consul resolved successfully"
+            exit 0
+          fi
+
+          # Also test a public DNS name to distinguish between general DNS failure
+          # vs Consul-specific issues (helpful for debugging)
+          if ! ${pkgs.glibc.bin}/bin/getent hosts www.google.com >/dev/null 2>&1; then
+            echo "Attempt $i/30: General DNS not working yet, waiting..."
+          else
+            echo "Attempt $i/30: General DNS works but Consul DNS not ready yet, waiting..."
+          fi
+
+          sleep 1
+        done
+
+        echo "Warning: DNS not fully ready after 30 seconds"
+        echo "NFS mounts with 'nofail' option will handle this gracefully"
+        exit 0  # Don't block boot - let nofail mounts handle DNS failures
+      '';
+    };
+  };
+}

common/wifi.nix

@@ -0,0 +1,35 @@
+{ config, lib, ... }:
+{
+  sops.secrets.wifi-password-pi = {
+    sopsFile = ./../secrets/wifi.yaml;
+  };
+
+  networking.wireless = {
+    enable = true;
+    secretsFile = config.sops.secrets.wifi-password-pi.path;
+    networks = {
+      "pi" = {
+        pskRaw = "ext:pi";
+      };
+    };
+    # Only enable on wireless interface, not ethernet
+    interfaces = [ "wlan0" ];
+  };
+
+  # Prefer wifi over ethernet, but keep ethernet as fallback
+  networking.dhcpcd.extraConfig = ''
+    # Prefer wlan0 over ethernet interfaces
+    interface wlan0
+    metric 100
+
+    interface eth0
+    metric 200
+  '';
+
+  # Persist wireless configuration across reboots (for impermanence)
+  environment.persistence.${config.custom.impermanence.persistPath} = {
+    files = [
+      "/etc/wpa_supplicant.conf"
+    ];
+  };
+}

common/workstation-node.nix

@@ -1,5 +1,12 @@
 { pkgs, inputs, ... }:
 {
+  # Workstation profile: Development workstation configuration
+  # Adds development tools and emulation on top of minimal-node
+  imports = [
+    ./minimal-node.nix
+    ./unattended-encryption.nix
+  ];
+
   environment.systemPackages = with pkgs; [
     wget
     deploy-rs

docs/AUTH_SETUP.md

@@ -0,0 +1,55 @@
+# Authentication Setup
+
+SSO for homelab services using OIDC.
+
+## Architecture
+
+**Pocket ID** (`pocket-id.v.paler.net`) - Lightweight OIDC provider, data in `/data/services/pocket-id`
+
+**Traefik** - Uses `traefik-oidc-auth` plugin (v0.16.0) to protect services
+- Plugin downloaded from GitHub at startup, cached in `/data/services/traefik/plugins-storage`
+- Middleware config in `/data/services/traefik/rules/middlewares.yml`
+- Protected services add tag: `traefik.http.routers.<name>.middlewares=oidc-auth@file`
+
+## Flow
+
+1. User hits protected service → Traefik intercepts
+2. Redirects to Pocket ID for login
+3. Pocket ID returns OIDC token
+4. Traefik validates and forwards with `X-Oidc-Username` header
+
+## Protected Services
+
+Use `oidc-auth@file` middleware (grep codebase for full list):
+- Wikis (TiddlyWiki instances)
+- Media stack (Radarr, Sonarr, Plex, etc.)
+- Infrastructure (Traefik dashboard, Loki, Jupyter, Unifi)
+
+## Key Files
+
+- `services/pocket-id.hcl` - OIDC provider
+- `services/traefik.hcl` - Plugin declaration
+- `/data/services/traefik/rules/middlewares.yml` - Middleware definitions (oidc-auth, simple-auth fallback)
+
+## Cold Start Notes
+
+- Traefik needs internet to download plugin on first start
+- Pocket ID needs `/data/services` NFS mounted
+- Pocket ID down = all protected services inaccessible
+
+## Troubleshooting
+
+**Infinite redirects**: Check `TRUST_PROXY=true` on Pocket ID
+
+**Plugin not loading**: Clear cache in `/data/services/traefik/plugins-storage/`, restart Traefik
+
+**401 after login**: Verify client ID/secret in middlewares.yml matches Pocket ID client config
+
+## Migration History
+
+- Previous: Authentik with forwardAuth (removed Nov 2024)
+- Current: Pocket ID + traefik-oidc-auth (simpler, lighter)
+
+---
+
+*Manage users/clients via Pocket ID UI. Basic auth fallback available via `simple-auth` middleware.*

docs/DIFF_CONFIGS.md

@@ -0,0 +1,288 @@
+# Configuration Diff Tool
+
+Tool to compare all NixOS host configurations between current working tree and HEAD commit.
+
+## Purpose
+
+Before committing changes (especially refactors), verify that you haven't accidentally broken existing host configurations. This tool:
+- Builds all host configurations in current state (with uncommitted changes)
+- Builds all host configurations at HEAD (last commit)
+- Uses `nvd` to show readable diffs for each host
+- Highlights which hosts changed and which didn't
+
+## Usage
+
+### Prerequisites
+
+The script requires `nvd` to be in PATH. Use either:
+
+**Option 1: direnv (recommended)**
+```bash
+# Allow direnv in the repository (one-time setup)
+direnv allow
+
+# direnv will automatically load the dev shell when you cd into the directory
+cd /home/ppetru/projects/alo-cluster
+# nvd is now in PATH
+```
+
+**Option 2: nix develop**
+```bash
+# Enter dev shell manually
+nix develop
+
+# Now run the script
+./scripts/diff-configs.sh
+```
+
+### Quick Start
+
+```bash
+# Compare all hosts (summary)
+./scripts/diff-configs.sh
+
+# Compare with detailed path listing
+./scripts/diff-configs.sh -v c1
+
+# Compare with content diffs of changed files (deep mode)
+./scripts/diff-configs.sh --deep c1
+
+# Compare only x86_64 hosts (avoid slow ARM cross-compilation)
+./scripts/diff-configs.sh c1 c2 c3 zippy chilly sparky
+
+# Verbose mode with multiple hosts
+./scripts/diff-configs.sh --verbose c1 c2 c3
+
+# Via flake app
+nix run .#diff-configs
+
+# Show help
+./scripts/diff-configs.sh --help
+```
+
+### Typical Workflow
+
+```bash
+# 1. Make changes to configurations
+vim common/impermanence.nix
+
+# 2. Stage changes (required for flake to see them)
+git add common/impermanence.nix
+
+# 3. Check what would change if you committed now
+# For quick feedback, compare only x86_64 hosts first:
+./scripts/diff-configs.sh c1 c2 c3 zippy chilly sparky
+
+# 4. Review output, make adjustments if needed
+
+# 5. If changes look good and affect ARM hosts, check those too:
+./scripts/diff-configs.sh stinky alo-cloud-1
+
+# 6. Commit when satisfied
+git commit -m "Refactor impermanence config"
+```
+
+## Output Explanation
+
+### No Changes
+```
+━━━ c1 ━━━
+  Building current... done
+  Building HEAD...    done
+  ✓ No changes
+```
+This host's configuration is identical between current and HEAD.
+
+### Changes Detected
+```
+━━━ stinky ━━━
+  Building current... done
+  Building HEAD...    done
+  ⚠ Configuration changed
+
+<<< /nix/store/abc-nixos-system-stinky-25.05 (HEAD)
+>>> /nix/store/xyz-nixos-system-stinky-25.05 (current)
+
+Version changes:
+[C]  octoprint: 1.9.3 -> 1.10.0
+[A+] libcamera: ∅ -> 0.1.0
+Closure size: 1500 -> 1520 (5 paths added, 2 paths removed, +3, +15.2 MB)
+```
+
+Legend:
+- `[C]` - Changed package version
+- `[A+]` - Added package
+- `[R-]` - Removed package
+- `[U.]` - Updated (same version, rebuilt)
+
+### Verbose Mode (--verbose)
+
+With `-v` or `--verbose`, also shows the actual store paths that changed:
+
+```
+━━━ c1 ━━━
+  Building current... done
+  Building HEAD...    done
+  ⚠ Configuration changed
+
+[nvd summary as above]
+
+  Changed store paths:
+    Removed (17 paths):
+    - config.fish
+    - system-units
+    - home-manager-generation
+    - etc-fuse.conf
+    ... and 13 more
+
+    Added (17 paths):
+    - config.fish
+    - system-units
+    - home-manager-generation
+    - etc-fuse.conf
+    ... and 13 more
+```
+
+This is useful when nvd shows "No version changes" but paths still changed (e.g., refactors that rebuild config files).
+
+### Deep Mode (--deep)
+
+With `-d` or `--deep`, shows actual content diffs of changed files within store paths (implies verbose):
+
+```
+━━━ c1 ━━━
+  Building current... done
+  Building HEAD...    done
+  ⚠ Configuration changed
+
+[nvd summary and path listing as above]
+
+  Content diffs of changed files:
+
+    ▸ etc-fuse.conf
+      @@ -1,2 +1,2 @@
+      -user_allow_other
+      +#user_allow_other
+       mount_max = 1000
+
+    ▸ nixos-system-c1-25.05
+      activate:
+        @@ -108,7 +108,7 @@
+         echo "setting up /etc..."
+        -/nix/store/...-perl/bin/perl /nix/store/...-setup-etc.pl /nix/store/abc-etc/etc
+        +/nix/store/...-perl/bin/perl /nix/store/...-setup-etc.pl /nix/store/xyz-etc/etc
+
+    ▸ unit-dbus.service
+      dbus.service:
+        @@ -1,5 +1,5 @@
+         [Service]
+        +Environment="LD_LIBRARY_PATH=/nix/store/.../systemd/lib"
+         Environment="LOCALE_ARCHIVE=..."
+```
+
+**What it shows**:
+- Matches changed paths by basename (e.g., both have "config.fish")
+- Diffs important files: activate scripts, etc/*, *.conf, *.fish, *.service, *.nix
+- Shows unified diff format (lines added/removed)
+- Limits to first 50 lines per file
+
+**When to use**:
+- When you need to know **what exactly changed** in config files
+- Debugging unexpected configuration changes
+- Reviewing refactors that don't change package versions
+- Understanding why a host rebuilt despite "No version changes"
+
+### Build Failures
+```
+━━━ broken-host ━━━
+  Building current... FAILED
+  Error: attribute 'foo' missing
+```
+If a host fails to build, the error is shown and the script continues with other hosts.
+
+## How It Works
+
+1. **Discovers hosts**: Queries `deploy.nodes` from flake to get all configured hosts
+2. **Creates worktree**: Uses `git worktree` to check out HEAD in a temporary directory
+3. **Builds configurations**: Builds `config.system.build.toplevel` for each host in both locations
+4. **Compares with nvd**: Runs `nvd diff` to show package-level changes
+5. **Cleans up**: Removes temporary worktree automatically
+
+## Important Notes
+
+### Git Staging Required
+
+Flakes only evaluate files that are tracked by git. To make changes visible:
+```bash
+# Stage new files
+git add new-file.nix
+
+# Stage changes to existing files
+git add modified-file.nix
+
+# Or stage everything
+git add .
+```
+
+Unstaged changes to tracked files **are** visible (flake uses working tree content).
+
+### Performance
+
+- First run may be slow (building all configurations)
+- Subsequent runs benefit from Nix evaluation cache
+- Typical runtime: 1-5 minutes depending on changes
+- **ARM cross-compilation is slow**: Use host filtering to avoid building ARM hosts when not needed
+  - Example: `./scripts/diff-configs.sh c1 c2 c3` (x86_64 only, fast)
+  - vs `./scripts/diff-configs.sh` (includes stinky/alo-cloud-1, slow)
+
+### When to Use
+
+**Good use cases**:
+- Refactoring shared modules (like impermanence)
+- Updating common configurations
+- Before committing significant changes
+- Verifying deploy target consistency
+
+**Not needed for**:
+- Adding a single new host
+- Trivial one-host changes
+- Documentation updates
+
+## Troubleshooting
+
+### "Not in a git repository"
+```bash
+cd /home/ppetru/projects/alo-cluster
+./scripts/diff-configs.sh
+```
+
+### "No changes detected"
+All changes are already committed. Stage some changes first:
+```bash
+git add .
+```
+
+### Build failures for all hosts
+Check flake syntax:
+```bash
+nix flake check
+```
+
+### nvd not found
+Install nvd:
+```bash
+nix profile install nixpkgs#nvd
+```
+(Already included in workstation-node.nix packages)
+
+## Related Tools
+
+- `nvd` - Package diff tool (used internally)
+- `nix diff-closures` - Low-level closure diff
+- `nix store diff-closures` - Alternative diff command
+- `deploy-rs` - Actual deployment tool
+
+## See Also
+
+- `common/global/show-changelog.nix` - Shows changes during system activation
+- `docs/RASPBERRY_PI_SD_IMAGE.md` - SD image building process

docs/MIGRATION_TODO.md

@@ -0,0 +1,160 @@
+# Cluster Revamp Migration TODO
+
+Track migration progress from GlusterFS to NFS-based architecture.
+See [CLUSTER_REVAMP.md](./CLUSTER_REVAMP.md) for detailed procedures.
+
+## Phase 0: Preparation
+- [x] Review cluster revamp plan
+- [ ] Backup everything (kopia snapshots current)
+- [ ] Document current state (nomad jobs, consul services)
+
+## Phase 1: Convert fractal to NixOS (DEFERRED - do after GlusterFS migration)
+- [ ] Document fractal's current ZFS layout
+- [ ] Install NixOS on fractal
+- [ ] Import ZFS pools (double1, double2, double3)
+- [ ] Create fractal NixOS configuration
+- [ ] Configure Samba server for media/shared/homes
+- [ ] Configure Kopia backup server
+- [ ] Deploy and verify fractal base config
+- [ ] Join fractal to cluster (5-server quorum)
+- [ ] Update all cluster configs for 5-server quorum
+- [ ] Verify fractal fully operational
+
+## Phase 2: Setup zippy storage layer
+- [x] Create btrfs subvolume `/persist/services` on zippy
+- [x] Configure NFS server on zippy (nfs-services-server.nix)
+- [x] Configure Consul service registration for NFS
+- [x] Setup btrfs replication to c1 (incremental, 5min intervals)
+- [x] Fix replication script to handle SSH command restrictions
+- [x] Setup standby storage on c1 (`/persist/services-standby`)
+- [x] Configure c1 as standby (nfs-services-standby.nix)
+- [x] Configure Kopia to exclude replication snapshots
+- [x] Deploy and verify NFS server on zippy
+- [x] Verify replication working to c1
+- [ ] Setup standby storage on c2 (if desired)
+- [ ] Configure replication to c2 (if desired)
+
+## Phase 3: Migrate from GlusterFS to NFS
+- [x] Update all nodes to mount NFS at `/data/services`
+- [x] Deploy updated configs (NFS client on all nodes)
+- [x] Stop all Nomad jobs temporarily
+- [x] Copy data from GlusterFS to zippy NFS
+  - [x] Copy `/data/compute/appdata/*` → `/persist/services/appdata/`
+  - [x] Copy `/data/compute/config/*` → `/persist/services/config/`
+  - [x] Copy `/data/sync/wordpress` → `/persist/services/appdata/wordpress`
+  - [x] Verify data integrity
+- [x] Verify NFS mounts working on all nodes
+- [x] Stop GlusterFS volume
+- [x] Delete GlusterFS volume
+- [x] Remove GlusterFS from NixOS configs
+- [x] Remove syncthing wordpress sync configuration (no longer used)
+
+## Phase 4: Update and redeploy Nomad jobs
+
+### Core Infrastructure (CRITICAL)
+- [x] mysql.hcl - moved to zippy, using `/data/services`
+- [x] postgres.hcl - migrated to `/data/services`
+- [x] redis.hcl - migrated to `/data/services`
+- [x] traefik.hcl - migrated to `/data/services`
+- [x] authentik.hcl - stateless, no changes needed
+
+### Monitoring Stack (HIGH)
+- [x] prometheus.hcl - migrated to `/data/services`
+- [x] grafana.hcl - migrated to `/data/services` (2025-10-23)
+- [x] loki.hcl - migrated to `/data/services`
+- [x] vector.hcl - removed glusterfs log collection (2025-10-23)
+
+### Databases (HIGH)
+- [x] clickhouse.hcl - migrated to `/data/services`
+- [x] unifi.hcl - migrated to `/data/services` (includes mongodb)
+
+### Web Applications (HIGH-MEDIUM)
+- [x] wordpress.hcl - migrated to `/data/services`
+- [x] gitea.hcl - migrated to `/data/services` (2025-10-23)
+- [x] wiki.hcl - migrated to `/data/services` (2025-10-23)
+- [x] plausible.hcl - stateless, no changes needed
+
+### Web Applications (LOW, may be deprecated)
+- [x] vikunja.hcl - migrated to `/data/services` (2025-10-23, not running)
+
+### Media Stack (MEDIUM)
+- [x] media.hcl - migrated to `/data/services`
+
+### Utility Services (MEDIUM-LOW)
+- [x] evcc.hcl - migrated to `/data/services`
+- [x] weewx.hcl - migrated to `/data/services` (2025-10-23)
+- [x] code-server.hcl - migrated to `/data/services`
+- [x] beancount.hcl - migrated to `/data/services`
+- [x] adminer.hcl - stateless, no changes needed
+- [x] maps.hcl - migrated to `/data/services`
+- [x] netbox.hcl - migrated to `/data/services`
+- [x] farmos.hcl - migrated to `/data/services` (2025-10-23)
+- [x] urbit.hcl - migrated to `/data/services`
+- [x] webodm.hcl - migrated to `/data/services` (2025-10-23, not running)
+- [x] velutrack.hcl - migrated to `/data/services`
+- [x] resol-gateway.hcl - migrated to `/data/services` (2025-10-23)
+- [x] igsync.hcl - migrated to `/data/services` (2025-10-23)
+- [x] jupyter.hcl - migrated to `/data/services` (2025-10-23, not running)
+- [x] whoami.hcl - stateless test service, no changes needed
+
+### Backup Jobs (HIGH)
+- [x] mysql-backup - moved to zippy, verified
+- [x] postgres-backup.hcl - migrated to `/data/services`
+
+### Host Volume Definitions (CRITICAL)
+- [x] common/nomad.nix - consolidated `appdata` and `code` volumes into single `services` volume (2025-10-23)
+
+### Verification
+- [ ] All services healthy in Nomad
+- [ ] All services registered in Consul
+- [ ] Traefik routes working
+- [ ] Database jobs running on zippy (verify via nomad alloc status)
+- [ ] Media jobs running on fractal (verify via nomad alloc status)
+
+## Phase 5: Convert sunny to NixOS (OPTIONAL - can defer)
+- [ ] Document current sunny setup (ethereum containers/VMs)
+- [ ] Backup ethereum data
+- [ ] Install NixOS on sunny
+- [ ] Restore ethereum data to `/persist/ethereum`
+- [ ] Create sunny container-based config (besu, lighthouse, rocketpool)
+- [ ] Deploy and verify ethereum stack
+- [ ] Monitor sync status and validation
+
+## Phase 6: Verification and cleanup
+- [ ] Test NFS failover procedure (zippy → c1)
+- [ ] Verify backups include `/persist/services` data
+- [ ] Verify backups exclude replication snapshots
+- [ ] Update documentation (README.md, architecture diagrams)
+- [x] Clean up old GlusterFS data (only after everything verified!)
+- [x] Remove old glusterfs directories from all nodes
+
+## Post-Migration Checklist
+- [ ] All 5 servers in quorum (consul members)
+- [ ] NFS mounts working on all nodes
+- [ ] Btrfs replication running (check systemd timers on zippy)
+- [ ] Critical services up (mysql, postgres, redis, traefik, authentik)
+- [ ] Monitoring working (prometheus, grafana, loki)
+- [ ] Media stack on fractal
+- [ ] Database jobs on zippy
+- [ ] Consul DNS working (dig @localhost -p 8600 data-services.service.consul)
+- [ ] Backups running (kopia snapshots include /persist/services)
+- [ ] GlusterFS removed (no processes, volumes deleted)
+- [ ] Documentation updated
+
+---
+
+**Last updated**: 2025-10-25
+**Current phase**: Phase 3 & 4 complete! GlusterFS removed, all services on NFS
+**Note**: Phase 1 (fractal NixOS conversion) deferred until after GlusterFS migration is complete
+
+## Migration Summary
+
+**All services migrated to `/data/services` (30 total):**
+mysql, mysql-backup, postgres, postgres-backup, redis, clickhouse, prometheus, grafana, loki, vector, unifi, wordpress, gitea, wiki, traefik, evcc, weewx, netbox, farmos, webodm, jupyter, vikunja, urbit, code-server, beancount, velutrack, maps, media, resol-gateway, igsync
+
+**Stateless/no changes needed (4 services):**
+authentik, adminer, plausible, whoami
+
+**Configuration changes:**
+- common/nomad.nix: consolidated `appdata` and `code` volumes into single `services` volume
+- vector.hcl: removed glusterfs log collection

