feat: add staging-vm module with libvirt/KVM infrastructure

Creates .gitea/workflows/build-nixos.yml that triggers on push/PR to
master when Nix files, flake.lock, secrets, hosts, or modules change.

Includes:
- Setup step to enable Nix experimental features and install nh
- Build step for lazyworkhorse (x86_64-linux) via nh os build
- Build step for cyt-pi (aarch64-linux) via nh os build
- Placeholder integration test step

Runner label: nixos-builder (Docker image nixos/nix)

.gitea/workflows/build-nixos.yml

@@ -1,15 +1,19 @@
-name: Build and test NixOS config
+name: NixOS Build & Test
+run-name: Build ${{ gitea.event_name == 'push' && gitea.ref_name || format('PR #{0}', gitea.event.pull_request.number) }}
+
 on:
-  pull_request:
-    branches: [ master ]
+  push:
+    branches:
+      - master
     paths:
       - '**.nix'
       - 'flake.lock'
       - 'secrets/**'
       - 'hosts/**'
       - 'modules/**'
-  push:
-    branches: [ master ]
+  pull_request:
+    branches:
+      - master
     paths:
       - '**.nix'
       - 'flake.lock'
@@ -22,31 +26,39 @@ jobs:
     runs-on: nixos-builder
     steps:
       - name: Checkout
-        run: |
-          git clone -b "${{ github.head_ref || github.ref_name }}" \
-            https://gitea:${{ secrets.GITHUB_TOKEN }}@code.lazyworkhorse.net/gortium/infra.git .
-          git log --oneline -3
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
-      - name: Build NixOS config
+      - name: Set up Nix environment
         run: |
-          nix --version
-          nh os build .#lazyworkhorse 2>&1
+          echo "extra-experimental-features = nix-command flakes" >> ~/.config/nix/nix.conf
+          cat ~/.config/nix/nix.conf
 
-      - name: Run integration tests (staging VM)
+      - name: Install nh (nix helper)
         run: |
-          echo "==> Running integration tests on staging VM..."
+          nix --extra-experimental-features "nix-command flakes" \
+            profile add nixpkgs#nh
+          nh --version
+
+      - name: Build NixOS configuration (lazyworkhorse)
+        run: |
+          nh os build .#lazyworkhorse
+        env:
+          NIX_CONFIG: "extra-experimental-features = nix-command flakes"
+
+      - name: Build NixOS configuration (cyt-pi)
+        run: |
+          nh os build .#cyt-pi
+        env:
+          NIX_CONFIG: "extra-experimental-features = nix-command flakes"
+
+      - name: Integration tests (placeholder)
+        run: |
+          echo "TODO: Add integration tests here"
           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."
+          echo "Suggested future checks:"
+          echo "  - nix flake check  (evaluate all NixOS configs)"
+          echo "  - Validate agenix secrets are decryptable"
+          echo "  - Check services are defined correctly"
+          echo "  - Run VM test if nixos-test infrastructure exists"

flake.nix

@@ -59,9 +59,9 @@
               ./modules/nixos/filesystem/hoardingcow-mount.nix
               ./modules/nixos/services/docker_manager.nix
               ./modules/nixos/services/open_code_server.nix
+              ./modules/nixos/services/staging-vm.nix
               ./modules/nixos/services/ollama_init_custom_models.nix
               ./modules/nixos/services/openclaw_node.nix
-              ./modules/nixos/services/staging-vm.nix
               ./modules/nixos/security/ai-worker-restricted.nix
               ./users/gortium.nix
               ./users/ai-worker.nix

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" "kvm-intel" "kvm" ];
+  boot.kernelModules = [ "nct6775" "lm96163" "iptable_nat" "iptable_filter" ];
   # 3. Force the nct6775 driver to recognize the chip if it's stubborn
   boot.extraModprobeConfig = ''
     options nct6775 force_id=0xd280
@@ -207,6 +207,7 @@
     ai = {
       path = self + "/assets/compose/ai";
       envFile = config.age.secrets.containers_env.path;
+      ports = [ 22000 ];  # Syncthing TCP sync
     };
 
     cloudstorage = {
@@ -328,21 +329,20 @@
   # Mi50 config
   hardware.graphics = {
     enable = true;
-    enable32Bit = true;
+    enable32Bit = true; # Useful for some compatibility layers
     extraPackages = with pkgs; [
-      rocmPackages.clr.icd
+      rocmPackages.clr.icd # OpenCL/HIP runtime
     ];
   };
   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";
   };
 
