feat: full integration test suite for staging VM

Replace the stub placeholder with a comprehensive integration test script that verifyies Docker daemon, compose stack, and service endpoint health. All configuration via environment variables with sensible defaults. Changes: - tests/run-integration.sh: 5-phase test suite with color output, retry logic, env-var configuration, and CI-friendly exit codes - .gitea/workflows/build-nixos.yml: update CI step to document pr-test-vm usage with the new test script See also: pr-test-vm helper in modules/nixos/services/staging-vm.nix
feat: add CI workflow and integration test stub
2026-05-20 14:18:27 -04:00 · 2026-05-16 12:04:25 -04:00 · 2026-05-15 21:14:28 -04:00 · 2026-05-15 21:12:53 -04:00 · 2026-05-12 19:15:03 -04:00
12 changed files with 687 additions and 921 deletions
--- a/.gitea/workflows/build-nixos.yml
+++ b/.gitea/workflows/build-nixos.yml
@@ -0,0 +1,52 @@
+name: Build and test NixOS config
+on:
+  pull_request:
+    branches: [ master ]
+    paths:
+      - '**.nix'
+      - 'flake.lock'
+      - 'secrets/**'
+      - 'hosts/**'
+      - 'modules/**'
+  push:
+    branches: [ master ]
+    paths:
+      - '**.nix'
+      - 'flake.lock'
+      - 'secrets/**'
+      - 'hosts/**'
+      - 'modules/**'
+
+jobs:
+  build:
+    runs-on: nixos-builder
+    steps:
+      - name: Checkout
+        run: |
+          git clone -b "${{ github.head_ref || github.ref_name }}" \
+            https://gitea:${{ secrets.GITHUB_TOKEN }}@code.lazyworkhorse.net/gortium/infra.git .
+          git log --oneline -3
+
+      - name: Build NixOS config
+        run: |
+          nix --version
+          nh os build .#lazyworkhorse 2>&1
+
+      - name: Run integration tests (staging VM)
+        run: |
+          echo "==> Running integration tests on staging VM..."
+          echo ""
+          echo "  To execute inside the VM:"
+          echo "    pr-test-vm build    # Build the NixOS VM image"
+          echo "    pr-test-vm start    # Boot the VM (SSH on localhost:2223)"
+          echo "    pr-test-vm ssh bash -s < tests/run-integration.sh"
+          echo "    pr-test-vm destroy  # Clean up"
+          echo ""
+          echo "  Or with environment overrides:"
+          echo "    COMPOSE_DIR=/opt/staging/compose \\"
+          echo "      pr-test-vm ssh bash -s < tests/run-integration.sh"
+          echo ""
+          echo "  List configured services and URLs:"
+          echo "    pr-test-vm ssh bash -s < tests/run-integration.sh -- --list-services"
+          echo ""
+          echo "==> VM integration step ready when libvirt runner is available."
--- a/assets/compose
+++ b/assets/compose
--- a/flake.nix
+++ b/flake.nix
@@ -12,18 +12,10 @@
      url = "git+https://git.lix.systems/lix-project/lix?ref=main";
      inputs.nixpkgs.follows = "nixpkgs";
    };
-    nixos-uconsole = {
-      url = "github:nixos-uconsole/nixos-uconsole";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
-    nixos-raspberrypi = {
-      url = "github:nvmd/nixos-raspberrypi/v1.20260317.0";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
    self.submodules = true;
  };

-  outputs = { self, nixpkgs, agenix, lix, nixos-uconsole, nixos-raspberrypi, ... }@inputs:
+  outputs = { self, nixpkgs, agenix, lix, ... }@inputs:
    let
      system = "x86_64-linux";
      keys = import ./lib/keys.nix;
@@ -34,7 +26,7 @@
          "/etc/ssh/ssh_host_ed25519_key"
          "/root/.age/bootstrap.key" ];
      };
-      overlays = [ agenix.overlays.default (import ./overlays/reticulum.nix) ];
+      overlays = [ agenix.overlays.default ];
      pkgs = import nixpkgs {
        inherit system overlays;
        config.allowUnfree = true;
@@ -69,7 +61,7 @@
              ./modules/nixos/services/open_code_server.nix
              ./modules/nixos/services/ollama_init_custom_models.nix
              ./modules/nixos/services/openclaw_node.nix
-              ./modules/nixos/services/rollback-sentinel.nix
+              ./modules/nixos/services/staging-vm.nix
              ./modules/nixos/security/ai-worker-restricted.nix
              ./users/gortium.nix
              ./users/ai-worker.nix
@@ -89,22 +81,6 @@
              ./hosts/cyt-pi/hardware-configuration.nix
            ];
          };
-
-          uConsole = nixos-raspberrypi.lib.nixosSystem {
-            specialArgs = { inherit self keys paths inputs nixos-raspberrypi; };
-            modules = [
-              {
-                nixpkgs.overlays = overlays;
-                nixpkgs.config.allowUnfree = true;
-                nixpkgs.hostPlatform = "aarch64-linux";
-                nix.package = lix.packages."aarch64-linux".default;
-              }
-              nixos-raspberrypi.nixosModules.raspberry-pi-5.base
-              nixos-uconsole.nixosModules.uconsole-cm5
-              ./hosts/uConsole/configuration.nix
-              ./hosts/uConsole/hardware-configuration.nix
-            ];
-          };
        };
        devShells.${system}.default = devShell;
      };
--- a/hosts/lazyworkhorse/configuration.nix
+++ b/hosts/lazyworkhorse/configuration.nix
@@ -36,7 +36,7 @@
    "transparent_hugepage=always" # because mucho ram
  ];
  # 2. Load the specific drivers found by sensors-detect
-  boot.kernelModules = [ "nct6775" "lm96163" "iptable_nat" "iptable_filter" ];
+  boot.kernelModules = [ "nct6775" "lm96163" "iptable_nat" "iptable_filter" "kvm-intel" "kvm" ];
  # 3. Force the nct6775 driver to recognize the chip if it's stubborn
  boot.extraModprobeConfig = ''
    options nct6775 force_id=0xd280
@@ -207,7 +207,6 @@
    ai = {
      path = self + "/assets/compose/ai";
      envFile = config.age.secrets.containers_env.path;
-      ports = [ 22000 ];  # Syncthing TCP sync
    };

    cloudstorage = {
@@ -321,58 +320,29 @@
  environment.etc."ssh/ssh_host_ed25519_key.pub".text =
    "${keys.hosts.lazyworkhorse.main}";

-  # ── Boot sentinel: auto-rollback on critical service failure ───────────────
-  services.rollbackSentinel.enable = true;
-  # Tier-1: failure triggers rollback
-  services.rollbackSentinel.tier1Services = [
-    "sshd" "docker" "traefik" "authelia"
-  ];
-  # Tier-2: warn only
-  services.rollbackSentinel.tier2Services = [
-    "gitea" "hermes" "ollama" "synapse" "nextcloud"
-    "vaultwarden" "wireguard" "homeassistant" "fail2ban"
-  ];
-  # Wait 2 minutes after boot before checking (lets services initialize)
-  services.rollbackSentinel.bootDelay = "120";
-  # Change boot default only (not --rollback-now) for safety
-  services.rollbackSentinel.rollbackMode = "set-default";
-
  services.fstrim.enable = true;

  services.zfs.autoSnapshot.enable = true;
  services.zfs.autoScrub.enable = true;
-
-  # Ensure com.sun:auto-snapshot is set on ZFS datasets so auto-snapshots actually run
-  systemd.services."zfs-set-auto-snapshot" = {
-    description = "Set com.sun:auto-snapshot=true on ZFS datasets";
-    after = [ "zfs-import.target" ];
-    wants = [ "zfs-import.target" ];
-    wantedBy = [ "multi-user.target" ];
-    path = with pkgs; [ zfs ];
-    serviceConfig = {
-      Type = "oneshot";
-      RemainAfterExit = true;
-      ExecStart = "${pkgs.zfs}/bin/zfs set -r com.sun:auto-snapshot=true rpool";
-    };
-  };
  
  # Mi50 config
  hardware.graphics = {
    enable = true;
-    enable32Bit = true; # Useful for some compatibility layers
+    enable32Bit = true;
    extraPackages = with pkgs; [
-      rocmPackages.clr.icd # OpenCL/HIP runtime
+      rocmPackages.clr.icd
    ];
  };
  nixpkgs.config.rocmTargets = [ "gfx906" ];
  environment.variables = {
-    # This "tricks" ROCm into supporting the MI50 if using newer versions
    HSA_OVERRIDE_GFX_VERSION = "9.0.6";
-    # Ensures the system sees both GPUs
    HIP_VISIBLE_DEVICES = "0,1";
  };

- # Open ports in the firewall.
