feat: enhance staging-vm module

Improved pr-test-vm script (virt-install, DHCP IP discovery), added packages (virt-manager, libguestfs, cdrtools, gawk, etc.), better firewall rules, storage pool auto-creation, gortium in libvirtd group, fixed OVMF package reference

modules/nixos/services/staging-vm.nix

@@ -4,6 +4,202 @@ with lib;
 
 let
   cfg = config.services.stagingVm;
+
+  # ── pr-test-vm helper script ──────────────────────────────────────────
+  pr-test-vm = pkgs.writeShellScriptBin "pr-test-vm" ''
+    set -euo pipefail
+
+    LIBVIRT_URI="qemu:///system"
+    VM_DIR="${cfg.dataPath}"
+    NETWORK="default"
+    SCRIPT_NAME="$(basename "$0")"
+
+    usage() {
+      cat <<EOF
+    Usage: $SCRIPT_NAME <command> [options]
+
+    Commands:
+      build   <nixos-config> [--name <name>]   Build VM image from a NixOS config
+      start   <vm-name>                         Start a VM
+      stop    <vm-name>                         Gracefully shut down a VM
+      destroy <vm-name>                         Force-power-off and undefine a VM
+      ssh     [user@]<vm-name>                  SSH into a running VM
+      console <vm-name>                         Connect to VM serial console
+      list                                      List all staging VMs
+      status  <vm-name>                         Show VM status
+
+    Examples:
+      $SCRIPT_NAME build ./vm-config.nix --name my-test
+      $SCRIPT_NAME start my-test
+      $SCRIPT_NAME ssh root@my-test
+    EOF
+      exit 1
+    }
+
+    # Find the VM's IP address from the DHCP lease
+    vm_ip() {
+      local name="$1"
+      local mac
+      mac=$(${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" domiflist "$name" 2>/dev/null \
+        | ${pkgs.gawk}/bin/awk 'NR>2 && $1 ~ /^vnet/ {print $NF; exit}')
+      [ -z "$mac" ] && { echo "error: cannot find MAC for VM '$name'"; exit 1; }
+
+      local ip
+      ip=$(${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" net-dhcp-leases "$NETWORK" 2>/dev/null \
+        | ${pkgs.gawk}/bin/awk -v mac="$mac" '$0 ~ mac {gsub(/-.*/, "", $3); print $3; exit}')
+      [ -z "$ip" ] && { echo "error: no DHCP lease found for VM '$name' (MAC: $mac)"; exit 1; }
+      echo "$ip"
+    }
+
+    case "''${1:-help}" in
+      build)
+        shift
+        CONFIG="''${1:?Missing NixOS config path}"
+        VM_NAME="''${2:-}"
+        [ -f "$CONFIG" ] || { echo "error: config file not found: $CONFIG"; exit 1; }
+
+        # Extract name from --name flag or config basename
+        if [ "''${2:-}" = "--name" ] && [ -n "''${3:-}" ]; then
+          VM_NAME="$3"
+        elif [ -z "$VM_NAME" ] || [ "''${VM_NAME#--}" != "$VM_NAME" ]; then
+          VM_NAME="$(basename "$CONFIG" .nix)"
+        fi
+
+        BUILD_DIR="$VM_DIR/$VM_NAME"
+        echo "==> Building VM '$VM_NAME' from config: $CONFIG"
+        mkdir -p "$BUILD_DIR"
+
+        # Build the NixOS VM derivation
+        nix build --no-link -f "$CONFIG" vm 2>&1 || {
+          echo "Trying flake build..."
+          nix build "''${CONFIG%/.nix}#nixosConfigurations.$VM_NAME.config.system.build.vm" --no-link 2>&1 || {
+            echo "error: failed to build VM (tried both import and flake)"
+            exit 1
+          }
+        }
+
+        echo "==> Build complete. Run 'pr-test-vm start $VM_NAME' to launch."
+        ;;
+
+      start)
+        VM_NAME="''${1:?Missing VM name}"
+        IMAGE="$VM_DIR/$VM_NAME/disk-image.qcow2"
+        [ -f "$IMAGE" ] || { echo "error: no disk image found at $IMAGE. Build first."; exit 1; }
+
+        # Check if already running
+        STATE=$(${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" domstate "$VM_NAME" 2>/dev/null || echo "undefined")
+        if [ "$STATE" = "running" ]; then
+          echo "VM '$VM_NAME' is already running."
+          exit 0
+        fi
+
+        echo "==> Starting VM '$VM_NAME'..."
+
+        # Undefine if defined but not running
+        if [ "$STATE" != "undefined" ]; then
+          ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" undefine "$VM_NAME" 2>/dev/null || true