-  # KVM/libvirt for staging VM
-  services.stagingVm.enable = true;
-
-  # Open ports in the firewall.
+ # Open ports in the firewall.
   # networking.firewall.allowedTCPPorts = [ ... ];
   # networking.firewall.allowedUDPPorts = [ ... ];
   # Or disable the firewall altogether.
@@ -475,7 +475,7 @@
   services.openssh.settings = {
     PermitRootLogin = "no";
     MaxAuthTries = 3;
-    MaxSessions = 10;
+    MaxSessions = 20;
     LoginGraceTime = 30;
     ClientAliveInterval = 300;
     ClientAliveCountMax = 2;

modules/nixos/services/staging-vm.nix

@@ -1,17 +1,21 @@
-{ config, pkgs, lib, ... }:
+{ config, lib, pkgs, ... }:
 
 with lib;
 
 let
-  cfg = config.services.stagingVm;
+  cfg = config.services.staging-vm;
+
+  # Resolve the first IP in the subnet (the gateway address for the NAT network)
+  networkIp = head (splitString "/" cfg.network.subnet);
 
   # ── pr-test-vm helper script ──────────────────────────────────────────
   pr-test-vm = pkgs.writeShellScriptBin "pr-test-vm" ''
     set -euo pipefail
 
     LIBVIRT_URI="qemu:///system"
-    VM_DIR="${cfg.dataPath}"
-    NETWORK="default"
+    STORAGE_POOL="${cfg.storagePool}"
+    VM_DIR="${cfg.dataDir}"
+    NETWORK="${cfg.network.name}"
     SCRIPT_NAME="$(basename "$0")"
 
     usage() {
@@ -27,6 +31,7 @@ let
       console <vm-name>                         Connect to VM serial console
       list                                      List all staging VMs
       status  <vm-name>                         Show VM status
+      rebuild <vm-name>                         Redeploy the VM (stop + start)
 
     Examples:
       $SCRIPT_NAME build ./vm-config.nix --name my-test
@@ -66,11 +71,14 @@ let
         fi
 
         BUILD_DIR="$VM_DIR/$VM_NAME"
+        IMAGE="$BUILD_DIR/disk-image.qcow2"
+
         echo "==> Building VM '$VM_NAME' from config: $CONFIG"
         mkdir -p "$BUILD_DIR"
 
         # Build the NixOS VM derivation
         nix build --no-link -f "$CONFIG" vm 2>&1 || {
+          # Fallback: try as flake output
           echo "Trying flake build..."
           nix build "''${CONFIG%/.nix}#nixosConfigurations.$VM_NAME.config.system.build.vm" --no-link 2>&1 || {
             echo "error: failed to build VM (tried both import and flake)"
@@ -191,6 +199,12 @@ let
         fi
         ;;
 
+      rebuild)
+        VM_NAME="''${1:?Missing VM name}"
+        "$0" destroy "$VM_NAME"
+        "$0" start "$VM_NAME"
+        ;;
+
       help|--help|-h)
         usage
         ;;
@@ -202,41 +216,63 @@ let
   '';
 in
 {
-  options.services.stagingVm = {
-    enable = mkOption {
-      type = types.bool;
-      default = false;
-      description = "Enable KVM/libvirt staging VM for compose PR testing";
+  options.services.staging-vm = {
+    enable = mkEnableOption "Staging VM infrastructure with libvirt/KVM";
+
+    network = {
+      name = mkOption {
+        type = types.str;
+        default = "staging";
+        description = "Name of the libvirt NAT network for staging VMs";
+      };
+
+      bridge = mkOption {
+        type = types.str;
+        default = "virbr1";
+        description = "Bridge interface name for the staging network";
+      };
+
+      subnet = mkOption {
+        type = types.str;
+        default = "192.168.122.0/24";
+        description = "NAT network subnet in CIDR notation";
+      };
+
+      dhcpStart = mkOption {
+        type = types.str;
+        default = "192.168.122.2";
+        description = "Start of the DHCP range";
+      };
+
+      dhcpEnd = mkOption {
+        type = types.str;
+        default = "192.168.122.254";
+        description = "End of the DHCP range";
+      };
     };
 
