CLAUDE.md: prefer nix develop -c for devshell commands

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

CLAUDE.md

@@ -61,10 +61,21 @@ Do not run `nix flake update`. Should only be done manually by user.
 ### Development Environment
 
 ```bash
-# Enter development shell (provides ansible, python3)
+# Enter development shell
 nix develop
 ```
 
+The devshell provides: `ansible`, `tofu` (OpenTofu), `vault` (OpenBao CLI), `create-host`, and `homelab-deploy`.
+
+**Important:** When suggesting commands that use devshell tools, always use `nix develop -c <command>` syntax rather than assuming the user is already in a devshell. For example:
+```bash
+# Good - works regardless of current shell
+nix develop -c tofu plan
+
+# Avoid - requires user to be in devshell
+tofu plan
+```
+
 ### Secrets Management
 
 Secrets are managed by OpenBao (Vault) using AppRole authentication. Most hosts use the

flake.lock

@@ -28,11 +28,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1770447502,
-        "narHash": "sha256-xH1PNyE3ydj4udhe1IpK8VQxBPZETGLuORZdSWYRmSU=",
+        "lastModified": 1770470613,
+        "narHash": "sha256-FOqOBdsQnLzA7+Y3hXuN9PcOHmpEDvNw64Ju8op9J2w=",
         "ref": "master",
-        "rev": "79db119d1ca6630023947ef0a65896cc3307c2ff",
-        "revCount": 22,
+        "rev": "36a74b8cf9a873202e28eecfb90f9af8650cca8b",
+        "revCount": 23,
         "type": "git",
         "url": "https://git.t-juice.club/torjus/homelab-deploy"
       },

flake.nix

@@ -186,15 +186,6 @@
             ./hosts/nats1
           ];
         };
-        testvm01 = nixpkgs.lib.nixosSystem {
-          inherit system;
-          specialArgs = {
-            inherit inputs self sops-nix;
-          };
-          modules = commonModules ++ [
-            ./hosts/testvm01
-          ];
-        };
         vault01 = nixpkgs.lib.nixosSystem {
           inherit system;
           specialArgs = {
@@ -204,13 +195,31 @@
             ./hosts/vault01
           ];
         };
-        vaulttest01 = nixpkgs.lib.nixosSystem {
+        testvm01 = nixpkgs.lib.nixosSystem {
           inherit system;
           specialArgs = {
             inherit inputs self sops-nix;
           };
           modules = commonModules ++ [
-            ./hosts/vaulttest01
+            ./hosts/testvm01
+          ];
+        };
+        testvm02 = nixpkgs.lib.nixosSystem {
+          inherit system;
+          specialArgs = {
+            inherit inputs self sops-nix;
+          };
+          modules = commonModules ++ [
+            ./hosts/testvm02
+          ];
+        };
+        testvm03 = nixpkgs.lib.nixosSystem {
+          inherit system;
+          specialArgs = {
+            inherit inputs self sops-nix;
+          };
+          modules = commonModules ++ [
+            ./hosts/testvm03
           ];
         };
       };

hosts/template2/bootstrap.nix

@@ -6,22 +6,72 @@ let
     text = ''
       set -euo pipefail
 
+      LOKI_URL="http://monitoring01.home.2rjus.net:3100/loki/api/v1/push"
+
+      # Send a log entry to Loki with bootstrap status
+      # Usage: log_to_loki <stage> <message>
+      # Fails silently if Loki is unreachable
+      log_to_loki() {
+        local stage="$1"
+        local message="$2"
+        local timestamp_ns
+        timestamp_ns="$(date +%s)000000000"
+
+        local payload
+        payload=$(jq -n \
+          --arg host "$HOSTNAME" \
+          --arg stage "$stage" \
+          --arg branch "''${BRANCH:-master}" \
+          --arg ts "$timestamp_ns" \
+          --arg msg "$message" \
+          '{
+            streams: [{
+              stream: {
+                job: "bootstrap",
+                host: $host,
+                stage: $stage,
+                branch: $branch
+              },
+              values: [[$ts, $msg]]
+            }]
+          }')
+
+        curl -s --connect-timeout 2 --max-time 5 \
+          -X POST \
+          -H "Content-Type: application/json" \
+          -d "$payload" \
+          "$LOKI_URL" >/dev/null 2>&1 || true
+      }
+
+      echo "================================================================================"
+      echo "                     NIXOS BOOTSTRAP IN PROGRESS"
+      echo "================================================================================"
+      echo ""
+
       # Read hostname set by cloud-init (from Terraform VM name via user-data)
       # Cloud-init sets the system hostname from user-data.txt, so we read it from hostnamectl
       HOSTNAME=$(hostnamectl hostname)
-      echo "DEBUG: Hostname from hostnamectl: '$HOSTNAME'"
+      # Read git branch from environment, default to master
+      BRANCH="''${NIXOS_FLAKE_BRANCH:-master}"
 
+      echo "Hostname: $HOSTNAME"
+      echo ""
       echo "Starting NixOS bootstrap for host: $HOSTNAME"
+
+      log_to_loki "starting" "Bootstrap starting for $HOSTNAME (branch: $BRANCH)"
+
       echo "Waiting for network connectivity..."
 