docs/NFS_FAILOVER.md

@@ -0,0 +1,438 @@
+# NFS Services Failover Procedures
+
+This document describes how to fail over the `/data/services` NFS server between hosts and how to fail back.
+
+## Architecture Overview
+
+- **Primary NFS Server**: Typically `zippy`
+  - Exports `/persist/services` via NFS
+  - Has local bind mount: `/data/services` → `/persist/services` (same path as clients)
+  - Registers `data-services.service.consul` in Consul
+  - Sets Nomad node meta: `storage_role = "primary"`
+  - Replicates snapshots to standbys every 5 minutes via btrfs send
+  - **Safety check**: Refuses to start if another NFS server is already active in Consul
+
+- **Standby**: Typically `c1`
+  - Receives snapshots at `/persist/services-standby/services@<timestamp>`
+  - Can be promoted to NFS server during failover
+  - No special Nomad node meta (not primary)
+
+- **Clients**: All cluster nodes (c1, c2, c3, zippy)
+  - Mount `/data/services` from `data-services.service.consul:/persist/services`
+  - Automatically connect to whoever is registered in Consul
+
+### Nomad Job Constraints
+
+Jobs that need to run on the primary storage node should use:
+
+```hcl
+constraint {
+  attribute = "${meta.storage_role}"
+  value     = "primary"
+}
+```
+
+This is useful for:
+- Database jobs (mysql, postgres, redis) that benefit from local storage
+- Jobs that need guaranteed fast disk I/O
+
+During failover, the `storage_role = "primary"` meta attribute moves to the new NFS server, and Nomad automatically reschedules constrained jobs to the new primary.
+
+## Prerequisites
+
+- Standby has been receiving snapshots (check: `ls /persist/services-standby/services@*`)
+- Last successful replication was recent (< 5-10 minutes)
+
+---
+
+## Failover: Promoting Standby to Primary
+
+**Scenario**: `zippy` is down and you need to promote `c1` to be the NFS server.
+
+### Step 1: Choose Latest Snapshot
+
+On the standby (c1):
+
+```bash
+ssh c1
+sudo ls -lt /persist/services-standby/services@* | head -5
+```
+
+Find the most recent snapshot. Note the timestamp to estimate data loss (typically < 5 minutes).
+
+### Step 2: Promote Snapshot to Read-Write Subvolume
+
+On c1:
+
+```bash
+# Find the latest snapshot
+LATEST=$(sudo ls -t /persist/services-standby/services@* | head -1)
+
+# Create writable subvolume from snapshot
+sudo btrfs subvolume snapshot "$LATEST" /persist/services
+
+# Verify
+ls -la /persist/services
+```
+
+### Step 3: Update NixOS Configuration
+
+Edit your configuration to swap the NFS server role:
+
+**In `hosts/c1/default.nix`**:
+```nix
+imports = [
+  # ... existing imports ...
+  # ../../common/nfs-services-standby.nix  # REMOVE THIS
+  ../../common/nfs-services-server.nix     # ADD THIS
+];
+
+# Add standbys if desired (optional - can leave empty during emergency)
+nfsServicesServer.standbys = [];  # Or ["c2"] to add a new standby
+```
+
+**Optional: Prepare zippy config for when it comes back**:
+
+In `hosts/zippy/default.nix` (can do this later too):
+```nix
+imports = [
+  # ... existing imports ...
+  # ../../common/nfs-services-server.nix   # REMOVE THIS
+  ../../common/nfs-services-standby.nix    # ADD THIS
+];
+
+# Add the replication key from c1 (get it from c1:/persist/root/.ssh/btrfs-replication.pub)
+nfsServicesStandby.replicationKeys = [
+  "ssh-ed25519 AAAA... root@c1-replication"
+];
+```
+
+### Step 4: Deploy Configuration
+
+```bash
+# From your workstation
+deploy -s '.#c1'
+
+# If zippy is still down, updating its config will fail, but that's okay
+# You can update it later when it comes back
+```
+
+### Step 5: Verify NFS Server is Running
+
+On c1:
+
+```bash
+sudo systemctl status nfs-server
+sudo showmount -e localhost
+dig @localhost -p 8600 data-services.service.consul  # Should show c1's IP
+```
+
+### Step 6: Verify Clients Can Access
+
+From any node:
+
+```bash
+df -h | grep services
+ls /data/services
+```
+
+The mount should automatically reconnect via Consul DNS.
+
+### Step 7: Check Nomad Jobs
+
+```bash
+nomad job status mysql
+nomad job status postgres
+# Verify critical services are healthy
+
+# Jobs constrained to ${meta.storage_role} = "primary" will automatically
+# reschedule to c1 once it's deployed with the NFS server module
+```
+
+**Recovery Time Objective (RTO)**: ~10-15 minutes
+**Recovery Point Objective (RPO)**: Last replication interval (5 minutes max)
+
+**Note**: Jobs with the `storage_role = "primary"` constraint will automatically move to c1 because it now has that node meta attribute. No job spec changes needed!
+
+---
+
+## What Happens When zippy Comes Back?
+
+**IMPORTANT**: If zippy reboots while still configured as NFS server, it will **refuse to start** the NFS service because it detects c1 is already active in Consul.
+
+You'll see this error in `journalctl -u nfs-server`:
+
+```
+ERROR: Another NFS server is already active at 192.168.1.X
+This host (192.168.1.2) is configured as NFS server but should be standby.
+To fix:
+  1. If this is intentional (failback), first demote the other server
+  2. Update this host's config to use nfs-services-standby.nix instead
+  3. Sync data from active server before promoting this host
+```
+
+This is a **safety feature** to prevent split-brain and data corruption.
+
+### Options when zippy comes back:
+
+**Option A: Keep c1 as primary** (zippy becomes standby)
+1. Update zippy's config to use `nfs-services-standby.nix`
+2. Deploy to zippy
+3. c1 will start replicating to zippy
+
+**Option B: Fail back to zippy as primary**
+Follow the "Failing Back to Original Primary" procedure below.
+
+---
+
+## Failing Back to Original Primary
+
+**Scenario**: `zippy` is repaired and you want to move the NFS server role back from `c1` to `zippy`.
+
+### Step 1: Sync Latest Data from c1 to zippy
+
+On c1 (current primary):
+
+```bash
+# Create readonly snapshot of current state
+sudo btrfs subvolume snapshot -r /persist/services /persist/services@failback-$(date +%Y%m%d-%H%M%S)
+
+# Find the snapshot
+FAILBACK=$(sudo ls -t /persist/services@failback-* | head -1)
+
+# Send to zippy (use root SSH key if available, or generate temporary key)
+sudo btrfs send "$FAILBACK" | ssh root@zippy "btrfs receive /persist/"
+```
+
+On zippy:
+
+```bash
+# Verify snapshot arrived
+ls -la /persist/services@failback-*
+
+# Create writable subvolume from the snapshot
+FAILBACK=$(ls -t /persist/services@failback-* | head -1)
+sudo btrfs subvolume snapshot "$FAILBACK" /persist/services
+
+# Verify
+ls -la /persist/services
+```
+
+### Step 2: Update NixOS Configuration
+
+Swap the roles back:
+
+**In `hosts/zippy/default.nix`**:
+```nix
+imports = [
+  # ... existing imports ...
+  # ../../common/nfs-services-standby.nix  # REMOVE THIS
+  ../../common/nfs-services-server.nix     # ADD THIS
+];
+
+nfsServicesServer.standbys = ["c1"];
+```
+
+**In `hosts/c1/default.nix`**:
+```nix
+imports = [
+  # ... existing imports ...
+  # ../../common/nfs-services-server.nix   # REMOVE THIS
+  ../../common/nfs-services-standby.nix    # ADD THIS
+];
+
+nfsServicesStandby.replicationKeys = [
+  "ssh-ed25519 AAAA... root@zippy-replication"  # Get from zippy:/persist/root/.ssh/btrfs-replication.pub
+];
+```
+
+### Step 3: Deploy Configurations
+
+```bash
+# IMPORTANT: Deploy c1 FIRST to demote it
+deploy -s '.#c1'
+
+# Wait for c1 to stop NFS server
+ssh c1 sudo systemctl status nfs-server  # Should be inactive
+
+# Then deploy zippy to promote it
+deploy -s '.#zippy'
+```
+
+The order matters! If you deploy zippy first, it will see c1 is still active and refuse to start.
+
+### Step 4: Verify Failback
+
+Check Consul DNS points to zippy:
+
+```bash
+dig @c1 -p 8600 data-services.service.consul  # Should show zippy's IP
+```
+
+Check clients are mounting from zippy:
+
+```bash
+for host in c1 c2 c3; do
+  ssh $host "df -h | grep services"
+done
+```
+
+### Step 5: Clean Up Temporary Snapshots
+
+On c1:
+
+```bash
+# Remove the failback snapshot and the promoted subvolume
+sudo btrfs subvolume delete /persist/services@failback-*
+sudo btrfs subvolume delete /persist/services
+```
+
+---
+
+## Adding a New Standby
+
+**Scenario**: You want to add `c2` as an additional standby.
+
+### Step 1: Create Standby Subvolume on c2
+
+```bash
+ssh c2
+sudo btrfs subvolume create /persist/services-standby
+```
+
+### Step 2: Update c2 Configuration
+
+**In `hosts/c2/default.nix`**:
+```nix
+imports = [
+  # ... existing imports ...
+  ../../common/nfs-services-standby.nix
+];
+
+nfsServicesStandby.replicationKeys = [
+  "ssh-ed25519 AAAA... root@zippy-replication"  # Get from current NFS server
+];
+```
+
+### Step 3: Update NFS Server Configuration
+
+On the current NFS server (e.g., zippy), update the standbys list:
+
+**In `hosts/zippy/default.nix`**:
+```nix
+nfsServicesServer.standbys = ["c1" "c2"];  # Added c2
+```
+
+### Step 4: Deploy
+
+```bash
+deploy -s '.#c2'
+deploy -s '.#zippy'
+```
+
+The next replication cycle (within 5 minutes) will do a full send to c2, then switch to incremental.
+
+---
+
+## Troubleshooting
+
+### Replication Failed
+
+Check the replication service logs:
+
+```bash
+# On NFS server
+sudo journalctl -u replicate-services-to-c1 -f
+```
+
+Common issues:
+- SSH key not found → Run key generation step (see stateful-commands.txt)
+- Permission denied → Check authorized_keys on standby
+- Snapshot already exists → Old snapshot with same timestamp, wait for next cycle
+
+### Clients Can't Mount
+
+Check Consul:
+
+```bash
+dig @localhost -p 8600 data-services.service.consul
+consul catalog services | grep data-services
+```
+
+If Consul isn't resolving:
+- NFS server might not have registered → Check `sudo systemctl status nfs-server`
+- Consul agent might be down → Check `sudo systemctl status consul`
+
+### Mount is Stale
+
+Force remount:
+
+```bash
+sudo systemctl restart data-services.mount
+```
+
+Or unmount and let automount handle it:
+
+```bash
+sudo umount /data/services
+ls /data/services  # Triggers automount
+```
+
+### Split-Brain Prevention: NFS Server Won't Start
+
+If you see:
+```
+ERROR: Another NFS server is already active at 192.168.1.X
+```
+
+This is **intentional** - the safety check is working! You have two options:
+
+1. **Keep the other server as primary**: Update this host's config to be a standby instead
+2. **Fail back to this host**: First demote the other server, sync data, then deploy both hosts in correct order
+
+---
+
+## Monitoring
+
+### Check Replication Status
+
+On NFS server:
+
+```bash
+# List recent snapshots
+ls -lt /persist/services@* | head
+
+# Check last replication run
+sudo systemctl status replicate-services-to-c1
+
+# Check replication logs
+sudo journalctl -u replicate-services-to-c1 --since "1 hour ago"
+```
+
+On standby:
+
+```bash
+# List received snapshots
+ls -lt /persist/services-standby/services@* | head
+
+# Check how old the latest snapshot is
+stat /persist/services-standby/services@* | grep Modify | head -1
+```
+
+### Verify NFS Exports
+
+```bash
+sudo showmount -e localhost
+```
+
+Should show:
+```
+/persist/services 192.168.1.0/24
+```
+
+### Check Consul Registration
+
+```bash
+consul catalog services | grep data-services
+dig @localhost -p 8600 data-services.service.consul
+```

