fix: remove serial console (root cause of 30s boot delay), enable syslog logging, disk auto-detect

Root cause found: console=ttyS0,115200n8 causes 30-second timeout at every
systemd boot phase on hardware without a physical serial UART. Each phase
transition blocks waiting for the non-existent UART.

Changes:
- Remove console=ttyS0 from kickstart bootloader args and %post setup
- Enable Anaconda syslog forwarding (logging --host --port) for install visibility
- Improve syslog IP→MAC resolution (register from kickstart fetch + progress)
- Fix disk auto-detect: default to empty string (not /dev/sda) for NVMe support
- Enable SysRq magic keys (kernel.sysrq=1) for emergency reboot via JetKVM
- Simplify debug command: remove --sshd flag (inst.sshd always available),
  add /debug-setup.sh HTTP endpoint for nc listener setup
- Add labctl provision logs -f (follow mode with polling)
- Add syslog listener unit tests
- Enable syslog log capture test in integration suite

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

bastion/completions/labctl.bash

@@ -29,43 +29,49 @@ _labctl() {
       COMPREPLY=($(compgen -W "--dir -h --help" -- "$cur"))
       return ;;
     "init bastion standalone status")
-      COMPREPLY=($(compgen -W "--dir --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
     "init bastion standalone")
       COMPREPLY=($(compgen -W "start stop status -h --help" -- "$cur"))
       return ;;
     "app labcontroller deploy")
-      COMPREPLY=($(compgen -W "--user --port --crdb-replicas -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--user --crdb-replicas -h --help" -- "$cur"))
       return ;;
     "app labcontroller status")
-      COMPREPLY=($(compgen -W "--user --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--user -h --help" -- "$cur"))
       return ;;
     "app k3s install")
-      COMPREPLY=($(compgen -W "--role --user --port --k3s-server --k3s-token -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--role --user --k3s-server --k3s-token -h --help" -- "$cur"))
       return ;;
     "app k3s health")
-      COMPREPLY=($(compgen -W "--user --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--user -h --help" -- "$cur"))
       return ;;
     "app k3s list")
-      COMPREPLY=($(compgen -W "--user --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--user -h --help" -- "$cur"))
       return ;;
     "init bastion")
       COMPREPLY=($(compgen -W "standalone -h --help" -- "$cur"))
       return ;;
     "provision list")
-      COMPREPLY=($(compgen -W "--port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
     "provision install")
-      COMPREPLY=($(compgen -W "--role --os --disk --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--role --os --disk -h --help" -- "$cur"))
       return ;;
     "provision reprovision")
-      COMPREPLY=($(compgen -W "--role --os --disk --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "--role --os --disk -h --help" -- "$cur"))
+      return ;;
+    "provision debug")
+      COMPREPLY=($(compgen -W "--pxe-boot -h --help" -- "$cur"))
       return ;;
     "provision forget")
-      COMPREPLY=($(compgen -W "--port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
     "provision logs")
-      COMPREPLY=($(compgen -W "-f --follow --port -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "-f --follow -h --help" -- "$cur"))
+      return ;;
+    "provision makeiso")
+      COMPREPLY=($(compgen -W "--arch --local --out -h --help" -- "$cur"))
       return ;;
     "config list")
       COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
@@ -92,7 +98,7 @@ _labctl() {
       COMPREPLY=($(compgen -W "bastion -h --help" -- "$cur"))
       return ;;
     "provision")
-      COMPREPLY=($(compgen -W "list install reprovision forget logs -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "list install reprovision debug forget logs makeiso -h --help" -- "$cur"))
       return ;;
     "config")
       COMPREPLY=($(compgen -W "list get set path -h --help" -- "$cur"))

bastion/completions/labctl.fish

@@ -118,38 +118,35 @@ complete -c labctl -n "__labctl_in_cmd init bastion standalone start" -l foregro
 # init bastion standalone stop options
 complete -c labctl -n "__labctl_in_cmd init bastion standalone stop" -l dir -d 'Bastion data directory' -x
 
-# init bastion standalone status options
-complete -c labctl -n "__labctl_in_cmd init bastion standalone status" -l dir -d 'Bastion data directory' -x
-complete -c labctl -n "__labctl_in_cmd init bastion standalone status" -l port -d 'Bastion HTTP port' -x
-
 # provision subcommands
 complete -c labctl -n "__labctl_using_cmd provision" -a list -d 'List all known machines'
 complete -c labctl -n "__labctl_using_cmd provision" -a install -d 'Queue a discovered machine for OS installation'
 complete -c labctl -n "__labctl_using_cmd provision" -a reprovision -d 'Queue install + SSH reboot into PXE (target: hostname, MAC, or IP)'
+complete -c labctl -n "__labctl_using_cmd provision" -a debug -d 'PXE boot into Fedora rescue mode for debugging (target: hostname, MAC, or IP)'
 complete -c labctl -n "__labctl_using_cmd provision" -a forget -d 'Remove a machine from bastion state'
 complete -c labctl -n "__labctl_using_cmd provision" -a logs -d 'Show provisioning logs for a machine (hostname, MAC, or IP)'
-
-# provision list options
-complete -c labctl -n "__labctl_in_cmd provision list" -l port -d 'Bastion HTTP port' -x
+complete -c labctl -n "__labctl_using_cmd provision" -a makeiso -d 'Generate a UEFI-bootable iPXE ISO for network provisioning'
 
 # provision install options
 complete -c labctl -n "__labctl_in_cmd provision install" -l role -d 'Machine role (see below)' -xa 'vanilla worker infra labcontroller'
 complete -c labctl -n "__labctl_in_cmd provision install" -l os -d 'Operating system' -xa 'fedora-43 ubuntu-26.04'
 complete -c labctl -n "__labctl_in_cmd provision install" -l disk -d 'Target disk device (auto-detect if omitted)' -x
-complete -c labctl -n "__labctl_in_cmd provision install" -l port -d 'Bastion HTTP port' -x
 
 # provision reprovision options
 complete -c labctl -n "__labctl_in_cmd provision reprovision" -l role -d 'Machine role (see below)' -xa 'vanilla worker infra labcontroller'
 complete -c labctl -n "__labctl_in_cmd provision reprovision" -l os -d 'Operating system' -xa 'fedora-43 ubuntu-26.04'
 complete -c labctl -n "__labctl_in_cmd provision reprovision" -l disk -d 'Target disk device (auto-detect if omitted)' -x
-complete -c labctl -n "__labctl_in_cmd provision reprovision" -l port -d 'Bastion HTTP port' -x
 
-# provision forget options
-complete -c labctl -n "__labctl_in_cmd provision forget" -l port -d 'Bastion HTTP port' -x
+# provision debug options
+complete -c labctl -n "__labctl_in_cmd provision debug" -l pxe-boot -d 'Boot installed system via PXE (kernel+initrd from network, root from NVMe)'
 
 # provision logs options
-complete -c labctl -n "__labctl_in_cmd provision logs" -s f -l follow -d 'Follow logs in real-time (SSE stream)'
-complete -c labctl -n "__labctl_in_cmd provision logs" -l port -d 'Bastion HTTP port' -x
+complete -c labctl -n "__labctl_in_cmd provision logs" -s f -l follow -d 'Follow log output in real-time'
+
+# provision makeiso options
+complete -c labctl -n "__labctl_in_cmd provision makeiso" -l arch -d 'Target architecture(s)' -xa 'x86_64 aarch64'
+complete -c labctl -n "__labctl_in_cmd provision makeiso" -l local -d 'Build ISO locally instead of using bastion-hosted URL'
+complete -c labctl -n "__labctl_in_cmd provision makeiso" -l out -d 'Output path for local ISO build' -x
 
 # config subcommands
 complete -c labctl -n "__labctl_using_cmd config" -a list -d 'Show all configuration values'
@@ -173,12 +170,10 @@ complete -c labctl -n "__labctl_using_cmd app labcontroller" -a status -d 'Check
 
 # app labcontroller deploy options
 complete -c labctl -n "__labctl_in_cmd app labcontroller deploy" -l user -d 'SSH user' -x
-complete -c labctl -n "__labctl_in_cmd app labcontroller deploy" -l port -d 'Bastion HTTP port' -x
 complete -c labctl -n "__labctl_in_cmd app labcontroller deploy" -l crdb-replicas -d 'CockroachDB replicas' -x
 
 # app labcontroller status options
 complete -c labctl -n "__labctl_in_cmd app labcontroller status" -l user -d 'SSH user' -x
-complete -c labctl -n "__labctl_in_cmd app labcontroller status" -l port -d 'Bastion HTTP port' -x
 
 # app k3s subcommands
 complete -c labctl -n "__labctl_using_cmd app k3s" -a install -d 'Install k3s on a target machine (hostname, IP, or MAC)'
@@ -188,15 +183,12 @@ complete -c labctl -n "__labctl_using_cmd app k3s" -a list -d 'List installed ma
 # app k3s install options
 complete -c labctl -n "__labctl_in_cmd app k3s install" -l role -d 'k3s role: infra (server) or worker (agent)' -x
 complete -c labctl -n "__labctl_in_cmd app k3s install" -l user -d 'SSH user' -x
-complete -c labctl -n "__labctl_in_cmd app k3s install" -l port -d 'Bastion HTTP port (for resolving target)' -x
 complete -c labctl -n "__labctl_in_cmd app k3s install" -l k3s-server -d 'k3s server URL (required for worker role)' -x
 complete -c labctl -n "__labctl_in_cmd app k3s install" -l k3s-token -d 'k3s join token (required for worker role)' -x
 
 # app k3s health options
 complete -c labctl -n "__labctl_in_cmd app k3s health" -l user -d 'SSH user' -x
-complete -c labctl -n "__labctl_in_cmd app k3s health" -l port -d 'Bastion HTTP port' -x
 
 # app k3s list options
 complete -c labctl -n "__labctl_in_cmd app k3s list" -l user -d 'SSH user' -x
-complete -c labctl -n "__labctl_in_cmd app k3s list" -l port -d 'Bastion HTTP port' -x
 

bastion/docs/kickstart-reference.md

@@ -0,0 +1,103 @@
+# Kickstart Reference — Lessons Learned
+
+This documents pitfalls discovered during PXE boot testing. Read before modifying
+the kickstart template (`src/bastion/src/templates/install.ks.ts`).
+
+## Package requirements
+
+### `kernel-modules` is mandatory
+
+`@core` only installs `kernel-modules-core`, which lacks common modules like `vfat`,
+`zram`, and many network/filesystem drivers. Without `kernel-modules`:
+
+- `/boot/efi` (FAT32) cannot mount → `systemd-remount-fs` fails → **root stays
+  read-only** → sshd-keygen can't write host keys → SSH unreachable
+- `zram-generator` fails → can trigger emergency mode
+
+**Always include `kernel-modules` in %packages.** This matches what the real
+labmaster (192.168.8.11) has installed.
+
+Regression introduced in commit `fac14b6` which removed `@server-product`
+(that group pulled in `kernel-modules` via `fedora-release-server`).
+
+### `dosfstools` is needed
+
+Provides `mkfs.vfat` and ensures FAT filesystem support is available. The real
+labmaster has it installed.
+
+### Verify against the real machine
+
+Before changing the package list, SSH to the labmaster and compare:
+```bash
+ssh 192.168.8.11 "rpm -q <package>"
+```
+
+## Anaconda %post execution order
+
+This is critical and not well documented:
+
+1. `%pre` scripts run
+2. Disk partitioning and formatting
+3. Package installation
+4. **Anaconda writes system config (fstab, hostname, etc.)**
+5. `%post` scripts run (in chroot of installed system)
+6. `%post --nochroot` scripts run
+7. **Anaconda MAY overwrite fstab again after %post scripts**
+
+**Consequence:** You cannot reliably modify `/etc/fstab` from `%post` or
+`%post --nochroot`. Anaconda overwrites it. Tested and confirmed — both
+`sed` in %post and %post --nochroot had no effect on the final fstab.
+
+What DOES work from %post:
+- Writing files to `/etc/` (systemd units, config files, SSH keys)
+- Enabling/disabling systemd services
+- Installing additional packages
+- Running `systemctl enable/mask`
+
+What does NOT work from %post:
+- Modifying `/etc/fstab` (Anaconda overwrites it)
+- `--fsoptions` on `part /boot/efi` (Anaconda ignores it for EFI partitions)
+
+## UEFI / EFI partition
+
+- Anaconda always creates an EFI System Partition for UEFI installs
+- The EFI partition is FAT32 — requires `vfat` kernel module to mount
+- If `/boot/efi` fails to mount, `systemd-remount-fs` fails, which leaves
+  root as read-only. This cascades to break ALL services that need to write
+- The EFI partition is used by firmware directly for bootloader — the OS
+  doesn't strictly need it mounted, but Anaconda adds it to fstab
+
+## VM-specific issues (libvirt/QEMU/OVMF)
+
+### iPXE exit behavior
+- `exit` (no args) returns EFI_SUCCESS → OVMF retries PXE, never reaches disk
+- `exit 1` returns EFI_ABORTED → OVMF moves to next boot device (disk)
+- VM boot order needs both `network` and `hd`: `--boot=uefi,network,hd`
+
+### nftables
+- libvirt creates reject rules for NAT networks in table `ip libvirt_network`
+  (NOT `inet libvirt` — this wrong table name cost hours of debugging)
+- These rules block new host→VM connections (SSH)
+- Rules are recreated on every `virsh start` — must delete after each VM restart
+- Chains: `guest_input` and `guest_output`
+
+### Serial console
+- VM serial port: `--serial=tcp,host=127.0.0.1:4555,mode=bind,protocol=telnet`
+- Use `virsh console <vm-name>` for interactive access (handles telnet protocol)
+- Raw `socat` works for reading but pagers/readline break interactive use
+- Add `console=ttyS0,115200n8` to kernel args for boot output on serial
+
+### SELinux on labmaster
+- Set to **permissive** — this is for k3s/kubernetes, NOT because SSH needs it
+- SSH works fine with SELinux enforcing on a properly installed Fedora system
+- The `ld.so.cache` AVC denials seen during debugging were caused by the
+  read-only root filesystem, not by SELinux policy
+
+## Testing checklist
+
+Before merging kickstart changes:
+1. Check the real labmaster has the same packages: `ssh 192.168.8.11 "rpm -q <pkg>"`
+2. Run the PXE integration test: `sudo pnpm run test:integration:pxe`
+3. Verify via serial console (root / `lab-root-pw`) if SSH fails
+4. Check `mount | grep " / "` — must show `rw`, not `ro`
+5. Check `systemctl --failed` — no critical failures

bastion/scripts/deploy.sh

@@ -0,0 +1,74 @@
+#!/bin/bash
+# Deploy bastion + labd to k3s cluster and install labctl locally.
+# Usage: ./scripts/deploy.sh [bastion|labd|labctl|all]
+#
+# Builds container images with existing build scripts, pushes to Gitea
+# registry, restarts k3s pods, and builds/installs labctl RPM.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PROJECT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+cd "$PROJECT_DIR"
+
+# Load .env if present
+if [ -f .env ]; then
+  set -a; source .env; set +a
+fi
+
+deploy_bastion() {
+    echo "=== Building & pushing bastion image ==="
+    bash scripts/build-bastion.sh --push latest
+    echo ""
+    echo "=== Restarting bastion pod ==="
+    kubectl rollout restart deployment/bastion -n lab-infra
+    kubectl rollout status deployment/bastion -n lab-infra --timeout=180s
+    echo "✓ Bastion deployed"
+}
+
+deploy_labd() {
+    echo "=== Building & pushing labd image ==="
+    bash scripts/build-labd.sh --push latest
+    echo ""
+    echo "=== Restarting labd pod ==="
+    kubectl rollout restart deployment/labd -n lab-system
+    kubectl rollout status deployment/labd -n lab-system --timeout=180s
+    echo "✓ Labd deployed"
+}
+
+deploy_labctl() {
+    echo "=== Building labctl RPM ==="
+    bash scripts/build-rpm.sh
+    echo ""
+    echo "=== Installing labctl ==="
+    RPM_FILE=$(ls dist/labctl-*.x86_64.rpm 2>/dev/null | head -1)
+    if [ -n "$RPM_FILE" ]; then
+        sudo rpm -U --force "$RPM_FILE"
+        echo "✓ labctl installed: $(labctl --version 2>/dev/null || echo 'installed')"
+    else
+        echo "WARNING: No RPM found, falling back to direct install"
+        pnpm build
+        sudo install -m 755 <(echo '#!/bin/bash'; echo "exec node $PROJECT_DIR/src/cli/dist/index.js \"\$@\"") /usr/local/bin/labctl
+        echo "✓ labctl installed (dev mode)"
+    fi
+}
+
+case "${1:-all}" in
+    bastion)  deploy_bastion ;;
+    labd)     deploy_labd ;;
+    labctl)   deploy_labctl ;;
+    all)
+        deploy_bastion
+        echo ""
+        deploy_labd
+        echo ""
+        deploy_labctl
+        ;;
+    *)
+        echo "Usage: $0 [bastion|labd|labctl|all]"
+        exit 1
+        ;;
+esac
+
+echo ""
+echo "=== Deploy complete ==="

bastion/src/bastion/src/config.ts

@@ -14,6 +14,8 @@ export function loadConfig(overrides: Partial<BastionConfig> = {}): BastionConfi
   const dhcpRangeStart = overrides.dhcpRangeStart ?? process.env["DHCP_RANGE_START"] ?? "";
   const dhcpRangeEnd = overrides.dhcpRangeEnd ?? process.env["DHCP_RANGE_END"] ?? "";
 