       # Verify we can reach the git server via HTTPS (doesn't respond to ping)
       if ! curl -s --connect-timeout 5 --max-time 10 https://git.t-juice.club >/dev/null 2>&1; then
         echo "ERROR: Cannot reach git.t-juice.club via HTTPS"
         echo "Check network configuration and DNS settings"
+        log_to_loki "failed" "Network check failed - cannot reach git.t-juice.club"
         exit 1
       fi
 
       echo "Network connectivity confirmed"
+      log_to_loki "network_ok" "Network connectivity confirmed"
 
       # Unwrap Vault token and store AppRole credentials (if provided)
       if [ -n "''${VAULT_WRAPPED_TOKEN:-}" ]; then
@@ -50,6 +100,7 @@ let
           chmod 600 /var/lib/vault/approle/secret-id
 
           echo "Vault credentials unwrapped and stored successfully"
+          log_to_loki "vault_ok" "Vault credentials unwrapped and stored"
         else
           echo "WARNING: Failed to unwrap Vault token"
           if [ -n "$UNWRAP_RESPONSE" ]; then
@@ -63,17 +114,17 @@ let
           echo "To regenerate token, run: create-host --hostname $HOSTNAME --force"
           echo ""
           echo "Vault secrets will not be available, but continuing bootstrap..."
+          log_to_loki "vault_warn" "Failed to unwrap Vault token - continuing without secrets"
         fi
       else
         echo "No Vault wrapped token provided (VAULT_WRAPPED_TOKEN not set)"
         echo "Skipping Vault credential setup"
+        log_to_loki "vault_skip" "No Vault token provided - skipping credential setup"
       fi
 
       echo "Fetching and building NixOS configuration from flake..."
-
-      # Read git branch from environment, default to master
-      BRANCH="''${NIXOS_FLAKE_BRANCH:-master}"
       echo "Using git branch: $BRANCH"
+      log_to_loki "building" "Starting nixos-rebuild boot"
 
       # Build and activate the host-specific configuration
       FLAKE_URL="git+https://git.t-juice.club/torjus/nixos-servers.git?ref=$BRANCH#''${HOSTNAME}"
@@ -81,18 +132,30 @@ let
       if nixos-rebuild boot --flake "$FLAKE_URL"; then
         echo "Successfully built configuration for $HOSTNAME"
         echo "Rebooting into new configuration..."
+        log_to_loki "success" "Build successful - rebooting into new configuration"
         sleep 2
         systemctl reboot
       else
         echo "ERROR: nixos-rebuild failed for $HOSTNAME"
         echo "Check that flake has configuration for this hostname"
         echo "Manual intervention required - system will not reboot"
+        log_to_loki "failed" "nixos-rebuild failed - manual intervention required"
         exit 1
       fi
     '';
   };
 in
 {
+  # Custom greeting line to indicate this is a bootstrap image
+  services.getty.greetingLine = lib.mkForce ''
+    ================================================================================
+                          BOOTSTRAP IMAGE - NixOS \V (\l)
+    ================================================================================
+
+    Bootstrap service is running. Logs are displayed on tty1.
+    Check status: journalctl -fu nixos-bootstrap
+  '';
+
   systemd.services."nixos-bootstrap" = {
     description = "Bootstrap NixOS configuration from flake on first boot";
 
@@ -107,12 +170,12 @@ in
     serviceConfig = {
       Type = "oneshot";
       RemainAfterExit = true;
-      ExecStart = "${bootstrap-script}/bin/nixos-bootstrap";
+      ExecStart = lib.getExe bootstrap-script;
 
       # Read environment variables from cloud-init (set by cloud-init write_files)
       EnvironmentFile = "-/run/cloud-init-env";
 
-      # Logging to journald
+      # Log to journal and console
       StandardOutput = "journal+console";
       StandardError = "journal+console";
     };

hosts/testvm01/configuration.nix

@@ -13,14 +13,17 @@
     ../../common/vm
   ];
 