docs/RASPBERRY_PI_SD_IMAGE.md

@@ -0,0 +1,98 @@
+# Raspberry Pi SD Image Building and Deployment
+
+Guide for building and deploying NixOS SD card images for Raspberry Pi hosts (e.g., stinky).
+
+## Overview
+
+Raspberry Pi hosts use a different deployment strategy than regular NixOS hosts:
+- **First deployment**: Build and flash an SD card image
+- **Subsequent updates**: Use `deploy-rs` like other hosts
+
+## Architecture
+
+### Storage Layout
+
+**Partition structure** (automatically created by NixOS):
+- `/boot/firmware` - FAT32 partition (label: `FIRMWARE`)
+  - Contains Raspberry Pi firmware, U-Boot bootloader, device trees
+- `/` - tmpfs (in-memory, ephemeral root)
+  - 2GB RAM disk, wiped on every boot
+- `/nix` - ext4 partition (label: `NIXOS_SD`)
+  - Nix store and persistent data
+  - Contains `/nix/persist` directory for impermanence
+
+### Impermanence with tmpfs
+
+Unlike btrfs-based hosts that use `/persist`, Pi hosts use `/nix/persist`:
+- Root filesystem is tmpfs (no disk writes, auto-wiped)
+- Single ext4 partition mounted at `/nix`
+- Persistent data stored in `/nix/persist/` (directory, not separate mount)
+- Better for SD card longevity (fewer writes)
+
+**Persisted paths**:
+- `/nix/persist/var/lib/nixos` - System state
+- `/nix/persist/home/ppetru` - User home directory
+- `/nix/persist/etc` - SSH host keys, machine-id
+- Service-specific: `/nix/persist/var/lib/octoprint`, etc.
+
+## Building the SD Image
+
+### Prerequisites
+
+- ARM64 emulation enabled on build machine:
+  ```nix
+  boot.binfmt.emulatedSystems = [ "aarch64-linux" ];
+  ```
+  (Already configured in `workstation-node.nix`)
+
+### Build Command
+
+```bash
+# Build SD image for stinky
+nix build .#packages.aarch64-linux.stinky-sdImage
+
+# Result location
+ls -lh result/sd-image/
+# nixos-sd-image-stinky-25.05-*.img.zst (compressed with zstd)
+```
+
+**Build location**: Defined in `flake.nix`:
+```nix
+packages.aarch64-linux.stinky-sdImage =
+  self.nixosConfigurations.stinky.config.system.build.sdImage;
+```
+
+## Flashing the SD Card
+
+### Find SD Card Device
+
+```bash
+# Before inserting SD card
+lsblk
+
+# Insert SD card, then check again
+lsblk
+
+# Look for new device, typically:
+# - /dev/sdX (USB SD card readers)
+# - /dev/mmcblk0 (built-in SD card slots)
+```
+
+**Warning**: Double-check the device! Wrong device = data loss.
+
+### Flash Image
+
+```bash
+# Decompress and flash in one command
+zstd -d -c result/sd-image/*.img.zst | sudo dd of=/dev/sdX bs=4M status=progress conv=fsync
+
+# Or decompress first, then flash
+unzstd result/sd-image/*.img.zst
+sudo dd if=result/sd-image/*.img of=/dev/sdX bs=4M status=progress conv=fsync
+```
+
+### Eject SD Card
+
+```bash
+sudo eject /dev/sdX
+```

docs/TODO

@@ -0,0 +1,7 @@
+* remote docker images used, can't come up if internet is down
+* local docker images pulled from gitea, can't come up if gitea isn't up (yet)
+* traefik-oidc-auth plugin downloaded from GitHub at startup (cached in /data/services/traefik/plugins-storage)
+* renovate system of some kind
+* vector (or other log ingestion) everywhere, consider moving it off docker if possible
+* monitor backup-persist success/fail
+

flake.nix

@@ -5,12 +5,16 @@
     deploy-rs.url = "github:serokell/deploy-rs";
     deploy-rs.inputs.nixpkgs.follows = "nixpkgs";
     impermanence.url = "github:nix-community/impermanence";
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-25.05";
     nixpkgs-unstable.url = "github:NixOS/nixpkgs/nixos-unstable";
     disko.url = "github:nix-community/disko";
     disko.inputs.nixpkgs.follows = "nixpkgs";
+    ethereum-nix = {
+      url = "github:nix-community/ethereum.nix";
+      inputs.nixpkgs.follows = "nixpkgs-unstable";
+    };
     home-manager = {
-      url = "github:nix-community/home-manager/release-24.11";
+      url = "github:nix-community/home-manager/release-25.05";
       inputs.nixpkgs.follows = "nixpkgs";
     };
     nix-index-database = {
@@ -25,6 +29,16 @@
       url = "github:Mic92/sops-nix";
       inputs.nixpkgs.follows = "nixpkgs";
     };
+    browser-previews = {
+      url = "github:nix-community/browser-previews";
+      inputs.nixpkgs.follows = "nixpkgs-unstable";
+    };
+    omarchy-nix = {
+      url = "github:henrysipp/omarchy-nix";
+      inputs.nixpkgs.follows = "nixpkgs";
+      inputs.home-manager.follows = "home-manager";
+    };
+    nixos-hardware.url = "github:NixOS/nixos-hardware/master";
   };
 
   outputs =
@@ -34,56 +48,88 @@
       nixpkgs-unstable,
       deploy-rs,
       disko,
+      ethereum-nix,
       home-manager,
-      sops-nix,
       impermanence,
+      sops-nix,
+      browser-previews,
+      omarchy-nix,
+      nixos-hardware,
       ...
     }@inputs:
     let
       inherit (self);
 
-      overlay-unstable = final: prev: { unstable = nixpkgs-unstable.legacyPackages.${prev.system}; };
+      overlay-unstable = final: prev: {
+        unstable = import nixpkgs-unstable {
+          inherit (prev) system;
+          config.allowUnfree = true;
+        };
+      };
 
-      mkNixos =
+      overlay-browser-previews = final: prev: {
-        system: modules:
+        browser-previews = browser-previews.packages.${prev.system};
+      };
+
+      mkHost =
+        system: profile: modules:
+        let
+          # Profile parameter is only used by home-manager for user environment
+          # NixOS system configuration is handled via explicit imports in host configs
+        in
         nixpkgs.lib.nixosSystem {
           system = system;
           modules = [
             (
               { config, pkgs, ... }:
               {
-                nixpkgs.overlays = [ overlay-unstable ];
+                nixpkgs.overlays = [ overlay-unstable overlay-browser-previews ];
                 nixpkgs.config.allowUnfree = true;
               }
             )
             disko.nixosModules.disko
             sops-nix.nixosModules.sops
             impermanence.nixosModules.impermanence
+            home-manager.nixosModules.home-manager
+            (
+              { lib, ... }:
+              lib.mkMerge [
+                {
+                  home-manager = {
+                    useGlobalPkgs = true;
+                    useUserPackages = true;
+                    users.ppetru = {
+                      imports = [
+                        inputs.nix-index-database.homeModules.nix-index
+                        inputs.nixvim.homeModules.nixvim
+                        ./home
+                      ] ++ lib.optionals (profile == "desktop") [
+                        omarchy-nix.homeManagerModules.default
+                      ];
+                    };
+                    extraSpecialArgs = {
+                      inherit profile;
+                    };
+                  };
+                }
+                (lib.optionalAttrs (profile == "desktop") {
+                  omarchy = {
+                    full_name = "Petru Paler";
+                    email_address = "petru@paler.net";
+                    theme = "tokyo-night";
+                    monitors = [ "DP-1,preferred,auto,1.5" ];
+                  };
+                })
+              ]
+            )
+          ] ++ nixpkgs.lib.optionals (profile == "desktop") [
+            omarchy-nix.nixosModules.default
           ] ++ modules;
           specialArgs = {
             inherit inputs self;
           };
         };
 
-      mkHMNixos =
-        system: modules:
-        mkNixos system ([
-          home-manager.nixosModules.home-manager
-          {
-            home-manager = {
-              useGlobalPkgs = true;
-              useUserPackages = true;
-              users.ppetru = {
-                imports = [
-                  (inputs.impermanence + "/home-manager.nix")
-                  inputs.nix-index-database.hmModules.nix-index
-                  inputs.nixvim.homeManagerModules.nixvim
-                  ./home
-                ];
-              };
-            };
-          }] ++ modules);
-
       pkgsFor =
         system:
         import nixpkgs {
@@ -97,7 +143,7 @@
           inherit system;
           overlays = [
             overlay-unstable
-            deploy-rs.overlay
+            deploy-rs.overlays.default
             (self: super: {
               deploy-rs = {
                 inherit (pkgsFor system) deploy-rs;
@@ -109,12 +155,18 @@
     in
     {
       nixosConfigurations = {
-        c1 = mkHMNixos "x86_64-linux" [ ./hosts/c1 ];
+        c1 = mkHost "x86_64-linux" "minimal" [ ./hosts/c1 ];
-        c2 = mkHMNixos "x86_64-linux" [ ./hosts/c2 ];
+        c2 = mkHost "x86_64-linux" "minimal" [ ./hosts/c2 ];
-        c3 = mkHMNixos "x86_64-linux" [ ./hosts/c3 ];
+        c3 = mkHost "x86_64-linux" "minimal" [ ./hosts/c3 ];
-        alo-cloud-1 = mkHMNixos "aarch64-linux" [ ./hosts/alo-cloud-1 ];
+        alo-cloud-1 = mkHost "aarch64-linux" "cloud" [ ./hosts/alo-cloud-1 ];
-        zippy = mkHMNixos "x86_64-linux" [ ./hosts/zippy ];
+        zippy = mkHost "x86_64-linux" "minimal" [ ./hosts/zippy ];
-        chilly = mkHMNixos "x86_64-linux" [ ./hosts/chilly ];
+        chilly = mkHost "x86_64-linux" "workstation" [ ./hosts/chilly ];
+        sparky = mkHost "x86_64-linux" "minimal" [ ./hosts/sparky ];
+        beefy = mkHost "x86_64-linux" "desktop" [ ./hosts/beefy ];
+        stinky = mkHost "aarch64-linux" "minimal" [
+          nixos-hardware.nixosModules.raspberry-pi-4
+          ./hosts/stinky
+        ];
       };
 
       deploy = {
@@ -167,9 +219,63 @@
               };
             };
           };
+          sparky = {
+            hostname = "sparky";
+            profiles = {
+              system = {
+                user = "root";
+                path = (deployPkgsFor "x86_64-linux").deploy-rs.lib.activate.nixos self.nixosConfigurations.sparky;
+              };
+            };
+          };
+          beefy = {
+            hostname = "beefy";
+            profiles = {
+              system = {
+                user = "root";
+                path = (deployPkgsFor "x86_64-linux").deploy-rs.lib.activate.nixos self.nixosConfigurations.beefy;
+              };
+            };
+          };
+          stinky = {
+            hostname = "stinky";
+            profiles = {
+              system = {
+                user = "root";
+                path = (deployPkgsFor "aarch64-linux").deploy-rs.lib.activate.nixos self.nixosConfigurations.stinky;
+              };
+            };
+          };
         };
       };
 
+      # SD card image for stinky (Raspberry Pi 4)
+      packages.aarch64-linux.stinky-sdImage = self.nixosConfigurations.stinky.config.system.build.sdImage;
+
+      # Apps - utility scripts
+      apps.x86_64-linux.diff-configs = {
+        type = "app";
+        program = "${(pkgsFor "x86_64-linux").writeShellScriptBin "diff-configs" (builtins.readFile ./scripts/diff-configs.sh)}/bin/diff-configs";
+      };
+
+      apps.aarch64-linux.diff-configs = {
+        type = "app";
+        program = "${(pkgsFor "aarch64-linux").writeShellScriptBin "diff-configs" (builtins.readFile ./scripts/diff-configs.sh)}/bin/diff-configs";
+      };
+
+      # Development shells
+      devShells.x86_64-linux.default = (pkgsFor "x86_64-linux").mkShell {
+        packages = with (pkgsFor "x86_64-linux"); [
+          nvd
+        ];
+      };
+
+      devShells.aarch64-linux.default = (pkgsFor "aarch64-linux").mkShell {
+        packages = with (pkgsFor "aarch64-linux"); [
+          nvd
+        ];
+      };
+
       checks = builtins.mapAttrs (system: deployLib: deployLib.deployChecks self.deploy) deploy-rs.lib;
 
       formatter.x86_64-linux = nixpkgs.legacyPackages.x86_64-linux.nixfmt-rfc-style;

home/default.nix

@@ -1,7 +1,9 @@
-{ pkgs, ... }:
+{ pkgs, profile ? "cli", ... }:
 {
+  imports = [ ./programs/${profile}.nix ];
+
   home = {
-    packages = (import ./packages.nix { inherit pkgs; }).packages;
+    packages = (import ./packages.nix { inherit pkgs profile; }).packages;
     stateVersion = "24.05"; # TODO: unify this with the references in flake.nix:inputs
 
     sessionVariables = {
@@ -10,34 +12,27 @@
       MOSH_SERVER_NETWORK_TMOUT = 604800;
       NOMAD_ADDR = "http://nomad.service.consul:4646";
       LESS = "-F -i -M -+S -R -w -X -z-4";
-      SYSTEMD_LESS = "FiM+SRwXz-4";
+      SYSTEMD_LESS = "FiM+SRwX";
       NIX_LD = "${pkgs.glibc}/lib/ld-linux-x86-64.so.2";
       NIX_LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath [
         pkgs.stdenv.cc.cc
       ];
       GEMINI_API_KEY = "AIzaSyBZkifYOFNKCjROLa_GZyzQbB2EbEYIby4";
       LLM_GEMINI_KEY = "AIzaSyBZkifYOFNKCjROLa_GZyzQbB2EbEYIby4";
+      PLAYWRIGHT_BROWSERS_PATH = "${pkgs.unstable.playwright-driver.browsers}";
+      NIXOS_OZONE_WL = "1";
     };
 
     shellAliases = {
       reload-home-manager-config = "home-manager switch --flake ${builtins.toString ./.}";
     };
 
-    persistence."/persist/home/ppetru" = {
+    file.".ssh/rc".text = ''
-      directories = [
+      #!/bin/sh
-        ".cache/nix"
+      if test "$SSH_AUTH_SOCK"; then
-        ".cache/nix-index"
+        ln -sf "$SSH_AUTH_SOCK" "$HOME/.ssh/ssh_auth_sock"
-        ".config/io.datasette.llm/"
+      fi
-        ".config/sops/"
+    '';
-        ".docker/"
+    file.".ssh/rc".executable = true;
-        ".local/share/fish"
-        ".ssh"
-        "projects"
-      ];
-      files = [ ];
-      allowOther = true;
-    };
   };
-
-  programs = import ./programs.nix { inherit pkgs; };
 }

home/packages.nix

@@ -1,30 +1,7 @@
-{ pkgs }:
+{ pkgs, profile ? "workstation" }:
 let
-  corePkgs = with pkgs; [
+  profilePackages = import ./profiles/${profile}.nix { inherit pkgs; };
-    direnv
-    fzf
-    git
-    mosh
-    ripgrep
-    tmux
-    zsh
-  ];
-
-  pythonEnv = pkgs.unstable.python3.withPackages (ps: [
-    ps.aider-chat
-    ps.google-generativeai
-    ps.ipython
-    ps.llm
-    ps.llm-gemini
-  ]);
-
-  fishPkgs = with pkgs.fishPlugins; [
-    pure
-    # don't add failed commands to history
-    sponge
-    transient-fish
-  ];
 in
 {
-  packages = corePkgs ++ [ pythonEnv ] ++ fishPkgs;
+  packages = profilePackages.packages;
 }

home/profiles/cloud.nix

@@ -0,0 +1,22 @@
+{ pkgs }:
+let
+  corePkgs = with pkgs; [
+    direnv
+    fzf
+    git
+    mosh
+    ripgrep
+    tmux
+    zsh
+  ];
+
+  fishPkgs = with pkgs.fishPlugins; [
+    pure
+    # don't add failed commands to history
+    sponge
+    transient-fish
+  ];
+in
+{
+  packages = corePkgs ++ fishPkgs;
+}

home/profiles/desktop.nix

@@ -0,0 +1,13 @@
+{ pkgs }:
+let
+  workstationProfile = import ./workstation.nix { inherit pkgs; };
+
+  desktopPkgs = with pkgs; [
+    browser-previews.google-chrome
+    foot # Wayland-native terminal emulator
+    wofi # Application launcher for Wayland
+  ];
+in
+{
+  packages = workstationProfile.packages ++ desktopPkgs;
+}

home/profiles/minimal.nix

@@ -0,0 +1,5 @@
+{ pkgs }:
+{
+  # Minimal profile: reuses server.nix for basic package list
+  packages = (import ./server.nix { inherit pkgs; }).packages;
+}

home/profiles/server.nix

@@ -0,0 +1,22 @@
+{ pkgs }:
+let
+  corePkgs = with pkgs; [
+    direnv
+    fzf
+    git
+    mosh
+    ripgrep
+    tmux
+    zsh
+  ];
+
+  fishPkgs = with pkgs.fishPlugins; [
+    pure
+    # don't add failed commands to history
+    # sponge
+    transient-fish
+  ];
+in
+{
+  packages = corePkgs ++ fishPkgs;
+}

home/profiles/workstation.nix

@@ -0,0 +1,20 @@
+{ pkgs }:
+let
+  serverProfile = import ./server.nix { inherit pkgs; };
+
+  cliPkgs = with pkgs; [
+    unstable.claude-code
+    unstable.codex
+    unstable.gemini-cli
+  ];
+
+  pythonEnv = pkgs.unstable.python3.withPackages (ps: [
+    ps.google-generativeai
+    ps.ipython
+    ps.llm
+    ps.llm-gemini
+  ]);
+in
+{
+  packages = serverProfile.packages ++ cliPkgs ++ [ pythonEnv ];
+}

home/programs/cloud.nix

@@ -0,0 +1,8 @@
+{ pkgs, ... }:
+{
+  imports = [ ./server.nix ];
+
+  # Cloud-specific home-manager programs
+  # Currently uses server profile's minimal CLI setup
+  # Add cloud-specific customizations here if needed in the future
+}

home/programs/desktop.nix

@@ -0,0 +1,27 @@
+{ pkgs, ... }:
+{
+  imports = [ ./workstation.nix ];
+
+  # Override ghostty to use unstable version (1.2.0+) for ssh-terminfo support
+  programs.ghostty.package = pkgs.unstable.ghostty;
+
+  wayland.windowManager.hyprland = {
+    enable = true;
+    settings = {
+      # Remap CapsLock to Super (Mod4)
+      "$mod" = "SUPER";
+
+      input = {
+        kb_options = "caps:super";
+      };
+
+      "$browser" = "google-chrome-stable --new-window --ozone-platform=wayland";
+    };
+  };
+
+  # Extend ghostty configuration from omarchy-nix
+  programs.ghostty.settings = {
+    # Automatically handle TERM compatibility for SSH (requires ghostty 1.2.0+)
+    shell-integration-features = "ssh-terminfo";
+  };
+}

home/programs/minimal.nix

@@ -0,0 +1,5 @@
+{ pkgs, ... }:
+{
+  # Minimal profile: reuses server.nix for basic CLI programs
+  imports = [ ./server.nix ];
+}

home/programs/server.nix

@@ -1,6 +1,7 @@
 { pkgs, ... }:
 {
-  dircolors = {
+  programs = {
+    dircolors = {
     enable = true;
     extraConfig = ''
       # Dark 256 color solarized theme for the color GNU ls utility.
@@ -315,88 +316,94 @@
       .ogx 01;38;5;166
     '';
     settings = pkgs.lib.mkForce { };
-  };
-
-  direnv = {
-    enable = true;
-    nix-direnv.enable = true;
-  };
-
-  fish = {
-    enable = true;
-
-    shellAbbrs = {
-      fix-ssh = "eval $(tmux show-env | grep ^SSH_AUTH_SOCK | sed 's/=/ /;s/^/set /')";
-      diff-persist = "sudo rsync -amvxx --dry-run --no-links --exclude '/tmp/*' --exclude '/root/*' / /persist/ | rg -v '^skipping|/$'";
     };
 
