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

@@ -0,0 +1,64 @@
+name: NixOS Build & Test
+run-name: Build ${{ gitea.event_name == 'push' && gitea.ref_name || format('PR #{0}', gitea.event.pull_request.number) }}
+
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - '**.nix'
+      - 'flake.lock'
+      - 'secrets/**'
+      - 'hosts/**'
+      - 'modules/**'
+  pull_request:
+    branches:
+      - master
+    paths:
+      - '**.nix'
+      - 'flake.lock'
+      - 'secrets/**'
+      - 'hosts/**'
+      - 'modules/**'
+
+jobs:
+  build:
+    runs-on: nixos-builder
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Nix environment
+        run: |
+          echo "extra-experimental-features = nix-command flakes" >> ~/.config/nix/nix.conf
+          cat ~/.config/nix/nix.conf
+
+      - name: Install nh (nix helper)
+        run: |
+          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 "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"

assets/ollama/Dockerfile

@@ -0,0 +1,106 @@
+# ollama-gfx906/Dockerfile
+#
+# Custom ollama image with ROCm 6.1 + gfx906 (MI50) support.
+# The official ollama/rocm image ships ROCm 7.2 which dropped gfx906.
+# This uses v0.23.2's native CMake build system with AMDGPU_TARGETS including gfx906.
+#
+# Build: docker build -t ollama/ollama:rocm-gfx906 ai/ollama
+
+FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder
+
+# Build dependencies (CMake, Ninja, Go)
+ARG CMAKEVERSION=3.31.2
+ARG NINJAVERSION=1.12.1
+ARG GOLANG_VERSION=1.22.0
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
+    curl git ccache build-essential pkg-config unzip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install CMake from official binaries
+RUN curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-x86_64.tar.gz \
+    | tar xz -C /usr/local --strip-components 1
+
+# Install Ninja
+RUN curl -fsSL -o /tmp/ninja.zip \
+    https://github.com/ninja-build/ninja/releases/download/v${NINJAVERSION}/ninja-linux.zip \
+    && unzip /tmp/ninja.zip -d /usr/local/bin && rm /tmp/ninja.zip
+
+# Install Go
+RUN curl -fsSL https://go.dev/dl/go${GOLANG_VERSION}.linux-amd64.tar.gz \
+    | tar xz -C /usr/local
+ENV PATH=/usr/local/go/bin:$PATH
+
+ARG OLLAMA_VERSION=v0.23.2
+RUN git clone --depth 1 --branch ${OLLAMA_VERSION} https://github.com/ollama/ollama.git /build
+WORKDIR /build
+
+# ROCm paths
+ENV HIP_PATH=/opt/rocm
+ENV ROCM_PATH=/opt/rocm
+ENV CMAKE_GENERATOR=Ninja
+ENV LDFLAGS=-s
+
+# Step 1: Build CPU backends with GCC (no ROCm preset)
+# Pre-set CMAKE_HIP_COMPILER="" to prevent check_language(HIP) from
+# finding a HIP compiler (it searches /opt/rocm even without PATH).
+# Remove /opt/rocm from PATH to prevent find_program from finding hipcc.
+RUN mkdir -p build-cpu && \
+    PATH=/usr/local/go/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
+    cmake -B build-cpu -DCMAKE_BUILD_TYPE=Release \
+      -DCMAKE_HIP_COMPILER="" \
+      -DCMAKE_INSTALL_PREFIX=/build/dist && \
+    cmake --build build-cpu --target ggml-cpu -- -l $(nproc) && \
+    cmake --install build-cpu --component CPU --strip && \
+    echo "=== CPU install ===" && \
+    (find /build/dist/lib/ollama -type f -o -type l 2>&1 | head -20 || echo "empty")
+
+# Step 2: Build HIP backend with ROCm preset + gfx906 target only
+# The ROCm 6 preset enables HIP language detection (enable_language(HIP))
+# which ensures GPU kernels are properly compiled for gfx906.
+# OLLAMA_RUNNER_DIR=rocm from the preset, so HIP goes to lib/ollama/rocm/
+# Need CMAKE_PREFIX_PATH so find_package(hip) finds hip-config.cmake
+# at /opt/rocm/lib/cmake/hip/hip-config.cmake.
+RUN mkdir -p build-hip && \
+    cmake -B build-hip \
+      --preset 'ROCm 6' \
+      -DAMDGPU_TARGETS="gfx906:xnack-" \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DCMAKE_PREFIX_PATH="/opt/rocm" && \
+    cmake --build build-hip --target ggml-hip -- -l $(nproc) && \
+    cmake --install build-hip --component HIP --strip && \
+    echo "=== HIP install ===" && \
+    find /build/dist/lib/ollama -type f -o -type l | head -20
+
+# Step 3: Build Go binary (GCC for CGo linking)
+ENV CGO_ENABLED=1
+RUN go build -trimpath -ldflags="-X=github.com/ollama/ollama/version.Version=${OLLAMA_VERSION}" -o /build/dist/ollama .
+
+# ---------- Runtime image ----------
+FROM ubuntu:24.04
+
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
+    ca-certificates curl libstdc++6 libgomp1 libvulkan1 libopenblas0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy ROCm 6.1 runtime libraries
+# These are needed at runtime by ggml-hip via LD_LIBRARY_PATH
+COPY --from=builder /opt/rocm/lib/ /opt/rocm/lib/
+COPY --from=builder /opt/rocm/share/ /opt/rocm/share/
+
+# Copy ollama binary + all backends (CPU + HIP)
+# CPU install:  /build/dist/lib/ollama/libggml-*.so
+# HIP install:  /build/dist/lib/ollama/rocm/libggml-hip.so
+COPY --from=builder /build/dist/ollama /usr/bin/ollama
+COPY --from=builder /build/dist/lib/ollama/ /usr/lib/ollama/
+
+RUN ldconfig
+
+ENV LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama/rocm:/usr/lib/ollama
+ENV HSA_OVERRIDE_GFX_VERSION=9.0.6
+ENV HCC_AMDGPU_TARGET=gfx906
+ENV HSA_ENABLE_SDMA=0
+
+EXPOSE 11434
+ENTRYPOINT ["/bin/ollama"]
+CMD ["serve"]