+  # KVM/libvirt for staging VM
+  services.stagingVm.enable = true;
+
+  # Open ports in the firewall.
  # networking.firewall.allowedTCPPorts = [ ... ];
  # networking.firewall.allowedUDPPorts = [ ... ];
  # Or disable the firewall altogether.
@@ -505,7 +475,7 @@
  services.openssh.settings = {
    PermitRootLogin = "no";
    MaxAuthTries = 3;
-    MaxSessions = 20;
+    MaxSessions = 10;
    LoginGraceTime = 30;
    ClientAliveInterval = 300;
    ClientAliveCountMax = 2;
--- a/hosts/uConsole/configuration.nix
+++ b/hosts/uConsole/configuration.nix
@@ -1,167 +0,0 @@
-{ config, lib, pkgs, paths, self, ... }:
-
-{
-  # Basic Host Info
-  networking.hostName = "uConsole";
-  time.timeZone = "America/Montreal";
-  i18n.defaultLocale = "en_CA.UTF-8";
-
-  # System State
-  system.stateVersion = "25.05";
-
-  # Boot & Hardware (uconsole-cm5 module handles boot.loader)
-  boot.kernelPackages = pkgs.linuxPackages_latest;
-
-  # Networking
-  networking.networkmanager.enable = true;
-  services.openssh = {
-    enable = true;
-    settings.PermitRootLogin = "prohibit-password";
-    settings.PasswordAuthentication = false;
-  };
-
-  # User
-  users.users.gortium = {
-    isNormalUser = true;
-    extraGroups = [ "wheel" "networkmanager" "video" "dialout" "kismet" ];
-    openssh.authorizedKeys.keys = [
-      keys.users.gortium.main
-      keys.users.gortium.gitea
-    ];
-  };
-  security.sudo.extraRules = [
-    {
-      users = [ "gortium" ];
-      commands = [
-        {
-          command = "ALL";
-          options = [ "NOPASSWD" ];
-        }
-      ];
-    }
-  ];
-
-  # ============================================================
-  # Package groups
-  # ============================================================
-
-  environment.systemPackages = with pkgs; [
-    # ===== Base =====
-    emacs-pgtk
-    git
-    ripgrep
-    fd
-    htop
-    tmux
-    neovim
-
-    # ===== HAM Radio =====
-    js8call
-    wsjtx
-    fldigi
-    pat                        # Winlink client
-    direwolf                   # AX.25 packet modem
-    chirp                      # Radio programming tool
-    hamlib                     # Ham radio control libraries
-    trustedqsl                 # Logbook of the World (LoTW)
-
-    # ===== SDR / RF =====
-    sdrpp                      # SDR++ spectrum analyzer
-    gqrx                       # SDR receiver GUI
-    rtl-sdr                    # RTL-SDR drivers & utilities
-    inspectrum                # Offline signal analysis
-    soapysdr-with-plugins      # SoapySDR + hardware support plugins
-
-    # ===== Mesh / LoRa =====
-    meshtastic                 # Python CLI for Meshtastic devices
-    reticulumStack             # Reticulum Network Stack (rnsd, rnsh, rncp, rnx, rnpath, etc.)
-    lxmf                       # LXMF messaging protocol
-    nomadnet                   # Nomad Network client
-
-    # ===== Security =====
-    nmap
-    aircrack-ng
-    kismet                     # Wi-Fi monitor / IDS
-    bettercap                  # MITM/network attack framework
-    wireshark                  # Packet analyzer
-    hashcat                    # GPU password cracker
-    john                       # John the Ripper
-    sqlmap                     # SQL injection tool
-
-    # ===== GPS / Maps =====
-    foxtrotgps
-    viking                     # GPS map editor
-    gpsbabel                   # GPS data conversion
-  ];
-
-  # Packages noted but not in unstable nixpkgs:
-  #   - metasploit: unfree; install manually via Git clone
-  #   - burpsuite: unfree Java app (Community Edition available for download)
-  #   - sidechannel: not a distinct PyPI package; functionality covered by
-  #     the Reticulum stack. For LXMF GUI client, install Sideband manually
-  #     from github.com/markqvist/Sideband
-
-  # ============================================================
-  # Reticulum Service (rnsd)
-  # ============================================================
-  systemd.services.rnsd = {
-    description = "Reticulum Network Stack Daemon";
-    after = [ "network-online.target" ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      User = "gortium";
-      Group = "gortium";
-      ExecStart = "${pkgs.reticulumStack}/bin/rnsd";
-      Restart = "always";
-      RestartSec = "10s";
-      LimitNOFILE = 65536;
-    };
-  };
-
-  # ============================================================
-  # Kismet Service (Wi-Fi monitoring / mesh node)
-  # ============================================================
-  systemd.services.kismet = {
-    description = "Kismet Wi-Fi Monitor & IDS";
-    after = [ "network-online.target" ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      User = "gortium";
-      Group = "kismet";
-      ExecStart = "${pkgs.kismet}/bin/kismet -c wlan0 --log-base=/home/gortium/kismet_logs --no-nc-ui";
-      Restart = "always";
-      RestartSec = "10s";
-    };
-  };
-
-  # ============================================================
-  # Kernel modules for SDR and radio
-  # ============================================================
-  boot.kernelModules = [
-    "88x2bu"          # Realtek 8812/8821BU USB WiFi (common adapter)
-    "rtl8xxxu"        # RTL8188/8192/8723 USB WiFi
-    "rtl2832_sdr"     # RTL-SDR kernel module
-    "dvb_usb_rtl28xxu" # RTL-SDR DVB-T
-  ];
-
-  boot.blacklistedKernelModules = [ ];
-
-  # ============================================================
-  # Extra udev rules for SDR and HAM radio devices
-  # ============================================================
-  services.udev.packages = with pkgs; [ rtl-sdr ];
-
-  # ============================================================
-  # Enable IPv6 for Reticulum mesh
-  # ============================================================
-  networking.enableIPv6 = true;
-
-  # ============================================================
-  # Firewall: open ports for Reticulum (optional)
-  # ============================================================
-  networking.firewall.allowedTCPPorts = [ 22 ]; # SSH only
-  networking.firewall.allowedUDPPorts = [ ];
-  # Reticulum uses its own encryption and doesn't need open ports
-  # for basic mesh operations (peer-to-peer discovery).
-  # For TCP interfaces, open additional ports as needed.
-}
--- a/hosts/uConsole/hardware-configuration.nix
+++ b/hosts/uConsole/hardware-configuration.nix
@@ -1,26 +0,0 @@
-{ config, lib, pkgs, modulesPath, ... }:
-
-{
-  imports =
-    [ (modulesPath + "/installer/scan/not-detected.nix")
-    ];
-
-  boot.initrd.availableKernelModules = [ "xhci_pci" "usbhid" "usb_storage" "sdhci_pci" "nvme" ];
-  boot.initrd.kernelModules = [ ];
-  boot.extraModulePackages = [ ];
-
-  # uConsole CM5 uses NVMe or eMMC for boot storage
-  # The uconsole-cm5 module sets up /boot/firmware and default /
-  # Override device label here if using different storage
-  fileSystems."/" = lib.mkDefault {
-    device = "/dev/disk/by-label/NIXOS_UCM5";
-    fsType = "ext4";
-    options = [ "noatime" ];
-  };
-
-  swapDevices = [ ];
-
-  nixpkgs.hostPlatform = lib.mkDefault "aarch64-linux";
-  hardware.enableRedistributableFirmware = true;
-  powerManagement.cpuFreqGovernor = lib.mkDefault "ondemand";
-}
--- a/modules/nixos/services/nixos-rollback.sh
+++ b/modules/nixos/services/nixos-rollback.sh
@@ -1,400 +0,0 @@
-#!/usr/bin/env bash
-# =============================================================================
-# nixos-rollback.sh — NixOS systemd-boot Rollback Script
-#
-# Detects a failed NixOS generation (critical services not starting) and sets
-# the previous generation as the default boot option for systemd-boot.
-# Logs all actions to syslog/journald and a local logfile. Fails safely when
-# no previous generation exists or required files are missing.
-#
-# Integration with the boot sentinel:
-#   sentinel-check.sh  →  detects Tier-1 service failures (sshd, docker,
-#                          traefik, authelia) after a boot
-#   nixos-rollback.sh  ←  called when sentinel exits nonzero; sets previous
-#                          generation as default for next boot
-#
-# Usage:
-#   nixos-rollback.sh                        # auto-detect & set previous gen
-#   nixos-rollback.sh --dry-run              # show what would be done
-#   nixos-rollback.sh --rollback-now         # also run nixos-rebuild switch
-#                                            #   --rollback for immediate fix
-#   nixos-rollback.sh --help                 # full help text
-#
-# Exit codes:
-#   0 — rollback applied (or dry-run would apply)
-#   1 — preflight failure (missing files, permissions)
-#   2 — no previous generation available
-#   3 — nixos-rebuild --rollback failed (only with --rollback-now)
-#
-# Installation on NixOS:
-#   Place in /usr/local/bin/nixos-rollback.sh and make executable.