-    vmName = mkOption {
+    storagePool = mkOption {
       type = types.str;
-      default = "compose-test-vm";
-      description = "Name of the staging VM";
+      default = "/var/lib/libvirt/images";
+      description = "Directory path for the libvirt storage pool";
+    };
+
+    dataDir = mkOption {
+      type = types.str;
+      default = "/var/lib/staging-vm";
+      description = "Directory for staging VM test data (images, cloud-init configs)";
     };
 
     memory = mkOption {
-      type = types.str;
-      default = "4096";
-      description = "RAM allocated to the staging VM (MB)";
+      type = types.int;
+      default = 2048;
+      description = "Default RAM in MiB for staging VMs";
     };
 
     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)";
+      description = "Default number of vCPUs for staging VMs";
     };
   };
 
@@ -244,15 +280,23 @@ in
     # ── libvirtd with QEMU/KVM ──────────────────────────────────────────
     virtualisation.libvirtd = {
       enable = true;
+
       qemu = {
         package = pkgs.qemu_kvm;
         runAsRoot = true;
-        swtpm.enable = true;
+
+        swtpm = {
+          enable = true;
+        };
+
         ovmf = {
           enable = true;
           packages = [ pkgs.OVMF ];
         };
       };
+
+      # Allow the staging bridge for guest networking
+      allowedBridges = [ cfg.network.bridge ];
     };
 
     # ── System packages ─────────────────────────────────────────────────
@@ -261,9 +305,9 @@ in
       qemu_kvm               # QEMU/KVM
       swtpm                  # Software TPM
       OVMF                   # UEFI firmware for VMs
-      virt-manager           # GUI + virt-install
+      virt-manager           # GUI management
       virt-viewer            # SPICE/VNC viewer
-      libguestfs             # virt-customize, guestfish
+      libguestfs             # virt-install, virt-customize, guestfish
       cdrtools               # genisoimage for cloud-init ISOs
       jq                     # JSON parsing
       gawk                   # awk for DHCP lease parsing
@@ -275,85 +319,93 @@ in
 
     # ── Directories ─────────────────────────────────────────────────────
     systemd.tmpfiles.rules = [
-      "d ${cfg.storagePath} 0755 root root -"
-      "d ${cfg.dataPath} 0755 root root -"
+      "d ${cfg.storagePool} 0755 root root -"
+      "d ${cfg.dataDir} 0755 root root -"
     ];
 
-    # ── Default NAT network (192.168.122.0/24) ──────────────────────────
-    # Define the default libvirt NAT network using virsh postStart hook
-    systemd.services.libvirtd = {
-      postStart = ''
+    # ── Default NAT network definition ──────────────────────────────────
+    systemd.services.define-staging-network = {
+      description = "Define the staging libvirt NAT network";
+      after = [ "libvirtd.service" ];
+      requires = [ "libvirtd.service" ];
+      wantedBy = [ "multi-user.target" ];
+      before = [ "define-staging-pool.service" ];
+      serviceConfig = {
+        Type = "oneshot";
+        RemainAfterExit = true;
+      };
+      script = let
+        networkXml = pkgs.writeText "staging-network.xml" ''
+          <network>
+            <name>${cfg.network.name}</name>
+            <forward mode='nat'/>
+            <bridge name='${cfg.network.bridge}' stp='on' delay='0'/>
+            <ip address='${networkIp}' netmask='255.255.255.0'>
+              <dhcp>
+                <range start='${cfg.network.dhcpStart}' end='${cfg.network.dhcpEnd}'/>
+              </dhcp>
+            </ip>
+          </network>
+        '';
+      in ''
         set -e
-        # Define the NAT network if it doesn't exist
-        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-info default 2>/dev/null && {
-          echo "Network 'default' already exists"
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-info "${cfg.network.name}" 2>/dev/null && {
+          echo "Network '${cfg.network.name}' already exists"
         } || {
-          echo "Defining default NAT network (192.168.122.0/24)..."
-          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-define /etc/libvirt/qemu/networks/default.xml
+          echo "Defining network '${cfg.network.name}'..."
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-define "${networkXml}"
         }
-        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-autostart default 2>/dev/null || true
-        # Start the network if not active
-        STATE=$(${pkgs.libvirt}/bin/virsh -c qemu:///system net-state default 2>/dev/null || echo "inactive")
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-autostart "${cfg.network.name}"
+        # Start the network if not already active
+        STATE=$(${pkgs.libvirt}/bin/virsh -c qemu:///system net-state "${cfg.network.name}" 2>/dev/null || echo "inactive")
         if [ "$STATE" != "active" ]; then
-          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-start default 2>/dev/null || true
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-start "${cfg.network.name}"
         fi
-        echo "Default network ready."
+        echo "Network '${cfg.network.name}' is ready."
       '';
     };
 
