docs(bastion): state the rescue-SSH evidence at its actual strength

The previous wording claimed the failure was "reproduced on x86_64", which
overstates it. The aarch64 observation is direct -- port 22 probed for 30
minutes with the Anaconda environment demonstrably up. The x86_64 run only
shows SSH not becoming available inside a 15-minute budget; that VM was
never observed reaching the rescue environment, because vitest's reporter
discards the streamed log.

The distinction decides where the next person looks, so it should not rest
on an inference presented as an observation.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015nRFZXpKwUVE4SRSHw6GjF

.gitignore

@@ -23,3 +23,11 @@ node_modules/
 
 # OS specific
 .DS_Store
+
+# Task files
+# tasks.json
+# tasks/ 
+
+# Asahi build artifacts (large)
+bastion/.asahi-cache/
+bastion/asahi-repo/*.zip

CLAUDE.md

@@ -0,0 +1,19 @@
+## Skill routing
+
+When the user's request matches an available skill, ALWAYS invoke it using the Skill
+tool as your FIRST action. Do NOT answer directly, do NOT use other tools first.
+The skill has specialized workflows that produce better results than ad-hoc answers.
+
+Key routing rules:
+- Product ideas, "is this worth building", brainstorming → invoke gstack-office-hours
+- Bugs, errors, "why is this broken", 500 errors → invoke gstack-investigate
+- Ship, deploy, push, create PR → invoke gstack-ship
+- QA, test the site, find bugs → invoke gstack-qa
+- Code review, check my diff → invoke gstack-review
+- Update docs after shipping → invoke gstack-document-release
+- Weekly retro → invoke gstack-retro
+- Design system, brand → invoke gstack-design-consultation
+- Visual audit, design polish → invoke gstack-design-review
+- Architecture review → invoke gstack-plan-eng-review
+- Save progress, checkpoint, resume → invoke gstack-checkpoint
+- Code quality, health check → invoke gstack-health

TODOS.md

@@ -0,0 +1,47 @@
+# TODOS
+
+## P1 — Ship with Phase 1
+
+### v2.0 Architecture Document Update
+Update `bastion/docs/ARCHITECTURE.md` to cover v2.0: driver model, fleet system,
+Pulumi integration, Vault secrets, Deno evaluator, new CLI grammar. The existing
+doc covers v1.0 comprehensively (432 lines). v2.0 adds 5+ major subsystems.
+**Effort:** M (human: 1 week / CC: 1-2 days)
+**Depends on:** Phase 1 complete
+**Source:** CEO review 2026-04-01
+
+## P2 — Post-v2.0 Core
+
+### SSH Emergency Mode (scoped)
+SSH-based operations limited to: (1) earliest necessary box provisioning before agent
+is installed, and (2) emergency debugging/fixing operations that can't be done via agent.
+NOT a general-purpose DeploymentTarget alternative. The v1.0 `recheck` and `fix-ssh-root.sh`
+patterns are the model. Agent stays the primary management path.
+**Effort:** S (human: 1 week / CC: 1 day)
+**Depends on:** Phase 2 complete (DeploymentTarget interface exists)
+**Source:** CEO review 2026-04-01
+
+### Prometheus Metrics Endpoint
+Add `/metrics` endpoint to labd: resource counts by status, apply duration histograms,
+driver operation latency, fleet pipeline completion rates. Standard Prometheus scraping
+for Grafana dashboards and alerting.
+**Effort:** S (human: 2-3 days / CC: 2-3 hours)
+**Depends on:** Phase 1 (labd exists with resource store)
+**Source:** CEO review 2026-04-01 (observability gap)
+
+## P3 — Future Enhancements
+
+### Infrastructure Graph Visualization
+Visual representation of resource dependencies, environment topology, fleet status.
+Could be a web UI or terminal-based (like `kubectl tree`).
+**Source:** CEO review 2026-04-01
+
+### `labctl import` for Existing Cloud Resources
+Discover and import existing AWS/GCP resources into the state store.
+Pulumi's import functionality could be leveraged.
+**Source:** CEO review 2026-04-01
+
+### Built-in Secrets Rotation
+Automatic rotation of managed secrets (database passwords, API keys).
+Vault handles rotation but a labctl-native workflow could simplify.
+**Source:** CEO review 2026-04-01

bastion/Dockerfile.labd

@@ -11,6 +11,7 @@ WORKDIR /app
 # Copy workspace config and package manifests first (layer cache)
 COPY pnpm-workspace.yaml pnpm-lock.yaml package.json tsconfig.base.json tsconfig.json ./
 COPY src/shared/package.json src/shared/tsconfig.json src/shared/
+COPY src/core/package.json   src/core/tsconfig.json   src/core/
 COPY src/labd/package.json   src/labd/tsconfig.json   src/labd/
 
 # Install all dependencies (dev included -- needed for build)
@@ -22,10 +23,13 @@ RUN pnpm --filter @lab/labd exec prisma generate
 
 # Copy source code
 COPY src/shared/src/ src/shared/src/
+COPY src/core/src/   src/core/src/
 COPY src/labd/src/   src/labd/src/
 
-# Build TypeScript (shared first via project references)
-RUN pnpm --filter @lab/shared build && pnpm --filter @lab/labd build
+# Build TypeScript (shared + core before labd via project references)
+RUN pnpm --filter @lab/shared build \
+ && pnpm --filter @lab/core build \
+ && pnpm --filter @lab/labd build
 
 # Hoist the generated Prisma client so stage 2 can COPY it from a stable path
 RUN mkdir -p /app/_prisma && \
@@ -41,6 +45,7 @@ WORKDIR /app
 # Copy workspace config and package manifests
 COPY pnpm-workspace.yaml pnpm-lock.yaml package.json ./
 COPY src/shared/package.json src/shared/
+COPY src/core/package.json   src/core/
 COPY src/labd/package.json   src/labd/
 
 # Install production dependencies only
@@ -48,6 +53,7 @@ RUN pnpm install --frozen-lockfile --prod 2>/dev/null || pnpm install --prod
 
 # Copy built output from builder
 COPY --from=builder /app/src/shared/dist/ src/shared/dist/
+COPY --from=builder /app/src/core/dist/   src/core/dist/
 COPY --from=builder /app/src/labd/dist/   src/labd/dist/
 
 # Copy Prisma schema + generated client into pnpm store location

bastion/asahi-repo/installer_data.json

@@ -0,0 +1,47 @@
+{
+  "os_list": [
+    {
+      "name": "Fedora Asahi Lab (infra)",
+      "default_os_name": "Fedora Linux Lab",
+      "boot_object": "m1n1.bin",
+      "next_object": "m1n1/boot.bin",
+      "package": "fedora-asahi-lab.zip",
+      "supported_fw": [
+        "12.3",
+        "12.3.1",
+        "13.5"
+      ],
+      "partitions": [
+        {
+          "name": "EFI",
+          "type": "EFI",
+          "size": "524288000B",
+          "format": "fat",
+          "volume_id": "0x804be8a6",
+          "copy_firmware": true,
+          "copy_installer_data": true,
+          "source": "esp"
+        },
+        {
+          "name": "Boot",
+          "type": "Linux",
+          "size": "1073741824B",
+          "image": "boot.img"
+        },
+        {
+          "name": "Root",
+          "type": "Linux",
+          "size": "4626296832B",
+          "expand": false,
+          "image": "root.img"
+        },
+        {
+          "name": "Data",
+          "type": "Linux",
+          "size": "1073741824B",
+          "expand": true
+        }
+      ]
+    }
+  ]
+}

bastion/bastion/.gitignore

@@ -0,0 +1,4 @@
+
+# Asahi build artifacts (large)
+.asahi-cache/
+asahi-repo/*.zip

bastion/completions/labctl.bash

@@ -49,6 +49,9 @@ _labctl() {
     "app k3s list")
       COMPREPLY=($(compgen -W "--user -h --help" -- "$cur"))
       return ;;
+    "app k3s kubeconfig")
+      COMPREPLY=($(compgen -W "--user --context --print -h --help" -- "$cur"))
+      return ;;
     "init bastion")
       COMPREPLY=($(compgen -W "standalone -h --help" -- "$cur"))
       return ;;
@@ -61,15 +64,27 @@ _labctl() {
     "provision reprovision")
       COMPREPLY=($(compgen -W "--role --os --disk -h --help" -- "$cur"))
       return ;;
+    "provision debug")
+      COMPREPLY=($(compgen -W "--pxe-boot -h --help" -- "$cur"))
+      return ;;
     "provision forget")
       COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
-    "provision logs")
+    "provision register")
+      COMPREPLY=($(compgen -W "--role --ip -h --help" -- "$cur"))
+      return ;;
+    "provision asahi")
       COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
+    "provision logs")
+      COMPREPLY=($(compgen -W "-f --follow -h --help" -- "$cur"))
+      return ;;
     "provision makeiso")
       COMPREPLY=($(compgen -W "--arch --local --out -h --help" -- "$cur"))
       return ;;
+    "provision recheck")
+      COMPREPLY=($(compgen -W "--user --target -h --help" -- "$cur"))
+      return ;;
     "config list")
       COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
       return ;;
@@ -86,7 +101,7 @@ _labctl() {
       COMPREPLY=($(compgen -W "deploy status -h --help" -- "$cur"))
       return ;;
     "app k3s")
-      COMPREPLY=($(compgen -W "install health list -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "install health list kubeconfig -h --help" -- "$cur"))
       return ;;
     "version")
       COMPREPLY=($(compgen -W "-h --help" -- "$cur"))
@@ -95,7 +110,7 @@ _labctl() {
       COMPREPLY=($(compgen -W "bastion -h --help" -- "$cur"))
       return ;;
     "provision")
-      COMPREPLY=($(compgen -W "list install reprovision forget logs makeiso -h --help" -- "$cur"))
+      COMPREPLY=($(compgen -W "list install reprovision debug forget register asahi logs makeiso recheck -h --help" -- "$cur"))
       return ;;
     "config")
       COMPREPLY=($(compgen -W "list get set path -h --help" -- "$cur"))

bastion/completions/labctl.fish

@@ -122,9 +122,13 @@ complete -c labctl -n "__labctl_in_cmd init bastion standalone stop" -l dir -d '
 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 register -d 'Register an already-installed machine (e.g. after state loss)'
+complete -c labctl -n "__labctl_using_cmd provision" -a asahi -d 'Show instructions to provision an Apple Silicon Mac with Asahi Linux'
 complete -c labctl -n "__labctl_using_cmd provision" -a logs -d 'Show provisioning logs for a machine (hostname, MAC, or IP)'
 complete -c labctl -n "__labctl_using_cmd provision" -a makeiso -d 'Generate a UEFI-bootable iPXE ISO for network provisioning'
+complete -c labctl -n "__labctl_using_cmd provision" -a recheck -d 'Refresh hardware info for all installed machines via SSH'
 
 # provision install options
 complete -c labctl -n "__labctl_in_cmd provision install" -l role -d 'Machine role (see below)' -xa 'vanilla worker infra labcontroller'
@@ -136,11 +140,25 @@ complete -c labctl -n "__labctl_in_cmd provision reprovision" -l role -d 'Machin
 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
 
+# 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 register options
+complete -c labctl -n "__labctl_in_cmd provision register" -l role -d 'Machine role' -xa 'vanilla worker infra labcontroller'
+complete -c labctl -n "__labctl_in_cmd provision register" -l ip -d 'Machine IP address' -x
+
+# provision logs options
+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
 
+# provision recheck options
+complete -c labctl -n "__labctl_in_cmd provision recheck" -l user -d 'SSH user' -x
+complete -c labctl -n "__labctl_in_cmd provision recheck" -l target -d 'Only recheck a specific machine (by hostname or MAC)' -x
+
 # config subcommands
 complete -c labctl -n "__labctl_using_cmd config" -a list -d 'Show all configuration values'
 complete -c labctl -n "__labctl_using_cmd config" -a get -d 'Get a configuration value'
@@ -172,6 +190,7 @@ complete -c labctl -n "__labctl_in_cmd app labcontroller status" -l user -d 'SSH
 complete -c labctl -n "__labctl_using_cmd app k3s" -a install -d 'Install k3s on a target machine (hostname, IP, or MAC)'
 complete -c labctl -n "__labctl_using_cmd app k3s" -a health -d 'Check k3s health (all hosts if no target given)'
 complete -c labctl -n "__labctl_using_cmd app k3s" -a list -d 'List installed machines and their k3s status'
+complete -c labctl -n "__labctl_using_cmd app k3s" -a kubeconfig -d 'Fetch kubeconfig from a target and merge into ~/.kube/config'
 
 # 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
@@ -185,3 +204,8 @@ complete -c labctl -n "__labctl_in_cmd app k3s health" -l user -d 'SSH user' -x
 # app k3s list options
 complete -c labctl -n "__labctl_in_cmd app k3s list" -l user -d 'SSH user' -x
 
+# app k3s kubeconfig options
+complete -c labctl -n "__labctl_in_cmd app k3s kubeconfig" -l user -d 'SSH user' -x
+complete -c labctl -n "__labctl_in_cmd app k3s kubeconfig" -l context -d 'Context name (defaults to hostname)' -x
+complete -c labctl -n "__labctl_in_cmd app k3s kubeconfig" -l print -d 'Print kubeconfig to stdout instead of merging'
+