+  const syslogPort = overrides.syslogPort ?? parseInt(process.env["SYSLOG_PORT"] ?? "5514", 10);
+
   const ubuntuVersion = overrides.ubuntuVersion ?? process.env["UBUNTU_VERSION"] ?? "26.04";
   const ubuntuMirror = overrides.ubuntuMirror ?? process.env["UBUNTU_MIRROR"]
     ?? `https://releases.ubuntu.com/${ubuntuVersion}`;
@@ -43,6 +45,7 @@ export function loadConfig(overrides: Partial<BastionConfig> = {}): BastionConfi
     gateway: overrides.gateway ?? "",
     sshKeys: overrides.sshKeys ?? [],
     adminUser: overrides.adminUser ?? "",
+    syslogPort,
     skipDnsmasq: overrides.skipDnsmasq,
     skipArtifacts: overrides.skipArtifacts,
     labdUrl: overrides.labdUrl ?? process.env["LABD_URL"],

bastion/src/bastion/src/main.ts

@@ -220,10 +220,11 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
     openFirewall(config);
   }
 
-  // Start HTTP server
-  const { app, state } = createApp(config);
+  // Start HTTP server + syslog listener
+  const { app, state, syslog } = createApp(config);
   await app.listen({ port: config.httpPort, host: "0.0.0.0" });
   logger.info(`HTTP server listening on :${config.httpPort}`);
+  syslog.start();
 
   // Start dnsmasq (unless skipped)
   if (config.skipDnsmasq !== true) {
@@ -256,7 +257,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
       state.update((s) => {
         s.install_queue[msg.mac] = {
           hostname: msg.hostname,
-          disk: msg.disk ?? "/dev/sda",
+          disk: msg.disk ?? "",
           role: msg.role as import("@lab/shared").Role,
           os: msg.os as import("@lab/shared").OsId,
           queued_at: new Date().toISOString(),
@@ -265,6 +266,22 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
       return { status: "ok", data: { mac: msg.mac, hostname: msg.hostname } };
     });
 
+    labdConn.onCommand("command-debug", async (msg) => {
+      if (msg.type !== "command-debug") throw new Error("unexpected");
+      const mac = msg.mac.toLowerCase();
+      const pxeBoot = msg.pxeBoot ?? false;
+      const currentState = state.load();
+      const hostname =
+        currentState.installed[mac]?.hostname ??
+        currentState.install_queue[mac]?.hostname ??
+        currentState.discovered[mac]?.product ??
+        mac;
+      state.update((s) => {
+        s.debug[mac] = { hostname, queued_at: new Date().toISOString(), pxeBoot };
+      });
+      return { status: "ok", data: { mac, hostname } };
+    });
+
     labdConn.onCommand("command-forget", async (msg) => {
       if (msg.type !== "command-forget") throw new Error("unexpected");
       const mac = msg.mac.toLowerCase();
@@ -272,6 +289,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
         delete s.discovered[mac];
         delete s.install_queue[mac];
         delete s.installed[mac];
+        delete s.debug[mac];
       });
       return { status: "ok", data: { mac } };
     });
@@ -310,6 +328,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
   // Graceful shutdown
   const shutdown = async (): Promise<void> => {
     logger.info("Shutting down...");
+    syslog.stop();
     if (labdConn) labdConn.close();
     if (config.skipDnsmasq !== true) stopDnsmasq();
     closeFirewall(config);

bastion/src/bastion/src/routes/api.ts

@@ -13,11 +13,13 @@ import { triggerPostProvisionK3s } from "../services/post-provision.js";
 import { progressBus } from "../services/progress-events.js";
 import type { ProgressEvent } from "../services/progress-events.js";
 import type { InstallLogBuffer } from "../services/install-log.js";
+import type { SyslogListener } from "../services/syslog-listener.js";
 
 export function registerApiRoutes(
   app: FastifyInstance,
   state: StateManager,
   installLog: InstallLogBuffer,
+  syslog: SyslogListener,
 ): void {
   // List all machines
   app.get("/api/machines", async (_request, reply) => {
@@ -84,6 +86,11 @@ export function registerApiRoutes(
     const { mac: rawMac, stage, detail } = request.body ?? {};
     const mac = (rawMac ?? "unknown").toLowerCase();
     const stageName = stage ?? "unknown";
+
+    // Register IP → MAC for syslog routing
+    if (mac !== "unknown") {
+      syslog.registerIp(request.ip, mac);
+    }
     const detailStr = detail ?? "";
 
     const GREEN = "\x1b[0;32m";
@@ -189,6 +196,32 @@ export function registerApiRoutes(
     return reply.send({ status: "ok", lines: allLines.length });
   });
 
+  // Queue debug/rescue mode for a machine
+  app.post<{
+    Body: { mac?: string; pxeBoot?: boolean };
+  }>("/api/debug", async (request, reply) => {
+    const mac = (request.body?.mac ?? "").toLowerCase().replace(/-/g, ":");
+    const pxeBoot = request.body?.pxeBoot ?? false;
+    if (mac === "") {
+      return reply.status(400).send({ error: "mac is required" });
+    }
+
+    // Look up hostname from installed or discovered state
+    const currentState = state.load();
+    const hostname =
+      currentState.installed[mac]?.hostname ??
+      currentState.install_queue[mac]?.hostname ??
+      currentState.discovered[mac]?.product ??
+      mac;
+
+    state.update((s) => {
+      s.debug[mac] = { hostname, queued_at: new Date().toISOString(), pxeBoot };
+    });
+
+    logger.info(`DEBUG QUEUED: ${mac} -> ${hostname}`);
+    return reply.send({ status: "ok", mac, hostname });
+  });
+
   // Delete a machine from all state
   app.delete<{
     Params: { mac: string };
@@ -213,6 +246,10 @@ export function registerApiRoutes(
         delete s.installed[mac];
         found = true;
       }
+      if (s.debug[mac] !== undefined) {
+        delete s.debug[mac];
+        found = true;
+      }
     });
 
     if (!found) {

bastion/src/bastion/src/routes/dispatch.ts

@@ -10,9 +10,12 @@ import type { StateManager } from "../services/state.js";
 import {
   renderDiscoverIpxe,
   renderInstallIpxe,
+  renderDebugIpxe,
+  renderPxeBootDebugIpxe,
   renderLocalBootIpxe,
 } from "../templates/boot.ipxe.js";
 import { renderUbuntuInstallIpxe } from "../templates/ubuntu-boot.ipxe.js";
+import { renderDebugKickstart } from "../templates/debug.ks.js";
 import { logger } from "../services/logger.js";
 
 export function registerDispatchRoutes(
@@ -20,10 +23,76 @@ export function registerDispatchRoutes(
   config: BastionConfig,
   state: StateManager,
 ): void {
+  // Serve debug/rescue kickstart (minimal: SSH keys + network for inst.sshd)
+  app.get<{ Querystring: { mac?: string } }>("/debug.ks", async (_request, reply) => {
+    const ks = renderDebugKickstart({
+      sshKeys: config.sshKeys ?? [],
+      serverIp: config.serverIp,
+      httpPort: config.httpPort,
+    });
+    return reply.type("text/plain").send(ks);
+  });
+
+  // Shell script for manual debug setup (nc listener + IP reporting)
+  // Usage from rescue shell: curl http://bastion:port/debug-setup.sh | bash
+  app.get("/debug-setup.sh", async (_request, reply) => {
+    const script = `#!/bin/bash
+# Lab Bastion debug setup — run from rescue shell
+set -x
+
+IP_ADDR=$(ip -4 addr show | awk '/inet / && !/127.0.0/ {split($2,a,"/"); print a[1]; exit}')
+MAC_ADDR=$(ip link show | awk '/ether/ && !/00:00:00:00/ {print $2; exit}')
+
+# Start persistent nc listener for remote shell
+(while true; do nc -l -p 2323 -e /bin/bash 2>/dev/null; done) &
+echo "nc shell listener on port 2323"
+
+# Report IP to bastion
+curl -sf -X POST "http://${config.serverIp}:${config.httpPort}/api/progress" \\
+    -H "Content-Type: application/json" \\
+    -d "{\\"mac\\":\\"$MAC_ADDR\\",\\"stage\\":\\"debug-ready\\",\\"detail\\":\\"nc $IP_ADDR 2323\\"}" 2>/dev/null || true
+
+echo ""
+echo "=== Debug environment ready ==="
+echo "  nc $IP_ADDR 2323    (remote shell)"
+echo "  ssh root@$IP_ADDR   (password: debug)"
+echo "==============================="
+`;
+    return reply.type("text/plain").send(script);
+  });
+
   app.get<{ Querystring: { mac?: string } }>("/dispatch", async (request, reply) => {
     const mac = (request.query.mac ?? "").toLowerCase().replace(/-/g, ":");
     const currentState = state.load();
 
+    // Debug mode takes highest priority — auto-clear after serving once
+    const debugEntry = currentState.debug[mac];
+    if (debugEntry) {
+      const hostname = debugEntry.hostname ?? "debug";
+      state.update((s) => { delete s.debug[mac]; });
+
+      let script: string;
+      if (debugEntry.pxeBoot) {
+        logger.info(`PXE BOOT DEBUG: ${mac} -> ${hostname} (kernel+initrd from PXE, root from NVMe)`);
+        script = renderPxeBootDebugIpxe({
+          mac,
+          hostname,
+          serverIp: config.serverIp,
+          httpPort: config.httpPort,
+        });
+      } else {
+        logger.info(`DEBUG BOOT: ${mac} -> ${hostname} (rescue mode)`);
+        script = renderDebugIpxe({
+          mac,
+          hostname,
+          serverIp: config.serverIp,
+          httpPort: config.httpPort,
+          fedoraMirror: config.fedoraMirror,
+        });
+      }
+      return reply.type("text/plain").send(script);
+    }
+
     const queueEntry = currentState.install_queue[mac];
     if (queueEntry) {
       const hostname = queueEntry.hostname ?? "lab-node";

bastion/src/bastion/src/routes/kickstart.ts

@@ -5,6 +5,7 @@
 import type { FastifyInstance } from "fastify";
 import type { BastionConfig } from "@lab/shared";
 import type { StateManager } from "../services/state.js";
+import type { SyslogListener } from "../services/syslog-listener.js";
 import { generateInstallKickstart, generateDiscoverKickstart } from "../services/kickstart-generator.js";
 import { renderUbuntuAutoinstall, renderUbuntuMetaData, type UbuntuAutoinstallParams } from "../templates/ubuntu-autoinstall.js";
 
@@ -12,6 +13,7 @@ export function registerKickstartRoutes(
   app: FastifyInstance,
   config: BastionConfig,
   state: StateManager,
+  syslog: SyslogListener,
 ): void {
   // Per-MAC install kickstart
   app.get<{ Querystring: { mac?: string } }>("/ks", async (request, reply) => {
@@ -19,6 +21,11 @@ export function registerKickstartRoutes(
     const currentState = state.load();
     const queueEntry = currentState.install_queue[mac];
 
+    // Register IP → MAC so syslog listener can route Anaconda logs
+    if (mac) {
+      syslog.registerIp(request.ip, mac);
+    }
+
     const ks = generateInstallKickstart(config, {
       hostname: queueEntry?.hostname ?? "lab-node",
       disk: queueEntry?.disk ?? "",

bastion/src/bastion/src/server.ts

@@ -6,13 +6,14 @@ import { mkdirSync, existsSync } from "node:fs";
 import type { BastionConfig } from "@lab/shared";
 import { StateManager } from "./services/state.js";
 import { InstallLogBuffer } from "./services/install-log.js";
+import { SyslogListener } from "./services/syslog-listener.js";
 import { logger } from "./services/logger.js";
 import { registerDispatchRoutes } from "./routes/dispatch.js";
 import { registerKickstartRoutes } from "./routes/kickstart.js";
 import { registerApiRoutes } from "./routes/api.js";
 
 
-export function createApp(config: BastionConfig): { app: ReturnType<typeof Fastify>; state: StateManager; installLog: InstallLogBuffer } {
+export function createApp(config: BastionConfig): { app: ReturnType<typeof Fastify>; state: StateManager; installLog: InstallLogBuffer; syslog: SyslogListener } {
   const app = Fastify({
     logger: false, // We use winston instead
   });
@@ -21,6 +22,7 @@ export function createApp(config: BastionConfig): { app: ReturnType<typeof Fasti
   state.init();
 
   const installLog = new InstallLogBuffer(config.bastionDir);
+  const syslog = new SyslogListener(config.syslogPort, installLog, state);
 
   // Serve static files (vmlinuz, initrd.img, iPXE binaries) from the HTTP directory
   mkdirSync(config.httpDir, { recursive: true });
@@ -41,8 +43,8 @@ export function createApp(config: BastionConfig): { app: ReturnType<typeof Fasti
 
   // Register route handlers
   registerDispatchRoutes(app, config, state);
-  registerKickstartRoutes(app, config, state);
-  registerApiRoutes(app, state, installLog);
+  registerKickstartRoutes(app, config, state, syslog);
+  registerApiRoutes(app, state, installLog, syslog);
   // boot.iso is generated at startup and served as a static file from httpDir
   // (static serving supports HTTP Range requests, required by JetKVM streaming)
 