flake.nix

@@ -59,8 +59,10 @@
               ./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/security/ai-worker-restricted.nix
               ./users/gortium.nix
               ./users/ai-worker.nix
             ];

hosts/lazyworkhorse/configuration.nix

@@ -207,6 +207,7 @@
     ai = {
       path = self + "/assets/compose/ai";
       envFile = config.age.secrets.containers_env.path;
+      ports = [ 22000 ];  # Syncthing TCP sync
     };
 
     cloudstorage = {
@@ -474,7 +475,7 @@
   services.openssh.settings = {
     PermitRootLogin = "no";
     MaxAuthTries = 3;
-    MaxSessions = 10;
+    MaxSessions = 20;
     LoginGraceTime = 30;
     ClientAliveInterval = 300;
     ClientAliveCountMax = 2;

modules/nixos/security/README-ai-worker.md

@@ -0,0 +1,105 @@
+# AI Worker Restricted Access
+
+This module provides SSH access for the AI worker (hermes-agent) to run ollama benchmarks on the host.
+
+## Security Model
+
+The `ai-worker` user has:
+
+### Filesystem Access
+- **Home directory**: `/home/ai-worker` (standard user home)
+- **No bind mounts**: Cannot access `/home/gortium/infra` or other host files
+- **Cannot access**: Any files outside standard system paths
+
+### Sudo Access
+- **NONE**: ai-worker has no sudo privileges
+- Cannot run `nh`, `nixos-rebuild`, `nixpkgs-fmt`, or `nix` with elevated permissions
+
+### Docker Access
+- Member of `docker` group - can run `docker` and `docker exec` commands
+- Primary use: `docker exec ollama ollama ...` for benchmarking
+- Can run `docker exec --privileged ollama rocm-smi ...` for VRAM monitoring
+
+## Workflow: SSH + Docker Benchmarking
+
+The AI worker connects from the Hermes container to the host via SSH, runs ollama benchmarks, then returns to save results.
+
+### Example Workflow
+
+```bash
+# From Hermes container, SSH to host
+ssh -i /path/to/ssh/key ai-worker@host.docker.internal
+
+# On host, run ollama benchmarks via docker
+docker exec ollama ollama pull devstral-small-2:24b
+
+# Create test modelfile
+docker exec ollama bash -c 'cat <<EOF > /root/.ollama/test.modelfile
+FROM devstral-small-2:24b
+PARAMETER num_ctx 65536
+PARAMETER num_gpu 99
+PARAMETER flash_attn true
+EOF'
+
+# Create and test model
+docker exec ollama ollama create test-model -f /root/.ollama/test.modelfile
+docker exec ollama ollama run test-model "Write a Python async function"
+
+# Check VRAM usage
+docker exec --privileged ollama rocm-smi --showmeminfo vram
+
+# Cleanup
+docker exec ollama ollama rm test-model
+
+# Exit SSH, return to Hermes container
+exit
+
+# Save results in Hermes container
+# /opt/data/ai-optimizer/state.json
+# /opt/data/ai-optimizer/results.csv
+```
+
+## SSH Access
+
+Connect as:
+```bash
+ssh ai-worker@lazyworkhorse
+```
+
+The working directory will be `/home/ai-worker`. No infra repo access.
+
+## Verification
+
+Check ai-worker permissions:
+```bash
+# On the host, as root or gortium:
+sudo -u ai-worker sudo -l
+# Should show: no sudo access
+
+# Check docker group membership
+groups ai-worker
+# Should show: ai-worker docker
+```
+
+## Troubleshooting
+
+If ai-worker cannot run docker commands:
+```bash
+# Check docker group membership
+groups ai-worker
+
+# Verify ollama container is running
+docker ps | grep ollama
+
+# Test docker access
+sudo -u ai-worker docker exec ollama ollama list
+```
+
+If SSH connection fails:
+```bash
+# Check SSH key is authorized
+cat /home/ai-worker/.ssh/authorized_keys
+
+# Check SSH service
+systemctl status sshd
+```