bastion/docs/ARCHITECTURE.md

@@ -0,0 +1,538 @@
+# Lab Platform Architecture
+
+## Overview
+
+A bare-metal and hybrid cloud infrastructure platform for automated machine provisioning, Kubernetes cluster management, and fleet operations. The platform discovers hardware via PXE boot, installs operating systems unattended, deploys k3s clusters, and provides centralized management through a CLI and API.
+
+**Components:**
+- **bastion** -- PXE boot server (DHCP/TFTP/HTTP) for machine discovery and OS installation
+- **labd** -- Master daemon for multi-bastion aggregation, persistent state, agent management
+- **labctl** -- CLI tool for operators (kubectl-style interface)
+- **lab-agent** -- Daemon on provisioned servers for remote execution and monitoring
+- **modules** -- Declarative configuration system (k3s, labcontroller)
+
+---
+
+## Architecture
+
+```
+                           labctl (CLI)
+                               |
+                        labd (master daemon)
+                        /    |    \
+                  bastion1  bastion2  ...     (PXE provisioning)
+                    /   \      |
+              [machines]  [machines]           (bare metal)
+                  |           |
+              lab-agent   lab-agent            (remote exec)
+```
+
+### Communication Patterns
+
+| Path | Protocol | Auth |
+|------|----------|------|
+| labctl -> labd | HTTP/HTTPS | mTLS cert (future: token) |
+| bastion -> labd | WebSocket | Join token enrollment |
+| lab-agent -> labd | WebSocket | mTLS certificate |
+| machine -> bastion | HTTP | None (local network) |
+| Anaconda -> bastion | HTTP + UDP syslog | None (install-time) |
+| labctl -> bastion | HTTP | None (standalone mode) |
+
+### Standalone vs Centralized
+
+The bastion can operate in two modes:
+
+1. **Standalone** -- single bastion, state in local JSON file, CLI talks directly to bastion HTTP API
+2. **Centralized** -- bastion registers with labd via WebSocket, state aggregated in CockroachDB, CLI talks to labd which routes commands to the correct bastion
+
+---
+
+## Machine Lifecycle
+
+```
+                     PXE boot
+                        |
+               +--------v--------+
+               |    DISCOVERED   |  Hardware inventory collected
+               +---------+-------+
+                         |
+              labctl provision install
+                         |
+               +---------v-------+
+               |  INSTALL_QUEUE  |  Waiting for next PXE boot
+               +---------+-------+
+                         |
+                   PXE boot (Anaconda)
+                         |
+               +---------v-------+
+               |   INSTALLING    |  Progress: partitioning -> packages -> post-install
+               +---------+-------+
+                         |
+               +---------v-------+
+               |    INSTALLED    |  OS ready, SSH accessible
+               +---------+-------+
+                         |
+              labctl app k3s install
+                         |
+               +---------v-------+
+               |   K3S RUNNING   |  Kubernetes node operational
+               +--------+--------+
+                        |
+              labctl provision reprovision
+                        |
+                   (back to INSTALL_QUEUE)
+```
+
+Side paths:
+- **DEBUG** -- `labctl provision debug` boots Anaconda rescue mode for diagnostics
+- **FORGET** -- `labctl provision forget` removes machine from all state
+
+---
+
+## Multi-architecture PXE
+
+The bastion serves both `x86_64` and `aarch64` over the network. Nothing about this is
+operator-configured -- there is no `--arch` flag, by design.
+
+### How a client's architecture is decided
+
+1. **DHCP option 93** (Client System Architecture) picks the *bootloader*. dnsmasq matches
+   it and hands out a matching iPXE binary:
+
+   | Option 93 | Client | Served |
+   |---|---|---|
+   | `0` | x86 BIOS | `undionly.kpxe` (TFTP) |
+   | `7`, `9` | x64 UEFI | `ipxe.efi` (TFTP) |
+   | `11` | **ARM64 UEFI** | `ipxe-arm64.efi` (TFTP) |
+   | `16` | x64 UEFI HTTP Boot | `http://…/ipxe.efi` |
+   | `19` | **ARM64 UEFI HTTP Boot** | `http://…/ipxe-arm64.efi` |
+
+   Values come from the IANA Processor Architecture Types registry. Note `19`, not `20` --
+   `20` is *pc/at bios boot from http*. EDK2/AAVMF prefers HTTP Boot over TFTP PXE, so the
+   iPXE binaries are staged in **both** `tftpDir` and `httpDir` (symlinked by `main.ts`).
+
+2. **`/dispatch` picks the kernel.** Option 93 never reaches the HTTP endpoint, so
+   `boot.ipxe` passes iPXE's own `${buildarch}` as `?arch=`. `resolveArch()` prefers, in
+   order: the tracked machine record → the reported `?arch=` → the configured default.
+   The record wins because it is what we observed on the machine itself.
+
+### Artifact naming
+
+`x86_64` keeps the original unsuffixed paths so its rendered iPXE scripts are unchanged;
+everything else is suffixed. `kernelPath()` / `initrdPath()` in `templates/boot.ipxe.ts`
+are the single source of truth, used by both the templates and `main.ts` staging.
+
+| arch | kernel | initrd |
+|---|---|---|
+| `x86_64` | `/vmlinuz` | `/initrd.img` |
+| `aarch64` | `/vmlinuz-aarch64` | `/initrd-aarch64.img` |
+
+`tests/ipxe-x86-regression.test.ts` pins the x86_64 output against a golden fixture.
+
+### arm64 gotchas
+
+- **LoadFile2 is mandatory.** arm64 has no `HdrS` boot protocol; the kernel's EFI stub
+  fetches the initrd over the UEFI `EFI_LOAD_FILE2_PROTOCOL`. An iPXE build without it
+  accepts the `initrd` line, silently drops it, and the kernel panics with
+  `VFS: Unable to mount root fs on unknown-block(0,0)`. Fedora's
+  `ipxe-bootimgs-aarch64` implements it; the integration test asserts this up front so
+  the failure names itself instead of looking like a disk problem.
+- **`nomodeset` is x86-only.** On arm64 there is no VGA path to fall back to. aarch64 gets
+  `console=tty0 console=ttyAMA0,115200` instead — the last `console=` wins for
+  `/dev/console`, so serial is the interactive one.
+- **Ubuntu is x86_64-only.** `releases.ubuntu.com` publishes no arm64 netboot artifacts.
+  `osSupportsArch()` encodes this, and both the install guard and `/dispatch` refuse the
+  combination rather than serving an x86 kernel to an ARM machine.
+
+---
+
+## Onboarding classification (vendor OS)
+
+Machines carry an `onboard` field: `"pxe"` (default) or `"ssh"`, plus `vendor_os` naming
+what they run. `classifyOnboard()` in `@lab/shared` sets it from DMI identity, with known
+hardware also matched by MAC — a machine can sit in state for a long time with no DMI, and
+a DMI-only rule would fail open exactly where it matters.
+
+`onboard: "ssh"` means *we cannot rebuild this machine's OS*. Installs are refused at both
+entry points (`/api/install` and the labd `command-install` handler) with an error naming
+the machine and pointing at `provision debug`. **Rescue is never guarded** — being unable
+to reinstall a machine is precisely when a rescue shell is needed.
+
+This is a fact about the machine, not a blocklist. The refusal follows from "no image in
+our pipeline restores `vendor_os`", so adding a DGX OS image to the pipeline is what
+unblocks the DGX Sparks — no entry needs deleting.
+
+Current classifications: NVIDIA DGX Spark (`spark-2935`, `spark-3a1c`) → `dgx-os`.
+
+---
+
+## Packages
+
+### Monorepo Structure
+
+TypeScript ESM monorepo with pnpm workspaces. Six packages:
+
+| Package | Role | Key Tech |
+|---------|------|----------|
+| `@lab/shared` | Types, protocol, constants | - |
+| `@lab/bastion` | PXE server | Fastify, dnsmasq |
+| `@lab/cli` | CLI binary | Commander.js |
+| `@lab/labd` | Master daemon | Fastify, Prisma, CockroachDB |
+| `@lab/agent` | Server agent | WebSocket |
+| `@lab/modules` | Config modules | SSH, k8s-client |
+
+### @lab/shared
+
+Core type system shared by all packages.
+
+**State Model:**
+```typescript
+interface BastionState {
+  discovered:    Record<MAC, HardwareInfo>
+  install_queue: Record<MAC, InstallConfig>
+  installed:     Record<MAC, InstalledInfo>
+  debug:         Record<MAC, DebugConfig>
+}
+```
+
+**Roles:**
+- `vanilla` -- OS only, no k3s, no cluster services
+- `worker` -- k3s agent + Longhorn storage (joins existing cluster)
+- `infra` -- k3s server + etcd (control plane node)
+- `labcontroller` -- infra + bastion + labd + CockroachDB (self-sufficient)
+
+**OS Support:**
+- `fedora-43` -- Anaconda kickstart installer
+- `ubuntu-26.04` -- cloud-init autoinstall
+
+**Protocol:** Discriminated union message types for WebSocket communication between agents, bastions, and labd. Type guards and parsers for runtime validation.
+
+### @lab/bastion
+
+PXE boot server that handles the physical provisioning lifecycle.
+
+**Services:**
+- `StateManager` -- JSON file persistence with immutable update pattern
+- `SyslogListener` -- UDP syslog receiver (port 5514) for Anaconda install logs
+- `InstallLogBuffer` -- In-memory ring buffer + disk persistence per machine
+- `BastionConnection` -- WebSocket client to labd for centralized mode
+- dnsmasq management (spawn, config generation, proxy/full DHCP)
+- Network auto-detection (interface, IP, subnet, gateway)
+- ISO builder (xorriso + mtools for non-PXE machines)
+
+**HTTP Routes:**
+
+| Endpoint | Purpose |
+|----------|---------|
+| `GET /dispatch?mac=` | Dynamic iPXE script (discover/install/debug/local-boot) |
+| `GET /ks?mac=` | Per-machine Anaconda kickstart |
+| `GET /debug.ks` | Rescue mode kickstart |
+| `GET /debug-setup.sh` | nc listener setup script for rescue shell |
+| `GET /discover.ks` | Hardware discovery kickstart |
+| `POST /api/discover` | Hardware inventory report |
+| `POST /api/install` | Queue machine for install |
+| `POST /api/progress` | Install progress callback |
+| `POST /api/log` | Raw log line ingestion |
+| `POST /api/debug` | Queue debug/rescue mode |
+| `GET /api/machines` | List all machines |
+| `GET /api/logs/:mac` | Install logs + progress |
+| `GET /api/logs/:mac/follow` | SSE stream of progress events |
+| `DELETE /api/machines/:mac` | Forget machine |
+
+**Templates:**
+- `boot.ipxe.ts` -- iPXE scripts for each boot mode (discover, install, debug, pxe-boot-debug, local-boot)
+- `install.ks.ts` -- Full Fedora kickstart with LVM, SSH, k3s prereqs, progress callbacks, SysRq keys
+- `debug.ks.ts` -- Minimal rescue kickstart (SSH via inst.sshd)
+- `ubuntu-autoinstall.ts` -- cloud-init for Ubuntu
+- `dnsmasq.conf.ts` -- DHCP/TFTP configuration
+
+**Boot Dispatch Logic:**
+```
+1. debug[mac]?        -> renderDebugIpxe (auto-clear after serving)
+2. install_queue[mac]? -> renderInstallIpxe
+3. installed[mac]?    -> renderLocalBootIpxe (exit to disk)
+4. unknown            -> renderDiscoverIpxe
+```
+
+### @lab/labd
+
+Central management daemon. Aggregates multiple bastions, stores persistent state in CockroachDB, relays commands, manages agent fleet.
+
+**Database (Prisma + CockroachDB):**
+- `Server` -- hostname, MAC, IP, role, status, cloud, environment, labels
+- `Bastion` -- hostname, network, serverIp, lastHeartbeat
+- `Agent` -- certificate, enrollment, heartbeat
+- `Cluster` -- name, cloud, environment, kubeconfig (encrypted)
+- `User` / `Role` / `Permission` -- RBAC (action:cloud:env:server matrix)
+- `JoinToken` -- one-time/reusable enrollment tokens
+- `AuditLog` -- action, resource, result, timestamp
+
+**Key Services:**
+- `BastionRegistry` -- in-memory registry of connected bastions, state aggregation, MAC-to-bastion routing
+- `AgentRegistry` -- connected agents, heartbeat tracking
+- `MessageRouter` -- command relay between CLI/agents and bastions
+
+**Command Routing:**
+```
+CLI: labctl provision install <mac> <hostname>
+  -> POST /api/machines/install
+  -> labd finds bastion that knows this MAC
+  -> WebSocket: {type: "command-install", mac, hostname, disk, role}
+  -> bastion updates install_queue
+  -> WebSocket: {type: "command-response", status: "ok"}
+  -> HTTP response to CLI
+```
+
+### @lab/cli (labctl)
+
+Operator CLI. Commander.js binary, distributed as RPM/DEB or standalone bun-compiled executable.
+
+**Command Groups:**
+
+```
+labctl init bastion standalone start|stop|status
+labctl provision list|install|reprovision|forget|debug|logs|makeiso
+labctl app k3s install|health|list
+labctl config list|get|set|path
+labctl login
+labctl doctor
+labctl roles
+```
+
+**Key Features:**
+- Target resolution: hostname, MAC, or IP -> machine lookup
+- SSH reboot into PXE for reprovision/debug (efibootmgr --bootnext)
+- Follow mode: `labctl provision logs <target> -f` (5s polling)
+- Shell completions: bash, fish
+
+### @lab/modules
+
+Declarative configuration modules with three-phase lifecycle: install -> configure -> health.
+
+**k3s Module:**
+- 5 operation groups: host-prep, networking, k3s-server, k3s-agent, hardening
+- 15+ individual operations: kernel modules, sysctl, firewall, Cilium CNI, SELinux, audit policy, pod security, cert checks
+- Health checks: service running, node ready, API health, pod status, Cilium status, secrets encryption
+- SSH execution backend with progress callbacks
+
+### @lab/agent
+
+Daemon on provisioned servers. WebSocket to labd for:
+- Heartbeat (hostname, uptime, CPU/mem usage)
+- Command execution (with stdout/stderr streaming)
+- Log streaming (journalctl relay)
+- mTLS certificate enrollment and rotation
+
+---
+
+## Disk Layout
+
+### LVM Partitioning (labvg)
+
+All roles share a common LVM layout. The kickstart `%pre` auto-detects the install disk (NVMe preferred, then SATA, skipping USB/removable).
+
+| Volume | Size | FS | Reprovision |
+|--------|------|-----|-------------|
+| `/boot/efi` | 600 MB | vfat | Reused |
+| `/boot` | 3 GB | ext4 | Reused |
+| `swap` | 27 GB | swap | Recreated |
+| `/` (root) | 33 GB | xfs | Recreated |
+| `/var` | 100 GB | xfs | Recreated |
+| `/var/log` | 10 GB | xfs | Recreated |
+| `/home` | 10 GB | xfs | **Preserved** |
+| `/srv` | 20 GB | xfs | **Preserved** |
+| `/var/lib/longhorn` | remaining | xfs | **Preserved** (worker) |
+| `/var/lib/rancher` | 20 GB | xfs | **Preserved** (infra) |
+| `/tmp` | 4 GB | tmpfs | - |
+
+Reprovision detection: if `labvg` VG exists, reuse EFI/boot partitions and preserve data volumes.
+
+---
+
+## Kickstart Features
+
+The Fedora kickstart template (`install.ks.ts`) includes:
+
+- **Dynamic disk detection** -- `%pre` probes NVMe/SATA/virtio, skips USB/removable, supports both fresh install and reprovision
+- **Progress callbacks** -- `curl -sf POST /api/progress` at each stage (partitioning, post-install substeps, complete)
+- **Anaconda syslog forwarding** -- `logging --host --port` streams real-time install logs to bastion
+- **SSH hardening** -- key-only auth, root login via pubkey only, admin user with passwordless sudo
+- **Network-first boot order** -- `efibootmgr` reorders boot entries so PXE is always first (bastion controls every reboot)
+- **SysRq magic keys** -- `kernel.sysrq=1` for emergency reboot via KVM keyboard
+- **Role-specific setup:**
+  - `vanilla`: chronyd only
+  - `worker`/`infra`: kernel modules (br_netfilter, overlay), sysctl (ip_forward, inotify), firewalld disabled, k3s binary installed
+  - `infra`: k3s server binary pre-installed
+
+**What is NOT in the kickstart:**
+- `console=ttyS0` -- causes 30s-per-step boot timeout on hardware without physical serial UART (discovered 2026-03-30, see docs/pxe-boot-debugging-2026-03-30.md)
+- Background log streamer (`tail -f`) -- prevents Anaconda from syncing filesystem, causes %post writes to not persist
+
+---
+
+## Deployment
+
+### Container Images
+
+**bastion** (`Dockerfile.bastion`):
+- Base: Fedora 43 (needs dnsmasq, iPXE)
+- Multi-stage: Alpine build -> Fedora runtime
+- iPXE rebuilt from source (SNP driver for EFI)
+- hostNetwork in k8s (DHCP needs raw sockets)
+- Capabilities: NET_ADMIN, NET_RAW
+
+**labd** (`Dockerfile.labd`):
+- Base: Alpine (minimal)
+- Multi-stage build with Prisma client generation
+- Runs as non-root `node` user
+
+### Kubernetes (k3s)
+
+```
+Namespace: lab-infra
+  Deployment: bastion (hostNetwork, PVC for /data, host SSH keys)
+  ConfigMap: bastion-config (env vars)
+  Secret: bastion-join-token
+  PVC: bastion-state (local-path)
+
+Namespace: lab-system
+  Deployment: labd
+  Service: labd (NodePort 30100)
+  StatefulSet: cockroachdb-0
+```
+
+### CLI Distribution
+
+Built with `nfpm` as RPM/DEB. Includes:
+- `/usr/bin/labctl` (bun-compiled standalone binary)
+- `/usr/share/bash-completion/completions/labctl`
+- `/usr/share/fish/vendor_completions.d/labctl.fish`
+
+Config: `~/.labctl/config.yaml` with `labdUrl`, output format, default cloud/environment.
+
+---
+
+## Build & Release
+
+```bash
+# Development
+pnpm install && pnpm build      # Compile all packages
+pnpm test:run                    # Unit tests (vitest)
+npx tsc --noEmit                 # Type check
+
+# Deploy
+bash scripts/deploy.sh all       # Build containers + RPM, push, restart pods
+bash scripts/deploy.sh bastion   # Just bastion
+bash scripts/deploy.sh labd      # Just labd
+bash scripts/deploy.sh labctl    # Just CLI (local RPM install)
+
+# Container builds
+bash scripts/build-bastion.sh --platforms linux/amd64 --push latest
+bash scripts/build-labd.sh --platforms linux/amd64 --push latest
+bash scripts/build-rpm.sh        # RPM + DEB packages
+
+# Integration tests (require libvirt, sudo)
+sudo tests/integration/run-pxe-test.sh
+```
+
+Registry: `mysources.co.uk` (Gitea at 10.0.0.194:3012)
+
+---
+
+## Testing
+
+### Unit Tests
+- Kickstart rendering (ksvalidator syntax check, partition layout, role-specific sections)
+- State management (load, save, update, debug field)
+- Dispatch routing (correct iPXE script for each machine state)
+- Syslog listener (UDP receive, IP->MAC resolution, RFC 3164 parsing)
+
+### Integration Tests (libvirt VMs)
+- **pxe-provision.test.ts** -- Full end-to-end: create VM -> PXE discovery -> queue install -> Anaconda install -> SSH verification -> systemd health -> SELinux enforcing -> boot order check
+- **iso-provision.test.ts** -- ISO boot for non-PXE machines
+- **k3s-single-node.test.ts** -- Post-provision k3s installation and health
+- VM screenshot capture during boot for debugging
+
+---
+
+## Security
+
+- **mTLS** for agent-labd communication (certificate enrollment via join tokens)
+- **SSH key-only auth** on provisioned machines (no password auth)
+- **SELinux enforcing** verified in integration tests
+- **RBAC** (planned): action:cloud:environment:server permission matrix
+- **Audit logging** (planned): every mutation tracked in CockroachDB
+- **Network-first boot order** prevents machines from booting without bastion approval
+- **SysRq keys** enabled for emergency reboot without SSH access
+
+---
+
+## Known Issues & Lessons Learned
+
+### Serial Console Boot Delay (2026-03-30)
+`console=ttyS0,115200n8` in kernel cmdline causes 30-second timeout at every systemd boot phase on hardware without a physical serial UART. Root cause: systemd blocks writing to non-existent UART. Fix: removed from kickstart entirely.
+
+### Anaconda %post Log Streamer
+Background `tail -f` in kickstart `%post` prevents Anaconda from syncing the filesystem. All file writes in %post appear to succeed but are lost on reboot. Fix: removed background log streamer, replaced with Anaconda's built-in `logging --host --port` syslog forwarding.
+
+### Disk Auto-Detection
+Hardcoded `/dev/sda` default broke NVMe-only machines. Fix: default to empty string (auto-detect) which triggers the `%pre` disk probe logic.
+
+### Anaconda Rescue Mode Limitations
+`%pre` and `%post` sections do not execute in `inst.rescue` mode. SSH in rescue mode is provided by Anaconda's `inst.sshd` kernel parameter + `sshpw` kickstart directive. Manual setup via `curl bastion:8080/debug-setup.sh | bash` for nc listener.
+
+**Unresolved (2026-08-11): rescue SSH has never been observed working.** Adding the first
+integration coverage for `provision debug` (`tests/integration/pxe-rescue.test.ts`) showed the
+rescue environment coming up correctly — the bastion serves the kernel and initrd, Anaconda
+boots, fetches `debug.ks`, and reaches its installer environment — but **nothing ever listens on
+port 22**.
+
+Strength of the evidence, stated precisely because it decides where to look next:
+- **aarch64 — direct.** Port 22 probed every 20s for 30 minutes while the Anaconda installer
+  environment was demonstrably running (NetworkManager, polkitd, rsyslog on the console). Never
+  opened.
+- **x86_64 — corroborating, not conclusive.** One clean KVM run (943s) where SSH never became
+  available inside a 15-minute budget. That VM's progress into the rescue environment was *not*
+  observed — vitest's final reporter discards the streamed log — so it is consistent with the
+  aarch64 result but does not independently prove it. Re-run with `KEEP_VM=1` and probe port 22
+  directly to settle it.
+
+If the x86_64 result holds up, this is orthogonal to the multi-architecture work, since x86_64 is
+untouched by it. Leads worth checking, in order:
+- Does `inst.sshd` actually start `sshd` in `inst.rescue` mode, or only in install mode? The
+  port never opens, so this is the prime suspect — an auth problem would still show an open port.
+- `sshkey` may apply only to the *installed* system, leaving the installer environment
+  password-only via `sshpw`. That would matter once sshd does listen: the test authenticates
+  key-only (`BatchMode=yes`).
+- The `%anaconda`-context directives in `debug.ks` may be skipped entirely when a kickstart is
+  supplied alongside `inst.rescue`.
+
+Until this is resolved, `provision debug` gets you a booted rescue environment on the console
+(including on arm64), but not an SSH shell. The `debug-setup.sh` nc-listener path is the
+documented workaround and is unaffected.
+
+---
+
+## Planned Work (Taskmaster)
+
+13 tasks in queue, all pending:
+
+1. **#72** Expand Prisma schema with resource relationships (Network, ServerNic, ServerDisk, ClusterMember)
+2. **#73** State persistence service (bastion state -> CockroachDB)
+3. **#74** State loading from labd on bastion startup
+4. **#75** Fix bastion --dir env var default
+5. **#76** Resource type registry with aliases (kubectl-style)
+6. **#77** `labctl get <resource>` command
+7. **#78** `labctl describe <resource>` command
+8. **#79** `labctl create/delete` commands
+9. **#80** Refactor provision commands to kubectl-style
+10. **#81** Server and resource API endpoints in labd
+11. **#82** RBAC permission checks in CLI
+12. **#83** Audit logging for resource operations
+13. **#84** Update CLI entry point and help text
+
+Additional items not in taskmaster:
+- Ubuntu autoinstall disk auto-detect (still defaults to /dev/sda)
+- Verify `inst.sshd` works end-to-end in rescue mode
+- k3s cluster join vs new cluster distinction in `labctl app k3s install`
+- arm64 container build (iPXE cross-compilation broken)