-    shellInit = ''
+    direnv = {
-      set fish_greeting
+      enable = true;
-
+      nix-direnv.enable = true;
-      set pure_color_mute green
-      set pure_check_for_new_release false
-      set pure_enable_nixdevshell true
-      set pure_show_prefix_root_prompt true
-      set sponge_regex_patterns 'password|passwd'
-    '';
-  };
-
-  fzf = {
-    enable = true;
-  };
-
-  git = {
-    enable = true;
-    userEmail = "petru@paler.net";
-    userName = "Petru Paler";
-  };
-
-  home-manager = {
-    enable = true;
-  };
-
-  less.enable = true;
-
-  lesspipe.enable = false;
-
-  nix-index-database.comma.enable = true;
-
-  nixvim = {
-    enable = true;
-
-    defaultEditor = true;
-    viAlias = true;
-    # makes lessopen complain sometimes
-    vimAlias = false;
-
-    opts = {
-      tabstop = 4;
-      softtabstop = 4;
-      shiftwidth = 4;
-      expandtab = true;
-      shiftround = true;
     };
 
-    plugins = {
+    fish = {
-      nix.enable = true;
+      enable = true;
+
+      shellAbbrs = {
+        diff-persist = "sudo rsync -amvxx --dry-run --no-links --exclude '/tmp/*' --exclude '/root/*' / /persist/ | rg -v '^skipping|/$'";
+      };
+
+      shellInit = ''
+        set fish_greeting
+
+        set pure_color_mute green
+        set pure_check_for_new_release false
+        set pure_enable_nixdevshell true
+        set pure_show_prefix_root_prompt true
+        set sponge_regex_patterns 'password|passwd'
+      '';
     };
-  };
 
-  tmux = {
+    fzf = {
-    enable = true;
+      enable = true;
-    prefix = "C-t";
+    };
-    terminal = "screen-256color";
-    historyLimit = 20000;
-    keyMode = "vi";
-    extraConfig = ''
-      bind-key t send-prefix
-      bind-key C-t last-window
 
-      set -g status-left ""
+    git = {
-      set -g status-right ""
+      enable = true;
+      userEmail = "petru@paler.net";
+      userName = "Petru Paler";
+    };
 
-      setw -g automatic-rename on
+    home-manager = {
-      set -g set-titles on
+      enable = true;
-    '';
+    };
+
+    less.enable = true;
+
+    lesspipe.enable = false;
+
+    nix-index-database.comma.enable = true;
+
+    nixvim = {
+      enable = true;
+
+      defaultEditor = true;
+      viAlias = true;
+      # makes lessopen complain sometimes
+      vimAlias = false;
+
+      opts = {
+        tabstop = 4;
+        softtabstop = 4;
+        shiftwidth = 4;
+        expandtab = true;
+        shiftround = true;
+      };
+
+      plugins = {
+        nix.enable = true;
+      };
+    };
+
+    tmux = {
+      enable = true;
+      prefix = "C-t";
+      terminal = "screen-256color";
+      historyLimit = 20000;
+      keyMode = "vi";
+      extraConfig = ''
+        bind-key t send-prefix
+        bind-key C-t last-window
+
+        set -g status-left ""
+        set -g status-right ""
+
+        setw -g automatic-rename on
+        set -g set-titles on
+
+        # first, unset update-environment[SSH_AUTH_SOCK] (idx 3), to prevent
+        # the client overriding the global value
+        set-option -g -u update-environment[3]
+        # And set the global value to our static symlink'd path:
+        set-environment -g SSH_AUTH_SOCK $HOME/.ssh/ssh_auth_sock
+      '';
+    };
   };
 }

home/programs/workstation.nix

@@ -0,0 +1,6 @@
+{ pkgs, ... }:
+{
+  imports = [ ./server.nix ];
+
+  # Add workstation-specific programs here if needed in the future
+}

hosts/alo-cloud-1/default.nix

@@ -1,8 +1,8 @@
-{ pkgs, inputs, ... }:
+{ pkgs, lib, inputs, ... }:
 {
   imports = [
     ../../common/global
-    ../../common/cloud-node.nix
+    ../../common/minimal-node.nix
     ./hardware.nix
     ./reverse-proxy.nix
   ];
@@ -12,4 +12,27 @@
 
   networking.hostName = "alo-cloud-1";
   services.tailscaleAutoconnect.authkey = "tskey-auth-kbdARC7CNTRL-pNQddmWV9q5C2sRV3WGep5ehjJ1qvcfD";
+
+  services.tailscale = {
+    enable = true;
+    useRoutingFeatures = lib.mkForce "server";   # enables IPv4/IPv6 forwarding + loose rp_filter
+    extraUpFlags = [ "--advertise-exit-node" ];
+  };
+
+  networking.nat = {
+    enable = true;
+    externalInterface = "enp1s0";
+    internalInterfaces = [ "tailscale0" ];
+  };
+
+  networking.firewall = {
+    enable = lib.mkForce true;
+    allowedTCPPorts = [ 80 443 ];  # Public web traffic only
+    allowedUDPPorts = [ 41641 ];   # Tailscale
+    trustedInterfaces = [ "tailscale0" ];  # Full access via VPN
+  };
+
+  services.openssh = {
+    settings.PasswordAuthentication = false;  # Keys only
+  };
 }

hosts/alo-cloud-1/reverse-proxy.nix

@@ -1,7 +1,7 @@
-{ pkgs, ... }:
+{ pkgs, config, ... }:
 {
   environment.systemPackages = [ pkgs.traefik ];
-  environment.persistence."/persist".files = [ "/acme/acme.json" ];
+  environment.persistence.${config.custom.impermanence.persistPath}.files = [ "/acme/acme.json" ];
 
   services.traefik = {
     enable = true;
@@ -73,7 +73,7 @@
           wordpress-paler-net = {
             entryPoints = "websecure";
             rule = "Host(`wordpress.paler.net`)";
-            service = "alo-cluster";
+            service = "varnish-cache";
           };
 
           ines-paler-net = {
@@ -117,6 +117,12 @@
             rule = "Host(`musictogethersilvercoast.pt`)";
             service = "varnish-cache";
           };
+
+          alo-land = {
+            entryPoints = "websecure";
+            rule = "Host(`alo.land`)";
+            service = "varnish-cache";
+          };
         };
       };
     };
@@ -135,6 +141,15 @@
         .host = "100.64.229.126";
         .port = "10080";
       }
+
+      sub vcl_backend_response {
+          # default TTL if backend didn't specify one
+          if (beresp.ttl <= 0s) {
+            set beresp.ttl = 1h;
+          }
+          # serve stale content in case home link is down
+          set beresp.grace = 240h;
+      }
     '';
   };
 }

hosts/beefy/default.nix

@@ -0,0 +1,24 @@
+{ pkgs, inputs, ... }:
+{
+  imports = [
+    ../../common/encrypted-btrfs-layout.nix
+    ../../common/global
+    ../../common/desktop-node.nix     # Hyprland + GUI environment
+    ../../common/cluster-member.nix  # Consul + storage clients
+    ../../common/cluster-tools.nix    # Nomad CLI (no service)
+    ./hardware.nix
+  ];
+
+  diskLayout = {
+    mainDiskDevice = "/dev/disk/by-id/nvme-CT1000P3PSSD8_25164F81F31D";
+    #keyDiskDevice = "/dev/disk/by-id/usb-Intenso_Micro_Line_22080777650797-0:0";
+    keyDiskDevice = "/dev/sda";
+  };
+
+  networking.hostName = "beefy";
+  networking.cluster.primaryInterface = "enp1s0";
+  services.tailscaleAutoconnect.authkey = "tskey-auth-k79UsDTw2v11CNTRL-oYqji35BE9c7CqM89Dzs9cBF14PmqYsi";
+
+  # Enable all SysRq functions for debugging hangs
+  boot.kernel.sysctl."kernel.sysrq" = 1;
+}

hosts/beefy/hardware.nix

@@ -0,0 +1,19 @@
+{
+  config,
+  lib,
+  pkgs,
+  modulesPath,
+  ...
+}:
+
+{
+  imports = [ (modulesPath + "/installer/scan/not-detected.nix") ];
+
+  boot.initrd.availableKernelModules = [ "nvme" "xhci_pci" "usbhid" "usb_storage" "sd_mod" ];
+  boot.initrd.kernelModules = [ ];
+  boot.kernelModules = [ "kvm-amd" ];
+  boot.extraModulePackages = [ ];
+
+  nixpkgs.hostPlatform = "x86_64-linux";
+  hardware.cpu.amd.updateMicrocode = true;  # Uncomment for AMD
+}

hosts/c1/default.nix

@@ -3,7 +3,14 @@
   imports = [
     ../../common/encrypted-btrfs-layout.nix
     ../../common/global
-    ../../common/compute-node.nix
+    ../../common/cluster-member.nix  # Consul + storage clients
+    ../../common/nomad-worker.nix     # Nomad client (runs jobs)
+    ../../common/nomad-server.nix     # Consul + Nomad server mode
+    ../../common/nfs-services-standby.nix  # NFS standby for /data/services
+    # To promote to NFS server (during failover):
+    # 1. Follow procedure in docs/NFS_FAILOVER.md
+    # 2. Replace above line with: ../../common/nfs-services-server.nix
+    # 3. Add nfsServicesServer.standbys = [ "c2" ]; (or leave empty)
     ./hardware.nix
   ];
 
@@ -15,4 +22,9 @@
 
   networking.hostName = "c1";
   services.tailscaleAutoconnect.authkey = "tskey-auth-k2nQ771YHM11CNTRL-YVpoumL2mgR6nLPG51vNhRpEKMDN7gLAi";
+
+  nfsServicesStandby.replicationKeys = [
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHyTKsMCbwCIlMcC/aopgz5Yfx/Q9QdlWC9jzMLgYFAV root@zippy-replication"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIO5s73FSUiysHijWRGYCJY8lCtZkX1DGKAqp2671REDq root@sparky-replication"
+  ];
 }

hosts/c2/default.nix

@@ -3,16 +3,18 @@
   imports = [
     ../../common/encrypted-btrfs-layout.nix
     ../../common/global
-    ../../common/compute-node.nix
+    ../../common/cluster-member.nix  # Consul + storage clients
+    ../../common/nomad-worker.nix     # Nomad client (runs jobs)
+    ../../common/nomad-server.nix     # Consul + Nomad server mode
     ./hardware.nix
   ];
 
   diskLayout = {
-    mainDiskDevice = "/dev/disk/by-id/nvme-SAMSUNG_MZVLB256HAHQ-000H1_S425NA1M132963";
+    mainDiskDevice = "/dev/disk/by-id/nvme-KINGSTON_SNV3S1000G_50026B73841C1892";
     #keyDiskDevice = "/dev/disk/by-id/usb-Intenso_Micro_Line_22080777650675-0:0";
     keyDiskDevice = "/dev/sda";
   };
 
   networking.hostName = "c2";
-  services.tailscaleAutoconnect.authkey = "tskey-auth-kbYnZK2CNTRL-SpUVCuzS6P3ApJiDaB6RM3M4b8M9TXgS";
+  services.tailscaleAutoconnect.authkey = "tskey-auth-kQ11fTmrzd11CNTRL-N4c2L3SAzUbvcAVhqCFWUbAEasJNTknd";
 }

hosts/c3/default.nix

@@ -3,7 +3,10 @@
   imports = [
     ../../common/encrypted-btrfs-layout.nix
     ../../common/global
-    ../../common/compute-node.nix
+    ../../common/cluster-member.nix  # Consul + storage clients
+    ../../common/nomad-worker.nix     # Nomad client (runs jobs)
+    ../../common/nomad-server.nix     # Consul + Nomad server mode
+    ../../common/binary-cache-server.nix
     ./hardware.nix
   ];
 

hosts/chilly/default.nix

@@ -8,7 +8,9 @@
   imports = [
     ../../common/encrypted-btrfs-layout.nix
     ../../common/global
-    ../../common/base-node.nix
+    ../../common/workstation-node.nix # Dev tools (deploy-rs, docker, nix-ld)
+    ../../common/cluster-member.nix  # Consul + storage clients
+    ../../common/cluster-tools.nix    # Nomad CLI (no service)
     ./hardware.nix
   ];
 