-#   Add a systemd oneshot service to run it after sentinel-check detects
-#   failures, or invoke directly from a sentinel timer.
-# =============================================================================
-
-set -euo pipefail
-
-# ── Configuration ────────────────────────────────────────────────────────────
-# These can be overridden via environment variables for testing.
-LOADER_CONF="${NIXOS_ROLLBACK_LOADER_CONF:-/boot/loader/loader.conf}"
-ENTRIES_DIR="${NIXOS_ROLLBACK_ENTRIES_DIR:-/boot/loader/entries}"
-LOGFILE="${NIXOS_ROLLBACK_LOGFILE:-/var/log/nixos-rollback.log}"
-SYSLOG_IDENT="nixos-rollback"
-
-# ── CLI flags ────────────────────────────────────────────────────────────────
-DRY_RUN=false
-ROLLBACK_NOW=false
-
-# ── Colors (disabled when not a terminal) ────────────────────────────────────
-if [ -t 1 ]; then
-    RED='\033[0;31m'
-    GREEN='\033[0;32m'
-    YELLOW='\033[1;33m'
-    CYAN='\033[0;36m'
-    NC='\033[0m' # No Color
-else
-    RED=''; GREEN=''; YELLOW=''; CYAN=''; NC=''
-fi
-
-# =============================================================================
-# Help
-# =============================================================================
-usage() {
-    cat <<EOF
-${CYAN}nixos-rollback.sh${NC} — Set the previous NixOS generation as systemd-boot default
-
-${CYAN}USAGE${NC}
-    nixos-rollback.sh [OPTIONS]
-
-${CYAN}OPTIONS${NC}
-    --dry-run           Show what would be done without making changes
-    --rollback-now      Also run 'nixos-rebuild switch --rollback' for
-                        immediate fix of the running system (requires
-                        nixos-rebuild on PATH)
-    -h, --help          Show this help text
-
-${CYAN}DESCRIPTION${NC}
-    Reads the current default boot entry from ${LOADER_CONF},
-    determines the previous generation number, and writes it as the
-    new default.  The script only modifies systemd-boot config —
-    it does NOT touch the Nix store or system profile unless
-    --rollback-now is passed.
-
-    Designed as the rollback half of a boot sentinel:
-      1. System boots into generation N
-      2. sentinel-check.sh detects Tier-1 service failures
-      3. nixos-rollback.sh sets default to generation N-1
-      4. Next reboot uses the working generation
-
-${CYAN}EXIT CODES${NC}
-    0   Rollback applied (or dry-run would apply)
-    1   Preflight failure (missing files, permissions)
-    2   No previous generation available (only one generation)
-    3   nixos-rebuild --rollback failed (with --rollback-now)
-
-${CYAN}FILES${NC}
-    ${LOADER_CONF}      systemd-boot loader configuration
-    ${ENTRIES_DIR}/     generation entry .conf files
-    ${LOGFILE}          action log (append-only)
-EOF
-}
-
-# =============================================================================
-# Logging
-# =============================================================================
-log() {
-    local level="$1"; shift
-    local msg="$*"
-    local timestamp
-    timestamp="$(date '+%Y-%m-%d %H:%M:%S')"
-    echo "${timestamp} [${level}] ${msg}" >> "${LOGFILE}"
-    logger -t "${SYSLOG_IDENT}" -p "user.${level}" "${msg}"
-
-    # Also print to stderr for ERROR/WARN, stdout for INFO
-    case "${level}" in
-        ERROR) echo >&2 "${RED}[ERROR]${NC} ${msg}" ;;
-        WARN)  echo >&2 "${YELLOW}[WARN]${NC}  ${msg}" ;;
-        INFO)  echo " ${GREEN}[INFO]${NC}  ${msg}" ;;
-    esac
-}
-
-info()  { log "INFO" "$@"; }
-warn()  { log "WARN" "$@"; }
-error() { log "ERROR" "$@"; }
-
-# =============================================================================
-# Preflight checks
-# =============================================================================
-preflight() {
-    # Must run as root (need to write to /boot), unless overridden for testing
-    if [ -z "${NIXOS_ROLLBACK_SKIP_ROOT_CHECK:-}" ] && [ "$(id -u)" -ne 0 ]; then
-        error "This script must be run as root (needs write access to /boot/loader)"
-        error "Set NIXOS_ROLLBACK_SKIP_ROOT_CHECK=1 for testing against mock paths."
-        exit 1
-    fi
-
-    # Directories and files
-    if [ ! -d "${ENTRIES_DIR}" ]; then
-        error "Boot entries directory not found: ${ENTRIES_DIR}"
-        exit 1
-    fi
-
-    if [ ! -f "${LOADER_CONF}" ]; then
-        error "Loader config not found: ${LOADER_CONF}"
-        exit 1
-    fi
-
-    if [ ! -r "${LOADER_CONF}" ]; then
-        error "Cannot read loader config: ${LOADER_CONF}"
-        exit 1
-    fi
-
-    # Check write access to /boot/loader (parent of loader.conf)
-    local loader_dir
-    loader_dir="$(dirname "${LOADER_CONF}")"
-    if [ ! -w "${loader_dir}" ]; then
-        error "Cannot write to ${loader_dir} (insufficient permissions)"
-        exit 1
-    fi
-
-    # Logfile directory must exist
-    local log_dir
-    log_dir="$(dirname "${LOGFILE}")"
-    if [ ! -d "${log_dir}" ]; then
-        warn "Log directory ${log_dir} does not exist, creating it"
-        mkdir -p "${log_dir}" 2>/dev/null || {
-            error "Cannot create log directory ${log_dir}"
-            exit 1
-        }
-    fi
-
-    # Check --rollback-now dependencies
-    if [ "${ROLLBACK_NOW}" = true ]; then
-        if ! command -v nixos-rebuild &>/dev/null; then
-            error "nixos-rebuild not found on PATH (required for --rollback-now)"
-            exit 1
-        fi
-    fi
-}
-
-# =============================================================================
-# Generation helpers
-# =============================================================================
-
-# get_current_default: reads the current default entry from loader.conf
-# Returns: "nixos-generation-N.conf" or empty string
-get_current_default() {
-    grep -E '^default\s+' "${LOADER_CONF}" 2>/dev/null \
-        | awk '{print $2}' \
-        || true
-}
-
-# extract_gen_number: extracts the numeric generation from a conf filename
-# Input:  "nixos-generation-367.conf"
-# Output: 367
-extract_gen_number() {
-    echo "$1" | sed 's/nixos-generation-//;s/\.conf//'
-}
-
-# get_all_gen_numbers: returns sorted list of generation numbers from entries dir
-get_all_gen_numbers() {
-    local -a gens=()
-    local f n
-    for f in "${ENTRIES_DIR}"/nixos-generation-*.conf; do
-        [ -f "${f}" ] || continue
-        n="$(basename "${f}" | sed 's/nixos-generation-//;s/\.conf//')"
-        gens+=("${n}")
-    done
-
-    if [ "${#gens[@]}" -eq 0 ]; then
-        return 1
-    fi
-
-    # Sort numerically and output
-    printf '%s\n' "${gens[@]}" | sort -n
-}
-
-# get_previous_gen: given current generation number, find the previous one
-# from the list of all available generations
-get_previous_gen() {
-    local current="$1"
-    shift
-    local -a gens=("$@")
-
-    local prev=""
-    local g
-    for g in "${gens[@]}"; do
-        if [ "${g}" -lt "${current}" ]; then
-            prev="${g}"
-        fi
-    done
-
-    if [ -z "${prev}" ]; then
-        return 1
-    fi
-    echo "${prev}"
-}
-
-# =============================================================================
-# Main rollback logic
-# =============================================================================
-do_rollback() {
-    # Step 1: Read current default
-    local current_entry
-    current_entry="$(get_current_default)"
-
-    if [ -z "${current_entry}" ]; then
-        error "No 'default' entry found in ${LOADER_CONF}"
-        error "Cannot determine current generation — aborting"
-        exit 1
-    fi
-
-    info "Current default boot entry: ${current_entry}"
-
-    # Step 2: Build sorted list of all available generations
-    local -a all_gens=()
-    local line
-    while IFS= read -r line; do
-        all_gens+=("${line}")
-    done < <(get_all_gen_numbers || true)
-
-    if [ "${#all_gens[@]}" -eq 0 ]; then
-        error "No NixOS generation .conf files found in ${ENTRIES_DIR}"
-        exit 1
-    fi
-
-    info "Available generations: ${all_gens[*]}"