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/docs/pxe-boot-debugging-2026-03-30.md

@@ -0,0 +1,91 @@
+# PXE Boot Debugging Session — 2026-03-30
+
+## Problem
+Beelink SER Mini Pro (AMD Ryzen 7 255, Radeon 780M, 64GB DDR5, 1TB NVMe) boots Fedora 43 100x slower than normal after PXE kickstart install. Every systemd boot phase takes ~30 seconds. The Anaconda installer/rescue mode boots fast on the same hardware.
+
+## Root Cause
+**`console=ttyS0,115200n8` in kernel cmdline** — added via kickstart `bootloader --append` during install.
+
+This mini PC has **no physical serial UART**. When systemd writes to ttyS0, each log write blocks for ~30 seconds waiting for the non-existent UART hardware. Since systemd logs at every phase transition, the total boot time was 10+ minutes.
+
+The Anaconda installer was unaffected because it uses a different init flow that doesn't go through the same systemd phase transitions.
+
+## How We Found It
+Hours of systematic elimination:
+
+| What we tried | Result | Ruled out |
+|---|---|---|
+| `modprobe.blacklist=amdgpu` | No change | GPU driver |
+| `amd_iommu=off` | No change | IOMMU |
+| Rebuild initramfs without plymouth/drm/fips | No change | Initramfs bloat |
+| systemd-boot instead of GRUB | Still slow | Bootloader |
+| PXE-boot kernel+initrd (skip local GRUB entirely) | Still slow | Local bootloader/firmware |
+| Disable TPM in BIOS | No change | TPM |
+| Remove `resume=` + resume dracut module | No change | Hibernate resume |
+| Manual LVM activation in rescue shell | **Fast** | NVMe/LVM themselves |
+| Remove `console=ttyS0,115200n8` from GRUB | **FAST BOOT** | **This was it** |
+
+The key breakthrough was noticing the timestamps showed **exactly 30-second gaps** between boot phases — a timeout pattern, not general slowness. Then realising the serial console was added during install and had never been tested without.
+
+## What Was Fixed (PR #4, merged)
+
+### 1. Removed serial console from kickstart
+- Removed `console=ttyS0,115200n8` from `bootloader --append`
+- Removed `serial-getty@ttyS0.service` enablement
+- Removed rsyslog serial forwarding
+
+### 2. Enabled Anaconda syslog forwarding
+- Uncommented `logging --host --port` directive in kickstart
+- Bastion's SyslogListener was already built — just needed IP→MAC resolution improvement
+- Added `registerIp()` calls from kickstart fetch and progress callbacks
+- Added syslog listener unit tests
+
+### 3. Fixed disk auto-detection
+- Default disk changed from `/dev/sda` to `""` (auto-detect) in labd route and bastion command handler
+- The kickstart `%pre` auto-detect logic probes nvme0n1, sda, sdb, vda in order
+- Without this fix, NVMe-only machines (like the SER Mini Pro) fail immediately
+
+### 4. SysRq magic keys
+- Added `kernel.sysrq=1` sysctl to kickstart `%post`
+- Enables Alt+SysRq+REISUB via JetKVM for emergency reboot of stuck machines
+
+### 5. Simplified debug command
+- Removed `--sshd` flag (SSH always available via `inst.sshd` + `sshpw` in rescue mode)
+- Added `/debug-setup.sh` HTTP endpoint for nc listener setup from rescue shell
+- Cleaned up `sshd` field from DebugConfig, protocol types, all routes
+
+### 6. Added `labctl provision logs -f`
+- Follow mode with 5-second polling for real-time install monitoring
+
+## What Works
+
+- **PXE discovery → install → boot** — full flow works end-to-end
+- **Anaconda syslog forwarding** — install logs stream to bastion
+- **Progress callbacks** — stage-by-stage install tracking via curl
+- **Auto disk detection** — works for NVMe and SATA
+- **Debug rescue mode** — `labctl provision debug <target>` boots Anaconda rescue with SSH
+- **Network-first boot order** — bastion controls every reboot via efibootmgr
+- **SysRq keys** — emergency reboot via JetKVM keyboard
+
+## What Doesn't Work / Known Issues
+
+- **`--sshd` in rescue mode** — Anaconda rescue mode skips both `%pre` and `%post` kickstart sections. `inst.sshd` + `sshpw` should provide SSH access, but hasn't been verified end-to-end yet. The `/debug-setup.sh` curl workaround exists for nc.
+- **arm64 container build** — iPXE cross-compilation fails on arm64 (GCC flag incompatibility). Workaround: build with `--platforms linux/amd64` only.
+- **Integration test SSH timeout** — VM boots fine but SSH times out due to libvirt nftables reject rules after VM restart. Test infrastructure issue, not a code bug.
+
+## What Was Skipped / Left To Do
+
+1. **Syslog UDP port in k3s** — works because bastion uses `hostNetwork: true`, but should be documented properly
+2. **Background log streamer** — the old `tail -f` approach broke Anaconda filesystem sync. Replaced with syslog forwarding. If more granular %post logging is needed, a synchronous log push at end of %post would be safe.
+3. **Per-machine hardware overrides** — turned out not to be needed (serial console was the only "special" setting, and removing it is universal)
+4. **Ubuntu autoinstall disk default** — `ubuntu-autoinstall.ts` still has `disk || "/dev/sda"` fallback (line 38), should be changed to auto-detect
+5. **Verify `inst.sshd` works in rescue mode** — test SSH with password "debug" next time debug mode is used
+6. **Re-enable TPM in BIOS** — was disabled during debugging, should be factory-reset (user plans to reset BIOS to factory)
+
+## Key Learnings
+
+1. **`console=ttyS0` on hardware without UART = 30s timeout per boot phase.** Never add serial console to kernel cmdline unless the hardware has a verified physical UART.
+2. **Exactly-N-second gaps in boot logs = timeout, not slowness.** Look for the timeout source, not performance issues.
+3. **The bisection approach works.** Systematically removing features one at a time found the root cause. But it took hours because the serial console was added early and seemed harmless.
+4. **Anaconda rescue mode is limited.** It skips `%pre` and `%post`, so you can't automate setup via kickstart. Use `inst.sshd` + `sshpw` for SSH, and serve helper scripts via HTTP for everything else.
+5. **Default disk paths break NVMe machines.** Always default to auto-detect (empty string) rather than `/dev/sda`.

bastion/package.json

@@ -22,7 +22,17 @@
     "test:integration:iso": "vitest run -c tests/integration/vitest.config.ts -t 'ISO boot'",
     "test:integration:iso:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'ISO boot'",
     "test:integration:arm-iso": "vitest run -c tests/integration/vitest.config.ts -t 'ARM ISO'",
-    "test:integration:arm-iso:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'ARM ISO'"
+    "test:integration:arm-iso:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'ARM ISO'",
+    "test:integration:rescue": "vitest run -c tests/integration/vitest.config.ts -t 'x86 rescue boot'",
+    "test:integration:rescue:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'x86 rescue boot'",
+    "test:integration:arm-pxe": "vitest run -c tests/integration/vitest.config.ts -t 'ARM PXE rescue'",
+    "test:integration:arm-pxe:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'ARM PXE rescue'",
+    "test:integration:arm-pxe-full": "ARM_PXE_FULL=1 vitest run -c tests/integration/vitest.config.ts -t 'ARM PXE'",
+    "test:integration:arm-pxe-full:host": "sudo -E ARM_PXE_FULL=1 $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'ARM PXE'",
+    "test:integration:asahi": "vitest run -c tests/integration/vitest.config.ts -t 'asahi firstboot'",
+    "test:integration:asahi:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'asahi firstboot'",
+    "test:integration:asahi-validate": "vitest run -c tests/integration/vitest.config.ts -t 'asahi.*validation'",
+    "test:integration:asahi-validate:host": "sudo -E $(which npx) vitest run -c tests/integration/vitest.config.ts -t 'asahi.*validation'"
   },
   "engines": {
     "node": ">=20.0.0",

bastion/scripts/build-asahi-rootfs.sh

@@ -0,0 +1,302 @@
+#!/bin/bash
+# Build a custom Fedora Asahi Remix rootfs with lab firstboot LVM setup.
+#
+# Downloads the upstream Fedora Asahi Remix Server package, injects our
+# firstboot script + systemd service, and repackages it for the bastion.
+#
+# Requirements: root, curl, unzip, mount (loop), zip
+# Output: bastion/asahi-repo/ directory with package + installer_data.json
+#
+# Usage: sudo ./scripts/build-asahi-rootfs.sh [--bastion-ip IP] [--http-port PORT]
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PROJECT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+ASAHI_DIR="$PROJECT_DIR/asahi-repo"
+CACHE_DIR="$PROJECT_DIR/.asahi-cache"
+WORK_DIR=""
+
+# Defaults
+BASTION_IP="${BASTION_IP:-192.168.8.23}"
+HTTP_PORT="${HTTP_PORT:-8080}"
+ROLE="${ROLE:-infra}"
+HOSTNAME="${HOSTNAME:-mac-studio}"
+MAC="${MAC:-00:00:00:00:00:00}"
+ADMIN_USER="${ADMIN_USER:-michal}"
+
+# Parse args
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        --bastion-ip) BASTION_IP="$2"; shift 2 ;;
+        --http-port) HTTP_PORT="$2"; shift 2 ;;
+        --role) ROLE="$2"; shift 2 ;;
+        --hostname) HOSTNAME="$2"; shift 2 ;;
+        --mac) MAC="$2"; shift 2 ;;
+        --admin-user) ADMIN_USER="$2"; shift 2 ;;
+        *) echo "Unknown option: $1"; exit 1 ;;
+    esac
+done
+
+# ── Resolve upstream package URL ─────────────────────────────────
+echo "==> Fetching Asahi installer data..."
+INSTALLER_DATA=$(curl -sfL "https://cdn.asahilinux.org/installer/installer_data.json")
+
+# Find the Server variant package URL
+SERVER_URL=$(echo "$INSTALLER_DATA" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+for os in data.get('os_list', []):
+    name = os.get('name', '').lower()
+    if 'server' in name and 'uefi' not in name and not os.get('expert'):
+        print(os['package'])
+        break
+" 2>/dev/null)
+
+if [ -z "$SERVER_URL" ]; then
+    echo "ERROR: Could not find Fedora Asahi Remix Server in installer data."
+    echo "Available variants:"
+    echo "$INSTALLER_DATA" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+for os in data.get('os_list', []):
+    print(f\"  - {os.get('name', '?')}\")" 2>/dev/null
+    exit 1
+fi
+
+PACKAGE_NAME=$(basename "$SERVER_URL")
+echo "    Variant: Fedora Asahi Remix Server"
+echo "    Package: $PACKAGE_NAME"
+
+# Also extract the partition layout and supported_fw from upstream
+UPSTREAM_CONFIG=$(echo "$INSTALLER_DATA" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+for os in data.get('os_list', []):
+    name = os.get('name', '').lower()
+    if 'server' in name and 'uefi' not in name and not os.get('expert'):
+        json.dump(os, sys.stdout)
+        break
+")
+
+# ── Download upstream package ────────────────────────────────────
+mkdir -p "$CACHE_DIR" "$ASAHI_DIR"
+
+CACHED_PKG="$CACHE_DIR/$PACKAGE_NAME"
+if [ -f "$CACHED_PKG" ]; then
+    echo "==> Using cached package: $CACHED_PKG"
+else
+    echo "==> Downloading $SERVER_URL..."
+    curl -# -L -o "$CACHED_PKG" "$SERVER_URL"
+fi
+
+# ── Extract and modify rootfs ────────────────────────────────────
+WORK_DIR=$(mktemp -d)
+trap 'echo "==> Cleaning up..."; umount "$WORK_DIR/rootfs" 2>/dev/null || true; rm -rf "$WORK_DIR"' EXIT
+
+echo "==> Extracting package..."
+unzip -q -o "$CACHED_PKG" -d "$WORK_DIR/pkg"
+
+# List contents
+echo "    Package contents:"
+ls -lh "$WORK_DIR/pkg/" | grep -v ^total | while read -r line; do echo "      $line"; done
+
+# Find root.img
+ROOT_IMG=$(find "$WORK_DIR/pkg" -name "root.img" -type f | head -1)
+if [ -z "$ROOT_IMG" ]; then
+    echo "ERROR: root.img not found in package."
+    echo "Contents: $(ls "$WORK_DIR/pkg/")"
+    exit 1
+fi
+
+echo "==> Mounting root.img..."
+mkdir -p "$WORK_DIR/rootfs"
+mount -o loop "$ROOT_IMG" "$WORK_DIR/rootfs"
+
+# ── Read SSH keys from the system ────────────────────────────────
+SSH_KEYS=""
+REAL_USER="${SUDO_USER:-$USER}"
+REAL_HOME=$(eval echo "~$REAL_USER")
+for keyfile in "$REAL_HOME/.ssh/id_ed25519.pub" "$REAL_HOME/.ssh/id_ecdsa.pub" "$REAL_HOME/.ssh/id_rsa.pub"; do
+    if [ -f "$keyfile" ]; then
+        SSH_KEYS=$(cat "$keyfile")
+        echo "    SSH key: $keyfile"
+        break
+    fi
+done
+
+if [ -z "$SSH_KEYS" ]; then
+    echo "WARNING: No SSH public key found. You'll need to add keys manually."
+fi
+
+# ── Generate firstboot script from bastion ───────────────────────
+echo "==> Generating firstboot script..."
+
+# Try to get the script from a running bastion, fall back to local generation
+FIRSTBOOT_SCRIPT=""
+FIRSTBOOT_URL="http://$BASTION_IP:$HTTP_PORT/asahi/firstboot.sh?hostname=$HOSTNAME&role=$ROLE&mac=$MAC&user=$ADMIN_USER"
+FIRSTBOOT_SCRIPT=$(curl -sf "$FIRSTBOOT_URL" 2>/dev/null || echo "")
+
+if [ -z "$FIRSTBOOT_SCRIPT" ]; then
+    echo "    Bastion not reachable, generating script locally..."
+    # Generate a basic firstboot script inline
+    FIRSTBOOT_SCRIPT=$(cd "$PROJECT_DIR" && node -e "
+const { renderFirstbootScript } = require('./src/bastion/dist/templates/asahi-firstboot.sh.js');
+process.stdout.write(renderFirstbootScript({
+    hostname: '$HOSTNAME',
+    role: '$ROLE',
+    serverIp: '$BASTION_IP',
+    httpPort: $HTTP_PORT,
+    sshKeys: $([ -n "$SSH_KEYS" ] && echo "[\"$SSH_KEYS\"]" || echo "[]"),
+    adminUser: '$ADMIN_USER',
+    mac: '$MAC',
+}));
+" 2>/dev/null) || {
+        echo "    ERROR: Could not generate firstboot script. Build the project first: npm run build"
+        exit 1
+    }
+fi
+
+# ── Inject files into rootfs ─────────────────────────────────────
+echo "==> Injecting lab configuration into rootfs..."
+
+# Firstboot script
+mkdir -p "$WORK_DIR/rootfs/usr/local/bin"
+echo "$FIRSTBOOT_SCRIPT" > "$WORK_DIR/rootfs/usr/local/bin/lab-firstboot.sh"
+chmod 755 "$WORK_DIR/rootfs/usr/local/bin/lab-firstboot.sh"
+echo "    Installed: /usr/local/bin/lab-firstboot.sh"
+
+# Systemd service
+mkdir -p "$WORK_DIR/rootfs/etc/systemd/system"
+cat > "$WORK_DIR/rootfs/etc/systemd/system/lab-firstboot.service" << 'UNIT'
+[Unit]
+Description=Lab first-boot LVM setup
+After=local-fs.target network-online.target
+Wants=network-online.target
+ConditionPathExists=!/etc/lab-lvm-setup-done
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/lab-firstboot.sh
+RemainAfterExit=yes
+StandardOutput=journal+console
+StandardError=journal+console
+
+[Install]
+WantedBy=multi-user.target
+UNIT
+echo "    Installed: /etc/systemd/system/lab-firstboot.service"
+
+# Enable the service
+mkdir -p "$WORK_DIR/rootfs/etc/systemd/system/multi-user.target.wants"
+ln -sf /etc/systemd/system/lab-firstboot.service \
+    "$WORK_DIR/rootfs/etc/systemd/system/multi-user.target.wants/lab-firstboot.service"
+echo "    Enabled: lab-firstboot.service"
+
+# SSH authorized keys for root (for initial access before firstboot runs user creation)
+if [ -n "$SSH_KEYS" ]; then
+    mkdir -p "$WORK_DIR/rootfs/root/.ssh"
+    chmod 700 "$WORK_DIR/rootfs/root/.ssh"
+    echo "$SSH_KEYS" > "$WORK_DIR/rootfs/root/.ssh/authorized_keys"
+    chmod 600 "$WORK_DIR/rootfs/root/.ssh/authorized_keys"
+    echo "    Installed: /root/.ssh/authorized_keys"
+fi
+
+# Ensure lvm2 and xfsprogs are installed (should be in server image already)
+echo "    Checking required packages..."
+if [ -f "$WORK_DIR/rootfs/usr/sbin/pvcreate" ] || [ -f "$WORK_DIR/rootfs/usr/bin/pvcreate" ]; then
+    echo "      lvm2: present"
+else
+    echo "      WARNING: lvm2 not found in rootfs. LVM setup may fail."
+fi
+if [ -f "$WORK_DIR/rootfs/usr/sbin/mkfs.xfs" ] || [ -f "$WORK_DIR/rootfs/usr/bin/mkfs.xfs" ]; then
+    echo "      xfsprogs: present"
+else
+    echo "      WARNING: xfsprogs not found in rootfs. LVM setup may fail."
+fi
+
+# ── Unmount and repackage ────────────────────────────────────────
+echo "==> Unmounting rootfs..."
+umount "$WORK_DIR/rootfs"
+
+echo "==> Repackaging..."
+OUTPUT_PKG="$ASAHI_DIR/fedora-asahi-lab.zip"
+rm -f "$OUTPUT_PKG"
+(cd "$WORK_DIR/pkg" && zip -q "$OUTPUT_PKG" *)
+echo "    Output: $OUTPUT_PKG ($(du -sh "$OUTPUT_PKG" | cut -f1))"
+
+# ── Generate installer_data.json ─────────────────────────────────
+echo "==> Generating installer_data.json..."
+
+# Parse upstream config to get supported_fw, boot_object, next_object, and partition details
+python3 << PYEOF > "$ASAHI_DIR/installer_data.json"
+import json, sys
+
+upstream = json.loads('''$UPSTREAM_CONFIG''')
+
+# Build our custom installer data based on upstream
+# Keep EFI and Boot partitions identical, modify Root to not expand,
+# add Data partition that expands for LVM.
+partitions = []
+for p in upstream.get('partitions', []):
+    if p.get('type') == 'EFI':
+        partitions.append(p)
+    elif p.get('name') == 'Boot':
+        partitions.append(p)
+    elif p.get('name') == 'Root':
+        # Fixed size root, no expand
+        root_p = dict(p)
+        root_p['expand'] = False
+        # Keep the original size (it's the minimum needed for the rootfs)
+        partitions.append(root_p)
+
+# Add Data partition for LVM
+partitions.append({
+    "name": "Data",
+    "type": "Linux",
+    "size": "1073741824B",  # 1GB minimum, will expand
+    "expand": True
+})
+
+data = {
+    "os_list": [{
+        "name": "Fedora Asahi Lab (${ROLE})",
+        "default_os_name": "Fedora Linux Lab",
+        "boot_object": upstream.get("boot_object", "m1n1.bin"),
+        "next_object": upstream.get("next_object", "m1n1/boot.bin"),
+        "package": "fedora-asahi-lab.zip",
+        "supported_fw": upstream.get("supported_fw", ["13.5"]),
+        "partitions": partitions,
+    }]
+}
+
+json.dump(data, sys.stdout, indent=2)
+print()
+PYEOF
+
+echo "    Generated: $ASAHI_DIR/installer_data.json"
+
+# Pretty-print the partition layout
+echo ""
+echo "    Partition layout:"
+python3 -c "
+import json
+with open('$ASAHI_DIR/installer_data.json') as f:
+    data = json.load(f)
+for p in data['os_list'][0]['partitions']:
+    size = p.get('size', '?')
+    expand = ' (expand)' if p.get('expand') else ''
+    image = f\" [{p['image']}]\" if 'image' in p else ''
+    print(f\"      {p['name']:8s} {p['type']:8s} {size:>16s}{expand}{image}\")
+"
+
+echo ""
+echo "==> Build complete!"
+echo ""
+echo "    Package: $ASAHI_DIR/fedora-asahi-lab.zip"
+echo "    Config:  $ASAHI_DIR/installer_data.json"
+echo ""
+echo "    To serve from bastion, copy to the bastion's HTTP directory"
+echo "    or configure REPO_BASE to point here."
+echo ""
+echo "    To install on Mac Studio:"
+echo "      curl http://$BASTION_IP:$HTTP_PORT/asahi | sh"