-  # Test VM - exclude from DNS zone generation
-  homelab.dns.enable = false;
-
+  # Host metadata (adjust as needed)
   homelab.host = {
-    tier = "test";
-    priority = "low";
+    tier = "test";  # Start in test tier, move to prod after validation
   };
 
+  # Enable Vault integration
+  vault.enable = true;
+
+  # Enable remote deployment via NATS
+  homelab.deploy.enable = true;
+
   nixpkgs.config.allowUnfree = true;
   boot.loader.grub.enable = true;
   boot.loader.grub.device = "/dev/vda";
@@ -29,7 +32,7 @@
   networking.domain = "home.2rjus.net";
   networking.useNetworkd = true;
   networking.useDHCP = false;
-  services.resolved.enable = false;
+  services.resolved.enable = true;
   networking.nameservers = [
     "10.69.13.5"
     "10.69.13.6"
@@ -39,7 +42,7 @@
   systemd.network.networks."ens18" = {
     matchConfig.Name = "ens18";
     address = [
-      "10.69.13.101/24"
+      "10.69.13.20/24"
     ];
     routes = [
       { Gateway = "10.69.13.1"; }

hosts/testvm02/configuration.nix

@@ -0,0 +1,72 @@
+{
+  config,
+  lib,
+  pkgs,
+  ...
+}:
+
+{
+  imports = [
+    ../template2/hardware-configuration.nix
+
+    ../../system
+    ../../common/vm
+  ];
+
+  # Host metadata (adjust as needed)
+  homelab.host = {
+    tier = "test";  # Start in test tier, move to prod after validation
+  };
+
+  # Enable Vault integration
+  vault.enable = true;
+
+  # Enable remote deployment via NATS
+  homelab.deploy.enable = true;
+
+  nixpkgs.config.allowUnfree = true;
+  boot.loader.grub.enable = true;
+  boot.loader.grub.device = "/dev/vda";
+
+  networking.hostName = "testvm02";
+  networking.domain = "home.2rjus.net";
+  networking.useNetworkd = true;
+  networking.useDHCP = false;
+  services.resolved.enable = true;
+  networking.nameservers = [
+    "10.69.13.5"
+    "10.69.13.6"
+  ];
+
+  systemd.network.enable = true;
+  systemd.network.networks."ens18" = {
+    matchConfig.Name = "ens18";
+    address = [
+      "10.69.13.21/24"
+    ];
+    routes = [
+      { Gateway = "10.69.13.1"; }
+    ];
+    linkConfig.RequiredForOnline = "routable";
+  };
+  time.timeZone = "Europe/Oslo";
+
+  nix.settings.experimental-features = [
+    "nix-command"
+    "flakes"
+  ];
+  nix.settings.tarball-ttl = 0;
+  environment.systemPackages = with pkgs; [
+    vim
+    wget
+    git
+  ];
+
+  # Open ports in the firewall.
+  # networking.firewall.allowedTCPPorts = [ ... ];
+  # networking.firewall.allowedUDPPorts = [ ... ];
+  # Or disable the firewall altogether.
+  networking.firewall.enable = false;
+
+  system.stateVersion = "25.11"; # Did you read the comment?
+}

hosts/testvm03/configuration.nix

@@ -0,0 +1,72 @@
+{
+  config,
+  lib,
+  pkgs,
+  ...
+}:
+
+{
+  imports = [
+    ../template2/hardware-configuration.nix
+
+    ../../system
+    ../../common/vm
+  ];
+
+  # Host metadata (adjust as needed)
+  homelab.host = {
+    tier = "test";  # Start in test tier, move to prod after validation
+  };
+
+  # Enable Vault integration
+  vault.enable = true;
+
+  # Enable remote deployment via NATS
+  homelab.deploy.enable = true;
+
+  nixpkgs.config.allowUnfree = true;
+  boot.loader.grub.enable = true;
+  boot.loader.grub.device = "/dev/vda";
+
+  networking.hostName = "testvm03";
+  networking.domain = "home.2rjus.net";
+  networking.useNetworkd = true;
+  networking.useDHCP = false;
+  services.resolved.enable = true;
+  networking.nameservers = [
+    "10.69.13.5"
+    "10.69.13.6"
+  ];
+
+  systemd.network.enable = true;
+  systemd.network.networks."ens18" = {
+    matchConfig.Name = "ens18";
+    address = [
+      "10.69.13.22/24"
+    ];
+    routes = [
+      { Gateway = "10.69.13.1"; }
+    ];
+    linkConfig.RequiredForOnline = "routable";
+  };
+  time.timeZone = "Europe/Oslo";
+
+  nix.settings.experimental-features = [
+    "nix-command"
+    "flakes"
+  ];
+  nix.settings.tarball-ttl = 0;
+  environment.systemPackages = with pkgs; [
+    vim
+    wget
+    git
+  ];
+
+  # Open ports in the firewall.
+  # networking.firewall.allowedTCPPorts = [ ... ];
+  # networking.firewall.allowedUDPPorts = [ ... ];
+  # Or disable the firewall altogether.
+  networking.firewall.enable = false;
+
+  system.stateVersion = "25.11"; # Did you read the comment?
+}