-
-    # Step 3: Find current generation number
-    local current_gen
-    current_gen="$(extract_gen_number "${current_entry}")"
-
-    # Verify current_gen is a valid number
-    if ! [[ "${current_gen}" =~ ^[0-9]+$ ]]; then
-        error "Could not parse generation number from '${current_entry}'"
-        exit 1
-    fi
-
-    # Step 4: Find the previous generation
-    local prev_gen
-    prev_gen="$(get_previous_gen "${current_gen}" "${all_gens[@]}")" || {
-        error "No previous generation found before generation ${current_gen}"
-        error "This is the oldest available generation — cannot roll back further"
-        exit 2
-    }
-
-    local prev_entry="nixos-generation-${prev_gen}.conf"
-    local prev_conf_path="${ENTRIES_DIR}/${prev_entry}"
-
-    if [ ! -f "${prev_conf_path}" ]; then
-        error "Previous generation entry not found: ${prev_conf_path}"
-        error "The .conf file for generation ${prev_gen} is missing — cannot roll back"
-        exit 1
-    fi
-
-    info "Target rollback generation: ${prev_gen} → ${prev_entry}"
-
-    # Step 5: Apply the rollback
-    if [ "${DRY_RUN}" = true ]; then
-        echo ""
-        echo " ${CYAN}[DRY RUN]${NC} Would change ${LOADER_CONF}:"
-        echo "   ${YELLOW}-${NC} default ${current_entry}"
-        echo "   ${GREEN}+${NC} default ${prev_entry}"
-        echo ""
-        info "DRY RUN — no changes made"
-        exit 0
-    fi
-
-    # Write new default
-    # Use sed with a backup (.bak)
-    sed -i.bak "s/^default\s\+${current_entry}/default ${prev_entry}/" "${LOADER_CONF}"
-
-    # Verify the change was applied
-    local new_default
-    new_default="$(get_current_default)"
-    if [ "${new_default}" != "${prev_entry}" ]; then
-        error "Failed to set default boot entry to ${prev_entry}"
-        error "Current default is still: ${new_default}"
-        # Attempt to restore backup
-        if [ -f "${LOADER_CONF}.bak" ]; then
-            cp "${LOADER_CONF}.bak" "${LOADER_CONF}"
-            info "Restored backup from ${LOADER_CONF}.bak"
-        fi
-        exit 1
-    fi
-
-    info "Successfully set default boot entry to ${prev_entry} (generation ${prev_gen})"
-    info "Backup of previous config saved to ${LOADER_CONF}.bak"
-
-    # Step 6: Optionally run nixos-rebuild switch --rollback
-    if [ "${ROLLBACK_NOW}" = true ]; then
-        echo ""
-        info "Running nixos-rebuild switch --rollback for immediate effect..."
-        if nixos-rebuild switch --rollback 2>&1 | while IFS= read -r line; do
-            logger -t "${SYSLOG_IDENT}" "nixos-rebuild: ${line}"
-            echo "    ${line}"
-        done; then
-            info "nixos-rebuild switch --rollback completed successfully"
-        else
-            local rc=$?
-            error "nixos-rebuild switch --rollback failed with exit code ${rc}"
-            error "The boot default has been changed but the current system was NOT rolled back"
-            error "Reboot to apply the rollback"
-            exit 3
-        fi
-    fi
-
-    info "Rollback complete. Next boot will use generation ${prev_gen}."
-    if [ "${ROLLBACK_NOW}" = false ]; then
-        echo ""
-        echo " ${YELLOW}NOTE:${NC} The current running system is unchanged."
-        echo "       Reboot to boot into generation ${prev_gen}."
-        echo "       Or re-run with --rollback-now for immediate effect."
-    fi
-}
-
-# =============================================================================
-# Main
-# =============================================================================
-main() {
-    # Parse arguments
-    while [ $# -gt 0 ]; do
-        case "$1" in
-            --dry-run)
-                DRY_RUN=true
-                shift
-                ;;
-            --rollback-now)
-                ROLLBACK_NOW=true
-                shift
-                ;;
-            -h|--help)
-                usage
-                exit 0
-                ;;
-            *)
-                echo >&2 "Unknown option: $1"
-                echo >&2 "Use --help for usage information."
-                exit 1
-                ;;
-        esac
-    done
-
-    echo ""
-    echo " ${CYAN}═══ NixOS systemd-boot Rollback ═══${NC}"
-    echo ""
-
-    preflight
-
-    if [ "${DRY_RUN}" = true ]; then
-        info "DRY RUN mode — no changes will be made"
-    fi
-    if [ "${ROLLBACK_NOW}" = true ]; then
-        info "ROLLBACK NOW mode — will also run nixos-rebuild switch --rollback"
-    fi
-
-    echo ""
-    do_rollback
-}
-
-main "$@"
--- a/modules/nixos/services/rollback-sentinel.nix
+++ b/modules/nixos/services/rollback-sentinel.nix
@@ -1,184 +0,0 @@
-{ config, pkgs, lib, ... }:
-
-with lib;
-
-let
-  cfg = config.services.rollbackSentinel;
-
-  # ── Scripts ────────────────────────────────────────────────────────────────
-
-  # Sentinel check — verifies Tier-1 services are active after boot.
-  # Exits nonzero when any Tier-1 service is down, which triggers the rollback.
-  sentinelCheck = pkgs.writeShellScriptBin "sentinel-check.sh" ''
-    #!/usr/bin/env bash
-    set -euo pipefail
-
-    SYSLOG_IDENT="nixos-sentinel"
-    LOGFILE="/var/log/nixos-sentinel.log"
-
-    echo "=== NixOS Sentinel Check ==="
-    echo "Tier-1 services: ${builtins.toString cfg.tier1Services}"
-    echo "Tier-2 services: ${builtins.toString cfg.tier2Services}"
-
-    FAILED=0
-
-    # Check Tier-1 services — any failure means rollback
-    for svc in ${builtins.toString cfg.tier1Services}; do
-      if systemctl is-active --quiet "$svc" 2>/dev/null; then
-        echo "  [OK]  Tier-1: $svc"
-      else
-        echo "  [FAIL] Tier-1: $svc is NOT active"
-        logger -t "$SYSLOG_IDENT" -p user.err "Tier-1 FAILURE: $svc is not active"
-        FAILED=1
-      fi
-    done
-
-    # Check Tier-2 services — warn only
-    for svc in ${builtins.toString cfg.tier2Services}; do
-      if systemctl is-active --quiet "$svc" 2>/dev/null; then
-        echo "  [OK]  Tier-2: $svc"
-      else
-        echo "  [WARN] Tier-2: $svc is NOT active"
-        logger -t "$SYSLOG_IDENT" -p user.warn "Tier-2 WARNING: $svc is not active"
-      fi
-    done
-
-    echo "=== Sentinel result: $([ "$FAILED" -eq 0 ] && echo 'PASS' || echo 'FAIL') ==="
-    echo "$(date '+%Y-%m-%d %H:%M:%S') [INFO] sentinel $([ "$FAILED" -eq 0 ] && echo 'PASS' || echo 'FAIL')" >> "$LOGFILE"
-    exit $FAILED
-  '';
-
-  # Rollback script — package the companion shell script from this directory.
-  # Uses builtins.readFile to embed the content at evaluation time.
-  rollbackScript = pkgs.writeShellScriptBin "nixos-rollback.sh" (builtins.readFile ./nixos-rollback.sh);
-
-  # Resolve rollback flags from config
-  rollbackFlags =
-    if cfg.rollbackMode == "dry-run" then "--dry-run"
-    else if cfg.rollbackMode == "rollback-now" then "--rollback-now"
-    else "";
-
-in {
-  options.services.rollbackSentinel = {
-    enable = mkEnableOption "NixOS Rollback Sentinel — auto-rollback on critical service failure";
-
-    tier1Services = mkOption {
-      type = types.listOf types.str;
-      default = [ "sshd" "docker" "traefik" "authelia" ];
-      description = ''
-        Tier-1 services whose failure triggers an automatic systemd-boot rollback.
-        On boot, the sentinel waits ${cfg.bootDelay} seconds, then checks each
-        service. If ANY service in this list is inactive, it runs the rollback
-        script which sets the previous NixOS generation as the default boot entry.
-      '';
-    };
-
-    tier2Services = mkOption {
-      type = types.listOf types.str;
-      default = [
-        "gitea" "hermes" "ollama" "synapse" "nextcloud"
-        "vaultwarden" "wireguard" "homeassistant" "fail2ban"
-      ];
-      description = ''
-        Tier-2 services whose failure is logged as a warning but does NOT trigger
-        an automatic rollback. Useful for detecting non-critical service issues.