bastion/scripts/build-bastion.sh

@@ -99,16 +99,22 @@ if [ "$PUSH" = true ]; then
     fi
   fi
 
+  # Use --tls-verify=false for plain HTTP registries (e.g. 10.0.0.194:3012)
+  TLS_FLAG=""
+  if [[ "$REGISTRY" =~ ^[0-9] ]] || [[ "$REGISTRY" =~ ^localhost ]]; then
+    TLS_FLAG="--tls-verify=false"
+  fi
+
   echo "==> Logging in to $REGISTRY..."
-  podman login -u michal -p "$GITEA_TOKEN" "$REGISTRY"
+  podman login $TLS_FLAG -u michal -p "$GITEA_TOKEN" "$REGISTRY"
 
   echo "==> Pushing $FULL_IMAGE:$TAG..."
-  podman manifest push --all "$MANIFEST" "docker://$FULL_IMAGE:$TAG"
+  podman manifest push --all $TLS_FLAG "$MANIFEST" "docker://$FULL_IMAGE:$TAG"
 
   # Also tag as :latest if not already
   if [ "$TAG" != "latest" ]; then
     echo "==> Also pushing as :latest..."
-    podman manifest push --all "$MANIFEST" "docker://$FULL_IMAGE:latest"
+    podman manifest push --all $TLS_FLAG "$MANIFEST" "docker://$FULL_IMAGE:latest"
   fi
 
   # Link package to repository if script exists

bastion/scripts/build-labd.sh

@@ -92,15 +92,21 @@ if [ "$PUSH" = true ]; then
     fi
   fi
 
+  # Use --tls-verify=false for plain HTTP registries (e.g. 10.0.0.194:3012)
+  TLS_FLAG=""
+  if [[ "$REGISTRY" =~ ^[0-9] ]] || [[ "$REGISTRY" =~ ^localhost ]]; then
+    TLS_FLAG="--tls-verify=false"
+  fi
+
   echo "==> Logging in to $REGISTRY..."
-  podman login -u michal -p "$GITEA_TOKEN" "$REGISTRY"
+  podman login $TLS_FLAG -u michal -p "$GITEA_TOKEN" "$REGISTRY"
 
   echo "==> Pushing $FULL_IMAGE:$TAG..."
-  podman manifest push --all "$MANIFEST" "docker://$FULL_IMAGE:$TAG"
+  podman manifest push --all $TLS_FLAG "$MANIFEST" "docker://$FULL_IMAGE:$TAG"
 
   if [ "$TAG" != "latest" ]; then
     echo "==> Also pushing as :latest..."
-    podman manifest push --all "$MANIFEST" "docker://$FULL_IMAGE:latest"
+    podman manifest push --all $TLS_FLAG "$MANIFEST" "docker://$FULL_IMAGE:latest"
   fi
 
   if [ -f "$SCRIPT_DIR/link-package.sh" ]; then

bastion/scripts/deploy.sh

@@ -24,6 +24,21 @@ deploy_bastion() {
     kubectl rollout restart deployment/bastion -n lab-infra
     kubectl rollout status deployment/bastion -n lab-infra --timeout=180s
     echo "✓ Bastion deployed"
+
+    # Sync Asahi rootfs package to bastion pod's persistent volume
+    if [ -d "$PROJECT_DIR/asahi-repo" ] && [ -f "$PROJECT_DIR/asahi-repo/fedora-asahi-lab.zip" ]; then
+        echo ""
+        echo "=== Syncing Asahi rootfs to bastion pod ==="
+        BASTION_POD=$(kubectl get pods -n lab-infra -l app=bastion -o jsonpath='{.items[0].metadata.name}' 2>/dev/null)
+        if [ -n "$BASTION_POD" ]; then
+            kubectl exec -n lab-infra "$BASTION_POD" -- mkdir -p /data/asahi-repo
+            kubectl cp "$PROJECT_DIR/asahi-repo/installer_data.json" "lab-infra/$BASTION_POD:/data/asahi-repo/installer_data.json"
+            kubectl cp "$PROJECT_DIR/asahi-repo/fedora-asahi-lab.zip" "lab-infra/$BASTION_POD:/data/asahi-repo/fedora-asahi-lab.zip"
+            echo "✓ Asahi rootfs synced ($(du -sh "$PROJECT_DIR/asahi-repo/fedora-asahi-lab.zip" | cut -f1))"
+        else
+            echo "WARNING: Could not find bastion pod — Asahi rootfs not synced"
+        fi
+    fi
 }
 
 deploy_labd() {

bastion/scripts/fix-ssh-root.sh

@@ -0,0 +1,131 @@
+#!/bin/bash
+# Fix root SSH access on all provisioned machines.
+# Tries root, lab, michal users to find one that works,
+# then ensures root has the SSH key and PermitRootLogin is enabled.
+set -euo pipefail
+
+SSH_KEY="ssh-rsa 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 michal@fedora"
+
+SSH_OPTS="-o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o LogLevel=ERROR -o ConnectTimeout=5"
+USERS_TO_TRY=(root lab michal)
+
+# Machines: hostname ip
+MACHINES=(
+    "labmaster 192.168.8.11"
+    "worker0-k8s0 192.168.8.23"
+    "worker1-k8s0 192.168.8.13"
+    "worker2-k8s0 192.168.8.25"
+    "spark-2935 192.168.8.12"
+)
+
+BOLD="\033[1m"
+GREEN="\033[0;32m"
+RED="\033[0;31m"
+DIM="\033[2m"
+RESET="\033[0m"
+
+# Script to run on each machine (via sudo if needed)
+read -r -d '' FIX_SCRIPT << 'FIXEOF' || true
+#!/bin/bash
+set -e
+KEY="$1"
+
+# 1. Ensure root .ssh dir exists
+mkdir -p /root/.ssh
+chmod 700 /root/.ssh
+touch /root/.ssh/authorized_keys
+chmod 600 /root/.ssh/authorized_keys
+
+# 2. Add key if not present
+if ! grep -qF "$KEY" /root/.ssh/authorized_keys 2>/dev/null; then
+    echo "$KEY" >> /root/.ssh/authorized_keys
+    echo "KEY_ADDED"
+else
+    echo "KEY_EXISTS"
+fi
+
+# 3. Fix sshd_config for root login with keys
+SSHD_CONF="/etc/ssh/sshd_config"
+CHANGED=0
+
+# Ensure PermitRootLogin allows key auth
+CURRENT=$(grep -E "^PermitRootLogin" "$SSHD_CONF" 2>/dev/null | tail -1 || true)
+if [ "$CURRENT" = "PermitRootLogin prohibit-password" ] || [ "$CURRENT" = "PermitRootLogin without-password" ]; then
+    echo "SSHD_OK"
+elif [ "$CURRENT" = "PermitRootLogin yes" ]; then
+    echo "SSHD_OK"
+else
+    # Remove any existing PermitRootLogin lines
+    sed -i '/^#*PermitRootLogin/d' "$SSHD_CONF"
+    echo "PermitRootLogin prohibit-password" >> "$SSHD_CONF"
+    CHANGED=1
+    echo "SSHD_FIXED"
+fi
+
+# Ensure PubkeyAuthentication is enabled
+if grep -qE "^PubkeyAuthentication no" "$SSHD_CONF" 2>/dev/null; then
+    sed -i 's/^PubkeyAuthentication no/PubkeyAuthentication yes/' "$SSHD_CONF"
+    CHANGED=1
+    echo "PUBKEY_FIXED"
+else
+    echo "PUBKEY_OK"
+fi
+
+# Restart sshd if changed
+if [ "$CHANGED" -eq 1 ]; then
+    systemctl restart sshd 2>/dev/null || systemctl restart ssh 2>/dev/null || true
+    echo "SSHD_RESTARTED"
+fi
+
+# 4. Verify root can be reached
+echo "DONE"
+FIXEOF
+
+echo ""
+echo -e "${BOLD}Fixing root SSH access on all machines...${RESET}"
+echo ""
+
+for entry in "${MACHINES[@]}"; do
+    read -r hostname ip <<< "$entry"
+    printf "  %-24s ${DIM}(%s)${RESET}  " "$hostname" "$ip"
+
+    # Try each user until one works
+    WORKING_USER=""
+    for user in "${USERS_TO_TRY[@]}"; do
+        if ssh $SSH_OPTS "$user@$ip" "true" 2>/dev/null; then
+            WORKING_USER="$user"
+            break
+        fi
+    done
+
+    if [ -z "$WORKING_USER" ]; then
+        echo -e "${RED}UNREACHABLE${RESET} (tried: ${USERS_TO_TRY[*]})"
+        continue
+    fi
+
+    # Run fix script (with sudo if not root)
+    if [ "$WORKING_USER" = "root" ]; then
+        RESULT=$(ssh $SSH_OPTS "root@$ip" "bash -s -- '$SSH_KEY'" <<< "$FIX_SCRIPT" 2>&1)
+    else
+        RESULT=$(ssh $SSH_OPTS "$WORKING_USER@$ip" "sudo bash -s -- '$SSH_KEY'" <<< "$FIX_SCRIPT" 2>&1)
+    fi
+
+    # Parse result
+    DETAILS=""
+    if echo "$RESULT" | grep -q "KEY_ADDED"; then DETAILS="key added"; fi
+    if echo "$RESULT" | grep -q "KEY_EXISTS"; then DETAILS="key ok"; fi
+    if echo "$RESULT" | grep -q "SSHD_FIXED"; then DETAILS="$DETAILS, sshd fixed"; fi
+    if echo "$RESULT" | grep -q "SSHD_OK"; then DETAILS="$DETAILS, sshd ok"; fi
+    if echo "$RESULT" | grep -q "SSHD_RESTARTED"; then DETAILS="$DETAILS, restarted"; fi
+
+    # Verify root works now
+    if ssh $SSH_OPTS "root@$ip" "true" 2>/dev/null; then
+        echo -e "${GREEN}OK${RESET} ${DIM}(via $WORKING_USER: $DETAILS)${RESET}"
+    else
+        echo -e "${RED}PARTIAL${RESET} ${DIM}(via $WORKING_USER: $DETAILS -- root still blocked)${RESET}"
+    fi
+done
+
+echo ""
+echo -e "${BOLD}Done.${RESET} Verify: labctl provision recheck --user root"
+echo ""

bastion/scripts/test-provision.sh

@@ -2,16 +2,19 @@
 # Run PXE and/or ISO boot integration tests.
 #
 # Usage:
-#   sudo ./scripts/test-provision.sh          # run PXE + ISO (x86_64)
-#   sudo ./scripts/test-provision.sh pxe      # PXE only
-#   sudo ./scripts/test-provision.sh iso      # ISO only (x86_64)
-#   sudo ./scripts/test-provision.sh arm      # ARM ISO boot (emulated, SLOW ~60min)
-#   sudo ./scripts/test-provision.sh all      # all tests including ARM
+#   sudo ./scripts/test-provision.sh              # run PXE + ISO (x86_64)
+#   sudo ./scripts/test-provision.sh pxe          # PXE only
+#   sudo ./scripts/test-provision.sh iso          # ISO only (x86_64)
+#   sudo ./scripts/test-provision.sh rescue       # x86_64 Anaconda rescue boot + SSH (~15min)
+#   sudo ./scripts/test-provision.sh arm          # ARM ISO boot (emulated, SLOW ~60min)
+#   sudo ./scripts/test-provision.sh arm-pxe      # ARM network PXE rescue: NBP + rescue over SSH (~25-30min)
+#   sudo ./scripts/test-provision.sh arm-pxe-full # ARM network PXE incl. discover + full install (~75-95min)
+#   sudo ./scripts/test-provision.sh all          # all tests including ARM
 #
 # Prerequisites:
 #   libvirtd, OVMF (edk2-ovmf), iPXE (ipxe-bootimgs-x86),
 #   dnsmasq, xorriso, mtools, virt-install, qemu-img
-#   ARM: qemu-system-aarch64, edk2-aarch64
+#   ARM: qemu-system-aarch64, edk2-aarch64, ipxe-bootimgs-aarch64
 set -e
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
@@ -58,6 +61,10 @@ if [ ! -f /usr/share/edk2/ovmf/OVMF_CODE.fd ]; then
     exit 1
 fi
 
+MODE="${1:-both}"
+
+# iPXE binaries are per-architecture. x86_64 is always required (the dnsmasq config
+# references it); arm64 only for the ARM network-PXE modes.
 IPXE_EFI=""
 for f in /usr/share/ipxe/ipxe-snponly-x86_64.efi /usr/share/ipxe/ipxe-snp-x86_64.efi /usr/share/ipxe/ipxe-x86_64.efi; do
     [ -f "$f" ] && IPXE_EFI="$f" && break
@@ -67,6 +74,20 @@ if [ -z "$IPXE_EFI" ]; then
     exit 1
 fi
 
+IPXE_EFI_ARM64=""
+for f in /usr/share/ipxe/arm64-efi/snponly.efi /usr/share/ipxe/arm64-efi/ipxe.efi; do
+    [ -f "$f" ] && IPXE_EFI_ARM64="$f" && break
+done
+
+case "$MODE" in
+    arm-pxe|arm-pxe-full|all)
+        if [ -z "$IPXE_EFI_ARM64" ] && [ "$MODE" != "all" ]; then
+            echo -e "${RED}arm64 iPXE binary not found.${RESET} Install: sudo dnf install ipxe-bootimgs-aarch64"
+            exit 1
+        fi
+        ;;
+esac
+
 # Find SSH key
 SSH_KEY=""
 for name in id_ed25519 id_ecdsa id_rsa; do
@@ -83,10 +104,19 @@ fi
 echo -e "  User:    ${BOLD}$REAL_USER${RESET}"
 echo -e "  SSH key: ${BOLD}$SSH_KEY${RESET}"
 echo -e "  iPXE:    ${BOLD}$IPXE_EFI${RESET}"
+echo -e "  iPXE a64:${BOLD} ${IPXE_EFI_ARM64:-not installed}${RESET}"
 echo ""
 