hosts/testvm03/default.nix

@@ -0,0 +1,5 @@
+{ ... }: {
+  imports = [
+    ./configuration.nix
+  ];
+}

hosts/vaulttest01/configuration.nix

@@ -1,135 +0,0 @@
-{
-  config,
-  lib,
-  pkgs,
-  ...
-}:
-
-let
-  vault-test-script = pkgs.writeShellApplication {
-    name = "vault-test";
-    text = ''
-      echo "=== Vault Secret Test ==="
-      echo "Secret path: hosts/vaulttest01/test-service"
-
-      if [ -f /run/secrets/test-service/password ]; then
-        echo "✓ Password file exists"
-        echo "Password length: $(wc -c < /run/secrets/test-service/password)"
-      else
-        echo "✗ Password file missing!"
-        exit 1
-      fi
-
-      if [ -d /var/lib/vault/cache/test-service ]; then
-        echo "✓ Cache directory exists"
-      else
-        echo "✗ Cache directory missing!"
-        exit 1
-      fi
-
-      echo "Test successful!"
-    '';
-  };
-in
-{
-  imports = [
-    ../template2/hardware-configuration.nix
-
-    ../../system
-    ../../common/vm
-  ];
-
-  homelab.host = {
-    tier = "test";
-    priority = "low";
-    role = "vault";
-  };
-
-  nixpkgs.config.allowUnfree = true;
-  boot.loader.grub.enable = true;
-  boot.loader.grub.device = "/dev/vda";
-
-  networking.hostName = "vaulttest01";
-  networking.domain = "home.2rjus.net";
-  networking.useNetworkd = true;
-  networking.useDHCP = false;
-  services.resolved.enable = true;
-  networking.nameservers = [
-    "10.69.13.5"
-    "10.69.13.6"
-  ];
-
-  systemd.network.enable = true;
-  systemd.network.networks."ens18" = {
-    matchConfig.Name = "ens18";
-    address = [
-      "10.69.13.150/24"
-    ];
-    routes = [
-      { Gateway = "10.69.13.1"; }
-    ];
-    linkConfig.RequiredForOnline = "routable";
-  };
-  time.timeZone = "Europe/Oslo";
-
-  nix.settings.experimental-features = [
-    "nix-command"
-    "flakes"
-  ];
-  nix.settings.tarball-ttl = 0;
-  environment.systemPackages = with pkgs; [
-    vim
-    wget
-    git
-    htop # test deploy verification
-  ];
-
-  # Open ports in the firewall.
-  # networking.firewall.allowedTCPPorts = [ ... ];
-  # networking.firewall.allowedUDPPorts = [ ... ];
-  # Or disable the firewall altogether.
-  networking.firewall.enable = false;
-
-  # Testing config
-  # Enable Vault secrets management
-  vault.enable = true;
-  homelab.deploy.enable = true;
-
-  # Define a test secret
-  vault.secrets.test-service = {
-    secretPath = "hosts/vaulttest01/test-service";
-    restartTrigger = true;
-    restartInterval = "daily";
-    services = [ "vault-test" ];
-  };
-
-  # Create a test service that uses the secret
-  systemd.services.vault-test = {
-    description = "Test Vault secret fetching";
-    wantedBy = [ "multi-user.target" ];
-    after = [ "vault-secret-test-service.service" ];
-
-    serviceConfig = {
-      Type = "oneshot";
-      RemainAfterExit = true;
-
-      ExecStart = lib.getExe vault-test-script;
-
-      StandardOutput = "journal+console";
-    };
-  };
-
-  # Test ACME certificate issuance from OpenBao PKI
-  # Override the global ACME server (from system/acme.nix) to use OpenBao instead of step-ca
-  security.acme.defaults.server = lib.mkForce "https://vault01.home.2rjus.net:8200/v1/pki_int/acme/directory";
-
-  # Request a certificate for this host
-  # Using HTTP-01 challenge with standalone listener on port 80
-  security.acme.certs."vaulttest01.home.2rjus.net" = {
-    listenHTTP = ":80";
-    enableDebugLogs = true;
-  };
-
-  system.stateVersion = "25.11"; # Did you read the comment?
-}
-