@@ -51,7 +53,7 @@ export function createApp(config: BastionConfig): { app: ReturnType<typeof Fasti
     logger.info(`HTTP: ${request.ip} ${request.method} ${request.url}`);
   });
 
-  return { app, state, installLog };
+  return { app, state, installLog, syslog };
 }
 
 export async function startServer(config: BastionConfig): Promise<void> {

bastion/src/bastion/src/services/kickstart-generator.ts

@@ -36,6 +36,7 @@ export function generateInstallKickstart(
     locale: config.locale,
     serverIp: config.serverIp,
     httpPort: config.httpPort,
+    syslogPort: config.syslogPort,
     sshKeys: config.sshKeys,
     adminUser: config.adminUser,
   };

bastion/src/bastion/src/services/labd-connection.ts

@@ -164,6 +164,7 @@ export class BastionConnection {
       case "command-install":
       case "command-forget":
       case "command-role-update":
+      case "command-debug":
         void this.handleCommand(msg);
         break;
     }

bastion/src/bastion/src/services/state.ts

@@ -11,6 +11,7 @@ const EMPTY_STATE: BastionState = {
   discovered: {},
   install_queue: {},
   installed: {},
+  debug: {},
 };
 
 export type StateChangeListener = (state: BastionState) => void;
@@ -33,6 +34,7 @@ export class StateManager {
         discovered: parsed.discovered ?? {},
         install_queue: parsed.install_queue ?? {},
         installed: parsed.installed ?? {},
+        debug: parsed.debug ?? {},
       };
     } catch {
       return { ...EMPTY_STATE };

bastion/src/bastion/src/services/syslog-listener.ts

@@ -0,0 +1,108 @@
+// UDP syslog listener for receiving Anaconda install logs.
+// Anaconda's `logging --host` sends RFC 3164 syslog over UDP.
+// We parse the messages and route them to InstallLogBuffer.
+
+import { createSocket, type Socket } from "node:dgram";
+import type { InstallLogBuffer } from "./install-log.js";
+import type { StateManager } from "./state.js";
+import { logger } from "./logger.js";
+
+/**
+ * Parse a BSD syslog (RFC 3164) message.
+ * Format: <PRI>TIMESTAMP HOSTNAME APP[PID]: MESSAGE
+ * Anaconda messages look like: <13>Mar 28 19:32:01 anaconda[1234]: some message
+ */
+function parseSyslogLine(raw: string): { program: string; message: string } {
+  // Strip priority: <NN>
+  const noPri = raw.replace(/^<\d+>/, "");
+  // Try to extract program and message after the timestamp + hostname
+  // RFC 3164: "Mon DD HH:MM:SS HOSTNAME PROGRAM[PID]: MESSAGE"
+  const match = noPri.match(/^\w+\s+\d+\s+[\d:]+\s+\S+\s+(\S+?)(?:\[\d+\])?:\s*(.*)/);
+  if (match?.[1] && match[2] !== undefined) {
+    return { program: match[1], message: match[2] };
+  }
+  // Fallback: just return the whole line
+  return { program: "unknown", message: noPri.trim() };
+}
+
+export class SyslogListener {
+  private socket: Socket | null = null;
+  private port: number;
+  private installLog: InstallLogBuffer;
+  private state: StateManager;
+  /** Explicit IP → MAC mapping registered from kickstart/progress requests. */
+  private ipToMac = new Map<string, string>();
+
+  constructor(port: number, installLog: InstallLogBuffer, state: StateManager) {
+    this.port = port;
+    this.installLog = installLog;
+    this.state = state;
+  }
+
+  /** Register an IP → MAC mapping (called when we learn a machine's IP). */
+  registerIp(ip: string, mac: string): void {
+    this.ipToMac.set(ip, mac.toLowerCase());
+  }
+
+  /** Resolve a source IP to a MAC address. */
+  private resolveIpToMac(ip: string): string | null {
+    // Check explicit mapping first (most reliable)
+    const explicit = this.ipToMac.get(ip);
+    if (explicit) return explicit;
+
+    const currentState = this.state.load();
+
+    // Check install queue — machines being installed have an IP from DHCP
+    for (const [mac, entry] of Object.entries(currentState.install_queue)) {
+      if (entry.progress_detail?.includes(ip)) return mac;
+    }
+
+    // Check installed machines
+    for (const [mac, info] of Object.entries(currentState.installed)) {
+      if (info.ip === ip) return mac;
+    }
+
+    return null;
+  }
+
+  /** Resolve a MAC to the hostname from install queue or installed state. */
+  private resolveHostname(mac: string): string {
+    const s = this.state.load();
+    return s.install_queue[mac]?.hostname ?? s.installed[mac]?.hostname ?? mac;
+  }
+
+  start(): void {
+    this.socket = createSocket("udp4");
+
+    this.socket.on("message", (msg, rinfo) => {
+      const raw = msg.toString("utf-8").trim();
+      if (!raw) return;
+
+      const { program, message } = parseSyslogLine(raw);
+      const mac = this.resolveIpToMac(rinfo.address);
+
+      if (mac) {
+        const hostname = this.resolveHostname(mac);
+        const line = program !== "unknown" ? `[${program}] ${message}` : message;
+        this.installLog.append(mac, [line], hostname);
+      }
+      // If we can't resolve the IP, we still log it for debugging
+      // but don't store it in the install log buffer
+    });
+
+    this.socket.on("error", (err) => {
+      logger.error(`Syslog listener error: ${err.message}`);
+    });
+
+    this.socket.bind(this.port, "0.0.0.0", () => {
+      logger.info(`Syslog listener on UDP :${this.port}`);
+    });
+  }
+
+  stop(): void {
+    if (this.socket) {
+      this.socket.close();
+      this.socket = null;
+    }
+  }
+}

bastion/src/bastion/src/templates/boot.ipxe.ts

@@ -42,7 +42,7 @@ echo   Collecting hardware info...
 echo =============================================
 echo
 
-kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.ks=http://${params.serverIp}:${params.httpPort}/discover.ks inst.stage2=${params.fedoraMirror} inst.text
+kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.ks=http://${params.serverIp}:${params.httpPort}/discover.ks inst.stage2=${params.fedoraMirror} inst.text nomodeset
 initrd http://${params.serverIp}:${params.httpPort}/initrd.img
 boot
 `;
@@ -69,7 +69,62 @@ echo   MAC:    ${params.mac}
 echo =============================================
 echo
 
-kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.ks=http://${params.serverIp}:${params.httpPort}/ks?mac=${params.mac} inst.repo=${params.fedoraMirror} inst.text
+kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.ks=http://${params.serverIp}:${params.httpPort}/ks?mac=${params.mac} inst.repo=${params.fedoraMirror} inst.text nomodeset
+initrd http://${params.serverIp}:${params.httpPort}/initrd.img
+boot
+`;
+}
+
+/**
+ * iPXE script for debug/rescue mode -- boots Fedora installer in rescue mode.
+ * Provides a shell with LVM tools, network, and SSH for inspecting installed systems.
+ */
+export function renderDebugIpxe(params: {
+  mac: string;
+  hostname: string;
+  serverIp: string;
+  httpPort: number;
+  fedoraMirror: string;
+}): string {
+  return `#!ipxe
+
+echo
+echo =============================================
+echo   Lab PXE Bastion - DEBUG/RESCUE MODE
+echo   Target: ${params.hostname}
+echo   MAC:    ${params.mac}
+echo =============================================
+echo
+
+kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.rescue inst.text inst.sshd inst.ks=http://${params.serverIp}:${params.httpPort}/debug.ks?mac=${params.mac} inst.stage2=${params.fedoraMirror}
+initrd http://${params.serverIp}:${params.httpPort}/initrd.img
+boot
+`;
+}
+
+/**
+ * iPXE script for PXE-boot debug mode -- boots the installed system's root
+ * filesystem using the bastion's PXE kernel+initrd instead of local GRUB.
+ * Workaround for UEFI firmware bugs that make local disk boot slow.
+ */
+export function renderPxeBootDebugIpxe(params: {
+  mac: string;
+  hostname: string;
+  serverIp: string;
+  httpPort: number;
+}): string {
+  return `#!ipxe
+
+echo
+echo =============================================
+echo   Lab PXE Bastion - PXE BOOT (debug)
+echo   Target: ${params.hostname}
+echo   MAC:    ${params.mac}
+echo   Kernel+initrd from PXE, root from NVMe
+echo =============================================
+echo
+
+kernel http://${params.serverIp}:${params.httpPort}/vmlinuz root=/dev/mapper/labvg-root ro rd.lvm.lv=labvg/root rd.lvm.lv=labvg/swap console=tty0
 initrd http://${params.serverIp}:${params.httpPort}/initrd.img
 boot
 `;
@@ -88,6 +143,6 @@ echo   Already installed, booting from local disk
 echo =============================================
 echo
 sleep 3
-exit
+exit 1
 `;
 }

bastion/src/bastion/src/templates/debug.ks.ts

@@ -0,0 +1,33 @@
+// Debug/rescue kickstart template.
+// Minimal kickstart for Anaconda rescue mode.
+//
+// SSH access: Anaconda's inst.sshd starts sshd automatically.
+// The sshpw directive sets the password, sshkey adds authorized keys.
+// %pre/%post do NOT run in rescue mode — don't put setup code there.
+
+export interface DebugKickstartParams {
+  sshKeys: string[];
+  serverIp?: string;
+  httpPort?: number;
+}
+
+export function renderDebugKickstart(params: DebugKickstartParams): string {
+  const sshkeyLine = params.sshKeys.length > 0
+    ? `sshkey --username=root "${params.sshKeys[0]}"`
+    : "";
+
+  return `# Lab Bastion -- Debug/Rescue Kickstart
+# Minimal: SSH + network for Anaconda rescue mode
+#
+# SSH is started by Anaconda (inst.sshd kernel param).
+# Password: debug  |  SSH keys from bastion config.
+# %pre/%post do NOT run in rescue mode.
+
+lang en_US.UTF-8
+keyboard uk
+network --bootproto=dhcp --activate
+
+sshpw --username=root --plaintext debug
+${sshkeyLine}
+`;
+}

bastion/src/bastion/src/templates/dnsmasq.conf.ts

@@ -88,6 +88,9 @@ pxe-service=tag:!ipxe,ARM64_EFI,"PXE Boot",ipxe-arm64.efi` : `# Full DHCP mode -
 # Discovery protocol which some UEFI implementations don't support). The dhcp-boot
 # directives above provide the boot filename directly in the DHCP offer.`}
 
+# Lease file in bastion directory (avoid default /var/lib/dnsmasq which needs root)
+dhcp-leasefile=${config.bastionDir}/dnsmasq.leases
+
 # Verbose logging
 log-dhcp
 `;

bastion/src/bastion/src/templates/install.ks.ts

@@ -14,6 +14,7 @@ export interface InstallKickstartParams {
   locale: string;
   serverIp: string;
   httpPort: number;
+  syslogPort: number;
   sshKeys: string[];
   adminUser: string;
 }
@@ -29,6 +30,7 @@ export function renderInstallKickstart(params: InstallKickstartParams): string {
     locale,
     serverIp,
     httpPort,
+    syslogPort,
     sshKeys,
     adminUser,
   } = params;
@@ -41,9 +43,10 @@ export function renderInstallKickstart(params: InstallKickstartParams): string {
   const isVanilla = role === "vanilla";
 
   // -- Auth section --
+  // Always set a root password (for serial console debugging) + SSH keys
   const auth = sshKeys.length > 0
-    ? `rootpw --lock\nsshkey --username=root "${sshKeys[0]}"`
-    : "rootpw --plaintext changeme";
+    ? `rootpw --plaintext lab-root-pw\nsshkey --username=root "${sshKeys[0]}"`
+    : "rootpw --plaintext lab-root-pw";
 
   // -- Admin user directive --
   const userDirective = adminUser
@@ -85,8 +88,23 @@ chmod 440 /etc/sudoers.d/${adminUser}`;
   const diskLine = disk
     ? `DISK="${disk}"`
     : `DISK=""
-for d in /dev/nvme0n1 /dev/sda /dev/vda; do
-    [ -b "$d" ] && { DISK="$(basename $d)"; break; }
+# Wait up to 10s for NVMe/SCSI disks to appear (they init async in initrd)
+for _wait in $(seq 1 10); do
+    for d in /dev/nvme0n1 /dev/nvme1n1 /dev/sda /dev/sdb /dev/vda; do
+        [ -b "$d" ] || continue
+        _bname=$(basename "$d")
+        # Skip removable disks (USB, CD-ROM, JetKVM virtual media)
+        [ -f "/sys/block/$_bname/removable" ] && [ "$(cat /sys/block/$_bname/removable)" = "1" ] && continue
+        # Skip USB-attached disks (JetKVM virtual media shows as SCSI over USB)
+        _transport=$(readlink -f /sys/block/$_bname/device 2>/dev/null || echo "")
+        echo "$_transport" | grep -q "usb" && continue
+        # Skip disks smaller than 20GB (likely USB sticks)
+        _size=$(cat /sys/block/$_bname/size 2>/dev/null || echo 0)
+        [ "$_size" -lt 41943040 ] && continue
+        DISK="$_bname"
+        break 2
+    done
+    sleep 1
 done
 [ -z "$DISK" ] && { echo "ERROR: no disk found"; exit 1; }`;
 
@@ -100,48 +118,6 @@ done
     ? `logvol /var/lib/rancher --vgname=${vg} --name=rancher --fstype=xfs --size=20480`
     : "";
 
-  // Helper: the bastion callback functions used in both %pre and %post.
-  // Defined as a template so each section gets its own copy (they run in different shells).
-  const bastionHelpers = `
-# Detect MAC address (first real ethernet MAC, skip loopback/veth)
-_BASTION_MAC=$(ip link show | awk '/ether/ && !/00:00:00:00/ {print $2; exit}')
-_BASTION_URL="http://${serverIp}:${httpPort}"
-
-# Send a structured progress stage to bastion
-bastion_progress() {
-    local stage="$1" detail="\${2:-}"
-    curl -sf -X POST "\${_BASTION_URL}/api/progress" \\
-        -H "Content-Type: application/json" \\
-        -d "{\\"mac\\":\\"$_BASTION_MAC\\",\\"stage\\":\\"$stage\\",\\"detail\\":\\"$detail\\"}" \\
-        --connect-timeout 5 --max-time 10 2>/dev/null || true
-}
-
-# Send log lines to bastion (batched)
-bastion_log() {
-    local line="$1"
-    curl -sf -X POST "\${_BASTION_URL}/api/log" \\
-        -H "Content-Type: application/json" \\
-        -d "{\\"mac\\":\\"$_BASTION_MAC\\",\\"line\\":\\"$(echo "$line" | sed 's/\\\\/\\\\\\\\/g; s/"/\\\\"/g')\\"}\" \\
-        --connect-timeout 5 --max-time 10 2>/dev/null || true
-}
-
-# Send an error stage to bastion with context
-bastion_error() {
-    local detail="$1"
-    bastion_progress "error" "$detail"
-    # Also send the last 50 lines of any log file as context
-    for logfile in /root/bastion-post-install.log /tmp/pre-partition.log; do
-        if [ -f "$logfile" ]; then
-            local tail_content
-            tail_content=$(tail -50 "$logfile" 2>/dev/null | sed 's/\\\\/\\\\\\\\/g; s/"/\\\\"/g; s/$/\\\\n/' | tr -d '\\n')
-            curl -sf -X POST "\${_BASTION_URL}/api/log" \\
-                -H "Content-Type: application/json" \\
-                -d "{\\"mac\\":\\"$_BASTION_MAC\\",\\"lines\\":[\\"--- $logfile (last 50 lines) ---\\"],\\"tail\\":\\"$tail_content\\"}" \\
-                --connect-timeout 5 --max-time 10 2>/dev/null || true
-        fi
-    done
-}`;
-
   return `# Lab Bastion -- Fedora ${fedoraVersion} server install
 # Generated: ${now}
 # Target: ${fqdn} (role=${role})
@@ -158,7 +134,9 @@ network --bootproto=dhcp --activate --hostname=${fqdn}
 ${auth}
 ${userDirective}
 