-# --- Determine which tests to run ---
-MODE="${1:-both}"
+require_arm_emulation() {
+    if ! command -v qemu-system-aarch64 &>/dev/null; then
+        echo -e "${RED}qemu-system-aarch64 not found.${RESET} Install: sudo dnf install qemu-system-aarch64 edk2-aarch64"
+        exit 1
+    fi
+    if [ ! -f /usr/share/edk2/aarch64/QEMU_EFI.fd ]; then
+        echo -e "${RED}AAVMF firmware not found.${RESET} Install: sudo dnf install edk2-aarch64"
+        exit 1
+    fi
+}
 
 run_test() {
     local name="$1" pattern="$2"
@@ -116,13 +146,26 @@ case "$MODE" in
         run_test "ISO boot" "ISO boot" || FAILED=1
         ;;
     arm|arm-iso)
-        if ! command -v qemu-system-aarch64 &>/dev/null; then
-            echo -e "${RED}qemu-system-aarch64 not found.${RESET} Install: sudo dnf install qemu-system-aarch64 edk2-aarch64"
-            exit 1
-        fi
+        require_arm_emulation
         echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 30-60 minutes.${RESET}"
         run_test "ARM ISO boot" "ARM ISO" || FAILED=1
         ;;
+    rescue)
+        echo -e "${YELLOW}x86_64 rescue boot (KVM). Expect ~15 minutes.${RESET}"
+        run_test "x86 rescue boot" "x86 rescue boot" || FAILED=1
+        ;;
+    arm-pxe)
+        require_arm_emulation
+        echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 25-30 minutes.${RESET}"
+        echo -e "${YELLOW}Covers option 93 -> arm64 NBP, arch resolution, and rescue over SSH.${RESET}"
+        echo -e "${YELLOW}For the full install too, use: $0 arm-pxe-full${RESET}"
+        run_test "ARM PXE rescue" "ARM PXE rescue" || FAILED=1
+        ;;
+    arm-pxe-full)
+        require_arm_emulation
+        echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 75-95 minutes.${RESET}"
+        ARM_PXE_FULL=1 run_test "ARM PXE (rescue + install)" "ARM PXE" || FAILED=1
+        ;;
     both)
         run_test "PXE boot" "PXE boot" || FAILED=1
         run_test "ISO boot" "ISO boot" || FAILED=1
@@ -133,12 +176,17 @@ case "$MODE" in
         if command -v qemu-system-aarch64 &>/dev/null; then
             echo -e "${YELLOW}ARM emulation is ~10x slower than native.${RESET}"
             run_test "ARM ISO boot" "ARM ISO" || FAILED=1
+            if [ -n "$IPXE_EFI_ARM64" ]; then
+                run_test "ARM PXE rescue" "ARM PXE rescue" || FAILED=1
+            else
+                echo -e "${YELLOW}Skipping ARM PXE test (ipxe-bootimgs-aarch64 not installed)${RESET}"
+            fi
         else
-            echo -e "${YELLOW}Skipping ARM test (qemu-system-aarch64 not installed)${RESET}"
+            echo -e "${YELLOW}Skipping ARM tests (qemu-system-aarch64 not installed)${RESET}"
         fi
         ;;
     *)
-        echo "Usage: $0 [pxe|iso|arm|both|all]"
+        echo "Usage: $0 [pxe|iso|rescue|arm|arm-pxe|arm-pxe-full|both|all]"
         exit 1
         ;;
 esac

bastion/src/bastion/src/main.ts

@@ -3,7 +3,9 @@
 
 import { mkdirSync, writeFileSync, readFileSync, existsSync, copyFileSync, symlinkSync, unlinkSync } from "node:fs";
 import { execSync } from "node:child_process";
-import type { BastionConfig } from "@lab/shared";
+import type { Arch, BastionConfig } from "@lab/shared";
+import { SUPPORTED_ARCHES, fedoraMirrorFor, classifyOnboard } from "@lab/shared";
+import { kernelPath, initrdPath } from "./templates/boot.ipxe.js";
 import { loadConfig } from "./config.js";
 import { populateNetworkConfig } from "./services/network.js";
 import { createApp } from "./server.js";
@@ -13,6 +15,7 @@ import { renderBootIpxe } from "./templates/boot.ipxe.js";
 import { logger } from "./services/logger.js";
 import { BastionConnection } from "./services/labd-connection.js";
 import { progressBus } from "./services/progress-events.js";
+import { checkInstallAllowed } from "./services/install-guard.js";
 import { ensureBootIso } from "./routes/boot-iso.js";
 
 function copyIfMissing(src: string, dest: string, label: string): void {
@@ -130,9 +133,14 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
   mkdirSync(config.tftpDir, { recursive: true });
   mkdirSync(config.httpDir, { recursive: true });
 
+  // Architectures we can actually network boot, reported in the banner so a missing
+  // arm64 payload is visible at startup instead of at 2am when a rescue is needed.
+  const bootArches: Arch[] = [];
+  let ipxeArm64Ready = false;
+
   // Prepare boot artifacts
   if (config.skipArtifacts !== true) {
-    logger.info(`Preparing boot artifacts (Fedora ${config.fedoraVersion} ${config.arch})...`);
+    logger.info(`Preparing boot artifacts (Fedora ${config.fedoraVersion}, ${SUPPORTED_ARCHES.join(" + ")})...`);
 
     copyIfMissing(
       "/usr/share/ipxe/undionly.kpxe",
@@ -150,20 +158,41 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
         `${config.tftpDir}/ipxe-arm64.efi`,
         "iPXE UEFI arm64",
       );
+      ipxeArm64Ready = true;
     } catch {
-      logger.warn("arm64 iPXE not available -- skipping");
+      logger.warn("arm64 iPXE not available -- arm64 machines cannot network boot.");
+      logger.warn("  Install with: sudo dnf install ipxe-bootimgs-aarch64");
     }
 
-    download(
-      `${config.fedoraMirror}/images/pxeboot/vmlinuz`,
-      `${config.httpDir}/vmlinuz`,
-      "Fedora kernel",
-    );
-    download(
-      `${config.fedoraMirror}/images/pxeboot/initrd.img`,
-      `${config.httpDir}/initrd.img`,
-      "Fedora initrd",
-    );
+    // Fedora pxeboot kernel + initrd per architecture. x86_64 keeps the unsuffixed
+    // names it has always used; other architectures are suffixed. The iPXE templates
+    // resolve the same paths via kernelPath()/initrdPath().
+    for (const arch of SUPPORTED_ARCHES) {
+      const mirror = fedoraMirrorFor(config.fedoraVersion, arch);
+      try {
+        download(
+          `${mirror}/images/pxeboot/vmlinuz`,
+          `${config.httpDir}${kernelPath(arch)}`,
+          `Fedora ${arch} kernel`,
+        );
+        download(
+          `${mirror}/images/pxeboot/initrd.img`,
+          `${config.httpDir}${initrdPath(arch)}`,
+          `Fedora ${arch} initrd`,
+        );
+        bootArches.push(arch);
+      } catch (err) {
+        // Non-fatal: a bastion with no arm64 artifacts still serves x86_64 fine.
+        // Failing startup over an unreachable mirror for an architecture that may not
+        // even be present on this network would be worse.
+        logger.warn(`Fedora ${arch} kernel/initrd unavailable -- ${arch} PXE disabled`);
+        logger.warn(`  ${err instanceof Error ? err.message : String(err)}`);
+      }
+    }
+
+    if (!bootArches.includes("x86_64")) {
+      throw new Error("Fedora x86_64 kernel/initrd could not be staged -- cannot serve PXE");
+    }
 
     // Ubuntu netboot artifacts (non-fatal — Ubuntu version may not be released yet)
     try {
@@ -254,10 +283,17 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
     // Wire up command handlers so labd can send install/forget/role commands
     labdConn.onCommand("command-install", async (msg) => {
       if (msg.type !== "command-install") throw new Error("unexpected");
+      const installMac = msg.mac.toLowerCase().replace(/-/g, ":");
+      const osId = (msg.os as import("@lab/shared").OsId | undefined) ?? "fedora-43";
+      const check = checkInstallAllowed(state.load(), installMac, osId);
+      if (check.allowed === false) {
+        logger.warn(`INSTALL REFUSED: ${installMac} -- ${check.error}`);
+        return { status: "error", error: check.error };
+      }
       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(),
@@ -269,6 +305,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
     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 ??
@@ -276,7 +313,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
         currentState.discovered[mac]?.product ??
         mac;
       state.update((s) => {
-        s.debug[mac] = { hostname, queued_at: new Date().toISOString() };
+        s.debug[mac] = { hostname, queued_at: new Date().toISOString(), pxeBoot };
       });
       return { status: "ok", data: { mac, hostname } };
     });
@@ -293,6 +330,71 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
       return { status: "ok", data: { mac } };
     });
 
+    labdConn.onCommand("command-register", async (msg) => {
+      if (msg.type !== "command-register") throw new Error("unexpected");
+      const mac = msg.mac.toLowerCase();
+      state.update((s) => {
+        s.installed[mac] = {
+          hostname: msg.hostname,
+          role: msg.role,
+          ip: msg.ip,
+          installed_at: new Date().toISOString(),
+        };
+      });
+      logger.info(`MACHINE REGISTERED: ${mac} -> ${msg.hostname} (${msg.role}) ip=${msg.ip}`);
+      return { status: "ok", data: { mac, hostname: msg.hostname } };
+    });
+
+    labdConn.onCommand("command-discover", async (msg) => {
+      if (msg.type !== "command-discover") throw new Error("unexpected");
+      const mac = (msg.mac as string).toLowerCase();
+      const now = new Date().toISOString();
+      const existing = state.load().discovered[mac];
+      const identity = {
+        mac,
+        manufacturer: (msg.manufacturer as string) ?? "unknown",
+        product: (msg.product as string) ?? "unknown",
+        board: (msg.board as string) ?? "unknown",
+        ...(existing?.onboard !== undefined ? { onboard: existing.onboard } : {}),
+        ...(existing?.vendor_os !== undefined ? { vendor_os: existing.vendor_os } : {}),
+      };
+      const onboarding = classifyOnboard(identity);
+      const rootDevice = msg.root_device ?? existing?.root_device;
+      const rootArgs = msg.root_args ?? existing?.root_args;
+      state.update((s) => {
+        s.discovered[mac] = {
+          mac,
+          product: identity.product,
+          board: identity.board,
+          serial: (msg.serial as string) ?? "unknown",
+          manufacturer: identity.manufacturer,
+          cpu_model: (msg.cpu_model as string) ?? "unknown",
+          cpu_cores: (msg.cpu_cores as number) ?? 0,
+          memory_gb: (msg.memory_gb as number) ?? 0,
+          arch: (msg.arch as string) ?? "unknown",
+          disks: (msg.disks as Array<{ name: string; size_gb: number; model: string }>) ?? [],
+          nics: (msg.nics as Array<{ name: string; mac: string; state: string }>) ?? [],
+          first_seen: existing?.first_seen ?? now,
+          last_seen: now,
+          onboard: onboarding.onboard,
+          ...(onboarding.vendor_os !== undefined ? { vendor_os: onboarding.vendor_os } : {}),
+          ...(rootDevice !== undefined ? { root_device: rootDevice } : {}),
+          ...(rootArgs !== undefined ? { root_args: rootArgs } : {}),
+        };
+        // Keep the installed record in step -- the guard and --pxe-boot both read it.
+        const inst = s.installed[mac];
+        if (inst) {
+          inst.arch = (msg.arch as string) ?? inst.arch;
+          inst.onboard = onboarding.onboard;
+          if (onboarding.vendor_os !== undefined) inst.vendor_os = onboarding.vendor_os;
+          if (rootDevice !== undefined) inst.root_device = rootDevice;
+          if (rootArgs !== undefined) inst.root_args = rootArgs;
+        }
+      });
+      logger.info(`HARDWARE UPDATED: ${mac} -- ${msg.manufacturer ?? "?"} ${msg.product ?? "?"} (${msg.cpu_model ?? "?"}, ${msg.cpu_cores ?? "?"} cores, ${msg.memory_gb ?? "?"}GB RAM)`);
+      return { status: "ok", data: { mac } };
+    });
+
     labdConn.onCommand("command-role-update", async (msg) => {
       if (msg.type !== "command-role-update") throw new Error("unexpected");
       const mac = msg.mac.toLowerCase();
@@ -322,7 +424,7 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
   }
 
   // Print banner
-  printBanner(config);
+  printBanner(config, bootArches, ipxeArm64Ready);
 
   // Graceful shutdown
   const shutdown = async (): Promise<void> => {
@@ -344,11 +446,22 @@ export async function startBastion(overrides: Partial<BastionConfig> = {}): Prom
   await new Promise(() => {});
 }
 
-function printBanner(config: BastionConfig): void {
+function printBanner(config: BastionConfig, bootArches: Arch[], ipxeArm64Ready: boolean): void {
   const dhcpInfo = config.dhcpMode === "full"
     ? `full (${config.dhcpRangeStart}-${config.dhcpRangeEnd})`
     : "proxy (alongside existing DHCP)";
 
+  // arm64 needs both an iPXE binary (DHCP hands it out on option 93 = 0x0b) and a
+  // kernel/initrd pair. Report the combination, since either missing breaks it.
+  const archInfo = config.skipArtifacts === true
+    ? "(artifacts skipped)"
+    : SUPPORTED_ARCHES
+        .map((a) => {
+          const ready = bootArches.includes(a) && (a !== "aarch64" || ipxeArm64Ready);
+          return ready ? a : `${a} (unavailable)`;
+        })
+        .join(", ");
+
   console.log("");
   console.log("\x1b[36m\x1b[1m" + "=".repeat(60) + "\x1b[0m");
   console.log("\x1b[36m\x1b[1m  Lab PXE Bastion -- Discovery Mode\x1b[0m");
@@ -357,7 +470,8 @@ function printBanner(config: BastionConfig): void {
   console.log(`  Network:   \x1b[1m${config.network}/24\x1b[0m via \x1b[1m${config.iface}\x1b[0m`);
   console.log(`  DHCP:      \x1b[1m${dhcpInfo}\x1b[0m`);
   console.log(`  HTTP:      \x1b[1mhttp://${config.serverIp}:${config.httpPort}/\x1b[0m`);
-  console.log(`  OS:        \x1b[1mFedora ${config.fedoraVersion} (${config.arch})\x1b[0m`);
+  console.log(`  OS:        \x1b[1mFedora ${config.fedoraVersion}\x1b[0m`);
+  console.log(`  Net boot:  \x1b[1m${archInfo}\x1b[0m`);
   console.log(`  Domain:    \x1b[1m${config.domain}\x1b[0m`);
   console.log(`  State:     \x1b[1m${config.stateFile}\x1b[0m`);
   console.log("");

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

@@ -6,18 +6,21 @@
 
 import type { FastifyInstance } from "fastify";
 import type { HardwareInfo, InstalledInfo, Role } from "@lab/shared";
-import { isValidOsId, SUPPORTED_ROLES } from "@lab/shared";
+import { isValidOsId, SUPPORTED_ROLES, classifyOnboard } from "@lab/shared";
 import type { StateManager } from "../services/state.js";
 import { logger } from "../services/logger.js";
 import { triggerPostProvisionK3s } from "../services/post-provision.js";
+import { checkInstallAllowed } from "../services/install-guard.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) => {
@@ -51,6 +54,12 @@ export function registerApiRoutes(
       return reply.status(400).send({ error: `invalid os: '${osId}'. Supported: fedora-43, ubuntu-26.04` });
     }
 
+    const check = checkInstallAllowed(state.load(), mac, osId);
+    if (check.allowed === false) {
+      logger.warn(`INSTALL REFUSED: ${mac} -- ${check.error}`);
+      return reply.status(409).send({ error: check.error });
+    }
+
     state.update((s) => {
       s.install_queue[mac] = {
         hostname: hostname ?? "lab-node",
@@ -84,6 +93,11 @@ 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";
@@ -132,16 +146,26 @@ export function registerApiRoutes(
             ? detailStr.replace("ready at ", "").trim()
             : "";
 
+          const hw = s.discovered[mac];
           const installedInfo: InstalledInfo = {
             hostname: cfg?.hostname ?? "?",
             role: cfg?.role ?? "?",
             ...(cfg?.os !== undefined ? { os: cfg.os } : {}),
             ip,
             installed_at: new Date().toISOString(),
+            // Preserve hardware info from discovery
+            ...(hw ? {
+              product: hw.product,
+              manufacturer: hw.manufacturer,
+              cpu_model: hw.cpu_model,
+              cpu_cores: hw.cpu_cores,
+              memory_gb: hw.memory_gb,
+              arch: hw.arch,
+            } : {}),
           };
           s.installed[mac] = installedInfo;
 
-          const admin = installedInfo.role !== "vanilla" && installedInfo.role !== "" ? "michal" : "root";
+          const admin = installedInfo.role !== "vanilla" && installedInfo.role !== "" ? "lab" : "root";
           console.log(`\n  \x1b[0;32m\x1b[1m  ssh ${admin}@${ip}\x1b[0m\n`);  // eslint-disable-line no-console
 
           // Auto-install k3s for non-vanilla roles
@@ -191,9 +215,10 @@ export function registerApiRoutes(
 