-      '';
-    };
-
-    tier3InfoServices = mkOption {
-      type = types.listOf types.str;
-      default = [
-        "act_runner" "syncthing" "restic" "fava"
-        "homer" "cups" "fstrim"
-      ];
-      description = ''
-        Tier-3 informational checks (log-only, no warning). These are services
-        that the sentinel will note the status of for diagnostics.
-      '';
-    };
-
-    bootDelay = mkOption {
-      type = types.str;
-      default = "120";
-      description = ''
-        Seconds to wait after multi-user.target before running the boot-time
-        sentinel check. This gives Tier-1 services time to start before
-        the sentinel decides they've failed.
-      '';
-    };
-
-    rollbackMode = mkOption {
-      type = types.enum [ "set-default" "rollback-now" "dry-run" ];
-      default = "set-default";
-      description = ''
-        Rollback strategy when Tier-1 failures are detected:
-        - set-default: Write the previous generation to loader.conf (next reboot).
-        - rollback-now: Also run nixos-rebuild switch --rollback for immediate fix.
-        - dry-run: Log what would happen but take no action (testing).
-      '';
-    };
-
-    enablePostRebuild = mkOption {
-      type = types.bool;
-      default = true;
-      description = ''
-        When enabled, the sentinel check runs after every nixos-rebuild switch
-        activation. If a newly deployed generation has Tier-1 failures, it
-        triggers rollback immediately.
-      '';
-    };
-  };
-
-  config = mkIf cfg.enable {
-    # ── Deploy scripts to PATH ───────────────────────────────────────────────
-    environment.systemPackages = [ sentinelCheck rollbackScript ];
-
-    # Ensure log directory exists
-    systemd.tmpfiles.rules = [
-      "d /var/log/nixos-sentinel 0755 root root -"
-    ];
-
-    # ── Boot-time sentinel service ───────────────────────────────────────────
-    # Runs after multi-user.target with a configurable delay, checks Tier-1
-    # services, and triggers rollback if any are down.
-    systemd.services.nixos-sentinel = {
-      description = "NixOS Boot Sentinel — check critical services, roll back on failure";
-      after = [ "network.target" "multi-user.target" ];
-      wants = [ "network.target" ];
-      wantedBy = [ "multi-user.target" ];
-
-      path = with pkgs; [ coreutils gawk gnused systemd ];
-
-      serviceConfig = {
-        Type = "oneshot";
-        RemainAfterExit = true;
-        ExecStartPre = "${pkgs.coreutils}/bin/sleep ${cfg.bootDelay}";
-        ExecStart = "${sentinelCheck}/bin/sentinel-check.sh";
-        ExecStartPost = "${rollbackScript}/bin/nixos-rollback.sh ${rollbackFlags}";
-      };
-    };
-
-    # ── Post-rebuild sentinel service (triggered by activation script) ──────
-    systemd.services.nixos-sentinel-rebuild = mkIf cfg.enablePostRebuild {
-      description = "NixOS Post-Rebuild Sentinel — check services after nixos-rebuild";
-      after = [ "network.target" ];
-
-      path = with pkgs; [ coreutils gawk gnused systemd ];
-
-      serviceConfig = {
-        Type = "oneshot";
-        ExecStart = "${sentinelCheck}/bin/sentinel-check.sh";
-        ExecStartPost = "${rollbackScript}/bin/nixos-rollback.sh ${rollbackFlags}";
-      };
-    };
-
-    # Activation script — fires after every nixos-rebuild switch
-    system.activationScripts.rollback-sentinel = mkIf cfg.enablePostRebuild ''
-      # Start the post-rebuild sentinel in the background.
-      # This runs on every activation (boot + nixos-rebuild). On boot the
-      # boot-time service handles it, so this is primarily for nixos-rebuild,
-      # but running twice is safe (idempotent rollback).
-      systemctl start nixos-sentinel-rebuild.service --no-block 2>/dev/null || true
-    '';
-  };
-}
--- a/modules/nixos/services/staging-vm.nix
+++ b/modules/nixos/services/staging-vm.nix
@@ -0,0 +1,275 @@
+{ config, pkgs, lib, ... }:
+
+with lib;
+
+let
+  cfg = config.services.stagingVm;
+in
+{
+  options.services.stagingVm = {
+    enable = mkOption {
+      type = types.bool;
+      default = false;
+      description = "Enable KVM/libvirt staging VM for compose PR testing";
+    };
+
+    vmName = mkOption {
+      type = types.str;
+      default = "compose-test-vm";
+      description = "Name of the staging VM";
+    };
+
+    memory = mkOption {
+      type = types.str;
+      default = "4096";
+      description = "RAM allocated to the staging VM (MB)";
+    };
+
+    vcpus = mkOption {
+      type = types.int;
+      default = 2;
+      description = "Number of vCPUs for the staging VM";
+    };
+
+    storagePath = mkOption {
+      type = types.str;
+      default = "/var/lib/libvirt/images";
+      description = "Path for libvirt storage pool";
+    };
+
+    dataPath = mkOption {
+      type = types.str;
+      default = "/var/lib/staging-vm";
+      description = "Path for compose test data (PR checkouts, test results)";
+    };
+  };
+
+  config = mkIf cfg.enable {
+    # Enable libvirt daemon
+    virtualisation.libvirtd = {
+      enable = true;
+      qemu = {
+        package = pkgs.qemu_kvm;
+        runAsRoot = true;
+        swtpm.enable = true;
+        ovmf = {
+          enable = true;
+          packages = [ pkgs.OVMFFull.fd ];
+        };
+      };
+    };
+
+    # Kernel modules + groups already handled in configuration.nix
+
+    # libvirt NAT network (192.168.122.0/24)
+    environment.etc."libvirt/qemu/networks/default.xml" = {
+      text = ''
+        <network>
+          <name>default</name>
+          <uuid>2b8f7a3c-9e5d-4a1f-bc3d-6e7a8f9b0c1d</uuid>
+          <forward mode='nat'>
+            <nat>
+              <port start='1024' end='65535'/>
+            </nat>
+          </forward>
+          <bridge name='virbr0' stp='on' delay='0'/>
+          <mac address='52:54:00:12:34:56'/>
+          <ip address='192.168.122.1' netmask='255.255.255.0'>
+            <dhcp>
+              <range start='192.168.122.2' end='192.168.122.254'/>
+            </dhcp>
+          </ip>
+        </network>
+      '';
+      # Autostart the network so it comes up on boot
+      mode = "0644";
+    };
+
+    # Ensure the default network is defined and autostarted
+    systemd.services.libvirtd = {
+      postStart = ''
+        ${pkgs.libvirt}/bin/virsh net-define /etc/libvirt/qemu/networks/default.xml 2>/dev/null || true
+        ${pkgs.libvirt}/bin/virsh net-autostart default 2>/dev/null || true
+        ${pkgs.libvirt}/bin/virsh net-start default 2>/dev/null || true
+      '';
+    };
+
+    # Storage directory for VM images
+    systemd.tmpfiles.rules = [
+      "d ${cfg.storagePath} 0755 root root -"
+      "d ${cfg.dataPath} 0755 root root -"
+    ];
+
+    # Ensure storage pool exists in libvirt
+    systemd.services.libvirtd.postStart = mkAfter ''
+      ${pkgs.libvirt}/bin/virsh pool-define-as default dir --target "${cfg.storagePath}" 2>/dev/null || true
+      ${pkgs.libvirt}/bin/virsh pool-autostart default 2>/dev/null || true
+      ${pkgs.libvirt}/bin/virsh pool-start default 2>/dev/null || true
+    '';
+
+    # Firewall: allow traffic from virbr0 to host and outbound NAT
+    networking.firewall = {
+      extraCommands = ''
+        # Allow inbound DHCP/DNS from libvirt guests
+        iptables -I INPUT -i virbr0 -p udp --dport 67:68 -j ACCEPT
+        iptables -I INPUT -i virbr0 -p tcp --dport 53 -j ACCEPT
+        iptables -I INPUT -i virbr0 -p udp --dport 53 -j ACCEPT
+        
+        # Allow established/related traffic back to guests
+        iptables -I FORWARD -i virbr0 -o virbr0 -j ACCEPT
+        iptables -I FORWARD -o virbr0 -j ACCEPT
+        iptables -I FORWARD -i virbr0 -j ACCEPT
+      '';
+    };
+
+    # Packages needed for VM management
+    environment.systemPackages = with pkgs; [
+      libvirt
+      qemu_kvm
+      virt-manager  # optional GUI for manual management
+      OVMFFull
+      swtpm
+    ];
+
+    # Enable docker in the host (already enabled, but ensure for compose testing)
+    virtualisation.docker.enable = true;
+
+    # Helper script: pr-test-vm
+    # Usage:
+    #   pr-test-vm build    — build the staging VM derivation
+    #   pr-test-vm start    — boot the VM with a compose PR branch
+    #   pr-test-vm stop     — graceful shutdown
+    #   pr-test-vm destroy  — force stop + delete VM
+    #   pr-test-vm ssh      — SSH into the running VM
+    systemd.tmpfiles.rules = mkAfter [
+      "d ${cfg.dataPath}/scripts 0755 root root -"
+    ];
+
+    environment.systemPackages = [ (pkgs.writeShellScriptBin "pr-test-vm" ''
+      set -euo pipefail
+
+      DATA="${cfg.dataPath}"
+      VM_NAME="${cfg.vmName}"
+      VM_IMAGE="''${DATA}/''${VM_NAME}.qcow2"
+      VM_PORT=2223
+
+      build_vm() {
+        echo "==> Building NixOS staging VM for compose testing..."