+        fi
+
+        # Define and start with virt-install
+        ${pkgs.virt-manager}/bin/virt-install \
+          --connect "$LIBVIRT_URI" \
+          --name "$VM_NAME" \
+          --memory "${toString cfg.memory}" \
+          --vcpus "${toString cfg.vcpus}" \
+          --disk "$IMAGE",bus=virtio \
+          --import \
+          --network network="$NETWORK",model=virtio \
+          --graphics none \
+          --console pty,target_type=virtio \
+          --serial pty \
+          --memballoon virtio \
+          --rng /dev/urandom \
+          --noautoconsole \
+          --os-variant detect=on,name=generic
+
+        echo "==> VM '$VM_NAME' started. Get IP with: pr-test-vm status $VM_NAME"
+        ;;
+
+      stop)
+        VM_NAME="''${1:?Missing VM name}"
+        echo "==> Stoping VM '$VM_NAME'..."
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" shutdown "$VM_NAME" 2>/dev/null && {
+          echo "Waiting for VM to shut down..."
+          for i in $(seq 1 30); do
+            STATE=$(${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" domstate "$VM_NAME" 2>/dev/null || echo "undefined")
+            [ "$STATE" != "running" ] && { echo "VM stopped."; exit 0; }
+            sleep 2
+          done
+          echo "warning: VM did not shut down gracefully, use 'destroy' for force"
+        } || {
+          echo "VM '$VM_NAME' not running or does not exist."
+        }
+        ;;
+
+      destroy)
+        VM_NAME="''${1:?Missing VM name}"
+        echo "==> Destroying VM '$VM_NAME'..."
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" destroy "$VM_NAME" 2>/dev/null || true
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" undefine "$VM_NAME" 2>/dev/null || true
+        echo "==> VM '$VM_NAME' destroyed and undefined."
+        ;;
+
+      ssh)
+        TARGET="''${1:?Usage: $SCRIPT_NAME ssh [user@]<vm-name>}"
+        # Split user@hostname if present
+        if echo "$TARGET" | ${pkgs.gnugrep}/bin/grep -q '@'; then
+          USER="''${TARGET%@*}"
+          VM_NAME="''${TARGET#*@}"
+        else
+          VM_NAME="$TARGET"
+          USER=""
+        fi
+
+        IP=$(vm_ip "$VM_NAME") || exit 1
+        if [ -n "$USER" ]; then
+          exec ${pkgs.openssh}/bin/ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null "''${USER}@''${IP}"
+        else
+          exec ${pkgs.openssh}/bin/ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null "$IP"
+        fi
+        ;;
+
+      console)
+        VM_NAME="''${1:?Missing VM name}"
+        exec ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" console "$VM_NAME"
+        ;;
+
+      list)
+        echo "Staging VMs:"
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" list --all
+        echo ""
+        echo "Active networks:"
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" net-list
+        echo ""
+        echo "Storage pools:"
+        ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" pool-list
+        ;;
+
+      status)
+        VM_NAME="''${1:?Missing VM name}"
+        echo "VM: $VM_NAME"
+        STATE=$(${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" domstate "$VM_NAME" 2>/dev/null || echo "not found")
+        echo "State: $STATE"
+        if [ "$STATE" = "running" ]; then
+          IP=$(vm_ip "$VM_NAME" 2>/dev/null || echo "N/A")
+          echo "IP: $IP"
+          ${pkgs.libvirt}/bin/virsh -c "$LIBVIRT_URI" dommemstat "$VM_NAME" 2>/dev/null | head -3 || true
+        fi
+        ;;
+
+      help|--help|-h)
+        usage
+        ;;
+
+      *)
+        usage
+        ;;
+    esac
+  '';
 in
 {
   options.services.stagingVm = {
@@ -45,7 +241,7 @@ in
   };
 
   config = mkIf cfg.enable {
-    # Enable libvirt daemon
+    # ── libvirtd with QEMU/KVM ──────────────────────────────────────────
     virtualisation.libvirtd = {
       enable = true;
       qemu = {
@@ -54,26 +250,64 @@ in
         swtpm.enable = true;
         ovmf = {
           enable = true;
-          packages = [ pkgs.OVMFFull.fd ];
+          packages = [ pkgs.OVMF ];
         };
       };
     };
 