playbooks/build-and-deploy-template.yml

@@ -99,3 +99,48 @@
     - name: Display success message
       ansible.builtin.debug:
         msg: "Template VM {{ template_vmid }} created successfully on {{ storage }}"
+
+- name: Update Terraform template name
+  hosts: localhost
+  gather_facts: false
+
+  vars:
+    terraform_dir: "{{ playbook_dir }}/../terraform"
+
+  tasks:
+    - name: Get image filename from earlier play
+      ansible.builtin.set_fact:
+        image_filename: "{{ hostvars['localhost']['image_filename'] }}"
+
+    - name: Extract template name from image filename
+      ansible.builtin.set_fact:
+        new_template_name: "{{ image_filename | regex_replace('\\.vma\\.zst$', '') | regex_replace('^vzdump-qemu-', '') }}"
+
+    - name: Read current Terraform variables file
+      ansible.builtin.slurp:
+        src: "{{ terraform_dir }}/variables.tf"
+      register: variables_tf_content
+
+    - name: Extract current template name from variables.tf
+      ansible.builtin.set_fact:
+        current_template_name: "{{ (variables_tf_content.content | b64decode) | regex_search('variable \"default_template_name\"[^}]+default\\s*=\\s*\"([^\"]+)\"', '\\1') | first }}"
+
+    - name: Check if template name has changed
+      ansible.builtin.set_fact:
+        template_name_changed: "{{ current_template_name != new_template_name }}"
+
+    - name: Display template name status
+      ansible.builtin.debug:
+        msg: "Template name: {{ current_template_name }} -> {{ new_template_name }} ({{ 'changed' if template_name_changed else 'unchanged' }})"
+
+    - name: Update default_template_name in variables.tf
+      ansible.builtin.replace:
+        path: "{{ terraform_dir }}/variables.tf"
+        regexp: '(variable "default_template_name"[^}]+default\s*=\s*)"[^"]+"'
+        replace: '\1"{{ new_template_name }}"'
+      when: template_name_changed
+
+    - name: Display update result
+      ansible.builtin.debug:
+        msg: "Updated terraform/variables.tf with new template name: {{ new_template_name }}"
+      when: template_name_changed

scripts/create-host/create_host.py

@@ -18,6 +18,8 @@ from manipulators import (
     remove_from_flake_nix,
     remove_from_terraform_vms,
     remove_from_vault_terraform,
+    remove_from_approle_tf,
+    find_host_secrets,
     check_entries_exist,
 )
 from models import HostConfig
@@ -255,7 +257,10 @@ def handle_remove(
         sys.exit(1)
 
     # Check what entries exist
-    flake_exists, terraform_exists, vault_exists = check_entries_exist(hostname, repo_root)
+    flake_exists, terraform_exists, vault_exists, approle_exists = check_entries_exist(hostname, repo_root)
+
+    # Check for secrets in secrets.tf
+    host_secrets = find_host_secrets(hostname, repo_root)
 
     # Collect all files in the host directory recursively
     files_in_host_dir = sorted([f for f in host_dir.rglob("*") if f.is_file()])
@@ -294,6 +299,21 @@ def handle_remove(
     else:
         console.print(f"  • terraform/vault/hosts-generated.tf [dim](not found)[/dim]")
 
+    if approle_exists:
+        console.print(f'  • terraform/vault/approle.tf (host_policies["{hostname}"])')
+    else:
+        console.print(f"  • terraform/vault/approle.tf [dim](not found)[/dim]")
+
+    # Warn about secrets in secrets.tf
+    if host_secrets:
+        console.print(f"\n[yellow]⚠️  Warning: Found {len(host_secrets)} secret(s) in terraform/vault/secrets.tf:[/yellow]")
+        for secret_path in host_secrets:
+            console.print(f'   • "{secret_path}"')
+        console.print(f"\n   [yellow]These will NOT be removed automatically.[/yellow]")
+        console.print(f"   After removal, manually edit secrets.tf and run:")
+        for secret_path in host_secrets:
+            console.print(f"   [white]vault kv delete secret/{secret_path}[/white]")
+
     # Warn about secrets directory
     if secrets_exist:
         console.print(f"\n[yellow]⚠️  Warning: secrets/{hostname}/ directory exists and will NOT be deleted[/yellow]")
@@ -323,6 +343,13 @@ def handle_remove(
         else:
             console.print("[yellow]⚠[/yellow]  Could not remove from terraform/vault/hosts-generated.tf")
 