+        # Build the VM config inline — a minimal NixOS with Docker + SSH
+        cat > /tmp/staging-vm-config.nix << 'NIXEOF'
+          { config, pkgs, lib, ... }: {
+            boot.loader.grub.devices = [ "/dev/vda" ];
+            boot.loader.timeout = 0;
+
+            # Minimal kernel
+            boot.kernelParams = [ "console=ttyS0" ];
+            boot.initrd.kernelModules = [ "virtio_blk" "virtio_net" "virtio_pci" ];
+
+            # SSH access
+            services.openssh = {
+              enable = true;
+              settings.PasswordAuthentication = false;
+              settings.PermitRootLogin = "prohibit-password";
+            };
+
+            # Docker for compose testing
+            virtualisation.docker.enable = true;
+
+            # Network (DHCP via virbr0)
+            networking.useDHCP = true;
+            networking.firewall.enable = false;
+
+            # Users
+            users.users.root.openssh.authorizedKeys.keys = [
+              "$(cat /root/.ssh/authorized_keys 2>/dev/null || echo 'ssh-ed25519 AAAAC3... placeholder')"
+            ];
+            users.users.testrunner = {
+              isNormalUser = true;
+              extraGroups = [ "docker" ];
+              openssh.authorizedKeys.keys = [
+                "$(cat /root/.ssh/authorized_keys 2>/dev/null || echo 'ssh-ed25519 AAAAC3... placeholder')"
+              ];
+            };
+
+            # Git + compose tools
+            environment.systemPackages = with pkgs; [ git docker-compose curl ];
+
+            system.stateVersion = "24.11";
+          }
+        NIXEOF
+
+        nixos-rebuild build-vm -I nixpkgs=channel:nixos-unstable \
+          --arg configuration 'import /tmp/staging-vm-config.nix' \
+          --out-link "''${DATA}/vm-result"
+        echo "==> VM built. Run 'pr-test-vm start' to boot."
+      }
+
+      start_vm() {
+        if [ -f "''${VM_IMAGE}" ]; then
+          echo "==> Booting existing VM..."
+        else
+          echo "==> Creating VM image..."
+          ${pkgs.qemu_kvm}/bin/qemu-img create -f qcow2 "''${VM_IMAGE}" 20G
+        fi
+
+        # Check if already running
+        if ${pkgs.libvirt}/bin/virsh list --name 2>/dev/null | grep -q "''${VM_NAME}"; then
+          echo "==> VM already running."
+          exit 0
+        fi
+
+        ${pkgs.qemu_kvm}/bin/qemu-system-x86_64 \
+          -name "''${VM_NAME}" \
+          -machine q35,accel=kvm \
+          -cpu host \
+          -smp ${toString cfg.vcpus} \
+          -m ${cfg.memory} \
+          -drive file="''${VM_IMAGE}",if=virtio,format=qcow2 \
+          -netdev user,id=net0,hostfwd=tcp::''${VM_PORT}-:22 \
+          -device virtio-net-pci,netdev=net0 \
+          -nographic \
+          -serial mon:stdio \
+          -pidfile "''${DATA}/''${VM_NAME}.pid" \
+          -daemonize
+
+        echo "==> VM booting... SSH on port ''${VM_PORT}"
+        echo "==> Wait for it: ssh -p ''${VM_PORT} testrunner@localhost"
+      }
+
+      stop_vm() {
+        PIDFILE="''${DATA}/''${VM_NAME}.pid"
+        if [ -f "''${PIDFILE}" ]; then
+          PID=$(cat "''${PIDFILE}")
+          kill "''${PID}" 2>/dev/null || true
+          rm -f "''${PIDFILE}"
+          echo "==> VM stopped."
+        else
+          ${pkgs.libvirt}/bin/virsh destroy "''${VM_NAME}" 2>/dev/null || true
+          echo "==> VM destroyed."
+        fi
+      }
+
+      ssh_vm() {
+        exec ssh -p "''${VM_PORT}" -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null "testrunner@localhost" "$@"
+      }
+
+      # Main dispatch
+      case "''${1:-help}" in
+        build)   build_vm ;;
+        start)   start_vm ;;
+        stop)    stop_vm ;;
+        destroy) stop_vm; rm -f "''${VM_IMAGE}"; echo "==> VM deleted." ;;
+        ssh)     shift; ssh_vm "$@" ;;
+        *)
+          echo "Usage: pr-test-vm {build|start|stop|destroy|ssh}"
+          echo ""
+          echo "  build    — build the NixOS VM derivation"
+          echo "  start    — boot the VM (create image if needed)"
+          echo "  stop     — graceful VM shutdown"
+          echo "  destroy  — stop + delete VM image"
+          echo "  ssh      — SSH into the running VM"
+          ;;
+      esac
+    '') ];
+  };
+}
--- a/overlays/reticulum.nix
+++ b/overlays/reticulum.nix
@@ -1,77 +0,0 @@
-final: prev: let
-  python3 = final.python3;
-  pyPkgs = python3.pkgs;
-in {
-  reticulumStack = python3.pkgs.buildPythonApplication rec {
-    pname = "reticulum";
-    version = "1.2.9";
-    src = pyPkgs.fetchPypi {
-      pname = "rns";
-      inherit version;
-      sha256 = "554814231c237b9caacf8df669312e57dd7d3f84b6d4810125087d1a79a75d75";
-    };
-    propagatedBuildInputs = with pyPkgs; [ cryptography pyserial ];
-    doCheck = false;
-    pythonImportsCheck = [ "RNS" ];
-    meta = with final.lib; {
-      description = "Self-configuring, encrypted and resilient mesh networking stack";
-      homepage = "https://reticulum.network/";
-      license = licenses.mit;
-      platforms = platforms.linux;
-    };
-  };
-
-  lxmf = python3.pkgs.buildPythonApplication rec {
-    pname = "lxmf";
-    version = "0.9.8";
-    src = pyPkgs.fetchPypi {
-      inherit pname version;
-      sha256 = "30f39f3a975a049c12ee2cfceb3261d24cb5adec881c6821f7354464b3f3650c";
-    };
-    propagatedBuildInputs = [ final.reticulumStack ];
-    doCheck = false;
-    pythonImportsCheck = [ "LXMF" ];
-    meta = with final.lib; {
-      description = "Lightweight Extensible Message Format for Reticulum";
-      homepage = "https://github.com/markqvist/lxmf";
-      license = licenses.mit;
-      platforms = platforms.linux;
-    };
-  };
-
-  nomadnet = python3.pkgs.buildPythonApplication rec {
-    pname = "nomadnet";
-    version = "1.1.1";
-    src = pyPkgs.fetchPypi {
-      inherit pname version;
-      sha256 = "fa13b64a10e75b705a58024815ab72451700aa726af96d415ba99dec28dfc40a";
-    };
-    propagatedBuildInputs = with pyPkgs; [ final.reticulumStack final.lxmf urwid qrcode ];
-    doCheck = false;
-    pythonImportsCheck = [ "nomadnet" ];
-    meta = with final.lib; {
-      description = "Nomad Network — resilient mesh communications platform";
-      homepage = "https://github.com/markqvist/NomadNet";
-      license = licenses.mit;
-      platforms = platforms.linux;
-    };
-  };
-
-  rnsh = python3.pkgs.buildPythonApplication rec {
-    pname = "rnsh";
-    version = "0.1.7";
-    src = pyPkgs.fetchPypi {
-      inherit pname version;
-      sha256 = "9cb72f25abb1c6d300f8014b264184ff78f592fe88e36094938012990b797c93";
-    };
-    propagatedBuildInputs = [ final.reticulumStack ];
-    doCheck = false;
-    pythonImportsCheck = [ "rnsh" ];
-    meta = with final.lib; {
-      description = "Remote shell over Reticulum";
-      homepage = "https://github.com/acehoss/rnsh";
-      license = licenses.mit;
-      platforms = platforms.linux;
-    };
-  };
-}
--- a/tests/run-integration.sh
+++ b/tests/run-integration.sh
@@ -0,0 +1,347 @@
+#!/usr/bin/env bash
+# =============================================================================
+# run-integration.sh — Staging VM Integration Test Suite
+#
+# Verifies Docker daemon, compose stack, and service endpoint health.