-bootloader --append="console=tty0 console=ttyS0,115200n8"
+bootloader --append="console=tty0"
+
+logging --host=${serverIp} --port=${syslogPort}
 
 url --mirrorlist=https://mirrors.fedoraproject.org/mirrorlist?repo=fedora-$releasever&arch=$basearch
 
@@ -168,25 +146,27 @@ url --mirrorlist=https://mirrors.fedoraproject.org/mirrorlist?repo=fedora-$relea
 %pre --log=/tmp/pre-partition.log
 #!/bin/bash
 set -x
-${bastionHelpers}
 
-# Error trap: report failures back to bastion
-trap 'bastion_error "%pre failed at line $LINENO: $(tail -1 /tmp/pre-partition.log 2>/dev/null)"' ERR
+# Progress callback helper
+bastion_progress() {
+    local stage="$1" detail="\${2:-}"
+    local mac=$(ip link show | awk '/ether/ && !/00:00:00:00/ {print $2; exit}')
+    curl -sf -X POST "http://${serverIp}:${httpPort}/api/progress" \\
+        -H "Content-Type: application/json" \\
+        -d "{\\"mac\\":\\"$mac\\",\\"stage\\":\\"$stage\\",\\"detail\\":\\"$detail\\"}" 2>/dev/null || true
+}
 
 bastion_progress "partitioning" "detecting disk"
 
 VG="${vg}"
 ${diskLine}
 
-bastion_log "disk detected: $DISK"
-
 REPROVISION=no
 
 # Check if VG exists (reprovision scenario)
 if vgs $VG &>/dev/null; then
     echo "=== Existing VG found - reprovision mode ==="
     REPROVISION=yes
-    bastion_progress "partitioning" "reprovision mode -- preserving data volumes"
 
     # Detect which data LVs to preserve
     PRESERVE_LONGHORN=no; PRESERVE_SRV=no; PRESERVE_HOME=no; PRESERVE_RANCHER=no
@@ -196,7 +176,6 @@ if vgs $VG &>/dev/null; then
     lvs $VG/rancher  &>/dev/null && PRESERVE_RANCHER=yes
 
     echo "Preserving: longhorn=$PRESERVE_LONGHORN srv=$PRESERVE_SRV home=$PRESERVE_HOME rancher=$PRESERVE_RANCHER"
-    bastion_log "preserving LVs: longhorn=$PRESERVE_LONGHORN srv=$PRESERVE_SRV home=$PRESERVE_HOME rancher=$PRESERVE_RANCHER"
 
     # Remove only OS logical volumes (keep data LVs)
     for lv in root var varlog swap; do
@@ -273,7 +252,6 @@ cat /tmp/part.ks
 echo "==================================="
 
 bastion_progress "partitioning" "disk layout ready"
-bastion_log "partition config written to /tmp/part.ks"
 
 %end
 
@@ -333,91 +311,37 @@ ruby-libs
 %post --log=/root/bastion-post-install.log
 #!/bin/bash
 set -x
-${bastionHelpers}
 
-# --- Error trap: catch any failure and report to bastion ---
-_post_error_handler() {
-    local exit_code=$? lineno=$1
-    bastion_error "%post failed at line $lineno (exit $exit_code)"
-}
-trap '_post_error_handler $LINENO' ERR
-
-# --- Background log streamer: sends %post output to bastion in real-time ---
-_LOG_FILE=/root/bastion-post-install.log
-_LOG_STREAMER_PID=""
-(
-    # Wait for the log file to exist
-    while [ ! -f "$_LOG_FILE" ]; do sleep 1; done
-    # Tail and batch-send lines every 3 seconds
-    _batch=""
-    _count=0
-    tail -f "$_LOG_FILE" 2>/dev/null | while IFS= read -r _line; do
-        # Escape for JSON
-        _escaped=$(echo "$_line" | sed 's/\\\\/\\\\\\\\/g; s/"/\\\\"/g; s/\\t/\\\\t/g')
-        if [ -z "$_batch" ]; then
-            _batch="\\"$_escaped\\""
-        else
-            _batch="$_batch,\\"$_escaped\\""
-        fi
-        _count=$((_count + 1))
-        # Send batch every 10 lines
-        if [ "$_count" -ge 10 ]; then
-            curl -sf -X POST "\${_BASTION_URL}/api/log" \\
-                -H "Content-Type: application/json" \\
-                -d "{\\"mac\\":\\"$_BASTION_MAC\\",\\"lines\\":[$_batch]}" \\
-                --connect-timeout 5 --max-time 10 2>/dev/null || true
-            _batch=""
-            _count=0
-        fi
-    done
-) &
-_LOG_STREAMER_PID=$!
-
-# Flush remaining log lines helper
-_flush_log_streamer() {
-    if [ -n "$_LOG_STREAMER_PID" ]; then
-        kill "$_LOG_STREAMER_PID" 2>/dev/null || true
-        wait "$_LOG_STREAMER_PID" 2>/dev/null || true
-    fi
-    # Send any remaining lines from the log
-    if [ -f "$_LOG_FILE" ]; then
-        local remaining
-        remaining=$(tail -20 "$_LOG_FILE" 2>/dev/null | sed 's/\\\\/\\\\\\\\/g; s/"/\\\\"/g; s/\\t/\\\\t/g; s/^/"/; s/$/"/' | paste -sd, -)
-        if [ -n "$remaining" ]; then
-            curl -sf -X POST "\${_BASTION_URL}/api/log" \\
-                -H "Content-Type: application/json" \\
-                -d "{\\"mac\\":\\"$_BASTION_MAC\\",\\"lines\\":[$remaining]}" \\
-                --connect-timeout 5 --max-time 10 2>/dev/null || true
-        fi
-    fi
+# Progress callback helper
+bastion_progress() {
+    local stage="$1" detail="\${2:-}"
+    local mac=$(ip link show | awk '/ether/ && !/00:00:00:00/ {print $2; exit}')
+    curl -sf -X POST "http://${serverIp}:${httpPort}/api/progress" \\
+        -H "Content-Type: application/json" \\
+        -d "{\\"mac\\":\\"$mac\\",\\"stage\\":\\"$stage\\",\\"detail\\":\\"$detail\\"}" 2>/dev/null || true
 }
 
-bastion_progress "installing" "packages installed, starting post-install"
+
+bastion_progress "post-install" "configuring system"
 
 # -- SSH --
-bastion_progress "post-install" "configuring SSH"
-systemctl enable --now sshd
+# Note: only 'enable', not '--now' — systemd is not running in the Anaconda chroot
+systemctl enable sshd || true
 sed -i 's/^#\\?PermitRootLogin.*/PermitRootLogin prohibit-password/' /etc/ssh/sshd_config
 sed -i 's/^#\\?PasswordAuthentication.*/PasswordAuthentication no/' /etc/ssh/sshd_config
 ${sshPostBlock}
-bastion_log "SSH configured: root login by key only, password auth disabled"
 
-# -- Hostname and domain --
-bastion_progress "post-install" "setting hostname to ${fqdn}"
-hostnamectl set-hostname ${fqdn}
+bastion_progress "post-install" "1-ssh done"
+
+# -- Hostname and domain (write directly, hostnamectl needs D-Bus) --
+echo "${fqdn}" > /etc/hostname
 
 # -- tmpfs for /tmp --
 echo "tmpfs /tmp tmpfs defaults,noatime,nosuid,nodev,size=4G 0 0" >> /etc/fstab
 
-# Make /boot/efi mount non-fatal (prevents emergency mode if EFI partition isn't found)
-sed -i '/boot\\/efi/ s/defaults/defaults,nofail/' /etc/fstab
-bastion_log "fstab /boot/efi set to nofail"
-
 ${isVanilla ? `# -- vanilla role: skip k3s kernel/sysctl/firewall setup --
-bastion_progress "post-install" "vanilla role -- skipping k3s setup"
 # -- Enable chronyd for time sync --
 systemctl enable chronyd || true` : `# -- Kernel modules for k3s --
-bastion_progress "post-install" "loading k3s kernel modules"
 cat > /etc/modules-load.d/k3s.conf << 'MODULES'
 br_netfilter
 overlay
@@ -427,7 +351,6 @@ modprobe br_netfilter || true
 modprobe overlay || true
 
 # -- Sysctl for k3s networking --
-bastion_progress "post-install" "configuring k3s sysctl"
 cat > /etc/sysctl.d/90-k3s.conf << 'SYSCTL'
 net.bridge.bridge-nf-call-iptables  = 1
 net.bridge.bridge-nf-call-ip6tables = 1
@@ -439,48 +362,38 @@ SYSCTL
 sysctl --system || true
 
 # -- Disable firewalld permanently (k3s/Cilium manage iptables directly) --
-bastion_progress "post-install" "disabling firewalld"
-# Must be masked to prevent re-enable on updates
-systemctl disable --now firewalld || true
+# Note: no '--now' — systemd is not running in the Anaconda chroot
+systemctl disable firewalld || true
 systemctl mask firewalld || true
 
 # -- Enable chronyd for time sync --
 systemctl enable chronyd || true`}
 
-# -- Serial console (for debugging — auto-login as root on ttyS0) --
-systemctl enable serial-getty@ttyS0.service || true
+bastion_progress "post-install" "2-system done"
 
 # -- Boot order: restore network first (Anaconda sets disk first, we undo it) --
-# Network boot must stay first so the bastion intercepts every reboot. It returns
-# exit (local disk) for installed machines, or install for reinstalls.
-bastion_progress "post-install" "restoring network-first boot order"
+# Network boot must stay first so the bastion intercepts every reboot.
 if command -v efibootmgr >/dev/null 2>&1; then
-    # Find network/PXE/HTTP boot entries (OVMF uses HTTPv4, real hardware uses PXE/Network)
     PXE_ENTRY=$(efibootmgr | grep -iE 'network|pxe|ipv4|ipv6|http' | head -1 | grep -oP 'Boot\\K[0-9A-F]+')
     if [ -n "$PXE_ENTRY" ]; then
         CURRENT_ORDER=$(efibootmgr | grep BootOrder | cut -d: -f2 | tr -d ' ')
-        # Move PXE entry to front
         REST=$(echo "$CURRENT_ORDER" | sed "s/$PXE_ENTRY,\\\\?//;s/,$//" | sed 's/^,//')
         NEW_ORDER="$PXE_ENTRY,$REST"
         efibootmgr -o "$NEW_ORDER" || true
-        bastion_log "boot order set: network first ($NEW_ORDER)"
-    else
-        bastion_log "no PXE boot entry found, boot order unchanged"
     fi
-else
-    bastion_log "efibootmgr not available"
 fi
 
-# -- Provisioning metadata --
-bastion_progress "post-install" "writing provisioning metadata"
-IP_ADDR=$(ip -4 addr show | awk '/inet / && !/127.0.0/ {split($2,a,"/"); print a[1]; exit}')
+bastion_progress "post-install" "3-bootorder done"
 
+# -- Enable SysRq magic keys (for emergency reboot via Alt+SysRq+REISUB) --
+echo "kernel.sysrq=1" > /etc/sysctl.d/90-sysrq.conf
+
+# -- Provisioning metadata --
 cat > /etc/lab-provisioned << PROVEOF
 hostname: ${fqdn}
 role: ${role}
 provisioned: $(date -Iseconds)
 bastion: ${serverIp}
-ip: $IP_ADDR
 PROVEOF
 
 cat > /root/README << 'README'
@@ -498,13 +411,11 @@ cat > /root/README << 'README'
 README
 
 ${hasRancher ? `# Install k3s server (skip start - will be configured manually)
-bastion_progress "post-install" "pre-installing k3s server"
 curl -sfL https://get.k3s.io | INSTALL_K3S_SKIP_START=true sh -
-bastion_log "k3s server pre-installed (not started)"
 ` : ""}
-# Stop log streamer and flush remaining lines
-_flush_log_streamer
+bastion_progress "post-install" "4-metadata done"
 
+IP_ADDR=$(ip -4 addr show | awk '/inet / && !/127.0.0/ {split($2,a,"/"); print a[1]; exit}')
 bastion_progress "complete" "ready at $IP_ADDR"
 
 %end

bastion/src/bastion/tests/dispatch.test.ts

@@ -28,6 +28,7 @@ function createTestConfig(testDir: string): BastionConfig {
     gateway: "10.0.0.1",
     sshKeys: ["ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAITEST test@test"],
     adminUser: "testadmin",
+    syslogPort: 15514,
     skipDnsmasq: true,
     skipArtifacts: true,
     fedoraMirror: "https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os",

bastion/src/bastion/tests/kickstart.test.ts

@@ -12,6 +12,7 @@ function baseParams(overrides: Partial<InstallKickstartParams> = {}): InstallKic
     locale: "en_GB.UTF-8",
     serverIp: "192.168.1.100",
     httpPort: 8080,
+    syslogPort: 5514,
     sshKeys: [
       "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAITEST1 user1@host",
       "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQTEST2 user2@host",
@@ -91,9 +92,8 @@ describe("renderInstallKickstart", () => {
       serverIp: "10.0.0.5",
       httpPort: 9090,
     }));
-    expect(ks).toContain('_BASTION_URL="http://10.0.0.5:9090"');
+    expect(ks).toContain("http://10.0.0.5:9090");
     expect(ks).toContain("/api/progress");
-    expect(ks).toContain("/api/log");
   });
 
   it("infra role has /var/lib/rancher partition", () => {
@@ -141,51 +141,73 @@ describe("renderInstallKickstart", () => {
     expect(ks).toContain("--name=swap --fstype=swap --size=27648");
   });
 
-  it("%pre has error trap", () => {
-    const ks = renderInstallKickstart(baseParams());
-    expect(ks).toContain("trap");
-    expect(ks).toContain("bastion_error");
-    expect(ks).toContain("%pre failed");
-  });
-
-  it("%post has error trap", () => {
-    const ks = renderInstallKickstart(baseParams());
-    expect(ks).toContain("_post_error_handler");
-    expect(ks).toContain("%post failed");
-  });
-
-  it("has granular progress stages in %post", () => {
-    const ks = renderInstallKickstart(baseParams());
-    expect(ks).toContain('"configuring SSH"');
-    expect(ks).toContain('"setting hostname');
-    expect(ks).toContain('"writing provisioning metadata"');
-    expect(ks).toContain('"writing provisioning metadata"');
-  });
-
-  it("has background log streamer in %post", () => {
-    const ks = renderInstallKickstart(baseParams());
-    expect(ks).toContain("_LOG_STREAMER_PID");
-    expect(ks).toContain("_flush_log_streamer");
-    expect(ks).toContain("tail -f");
-  });
-
-  it("has bastion_log function for sending log lines", () => {
-    const ks = renderInstallKickstart(baseParams());
-    expect(ks).toContain("bastion_log()");
-    expect(ks).toContain("/api/log");
-  });
-
-  it("vanilla role skips k3s progress stages", () => {
+  it("vanilla role skips k3s setup", () => {
     const ks = renderInstallKickstart(baseParams({ role: "vanilla" }));
     expect(ks).toContain("vanilla role");
-    expect(ks).not.toContain('"loading k3s kernel modules"');
-    expect(ks).not.toContain('"disabling firewalld"');
+    expect(ks).not.toContain("modules-load.d/k3s.conf");
+    expect(ks).not.toContain("firewalld");
   });
 