-    # Define the default network as an XML config file
-    environment.etc."libvirt/qemu/networks/default.xml" = {
-      text = ''
-        <network>
-          <name>default</name>
-          <forward mode='nat'/>
-          <bridge name='virbr0' stp='on' delay='0'/>
-          <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>
+    # ── Storage pool definition ─────────────────────────────────────────
+    systemd.services.define-staging-pool = {
+      description = "Define the staging libvirt storage pool";
+      after = [ "libvirtd.service" "define-staging-network.service" ];
+      requires = [ "libvirtd.service" ];
+      wantedBy = [ "multi-user.target" ];
+      serviceConfig = {
+        Type = "oneshot";
+        RemainAfterExit = true;
+      };
+      script = ''
+        set -e
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-info staging 2>/dev/null && {
+          echo "Storage pool 'staging' already exists"
+        } || {
+          echo "Defining storage pool 'staging' at ${cfg.storagePool}..."
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-define-as \
+            --name staging --type dir --target "${cfg.storagePool}"
+        }
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-autostart staging
+        STATE=$(${pkgs.libvirt}/bin/virsh -c qemu:///system pool-state staging 2>/dev/null || echo "inactive")
+        if [ "$STATE" != "running" ]; then
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-build staging
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-start staging
+        fi
+        echo "Storage pool 'staging' is ready."
       '';
-      mode = "0644";
     };
 
-    # ── Storage pool ────────────────────────────────────────────────────
-    systemd.services.libvirtd.postStart = mkAfter ''
-      set -e
-      ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-info default 2>/dev/null && {
-        echo "Storage pool 'default' already exists"
-      } || {
-        echo "Defining storage pool at ${cfg.storagePath}..."
-        ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-define-as \
-          --name default --type dir --target "${cfg.storagePath}"
-      }
-      ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-autostart default 2>/dev/null || true
-      STATE=$(${pkgs.libvirt}/bin/virsh -c qemu:///system pool-state default 2>/dev/null || echo "inactive")
-      if [ "$STATE" != "running" ]; then
-        ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-build default 2>/dev/null || true
-        ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-start default 2>/dev/null || true
-      fi
-      echo "Storage pool ready."
-    '';
-
     # ── Firewall rules for libvirt guests ───────────────────────────────
     networking.firewall = {
-      trustedInterfaces = [ "virbr0" ];
+      # Trust the bridge interface to allow guest traffic
+      trustedInterfaces = [ cfg.network.bridge ];
 
       extraCommands = mkAfter ''
-        # Allow DHCP (port 67/68) and DNS (port 53) to libvirt guests
-        iptables -I INPUT -i virbr0 -p udp --dport 67:68 -j ACCEPT 2>/dev/null || true
-        iptables -I INPUT -i virbr0 -p tcp --dport 53 -j ACCEPT 2>/dev/null || true
-        iptables -I INPUT -i virbr0 -p udp --dport 53 -j ACCEPT 2>/dev/null || true
-
-        # Allow forwarding between the bridge and the outside world
-        iptables -I FORWARD -i virbr0 -o virbr0 -j ACCEPT 2>/dev/null || true
-        iptables -I FORWARD -o virbr0 -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT 2>/dev/null || true
-        iptables -I FORWARD -i virbr0 -j ACCEPT 2>/dev/null || true
+        # Allow forwarding between the staging bridge and the outside world
+        iptables -I FORWARD -i ${cfg.network.bridge} -j ACCEPT 2>/dev/null || true
+        iptables -I FORWARD -o ${cfg.network.bridge} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT 2>/dev/null || true
 
         # NAT for guest outbound traffic
-        iptables -t nat -I POSTROUTING -s 192.168.122.0/24 -j MASQUERADE 2>/dev/null || true
+        iptables -t nat -I POSTROUTING -s ${cfg.network.subnet} -j MASQUERADE 2>/dev/null || true
       '';
     };
 

tests/run-integration.sh

@@ -1,347 +0,0 @@
-#!/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

users/ai-worker.nix

@@ -4,7 +4,7 @@
     group = "ai-worker";
     home = "/home/ai-worker";
     createHome = true;
-    extraGroups = [ "docker" "libvirtd" ];
+    extraGroups = [ "docker" ];
     shell = pkgs.bashInteractive;
     openssh.authorizedKeys.keys = [
       keys.users.ai-worker.main