+# Designed to run inside the staging VM as part of CI/CD pipeline.
+#
+# Usage:
+#   ./tests/run-integration.sh                  # all defaults
+#   ./tests/run-integration.sh --verbose         # detailed output
+#   ./tests/run-integration.sh --list-services   # print detected services and exit
+#
+# Environment variables (all optional):
+#   COMPOSE_DIR       Path to compose service directories  (default: /opt/infra/compose)
+#   COMPOSE_PROJECT   Docker Compose project name          (default: staging)
+#   STAGING_DOMAIN    Base domain for health checks        (default: staging.lazyworkhorse.net)
+#   SERVICE_LIST      Space-separated service dirs to check (default: auto-detect)
+#   HEALTH_URLS       Space-separated URLs for health checks (default: auto-detect from SERVICE_LIST)
+#   HEALTH_TIMEOUT    Curl timeout per check (seconds)      (default: 5)
+#   HEALTH_RETRIES    Number of retries per endpoint         (default: 1)
+#   HEALTH_INTERVAL   Seconds between retries                (default: 2)
+# =============================================================================
+
+set -euo pipefail
+
+# ---- Colors for readable output ----
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+CYAN='\033[0;36m'
+BOLD='\033[1m'
+NC='\033[0m' # No Color
+
+# ---- Configuration (all env-overridable) ----
+COMPOSE_DIR="${COMPOSE_DIR:-/opt/infra/compose}"
+COMPOSE_PROJECT="${COMPOSE_PROJECT:-staging}"
+STAGING_DOMAIN="${STAGING_DOMAIN:-staging.lazyworkhorse.net}"
+HEALTH_TIMEOUT="${HEALTH_TIMEOUT:-5}"
+HEALTH_RETRIES="${HEALTH_RETRIES:-1}"
+HEALTH_INTERVAL="${HEALTH_INTERVAL:-2}"
+
+# Known compose service directories in order — override via SERVICE_LIST env var
+DEFAULT_SERVICES=(
+  network
+  authentification
+  homepage
+  ai
+  cloudstorage
+  versioncontrol
+  backup
+  coms
+  finance
+  homeautomation
+  passwordmanager
+)
+
+# Map service directory -> default health check URL (relative to STAGING_DOMAIN)
+# Override entirely via HEALTH_URLS env var.
+declare -A DEFAULT_HEALTH_URLS
+DEFAULT_HEALTH_URLS[network]="https://traefik.${STAGING_DOMAIN}/ping"
+DEFAULT_HEALTH_URLS[authentification]="https://auth.${STAGING_DOMAIN}/api/verify"
+DEFAULT_HEALTH_URLS[homepage]="https://${STAGING_DOMAIN}/"
+DEFAULT_HEALTH_URLS[ai]="https://hermes.${STAGING_DOMAIN}/health"
+DEFAULT_HEALTH_URLS[cloudstorage]="https://cloud.${STAGING_DOMAIN}/status.php"
+DEFAULT_HEALTH_URLS[versioncontrol]="https://code.${STAGING_DOMAIN}/api/healthz"
+
+# ---- Trackers ----
+PASS_COUNT=0
+FAIL_COUNT=0
+WARN_COUNT=0
+FAILURES=()
+
+# ---- Helpers ----
+
+log_info()  { echo -e "${CYAN}[INFO]${NC}  $*"; }
+log_pass()  { echo -e "${GREEN}[PASS]${NC}  $*"; ((PASS_COUNT++)); }
+log_fail()  { echo -e "${RED}[FAIL]${NC}  $*"; ((FAIL_COUNT++)); FAILURES+=("$*"); }
+log_warn()  { echo -e "${YELLOW}[WARN]${NC}  $*"; ((WARN_COUNT++)); }
+log_step()  { echo -e "\n${BOLD}── $* ──${NC}"; }
+log_raw()   { echo -e "         $*"; }
+
+# Check if a command exists
+require_cmd() {
+  if ! command -v "$1" &>/dev/null; then
+    log_fail "Required command not found: $1"
+    return 1
+  fi
+}
+
+# Retry a command with exponential-like backoff
+retry() {
+  local cmd="$*"
+  local attempt=0
+  local max_attempts=$((HEALTH_RETRIES + 1))
+  local result
+
+  while [[ $attempt -lt $max_attempts ]]; do
+    if eval "$cmd" 2>/dev/null; then
+      return 0
+    fi
+    attempt=$((attempt + 1))
+    if [[ $attempt -lt $max_attempts ]]; then
+      sleep "$HEALTH_INTERVAL"
+    fi
+  done
+  return 1
+}
+
+# ---- Parse arguments ----
+VERBOSE=false
+LIST_SERVICES=false
+POSITIONAL=()
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --verbose|-v)  VERBOSE=true; shift ;;
+    --list-services) LIST_SERVICES=true; shift ;;
+    --) shift; POSITIONAL+=("$@"); break ;;
+    *) POSITIONAL+=("$1"); shift ;;
+  esac
+done
+set -- "${POSITIONAL[@]}"
+
+# Resolve service list
+if [[ -n "${SERVICE_LIST:-}" ]]; then
+  IFS=' ' read -ra SERVICES <<< "$SERVICE_LIST"
+else
+  SERVICES=("${DEFAULT_SERVICES[@]}")
+fi
+
+# Resolve health URLs — default map with overrides from env
+declare -A HEALTH_URLS
+if [[ -n "${HEALTH_URLS:-}" ]]; then
+  # User-supplied mapping: "network=https://... authentification=https://..."
+  for pair in $HEALTH_URLS; do
+    key="${pair%%=*}"
+    val="${pair#*=}"
+    HEALTH_URLS["$key"]="$val"
+  done
+else
+  for svc in "${SERVICES[@]}"; do
+    if [[ -n "${DEFAULT_HEALTH_URLS[$svc]:-}" ]]; then
+      HEALTH_URLS["$svc"]="${DEFAULT_HEALTH_URLS[$svc]}"
+    fi
+  done
+fi
+
+# --list-services mode (for CI integration)
+if $LIST_SERVICES; then
+  echo "Configured services:"
+  for svc in "${SERVICES[@]}"; do
+    url="${HEALTH_URLS[$svc]:-no-health-check}"
+    echo "  $svc -> $url"
+  done
+  exit 0
+fi
+
+# ---- Pre-flight ----
+echo -e "${BOLD}============================================${NC}"
+echo -e "${BOLD}  Staging VM Integration Test Suite${NC}"
+echo -e "${BOLD}  $(date -u '+%Y-%m-%dT%H:%M:%SZ')${NC}"
+echo -e "${BOLD}============================================${NC}"
+
+# ---- Phase 1: Prerequisites ----
+log_step "Phase 1: Prerequisites"
+
+PREREQ_OK=true
+for cmd in docker curl jq; do
+  if ! require_cmd "$cmd"; then
+    PREREQ_OK=false
+  fi
+done
+$PREREQ_OK && log_pass "All required commands available" || log_fail "Missing prerequisites"
+
+# ---- Phase 2: Docker daemon ----
+log_step "Phase 2: Docker Daemon"
+
+if docker info --format '{{.ServerVersion}}' &>/dev/null; then
+  DOCKER_VERSION=$(docker info --format '{{.ServerVersion}}' 2>/dev/null)
+  log_pass "Docker daemon is running (version: $DOCKER_VERSION)"
+
+  if docker info --format '{{.Driver}}' 2>/dev/null | grep -qi "overlay"; then
+    log_pass "Storage driver: overlay"
+  else
+    log_warn "Non-overlay storage driver detected"
+  fi
+else
+  log_fail "Docker daemon is NOT running or not accessible"
+fi
+
+# ---- Phase 3: Docker Compose stack ----
+log_step "Phase 3: Compose Stack Status"
+
+# Check if any compose files exist
+COMPOSE_FILES=()
+for svc in "${SERVICES[@]}"; do
+  cf="${COMPOSE_DIR}/${svc}/compose.yml"
+  if [[ -f "$cf" ]]; then
+    COMPOSE_FILES+=("$cf")
+  else
+    cf2="${COMPOSE_DIR}/${svc}/docker-compose.yml"
+    if [[ -f "$cf2" ]]; then
+      COMPOSE_FILES+=("$cf2")
+    else
+      log_warn "No compose file found for service '$svc' (expected: ${cf})"
+    fi
+  fi
+done
+
+if [[ ${#COMPOSE_FILES[@]} -eq 0 ]]; then
+  log_fail "No compose files found under COMPOSE_DIR=${COMPOSE_DIR}"