modules/nixos/security/ai-worker-restricted.nix

@@ -0,0 +1,17 @@
+{ config, pkgs, lib, ... }:
+
+with lib;
+
+{
+  options.services.aiWorkerAccess = mkOption {
+    type = types.bool;
+    default = false;
+    description = "Enable AI worker SSH access with docker group membership for ollama benchmarking";
+  };
+
+  config = mkIf config.services.aiWorkerAccess {
+    # ai-worker is member of docker group - can run docker commands via SSH
+    # No bind mounts, no sudo access - docker-only for ollama benchmarking
+    users.groups.docker.members = [ "ai-worker" ];
+  };
+}

modules/nixos/services/ollama_init_custom_models.nix

@@ -1,67 +1,87 @@
 { pkgs, ... }: {
   systemd.services.init-ollama-model = {
     description = "Initialize LLM models with extra context in Ollama Docker";
-    after = [ "docker-ollama.service" ];
+    
+    # On s'assure que Docker tourne avant de lancer ce script
+    after = [ "docker.service" ];
     wantedBy = [ "multi-user.target" ];
+    
     script = ''
-      # Wait for Ollama
+      # Fonction de création asynchrone pour ne pas bloquer le démarrage
-      while ! ${pkgs.curl}/bin/curl -s http://localhost:11434/api/tags > /dev/null; do
+      (
-        sleep 2
+        echo "Starting asynchronous Ollama initialization..."
-      done
+        
+        # Attente d'Ollama (maximum 120 secondes pour éviter une boucle infinie)
+        TIMEOUT=60
+        COUNT=0
+        while ! ${pkgs.curl}/bin/curl -s -f http://127.0.0.1:11434/api/tags > /dev/null; do
+          if [ $COUNT -ge $TIMEOUT ]; then
+            echo "Ollama did not become ready in time. Exiting."
+            exit 1
+          fi
+          echo "Waiting for Ollama API to be reachable..."
+          sleep 5
+          COUNT=$((COUNT + 5))
+        done
 
-      create_model_if_missing() {
+        create_model_if_missing() {
-        local model_name=$1
+          local model_name=$1
-        local base_model=$2
+          local base_model=$2
-        if ! ${pkgs.docker}/bin/docker exec ollama ollama list | grep -q "$model_name"; then
-          echo "$model_name not found, creating from $base_model..."
           