+    # Remove from terraform/vault/approle.tf
+    if approle_exists:
+        if remove_from_approle_tf(hostname, repo_root):
+            console.print("[green]✓[/green] Removed from terraform/vault/approle.tf")
+        else:
+            console.print("[yellow]⚠[/yellow]  Could not remove from terraform/vault/approle.tf")
+
     # Remove from terraform/vms.tf
     if terraform_exists:
         if remove_from_terraform_vms(hostname, repo_root):
@@ -345,19 +372,34 @@ def handle_remove(
     console.print(f"\n[bold green]✓ Host {hostname} removed successfully![/bold green]\n")
 
     # Display next steps
-    display_removal_next_steps(hostname, vault_exists)
+    display_removal_next_steps(hostname, vault_exists, approle_exists, host_secrets)
 
 
-def display_removal_next_steps(hostname: str, had_vault: bool) -> None:
+def display_removal_next_steps(hostname: str, had_vault: bool, had_approle: bool, host_secrets: list) -> None:
     """Display next steps after successful removal."""
-    vault_file = " terraform/vault/hosts-generated.tf" if had_vault else ""
-    vault_apply = ""
+    vault_files = ""
     if had_vault:
+        vault_files += " terraform/vault/hosts-generated.tf"
+    if had_approle:
+        vault_files += " terraform/vault/approle.tf"
+
+    vault_apply = ""
+    if had_vault or had_approle:
         vault_apply = f"""
 3. Apply Vault changes:
    [white]cd terraform/vault && tofu apply[/white]
 """
 
+    secrets_cleanup = ""
+    if host_secrets:
+        secrets_cleanup = f"""
+5. Clean up secrets (manual):
+   Edit terraform/vault/secrets.tf to remove entries for {hostname}
+   Then delete from Vault:"""
+        for secret_path in host_secrets:
+            secrets_cleanup += f"\n   [white]vault kv delete secret/{secret_path}[/white]"
+        secrets_cleanup += "\n"
+
     next_steps = f"""[bold cyan]Next Steps:[/bold cyan]
 
 1. Review changes:
@@ -367,9 +409,9 @@ def display_removal_next_steps(hostname: str, had_vault: bool) -> None:
    [white]cd terraform && tofu destroy -target='proxmox_vm_qemu.vm["{hostname}"]'[/white]
 {vault_apply}
 4. Commit changes:
-   [white]git add -u hosts/{hostname} flake.nix terraform/vms.tf{vault_file}
+   [white]git add -u hosts/{hostname} flake.nix terraform/vms.tf{vault_files}
    git commit -m "hosts: remove {hostname}"[/white]
-"""
+{secrets_cleanup}"""
     console.print(Panel(next_steps, border_style="cyan"))
 
 

scripts/create-host/generators.py

@@ -144,7 +144,7 @@ resource "vault_approle_auth_backend_role" "generated_hosts" {
 
   backend            = vault_auth_backend.approle.path
   role_name          = each.key
-  token_policies     = ["host-\${each.key}"]
+  token_policies     = ["host-\${each.key}", "homelab-deploy"]
   secret_id_ttl      = 0  # Never expire (wrapped tokens provide time limit)
   token_ttl          = 3600
   token_max_ttl      = 3600

scripts/create-host/manipulators.py

@@ -22,12 +22,12 @@ def remove_from_flake_nix(hostname: str, repo_root: Path) -> bool:
     content = flake_path.read_text()
 
     # Check if hostname exists
-    hostname_pattern = rf"^      {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem"
+    hostname_pattern = rf"^        {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem"
     if not re.search(hostname_pattern, content, re.MULTILINE):
         return False
 
     # Match the entire block from "hostname = " to "};"
-    replace_pattern = rf"^      {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem \{{.*?^      \}};\n"
+    replace_pattern = rf"^        {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem \{{.*?^        \}};\n"
     new_content, count = re.subn(replace_pattern, "", content, flags=re.MULTILINE | re.DOTALL)
 
     if count == 0:
@@ -101,7 +101,68 @@ def remove_from_vault_terraform(hostname: str, repo_root: Path) -> bool:
     return True
 