-    # Kernel modules + groups already handled in configuration.nix
+    # ── System packages ─────────────────────────────────────────────────
+    environment.systemPackages = with pkgs; [
+      libvirt                # virsh, virt-admin
+      qemu_kvm               # QEMU/KVM
+      swtpm                  # Software TPM
+      OVMF                   # UEFI firmware for VMs
+      virt-manager           # GUI + virt-install
+      virt-viewer            # SPICE/VNC viewer
+      libguestfs             # virt-customize, guestfish
+      cdrtools               # genisoimage for cloud-init ISOs
+      jq                     # JSON parsing
+      gawk                   # awk for DHCP lease parsing
+      gnugrep                # grep
+    ];
 
-    # libvirt NAT network (192.168.122.0/24)
+    # ── User permissions ────────────────────────────────────────────────
+    users.users.gortium.extraGroups = [ "libvirtd" ];
+
+    # ── Directories ─────────────────────────────────────────────────────
+    systemd.tmpfiles.rules = [
+      "d ${cfg.storagePath} 0755 root root -"
+      "d ${cfg.dataPath} 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 = ''
+        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"
+        } || {
+          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
+        }
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-autostart default 2>/dev/null || true
+        # Start the network if not active
+        STATE=$(${pkgs.libvirt}/bin/virsh -c qemu:///system net-state default 2>/dev/null || echo "inactive")
+        if [ "$STATE" != "active" ]; then
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-start default 2>/dev/null || true
+        fi
+        echo "Default network ready."
+      '';
+    };
+
+    # Define the default network as an XML config file
     environment.etc."libvirt/qemu/networks/default.xml" = {
       text = ''
         <network>
           <name>default</name>
-          <uuid>2b8f7a3c-9e5d-4a1f-bc3d-6e7a8f9b0c1d</uuid>
+          <forward mode='nat'/>
-          <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'/>
@@ -81,195 +315,49 @@ in
           </ip>
         </network>
       '';
-      # Autostart the network so it comes up on boot
       mode = "0644";
     };
 
-    # Ensure the default network is defined and autostarted
+    # ── Storage pool ────────────────────────────────────────────────────
-    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
+      set -e
-      ${pkgs.libvirt}/bin/virsh pool-autostart default 2>/dev/null || true
+      ${pkgs.libvirt}/bin/virsh -c qemu:///system pool-info default 2>/dev/null && {
-      ${pkgs.libvirt}/bin/virsh pool-start default 2>/dev/null || true
+        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: allow traffic from virbr0 to host and outbound NAT
+    # ── Firewall rules for libvirt guests ───────────────────────────────
     networking.firewall = {
-      extraCommands = ''
+      trustedInterfaces = [ "virbr0" ];
-        # Allow inbound DHCP/DNS from libvirt guests
+
-        iptables -I INPUT -i virbr0 -p udp --dport 67:68 -j ACCEPT
+      extraCommands = mkAfter ''
-        iptables -I INPUT -i virbr0 -p tcp --dport 53 -j ACCEPT
+        # Allow DHCP (port 67/68) and DNS (port 53) to libvirt guests
-        iptables -I INPUT -i virbr0 -p udp --dport 53 -j ACCEPT
+        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
-        # Allow established/related traffic back to guests
+        iptables -I INPUT -i virbr0 -p udp --dport 53 -j ACCEPT 2>/dev/null || true
-        iptables -I FORWARD -i virbr0 -o virbr0 -j ACCEPT
+
-        iptables -I FORWARD -o virbr0 -j ACCEPT
+        # Allow forwarding between the bridge and the outside world
-        iptables -I FORWARD -i virbr0 -j ACCEPT
+        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
+
+        # NAT for guest outbound traffic
+        iptables -t nat -I POSTROUTING -s 192.168.122.0/24 -j MASQUERADE 2>/dev/null || true
       '';
     };
 
-    # Packages needed for VM management
+    # ── pr-test-vm helper script ────────────────────────────────────────
-    environment.systemPackages = with pkgs; [
+    environment.systemPackages = [ pr-test-vm ];
-      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
-    '') ];
   };
 }