   // Queue debug/rescue mode for a machine
   app.post<{
-    Body: { mac?: string };
+    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" });
     }
@@ -207,7 +232,7 @@ export function registerApiRoutes(
       mac;
 
     state.update((s) => {
-      s.debug[mac] = { hostname, queued_at: new Date().toISOString() };
+      s.debug[mac] = { hostname, queued_at: new Date().toISOString(), pxeBoot };
     });
 
     logger.info(`DEBUG QUEUED: ${mac} -> ${hostname}`);
@@ -266,6 +291,10 @@ export function registerApiRoutes(
       arch?: string;
       disks?: Array<{ name: string; size_gb: number; model: string }>;
       nics?: Array<{ name: string; mac: string; state: string }>;
+      // Root filesystem, when the reporter could observe it (recheck over SSH, or the
+      // probe script run from a rescue shell). Used by --pxe-boot.
+      root_device?: string;
+      root_args?: string;
     };
   }>("/api/discover", async (request, reply) => {
     const data = request.body;
@@ -280,22 +309,53 @@ export function registerApiRoutes(
 
     state.update((s) => {
       const existing = s.discovered[mac];
+      // Classify onboarding from the DMI identity we just received. An explicit
+      // classification already on the record wins (see classifyOnboard).
+      const onboarding = classifyOnboard({
+        mac,
+        manufacturer: data.manufacturer ?? existing?.manufacturer ?? "unknown",
+        product: data.product ?? existing?.product ?? "unknown",
+        board: data.board ?? existing?.board ?? "unknown",
+        ...(existing?.onboard !== undefined ? { onboard: existing.onboard } : {}),
+        ...(existing?.vendor_os !== undefined ? { vendor_os: existing.vendor_os } : {}),
+      });
+      const rootDevice = data.root_device ?? existing?.root_device;
+      const rootArgs = data.root_args ?? existing?.root_args;
+
+      // Absent fields keep whatever we already knew. Reporters are not all the full
+      // discovery kickstart: the rescue-shell probe posts only a root device, and
+      // blanking a machine's hardware inventory as a side effect of that would be
+      // silent data loss.
       const hwInfo: HardwareInfo = {
         mac,
-        product: data.product ?? "unknown",
-        board: data.board ?? "unknown",
-        serial: data.serial ?? "unknown",
-        manufacturer: data.manufacturer ?? "unknown",
-        cpu_model: data.cpu_model ?? "unknown",
-        cpu_cores: data.cpu_cores ?? 0,
-        memory_gb: data.memory_gb ?? 0,
-        arch: data.arch ?? "unknown",
-        disks: data.disks ?? [],
-        nics: data.nics ?? [],
+        product: data.product ?? existing?.product ?? "unknown",
+        board: data.board ?? existing?.board ?? "unknown",
+        serial: data.serial ?? existing?.serial ?? "unknown",
+        manufacturer: data.manufacturer ?? existing?.manufacturer ?? "unknown",
+        cpu_model: data.cpu_model ?? existing?.cpu_model ?? "unknown",
+        cpu_cores: data.cpu_cores ?? existing?.cpu_cores ?? 0,
+        memory_gb: data.memory_gb ?? existing?.memory_gb ?? 0,
+        arch: data.arch ?? existing?.arch ?? "unknown",
+        disks: data.disks ?? existing?.disks ?? [],
+        nics: data.nics ?? existing?.nics ?? [],
         first_seen: existing?.first_seen ?? now,
         last_seen: now,
+        onboard: onboarding.onboard,
+        ...(onboarding.vendor_os !== undefined ? { vendor_os: onboarding.vendor_os } : {}),
+        ...(rootDevice !== undefined ? { root_device: rootDevice } : {}),
+        ...(rootArgs !== undefined ? { root_args: rootArgs } : {}),
       };
       s.discovered[mac] = hwInfo;
+
+      // Keep the installed record in step -- the install guard and --pxe-boot read it.
+      const inst = s.installed[mac];
+      if (inst) {
+        if (data.arch !== undefined) inst.arch = data.arch;
+        inst.onboard = onboarding.onboard;
+        if (onboarding.vendor_os !== undefined) inst.vendor_os = onboarding.vendor_os;
+        if (rootDevice !== undefined) inst.root_device = rootDevice;
+        if (rootArgs !== undefined) inst.root_args = rootArgs;
+      }
     });
 
     const label = isNew ? "NEW MACHINE DISCOVERED" : "MACHINE RE-DISCOVERED";
@@ -307,6 +367,67 @@ export function registerApiRoutes(
     return reply.send({ status: "ok", mac, new: isNew });
   });
 
+  // Register an already-installed machine (e.g. re-add after state loss)
+  app.post<{
+    Body: {
+      mac?: string;
+      hostname?: string;
+      role?: string;
+      ip?: string;
+    };
+  }>("/api/register", async (request, reply) => {
+    const { mac: rawMac, hostname, role, ip } = request.body ?? {};
+    const mac = (rawMac ?? "").toLowerCase().replace(/-/g, ":");
+
+    if (mac === "") {
+      return reply.status(400).send({ error: "mac is required" });
+    }
+    if (!hostname) {
+      return reply.status(400).send({ error: "hostname is required" });
+    }
+
+    const validRole = role ?? "worker";
+    if (!(SUPPORTED_ROLES as readonly string[]).includes(validRole)) {
+      return reply.status(400).send({ error: `invalid role: '${validRole}'. Supported: ${SUPPORTED_ROLES.join(", ")}` });
+    }
+
+    state.update((s) => {
+      s.installed[mac] = {
+        hostname,
+        role: validRole,
+        ip: ip ?? "",
+        installed_at: new Date().toISOString(),
+      };
+    });
+
+    logger.info(`MACHINE REGISTERED: ${mac} -> hostname=${hostname} role=${validRole} ip=${ip ?? ""}`);
+
+    return reply.send({
+      status: "registered",
+      mac,
+      hostname,
+      role: validRole,
+      ip: ip ?? "",
+    });
+  });
+
+  // Simple machine state query (used by ks-auto for ISO boot dispatch)
+  app.get<{
+    Params: { mac: string };
+  }>("/api/machine-state/:mac", async (request, reply) => {
+    const mac = request.params.mac.toLowerCase().replace(/-/g, ":");
+    const currentState = state.load();
+
+    if (currentState.debug[mac]) return reply.send("debug");
+    if (currentState.install_queue[mac]) {
+      const progress = currentState.install_queue[mac].progress;
+      return reply.send(progress ? "installing" : "queued");
+    }
+    if (currentState.installed[mac]) return reply.send("installed");
+    if (currentState.discovered[mac]) return reply.send("discovered");
+    return reply.send("unknown");
+  });
+
   // Update a machine's role (e.g. promote infra -> labcontroller)
   app.post<{
     Body: {

bastion/src/bastion/src/routes/asahi.ts

@@ -0,0 +1,176 @@
+// Routes for Asahi Linux provisioning.
+// GET /asahi                     — wrapper script (curl bastion:8080/asahi | sh)
+// GET /asahi/installer_data.json — custom installer config (built or fallback)
+// GET /asahi/repo/*              — serves built rootfs package (fedora-asahi-lab.zip)
+// GET /asahi/firstboot.sh        — first-boot LVM setup script (for manual use)
+
+import type { FastifyInstance } from "fastify";
+import fastifyStatic from "@fastify/static";
+import { existsSync, readFileSync } from "node:fs";
+import { join, dirname } from "node:path";
+import { fileURLToPath } from "node:url";
+import type { BastionConfig } from "@lab/shared";
+import { renderFirstbootScript, renderFirstbootUnit } from "../templates/asahi-firstboot.sh.js";
+import type { Role } from "@lab/shared";
+
+/** Find the asahi-repo directory (built by scripts/build-asahi-rootfs.sh). */
+function findAsahiRepo(config: BastionConfig): string | null {
+  // Check relative to bastionDir (container deploy)
+  const inBastionDir = join(config.bastionDir, "asahi-repo");
+  if (existsSync(inBastionDir)) return inBastionDir;
+
+  // Check /data/asahi-repo (PVC mount in k3s container)
+  if (existsSync("/data/asahi-repo")) return "/data/asahi-repo";
+
+  // Check relative to project root (dev mode)
+  try {
+    const thisDir = dirname(fileURLToPath(import.meta.url));
+    const projectRoot = join(thisDir, "..", "..", "..", "..");
+    const inProjectRoot = join(projectRoot, "asahi-repo");
+    if (existsSync(inProjectRoot)) return inProjectRoot;
+  } catch { /* import.meta.url not available in tests */ }
+
+  return null;
+}
+
+export function registerAsahiRoutes(app: FastifyInstance, config: BastionConfig): void {
+  const repoDir = findAsahiRepo(config);
+
+  // Serve built rootfs package files (fedora-asahi-lab.zip, etc.)
+  if (repoDir) {
+    app.register(fastifyStatic, {
+      root: repoDir,
+      prefix: "/asahi/repo/",
+      decorateReply: false,
+    });
+  }
+
+  // Wrapper script — user runs: curl http://bastion:8080/asahi | sh
+  app.get("/asahi", async (_request, reply) => {
+    const script = `#!/bin/bash
+# Lab Asahi provisioner — sets up Apple Silicon machines with lab LVM layout.
+# This wraps the standard Asahi installer with custom installer_data.json
+# that creates a separate LVM data partition.
+set -euo pipefail
+
+BASTION="http://${config.serverIp}:${config.httpPort}"
+
+echo ""
+echo "  ╔══════════════════════════════════════════════╗"
+echo "  ║  Lab Asahi Provisioner                       ║"
+echo "  ║  Bastion: \${BASTION}                         ║"
+echo "  ╚══════════════════════════════════════════════╝"
+echo ""
+
+# Check we're on macOS
+if [ "$(uname)" != "Darwin" ]; then
+    echo "ERROR: This script must be run from macOS on the target Mac."
+    echo "       It uses the Asahi Linux installer to set up Apple Silicon boot."
+    exit 1
+fi
+
+# Download the standard Asahi installer
+echo "Downloading Asahi Linux installer..."
+WORKDIR=$(mktemp -d)
+cd "$WORKDIR"
+
+INSTALLER_BASE="https://cdn.asahilinux.org/installer"
+PKG_VER=$(curl -s "\${INSTALLER_BASE}/latest")
+echo "  Version: \${PKG_VER}"
+
+curl -# -L -o "installer-\${PKG_VER}.tar.gz" "\${INSTALLER_BASE}/installer-\${PKG_VER}.tar.gz"
+
+echo "  Extracting..."
+tar xf "installer-\${PKG_VER}.tar.gz"
+
+# Download our custom installer_data.json (installer reads it as a local file)
+echo "  Downloading custom installer data from bastion..."
+curl -sfL -o installer_data.json "\${BASTION}/asahi/installer_data.json"
+
+# Pre-download the rootfs package (avoids Python HTTP streaming issues on macOS)
+echo "  Downloading rootfs package from bastion..."
+mkdir -p os
+curl -# -L -o os/fedora-asahi-lab.zip "\${BASTION}/asahi/repo/fedora-asahi-lab.zip"
+
+# Point installer to local directory (REPO_BASE + /os/ + package name)
+export REPO_BASE="\${PWD}"
+
+echo ""
+echo "  Using custom partition layout + rootfs from bastion."
+echo "  This will create:"
+echo "    - Standard Asahi boot infrastructure (m1n1 + U-Boot)"
+echo "    - Fedora Asahi Remix root partition"
+echo "    - LVM data partition (remaining space)"
+echo ""
+echo "  After first boot, SSH in and set up LVM:"
+echo "    ssh lab@<ip> 'curl -sf \${BASTION}/asahi/firstboot.sh | sudo bash'"
+echo ""
+
+# Run the installer
+if [ "$USER" != "root" ]; then
+    echo "The installer needs root. Enter your sudo password if prompted."
+    exec caffeinate -dis sudo -E ./install.sh "$@"
+else
+    exec caffeinate -dis ./install.sh "$@"
+fi
+`;
+    return reply.type("text/x-shellscript").send(script);
+  });
+
+  // Custom installer_data.json — serves built config or fallback
+  app.get("/asahi/installer_data.json", async (_request, reply) => {
+    // Prefer the built installer_data.json (from build-asahi-rootfs.sh)
+    if (repoDir) {
+      const builtConfig = join(repoDir, "installer_data.json");
+      if (existsSync(builtConfig)) {
+        const data = JSON.parse(readFileSync(builtConfig, "utf-8"));
+        return reply.type("application/json").send(data);
+      }
+    }
+
+    // Fallback: minimal config (won't have boot.img, for testing only)
+    return reply.type("application/json").send({
+      os_list: [{
+        name: "Fedora Asahi Lab",
+        default_os_name: "Fedora Linux with Lab LVM",
+        boot_object: "m1n1.bin",
+        next_object: "m1n1/boot.bin",
+        package: "fedora-asahi-lab.zip",
+        supported_fw: ["13.5"],
+        partitions: [
+          { name: "EFI", type: "EFI", size: "524288000B", format: "fat",
+            copy_firmware: true, copy_installer_data: true, source: "esp" },
+          { name: "Root", type: "Linux", size: "5368709120B", image: "root.img", expand: false },
+          { name: "Data", type: "Linux", size: "1073741824B", expand: true },
+        ],
+      }],
+    });
+  });
+
+  // First-boot script — for manual download or embedding in rootfs
+  app.get<{
+    Querystring: { hostname?: string; role?: string; mac?: string; user?: string };
+  }>("/asahi/firstboot.sh", async (request, reply) => {
+    const hostname = request.query.hostname ?? "unknown";
+    const role = (request.query.role ?? "infra") as Role;
+    const mac = request.query.mac ?? "unknown";
+    const user = request.query.user ?? "lab";
+
+    const script = renderFirstbootScript({
+      hostname,
+      role,
+      serverIp: config.serverIp,
+      httpPort: config.httpPort,
+      sshKeys: config.sshKeys ?? [],
+      adminUser: user,
+      mac,
+    });
+
+    return reply.type("text/x-shellscript").send(script);
+  });
+
+  // Systemd unit file for first-boot service
+  app.get("/asahi/firstboot.service", async (_request, reply) => {
+    return reply.type("text/plain").send(renderFirstbootUnit());
+  });
+}

bastion/src/bastion/src/routes/boot-iso.ts

@@ -137,7 +137,7 @@ function generateIso(config: BastionConfig, outputPath: string): void {
     "# Map iPXE arch names to Fedora mirror paths (arm64 -> aarch64)",
     "set fedarch ${buildarch}",
     "iseq ${buildarch} arm64 && set fedarch aarch64 ||",
-    `kernel file:/vmlinuz-\${buildarch} inst.ks=${bastionUrl}/discover.ks inst.repo=${FEDORA_MIRROR_BASE}/${config.fedoraVersion}/Everything/\${fedarch}/os inst.text || goto no_kernel`,
+    `kernel file:/vmlinuz-\${buildarch} inst.ks=${bastionUrl}/ks-auto inst.repo=${FEDORA_MIRROR_BASE}/${config.fedoraVersion}/Everything/\${fedarch}/os inst.text || goto no_kernel`,
     `initrd file:/initrd-\${buildarch} || goto no_kernel`,
     "boot || shell",
     "",

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

@@ -5,48 +5,208 @@
 //   - unknown       -> discovery mode (collect hardware, POST to bastion)
 
 import type { FastifyInstance } from "fastify";
-import type { BastionConfig } from "@lab/shared";
+import type { Arch, BastionConfig, BastionState, OsId } from "@lab/shared";
+import { normalizeArch, fedoraMirrorFor, osSupportsArch } from "@lab/shared";
 import type { StateManager } from "../services/state.js";
 import {
   renderDiscoverIpxe,
   renderInstallIpxe,
   renderDebugIpxe,
+  renderPxeBootDebugIpxe,
   renderLocalBootIpxe,
+  renderUnsupportedIpxe,
 } 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";
 
+/**
+ * Resolve a booting machine's architecture.
+ *
+ * Order matters. The tracked record is what we actually observed on the machine, so it
+ * wins. `reported` is iPXE's ${buildarch}, which is only as good as the binary DHCP
+ * handed the client -- correct in practice, but a misconfigured option 93 mapping would
+ * make it lie. The configured default is the last resort.
+ *
+ * There is deliberately no operator-supplied architecture anywhere in this path.
+ */
+export function resolveArch(
+  state: BastionState,
+  mac: string,
+  reported: string | undefined,
+  config: BastionConfig,
+): Arch {
+  return normalizeArch(state.installed[mac]?.arch)
+    ?? normalizeArch(state.install_queue[mac]?.arch)
+    ?? normalizeArch(state.discovered[mac]?.arch)
+    ?? normalizeArch(reported)
+    ?? normalizeArch(config.arch)
+    ?? "x86_64";
+}
+
+/** The root filesystem to boot for --pxe-boot, if the machine's record carries one. */
+function resolveRoot(
+  state: BastionState,
+  mac: string,
+): { rootDevice: string; rootArgs?: string } | null {
+  const installed = state.installed[mac];
+  const discovered = state.discovered[mac];
+  const rootDevice = installed?.root_device ?? discovered?.root_device;
+  if (rootDevice === undefined || rootDevice === "") return null;
+  const rootArgs = installed?.root_args ?? discovered?.root_args;
+  return rootArgs !== undefined && rootArgs !== ""
+    ? { rootDevice, rootArgs }
+    : { rootDevice };
+}
+
 export function registerDispatchRoutes(
   app: FastifyInstance,
   config: BastionConfig,
   state: StateManager,
 ): void {
-  // Serve debug/rescue kickstart (minimal: SSH keys + network)
+  // 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 ?? [] });
+    const ks = renderDebugKickstart({
+      sshKeys: config.sshKeys ?? [],
+      serverIp: config.serverIp,
+      httpPort: config.httpPort,
+    });
     return reply.type("text/plain").send(ks);
   });
 