@@ -19,8 +21,8 @@
   };
 
   networking.hostName = "chilly";
+  networking.cluster.primaryInterface = "br0";
   services.tailscaleAutoconnect.authkey = "tskey-auth-kRXS9oPyPm11CNTRL-BE6YnbP9J6ZZuV9dHkX17ZMnm1JGdu93";
-  services.consul.interface.advertise = lib.mkForce "br0";
 
   networking.useNetworkd = true;
   systemd.network.enable = true;

hosts/sparky/default.nix

@@ -0,0 +1,26 @@
+{ pkgs, inputs, ... }:
+{
+  imports = [
+    ../../common/encrypted-btrfs-layout.nix
+    ../../common/global
+    ../../common/cluster-member.nix
+    ../../common/nomad-worker.nix
+    ../../common/nfs-services-server.nix
+    # To move NFS server role to another host:
+    # 1. Follow procedure in docs/NFS_FAILOVER.md
+    # 2. Replace above line with: ../../common/nfs-services-standby.nix
+    # 3. Add nfsServicesStandby.replicationKeys with the new server's public key
+    ./hardware.nix
+  ];
+
+  diskLayout = {
+    mainDiskDevice = "/dev/disk/by-id/nvme-KIOXIA-EXCERIA_with_Heatsink_SSD_84GF7016FA4S";
+    #keyDiskDevice = "/dev/disk/by-id/usb-Intenso_Micro_Line_22080777660468-0:0";
+    keyDiskDevice = "/dev/sda";
+  };
+
+  networking.hostName = "sparky";
+  services.tailscaleAutoconnect.authkey = "tskey-auth-k6VC79UrzN11CNTRL-rvPmd4viyrQ261ifCrfTrQve7c2FesxrG";
+
+  nfsServicesServer.standbys = [ "c1" ];
+}

hosts/sparky/hardware.nix

@@ -0,0 +1,21 @@
+{
+  config,
+  lib,
+  pkgs,
+  modulesPath,
+  ...
+}:
+
+{
+  imports = [ (modulesPath + "/installer/scan/not-detected.nix") ];
+
+  boot.initrd.availableKernelModules = [ "xhci_pci" "ahci" "nvme" "usb_storage" "usbhid" "sd_mod" "rtsx_pci_sdmmc" ];
+  boot.initrd.kernelModules = [ ];
+  boot.kernelModules = [
+    "kvm-intel"
+  ];
+  boot.extraModulePackages = [ ];
+
+  nixpkgs.hostPlatform = "x86_64-linux";
+  hardware.cpu.intel.updateMicrocode = true;
+}

hosts/stinky/default.nix

@@ -0,0 +1,61 @@
+{
+  lib,
+  pkgs,
+  config,
+  ...
+}:
+{
+  imports = [
+    ../../common/global
+    ../../common/impermanence-common.nix  # Impermanence with custom root config (see hardware.nix)
+    ../../common/resource-limits.nix
+    ../../common/sshd.nix
+    ../../common/user-ppetru.nix
+    ../../common/wifi.nix
+    # Note: No systemd-boot.nix - Raspberry Pi uses generic-extlinux-compatible (from sd-image module)
+    ./hardware.nix
+  ];
+
+  hardware = {
+    raspberry-pi."4".apply-overlays-dtmerge.enable = true;
+    deviceTree = {
+      enable = true;
+      filter = "*rpi-4-*.dtb";
+    };
+  };
+
+  networking.hostName = "stinky";
+
+  # Configure impermanence for tmpfs root (filesystem config in hardware.nix)
+  custom.impermanence.persistPath = "/nix/persist";
+
+  # Tailscale configuration
+  services.tailscaleAutoconnect.authkey = "tskey-auth-kZC8HX3wSw11CNTRL-7QvqxAphyzM7QeMUTKXv2Ng2RK4XCmg9A";
+
+  # OctoPrint for 3D printer
+  services.octoprint = {
+    enable = true;
+  };
+
+  # Persist OctoPrint data
+  environment.persistence.${config.custom.impermanence.persistPath}.directories = [
+    "/var/lib/octoprint"
+  ];
+
+  # Pi HQ Camera support
+  boot.kernelModules = [ "bcm2835-v4l2" ];
+
+  environment.systemPackages = with pkgs; [
+    libcamera
+    libraspberrypi
+    raspberrypi-eeprom
+  ];
+
+  # Firewall: Allow access to OctoPrint
+  networking.firewall.allowedTCPPorts = [
+    5000  # OctoPrint
+  ];
+
+  # Override global default (stinky is a new system with 25.05)
+  system.stateVersion = lib.mkForce "25.05";
+}

hosts/stinky/hardware.nix

@@ -0,0 +1,73 @@
+{
+  config,
+  lib,
+  pkgs,
+  modulesPath,
+  ...
+}:
+{
+  imports = [
+    (modulesPath + "/installer/sd-card/sd-image-aarch64.nix")
+  ];
+
+  # Raspberry Pi 4 platform
+  nixpkgs.hostPlatform = lib.mkDefault "aarch64-linux";
+
+  # Disable ZFS (not needed, and broken with latest kernel)
+  boot.supportedFilesystems.zfs = lib.mkForce false;
+
+  # Boot configuration - provided by sd-image-aarch64.nix
+  # (grub disabled, generic-extlinux-compatible enabled, U-Boot setup)
+
+  # /boot/firmware is automatically configured by sd-image module
+  # Device: /dev/disk/by-label/FIRMWARE (vfat)
+
+  # tmpfs root with impermanence
+  # Override sd-image module's ext4 root definition with mkForce
+  fileSystems."/" = lib.mkForce {
+    device = "none";
+    fsType = "tmpfs";
+    options = [
+      "defaults"
+      "size=2G"
+      "mode=755"
+    ];
+  };
+
+  # The SD partition contains /nix/store and /nix/persist at its root
+  # Mount it at a hidden location, then bind mount its /nix to /nix
+  fileSystems."/mnt/nixos-sd" = {
+    device = "/dev/disk/by-label/NIXOS_SD";
+    fsType = "ext4";
+    options = [ "noatime" ];
+    neededForBoot = true;
+  };
+
+  # Bind mount /nix from the SD partition
+  fileSystems."/nix" = {
+    device = "/mnt/nixos-sd/nix";
+    fsType = "none";
+    options = [ "bind" ];
+    neededForBoot = true;
+    depends = [ "/mnt/nixos-sd" ];
+  };
+
+  # No swap on SD card (wear concern)
+  swapDevices = [ ];
+
+  # SD image build configuration
+  sdImage = {
+    compressImage = true;
+
+    # Populate root with directories
+    populateRootCommands = ''
+      mkdir -p ./files/boot
+      ${config.boot.loader.generic-extlinux-compatible.populateCmd} -c ${config.system.build.toplevel} -d ./files/boot
+
+      # Create /nix/persist directory structure for impermanence
+      mkdir -p ./files/nix/persist/var/lib/nixos
+      mkdir -p ./files/nix/persist/home/ppetru
+      mkdir -p ./files/nix/persist/etc
+    '';
+  };
+}

hosts/zippy/default.nix

@@ -3,8 +3,8 @@
   imports = [
     ../../common/encrypted-btrfs-layout.nix
     ../../common/global
-    ../../common/compute-node.nix
+    ../../common/cluster-member.nix  # Consul + storage clients
-    ../../common/dev-node.nix
+    ../../common/nomad-worker.nix     # Nomad client (runs jobs)
     ./hardware.nix
   ];
 

scripts/diff-configs.sh

@@ -0,0 +1,374 @@
+#!/usr/bin/env bash
+# Compare NixOS configurations between current state and HEAD
+# Shows what would change if you committed the current changes
+#
+# Requirements: nvd must be in PATH
+# Run inside `nix develop` or with direnv enabled
+
+set -euo pipefail
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+YELLOW='\033[0;33m'
+NC='\033[0m' # No Color
+
+# Normalize nix store paths by replacing 32-char hashes with placeholder
+normalize_nix_paths() {
+    sed -E 's|/nix/store/[a-z0-9]{32}-|/nix/store/HASH-|g'
+}
+
+# Filter diff output to remove hunks where only nix store hashes differ
+# Returns: filtered diff (empty if only hash changes), exit code 0 if real changes found
+filter_hash_only_diffs() {
+    local diff_output="$1"
+    local current_hunk=""
+    local output=""
+    local has_real_changes=false
+
+    # Process line by line
+    while IFS= read -r line || [ -n "$line" ]; do
+        if [[ "$line" =~ ^@@ ]]; then
+            # New hunk starts - process previous one if it exists
+            if [ -n "$current_hunk" ]; then
+                if hunk_has_real_changes "$current_hunk"; then
+                    output+="$current_hunk"$'\n'
+                    has_real_changes=true
+                fi
+            fi
+            # Start new hunk
+            current_hunk="$line"$'\n'
+        else
+            # Add line to current hunk
+            current_hunk+="$line"$'\n'
+        fi
+    done <<< "$diff_output"
+
+    # Process last hunk
+    if [ -n "$current_hunk" ]; then
+        if hunk_has_real_changes "$current_hunk"; then
+            output+="$current_hunk"
+            has_real_changes=true
+        fi
+    fi
+
+    # Remove trailing newline
+    output="${output%$'\n'}"
+
+    if [ "$has_real_changes" = true ]; then
+        echo "$output"
+        return 0
+    else
+        return 1
+    fi
+}
+
+# Check if a diff hunk has real changes (not just hash changes)
+hunk_has_real_changes() {
+    local hunk="$1"
+
+    # Use temp file to avoid bash here-string issues
+    local temp_hunk=$(mktemp)
+    printf '%s' "$hunk" > "$temp_hunk"
+
+    local minus_lines=()
+    local plus_lines=()
+
+    # Extract - and + lines (skip @@ and context lines)
+    while IFS= read -r line || [ -n "$line" ]; do
+        if [[ "$line" =~ ^- && ! "$line" =~ ^--- ]]; then
+            minus_lines+=("${line:1}")  # Remove the - prefix
+        elif [[ "$line" =~ ^\+ && ! "$line" =~ ^\+\+\+ ]]; then
+            plus_lines+=("${line:1}")  # Remove the + prefix
+        fi
+    done < "$temp_hunk"
+
+    rm -f "$temp_hunk"
+
+    # If counts don't match, there are structural changes
+    if [ ${#minus_lines[@]} -ne ${#plus_lines[@]} ]; then
+        return 0  # Has real changes
+    fi
+
+    # If no changes at all, skip
+    if [ ${#minus_lines[@]} -eq 0 ]; then
+        return 1  # No real changes
+    fi
+
+    # Compare each pair of lines after normalization
+    for i in "${!minus_lines[@]}"; do
+        local minus_norm=$(echo "${minus_lines[$i]}" | normalize_nix_paths)
+        local plus_norm=$(echo "${plus_lines[$i]}" | normalize_nix_paths)
+
+        if [ "$minus_norm" != "$plus_norm" ]; then
+            return 0  # Has real changes
+        fi
+    done
+
+    # All changes are hash-only
+    return 1
+}
+
+# Check for nvd
+if ! command -v nvd &> /dev/null; then
+    echo "Error: nvd not found in PATH"
+    echo "Run this script inside 'nix develop' or enable direnv"
+    exit 1
+fi
+
+# Parse flags
+verbose=false
+deep=false
+hosts_args=()
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            echo "Usage: $0 [-v|--verbose] [-d|--deep] [HOST...]"
+            echo "Compare NixOS configurations between working tree and HEAD"
+            echo ""
+            echo "Options:"
+            echo "  -v, --verbose   Show detailed list of added/removed store paths"
+            echo "  -d, --deep      Show content diffs of changed files (implies -v)"
+            echo ""
+            echo "Arguments:"
+            echo "  HOST            One or more hostnames to compare (default: all)"
+            echo ""
+            echo "Examples:"
+            echo "  $0                      # Compare all hosts (summary)"
+            echo "  $0 -v c1                # Compare c1 with path list"
+            echo "  $0 --deep c1            # Compare c1 with content diffs"
+            echo "  $0 c1 c2 c3            # Compare only c1, c2, c3"
+            exit 0
+            ;;
+        -v|--verbose)
+            verbose=true
+            shift
+            ;;
+        -d|--deep)
+            deep=true
+            verbose=true  # deep implies verbose
+            shift
+            ;;
+        *)
+            hosts_args+=("$1")
+            shift
+            ;;
+    esac
+done
+
+# Restore positional parameters
+set -- "${hosts_args[@]}"
+
+# Check if we're in a git repo
+if ! git rev-parse --git-dir > /dev/null 2>&1; then
+    echo "Error: Not in a git repository"
+    exit 1
+fi
+
+# Check if there are any changes
+if git diff --quiet && git diff --cached --quiet; then
+    echo "No changes detected between working tree and HEAD"
+    exit 0
+fi
+
+echo "Comparing configurations: current working tree vs HEAD"
+echo "======================================================="
+echo
+
+# Get list of hosts to compare
+if [ $# -gt 0 ]; then
+    # Use hosts provided as arguments
+    hosts="$@"
+    echo -e "${YELLOW}Comparing selected hosts: $hosts${NC}"
+else
+    # Get all hosts from flake
+    echo "Discovering all hosts from flake..."
+    hosts=$(nix eval --raw .#deploy.nodes --apply 'nodes: builtins.concatStringsSep "\n" (builtins.attrNames nodes)' 2>/dev/null)
+
+    if [ -z "$hosts" ]; then
+        echo "Error: No hosts found in flake"
+        exit 1
+    fi
+fi
+
+echo
+
+# Create temp worktree at HEAD
+worktree=$(mktemp -d)
+trap "git worktree remove --force '$worktree' &>/dev/null || true; rm -rf '$worktree'" EXIT
+
+echo "Creating temporary worktree at HEAD..."
+git worktree add --quiet --detach "$worktree" HEAD
+
+echo "Building and comparing configurations..."
+echo
+
+any_changes=false
+
+for host in $hosts; do
+    echo -e "${BLUE}━━━ $host ━━━${NC}"
+
+    # Build current (with uncommitted changes)
+    echo -n "  Building current... "
+    if ! current=$(nix build --no-link --print-out-paths \
+        ".#nixosConfigurations.$host.config.system.build.toplevel" 2>/dev/null); then
+        echo -e "${RED}FAILED${NC}"
+        # Re-run to show error
+        nix build --no-link ".#nixosConfigurations.$host.config.system.build.toplevel" 2>&1 | head -20 | sed 's/^/  /'
+        continue
+    fi
+    echo "done"
+
+    # Build HEAD
+    echo -n "  Building HEAD...    "
+    if ! head=$(nix build --no-link --print-out-paths \
+        "$worktree#nixosConfigurations.$host.config.system.build.toplevel" 2>/dev/null); then
+        echo -e "${RED}FAILED${NC}"
+        # Re-run to show error
+        nix build --no-link "$worktree#nixosConfigurations.$host.config.system.build.toplevel" 2>&1 | head -20 | sed 's/^/  /'
+        continue
+    fi
+    echo "done"
+
+    # Compare
+    if [ "$head" = "$current" ]; then
+        echo -e "  ${GREEN}✓ No changes${NC}"
+    else
+        any_changes=true
+        echo -e "  ${RED}⚠ Configuration changed${NC}"
+        echo
+
+        # Show nvd summary
+        if ! nvd diff "$head" "$current" 2>&1; then
+            echo -e "  ${RED}(nvd diff failed - see error above)${NC}"
+        fi
+
+        # Show detailed closure diff if verbose
+        if [ "$verbose" = true ]; then
+            echo
+            echo -e "  ${YELLOW}Changed store paths:${NC}"
+
+            # Get paths unique to HEAD and current
+            head_only=$(comm -23 <(nix-store -q --requisites "$head" 2>/dev/null | sort) \
+                                  <(nix-store -q --requisites "$current" 2>/dev/null | sort))
+            current_only=$(comm -13 <(nix-store -q --requisites "$head" 2>/dev/null | sort) \
+                                    <(nix-store -q --requisites "$current" 2>/dev/null | sort))
+
+            # Count changes
+            removed_count=$(echo "$head_only" | wc -l)
+            added_count=$(echo "$current_only" | wc -l)
+
+            echo -e "    ${RED}Removed ($removed_count paths):${NC}"
+            echo "$head_only" | head -10 | sed 's|^/nix/store/[^-]*-|    - |'
+            if [ "$removed_count" -gt 10 ]; then
+                echo "    ... and $((removed_count - 10)) more"
+            fi
+
+            echo
+            echo -e "    ${GREEN}Added ($added_count paths):${NC}"
+            echo "$current_only" | head -10 | sed 's|^/nix/store/[^-]*-|    - |'
+            if [ "$added_count" -gt 10 ]; then
+                echo "    ... and $((added_count - 10)) more"
+            fi
+
+            # Show content diffs if deep mode
+            if [ "$deep" = true ]; then
+                echo
+                echo -e "  ${YELLOW}Content diffs of changed files:${NC}"
+
+                # Extract basenames for matching
+                declare -A head_paths
+                while IFS= read -r path; do
+                    [ -z "$path" ] && continue
+                    basename="${path#/nix/store/[a-z0-9]*-}"
+                    head_paths["$basename"]="$path"
+                done <<< "$head_only"
+
+                # Find matching pairs and diff them
+                matched=false
+                while IFS= read -r path; do
+                    [ -z "$path" ] && continue
+                    basename="${path#/nix/store/[a-z0-9]*-}"
+
+                    # Check if we have a matching path in head
+                    if [ -n "${head_paths[$basename]:-}" ]; then
+                        old_path="${head_paths[$basename]}"
+                        new_path="$path"
+                        matched=true
+
+                        echo
+                        echo -e "    ${BLUE}▸ $basename${NC}"
+
+                        # If it's a directory, diff all files within it
+                        if [ -d "$old_path" ] && [ -d "$new_path" ]; then
+                            # Count files to avoid processing huge directories
+                            file_count=$(find "$new_path" -maxdepth 3 -type f 2>/dev/null | wc -l)
+
+                            # Skip very large directories (e.g., system-path with 900+ files)
+                            if [ "$file_count" -gt 100 ]; then
+                                echo "      (skipping directory with $file_count files - too large)"
+                            else
+                                # Diff all files in the directory
+                                for file in $(find "$new_path" -maxdepth 3 -type f 2>/dev/null); do
+                                    [ -z "$file" ] && continue
+                                    relpath="${file#$new_path/}"
+                                    old_file="$old_path/$relpath"
+
+                                    if [ -f "$old_file" ] && [ -f "$file" ]; then
+                                        # Check if file is text
+                                        if file "$file" | grep -q "text"; then
+                                            # Get diff output
+                                            diff_output=$(diff -u "$old_file" "$file" 2>/dev/null | head -50 | tail -n +3 || true)
+
+                                            # Filter hash-only changes
+                                            if [ -n "$diff_output" ]; then
+                                                filtered_diff=$(filter_hash_only_diffs "$diff_output" || true)
+
+                                                if [ -n "$filtered_diff" ]; then
+                                                    echo -e "      ${YELLOW}$relpath:${NC}"
+                                                    echo "$filtered_diff" | sed 's/^/        /'
+                                                fi
+                                            fi
+                                        fi
+                                    fi
+                                done
+                            fi
+                        # If it's a file, diff it directly
+                        elif [ -f "$old_path" ] && [ -f "$new_path" ]; then
+                            if file "$new_path" | grep -q "text"; then
+                                # Get diff output
+                                diff_output=$(diff -u "$old_path" "$new_path" 2>/dev/null | head -50 | tail -n +3 || true)
+
+                                # Filter hash-only changes
+                                if [ -n "$diff_output" ]; then
+                                    filtered_diff=$(filter_hash_only_diffs "$diff_output" || true)
+
+                                    if [ -n "$filtered_diff" ]; then
+                                        echo "$filtered_diff" | sed 's/^/      /'
+                                    else
+                                        echo "      (only hash changes)"
+                                    fi
+                                fi
+                            else
+                                echo "      (binary file)"
+                            fi
+                        fi
+                    fi
+                done <<< "$current_only"
+
+                if [ "$matched" = false ]; then
+                    echo "    (no matching paths found to compare)"
+                fi
+            fi
+        fi
+    fi
+    echo
+done
+
+if [ "$any_changes" = false ]; then
+    echo -e "${GREEN}✓ All configurations unchanged${NC}"
+else
+    echo -e "${RED}⚠ Some configurations changed - review carefully before committing${NC}"
+fi