-  it("worker role has k3s-related progress stages", () => {
+  it("worker role has k3s setup", () => {
     const ks = renderInstallKickstart(baseParams({ role: "worker" }));
-    expect(ks).toContain('"loading k3s kernel modules"');
-    expect(ks).toContain('"configuring k3s sysctl"');
-    expect(ks).toContain('"disabling firewalld"');
+    expect(ks).toContain("modules-load.d/k3s.conf");
+    expect(ks).toContain("sysctl.d/90-k3s.conf");
+    expect(ks).toContain("firewalld");
+  });
+
+  it("kickstart syntax: no merged partition lines", () => {
+    for (const role of ["vanilla", "worker", "infra"] as const) {
+      const ks = renderInstallKickstart(baseParams({ role }));
+      const lines = ks.split("\n");
+      for (let i = 0; i < lines.length; i++) {
+        const l = lines[i].trim();
+        if (l.startsWith("part ")) {
+          const partCount = (l.match(/\bpart\b/g) || []).length;
+          expect(partCount, `line ${i + 1} has ${partCount} 'part' commands (role=${role}): ${l}`).toBe(1);
+        }
+      }
+    }
+  });
+
+  it("kickstart syntax: each section-opening has a %end", () => {
+    const ks = renderInstallKickstart(baseParams());
+    // Only match section openers at start of line
+    const sections = (ks.match(/^%(?:pre|post|packages)\b/gm) || []).length;
+    const ends = (ks.match(/^%end$/gm) || []).length;
+    expect(ends, `${sections} sections but ${ends} %end markers`).toBe(sections);
+  });
+
+  it("has complete progress stage", () => {
+    const ks = renderInstallKickstart(baseParams());
+    expect(ks).toContain('"complete"');
+    expect(ks).toContain("ready at");
+  });
+
+  it("sends install logs to bastion via syslog", () => {
+    const ks = renderInstallKickstart(baseParams({ syslogPort: 5514 }));
+    expect(ks).toContain("logging --host=192.168.1.100 --port=5514");
+  });
+
+  it("passes ksvalidator syntax check", () => {
+    for (const role of ["vanilla", "worker", "infra"] as const) {
+      const ks = renderInstallKickstart(baseParams({ role }));
+      const { execSync } = require("node:child_process");
+      const { writeFileSync, unlinkSync } = require("node:fs");
+      const tmp = `/tmp/ks-test-${role}.ks`;
+      writeFileSync(tmp, ks);
+      try {
+        execSync(`ksvalidator -v F43 ${tmp}`, { encoding: "utf-8" });
+      } catch (err: unknown) {
+        const msg = err instanceof Error ? (err as { stderr?: string }).stderr ?? err.message : String(err);
+        throw new Error(`ksvalidator failed for role=${role}: ${msg}`);
+      } finally {
+        try { unlinkSync(tmp); } catch {}
+      }
+    }
+  });
+
+  it("does not include serial console (causes 30s boot timeout on hardware without UART)", () => {
+    const ks = renderInstallKickstart(baseParams({ role: "vanilla" }));
+    expect(ks).not.toContain("ttyS0");
   });
 });

bastion/src/bastion/tests/state.test.ts

@@ -26,6 +26,7 @@ describe("StateManager", () => {
       discovered: {},
       install_queue: {},
       installed: {},
+      debug: {},
     });
   });
 
@@ -39,6 +40,7 @@ describe("StateManager", () => {
       discovered: {},
       install_queue: {},
       installed: {},
+      debug: {},
     });
   });
 

bastion/src/bastion/tests/syslog-listener.test.ts

@@ -0,0 +1,121 @@
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { createSocket } from "node:dgram";
+import { mkdtempSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { SyslogListener } from "../src/services/syslog-listener.js";
+import { InstallLogBuffer } from "../src/services/install-log.js";
+import { StateManager } from "../src/services/state.js";
+
+function sendUdpSyslog(port: number, message: string): Promise<void> {
+  return new Promise((resolve, reject) => {
+    const client = createSocket("udp4");
+    const buf = Buffer.from(message);
+    client.send(buf, 0, buf.length, port, "127.0.0.1", (err) => {
+      client.close();
+      if (err) reject(err);
+      else resolve();
+    });
+  });
+}
+
+describe("SyslogListener", () => {
+  let tmpDir: string;
+  let state: StateManager;
+  let installLog: InstallLogBuffer;
+  let syslog: SyslogListener;
+  const PORT = 15514; // use non-privileged port for testing
+
+  beforeEach(() => {
+    tmpDir = mkdtempSync(join(tmpdir(), "syslog-test-"));
+    state = new StateManager(join(tmpDir, "state.json"));
+    state.init();
+    installLog = new InstallLogBuffer(tmpDir);
+    syslog = new SyslogListener(PORT, installLog, state);
+    syslog.start();
+  });
+
+  afterEach(() => {
+    syslog.stop();
+    rmSync(tmpDir, { recursive: true, force: true });
+  });
+
+  it("receives and stores syslog messages for registered IP", async () => {
+    const mac = "aa:bb:cc:dd:ee:ff";
+    // Queue a machine so hostname can be resolved
+    state.update((s) => {
+      s.install_queue[mac] = {
+        hostname: "testnode",
+        disk: "/dev/sda",
+        role: "worker",
+        os: "fedora-43",
+        queued_at: new Date().toISOString(),
+      };
+    });
+
+    // Register IP → MAC mapping
+    syslog.registerIp("127.0.0.1", mac);
+
+    // Send a syslog message (RFC 3164 format)
+    await sendUdpSyslog(PORT, "<13>Mar 30 01:30:00 localhost anaconda[1234]: Installing package vim-enhanced");
+
+    // Wait for UDP delivery
+    await new Promise((r) => setTimeout(r, 200));
+
+    const lines = installLog.getLines(mac);
+    expect(lines.length).toBeGreaterThan(0);
+    expect(lines[0]!.line).toContain("anaconda");
+    expect(lines[0]!.line).toContain("Installing package vim-enhanced");
+  });
+
+  it("ignores messages from unknown IPs", async () => {
+    // Don't register any IP mapping
+    await sendUdpSyslog(PORT, "<13>Mar 30 01:30:00 localhost anaconda[1234]: test message");
+    await new Promise((r) => setTimeout(r, 200));
+
+    // No MAC to check, but the listener should not crash
+    // and no logs should be stored for any MAC
+    expect(installLog.lineCount("unknown")).toBe(0);
+  });
+
+  it("resolves IP from installed machines state", async () => {
+    const mac = "11:22:33:44:55:66";
+    state.update((s) => {
+      s.installed[mac] = {
+        hostname: "installed-node",
+        role: "worker",
+        ip: "127.0.0.1",
+        installed_at: new Date().toISOString(),
+      };
+    });
+
+    await sendUdpSyslog(PORT, "<14>Mar 30 02:00:00 installed-node sshd[5678]: Accepted publickey for root");
+    await new Promise((r) => setTimeout(r, 200));
+
+    const lines = installLog.getLines(mac);
+    expect(lines.length).toBeGreaterThan(0);
+    expect(lines[0]!.line).toContain("sshd");
+  });
+
+  it("parses various syslog formats", async () => {
+    const mac = "aa:bb:cc:dd:ee:ff";
+    syslog.registerIp("127.0.0.1", mac);
+    state.update((s) => {
+      s.install_queue[mac] = {
+        hostname: "testnode",
+        disk: "/dev/sda",
+        role: "worker",
+        os: "fedora-43",
+        queued_at: new Date().toISOString(),
+      };
+    });
+
+    // Message without PID
+    await sendUdpSyslog(PORT, "<13>Mar 30 01:30:00 localhost kernel: NVMe device ready");
+    await new Promise((r) => setTimeout(r, 200));
+
+    const lines = installLog.getLines(mac);
+    expect(lines.length).toBeGreaterThan(0);
+    expect(lines[0]!.line).toContain("kernel");
+  });
+});

bastion/src/cli/src/api/client.ts

@@ -94,6 +94,10 @@ export class LabdClient {
     return this.request("POST", "/api/machines/install", { body: opts });
   }
 
+  async debugMachine(mac: string, opts?: { pxeBoot?: boolean }): Promise<{ status: string; data?: { mac: string; hostname: string }; error?: string }> {
+    return this.request("POST", "/api/machines/debug", { body: { mac, pxeBoot: opts?.pxeBoot } });
+  }
+
   async forgetMachine(mac: string): Promise<{ status: string }> {
     return this.request("DELETE", `/api/machines/${encodeURIComponent(mac)}`);
   }

bastion/src/cli/src/commands/debug.ts

@@ -0,0 +1,155 @@
+// CLI command: provision debug
+// Queue a machine for debug/rescue PXE boot and optionally SSH reboot into PXE.
+
+import { execFileSync } from "node:child_process";
+import { existsSync } from "node:fs";
+import { homedir } from "node:os";
+import { join } from "node:path";
+import { Command } from "commander";
+import type { BastionState } from "@lab/shared";
+import { getLabdClient } from "../api/config.js";
+
+/** Resolve a target (hostname, MAC, or IP) to {mac, hostname, ip} from state. */
+function resolveTarget(
+  target: string,
+  state: BastionState,
+): { mac: string; hostname: string; ip: string } | null {
+  const normalized = target.toLowerCase().replace(/-/g, ":");
+
+  if (state.installed[normalized]) {
+    const info = state.installed[normalized];
+    return { mac: normalized, hostname: info.hostname, ip: info.ip };
+  }
+
+  if (state.discovered[normalized]) {
+    return { mac: normalized, hostname: normalized, ip: "" };
+  }
+
+  if (state.install_queue[normalized]) {
+    return { mac: normalized, hostname: state.install_queue[normalized].hostname, ip: "" };
+  }
+
+  for (const [mac, info] of Object.entries(state.installed)) {
+    if (info.hostname === target || info.hostname.startsWith(target + ".")) {
+      return { mac, hostname: info.hostname, ip: info.ip };
+    }
+  }
+
+  for (const [mac, info] of Object.entries(state.installed)) {
+    if (info.ip === target) {
+      return { mac, hostname: info.hostname, ip: info.ip };
+    }
+  }
+
+  return null;
+}
+
+export function registerDebugCommand(parent: Command): void {
+  parent
+    .command("debug <target>")
+    .description("PXE boot into Fedora rescue mode for debugging (target: hostname, MAC, or IP)")
+    .option("--pxe-boot", "Boot installed system via PXE (kernel+initrd from network, root from NVMe)")
+    .showHelpAfterError(true)
+    .action(async (target: string, opts: { pxeBoot?: boolean }) => {
+      const client = getLabdClient();
+
+      // Resolve target from labd aggregated state
+      let state: BastionState;
+      try {
+        state = await client.getMachines();
+      } catch (err) {
+        console.error(`Cannot reach labd: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+      }
+
+      const resolved = resolveTarget(target, state);
+      if (!resolved) {
+        console.error(`Cannot find machine: ${target}`);
+        console.error("Provide a hostname, MAC, or IP of a known machine.");
+        console.error("Run 'labctl provision list' to see available machines.");
+        process.exit(1);
+      }
+
+      const { mac, hostname, ip } = resolved;
+      console.log(`Queuing debug mode for ${hostname} (${mac})...`);
+
+      try {
+        const result = await client.debugMachine(mac, { pxeBoot: opts.pxeBoot === true });
+        if (result.error) {
+          console.error(`Failed: ${result.error}`);
+          process.exit(1);
+        }
+      } catch (err) {
+        console.error(`Failed to queue debug: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+      }
+
+      // Try SSH reboot into PXE
+      if (ip !== "") {
+        const adminUser = process.env["SUDO_USER"] ?? process.env["USER"] ?? "";
+        const effectiveUser = adminUser === "root" ? "" : adminUser;
+
+        if (effectiveUser !== "") {
+          console.log(`\nAttempting SSH reboot into PXE (${effectiveUser}@${ip})...`);
+
+          const sudoUser = process.env["SUDO_USER"];
+          const realHome = sudoUser !== undefined ? join("/home", sudoUser) : homedir();
+          const keyPaths = [
+            join(realHome, ".ssh", "id_ed25519"),
+            join(realHome, ".ssh", "id_rsa"),
+            join(realHome, ".ssh", "id_ecdsa"),
+          ];
+          const sshKey = keyPaths.find(k => existsSync(k));
+
+          const sshArgs = [
+            "-o", "StrictHostKeyChecking=no",
+            "-o", "ConnectTimeout=10",
+            ...(sshKey !== undefined ? ["-i", sshKey] : []),
+            `${effectiveUser}@${ip}`,
+            'PXE_ENTRY=$(sudo efibootmgr | grep -iE "pxe|network|ipv4" | head -1 | grep -oP "Boot\\K[0-9A-F]+"); if [ -n "$PXE_ENTRY" ]; then sudo efibootmgr --bootnext "$PXE_ENTRY" && echo "PXE set as next boot" && sudo reboot; else echo "No PXE boot entry found, rebooting anyway..." && sudo reboot; fi',
+          ];
+
+          try {
+            execFileSync("ssh", sshArgs, { stdio: "inherit" });
+          } catch {
+            // SSH connection closing during reboot is expected
+          }
+        }
+      }
+
+      // Determine bastion URL from labd config for the setup script URL
+      const bastionUrl = process.env["LABD_URL"]
+        ? process.env["LABD_URL"].replace(/\/ws\/bastion$/, "").replace(/^wss?:/, "http:")
+        : "http://<bastion-ip>:8080";
+
+      console.log(`
+Debug mode queued for ${hostname} (${mac}).
+Reboot the machine to enter Fedora rescue mode.
+
+SSH access (started by Anaconda):
+  ssh root@<ip>   (password: debug)
+
+For nc remote shell, run from rescue shell:
+  curl ${bastionUrl}/debug-setup.sh | bash
+
+Once in rescue shell:
+
+  # Activate LVM and mount installed system
+  vgchange -ay
+  mkdir -p /mnt/sysroot
+  mount /dev/<vg>/root /mnt/sysroot
+  cat /mnt/sysroot/etc/fstab
+  mount /dev/<vg>/var  /mnt/sysroot/var
+  mount /dev/<vg>/home /mnt/sysroot/home
+
+  # Boot installed system in a container
+  /mnt/sysroot/usr/bin/systemd-nspawn -D /mnt/sysroot --boot
+
+  # Or chroot for quick fixes
+  mount --bind /dev  /mnt/sysroot/dev
+  mount --bind /proc /mnt/sysroot/proc
+  mount --bind /sys  /mnt/sysroot/sys
+  chroot /mnt/sysroot
+`);
+    });
+}

bastion/src/cli/src/commands/logs.ts

@@ -39,19 +39,25 @@ export function registerLogsCommand(parent: Command): void {
   parent
     .command("logs <target>")
     .description("Show provisioning logs for a machine (hostname, MAC, or IP)")
-    .action(async (target: string) => {
+    .option("-f, --follow", "Follow log output in real-time")
+    .action(async (target: string, opts: { follow?: boolean }) => {
       const mac = await resolveToMac(target);
 