-          # We use a custom TEMPLATE block to strip the 'currentDate' function 
+          # Vérification robuste via l'API HTTP d'Ollama plutôt que docker exec (évite les conflits de tty)
-          # which is unsupported in Ollama 0.5.7 but present in Devstral's default manifest.
+          if ! ${pkgs.curl}/bin/curl -s http://127.0.0.1:11434/api/tags | ${pkgs.jq}/bin/jq -e ".models[] | select(.name == \"$model_name\")" > /dev/null; then
-          ${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
+            echo "$model_name not found, creating from $base_model..."
+            
+            # Utilisation d'un fichier temporaire sur l'hôte pour l'injecter proprement dans Docker
+            TMP_FILE=$(mktemp)
+            cat <<EOF > "$TMP_FILE"
 FROM $base_model
-TEMPLATE \"\"\"{{- if .System }}
+TEMPLATE """{{- if .System }}
 [SYSTEM_PROMPT]
 {{ .System }}
 [/SYSTEM_PROMPT]
 {{- end }}
 {{- range .Messages }}
-{{- if eq .Role \"user\" }}
+{{- if eq .Role "user" }}
 [INST]
 {{ .Content }}
 [/INST]
-{{- else if eq .Role \"assistant\" }}
+{{- else if eq .Role "assistant" }}
 {{ .Content }}
 {{- end }}
-{{- end }}\"\"\"
+{{- end }}"""
 PARAMETER num_ctx 131072
 PARAMETER num_predict 4096
 PARAMETER num_keep 1024
 PARAMETER repeat_penalty 1.1
 PARAMETER top_k 40
-PARAMETER stop \"[INST]\"
+PARAMETER stop "[INST]"
-PARAMETER stop \"[/INST]\"
+PARAMETER stop "[/INST]"
-PARAMETER stop \"</s>\"
+PARAMETER stop "</s>"
-EOF"
+EOF
-          ${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f "/root/.ollama/$model_name.modelfile"
-          ${pkgs.docker}/bin/docker exec ollama rm "/root/.ollama/$model_name.modelfile"
-        else
-          echo "$model_name already exists, skipping."
-        fi
-      }
 
-      # Create Nemotron
+            # Copie et création dans le conteneur
-      create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
+            ${pkgs.docker}/bin/docker cp "$TMP_FILE" ollama:/tmp/model.modelfile
-      
+            ${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f /tmp/model.modelfile
-      # Create Devstral
+            ${pkgs.docker}/bin/docker exec ollama rm /tmp/model.modelfile
-      create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b" 
+            rm -f "$TMP_FILE"
-      
+          else
-      # create_model_if_missing "qwen2.5-coder:32b-128k" "qwen2.5-coder:32b"
+            echo "$model_name already exists, skipping."
-      
+          fi
-      # create_model_if_missing "mistral-large-planner:123b" "mistral-large:123b-instruct-v2407-q4_K_S"
+        }
+
+        # Create Nemotron
+        create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
+        
+        # Create Devstral
+        create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b" 
+        
+      ) &
     '';
+
     serviceConfig = {
-      Type = "oneshot";
+      Type = "forking"; # Permet à systemd de savoir que le script passe en arrière-plan via '&'
-      RemainAfterExit = true;
+      User = "root";
     };
   };
 }