-  app.get<{ Querystring: { mac?: string } }>("/dispatch", async (request, reply) => {
+  // 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 $IP_ADDR 2323\\"}" 2>/dev/null || true
+
+# --- Find the installed root filesystem and report it ---
+# This is what 'labctl provision debug --pxe-boot' needs. The rescue image cannot
+# report it by itself: %pre/%post do not run in rescue mode, so it happens here.
+vgchange -ay >/dev/null 2>&1 || true
+
+ROOT_DEVICE=""
+ROOT_ARGS=""
+PROBE_MNT=/tmp/lab-rootprobe
+mkdir -p "$PROBE_MNT"
+
+# Candidates: every LVM logical volume plus every non-LVM partition with a filesystem.
+for CAND in $(lvs --noheadings -o lv_path 2>/dev/null) \\
+            $(blkid -o device 2>/dev/null | grep -v '^/dev/mapper/'); do
+    [ -b "$CAND" ] || continue
+    mount -o ro "$CAND" "$PROBE_MNT" >/dev/null 2>&1 || continue
+    # A root filesystem has both of these; /boot and /home do not.
+    if [ -f "$PROBE_MNT/etc/fstab" ] && [ -d "$PROBE_MNT/usr" ]; then
+        ROOT_DEVICE="$CAND"
+        PRETTY=$(. "$PROBE_MNT/etc/os-release" 2>/dev/null && echo "$PRETTY_NAME")
+        echo "  found root: $CAND \${PRETTY:+($PRETTY)}"
+        if [ "$(lsblk -no TYPE "$CAND" 2>/dev/null | head -1)" = "lvm" ]; then
+            VGLV=$(lvs --noheadings -o vg_name,lv_name "$CAND" 2>/dev/null | awk '{print $1"/"$2}')
+            [ -n "$VGLV" ] && ROOT_ARGS="rd.lvm.lv=$VGLV"
+            # Swap comes from fstab here — /proc/swaps is the rescue image's, not the host's.
+            SWLV=$(awk '$3=="swap" && $1 ~ /^\\/dev\\// {print $1; exit}' "$PROBE_MNT/etc/fstab" 2>/dev/null)
+            if [ -n "$SWLV" ]; then
+                SWVGLV=$(lvs --noheadings -o vg_name,lv_name "$SWLV" 2>/dev/null | awk '{print $1"/"$2}')
+                [ -n "$SWVGLV" ] && [ "$SWVGLV" != "$VGLV" ] && ROOT_ARGS="$ROOT_ARGS rd.lvm.lv=$SWVGLV"
+            fi
+        fi
+        umount "$PROBE_MNT" >/dev/null 2>&1 || true
+        break
+    fi
+    umount "$PROBE_MNT" >/dev/null 2>&1 || true
+done
+
+if [ -n "$ROOT_DEVICE" ]; then
+    curl -sf -X POST "http://${config.serverIp}:${config.httpPort}/api/discover" \\
+        -H "Content-Type: application/json" \\
+        -d "{\\"mac\\":\\"$MAC_ADDR\\",\\"root_device\\":\\"$ROOT_DEVICE\\",\\"root_args\\":\\"$ROOT_ARGS\\"}" 2>/dev/null \\
+        && echo "  reported to bastion — 'labctl provision debug --pxe-boot' will work now"
+else
+    echo "  no root filesystem found — --pxe-boot cannot be used on this machine"
+fi
+
+echo ""
+echo "=== Debug environment ready ==="
+echo "  nc $IP_ADDR 2323    (remote shell)"
+echo "  ssh root@$IP_ADDR   (password: debug)"
+if [ -n "$ROOT_DEVICE" ]; then
+    echo "  root: $ROOT_DEVICE $ROOT_ARGS"
+fi
+echo "==============================="
+`;
+    return reply.type("text/plain").send(script);
+  });
+
+  app.get<{ Querystring: { mac?: string; arch?: string } }>("/dispatch", async (request, reply) => {
     const mac = (request.query.mac ?? "").toLowerCase().replace(/-/g, ":");
     const currentState = state.load();
+    const arch = resolveArch(currentState, mac, request.query.arch, config);
+    const fedoraMirror = fedoraMirrorFor(config.fedoraVersion, arch);
 
     // Debug mode takes highest priority — auto-clear after serving once
     const debugEntry = currentState.debug[mac];
     if (debugEntry) {
       const hostname = debugEntry.hostname ?? "debug";
-      logger.info(`DEBUG BOOT: ${mac} -> ${hostname} (rescue mode)`);
-
       state.update((s) => { delete s.debug[mac]; });
 
-      const script = renderDebugIpxe({
-        mac,
-        hostname,
-        serverIp: config.serverIp,
-        httpPort: config.httpPort,
-        fedoraMirror: config.fedoraMirror,
-      });
+      let script: string;
+      const wantsPxeBoot = debugEntry.pxeBoot === true;
+      const root = wantsPxeBoot ? resolveRoot(currentState, mac) : null;
+
+      if (root !== null) {
+        logger.info(`PXE BOOT DEBUG: ${mac} -> ${hostname} (${arch}, root=${root.rootDevice})`);
+        script = renderPxeBootDebugIpxe({
+          mac,
+          hostname,
+          serverIp: config.serverIp,
+          httpPort: config.httpPort,
+          arch,
+          ...root,
+        });
+      } else {
+        // --pxe-boot without a known root device falls back to rescue rather than
+        // guessing. A wrong root= leaves the machine unbootable, and rescue is where
+        // the operator can find the real one (curl /debug-setup.sh reports it back).
+        const notice = wantsPxeBoot
+          ? [
+              "",
+              "NOTE: --pxe-boot requested, but no root device is recorded",
+              "      for this machine. Booting rescue instead.",
+              "      From the rescue shell, run:",
+              // No pipe or && here: iPXE treats || and && as command separators, so keep
+              // the printed command free of anything its parser might claim.
+              `        curl -s http://${config.serverIp}:${config.httpPort}/debug-setup.sh -o /tmp/s.sh ; sh /tmp/s.sh`,
+              "      then retry --pxe-boot.",
+            ]
+          : undefined;
+        if (wantsPxeBoot) {
+          logger.warn(`PXE BOOT DEBUG: ${mac} -> ${hostname} has no recorded root device -- serving rescue instead`);
+        } else {
+          logger.info(`DEBUG BOOT: ${mac} -> ${hostname} (${arch}, rescue mode)`);
+        }
+        script = renderDebugIpxe({
+          mac,
+          hostname,
+          serverIp: config.serverIp,
+          httpPort: config.httpPort,
+          fedoraMirror,
+          arch,
+          ...(notice ? { notice } : {}),
+        });
+      }
       return reply.type("text/plain").send(script);
     }
 
@@ -54,10 +214,24 @@ export function registerDispatchRoutes(
     if (queueEntry) {
       const hostname = queueEntry.hostname ?? "lab-node";
       const os = queueEntry.os ?? "fedora-43";
-      logger.info(`INSTALL STARTED: ${mac} -> ${hostname} (${os})`);
+      logger.info(`INSTALL STARTED: ${mac} -> ${hostname} (${os}, ${arch})`);
 
       let script: string;
       if (os.startsWith("ubuntu")) {
+        // Last line of defence. The install guard refuses this combination when the
+        // machine's architecture is already known, but a machine queued before it was
+        // discovered can reach here. Serving the x86-only Ubuntu kernel to an arm64
+        // client is precisely the bug this work exists to fix, so stop instead.
+        if (!osSupportsArch(os as OsId, arch)) {
+          logger.error(`INSTALL BLOCKED: ${mac} -> ${hostname} -- ${os} has no ${arch} artifacts`);
+          script = renderUnsupportedIpxe({
+            hostname,
+            mac,
+            reason: `${os} publishes no ${arch} netboot artifacts`,
+            action: `labctl provision install ${mac} ${hostname} --os fedora-43`,
+          });
+          return reply.type("text/plain").send(script);
+        }
         script = renderUbuntuInstallIpxe({
           mac,
           hostname,
@@ -72,7 +246,8 @@ export function registerDispatchRoutes(
           serverIp: config.serverIp,
           httpPort: config.httpPort,
           fedoraVersion: config.fedoraVersion,
-          fedoraMirror: config.fedoraMirror,
+          fedoraMirror,
+          arch,
         });
       }
 
@@ -89,13 +264,14 @@ export function registerDispatchRoutes(
     }
 
     // Unknown MAC -> discovery mode
-    logger.info(`PXE request from ${mac} -> discovery mode`);
+    logger.info(`PXE request from ${mac} (${arch}) -> discovery mode`);
 
     const script = renderDiscoverIpxe({
       mac,
       serverIp: config.serverIp,
       httpPort: config.httpPort,
-      fedoraMirror: config.fedoraMirror,
+      fedoraMirror,
+      arch,
     });
 
     return reply.type("text/plain").send(script);

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 ?? "",
@@ -34,6 +41,150 @@ export function registerKickstartRoutes(
     return reply.type("text/plain").send(ks);
   });
 
+  // Auto-detecting kickstart for ISO boot (no-network machines like R1 ARM).
+  // %pre detects MAC, queries bastion state, writes dynamic kickstart to /tmp.
+  // Main body %include's it — so Anaconda gets either discover or install content.
+  app.get("/ks-auto", async (_request, reply) => {
+    const bastionUrl = `http://${config.serverIp}:${config.httpPort}`;
+
+    const ks = `# Lab Bastion -- Auto-detect kickstart (ISO boot)
+# %pre detects MAC, queries bastion state, writes /tmp/dynamic.ks.
+# Main body %include's it to get either discovery reboot or full install.
+
+%pre --erroronfail --log=/tmp/ks-auto.log
+#!/bin/bash
+set -x
+
+# -- Detect MAC address --
+MAC=$(ip link show | awk '/ether/ && !/00:00:00:00/ {print $2; exit}')
+echo "Detected MAC: $MAC"
+
+# -- Wait for network (Linux drivers may take a moment) --
+for i in $(seq 1 30); do
+    if curl -sf "${bastionUrl}/healthz" >/dev/null 2>&1; then
+        echo "Bastion reachable at ${bastionUrl}"
+        break
+    fi
+    echo "Waiting for network... ($i/30)"
+    sleep 2
+done
+
+# -- Query bastion for machine state --
+STATE=$(curl -sf "${bastionUrl}/api/machine-state/$MAC" 2>/dev/null || echo "unknown")
+echo "Machine state: $STATE"
+
+case "$STATE" in
+    queued|installing)
+        echo "=== Machine queued for install. Fetching install kickstart... ==="
+        curl -sf "${bastionUrl}/ks?mac=$MAC" > /tmp/dynamic.ks
+        if [ -s /tmp/dynamic.ks ]; then
+            echo "Install kickstart downloaded ($(wc -l < /tmp/dynamic.ks) lines)"
+        else
+            echo "ERROR: Failed to download install kickstart"
+            exit 1
+        fi
+
+        # Run any %pre scripts from the downloaded kickstart.
+        # Anaconda only runs %pre from the top-level file, not from %include'd files.
+        python3 -c "
+import re, subprocess
+content = open('/tmp/dynamic.ks').read()
+blocks = re.findall(r'%pre[^\\n]*\\n(.*?)%end', content, re.DOTALL)
+for i, script in enumerate(blocks):
+    path = f'/tmp/inner-pre-{i}.sh'
+    with open(path, 'w') as f:
+        f.write(script)
+    print(f'Running inner %pre script {i} ({len(script.splitlines())} lines)')
+    subprocess.run(['bash', path], check=False)
+"
+        ;;
+
+    debug)
+        echo "=== Debug mode ==="
+        curl -sf "${bastionUrl}/debug.ks?mac=$MAC" > /tmp/dynamic.ks 2>/dev/null
+        if [ ! -s /tmp/dynamic.ks ]; then
+            echo "rescue" > /tmp/dynamic.ks
+        fi
+        ;;
+
+    *)
+        echo "=== Running hardware discovery ==="
+        # Collect hardware info
+        PRODUCT=$(cat /sys/class/dmi/id/product_name 2>/dev/null || echo "unknown")
+        BOARD=$(cat /sys/class/dmi/id/board_name 2>/dev/null || echo "unknown")
+        SERIAL=$(cat /sys/class/dmi/id/product_serial 2>/dev/null || echo "unknown")
+        MANUFACTURER=$(cat /sys/class/dmi/id/sys_vendor 2>/dev/null || echo "unknown")
+        CPUMODEL=$(grep -m1 'model name' /proc/cpuinfo | cut -d: -f2 | sed 's/^ //')
+        CPUCORES=$(grep -c '^processor' /proc/cpuinfo)
+        MEMGB=$(awk '/MemTotal/ {printf "%d", $2/1024/1024}' /proc/meminfo)
+        ARCHTYPE=$(uname -m)
+
+        DISKS_JSON=$(lsblk -Jb -o NAME,SIZE,TYPE,MODEL 2>/dev/null | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+disks = [d for d in data.get('blockdevices', []) if d.get('type') == 'disk']
+result = []
+for d in disks:
+    size_gb = round(int(d.get('size', 0)) / 1073741824, 1)
+    result.append({'name': d.get('name', '?'), 'size_gb': size_gb, 'model': (d.get('model') or 'unknown').strip()})
+print(json.dumps(result))
+" 2>/dev/null || echo '[]')
+
+        NICS_JSON=$(ip -j link show 2>/dev/null | python3 -c "
+import sys, json
+nics = json.load(sys.stdin)
+result = []
+for n in nics:
+    if n.get('link_type') == 'loopback': continue
+    result.append({'name': n.get('ifname', '?'), 'mac': n.get('address', '?'), 'state': n.get('operstate', '?')})
+print(json.dumps(result))
+" 2>/dev/null || echo '[]')
+
+        PAYLOAD=$(python3 -c "
+import json
+print(json.dumps({
+    'mac': '$MAC', 'product': '$PRODUCT', 'board': '$BOARD', 'serial': '$SERIAL',
+    'manufacturer': '$MANUFACTURER', 'cpu_model': '$CPUMODEL',
+    'cpu_cores': int('$CPUCORES' or 0), 'memory_gb': int('$MEMGB' or 0),
+    'arch': '$ARCHTYPE', 'disks': $DISKS_JSON, 'nics': $NICS_JSON
+}))
+")
+
+        curl -sf -X POST "${bastionUrl}/api/discover" \\
+            -H "Content-Type: application/json" \\
+            -d "$PAYLOAD" || true
+
+        echo ""
+        echo "=== Discovery complete ==="
+        echo "Machine MAC: $MAC"
+        echo "Queue for install: labctl provision install $MAC <hostname> --role infra"
+        echo "Then reboot to start installation."
+        echo ""
+
+        # Write a minimal kickstart that just reboots
+        cat > /tmp/dynamic.ks << 'DISCOVER_KS'
+# Discovery mode -- reboot to allow install queue
+reboot
+DISCOVER_KS
+
+        # Force reboot now (don't wait for Anaconda)
+        sleep 3
+        echo 1 > /proc/sys/kernel/sysrq
+        echo b > /proc/sysrq-trigger
+        sleep 5
+        reboot -f
+        ;;
+esac
+
+%end
+
+# Include the dynamically chosen kickstart
+%include /tmp/dynamic.ks
+`;
+
+    return reply.type("text/plain").send(ks);
+  });
+
   // Ubuntu autoinstall user-data (cloud-init)
   app.get<{ Params: { mac: string } }>("/autoinstall/:mac/user-data", async (request, reply) => {
     const mac = request.params.mac.toLowerCase().replace(/-/g, ":");

bastion/src/bastion/src/server.ts

@@ -11,6 +11,7 @@ import { logger } from "./services/logger.js";
 import { registerDispatchRoutes } from "./routes/dispatch.js";
 import { registerKickstartRoutes } from "./routes/kickstart.js";
 import { registerApiRoutes } from "./routes/api.js";
+import { registerAsahiRoutes } from "./routes/asahi.js";
 
 
 export function createApp(config: BastionConfig): { app: ReturnType<typeof Fastify>; state: StateManager; installLog: InstallLogBuffer; syslog: SyslogListener } {
@@ -43,8 +44,9 @@ 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);
+  registerAsahiRoutes(app, config);
   // boot.iso is generated at startup and served as a static file from httpDir
   // (static serving supports HTTP Range requests, required by JetKVM streaming)
 

bastion/src/bastion/src/services/install-guard.ts

@@ -0,0 +1,94 @@
+// Pre-flight checks for queuing an OS install.
+//
+// Both entry points -- the HTTP /api/install route and the labd command-install handler
+// -- run this, so `labctl provision install` and `provision reprovision` are covered
+// whichever way the request arrives.
+//
+// Rescue/debug is deliberately NOT guarded. Being unable to reinstall a machine is
+// exactly when you most need to boot it into a rescue shell.
+
+import type { Arch, BastionState, OsId } from "@lab/shared";
+import { classifyOnboard, normalizeArch, osSupportsArch, vendorOsDescription, archesForOs } from "@lab/shared";
+
+export type InstallCheck =
+  | { allowed: true }
+  | { allowed: false; error: string };
+
+interface MachineIdentity {
+  hostname: string;
+  arch: Arch | undefined;
+  identity: Parameters<typeof classifyOnboard>[0];
+}
+
+/** Best-known identity for a MAC, merged across the three state maps. */
+function identify(state: BastionState, mac: string): MachineIdentity {
+  const discovered = state.discovered[mac];
+  const installed = state.installed[mac];
+  const queued = state.install_queue[mac];
+
+  const manufacturer = discovered?.manufacturer ?? installed?.manufacturer;
+  const product = discovered?.product ?? installed?.product;
+  const board = discovered?.board;
+  const onboard = installed?.onboard ?? discovered?.onboard;
+  const vendorOs = installed?.vendor_os ?? discovered?.vendor_os;
+
+  return {
+    hostname: installed?.hostname ?? queued?.hostname ?? discovered?.product ?? mac,
+    arch: normalizeArch(installed?.arch ?? queued?.arch ?? discovered?.arch),
+    identity: {
+      mac,
+      ...(manufacturer !== undefined ? { manufacturer } : {}),
+      ...(product !== undefined ? { product } : {}),
+      ...(board !== undefined ? { board } : {}),
+      ...(onboard !== undefined ? { onboard } : {}),
+      ...(vendorOs !== undefined ? { vendor_os: vendorOs } : {}),
+    },
+  };
+}
+
+/**
+ * Decide whether `mac` may be queued for an install of `os`.
+ *
+ * Refusals name the machine and the reason, and point at the action that is available
+ * instead. An operator hitting this at 2am should not have to read the source to work
+ * out what happened.
+ */
+export function checkInstallAllowed(
+  state: BastionState,
+  mac: string,
+  os: OsId,
+): InstallCheck {
+  const machine = identify(state, mac);
+  const { onboard, vendor_os } = classifyOnboard(machine.identity);
+
+  // 1. Machines running a vendor OS we cannot rebuild.
+  if (onboard === "ssh") {
+    const what = vendorOsDescription(vendor_os);
+    return {
+      allowed: false,
+      error:
+        `Refusing to install ${machine.hostname} (${mac}): it runs ${what}. ` +
+        `No image in our pipeline can restore it, so installing ${os} would destroy that ` +
+        `driver and firmware stack permanently. This machine is SSH-onboard: we manage its ` +
+        `userspace, not its OS. ` +
+        `To boot it into a rescue shell instead, run: labctl provision debug ${machine.hostname}`,
+      // TODO: when a DGX OS / SparkOS image joins the pipeline, an install targeting a
+      // machine whose vendor_os matches that image should be allowed through here.
+    };
+  }
+
+  // 2. Architecture the OS has no netboot artifacts for.
+  if (machine.arch !== undefined && !osSupportsArch(os, machine.arch)) {
+    const supported = archesForOs(os);
+    return {
+      allowed: false,
+      error:
+        `Refusing to install ${os} on ${machine.hostname} (${mac}): ` +
+        `${os} has no ${machine.arch} netboot artifacts` +
+        (supported.length > 0 ? ` (only ${supported.join(", ")})` : "") +
+        `. Use an OS that supports ${machine.arch}.`,
+    };
+  }
+
+  return { allowed: true };
+}

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

@@ -165,6 +165,8 @@ export class BastionConnection {
       case "command-forget":
       case "command-role-update":
       case "command-debug":
+      case "command-register":
+      case "command-discover":
         void this.handleCommand(msg);
         break;
     }