+      const BOLD = "\x1b[1m";
+      const GREEN = "\x1b[32m";
+      const YELLOW = "\x1b[33m";
+      const RED = "\x1b[31m";
+      const DIM = "\x1b[2m";
+      const RESET = "\x1b[0m";
+
+      if (opts.follow) {
+        await followLogs(mac, { BOLD, GREEN, YELLOW, RED, DIM, RESET });
+        return;
+      }
+
       try {
         const data = await getLabdClient().getMachineLogs(mac);
 
-        const BOLD = "\x1b[1m";
-        const GREEN = "\x1b[32m";
-        const YELLOW = "\x1b[33m";
-        const RED = "\x1b[31m";
-        const DIM = "\x1b[2m";
-        const RESET = "\x1b[0m";
-
         console.log(`${BOLD}${data["hostname"]}${RESET} (${mac})`);
         console.log(`  Status:   ${data["status"] === "installed" ? GREEN : YELLOW}${data["status"]}${RESET}`);
         console.log(`  Role:     ${data["role"]}`);
@@ -83,3 +89,58 @@ export function registerLogsCommand(parent: Command): void {
       }
     });
 }
+
+/** Follow logs by polling labd. */
+async function followLogs(
+  mac: string,
+  colors: { BOLD: string; GREEN: string; YELLOW: string; RED: string; DIM: string; RESET: string },
+): Promise<void> {
+  const { BOLD, GREEN, YELLOW, RED, DIM, RESET } = colors;
+  const client = getLabdClient();
+
+  console.log(`${DIM}Following logs for ${mac} (Ctrl+C to stop)${RESET}`);
+  console.log("");
+
+  let lastStageCount = 0;
+  let lastStatus = "";
+
+  while (true) {
+    try {
+      const data = await client.getMachineLogs(mac);
+      const status = String(data["status"] ?? "");
+      const log = data["log"] as Array<{ stage: string; detail: string; timestamp: string }> | undefined;
+
+      // Print header once or on status change
+      if (status !== lastStatus) {
+        const hostname = String(data["hostname"] ?? mac);
+        const statusColor = status === "installed" ? GREEN : YELLOW;
+        console.log(`  ${BOLD}${hostname}${RESET}  ${statusColor}${status}${RESET}`);
+        lastStatus = status;
+      }
+
+      // Print new stages
+      if (log && log.length > lastStageCount) {
+        for (let i = lastStageCount; i < log.length; i++) {
+          const entry = log[i]!;
+          const time = entry.timestamp.slice(11, 19);
+          const color = entry.stage === "complete" ? GREEN : entry.stage === "error" ? RED : YELLOW;
+          const detail = entry.detail ? ` ${DIM}-- ${entry.detail}${RESET}` : "";
+          console.log(`  ${DIM}${time}${RESET}  ${color}${entry.stage}${RESET}${detail}`);
+        }
+        lastStageCount = log.length;
+      }
+
+      // Done
+      if (status === "installed") {
+        const ip = data["ip"] ?? "";
+        console.log("");
+        console.log(`  ${GREEN}${BOLD}Install complete!${RESET}${ip ? ` ${DIM}ssh lab@${ip}${RESET}` : ""}`);
+        process.exit(0);
+      }
+    } catch {
+      // Machine may not be in logs yet (still queued)
+    }
+
+    await new Promise((r) => setTimeout(r, 5000));
+  }
+}

bastion/src/cli/src/index.ts

@@ -14,6 +14,7 @@ import { registerStatusCommand } from "./commands/status.js";
 import { registerInstallCommand } from "./commands/install.js";
 import { registerListCommand } from "./commands/list.js";
 import { registerReprovisionCommand } from "./commands/reprovision.js";
+import { registerDebugCommand } from "./commands/debug.js";
 import { registerForgetCommand } from "./commands/forget.js";
 import { registerLogsCommand } from "./commands/logs.js";
 import { registerMakeIsoCommand } from "./commands/makeiso.js";
@@ -95,6 +96,7 @@ export function createProgram(): Command {
   registerListCommand(provisionCmd);
   registerInstallCommand(provisionCmd);
   registerReprovisionCommand(provisionCmd);
+  registerDebugCommand(provisionCmd);
   registerForgetCommand(provisionCmd);
   registerLogsCommand(provisionCmd);
   registerMakeIsoCommand(provisionCmd);

bastion/src/labd/src/main.ts

@@ -34,6 +34,7 @@ async function main(): Promise<void> {
       server: {
         findMany: () => dbError(),
         findUnique: () => dbError(),
+        upsert: () => dbError(),
       },
       joinToken: {
         findUnique: () => dbError(),

bastion/src/labd/src/routes/bastions.ts

@@ -80,9 +80,54 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     });
   });
 
-  // Aggregated machines from all connected bastions
+  // Aggregated machines from all connected bastions + DB fallback
   app.get("/api/machines", async () => {
-    return bastionRegistry.getAggregatedState();
+    const live = bastionRegistry.getAggregatedState();
+
+    // Merge DB records for machines not currently in any bastion's live state
+    try {
+      const dbServers = (await db.server.findMany({})) as Array<{
+        mac: string | null; hostname: string; role: string; ip: string | null;
+        status: string; labels: Record<string, unknown>;
+      }>;
+      for (const s of dbServers) {
+        if (!s.mac) continue;
+        const mac = s.mac.toLowerCase();
+        // Only add from DB if not already in live state
+        if (!(mac in live.discovered) && !(mac in live.install_queue) && !(mac in live.installed)) {
+          if (s.status === "discovered") {
+            live.discovered[mac] = {
+              mac,
+              product: String(s.labels?.product ?? "unknown"),
+              board: "unknown",
+              serial: "unknown",
+              manufacturer: String(s.labels?.manufacturer ?? "unknown"),
+              cpu_model: String(s.labels?.cpu ?? "unknown"),
+              cpu_cores: Number(s.labels?.cores ?? 0),
+              memory_gb: Number(s.labels?.memory_gb ?? 0),
+              arch: String(s.labels?.arch ?? "unknown"),
+              disks: [],
+              nics: [],
+              first_seen: "",
+              last_seen: "",
+              bastionId: "db",
+            };
+          } else if (s.status === "online" || s.status === "offline") {
+            live.installed[mac] = {
+              hostname: s.hostname,
+              role: s.role,
+              ip: s.ip ?? "",
+              installed_at: "",
+              bastionId: "db",
+            };
+          }
+        }
+      }
+    } catch {
+      // DB unavailable — return live state only
+    }
+
+    return live;
   });
 
   // Queue install — route to correct bastion by MAC
@@ -106,7 +151,7 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
         try {
           const result = await sendCommand(all[0]!.bastionId, {
             type: "command-install",
-            mac, hostname, disk: disk ?? "/dev/sda", role: role ?? "infra", os: os ?? "fedora-43",
+            mac, hostname, disk: disk ?? "", role: role ?? "infra", os: os ?? "fedora-43",
           });
           return reply.code(result.status === "ok" ? 200 : 500).send(result);
         } catch (err) {
@@ -119,7 +164,7 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     try {
       const result = await sendCommand(bastion.bastionId, {
         type: "command-install",
-        mac, hostname, disk: disk ?? "/dev/sda", role: role ?? "infra", os: os ?? "fedora-43",
+        mac, hostname, disk: disk ?? "", role: role ?? "infra", os: os ?? "fedora-43",
       });
       return reply.code(result.status === "ok" ? 200 : 500).send(result);
     } catch (err) {
@@ -127,6 +172,41 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     }
   });
 
+  // Queue debug/rescue mode — route to correct bastion by MAC
+  app.post<{
+    Body: { mac?: string; pxeBoot?: boolean };
+  }>("/api/machines/debug", async (request, reply) => {
+    const mac = (request.body?.mac ?? "").toLowerCase().replace(/-/g, ":");
+    const pxeBoot = request.body?.pxeBoot ?? false;
+    if (!mac) {
+      return reply.code(400).send({ error: "mac is required" });
+    }
+
+    const bastion = bastionRegistry.findBastionByMac(mac);
+    if (!bastion) {
+      const all = bastionRegistry.getAll();
+      if (all.length === 0) {
+        return reply.code(503).send({ error: "No bastions connected" });
+      }
+      if (all.length === 1) {
+        try {
+          const result = await sendCommand(all[0]!.bastionId, { type: "command-debug", mac, pxeBoot });
+          return reply.code(result.status === "ok" ? 200 : 500).send(result);
+        } catch (err) {
+          return reply.code(500).send({ error: err instanceof Error ? err.message : String(err) });
+        }
+      }
+      return reply.code(404).send({ error: `MAC ${mac} not found on any bastion` });
+    }
+
+    try {
+      const result = await sendCommand(bastion.bastionId, { type: "command-debug", mac, pxeBoot });
+      return reply.code(result.status === "ok" ? 200 : 500).send(result);
+    } catch (err) {
+      return reply.code(500).send({ error: err instanceof Error ? err.message : String(err) });
+    }
+  });
+
   // Forget machine
   app.delete<{ Params: { mac: string } }>("/api/machines/:mac", async (request, reply) => {
     const mac = request.params.mac.toLowerCase().replace(/-/g, ":");

bastion/src/labd/src/server.ts

@@ -19,6 +19,7 @@ export interface DbClient {
   server: {
     findMany: (...args: unknown[]) => Promise<unknown[]>;
     findUnique: (...args: unknown[]) => Promise<unknown>;
+    upsert: (...args: unknown[]) => Promise<unknown>;
   };
   joinToken: {
     findUnique: (...args: unknown[]) => Promise<unknown>;
@@ -139,7 +140,7 @@ export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
                     socket,
                     connectedAt: new Date(),
                     lastHeartbeat: new Date(),
-                    state: { discovered: {}, install_queue: {}, installed: {} },
+                    state: { discovered: {}, install_queue: {}, installed: {}, debug: {} },
                   });
 
                   socket.send(JSON.stringify({ type: "bastion-enrolled", bastionId: record.id }));
@@ -175,6 +176,52 @@ export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
               if (bastionId) {
                 bastionRegistry.updateState(bastionId, msg.state);
                 logger.info(`Bastion ${bastionId.slice(0, 8)} state sync: ${Object.keys(msg.state.discovered).length} discovered, ${Object.keys(msg.state.installed).length} installed`);
+
+                // Persist machines to DB
+                void (async () => {
+                  try {
+                    // Upsert discovered machines
+                    for (const [mac, hw] of Object.entries(msg.state.discovered)) {
+                      await db.server.upsert({
+                        where: { mac },
+                        create: {
+                          hostname: hw.product ?? mac,
+                          mac,
+                          role: "unknown",
+                          status: "discovered",
+                          labels: { cpu: hw.cpu_model, cores: hw.cpu_cores, memory_gb: hw.memory_gb, arch: hw.arch, product: hw.product, manufacturer: hw.manufacturer },
+                        },
+                        update: {
+                          status: "discovered",
+                          lastHeartbeat: new Date(),
+                          labels: { cpu: hw.cpu_model, cores: hw.cpu_cores, memory_gb: hw.memory_gb, arch: hw.arch, product: hw.product, manufacturer: hw.manufacturer },
+                        },
+                      });
+                    }
+                    // Upsert installed machines
+                    for (const [mac, info] of Object.entries(msg.state.installed)) {
+                      await db.server.upsert({
+                        where: { mac },
+                        create: {
+                          hostname: info.hostname,
+                          mac,
+                          role: info.role ?? "worker",
+                          ip: info.ip,
+                          status: "online",
+                        },
+                        update: {
+                          hostname: info.hostname,
+                          role: info.role ?? "worker",
+                          ip: info.ip,
+                          status: "online",
+                          lastHeartbeat: new Date(),
+                        },
+                      });
+                    }
+                  } catch (err) {
+                    logger.warn(`Failed to persist machines to DB: ${err instanceof Error ? err.message : String(err)}`);
+                  }
+                })();
               }
               break;
             }

bastion/src/labd/src/services/bastion-registry.ts

@@ -3,7 +3,7 @@
 
 import { EventEmitter } from "node:events";
 import type { WebSocket } from "ws";
-import type { BastionState, HardwareInfo, InstallConfig, InstalledInfo } from "@lab/shared";
+import type { BastionState, HardwareInfo, InstallConfig, InstalledInfo, DebugConfig } from "@lab/shared";
 
 export interface ConnectedBastion {
   bastionId: string;
@@ -20,6 +20,7 @@ export interface AggregatedState {
   discovered: Record<string, HardwareInfo>;
   install_queue: Record<string, InstallConfig>;
   installed: Record<string, InstalledInfo>;
+  debug: Record<string, DebugConfig>;
 }
 
 export class BastionRegistry extends EventEmitter {
@@ -86,6 +87,7 @@ export class BastionRegistry extends EventEmitter {
       discovered: {},
       install_queue: {},
       installed: {},
+      debug: {},
     };
 
     for (const bastion of this.bastions.values()) {
@@ -98,6 +100,9 @@ export class BastionRegistry extends EventEmitter {
       for (const [mac, info] of Object.entries(bastion.state.installed)) {
         result.installed[mac] = { ...info, bastionId: bastion.bastionId };
       }
+      for (const [mac, dbg] of Object.entries(bastion.state.debug ?? {})) {
+        result.debug[mac] = { ...dbg };
+      }
     }
 
     return result;

bastion/src/shared/src/index.ts

@@ -5,6 +5,7 @@ export type {
   HardwareInfo,
   InstallConfig,
   InstalledInfo,
+  DebugConfig,
   BastionState,
   BastionConfig,
 } from "./types/index.js";

bastion/src/shared/src/protocol/index.ts

@@ -100,6 +100,7 @@ export type BastionMessage =
   | { type: "bastion-heartbeat"; bastionId: string; uptime: number; machineCount: number }
   | { type: "bastion-state-sync"; bastionId: string; state: import("../types/state.js").BastionState }
   | { type: "bastion-progress"; bastionId: string; mac: string; stage: string; detail: string; timestamp: string }
+  | { type: "bastion-install-log"; bastionId: string; mac: string; hostname: string; provisionerType: import("../types/state.js").ProvisionStackType; sessionId: string; lines: string[]; timestamp: string }
   | { type: "command-response"; requestId: string; status: "ok" | "error"; data?: unknown; error?: string };
 
 // --- labd -> Bastion messages ---
@@ -110,6 +111,7 @@ export type LabdBastionMessage =
   | { type: "command-install"; requestId: string; mac: string; hostname: string; disk?: string; role: string; os: string }
   | { type: "command-forget"; requestId: string; mac: string }
   | { type: "command-role-update"; requestId: string; mac: string; role: string }
+  | { type: "command-debug"; requestId: string; mac: string; pxeBoot?: boolean }
   | { type: "server-shutdown"; reconnectAfter: number };
 
 export type BastionMessageType = BastionMessage["type"];
@@ -119,12 +121,12 @@ export type LabdBastionMessageType = LabdBastionMessage["type"];
 
 const BASTION_MESSAGE_TYPES = new Set<string>([
   "bastion-enroll", "bastion-heartbeat", "bastion-state-sync",
-  "bastion-progress", "command-response",
+  "bastion-progress", "bastion-install-log", "command-response",
 ]);
 
 const LABD_BASTION_MESSAGE_TYPES = new Set<string>([
   "bastion-enrolled", "bastion-heartbeat-ack", "command-install",
-  "command-forget", "command-role-update", "server-shutdown",
+  "command-forget", "command-role-update", "command-debug", "server-shutdown",
 ]);
 
 export function isBastionMessage(msg: unknown): msg is BastionMessage {

bastion/src/shared/src/types/config.ts

@@ -14,6 +14,8 @@ export interface BastionConfig {
   // Ubuntu support
   ubuntuVersion: string;
   ubuntuMirror: string;
+  // Syslog listener for install logs (Anaconda logging --host)
+  syslogPort: number;
   // Flags
   skipDnsmasq?: boolean | undefined;
   skipArtifacts?: boolean | undefined;

bastion/src/shared/src/types/index.ts

@@ -5,6 +5,7 @@ export type {
   HardwareInfo,
   InstallConfig,
   InstalledInfo,
+  DebugConfig,
   BastionState,
 } from "./state.js";
 

bastion/src/shared/src/types/state.ts

@@ -1,5 +1,7 @@
 // State types for discovered machines, install queue, and installed machines.
 