secrets/beefy.yaml

@@ -0,0 +1,25 @@
+kopia: ENC[AES256_GCM,data:/6jqArNgeBoGnEdJ1eshrsG8RJs=,iv:2nNdrKczus70QDdvO/MC2wJubGnAf3M8PtzSe1aoBF4=,tag:aOoktsqhQLXr0YkjYZq4OQ==,type:str]
+sops:
+    age:
+        - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBBODczb2FsMis0cVIvN2FK
+            UG1QVWt6U1MvaU1Rd0dXWDhmK2RpZ2dSUXlRClZ5ZGRZRk1vUFp0eVVwVzA5R0Ni
+            RUdjVFh5T3o5ZllFaHVFS1pCWjNzVkEKLS0tIGoxNWhhZUhVSms5cEJEa3lZQWlz
+            aXNBMWhUNFBHTDJUZEtDeU85Z1pPU1kKWNm6Wk+Mbc9QIXMXiwleIvP4hlGLvmpI
+            u+udOAinxTxmB9LOXG+y3iPuS9n0B6Y+4WbTjKm9jEqaqNoW8JypJA==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age1cs8uqj243lspyp042ueu5aes4t3azgyuaxl9au70ggrl2meulq4sgqpc7y
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjTG1MZjM1bVNqeFNqeTgy
+            UXZBWVVacVVsaHJKMkJ1ZWdCbG4zS2tBWDFjCnpSbUw0ZFZMVENNNmYyTWZFdndL
+            RmxUajdsU1l1cmlZa2NQQjJublVsMmMKLS0tIHNpZmRpY2hIbVVZSUdGNHM2WnN6
+            R21jYU96SGVHOUxmZjlldS96K2VqbWcKC28wLdT/zx6yHluCLqB/cFRmc0Alq6AH
+            DqmAaxRhOg/SI5ljCX1gE5BB9rNIJ1Gq8+li7wCpsdfLMr5Yy/HAsw==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2025-11-04T20:25:17Z"
+    mac: ENC[AES256_GCM,data:llS+R5Pj51ZUkU8FkJx2KqqE4D42Uno3Btn31FadIl4kFamnrL6uJjbiNEJpFFO+SchXD3l7VCatbBhMSoxsPYd+rdDRT2klq+iIcZU/k413GC87xdmHIwWE+L2pujv36iBjtM+HJTSvXI0xOxjUmzH4FPdEa1r3Z5yGNnCI+Q4=,iv:ld6pSEzvKTSZtBb+QjHyqqj2VT05YegxBrUR2yxhjKY=,tag:7/vYBh8lDOcVXJL3esTIZQ==,type:str]
+    unencrypted_suffix: _unencrypted
+    version: 3.11.0

secrets/c2.yaml

@@ -1,30 +1,25 @@
 kopia: ENC[AES256_GCM,data:pZrOFlW5wy8I/leTc1mJEB31Kr0=,iv:COsdcI32ZD66M6h+5L2bBf1N8471LbVEt7TlhYQyMnM=,tag:hJXohn6/zUd5WOSYzXdPwQ==,type:str]
 sops:
-    kms: []
-    gcp_kms: []
-    azure_kv: []
-    hc_vault: []
     age:
         - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqN0txU0NKVVprUnlCWGtt
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpTGZsSS9MWmZFTFdKa0hz
-            azFFdzJuMHN1MVlWemJIQ0lQRU5TZURpQjEwCkNHcGVaUUtESTZCVVFpa2pxLzF6
+            SENqbHVIMzlPVGkvNThOQ0JHNXZFR1ZkdTFVClNoUVdUVkxEV3NCVXZ1eE5uY2pW
-            bmZmMVlqRWtvUVNtajNqWTZxNWJWZEEKLS0tIHovT1N1TFgrVjlXYUZSckJ2K1lr
+            TmVLSWRaaVd4ZzdVYnZvekpWK2dUb0kKLS0tIEw5WjVoc1ZBTmluUVhlVmdKc0tB
-            VWZoTjBWWVl3WjVSMXc5VENPbkJlNXMK1Mi9CDyY/zn090pgGIWmbY5fR/G9fpwm
+            bzZ1U0YydlNMSGExUTRrMWViWXhTekEK51bUaoMKTPTvGeG0vk9tu1TxkbgkNdff
-            rtl32WdXCcpo8c+XgzYowRw4qxNnNL4gzvGn+91And55eF25Ozl+yA==
+            u9NLDF1LhHOet7iisUOUFjXtZuA/1IFwUlFMKgF7w1PQtoA+G3+X6A==
             -----END AGE ENCRYPTED FILE-----
-        - recipient: age1gekmz8kc8r2lc2x6d4u63s2lnpmres4hu9wulxh29ch74ud7wfksq56xam
+        - recipient: age1jy7pe4530s8w904wtvrmpxvteztqy5ewdt92a7y3lq87sg9jce5qxxuydt
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAwMm1BWUxKdi9VNFNFOUdv
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA1N0JsTmJUTE5Qd3QyaDV5
-            UTB3ZzdiTVBUKzd1eFZ6ZWxteW1lc3NFOXljClFVUkRqVjVtSTg2aVluNnZNNzdx
+            ejBmMS82OHFSZW9tQTUvbVlKaVY2N0lqVWtZCnAxSnFreklwWG91cFFEelVHZ0pJ
-            RFVvT1hxUkR3SzU4NXFqbXNYUU5JWk0KLS0tICtFWFQveDB6SnVqNXRXZS9FbU9D
+            eDBYVzVwNHlZZUx0bXZvZm9GdUttR1UKLS0tIHc0N01UNFcxL1V2cHMwVXVkZ3pB
-            TDhodzYzV3AzWmdjQ0Q5UEJLWTFKT2sKoIz2O7Ot/F+crGjaYvCQRM5iuzMG3L3J
+            dUFCbXZtWjJNL0xEMmRtZjBEdnpLOWsKHaS5RtzjIRyQLEwiTrDaGB/oN6dMi/DL
-            sjysqAuESLrcUwPX574NwRaOKvlpTaNnKtl7ZXqKnbfucTJPc6o8NQ==
+            Hf0pBSvjLjuAL7YIgfTzLUuHR62PdgH39fhpd3W7LG4/WerXjLS/Lg==
             -----END AGE ENCRYPTED FILE-----
     lastmodified: "2025-03-12T11:54:39Z"
     mac: ENC[AES256_GCM,data:g8nz1Azs5X59ulimMRzgvKz9Y7lKnjFq2SCctdt+yMBLojlk8RXMSf7tY311dZLcd00wi8xsGlBY1XaCbDjIlkG4sLWuQIareYjfqGK5s0pRvELTTF2ZE9yY+5iYdeVkBe7yv44sWJGNN1BcgFpR9zUouA+6yKVt2/XcPu8+7Fs=,iv:zDyECD2w1bTq0xbart+cIjHBAmfSHnpFG5nHPbiT2UY=,tag:b50oQfRgLtI/XbkINuzx5A==,type:str]
-    pgp: []
     unencrypted_suffix: _unencrypted
     version: 3.9.4

secrets/common.yaml

@@ -1,75 +1,97 @@
 ppetru-password: ENC[AES256_GCM,data:ykxGdbwTLNGKGy7PI/6uLyeWzEyfTo6R7d56m8Lb7kyY6rF0ovDzMGv71ruBA3CwznIp5EaCopvKVXf35xIEyptpQJie++ireQ==,iv:ArWScjeDHp/4DurW+id6PLUiwnMVVwk7iD5S9Bzc8lc=,tag:uErsF74I5D1M86Yl78Gqlw==,type:str]
 sops:
-    kms: []
-    gcp_kms: []
-    azure_kv: []
-    hc_vault: []
     age:
         - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBDZ0dzYmlHVHRnSjNwUWhI
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4WExPaEtTdEljYkF1ZUQw
-            M2ZhTVRtN2ZIb0JacXpaM2hxejFab2tkdTJrCnFaVUpBSGpKUUNzL0xEMUo4Qkg4
+            UHhRNDJZb2wydWVUaXFmR213SjJsNDFKU0FjCnJ3Tk1yZDZkU3orcHZ2UDY3elRi
-            eWpLL3RRMkovR1AvYklLNXcvZGtrR2cKLS0tIExPN3lPTjFueGlzc3c4UFVjcHVO
+            WW9FMXU0cDNjV3QrOWo3MVB0UzMwakUKLS0tIEhQVldBVWhmR0k0WW9jTE0xc2ZW
-            Y0N2cFlKSkNSU01SOEN1OXIvRmtQbFEKDGuIvYvMhXWOz9GLIDSs/PEaXpwn3Ust
+            RWp4ZjlVN0FWaURlRHNONDhXdmJpS1EKZVXYyFRFD9KdyWuMoQytkQk4VxpBRyAV
-            BffIB24x01nPXdz0O+GHC8J4LkvdwRrYL5kX6vqZ/RWOQEpPDpjvFA==
+            lF4FA99wjGMhHFNQExnqYYLYtFkA18/SB6pkneOjdhIvEr0IFLJEqg==
             -----END AGE ENCRYPTED FILE-----
         - recipient: age1gtyw202hd07hddac9886as2cs8pm07e4exlnrgfm72lync75ng9qc5fjac
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA2TkxMSFJLbzdPTTdYR0hC
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjZ29wdk1aOHZJYWFjaG9v
-            U1dSVENJckFjVlBkUThrYnRUN2Q5ek9JcFhjCllmVFYzenF6SHByUGtFQUhTZWg2
+            RGxsek95QmtrZS9xRWdKMFdLSHZ3NmlZRGxzCnBvRXZkYnkxdkhJWkY0Ukg1M0dE
-            UTBLckZpYWQ2QXkxaWMvR2d6eHREYTgKLS0tIC9DMmZ0QXVUMlJ1NVZielV6dWlv
+            dWc3QWtCdkV5Ymd4MkxhZWl0ZDNCZXcKLS0tIGMrVWtNNWtscm9STUN1aHVZc2Ny
-            QWpybkVtcVhXOEhHRVFNMUJhMXhqSW8KcrPWhqGA8J5zIu5JaBd7N4VjR4iq/6Mq
+            Vm1oaFFTbTBpRWxuR3gxbUZ0YkZieVkKdaSSXrDzAUGkj3w8/YcFZaJTiUUEbJdw
-            qfi3OPQQlisN6zLzpM1kWs+BTzeAVzfC+UXKmuFeOUHcVJFG6TbLMg==
+            GjuLz7bxX8+HQvhSbu6/KCwG6R4j1eO5Zg1w0wYtyeUOV1HfZEGQog==
             -----END AGE ENCRYPTED FILE-----
         - recipient: age16yqffw4yl5jqvsr7tyd883vn98zw0attuv9g5snc329juff6dy3qw2w5wp
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBQMWltT2Yvdk96elVqWWI0
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBIMGpibmNRUDRFaFVOTDB4
-            WE5rR1ZjYXMxYXNiNWdlLzJWMkJObGFENnpVCnVsenJzdUIrc1M2cFJReUExSVU3
+            RVdTc1RrTmRPb0dlZGlpcGxuRlJ1L2w5MVVBCi9HdXNGZmdSaVZsQWRoa2RpVDNV
-            dWpMUk53dU9UTG9EUlNOTHBja0JqazAKLS0tIGYzU2pxVmpFR3UzaDhCd0ZrdkRj
+            OXBtS0pwYnhjS2hCUk10UUtwam4zMWcKLS0tIFV0dVpQNGpSOEVoZnE5OGpCZkxa
-            V1V5M2g2elRMR2lYZHM0QVRTdDFBOHcKFIlNxdy6KyZK42qsLgXNIR0lTmNnCOLS
+            MFMxSG95dmJncGJzR29mQkVzNjFIQUEKrJ0MDTBmiwiAaLt7CJ1pjlxuFvZJuRkR
-            xn0MT+YG6j4YP23OslkjXlr8lEAOggh6+2fFssRXtXZGKdQobQl3Jw==
+            EuLYOYLdVaxgZ442io5OE7wme0P4LLcxSAreDG84GVs67JHvsFE89g==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age14aml5s3sxksa8qthnt6apl3pu6egxyn0cz7pdzzvp2yl6wncad0q56udyj
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBucHdSNGNyRkVITmNDVkpx
+            QVFKK0VucFNSMnNqSGRFRmRoRWpsZ0srUUhrCkwwY2pDSkJ0aGlqc3U3ZXNJUVl0
+            bXZMSVg3bDhaK3d1MTBnL1BQVUhkMUkKLS0tIDdxSk1DMVpsbnI1QlFnNEFJYXRD
+            RTNxYUxlUGxsM1NvekZ4R1hQVE9KMk0KocfE75DTfQMj/RsznOdeF82aO8WwO4HD
+            1xakOM2FHoHi60Q5uOWzfGtz0i+R4ue9hafa5Esn01TOjc3qWSlW3A==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age1me78u46409q9ez6fj0qanrfffc5e9kuq7n7uuvlljfwwc2mdaezqmyzxhx
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBYTEhiSDZvZTg3ZWxJRXlu
+            a0ozOXRVL2lia054SkNLc2tEYmlZUCt1NW1JCkorK0hub1pLQTE0QThEUDRDWXJV
+            YWtGamNxMTFIYjVDT2RqTXh0Z2hVTjAKLS0tIGxoRTAwc3FKVVNSQndtbTZmc3BR
+            QnMrK2lMT25tR1ErV2xvS01JWWswVUEKtrGaLETMfY2D8qmgml/fgGxkvQLoiMTP
+            l3a7Y6kwutuzRnmW1tnWv7yoPbTn+BDwfOwBcnesl2x0aJ5iLUKruA==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age1cs8uqj243lspyp042ueu5aes4t3azgyuaxl9au70ggrl2meulq4sgqpc7y
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqMFJ1bzQxWjlZTmF6eEl0
+            d3VVd0VsbGZGdDBKRG9uNEhaMThmWmpuQ1hFClA1aDhwRU1Pb2pibGh6T0pqdmlq
+            S3cxM0wyWWlCL3U5TjV4Vkg4blRsUVkKLS0tIENnYk5GbmZWbFo4cElON1Z0ZVlv
+            ZDdsci9rcG5Wc2V0NlQ3MWx1cFF4dUkKumFT4xtjGDBGK+/SV27Dh/vyGMJAEZNo
+            9gTmVLfR9vXVAXUdOMcqgo7Nl4OJCS4HrDxvVCoER/bVoQVRiPzuXw==
             -----END AGE ENCRYPTED FILE-----
         - recipient: age1w5w4wfvtul3sge9mt205zvrkjaeh3qs9gsxhmq7df2g4dztnvv6qylup8z
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzK1FBcHh2NlBCMDVJTVJi
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCM2E5a2lsZGJzRnk5N3Rr
-            V3JzYmRqVnNxcTBZSWJacDF5NUF0dGJqWWxZCk1aaTdra3RRcklIb1VkU1VpRGlI
+            bWRwRlI2c0c4NzBNdEVqMGZFWTZtNDlvSzJFCmFPM05XbndsazRGWEw3Zy83dldm
-            VVZNTUFXQzcwT1NRUFFtZTFaZERiOTgKLS0tIFNTbUVXQmRaWmdPWWVzMTJEYk83
+            eXhEZUZQZWk5bVNwaEk5SDRka0NOWjAKLS0tIHNvZ016Rjh5bmYwRUxyRWRydFpI
-            RGo1aDJJV3RiRkJsTXNoa2ZFSWJNcFUKM21CtHAX2swT++JqKSQ2R9htE0+Csvlz
+            Z0NHYjFzem55bVNORGlVbVNxR2psc2cK6JpNZwznwgl61d/W9g+48/894TQRe4gJ
-            h/SfoTkVlm8OPrYzaEQV0SB0yxC7jgBKL9X5HZQDaflGbTUBi9LP1A==
+            nl4oDwRPbZwJZgdAKQVfTTujB0QbWpJc24mDGD4I4CydqTKwy6FN3A==
             -----END AGE ENCRYPTED FILE-----
         - recipient: age1wwufz86tm3auxn6pn27c47s8rvu7en58rk00nghtaxsdpw0gya6qj6qxdt
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtRGxmaUE5V1NabytJT3E0
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlK1A1eVdRQThQUHdqbHdk
-            elZ0T1YybS9OQXdERWdoSkxpbDcvM3Buem1jCnBjSWROT1NxWGxXOERCLy82akJ4
+            b1MyMlBJUFluTm13ZWwwc1RNbThFZUMrNXhzCnRPTVhPSzUzM0VtaUVJbFl5Wllj
-            clVyVVpZMTI3cTEvT0U5aWorQ21LN0UKLS0tIGJDZGhtUWVVQmpKcnFvNlZvUS9B
+            NUlndzc3Yzhjd1JSb3czajI3UmRDZ1kKLS0tIE03M1hab1MxU0I2VExBWlh2TnJC
-            STdUQUxXcUNnRmZvNzVIZjlVUGVuWFUKp8qPooDNNFa73mRtmBuzwlccVBX7TF7P
+            eGRXRTlsWmlpenJrVkMxakJZVTV0cE0KMQCKscSLnCu3NsurFFiDaUGjJbyIAwd0
-            NcQQUzTe5i1B2S5Q8iDVkEKnPJxb10KGJEGGD+gh29beOWsZXEu06g==
+            HTutCiuPYVI4zznQ3RZDBeO5L6a/twXxMRTePUCwOkRNWRWpzR9nxg==
             -----END AGE ENCRYPTED FILE-----
-        - recipient: age1gekmz8kc8r2lc2x6d4u63s2lnpmres4hu9wulxh29ch74ud7wfksq56xam
+        - recipient: age1jy7pe4530s8w904wtvrmpxvteztqy5ewdt92a7y3lq87sg9jce5qxxuydt
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAwVVJQOXlXRVhYMHVZQjdD
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB1VEJmMWlnemFGNExWYUI4
-            VzRGSUw5L2hRbXdJYkJndUlOb3ZPVWJ1dUcwCkxGLzBLd0RUeWwxc1ZZL2hTYzUz
+            QWRwRktwODNvSmlEcGJORHNlQXNVeXVpbFNrCms0QUFNdDlrNjMxazU1UTcwc2JF
-            VVBjZVFzN3VCY3o4UXFIT0plSEFoWm8KLS0tIGhJRVRLMVE0eGtkeE82SlMydE1m
+            RC9JUnJsWmgyc01zZU9JQmxuM3V6STQKLS0tIGxQZGFsZ0pNTjQ3QW1sS0E2Y2RM
-            TDhLOENRREVlemt0ZHBid0RNelV0bUkK0MYZpO5AWieaHnW/tP8bND/bJQYKf85e
+            aVVrNW1BNXQ5UDk1UEtVVWJPNHpwUFUKcArFPFknBj8ss1lD38YtMaB06L/ASeu5
-            fEs1AE83bhS4pLGhf7elXUW9Yc7YG7M7maPyK9Yf3G8cFH1sYLYhVQ==
+            u4ff0rTDx237snaSFg5RIJ+6uxX16p5ODg3xOYGOMkDeuTLdl2bg3A==
             -----END AGE ENCRYPTED FILE-----
         - recipient: age1zjgqu3zks5kvlw6hvy6ytyygq7n25lu0uj2435zlf30smpxuy4hshpmfer
           enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBIcjlObDQ4eVE1SjJrUlBF
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArWTNkaFlrQkJHRnd4cTBw
-            YlVyS1FDYThtdDNGSTVReTRidGVPMXRZVGdjCnkvZENzMkFBKzZaU0paOFJkRmMw
+            N3dnTXk3SlJkQkZDdWpLcEpNQ2Z2RHZoVjBJCjBaK1MzbzdaaXluR1dFaFFNaGEx
-            MWpQaTg0c1RweStNeFVZZ05KY0VDbmcKLS0tIGhjNkxMeDhxVEtLdTF5Qjl1MVJv
+            VTNrVU0yeG9KQkhqUkYxU3VBM0E0R1UKLS0tIDJHek9vVldSZGN0M0c0UHcySGhk
-            UHZwRmc2NjNDUlJCdWN1V1dhS1RkelEKF1KiZLQvruEAfjwbW8lIyzvcCqeAMReI
+            Z2RoZno4bmhidytlL2ZmNWUzNTcwcVEKXvgaO8Uo0R+Kc8lizLtVxmTi0W5XHjYw
-            svl1uSaSaxPtCbnc9RA2nfo0vvCoz0a02dhr7CAy3syfQPLLZqRAIA==
+            7evdCHQHmFl0vg/bGOJBmcTUhioJv06D0LR3XMl9I6ufXDNaT/NHxw==
             -----END AGE ENCRYPTED FILE-----
-    lastmodified: "2025-03-11T15:54:47Z"
+    lastmodified: "2025-04-04T09:34:06Z"
-    mac: ENC[AES256_GCM,data:GIHJcwKrRLBhTb3lj9pUza5Fyr9XcKbOMQAe+WETsyr5uHf7lNtlJOXjk1rjBIyJNUJDDnaGSUxCZ213xXIeNBJ92zN54kPheakOiLPOZN7N0YEsU6iENxsuVbQLvvDGvTY5t86DkV6vgClATKj/nqVpkPFAluh2zxLVbBeQrm0=,iv:rF8pesuNU3moerP0+wFuW02A6FYOTMyWWWWr90OB4Zc=,tag:ZXr/FAW37OynDBrGiksLLw==,type:str]
+    mac: ENC[AES256_GCM,data:YIcRrsPparPfPaI2+MLlKsxu7M19H8nndOsrDLuh/5BXzIZNiuTIWyvxODyhI745rDwlibO+7Q0QctanhTl4+IzGaYtuY4i+rb+3dzBMpcdT2VAbtCHHxcltWeanRGFq2K3WM2tbnQCERst5kejfn0Razjq3UU5vNwfBsdJMwGc=,iv:izDxy0ufVnH8ImkZIngcYhGuj0PGpLqBD/ZDvQyE+5I=,tag:oYBUEQS52pr09h5OvOadNg==,type:str]
-    pgp: []
     unencrypted_suffix: _unencrypted
     version: 3.9.4