modules/nixos/services/staging-vm.nix

@@ -0,0 +1,415 @@
+{ config, lib, pkgs, ... }:
+
+with lib;
+
+let
+  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"
+    STORAGE_POOL="${cfg.storagePool}"
+    VM_DIR="${cfg.dataDir}"
+    NETWORK="${cfg.network.name}"
+    SCRIPT_NAME="$(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
+      rebuild <vm-name>                         Redeploy the VM (stop + start)
+
+    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"
+        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)"
+            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 "$VM_NAME" 2>/dev/null | head -3 || true
+        fi
+        ;;
+
+      rebuild)
+        VM_NAME="''${1:?Missing VM name}"
+        "$0" destroy "$VM_NAME"
+        "$0" start "$VM_NAME"
+        ;;
+
+      help|--help|-h)
+        usage
+        ;;
+
+      *)
+        usage
+        ;;
+    esac
+  '';
+in
+{
+  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";
+      };
+    };
+
+    storagePool = mkOption {
+      type = types.str;
+      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.int;
+      default = 2048;
+      description = "Default RAM in MiB for staging VMs";
+    };
+
+    vcpus = mkOption {
+      type = types.int;
+      default = 2;
+      description = "Default number of vCPUs for staging VMs";
+    };
+  };
+
+  config = mkIf cfg.enable {
+    # ── libvirtd with QEMU/KVM ──────────────────────────────────────────
+    virtualisation.libvirtd = {
+      enable = true;
+
+      qemu = {
+        package = pkgs.qemu_kvm;
+        runAsRoot = true;
+
+        swtpm = {
+          enable = true;
+        };
+
+        ovmf = {
+          enable = true;
+          packages = [ pkgs.OVMF ];
+        };
+      };
+
+      # Allow the staging bridge for guest networking
+      allowedBridges = [ cfg.network.bridge ];
+    };
+
+    # ── 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 management
+      virt-viewer            # SPICE/VNC viewer
+      libguestfs             # virt-install, virt-customize, guestfish
+      cdrtools               # genisoimage for cloud-init ISOs
+      jq                     # JSON parsing
+      gawk                   # awk for DHCP lease parsing
+      gnugrep                # grep
+    ];
+
+    # ── User permissions ────────────────────────────────────────────────
+    users.users.gortium.extraGroups = [ "libvirtd" ];
+
+    # ── Directories ─────────────────────────────────────────────────────
+    systemd.tmpfiles.rules = [
+      "d ${cfg.storagePool} 0755 root root -"
+      "d ${cfg.dataDir} 0755 root root -"
+    ];
+
+    # ── Default NAT network definition ──────────────────────────────────
+    systemd.services.define-staging-network = {
+      description = "Define the staging libvirt NAT network";
+      after = [ "libvirtd.service" ];
+      requires = [ "libvirtd.service" ];
+      wantedBy = [ "multi-user.target" ];
+      before = [ "define-staging-pool.service" ];
+      serviceConfig = {
+        Type = "oneshot";
+        RemainAfterExit = true;
+      };
+      script = let
+        networkXml = pkgs.writeText "staging-network.xml" ''
+          <network>
+            <name>${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
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-info "${cfg.network.name}" 2>/dev/null && {
+          echo "Network '${cfg.network.name}' already exists"
+        } || {
+          echo "Defining network '${cfg.network.name}'..."
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-define "${networkXml}"
+        }
+        ${pkgs.libvirt}/bin/virsh -c qemu:///system net-autostart "${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
+          ${pkgs.libvirt}/bin/virsh -c qemu:///system net-start "${cfg.network.name}"
+        fi
+        echo "Network '${cfg.network.name}' is ready."
+      '';
+    };
+
+    # ── 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."
+      '';
+    };
+
+    # ── Firewall rules for libvirt guests ───────────────────────────────
+    networking.firewall = {
+      # Trust the bridge interface to allow guest traffic
+      trustedInterfaces = [ cfg.network.bridge ];
+
+      extraCommands = mkAfter ''
+        # 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 ${cfg.network.subnet} -j MASQUERADE 2>/dev/null || true
+      '';
+    };
+
+    # ── pr-test-vm helper script ────────────────────────────────────────
+    environment.systemPackages = [ pr-test-vm ];
+  };
+}

secrets/wireguard_preshared_key.age

@@ -0,0 +1,9 @@
+-----BEGIN AGE ENCRYPTED FILE-----
+YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSA3VG9Z
+MVFPVFc2VVJ3d0h0dmtBUnI3WHl2SzUxTkRZbjFCaGloWmV3dnd3ClcxdnVPeGd6
+SU4zR0Q0K1dtVjRRVHd0VW5XSFI0dVFpTjZnYk1DNjRxTVEKLT4gQzlgRy1ncmVh
+c2UKeUozOWgyUytSTVF0NjY2STBEb2VadwotLS0gblI3bmJCUWxxU3QrYTEyVFBI
+Snc4NC9rTkh0NnZYbUtxUE9hRWRkelpmMAq58fmH6cK13GeD7wGLxKmx10hmJeW4
+b7KqnCD1ZP7uG85s32xzVRwRG8RrG4xZo5nR9Mrtg1CoTSFfUGeFnf5xveN+Ej0X
+wDVB1LwC+Q==
+-----END AGE ENCRYPTED FILE-----

secrets/wireguard_private_key.age

@@ -0,0 +1,11 @@
+-----BEGIN AGE ENCRYPTED FILE-----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+-----END AGE ENCRYPTED FILE-----

users/ai-worker.nix

@@ -9,8 +9,20 @@
     openssh.authorizedKeys.keys = [
       keys.users.ai-worker.main
     ];
+    # No password login - SSH key only
+    hashedPassword = "!";
   };
   users.groups.ai-worker = {};
+
+  # Enable restricted AI worker SSH access for ollama benchmarking
+  # SECURITY: ai-worker can only:
+  #   - SSH into host from Hermes container
+  #   - Run docker commands (docker exec ollama ...) via docker group
+  #   - Run specific security audit commands
+  #   - NO access to infra repo (no bind mount)
+  #   - NO sudo access (no nh, nixos-rebuild, nixpkgs-fmt, nix)
+  # WORKFLOW: SSH from Hermes container, run docker benchmarks, return and save results to /opt/data/ai-optimizer/
+  services.aiWorkerAccess = true;
   
   # Restricted sudo for ai-worker - security checks only
   security.sudo.extraRules = [