 
-def check_entries_exist(hostname: str, repo_root: Path) -> Tuple[bool, bool, bool]:
+def remove_from_approle_tf(hostname: str, repo_root: Path) -> bool:
+    """
+    Remove host entry from terraform/vault/approle.tf locals.host_policies.
+
+    Args:
+        hostname: Hostname to remove
+        repo_root: Path to repository root
+
+    Returns:
+        True if found and removed, False if not found
+    """
+    approle_path = repo_root / "terraform" / "vault" / "approle.tf"
+
+    if not approle_path.exists():
+        return False
+
+    content = approle_path.read_text()
+
+    # Check if hostname exists in host_policies
+    hostname_pattern = rf'^\s+"{re.escape(hostname)}" = \{{'
+    if not re.search(hostname_pattern, content, re.MULTILINE):
+        return False
+
+    # Match the entire block from "hostname" = { to closing }
+    # The block contains paths = [ ... ] and possibly extra_policies = [...]
+    replace_pattern = rf'\n?\s+"{re.escape(hostname)}" = \{{[^}}]*\}}\n?'
+    new_content, count = re.subn(replace_pattern, "\n", content, flags=re.DOTALL)
+
+    if count == 0:
+        return False
+
+    approle_path.write_text(new_content)
+    return True
+
+
+def find_host_secrets(hostname: str, repo_root: Path) -> list:
+    """
+    Find secrets in terraform/vault/secrets.tf that belong to a host.
+
+    Args:
+        hostname: Hostname to search for
+        repo_root: Path to repository root
+
+    Returns:
+        List of secret paths found (e.g., ["hosts/hostname/test-service"])
+    """
+    secrets_path = repo_root / "terraform" / "vault" / "secrets.tf"
+
+    if not secrets_path.exists():
+        return []
+
+    content = secrets_path.read_text()
+
+    # Find all secret paths matching hosts/{hostname}/
+    pattern = rf'"(hosts/{re.escape(hostname)}/[^"]+)"'
+    matches = re.findall(pattern, content)
+
+    # Return unique paths, preserving order
+    return list(dict.fromkeys(matches))
+
+
+def check_entries_exist(hostname: str, repo_root: Path) -> Tuple[bool, bool, bool, bool]:
     """
     Check which entries exist for a hostname.
 
@@ -110,12 +171,12 @@ def check_entries_exist(hostname: str, repo_root: Path) -> Tuple[bool, bool, boo
         repo_root: Path to repository root
 
     Returns:
-        Tuple of (flake_exists, terraform_vms_exists, vault_exists)
+        Tuple of (flake_exists, terraform_vms_exists, vault_generated_exists, approle_exists)
     """
     # Check flake.nix
     flake_path = repo_root / "flake.nix"
     flake_content = flake_path.read_text()
-    flake_pattern = rf"^      {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem"
+    flake_pattern = rf"^        {re.escape(hostname)} = nixpkgs\.lib\.nixosSystem"
     flake_exists = bool(re.search(flake_pattern, flake_content, re.MULTILINE))
 
     # Check terraform/vms.tf
@@ -131,7 +192,15 @@ def check_entries_exist(hostname: str, repo_root: Path) -> Tuple[bool, bool, boo
         vault_content = vault_tf_path.read_text()
         vault_exists = f'"{hostname}"' in vault_content
 
-    return (flake_exists, terraform_exists, vault_exists)
+    # Check terraform/vault/approle.tf
+    approle_path = repo_root / "terraform" / "vault" / "approle.tf"
+    approle_exists = False
+    if approle_path.exists():
+        approle_content = approle_path.read_text()
+        approle_pattern = rf'^\s+"{re.escape(hostname)}" = \{{'
+        approle_exists = bool(re.search(approle_pattern, approle_content, re.MULTILINE))
+
+    return (flake_exists, terraform_exists, vault_exists, approle_exists)
 
 
 def update_flake_nix(config: HostConfig, repo_root: Path, force: bool = False) -> None:
@@ -147,32 +216,25 @@ def update_flake_nix(config: HostConfig, repo_root: Path, force: bool = False) -
     content = flake_path.read_text()
 
     # Create new entry
-    new_entry = f"""      {config.hostname} = nixpkgs.lib.nixosSystem {{
-        inherit system;
-        specialArgs = {{
-          inherit inputs self sops-nix;
+    new_entry = f"""        {config.hostname} = nixpkgs.lib.nixosSystem {{
+          inherit system;
+          specialArgs = {{
+            inherit inputs self sops-nix;
+          }};
+          modules = commonModules ++ [
+            ./hosts/{config.hostname}
+          ];
         }};
-        modules = [
-          (
-            {{ config, pkgs, ... }}:
-            {{
-              nixpkgs.overlays = commonOverlays;
-            }}
-          )
-          ./hosts/{config.hostname}
-          sops-nix.nixosModules.sops
-        ];
-      }};
 """
 