secrets/sparky.yaml

@@ -0,0 +1,25 @@
+kopia: ENC[AES256_GCM,data:AS5zTDpPPuPGEoT05uHyAfPTbls=,iv:YZK8O0/osP0/ay1tw2kkiCoxws+DlzquVqXNdVayE+k=,tag:tCNM8fzEEuRTPDJybq7fUA==,type:str]
+sops:
+    age:
+        - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtSjhXazlWd3YwNVFKVkw4
+            dDMydVFCN1lLeUJOWkxuSGJ1a0srNm9PaWswCm8yZ3hiOWFHUlAzNVRrck53OElD
+            b056YmV4S2NtNnEzRkpnRVNEblV5blkKLS0tIG1ramoya3RHV1FJZGlFU2ZSeUtS
+            KzJlbEsvYWlXaHhEQU5oOS9HaDdYSDAKvlhKgi4Pf8xVB5MnO33GWYg313mRdUGu
+            kFCs5b1N96x9JOS7zgnM0AKDY8IPBSe33tmDqtYygwPdkOys1PmZkw==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age14aml5s3sxksa8qthnt6apl3pu6egxyn0cz7pdzzvp2yl6wncad0q56udyj
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBYTVovQld2RkRxaW90b3lR
+            NGFtbWVLZUNHdnlZVWkrL1RXUHBVeGdvSDJrClJmSmZRZmdjcy8rNnJBVmVUWDZq
+            M2lPbDBhT0Y0NkJ5a1FNYnU3Zkl0TkEKLS0tIGxqM2h2TDB2akl4ODlYY042R1Z4
+            ZVJWN3pZelFJR0Jid3JseEZKVFZtYmsKmKXQRjnghuF/s9z2Xk98sFvxic91fGa2
+            V7IGmpqAYQV3jJ1G4cjJxtpidQ6fLCqlnR+sq+y8+dT+LN7i+Zbnnw==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2025-10-19T17:33:13Z"
+    mac: ENC[AES256_GCM,data:IwEyBr/I7BJa0gWZ494dCT0ogyP2PbnUg5fLOn15vZAHIyYtTB3dI3gV5Lx7oPdqOPlI61MsShIYBnk0uBChpNu6O4oiGUfwvBfegzlDyHHERLx+S7nZpcwmf/3JoNXwq0f2OtOu8nA6Q1V4gVjFFNWUCAh5cq106vG1awsQkn0=,iv:j+JcVtKz2RfyWu55dUeJJTRK6prB9DGLvcjiAAdVySM=,tag:Pg5sKiLzYUFoN9Duu+nF0w==,type:str]
+    unencrypted_suffix: _unencrypted
+    version: 3.9.4

secrets/stinky.yaml

@@ -0,0 +1,25 @@
+kopia: ENC[AES256_GCM,data:boi8V0Kn,iv:Kwe1hn44DJe9dpv8jVrJjwyblVouakuCdnEK9uotTkY=,tag:B5hrpRBP17kFVn4iy5TOlA==,type:str]
+sops:
+    age:
+        - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA4aXRBWUg3QU12UWNBNXI4
+            RS91amdnOXhibXpiYjgrQ2FwR3J0VER1cEdjCnlaTXFSMzFPNmlnSTIvejJuMUFU
+            T2lUSDRQeFVtT1ZHb2xNZVNpWDJOTmsKLS0tIElHK3FVbUFSREMwcVN5V0tPSEtt
+            a2ZyNXFnZzBkeWZsU2docUxzQVMyUFkKkiEW3ovgVBLlBEHyx6hSXVp8PTeZ+2PL
+            kzW8AnQTi714iQqyN3NlkJ8r+1doGBr9U492KXpjdt1woY4MwMvWkA==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age1me78u46409q9ez6fj0qanrfffc5e9kuq7n7uuvlljfwwc2mdaezqmyzxhx
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCN0Fvdm5Mc3lqNDh6VEp5
+            Mk83N0dNU2pnWVFRODl5MllIaHdIUm5SclJJCjNPQVBGOGRIRlVVL1lzYU5ocjRx
+            Sis5VzZXN3AxYUpxNm9pZE5WUzZGaTQKLS0tIFlpL09vQmpDWjNJeXg5dUZZSm5O
+            S2ZOdExQdzJRcGdmUWtrRUpmVy9lY3cKJwEoO9WltW2FIFEylGuWBHwSJlnAIy8M
+            FFCmmApdkzJLwvQGg5kNC/4Xx34ZfNTTpePxh9qP0ASxUQASZo2urA==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2025-10-26T16:59:40Z"
+    mac: ENC[AES256_GCM,data:FlSv9PIcmX+oJNVaUpXIG2thzUvEb7bMGDOvIRgAFVzoUipIes0qdbU0R/pqogW0NpgbXNLhNBmemKfheGusngatJmbNwHT9Hqo7a82U9j1G302sziqrcz1pOxG79oacFEM+coWpXGgmMXYeNlQEihUvvvUt810VWBb3Hjba80g=,iv:6gSTUd2y9YxiOCzwQ/udLN46lgfwgWDgfSTOpaJpPmY=,tag:q/Ta6fejjKMg0TmZhNmy8Q==,type:str]
+    unencrypted_suffix: _unencrypted
+    version: 3.11.0

secrets/wifi.yaml

@@ -0,0 +1,25 @@
+wifi-password-pi: ENC[AES256_GCM,data:n5ZfyhBCrHx98uUxFQ==,iv:9SQHcIw252GeS0IxON3ThqOk02Wtlfu/Df6KMLAmokw=,tag:F5pAHlInkqVUQDg8MPnMgQ==,type:str]
+sops:
+    age:
+        - recipient: age1df9ukkmg9yn9cjeheq9m6wspa420su8qarmq570rdvf2de3rl38saqauwn
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBUd1lyZG9GVHBZZHU0Wkl5
+            RFJ2NUdtUFRUbmd3aTRFV2dGaVA2S3RWOGk0CmlLV2ZYdERvb21iT0dlUk42TW5S
+            LzdxVlA1U1FpWkxIb1pMeUtRRm9NdFkKLS0tIGszaFM0dkhHeWZUcXc1dlo3SDBX
+            WjltV282VlJtTlBCRmdzOU16R0x5UUUKBTFArSUNWtq7r+HduxT0ChvYfjo8HtbG
+            KeYBoB9QwY5wNRMlk0AIlJVNLKW8A2tC9T8ehbtjol13H7PQK+wsQQ==
+            -----END AGE ENCRYPTED FILE-----
+        - recipient: age1me78u46409q9ez6fj0qanrfffc5e9kuq7n7uuvlljfwwc2mdaezqmyzxhx
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4THVFa1p5c2l5V0pKckVC
+            YUdYbitJbUpjclAydG4yekxhbXdzeDNpbXdRCnRCZVI1cWJiQi9TdkR3Y0E5TklO
+            T2dHYXFKeW9KSkdXOWFnbWVRQUZOL28KLS0tIDVMVldvd0NWcU5QWkhDTTBmUTla
+            aUs0dTB3Y3RXTlBCOCtYSHdOMUYxdTgKQShxsJ+3EQU18uixmM3FlCe5C9Rl3oS5
+            gwZIrh0amSzX3f9SOjf42h1d+IDL/DMWAlSA/3XMx8TK9A1zKZDgVA==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2025-10-29T14:55:56Z"
+    mac: ENC[AES256_GCM,data:2zTEzx8UxOMHIytiufCHS/B1ci7kI05+SIE8ziMY8/ItoAYtt0zXXEgRWs0NLVb3P2vXMOhnXG4qO1o20UXt6Wqq9j1zXPVaQTQie4QSPDdX/8OXXi87Ggm3WQyeA1IfABacfL0D6XkNvxfMHGvMrnhYltPPgYDuNlgjnnjTm8o=,iv:FJMKLSlAenvSNUH6OmeGIR7f9Bzl3NwqaUaokoHEj50=,tag:WU4BnlLu5cKSbtiYL0mNKg==,type:str]
+    unencrypted_suffix: _unencrypted
+    version: 3.11.0

secrets/zippy.yaml

@@ -1,4 +1,5 @@
 kopia: ENC[AES256_GCM,data:MtzeNkkIwMnImZBx0mrpFVwkNXk=,iv:1iRQTyJgF1vEchOwFxv7qLte8lhrM+16cldUlMwyprQ=,tag:Bz/jLj9iGOgALPmvWe48pw==,type:str]
+lighthouse_jwt: ENC[AES256_GCM,data:gosbFx1lpJUA4OAIVzi1lV3NhEVJNBF8Bvt6QW3+QobeNx4jrHbWKycYG9e7ig6IcePbFpirmqwhbs81FWjlSA==,iv:j2IKvWNp6+bkWta7q0PcQHNca0TMk1+5qtGJA5fULnU=,tag:Pk6IobanGpl2Fz13EsxAXg==,type:str]
 sops:
     kms: []
     gcp_kms: []
@@ -23,8 +24,8 @@ sops:
             MzlQcFpSMTVTRXplSTN5WllsOTM4S00KRgnKz0cA/fMueZzFJ7VCs2jrQ29rn9sO
             kE/8FyD1YBR/+I3qUYfRvlKAKlSrI2Mb3tlRSaSw5te3Dbqh5+tN7Q==
             -----END AGE ENCRYPTED FILE-----
-    lastmodified: "2025-03-12T22:11:51Z"
+    lastmodified: "2025-04-04T09:34:11Z"
-    mac: ENC[AES256_GCM,data:hlZcDq5MHF+LvWPx170QWadDFndBQ1VMNZtt6ySaLXqoetQQGDQsRCpFMd2aktwkUYVg5Opoyv+2VyvFQNjogh+j7u0mQCpTksqdJ02rgKa2zdaigpyl3wvHFbTXIx0t3aTN8ZZJBQJpo9e2b4LDJWwLi065uhspMrIjURlTwjg=,iv:NjFE6PnMjaSc/tvgqES8kbDtDI8LwPEIQU9K3wdnI8Q=,tag:BLJQAbnwwIm6CNs6BIK/tQ==,type:str]
+    mac: ENC[AES256_GCM,data:iE8FwepvNR//w/9X1nklaoOmO5ICG5Sym/1IcKsZPJiMcdxN+T6Vrgp9+I1Fmn+y7KD06iwG8cQ2IJf7wO5KplzRyCyol8fGNsh4KiiGU52MJLOzVDC4XxcRDNpxi1abrfm7xuxt1v8iL6+FIAyxtpd5QCXIihn2XnPpZymSf0Q=,iv:qZ9jFy9mIbT3GLBtKrrgz8HhjpYz7rMviyJ1PP38y6c=,tag:y+AymYMmQRIqsziqlEoR7w==,type:str]
     pgp: []
     unencrypted_suffix: _unencrypted
     version: 3.9.4

services/adminer.hcl

@@ -27,7 +27,7 @@ job "adminer" {
         tags = [
           "traefik.enable=true",
           "traefik.http.routers.adminer.entryPoints=websecure",
-          "traefik.http.routers.adminer.middlewares=authentik@file",
+          "traefik.http.routers.adminer.middlewares=oidc-auth@file",
         ]
       }
     }