+  log_info "Skipping stack checks"
+else
+  log_info "Found ${#COMPOSE_FILES[@]} compose file(s) in ${COMPOSE_DIR}"
+
+  # Build the compose file args
+  COMPOSE_CMD="docker compose -p ${COMPOSE_PROJECT}"
+  for cf in "${COMPOSE_FILES[@]}"; do
+    COMPOSE_CMD+=" -f ${cf}"
+  done
+
+  log_info "Project name: ${COMPOSE_PROJECT}"
+
+  # Check stack ps
+  if $VERBOSE; then
+    log_raw "--- docker compose ps output ---"
+    eval "$COMPOSE_CMD ps" 2>&1 | while IFS= read -r line; do log_raw "$line"; done
+    log_raw "--- end ---"
+  fi
+
+  # Get all services and their status
+  if STACK_STATUS=$(eval "$COMPOSE_CMD ps --format '{{.Name}}\t{{.Status}}'" 2>/dev/null); then
+    if [[ -z "$STACK_STATUS" ]]; then
+      log_warn "Stack exists but no running services — VM may be freshly provisioned"
+    else
+      ALL_RUNNING=true
+      RUNNING_COUNT=0
+      TOTAL_COUNT=0
+      while IFS=$'\t' read -r name status; do
+        TOTAL_COUNT=$((TOTAL_COUNT + 1))
+        status_lower=$(echo "$status" | tr '[:upper:]' '[:lower:]')
+        if echo "$status_lower" | grep -qE '^(up|running|healthy)'; then
+          RUNNING_COUNT=$((RUNNING_COUNT + 1))
+          $VERBOSE && log_pass "  $name — $status"
+        else
+          ALL_RUNNING=false
+          log_warn "  $name — $status (not healthy)"
+        fi
+      done <<< "$STACK_STATUS"
+
+      if [[ "$TOTAL_COUNT" -eq 0 ]]; then
+        log_fail "No services found in compose project"
+      elif $ALL_RUNNING && [[ "$TOTAL_COUNT" -eq "$RUNNING_COUNT" ]]; then
+        log_pass "All ${TOTAL_COUNT} service(s) running (${RUNNING_COUNT}/${TOTAL_COUNT})"
+      else
+        log_fail "${RUNNING_COUNT}/${TOTAL_COUNT} service(s) running — some services are down"
+      fi
+    fi
+  else
+    log_fail "Failed to query compose stack status"
+  fi
+fi
+
+# ---- Phase 4: Service health checks ----
+log_step "Phase 4: Service Endpoint Health Checks"
+
+ENDPOINT_CHECKS=0
+ENDPOINT_PASS=0
+
+for svc in "${SERVICES[@]}"; do
+  url="${HEALTH_URLS[$svc]:-}"
+  if [[ -z "$url" ]]; then
+    $VERBOSE && log_info "No health check URL for service '$svc' — skipping"
+    continue
+  fi
+
+  ENDPOINT_CHECKS=$((ENDPOINT_CHECKS + 1))
+  echo -ne "  Checking ${svc} ... "
+
+  # Perform the HTTP health check with retries
+  if retry "curl -sf -o /dev/null -w '%{http_code}' --max-time ${HEALTH_TIMEOUT} '${url}' 2>/dev/null"; then
+    HTTP_CODE=$(curl -sf -o /dev/null -w '%{http_code}' --max-time "${HEALTH_TIMEOUT}" "${url}" 2>/dev/null || true)
+    ENDPOINT_PASS=$((ENDPOINT_PASS + 1))
+    echo -e "${GREEN}OK${NC} (HTTP ${HTTP_CODE})"
+  else
+    LAST_CODE=$(curl -s -o /dev/null -w '%{http_code}' --max-time "${HEALTH_TIMEOUT}" "${url}" 2>/dev/null || echo "000")
+    echo -e "${RED}FAIL${NC} (HTTP ${LAST_CODE})"
+    log_fail "Health check failed for ${svc} @ ${url}"
+  fi
+done
+
+if [[ $ENDPOINT_CHECKS -eq 0 ]]; then
+  log_warn "No health check URLs configured — skipping endpoint phase"
+elif [[ $ENDPOINT_PASS -eq $ENDPOINT_CHECKS ]]; then
+  log_pass "All ${ENDPOINT_CHECKS} endpoint(s) healthy"
+else
+  log_fail "${ENDPOINT_PASS}/${ENDPOINT_CHECKS} endpoint(s) healthy"
+fi
+
+# ---- Phase 5: Docker system sanity ----
+log_step "Phase 5: Docker System Sanity"
+
+# Check disk space for Docker
+DOCKER_ROOT=$(docker info --format '{{.DockerRootDir}}' 2>/dev/null || echo "/var/lib/docker")
+log_info "Docker root: ${DOCKER_ROOT}"
+
+if command -v df &>/dev/null && [[ -d "$DOCKER_ROOT" ]]; then
+  AVAIL_PCT=$(df -h "$DOCKER_ROOT" | awk 'NR==2 {print $5}' | tr -d '%')
+  if [[ -n "$AVAIL_PCT" ]]; then
+    if [[ "$AVAIL_PCT" -ge 90 ]]; then
+      log_warn "Docker storage is ${AVAIL_PCT}% full — consider cleanup"
+    else
+      log_pass "Docker storage at ${AVAIL_PCT}% — within limits"
+    fi
+  fi
+fi
+
+# Check for dangling images
+DANGLING=$(docker images -f "dangling=true" -q 2>/dev/null | wc -l)
+if [[ "$DANGLING" -gt 10 ]]; then
+  log_warn "${DANGLING} dangling images found — consider docker image prune"
+fi
+
+# ---- Summary ----
+echo ""
+echo -e "${BOLD}============================================${NC}"
+echo -e "${BOLD}  Test Summary${NC}"
+echo -e "${BOLD}  $(date -u '+%Y-%m-%dT%H:%M:%SZ')${NC}"
+echo -e "${BOLD}============================================${NC}"
+echo -e "  ${GREEN}Passed:${NC}  ${PASS_COUNT}"
+echo -e "  ${RED}Failed:${NC}  ${FAIL_COUNT}"
+echo -e "  ${YELLOW}Warnings:${NC} ${WARN_COUNT}"
+
+if [[ ${#FAILURES[@]} -gt 0 ]]; then
+  echo -e "\n${BOLD}Failed checks:${NC}"
+  for f in "${FAILURES[@]}"; do
+    echo -e "  ${RED}•${NC} $f"
+  done
+fi
+
+echo ""
+if [[ $FAIL_COUNT -eq 0 ]]; then
+  echo -e "${GREEN}${BOLD}✓ All integration checks passed${NC}"
+  exit 0
+else
+  echo -e "${RED}${BOLD}✗ ${FAIL_COUNT} integration check(s) failed${NC}"
+  exit 1
+fi
--- a/users/ai-worker.nix
+++ b/users/ai-worker.nix
@@ -4,7 +4,7 @@
    group = "ai-worker";
    home = "/home/ai-worker";
    createHome = true;
-    extraGroups = [ "docker" ];
+    extraGroups = [ "docker" "libvirtd" ];
    shell = pkgs.bashInteractive;
    openssh.authorizedKeys.keys = [
      keys.users.ai-worker.main
Author	SHA1	Message	Date
Hermes	2c981578a5	feat: full integration test suite for staging VM Some checks failed Build and test NixOS config / build (pull_request) Has been cancelled Details Replace the stub placeholder with a comprehensive integration test script that verifyies Docker daemon, compose stack, and service endpoint health. All configuration via environment variables with sensible defaults. Changes: - tests/run-integration.sh: 5-phase test suite with color output, retry logic, env-var configuration, and CI-friendly exit codes - .gitea/workflows/build-nixos.yml: update CI step to document pr-test-vm usage with the new test script See also: pr-test-vm helper in modules/nixos/services/staging-vm.nix	2026-05-20 14:18:27 -04:00
Hermes	ec3da64594	feat: add CI workflow and integration test stub Some checks failed Build and test NixOS config / build (pull_request) Has been cancelled Details	2026-05-16 12:04:25 -04:00
Hermes	f1b1e5dc4c	cleanup-remove-stray-plan-file	2026-05-15 21:14:28 -04:00
Hermes	9158a0f93b	staging-vm-full-module	2026-05-15 21:12:53 -04:00
Hermes	37d690e4de	feat: add KVM/libvirt support for staging VM - Load kvm-intel and kvm kernel modules - Enable libvirtd service - Add ai-worker to libvirtd group Requires Intel VT-x to be enabled in BIOS. After reboot: verify /dev/kvm exists, then deploy staging VM.	2026-05-12 19:15:03 -04:00