     # Check if hostname already exists
-    hostname_pattern = rf"^      {re.escape(config.hostname)} = nixpkgs\.lib\.nixosSystem"
+    hostname_pattern = rf"^        {re.escape(config.hostname)} = nixpkgs\.lib\.nixosSystem"
     existing_match = re.search(hostname_pattern, content, re.MULTILINE)
 
     if existing_match and force:
         # Replace existing entry
         # Match the entire block from "hostname = " to "};"
-        replace_pattern = rf"^      {re.escape(config.hostname)} = nixpkgs\.lib\.nixosSystem \{{.*?^      \}};\n"
+        replace_pattern = rf"^        {re.escape(config.hostname)} = nixpkgs\.lib\.nixosSystem \{{.*?^        \}};\n"
         new_content, count = re.subn(replace_pattern, new_entry, content, flags=re.MULTILINE | re.DOTALL)
 
         if count == 0:

scripts/create-host/templates/configuration.nix.j2

@@ -18,6 +18,12 @@
     tier = "test";  # Start in test tier, move to prod after validation
   };
 
+  # Enable Vault integration
+  vault.enable = true;
+
+  # Enable remote deployment via NATS
+  homelab.deploy.enable = true;
+
   nixpkgs.config.allowUnfree = true;
   boot.loader.grub.enable = true;
   boot.loader.grub.device = "/dev/vda";

terraform/variables.tf

@@ -33,7 +33,7 @@ variable "default_target_node" {
 variable "default_template_name" {
   description = "Default template VM name to clone from"
   type        = string
-  default     = "nixos-25.11.20260131.41e216c"
+  default     = "nixos-25.11.20260203.e576e3c"
 }
 
 variable "default_ssh_public_key" {

terraform/vault/approle.tf

@@ -101,11 +101,6 @@ locals {
       ]
     }
 
-    "vaulttest01" = {
-      paths = [
-        "secret/data/hosts/vaulttest01/*",
-      ]
-    }
   }
 }
 

terraform/vault/hosts-generated.tf

@@ -5,12 +5,22 @@
 # Each host gets access to its own secrets under hosts/<hostname>/*
 locals {
   generated_host_policies = {
-    "vaulttest01" = {
+    "testvm01" = {
       paths = [
-        "secret/data/hosts/vaulttest01/*",
+        "secret/data/hosts/testvm01/*",
       ]
     }
-
+    "testvm02" = {
+      paths = [
+        "secret/data/hosts/testvm02/*",
+      ]
+    }
+    "testvm03" = {
+      paths = [
+        "secret/data/hosts/testvm03/*",
+      ]
+    }
+  
   }
 
   # Placeholder secrets - user should add actual secrets manually or via tofu
@@ -40,7 +50,7 @@ resource "vault_approle_auth_backend_role" "generated_hosts" {
 
   backend            = vault_auth_backend.approle.path
   role_name          = each.key
-  token_policies     = ["host-${each.key}"]
+  token_policies     = ["host-${each.key}", "homelab-deploy"]
   secret_id_ttl      = 0 # Never expire (wrapped tokens provide time limit)
   token_ttl          = 3600
   token_max_ttl      = 3600

terraform/vault/secrets.tf

@@ -45,12 +45,6 @@ locals {
       password_length = 24
     }
 
-    # TODO: Remove after testing
-    "hosts/vaulttest01/test-service" = {
-      auto_generate   = true
-      password_length = 32
-    }
-
     # Shared backup password (auto-generated, add alongside existing restic key)
     "shared/backup/password" = {
       auto_generate   = true

terraform/vms.tf

@@ -31,13 +31,6 @@ locals {
     # Example Minimal VM using all defaults (uncomment to deploy):
     # "minimal-vm" = {}
     # "bootstrap-verify-test" = {}
-    "testvm01" = {
-      ip           = "10.69.13.101/24"
-      cpu_cores    = 2
-      memory       = 2048
-      disk_size    = "20G"
-      flake_branch = "pipeline-testing-improvements"
-    }
     "vault01" = {
       ip           = "10.69.13.19/24"
       cpu_cores    = 2
@@ -45,13 +38,25 @@ locals {
       disk_size    = "20G"
       flake_branch = "vault-setup" # Bootstrap from this branch instead of master
     }
-    "vaulttest01" = {
-      ip                  = "10.69.13.150/24"
+    "testvm01" = {
+      ip                  = "10.69.13.20/24"
       cpu_cores           = 2
       memory              = 2048
       disk_size           = "20G"
-      flake_branch        = "pki-migration"
-      vault_wrapped_token = "s.UCpQCOp7cOKDdtGGBvfRWwAt"
+      flake_branch        = "improve-bootstrap-visibility"
+      vault_wrapped_token = "s.l5q88wzXfEcr5SMDHmO6o96b"
+    }
+    "testvm02" = {
+      ip        = "10.69.13.21/24"
+      cpu_cores = 2
+      memory    = 2048
+      disk_size = "20G"
+    }
+    "testvm03" = {
+      ip        = "10.69.13.22/24"
+      cpu_cores = 2
+      memory    = 2048
+      disk_size = "20G"
     }
   }