+export type ProvisionStackType = "dhcpproxy" | "iso" | "cloud-init";
+
 export type OsId = "fedora-43" | "ubuntu-26.04";
 export type Arch = "x86_64" | "aarch64";
 
@@ -96,8 +98,15 @@ export interface InstalledInfo {
   bastionId?: string;  // set when aggregated through labd
 }
 
+export interface DebugConfig {
+  hostname: string;
+  queued_at: string;
+  pxeBoot?: boolean;
+}
+
 export interface BastionState {
   discovered: Record<string, HardwareInfo>;
   install_queue: Record<string, InstallConfig>;
   installed: Record<string, InstalledInfo>;
+  debug: Record<string, DebugConfig>;
 }

bastion/tests/integration/helpers/jetkvm.sh

@@ -0,0 +1,82 @@
+#!/bin/bash
+# JetKVM helper — authenticate and interact with JetKVM device.
+# Usage:
+#   jetkvm.sh status              — check device status
+#   jetkvm.sh reboot              — reboot the target machine via ATX
+#   jetkvm.sh poweron             — power on via ATX short press
+#   jetkvm.sh poweroff            — power off via ATX long press
+#
+# Environment:
+#   JETKVM_HOST    — JetKVM IP (default: 192.168.3.10)
+#   JETKVM_PASS    — device password
+
+set -euo pipefail
+
+HOST="${JETKVM_HOST:-192.168.3.10}"
+PASS="${JETKVM_PASS:-}"
+
+if [ -z "$PASS" ]; then
+    echo "ERROR: JETKVM_PASS not set" >&2
+    exit 1
+fi
+
+BASE="http://$HOST"
+
+# Authenticate and get token
+login() {
+    local resp
+    resp=$(curl -s -X POST "$BASE/auth/login-local" \
+        -H "Content-Type: application/json" \
+        -d "{\"password\":\"$PASS\"}" 2>&1)
+
+    local token
+    token=$(echo "$resp" | grep -oP '"token"\s*:\s*"[^"]*"' | head -1 | grep -oP '"[^"]*"$' | tr -d '"')
+
+    if [ -z "$token" ]; then
+        echo "ERROR: Login failed: $resp" >&2
+        exit 1
+    fi
+    echo "$token"
+}
+
+# Make authenticated request
+api() {
+    local method="$1" path="$2" body="${3:-}"
+    local token
+    token=$(login)
+
+    if [ -n "$body" ]; then
+        curl -s -X "$method" "$BASE$path" \
+            -H "Authorization: Bearer $token" \
+            -H "Content-Type: application/json" \
+            -d "$body"
+    else
+        curl -s -X "$method" "$BASE$path" \
+            -H "Authorization: Bearer $token"
+    fi
+}
+
+case "${1:-status}" in
+    status)
+        curl -s "$BASE/device/status" 2>&1
+        ;;
+    device)
+        api GET /device
+        ;;
+    reboot)
+        echo "Sending ATX reset..."
+        api POST /device/atx/reset
+        ;;
+    poweron)
+        echo "Sending ATX short power press..."
+        api POST /device/atx/power-short
+        ;;
+    poweroff)
+        echo "Sending ATX long power press..."
+        api POST /device/atx/power-long
+        ;;
+    *)
+        echo "Usage: $0 {status|device|reboot|poweron|poweroff}"
+        exit 1
+        ;;
+esac

bastion/tests/integration/helpers/pxe-network.ts

@@ -40,50 +40,50 @@ export function ensurePxeNetwork(): void {
 
   if (result.status === 0 && result.stdout.includes("Active:         yes")) {
     log(`Network ${PXE_NETWORK_NAME} already active`);
-    return;
+  } else {
+    // Destroy existing if present but inactive
+    if (result.status === 0) {
+      virsh("net-destroy", PXE_NETWORK_NAME);
+      virsh("net-undefine", PXE_NETWORK_NAME);
+    }
+
+    const xmlPath = "/tmp/lab-pxe-test-network.xml";
+    writeFileSync(xmlPath, NETWORK_XML);
+
+    log(`Creating PXE libvirt network: ${PXE_NETWORK_NAME} (${PXE_SUBNET}.0/24, no DHCP)`);
+    run(`virsh net-define "${xmlPath}"`);
+    run(`virsh net-start "${PXE_NETWORK_NAME}"`);
+
+    try { unlinkSync(xmlPath); } catch { /* ignore */ }
+
+    log(`Network ${PXE_NETWORK_NAME} created and active`);
   }
 
-  // Destroy existing if present but inactive
-  if (result.status === 0) {
-    virsh("net-destroy", PXE_NETWORK_NAME);
-    virsh("net-undefine", PXE_NETWORK_NAME);
-  }
+  // Libvirt adds nftables reject rules for NAT networks that block host→VM SSH.
+  // Delete them now and after every VM reboot (libvirt recreates them).
+  deleteNftablesRejectRules();
+}
 
-  const xmlPath = "/tmp/lab-pxe-test-network.xml";
-  writeFileSync(xmlPath, NETWORK_XML);
-
-  log(`Creating PXE libvirt network: ${PXE_NETWORK_NAME} (${PXE_SUBNET}.0/24, no DHCP)`);
-  run(`virsh net-define "${xmlPath}"`);
-  run(`virsh net-start "${PXE_NETWORK_NAME}"`);
-
-  try { unlinkSync(xmlPath); } catch { /* ignore */ }
-
-  // Libvirt creates nftables rules that reject traffic on the bridge.
-  // DHCP works (dnsmasq uses raw sockets) but TFTP/HTTP from VM->host gets blocked.
-  // Delete the reject rules so VM traffic can reach the bastion.
-  try {
-    // Delete the reject rules that libvirt added for our bridge.
-    // We find and delete each rule by its handle number.
-    const deleteRejectRules = (chain: string): void => {
-      const output = run(`nft -a list chain inet libvirt ${chain} 2>/dev/null || true`);
-      const lines = output.split("\n");
-      for (const line of lines) {
-        if (line.includes(PXE_BRIDGE) && line.includes("reject")) {
-          const handleMatch = line.match(/# handle (\d+)/);
-          if (handleMatch) {
-            run(`nft delete rule inet libvirt ${chain} handle ${handleMatch[1]}`);
+/** Delete libvirt's nftables reject rules for our bridge so host→VM traffic works.
+ *  Must be called after every VM start/restart — libvirt recreates them. */
+export function deleteNftablesRejectRules(): void {
+  // libvirt uses "ip libvirt_network" table (not "inet libvirt")
+  const tables = ["ip libvirt_network", "ip6 libvirt_network", "inet libvirt"];
+  for (const table of tables) {
+    try {
+      for (const chain of ["guest_input", "guest_output"]) {
+        const output = run(`nft -a list chain ${table} ${chain} 2>/dev/null || true`);
+        for (const line of output.split("\n")) {
+          if (line.includes(PXE_BRIDGE) && line.includes("reject")) {
+            const handleMatch = line.match(/# handle (\d+)/);
+            if (handleMatch) {
+              run(`nft delete rule ${table} ${chain} handle ${handleMatch[1]}`);
+            }
           }
         }
       }
-    };
-    deleteRejectRules("guest_input");
-    deleteRejectRules("guest_output");
-    log(`Removed nftables reject rules for ${PXE_BRIDGE}`);
-  } catch {
-    log(`Could not update nftables rules (may need manual firewall config)`);
+    } catch { /* table may not exist */ }
   }
-
-  log(`Network ${PXE_NETWORK_NAME} created and active`);
 }
 
 /** Destroy the PXE test network. */

bastion/tests/integration/helpers/pxe-vm.ts

@@ -63,7 +63,7 @@ export function createPxeVm(config: PxeVmConfig): void {
     `--disk=path=${diskPath},format=qcow2,bus=virtio`,
     `--network=network=${config.network},model=virtio`,
     // UEFI firmware — required for PXE boot in modern mode
-    `--boot=uefi,network`,
+    `--boot=uefi,network,hd`,
     // No OS to install — PXE provides everything
     "--os-variant=generic",
     "--noautoconsole",
@@ -113,29 +113,54 @@ export function rebootPxeVm(name: string): void {
   log(`PXE VM ${name} restarted`);
 }
 
-/** Change VM boot order to disk first (skip PXE on next boot). */
-export function setBootDisk(name: string): void {
-  log(`Setting ${name} boot order to disk first`);
-  virsh("destroy", name);
-  spawnSync("sleep", ["2"]);
-  // Get current XML, replace boot dev='network' with boot dev='hd'
-  // This preserves UEFI loader/nvram settings (virt-xml --boot hd can break them)
-  const dumpXml = virsh("dumpxml", name);
-  if (dumpXml.status !== 0) throw new Error("Failed to dump VM XML");
-  let xml = dumpXml.stdout;
-  // Replace any <boot dev='...' /> entries with hd
-  xml = xml.replace(/<boot dev='[^']*'\/>/g, "<boot dev='hd'/>");
-  // If no boot dev entry, add one before </os>
-  if (!xml.includes("<boot dev=")) {
-    xml = xml.replace("</os>", "  <boot dev='hd'/>\n  </os>");
-  }
-  const xmlPath = `/tmp/${name}-bootfix.xml`;
-  const { writeFileSync: writeFs, unlinkSync: unlinkFs } = require("node:fs") as typeof import("node:fs");
-  writeFs(xmlPath, xml);
-  run(`virsh define "${xmlPath}"`);
-  try { unlinkFs(xmlPath); } catch { /* ignore */ }
-  virsh("start", name);
-  log(`${name} restarted with disk boot (UEFI preserved)`);
+/**
+ * Read raw output from the VM's serial console (telnet TCP port).
+ * Returns the last N lines. Useful for diagnostics when SSH isn't available.
+ */
+export async function readSerialLog(
+  port: number,
+  opts: { lastLines?: number; timeoutMs?: number } = {},
+): Promise<string> {
+  const { lastLines = 50, timeoutMs = 10_000 } = opts;
+  return new Promise((resolve) => {
+    const sock = createConnection({ host: "127.0.0.1", port });
+    let buf = "";
+    const timer = setTimeout(() => { sock.destroy(); resolve(buf); }, timeoutMs);
+    sock.on("data", (d: Buffer) => { buf += d.toString(); });
+    sock.on("error", () => { clearTimeout(timer); resolve(`(connection error) ${buf}`); });
+    sock.on("close", () => { clearTimeout(timer); resolve(buf); });
+    // Send a newline to trigger any buffered output / prompt
+    setTimeout(() => sock.write("\r\n"), 500);
+  }).then((raw: unknown) => {
+    const lines = (raw as string).split("\n").map(l => l.trimEnd()).filter(Boolean);
+    return lines.slice(-lastLines).join("\n");
+  });
+}
+
+/**
+ * Execute a command on the VM's serial console via socat.
+ * Requires auto-login root shell on the serial port.
+ */
+export function serialExec(
+  port: number,
+  command: string,
+  timeoutMs = 15_000,
+): string {
+  const marker = `__END_${Date.now()}__`;
+  // Use socat to handle telnet negotiation properly
+  const input = `\r\n${command}; echo '${marker}'\r\n`;
+  const result = spawnSync("bash", ["-c",
+    `echo -e '${input.replace(/'/g, "\\'")}' | socat -T${Math.ceil(timeoutMs / 1000)} - TCP:127.0.0.1:${port} 2>/dev/null`
+  ], { encoding: "utf-8", stdio: "pipe", timeout: timeoutMs + 5000 });
+  const output = result.stdout ?? "";
+  const markerIdx = output.indexOf(marker);
+  if (markerIdx < 0) return `(no marker) ${output.slice(-500)}`;
+  // Get lines between command echo and marker
+  const before = output.substring(0, markerIdx);
+  const lines = before.split("\n");
+  // Skip everything up to and including the command echo line
+  const cmdIdx = lines.findIndex(l => l.includes(command.substring(0, 20)));
+  return lines.slice(cmdIdx >= 0 ? cmdIdx + 1 : 1).join("\n").trim();
 }
 
 export interface IsoVmConfig {
@@ -187,69 +212,3 @@ export function createIsoVm(config: IsoVmConfig): void {
   log(`ISO boot VM ${config.name} created (serial: telnet 127.0.0.1 4556)`);
 }
 