services/authentik.hcl

@@ -1,118 +0,0 @@
-job "authentik" {
-  datacenters = ["alo"]
-
-  group "auth" {
-    network {
-      port "http" {
-        # traefik forwardAuth hardcodes this port
-        static = 9000
-      }
-      port "https" {
-        to = 9443
-      }
-      port "metrics" {
-        to = 9300
-      }
-    }
-
-    task "server" {
-      driver = "docker"
-
-      config {
-        image = "ghcr.io/goauthentik/server:${var.authentik_version}"
-        ports = [
-          "http",
-          "https",
-          "metrics"
-        ]
-        command = "server"
-      }
-
-      env {
-        AUTHENTIK_REDIS__HOST = "redis.service.consul"
-        AUTHENTIK_POSTGRESQL__HOST = "postgres.service.consul"
-        AUTHENTIK_POSTGRESQL__NAME = "${var.pg_db}"
-        AUTHENTIK_POSTGRESQL__USER = "${var.pg_user}"
-        AUTHENTIK_POSTGRESQL__PASSWORD = "${var.pg_password}"
-        AUTHENTIK_SECRET_KEY = "${var.secret_key}" 
-        AUTHENTIK_EMAIL__HOST = "192.168.1.1"
-        AUTHENTIK_EMAIL__FROM = "authentik@paler.net"
-      }
-
-      resources {
-        cpu = 2000
-        memory = 1024
-      }
-
-      service {
-        name = "authentik"
-        port = "http"
-        tags = [
-          "traefik.enable=true",
-          # Main UI
-          "traefik.http.routers.authentik.entryPoints=websecure",
-          "traefik.http.routers.authentik.rule=Host(`authentik.v.paler.net`) || Host(`authentik.alo.land`)",
-          # Embedded outpost for forward auth
-          "traefik.http.routers.authentik-palernet.entryPoints=websecure",
-          "traefik.http.routers.authentik-palernet.rule=HostRegexp(`{subdomain:[a-z0-9-]+}.v.paler.net`) && PathPrefix(`/outpost.goauthentik.io/`)",
-          "traefik.http.routers.authentik-aloland.entryPoints=websecure",
-          "traefik.http.routers.authentik-aloland.rule=HostRegexp(`{subdomain:[a-z0-9-]+}.alo.land`) && PathPrefix(`/outpost.goauthentik.io/`)",
-        ]
-      }
-      service {
-        name = "authentik-metrics"
-        port = "metrics"
-        tags = [ "metrics" ]
-      }
-    }
-
-    task "worker" {
-      driver = "docker"
-
-      config {
-        image = "ghcr.io/goauthentik/server:${var.authentik_version}"
-        command = "worker"
-      }
-
-      env {
-        AUTHENTIK_REDIS__HOST = "redis.service.consul"
-        AUTHENTIK_POSTGRESQL__HOST = "postgres.service.consul"
-        AUTHENTIK_POSTGRESQL__NAME = "${var.pg_db}"
-        AUTHENTIK_POSTGRESQL__USER = "${var.pg_user}"
-        AUTHENTIK_POSTGRESQL__PASSWORD = "${var.pg_password}"
-        AUTHENTIK_SECRET_KEY = "${var.secret_key}" 
-        AUTHENTIK_EMAIL__HOST = "192.168.1.1"
-        AUTHENTIK_EMAIL__FROM = "authentik@paler.net"
-      }
-
-      resources {
-        memory = 600
-      }
-    }
-  }
-}
-
-variable "pg_user" {
-  type = string
-  default = "authentik"
-}
-
-variable "pg_password" {
-  type = string
-  default = "aQueiquuo6aiyah5eoch"
-}
-
-variable "pg_db" {
-  type = string
-  default = "authentik"
-}
-
-variable "secret_key" {
-  type = string
-  default = "uUzCYhGV93Z8wKLAScuGFqBskxyzSfG4cz6bnXq6McM67Ho7p9"
-}
-
-variable "authentik_version" {
-  type = string
-  default = "2024.12.3"
-}

services/beancount.hcl

@@ -22,7 +22,7 @@ job "beancount" {
         image = "gitea.v.paler.net/ppetru/fava:latest"
         ports = ["http"]
         volumes = [
-          "/data/compute/appdata/beancount:/beancount",
+          "/data/services/beancount:/beancount",
         ]
       }
 
@@ -37,7 +37,7 @@ job "beancount" {
         tags = [
           "traefik.enable=true",
           "traefik.http.routers.finances.entryPoints=websecure",
-          "traefik.http.routers.finances.middlewares=authentik@file",
+          "traefik.http.routers.finances.middlewares=oidc-auth@file",
         ]
       }
 

services/clickhouse.hcl

@@ -6,6 +6,13 @@ job "clickhouse" {
   }
 
   group "db" {
+    # Run on primary storage node (zippy) for local disk performance
+    # TODO: move to fractal once it's converted to NixOS (spinning disks OK for time-series data)
+    constraint {
+      attribute = "${meta.storage_role}"
+      value     = "primary"
+    }
+
     network {
       port "clickhouse" {
         static = 8123
@@ -16,9 +23,9 @@ job "clickhouse" {
       driver = "docker"
 
       config {
-        image = "clickhouse/clickhouse-server:25.2-alpine"
+        image = "clickhouse/clickhouse-server:25.9"
         volumes = [
-          "/data/compute/appdata/clickhouse:/var/lib/clickhouse",
+          "/data/services/clickhouse:/var/lib/clickhouse",
           "local/clickhouse-config.xml:/etc/clickhouse-server/config.d/logging.xml:ro",
           "local/clickhouse-user-config.xml:/etc/clickhouse-server/users.d/logging.xml:ro",
         ]

services/couchdb.hcl

@@ -1,102 +0,0 @@
-job "couchdb" {
-  datacenters = ["alo"]
-
-  meta {
-    uuid = uuidv4()
-  }
-
-  group "db" {
-    network {
-      port "api" {
-        to = 5984
-      }
-    }
-
-    task "server" {
-      driver = "docker"
-
-      config {
-        image = "couchdb:3.3"
-        ports = ["api"]
-        volumes = [
-          "/data/compute/appdata/couchdb:/opt/couchdb/data",
-          "local/couchdb.ini:/opt/couchdb/etc/local.d/local.ini",
-          "local/vm.args:/opt/couchdb/etc/vm.args",
-        ]
-      }
-
-      service {
-        name = "couchdb"
-        port = "api"
-
-        tags = [
-          "traefik.enable=true",
-          "traefik.http.routers.couchdb.entryPoints=websecure",
-          "traefik.http.routers.couchdb.rule=Host(`pidb.paler.net`)",
-        ]
-      }
-
-      resources {
-        memory = 2000
-      }
-
-      template {
-        data = <<EOH
-# (Debian) Package-introduced administrative user
-[admins]
-admin = -pbkdf2-eeb3e20eb9b58edec62d10987d7aed3465c425d4,3cf6e90591d435fbfa9262693490b9c8,10
-
-[couchdb]
-uuid = 66ab957b6c21d9fd2ff6bda36da9f4b7
-
-[couch_httpd_auth]
-secret = a57bfaa045b960c301411bb0893d88ac
-allow_persistent_cookies = true
-; 8 weeks
-timeout = 4838400
-
-[cors]
-origins = https://pi.paler.net,https://noteself.org
-credentials = true
-headers = accept, authorization, content-type, origin, referer
-methods = GET, PUT, POST, HEAD, DELETE
-
-[httpd]
-enable_cors = true
-EOH
-        destination = "local/couchdb.ini"
-      }
-
-      template {
-        data = <<EOH
--name couchdb@127.0.0.1
-
-# All nodes must share the same magic cookie for distributed Erlang to work.
-# Comment out this line if you synchronized the cookies by other means (using
-# the ~/.erlang.cookie file, for example).
-#-setcookie monster
-
-# Tell kernel and SASL not to log anything
--kernel error_logger silent
--sasl sasl_error_logger false
-
-# Use kernel poll functionality if supported by emulator
-+K true
-
-# Start a pool of asynchronous IO threads
-+A 16
-
-# Comment this line out to enable the interactive Erlang shell on startup
-+Bd -noinput
-
-# Force use of the smp scheduler, fixes #1296
--smp enable
-
-# Set maximum SSL session lifetime to reap terminated replication readers
--ssl session_lifetime 300
-EOH
-        destination = "local/vm.args"
-      }
-    }
-  }
-}

services/evcc.hcl

@@ -32,8 +32,8 @@ job "evcc" {
         ]
 
         volumes = [
-          "/data/compute/appdata/evcc/evcc.yaml:/etc/evcc.yaml",
+          "/data/services/evcc/evcc.yaml:/etc/evcc.yaml",
-          "/data/compute/appdata/evcc/evcc:/root/.evcc",
+          "/data/services/evcc/evcc:/root/.evcc",
         ]
       }
 
@@ -49,7 +49,7 @@ job "evcc" {
         tags = [
           "traefik.enable=true",
           "traefik.http.routers.evcc.entryPoints=websecure",
-          "traefik.http.routers.evcc.middlewares=authentik@file",
+          "traefik.http.routers.evcc.middlewares=oidc-auth@file",
         ]
       }
     }

services/farmos.hcl

@@ -19,8 +19,8 @@ job "farmos" {
         image = "gitea.v.paler.net/ppetru/farmos:latest"
         ports = ["http"]
         volumes = [
-          "/data/compute/appdata/farmos/sites:/opt/drupal/web/sites",
+          "/data/services/farmos/sites:/opt/drupal/web/sites",
-          "/data/compute/appdata/farmos/keys:/opt/drupal/keys",
+          "/data/services/farmos/keys:/opt/drupal/keys",
         ]
       }
 

services/ghost.hcl

@@ -1,69 +0,0 @@
-job "ghost" {
-  datacenters = ["alo"]
-
-  meta {
-    uuid = uuidv4()
-  }
-
-  group "web" {
-    network {
-      port "http" {
-        to = 2368
-      }
-    }
-
-    task "server" {
-      driver = "docker"
-
-      config {
-        image = "ghost:latest"
-        ports = ["http"]
-        volumes = [
-          "/data/compute/appdata/ghost:/var/lib/ghost/content",
-        ]
-      }
-
-      env {
-        url = "https://alo.land"
-        mail__transport = "SMTP"
-        mail__options__service = "Mailgun"
-        mail__options__host = "smtp.eu.mailgun.org"
-        mail__options__port = "465"
-        mail__options__secure = "true"
-        mail__options__auth__user = "postmaster@mg.alo.land"
-        mail__options__auth__pass = "63eb13eabe77f639cbde3d14793f42ef-602cc1bf-36f99a0c"
-        database__connection__host = "mysql.service.consul"
-        database__connection__database = "alo"
-        database__connection__user = "ghost"
-        database__connection__password = "cohNeiveoGa9eedohFie"
-      }
-
-      service {
-        name = "ghost"
-        port = "http"
-        check {
-          type = "http"
-          port = "http"
-          path = "/ghost/api/admin/site/"
-          header {
-            X-Forwarded-Proto = ["https"]
-            Host = ["alo.land"]
-          }
-          interval = "30s"
-          timeout = "2s"
-        }
-
-        tags = [
-          "traefik.enable=true",
-          "traefik.http.routers.ghost.entryPoints=websecure",
-          "traefik.http.routers.ghost.rule=Host(`alo.land`)",
-        ]
-      }
-
-      resources {
-        cpu = 500
-        memory = 512
-      }
-    }
-  }
-}

services/gitea.hcl

@@ -25,8 +25,8 @@ job "gitea" {
           "ssh",
         ]
         volumes = [
-          "/data/compute/appdata/gitea/data:/var/lib/gitea",
+          "/data/services/gitea/data:/var/lib/gitea",
-          "/data/compute/appdata/gitea/config:/etc/gitea",
+          "/data/services/gitea/config:/etc/gitea",
           "/etc/timezone:/etc/timezone:ro",
           "/etc/localtime:/etc/localtime:ro",
         ]
@@ -51,6 +51,7 @@ job "gitea" {
         tags = [
           "traefik.enable=true",
           "traefik.http.routers.gitea.entryPoints=websecure",
+          "traefik.http.services.gitea.loadBalancer.serversTransport=gitea-transport@file",
         ]
       }
 

services/grafana.hcl

@@ -14,7 +14,7 @@ job "grafana" {
       config {
         image = "grafana/grafana-enterprise:latest"
         ports = [ "http" ]
-        volumes = [ "/data/compute/appdata/grafana:/var/lib/grafana" ]
+        volumes = [ "/data/services/grafana:/var/lib/grafana" ]
       }
 
       env {
@@ -25,19 +25,22 @@ job "grafana" {
         GF_SERVER_ROOT_URL = "https://grafana.v.paler.net"
         GF_AUTH_BASIC_ENABLED = "false"
         GF_AUTH_GENERIC_OAUTH_ENABLED = "true"
-        GF_AUTH_GENERIC_OAUTH_NAME = "authentik"
+        GF_AUTH_GENERIC_OAUTH_NAME = "Pocket ID"
-        GF_AUTH_GENERIC_OAUTH_CLIENT_ID = "E78NG1AZeW6FaAox0mUhaTSrHeqFgNkWG12My2zx"
+        GF_AUTH_GENERIC_OAUTH_CLIENT_ID = "99e44cf2-ecc6-4e82-8882-129c017f8a4a"
-        GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET = "N7u2RfFZ5KVLdEkhlpUTzymGxeK5rLo9SYZLSGGBXJDr46p5g5uv1qZ4Jm2d1rP4aJX4PSzauZlxHhkG2byiBFMbdo6K742KXcEimZsOBFiNKeWOHxofYerBnPuoECQW"
+        GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET = "NjJ9Uro4MK7siqLGSmkiQmjFuESulqQN"
-        GF_AUTH_GENERIC_OAUTH_SCOPES = "openid profile email offline_access"
+        GF_AUTH_GENERIC_OAUTH_SCOPES = "openid profile email groups"
-        GF_AUTH_GENERIC_OAUTH_AUTH_URL = "https://authentik.v.paler.net/application/o/authorize/"
+        GF_AUTH_GENERIC_OAUTH_AUTH_URL = "https://pocket-id.v.paler.net/authorize"
-        GF_AUTH_GENERIC_OAUTH_TOKEN_URL = "https://authentik.v.paler.net/application/o/token/"
+        GF_AUTH_GENERIC_OAUTH_TOKEN_URL = "https://pocket-id.v.paler.net/api/oidc/token"
-        GF_AUTH_GENERIC_OAUTH_API_URL = "https://authentik.v.paler.net/application/o/userinfo/"
+        GF_AUTH_GENERIC_OAUTH_API_URL = "https://pocket-id.v.paler.net/api/oidc/userinfo"
-        GF_AUTH_SIGNOUT_REDIRECT_URL = "https://authentik.v.paler.net/application/o/grafana/end-session/"
+        GF_AUTH_SIGNOUT_REDIRECT_URL = "https://pocket-id.v.paler.net/logout"
         # Optionally enable auto-login (bypasses Grafana login screen)
         GF_AUTH_OAUTH_AUTO_LOGIN = "true"
         # Optionally map user groups to Grafana roles
-        GF_AUTH_GENERIC_OAUTH_ROLE_ATTRIBUTE_PATH = "contains(groups[*], 'Grafana Admins') && 'Admin' || contains(groups[*], 'Grafana Editors') && 'Editor' || 'Viewer'"
+        GF_AUTH_GENERIC_OAUTH_ROLE_ATTRIBUTE_PATH = "contains(groups[*], 'admins') && 'Admin' || contains(groups[*], 'residents') && 'Editor' || 'Viewer'"
         GF_AUTH_GENERIC_OAUTH_USE_REFRESH_TOKEN = "true"
+        GF_AUTH_GENERIC_OAUTH_EMAIL_ATTRIBUTE_PATH = "email"
+        GF_AUTH_GENERIC_OAUTH_LOGIN_ATTRIBUTE_PATH = "preferred_username"
+        GF_AUTH_GENERIC_OAUTH_NAME_ATTRIBUTE_PATH = "name"
         #GF_LOG_LEVEL = "debug"
       }
 

services/homepage.hcl

@@ -0,0 +1,50 @@
+job "homepage" {
+  datacenters = ["alo"]
+
+  group "app" {
+    network {
+      port "http" { to = 3000 }
+    }
+
+    task "homepage" {
+      driver = "docker"
+
+      config {
+        image = "ghcr.io/gethomepage/homepage:latest"
+        ports = [ "http" ]
+        volumes = [
+          "/data/services/homepage:/app/config",
+        ]
+      }
+
+      env {
+        PUID = 1000
+        PGID = 1000
+        HOMEPAGE_ALLOWED_HOSTS = "homepage.v.paler.net"
+      }
+
+      resources {
+        cpu = 200
+        memory = 256
+      }
+
+      service {
+        name = "homepage"
+        port = "http"
+
+        tags = [
+          "traefik.enable=true",
+          "traefik.http.routers.homepage.entryPoints=websecure",
+          "traefik.http.routers.homepage.middlewares=oidc-auth@file",
+        ]
+
+        check {
+          type     = "http"
+          path     = "/"
+          interval = "10s"
+          timeout  = "5s"
+        }
+      }
+    }
+  }
+}