-/**
- * Execute a command on a VM via its serial console (telnet).
- * Works even when the VM has no network/SSH.
- * Returns the output after the command's echo.
- */
-export async function serialExec(
-  port: number,
-  command: string,
-  timeoutMs = 10_000,
-): Promise<string> {
-  return new Promise((resolve, reject) => {
-    const timer = setTimeout(() => {
-      sock.destroy();
-      reject(new Error(`Serial exec timeout after ${timeoutMs}ms`));
-    }, timeoutMs);
-
-    const sock = createConnection({ host: "127.0.0.1", port });
-    let buffer = "";
-    let sentCommand = false;
-    // Random marker to delimit command output
-    const marker = `__SERIAL_END_${Date.now()}__`;
-
-    sock.on("connect", () => {
-      // Wait for login prompt or shell prompt, then send command
-      setTimeout(() => {
-        // Send a newline first to get a prompt
-        sock.write("\r\n");
-      }, 500);
-    });
-
-    sock.on("data", (data: Buffer) => {
-      buffer += data.toString();
-
-      if (!sentCommand && (buffer.includes("login:") || buffer.includes("# ") || buffer.includes("$ "))) {
-        if (buffer.includes("login:")) {
-          // Auto-login as root
-          sock.write("root\r\n");
-          sentCommand = false; // wait for shell prompt after login
-          buffer = "";
-          return;
-        }
-        // At shell prompt — send command with marker
-        sentCommand = true;
-        buffer = "";
-        sock.write(`${command}; echo "${marker}"\r\n`);
-      }
-
-      if (sentCommand && buffer.includes(marker)) {
-        clearTimeout(timer);
-        // Extract output between command echo and marker
-        const markerIdx = buffer.indexOf(marker);
-        const output = buffer.substring(0, markerIdx).trim();
-        // Remove the command echo (first line)
-        const lines = output.split("\n");
-        const result = lines.slice(1).join("\n").trim();
-        sock.destroy();
-        resolve(result);
-      }
-    });
-
-    sock.on("error", (err) => {
-      clearTimeout(timer);
-      reject(new Error(`Serial connection failed: ${err.message}`));
-    });
-  });
-}

bastion/tests/integration/helpers/vm-screenshot.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+# Capture a screenshot of a libvirt VM and convert to PNG for viewing.
+# Usage: vm-screenshot.sh [VM_NAME] [OUTPUT_PATH]
+VM_NAME="${1:-lab-pxe-test}"
+OUTPUT="${2:-/tmp/vm-screenshot.png}"
+PPM="/tmp/vm-screenshot-$$.ppm"
+
+if ! sudo virsh domstate "$VM_NAME" &>/dev/null; then
+    echo "ERROR: VM '$VM_NAME' not found or not running" >&2
+    exit 1
+fi
+
+sudo virsh screenshot "$VM_NAME" "$PPM" --screen 0 2>/dev/null
+if [ ! -f "$PPM" ]; then
+    echo "ERROR: screenshot failed" >&2
+    exit 1
+fi
+
+# Convert to PNG (ppm -> png)
+if command -v convert &>/dev/null; then
+    convert "$PPM" "$OUTPUT"
+elif command -v ffmpeg &>/dev/null; then
+    ffmpeg -y -i "$PPM" "$OUTPUT" 2>/dev/null
+elif command -v pnmtopng &>/dev/null; then
+    pnmtopng "$PPM" > "$OUTPUT"
+else
+    # fallback: just copy the PPM (Read tool can handle it)
+    cp "$PPM" "${OUTPUT%.png}.ppm"
+    OUTPUT="${OUTPUT%.png}.ppm"
+fi
+
+rm -f "$PPM"
+echo "$OUTPUT"

bastion/tests/integration/pxe-provision.test.ts

@@ -23,17 +23,56 @@ import { execSync } from "node:child_process";
 import { join } from "node:path";
 import { homedir, tmpdir } from "node:os";
 import { log, waitForSsh } from "./helpers/libvirt.js";
-import { ensurePxeNetwork, destroyPxeNetwork, PXE_NETWORK_NAME, PXE_GATEWAY, PXE_SUBNET } from "./helpers/pxe-network.js";
-import { createPxeVm, destroyPxeVm, getVmMac, rebootPxeVm, serialExec } from "./helpers/pxe-vm.js";
+import { ensurePxeNetwork, destroyPxeNetwork, deleteNftablesRejectRules, PXE_NETWORK_NAME, PXE_GATEWAY, PXE_SUBNET } from "./helpers/pxe-network.js";
+import { createPxeVm, destroyPxeVm, getVmMac, rebootPxeVm, readSerialLog } from "./helpers/pxe-vm.js";
 import { sshExec } from "./helpers/ssh.js";
 
+// --- Boot screenshot capture ---
+const SCREENSHOT_DIR = "/tmp/vm-screenshots";
+
+function startBootScreenshots(vmName: string): { stop: () => void } {
+  try { mkdirSync(SCREENSHOT_DIR, { recursive: true }); } catch {}
+  // Clean old screenshots
+  try {
+    for (const f of require("node:fs").readdirSync(SCREENSHOT_DIR)) {
+      rmSync(join(SCREENSHOT_DIR, f), { force: true });
+    }
+  } catch {}
+
+  let running = true;
+  let seq = 0;
+  const BUFFER_SIZE = 60; // keep last 60 screenshots (1 per second)
+
+  const loop = async () => {
+    while (running) {
+      try {
+        const idx = String(seq % BUFFER_SIZE).padStart(4, "0");
+        const ppm = join(SCREENSHOT_DIR, `tmp-${idx}.ppm`);
+        const png = join(SCREENSHOT_DIR, `boot-${idx}.png`);
+        execSync(`sudo virsh screenshot ${vmName} ${ppm} --screen 0 2>/dev/null`, { timeout: 3000 });
+        execSync(`convert ${ppm} ${png} 2>/dev/null && rm -f ${ppm}`, { timeout: 3000 });
+        seq++;
+      } catch {}
+      await new Promise(r => setTimeout(r, 1000));
+    }
+  };
+  loop();
+
+  return {
+    stop: () => {
+      running = false;
+      log(`Boot screenshots saved to ${SCREENSHOT_DIR}/ (${seq} captured, last ${Math.min(seq, BUFFER_SIZE)} kept)`);
+    },
+  };
+}
+
 // --- Test constants ---
 const VM_NAME = "lab-pxe-test";
 const VM_MEMORY = 4096;     // 4GB (Anaconda needs ~2GB minimum)
-const VM_VCPUS = 2;
+const VM_VCPUS = 12;
 const VM_DISK_GB = 250;      // LVM layout needs ~204GB (swap 27 + root 33 + var 100 + etc). QCOW2 is sparse.
 const HTTP_PORT = 8099;      // Avoid conflicts with real bastion
-const SSH_USER = "michal";   // Admin user created by kickstart
+const SSH_USER = "lab";      // Admin user created by kickstart
 const BASTION_IP = PXE_GATEWAY; // 192.168.251.1
 const DHCP_RANGE_START = `${PXE_SUBNET}.100`;
 const DHCP_RANGE_END = `${PXE_SUBNET}.200`;
@@ -185,15 +224,19 @@ describe("PXE boot provisioning", () => {
     // Generate dnsmasq config
     generateDnsmasqConf(config);
 
-    // Start HTTP server
-    const { app, state } = createApp(config);
+    // Start HTTP server + syslog listener
+    const { app, state, syslog } = createApp(config);
     bastionApp = app;
     await app.listen({ port: config.httpPort, host: "0.0.0.0" });
-    log(`Bastion HTTP server listening on :${HTTP_PORT}`);
+    syslog.start();
+    log(`Bastion HTTP server listening on :${HTTP_PORT}, syslog on UDP :${config.syslogPort}`);
 
     // Start dnsmasq (fire-and-forget — it runs until killed)
-    log("Starting dnsmasq (full DHCP mode)...");
-    void startDnsmasq(config);
+    // May fail without root (DHCP socket needs CAP_NET_BIND_SERVICE); libvirt network provides DHCP fallback
+    log("Starting dnsmasq (proxy DHCP mode)...");
+    startDnsmasq(config).catch((err) => {
+      log(`dnsmasq failed (expected without root): ${err instanceof Error ? err.message : String(err)}`);
+    });
     // Give dnsmasq a moment to bind ports
     await sleep(1000);
 
@@ -267,38 +310,32 @@ describe("PXE boot provisioning", () => {
     vmIp = finalState.ip ?? "";
     log(`Install complete! VM IP: ${vmIp}`);
 
-    // 9. Force-restart VM to ensure clean boot with updated NVRAM.
-    // The %post efibootmgr sets network-first boot order, but OVMF may not
-    // reread NVRAM during a warm reboot. Force cold-restart ensures it does.
-    log("Force-restarting VM for clean network-first boot...");
+    // 9. Reboot VM — it network-boots again, bastion /dispatch returns
+    // "exit" (already installed), iPXE falls through to local disk boot.
+    log("Rebooting VM (network-first → bastion dispatch → local disk)...");
     await sleep(15_000);
     rebootPxeVm(VM_NAME);
+    // Libvirt recreates nftables reject rules on VM restart — wait for them then delete
+    await sleep(3_000);
+    deleteNftablesRejectRules();
 
-    // 10. Wait for SSH — VM network-boots, iPXE chains to /dispatch,
-    // bastion returns exit (installed), iPXE falls through to disk boot
+    // 10. Wait for SSH (with aggressive boot screenshots)
     log("Waiting for SSH access...");
+    const screenshots = startBootScreenshots(VM_NAME);
     try {
       await waitForSsh(vmIp, SSH_USER, SSH_TIMEOUT_MS, sshKeyPath);
     } catch {
-      // SSH failed — use serial console to diagnose
-      log("SSH timed out. Diagnosing via serial console...");
+      // SSH failed — read serial console (lab-boot-diag.service dumps diagnostics there)
+      log("SSH timed out. Reading serial console diagnostics...");
       try {
-        const hostname = await serialExec(4555, "hostname", 15_000);
-        log(`Serial: hostname = ${hostname}`);
-        const ip = await serialExec(4555, "ip -4 addr show | grep inet", 15_000);
-        log(`Serial: ip = ${ip}`);
-        const nm = await serialExec(4555, "systemctl is-active NetworkManager", 15_000);
-        log(`Serial: NetworkManager = ${nm}`);
-        const sshd = await serialExec(4555, "systemctl is-active sshd", 15_000);
-        log(`Serial: sshd = ${sshd}`);
-        const failed = await serialExec(4555, "systemctl --failed --no-pager", 15_000);
-        log(`Serial: failed units = ${failed}`);
-        const fstab = await serialExec(4555, "grep efi /etc/fstab", 15_000);
-        log(`Serial: fstab efi = ${fstab}`);
+        const serialOut = await readSerialLog(4555, { lastLines: 80, timeoutMs: 15_000 });
+        log(`Serial console:\n${serialOut}`);
       } catch (serialErr) {
         log(`Serial console failed: ${serialErr instanceof Error ? serialErr.message : String(serialErr)}`);
       }
-      throw new Error(`SSH not available on ${vmIp} — check serial console diagnostics above`);
+      throw new Error(`SSH not available on ${vmIp} — check serial console diagnostics above. Screenshots: ${SCREENSHOT_DIR}/`);
+    } finally {
+      screenshots.stop();
     }
 
     log("PXE provision test setup complete.");
@@ -316,10 +353,7 @@ describe("PXE boot provisioning", () => {
     const { stopDnsmasq } = await import("../../src/bastion/src/services/dnsmasq.js");
     stopDnsmasq();
 
-    // Destroy VM
     destroyPxeVm(VM_NAME);
-
-    // Destroy network
     destroyPxeNetwork();
 
     // Clean up test dir
@@ -354,10 +388,10 @@ describe("PXE boot provisioning", () => {
     expect(data.progress).toBe("complete");
   });
 
-  it("log lines were captured", async () => {
+  it("syslog install logs were captured", async () => {
+    // Anaconda forwards logs via syslog (logging --host directive in kickstart)
     const res = await fetch(`http://${BASTION_IP}:${HTTP_PORT}/api/logs/${encodeURIComponent(vmMac)}`);
     const data = (await res.json()) as { log_total?: number; log_lines?: Array<{ line: string }> };
-    // Should have at least some log lines from the log streamer
     expect(data.log_total).toBeGreaterThan(0);
   });
 
@@ -400,7 +434,15 @@ describe("PXE boot provisioning", () => {
   it("EFI boot order keeps network first (bastion controls boot)", () => {
     const result = sshExec(vmIp, SSH_USER, "sudo efibootmgr", { keyPath: sshKeyPath });
     expect(result.exitCode).toBe(0);
-    expect(result.stdout).toContain("BootOrder:");
+    // The first entry in BootOrder should be a network/PXE/HTTP boot entry
+    const orderMatch = result.stdout.match(/BootOrder:\s*([0-9A-Fa-f]+)/);
+    expect(orderMatch).toBeTruthy();
+    const firstEntry = orderMatch![1];
+    // Find what that entry maps to — should be network-related
+    const entryLine = result.stdout.match(new RegExp(`Boot${firstEntry}\\*?\\s+(.+)`));
+    expect(entryLine).toBeTruthy();
+    const entryName = entryLine![1].toLowerCase();
+    expect(entryName).toMatch(/network|pxe|ipv4|ipv6|http|uefi.*nic/i);
   });
 
   it("tmpfs mount for /tmp is configured", () => {
@@ -422,4 +464,53 @@ describe("PXE boot provisioning", () => {
       expect(lvs).toContain(expected);
     }
   });
+
+  // --- Post-provision health checks ---
+
+  it("no failed systemd services", () => {
+    const result = sshExec(vmIp, SSH_USER, "sudo systemctl --failed --no-legend --no-pager", { keyPath: sshKeyPath });
+    expect(result.exitCode).toBe(0);
+    const failed = result.stdout.trim();
+    expect(failed).toBe("");
+  });
+
+  it("root filesystem is mounted read-write", () => {
+    const result = sshExec(vmIp, SSH_USER, "mount | grep ' / '", { keyPath: sshKeyPath });
+    expect(result.stdout).toContain("rw,");
+    expect(result.stdout).not.toContain("(ro,");
+  });
+
+  it("/boot/efi is mounted", () => {
+    const result = sshExec(vmIp, SSH_USER, "mount | grep /boot/efi", { keyPath: sshKeyPath });
+    expect(result.exitCode).toBe(0);
+    expect(result.stdout).toContain("vfat");
+  });
+
+  it("kernel modules are loaded (depmod correct)", () => {
+    const result = sshExec(vmIp, SSH_USER, "lsmod | wc -l", { keyPath: sshKeyPath });
+    expect(result.exitCode).toBe(0);
+    // Should have a reasonable number of modules loaded
+    expect(Number(result.stdout.trim())).toBeGreaterThan(10);
+  });
+
+  it("SELinux is enforcing", () => {
+    const result = sshExec(vmIp, SSH_USER, "getenforce", { keyPath: sshKeyPath });
+    expect(result.exitCode).toBe(0);
+    expect(result.stdout.trim()).toBe("Enforcing");
+  });
+
+  it("SELinux context on /etc/fstab is correct", () => {
+    const result = sshExec(vmIp, SSH_USER, "ls -Z /etc/fstab", { keyPath: sshKeyPath });
+    expect(result.stdout).toContain("etc_t");
+  });
+
+  it("sshd is running", () => {
+    const result = sshExec(vmIp, SSH_USER, "sudo systemctl is-active sshd", { keyPath: sshKeyPath });
+    expect(result.stdout.trim()).toBe("active");
+  });
+
+  it("chronyd is running for time sync", () => {
+    const result = sshExec(vmIp, SSH_USER, "sudo systemctl is-active chronyd", { keyPath: sshKeyPath });
+    expect(result.stdout.trim()).toBe("active");
+  });
 });

bastion/tests/integration/run-pxe-test.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# One-shot PXE integration test runner.
+# Compiles, runs unit tests, cleans up, and runs the full integration test.
+set -e
+
+cd "$(dirname "$0")/../.."
+
+echo "=== Step 1: Compile ==="
+npx tsc --noEmit
+echo "✓ Compile OK"
+
+echo ""
+echo "=== Step 2: Kickstart unit tests ==="
+npx vitest run src/bastion/tests/kickstart.test.ts 2>&1 | tail -5
+echo "✓ Unit tests OK"
+
+echo ""
+echo "=== Step 3: Clean up ==="
+sudo lsof -ti:8099 2>/dev/null | xargs -r sudo kill -9 || true
+sudo virsh destroy lab-pxe-test 2>/dev/null || true
+sudo virsh undefine lab-pxe-test --nvram 2>/dev/null || true
+sudo rm -f /var/lib/libvirt/images/lab-pxe-test.qcow2
+echo "✓ Cleanup done"
+
+echo ""
+echo "=== Step 4: Integration test ==="
+npx vitest run -c /dev/null tests/integration/pxe-provision.test.ts 2>&1

bastion/vitest.integration.config.ts

@@ -0,0 +1,9 @@
+import { defineConfig } from 'vitest/config';
+
+export default defineConfig({
+  test: {
+    globals: true,
+    include: ['tests/integration/**/*.test.ts'],
+    testTimeout: 600000,
+  },
+});