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

@@ -30,6 +30,8 @@ export class SyslogListener {
   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;
@@ -37,14 +39,21 @@ export class SyslogListener {
     this.state = state;
   }
 
-  /** Resolve a source IP to a MAC address using the install queue. */
+  /** 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)) {
-      // The progress callback sends IP in "complete" detail, but during install
-      // we need to match by what we know. Check if any progress mentions this IP.
       if (entry.progress_detail?.includes(ip)) return mac;
     }
 

bastion/src/bastion/src/templates/asahi-firstboot.sh.ts

@@ -0,0 +1,311 @@
+// First-boot LVM setup script for Asahi-provisioned machines.
+// Embedded in the custom rootfs as a systemd service that runs once on first boot.
+// Creates the standard lab LVM layout on the data partition, matching install.ks.ts.
+
+import type { Role } from "@lab/shared";
+
+export interface AsahiFirstbootParams {
+  hostname: string;
+  role: Role;
+  serverIp: string;
+  httpPort: number;
+  sshKeys: string[];
+  adminUser: string;
+  mac: string;
+}
+
+export function renderFirstbootScript(params: AsahiFirstbootParams): string {
+  const { hostname, role, serverIp, httpPort, sshKeys, adminUser, mac } = params;
+
+  const isWorker = role === "worker";
+  const isInfra = role === "infra" || role === "labcontroller";
+
+  // Role-specific LV creation commands
+  const roleLvLines: string[] = [];
+  const roleFormatLines: string[] = [];
+  const roleMountLines: string[] = [];
+  const roleFstabLines: string[] = [];
+
+  if (isInfra) {
+    roleLvLines.push('lvcreate -L 20480M -n rancher labvg -y');
+    roleFormatLines.push('mkfs.xfs /dev/labvg/rancher');
+    roleMountLines.push('mount_lv rancher /var/lib/rancher');
+    roleFstabLines.push('echo "/dev/labvg/rancher /var/lib/rancher xfs defaults 0 0" >> /etc/fstab');
+  }
+  if (isWorker || isInfra) {
+    roleLvLines.push('lvcreate -l 100%FREE -n longhorn labvg -y');
+    roleFormatLines.push('mkfs.xfs /dev/labvg/longhorn');
+    roleMountLines.push('mount_lv longhorn /var/lib/longhorn');
+    roleFstabLines.push('echo "/dev/labvg/longhorn /var/lib/longhorn xfs defaults 0 0" >> /etc/fstab');
+  }
+
+  // SSH key injection block (empty if no keys)
+  const sshKeyBlock = sshKeys.length > 0
+    ? sshKeys.map(k => `echo '${k}' >> "$ADMIN_SSH/authorized_keys"`).join('\n')
+    : 'true  # no SSH keys configured';
+  const rootSshKeyBlock = sshKeys.length > 0
+    ? sshKeys.map(k => `echo '${k}' >> /root/.ssh/authorized_keys`).join('\n')
+    : 'true  # no SSH keys configured';
+
+  // NOTE: All bash $ references use $VAR not \${VAR} to avoid TS template conflicts.
+  // Where ${} is needed in bash, we use \\${...} to escape.
+  return `#!/bin/bash
+# Lab first-boot LVM setup — generated by bastion
+# This script runs once on first boot via systemd, then disables itself.
+set -euo pipefail
+
+MARKER="/etc/lab-lvm-setup-done"
+LOG="/var/log/lab-firstboot.log"
+
+exec > >(tee -a "$LOG") 2>&1
+echo "=== Lab first-boot LVM setup ==="
+date
+
+# Already done?
+if [ -f "$MARKER" ]; then
+    echo "LVM setup already completed, skipping."
+    exit 0
+fi
+
+# ── Find the data partition ──────────────────────────────────────
+# The data partition/disk is a large block device that is NOT the root filesystem.
+# Handles: NVMe partitions, SCSI partitions, whole unpartitioned disks.
+ROOT_DEV=$(findmnt -n -o SOURCE / | sed 's/\\[.*\\]//')  # strip btrfs subvol
+ROOT_DISK=$(lsblk -n -o PKNAME "$ROOT_DEV" 2>/dev/null | head -1)
+echo "Root device: $ROOT_DEV (disk: $ROOT_DISK)"
+
+DATA_PART=""
+# Scan partitions first, then whole disks
+for part in /dev/nvme*n*p* /dev/sd*[0-9] /dev/vd*[0-9] /dev/nvme*n* /dev/sd[b-z] /dev/vd[b-z]; do
+    [ -b "$part" ] || continue
+    # Skip root device and root disk
+    [ "$part" = "$ROOT_DEV" ] && continue
+    PART_DISK=$(basename "$part" | sed 's/p[0-9]*$//' | sed 's/[0-9]*$//')
+    [ "$PART_DISK" = "$ROOT_DISK" ] && continue
+    # Skip small devices (<50GB) — EFI, boot, APFS stubs
+    SIZE_BYTES=$(blockdev --getsize64 "$part" 2>/dev/null || echo 0)
+    SIZE_GB=$((SIZE_BYTES / 1073741824))
+    [ "$SIZE_GB" -lt 50 ] && continue
+    # Use if unformatted or already LVM
+    FSTYPE=$(blkid -o value -s TYPE "$part" 2>/dev/null || echo "")
+    if [ -z "$FSTYPE" ] || [ "$FSTYPE" = "LVM2_member" ]; then
+        DATA_PART="$part"
+        echo "Found data device: $DATA_PART ($SIZE_GB GB)"
+        break
+    fi
+done
+
+if [ -z "$DATA_PART" ]; then
+    echo "ERROR: No suitable data partition found for LVM."
+    echo "Expected a large (>50GB) unformatted partition."
+    exit 1
+fi
+
+# ── Helper function ──────────────────────────────────────────────
+mount_lv() {
+    local lv="$1" mp="$2"
+    if lvs "labvg/$lv" &>/dev/null; then
+        mkdir -p "$mp"
+        mount "/dev/labvg/$lv" "$mp" 2>/dev/null || true
+        echo "  Mounted $lv -> $mp"
+    fi
+}
+
+# ── Write fstab function (idempotent) ────────────────────────────
+write_lab_fstab() {
+    # Remove any previous lab LVM entries (clean slate)
+    sed -i '/# lab-lvm:/d' /etc/fstab
+    sed -i '/# Lab LVM volumes/d' /etc/fstab
+    grep -v "/dev/labvg/" /etc/fstab > /etc/fstab.tmp && mv /etc/fstab.tmp /etc/fstab
+    # Comment out non-LVM entries for mount points we manage
+    for mp in "/var " "/var/log " "/home " "/srv "; do
+        if grep -q "$mp" /etc/fstab; then
+            awk -v m="$mp" '{if($0 !~ /^#/ && index($0,m)) print "# lab-lvm: " $0; else print}' /etc/fstab > /etc/fstab.tmp
+            mv /etc/fstab.tmp /etc/fstab
+        fi
+    done
+    # Add fresh LVM entries
+    echo "# Lab LVM volumes" >> /etc/fstab
+    echo "/dev/labvg/swap    none         swap defaults 0 0" >> /etc/fstab
+    echo "/dev/labvg/var     /var         xfs  defaults 0 0" >> /etc/fstab
+    echo "/dev/labvg/varlog  /var/log     xfs  defaults 0 0" >> /etc/fstab
+    echo "/dev/labvg/home    /home        xfs  defaults 0 0" >> /etc/fstab
+    echo "/dev/labvg/srv     /srv         xfs  defaults 0 0" >> /etc/fstab
+    ${roleFstabLines.join('\n    ')}
+}
+
+# ── Check for existing VG ────────────────────────────────────────
+if vgs labvg &>/dev/null; then
+    echo "Volume group 'labvg' already exists — reprovision detected."
+    echo "Activating existing volumes..."
+    vgchange -ay labvg
+
+    mount_lv var /var
+    mount_lv varlog /var/log
+    mount_lv home /home
+    mount_lv srv /srv
+${roleMountLines.map(l => `    ${l}`).join('\n')}
+
+    # Enable swap
+    if lvs labvg/swap &>/dev/null; then
+        swapon /dev/labvg/swap 2>/dev/null || true
+        echo "  Enabled swap"
+    fi
+
+    # Ensure fstab entries exist — comment out conflicting btrfs subvol entries
+    write_lab_fstab
+
+    echo "Existing LVM volumes re-mounted."
+else
+# ── Fresh install: create LVM ────────────────────────────────────
+echo "Creating LVM on $DATA_PART..."
+
+pvcreate "$DATA_PART"
+vgcreate labvg "$DATA_PART"
+
+# Create LVs — sizes match install.ks.ts (in MiB)
+echo "Creating logical volumes..."
+lvcreate -L 27648M  -n swap   labvg -y   # 27GB swap
+lvcreate -L 102400M -n var    labvg -y   # 100GB /var
+lvcreate -L 10240M  -n varlog labvg -y   # 10GB /var/log
+lvcreate -L 10240M  -n home   labvg -y   # 10GB /home
+lvcreate -L 20480M  -n srv    labvg -y   # 20GB /srv
+${roleLvLines.join('\n')}
+
+# Format
+echo "Formatting volumes..."
+mkswap /dev/labvg/swap
+mkfs.xfs /dev/labvg/var
+mkfs.xfs /dev/labvg/varlog
+mkfs.xfs /dev/labvg/home
+mkfs.xfs /dev/labvg/srv
+${roleFormatLines.join('\n')}
+
+# Migrate and mount volumes that can be switched live.
+# Copy existing content first so we don't shadow files (e.g. /home/user/.ssh).
+for LV_MOUNT in "home /home" "srv /srv"; do
+    LV_NAME=$(echo "$LV_MOUNT" | awk '{print $1}')
+    MOUNT_PT=$(echo "$LV_MOUNT" | awk '{print $2}')
+    STAGING="/mnt/labvg-$LV_NAME-staging"
+    mkdir -p "$STAGING"
+    mount "/dev/labvg/$LV_NAME" "$STAGING"
+    cp -a "$MOUNT_PT"/. "$STAGING/" 2>/dev/null || true
+    umount "$STAGING"
+    rmdir "$STAGING"
+    mount_lv "$LV_NAME" "$MOUNT_PT"
+done
+
+# Mount role-specific volumes (empty, no content to preserve)
+set +e
+${roleMountLines.join('\n')}
+set -e
+
+# Copy existing /var content into the LV for next boot
+echo "Preparing /var LV for next boot..."
+TMPVAR="/mnt/labvg-var-staging"
+mkdir -p "$TMPVAR"
+mount /dev/labvg/var "$TMPVAR"
+cp -a /var/. "$TMPVAR/" 2>/dev/null || true
+umount "$TMPVAR"
+rmdir "$TMPVAR"
+
+# Same for /var/log
+TMPVARLOG="/mnt/labvg-varlog-staging"
+mkdir -p "$TMPVARLOG"
+mount /dev/labvg/varlog "$TMPVARLOG"
+cp -a /var/log/. "$TMPVARLOG/" 2>/dev/null || true
+umount "$TMPVARLOG"
+rmdir "$TMPVARLOG"
+
+echo "NOTE: /var and /var/log will switch to LVM on next reboot."
+
+# Enable swap
+swapon /dev/labvg/swap 2>/dev/null || true
+
+write_lab_fstab
+
+echo "LVM setup complete."
+lvs labvg
+
+fi  # end if/else for reprovision vs fresh install
+
+# ── Set hostname (use configured value, or keep existing) ────────
+CONF_HOSTNAME="${hostname}"
+if [ "$CONF_HOSTNAME" != "unknown" ] && [ -n "$CONF_HOSTNAME" ]; then
+    hostnamectl set-hostname "$CONF_HOSTNAME"
+fi
+ACTUAL_HOSTNAME=$(hostname)
+
+# ── Detect MAC address ───────────────────────────────────────────
+CONF_MAC="${mac}"
+if [ "$CONF_MAC" = "unknown" ] || [ -z "$CONF_MAC" ]; then
+    CONF_MAC=$(ip -o link show | grep -v "lo:" | grep "state UP" | head -1 | grep -oP 'link/ether \\K[^ ]+' || echo "unknown")
+fi
+
+# ── Configure admin user ─────────────────────────────────────────
+ADMIN="${adminUser}"
+if ! id "$ADMIN" &>/dev/null; then
+    useradd -m -G wheel "$ADMIN"
+    echo "$ADMIN ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/$ADMIN
+    chmod 440 /etc/sudoers.d/$ADMIN
+fi
+ADMIN_SSH="/home/$ADMIN/.ssh"
+mkdir -p "$ADMIN_SSH"
+chmod 700 "$ADMIN_SSH"
+${sshKeyBlock}
+chmod 600 "$ADMIN_SSH/authorized_keys"
+chown -R $ADMIN:$ADMIN "$ADMIN_SSH"
+
+# Also authorize root
+mkdir -p /root/.ssh
+chmod 700 /root/.ssh
+${rootSshKeyBlock}
+chmod 600 /root/.ssh/authorized_keys
+
+# ── Harden SSH (takes effect on next sshd restart/reboot) ────────
+sed -i 's/^#*PermitRootLogin.*/PermitRootLogin prohibit-password/' /etc/ssh/sshd_config
+sed -i 's/^#*PasswordAuthentication.*/PasswordAuthentication no/' /etc/ssh/sshd_config
+
+# ── Write provisioning metadata ──────────────────────────────────
+cat > /etc/lab-provisioned << LABMETA
+hostname=$ACTUAL_HOSTNAME
+role=${role}
+mac=$CONF_MAC
+provisioned_at=$(date -Iseconds)
+method=asahi-firstboot
+LABMETA
+
+# ── Register with bastion ─────────────────────────────────────────
+IP=$(hostname -I | awk '{print $1}')
+echo "Registering with bastion at ${serverIp}:${httpPort}..."
+curl -sf -X POST "http://${serverIp}:${httpPort}/api/register" \\
+    -H "Content-Type: application/json" \\
+    -d "{\\"mac\\":\\"$CONF_MAC\\",\\"hostname\\":\\"$ACTUAL_HOSTNAME\\",\\"role\\":\\"${role}\\",\\"ip\\":\\"$IP\\"}" \\
+    2>/dev/null && echo "  Registered as $ACTUAL_HOSTNAME ($IP)" \\
+    || echo "  WARNING: Could not reach bastion — register manually with: labctl provision register $CONF_MAC $ACTUAL_HOSTNAME --role ${role} --ip $IP"
+
+# ── Mark done ────────────────────────────────────────────────────
+touch "$MARKER"
+echo "=== First-boot setup complete ==="
+`;
+}
+
+/** Systemd unit file for the first-boot service */
+export function renderFirstbootUnit(): string {
+  return `[Unit]
+Description=Lab first-boot LVM setup
+After=local-fs.target network-online.target
+Wants=network-online.target
+ConditionPathExists=!/etc/lab-lvm-setup-done
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/lab-firstboot.sh
+RemainAfterExit=yes
+StandardOutput=journal+console
+StandardError=journal+console
+
+[Install]
+WantedBy=multi-user.target
+`;
+}

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

@@ -1,4 +1,55 @@
 // iPXE boot script templates for dispatch routing.
+//
+// Architecture handling: the bastion serves one kernel/initrd pair per architecture.
+// x86_64 keeps the original unsuffixed paths so its output is unchanged; every other
+// architecture gets an arch-suffixed pair. See stageBootArtifacts() in main.ts for the
+// matching staging side, and boot-iso.ts for the same scheme on the ISO path.
+
+import type { Arch } from "@lab/shared";
+
+/** Kernel/initrd URL paths, keyed by architecture. */
+export function kernelPath(arch: Arch): string {
+  return arch === "x86_64" ? "/vmlinuz" : `/vmlinuz-${arch}`;
+}
+
+export function initrdPath(arch: Arch): string {
+  return arch === "x86_64" ? "/initrd.img" : `/initrd-${arch}.img`;
+}
+
+/**
+ * Console arguments per architecture.
+ *
+ * arm64 has no VGA text console: a headless machine only talks over the SoC UART, so
+ * ttyAMA0 must be listed as well. The last console= wins for /dev/console, so serial
+ * is the interactive one while tty0 still receives boot output on machines with a
+ * display attached.
+ */
+const CONSOLE_ARGS: Record<Arch, string> = {
+  x86_64: "console=tty0",
+  aarch64: "console=tty0 console=ttyAMA0,115200",
+};
+
+/**
+ * Anaconda arguments for the graphical-suppression / console setup.
+ *
+ * `nomodeset` disables kernel mode setting, which on x86 forces the generic VGA path
+ * and makes flaky GPU drivers survive the installer. On arm64 it does not mean the
+ * same thing -- there is no VGA fallback to drop back to, and it can leave the machine
+ * with no usable console at all -- so arm64 gets explicit console arguments instead.
+ */
+function installerArgs(arch: Arch): string {
+  return arch === "x86_64" ? "inst.text nomodeset" : `inst.text ${CONSOLE_ARGS[arch]}`;
+}
+
+/** Extra console arguments appended to templates that don't already set them. */
+function extraConsoleArgs(arch: Arch): string {
+  return arch === "x86_64" ? "" : ` ${CONSOLE_ARGS[arch]}`;
+}
+
+/** Join kernel arguments, dropping empties so callers can pass optional groups. */
+function joinArgs(...parts: Array<string | undefined>): string {
+  return parts.filter((p) => p !== undefined && p !== "").join(" ");
+}
 
 export interface BootIpxeParams {
   serverIp: string;
@@ -8,6 +59,11 @@ export interface BootIpxeParams {
 /**
  * Initial iPXE boot script that chains to the dispatch endpoint.
  * This is what dnsmasq serves to iPXE clients via HTTP.
+ *
+ * `${buildarch}` is iPXE's own build architecture ("x86_64" or "arm64"), which is the
+ * one architecture signal available on every path -- network PXE, UEFI HTTP boot and
+ * the boot ISO alike. DHCP option 93 only reaches dnsmasq, never this HTTP endpoint.
+ * dispatch prefers the tracked machine record and falls back to this.
  */
 export function renderBootIpxe(params: BootIpxeParams): string {
   return `#!ipxe
@@ -19,7 +75,7 @@ echo   Contacting server for instructions...
 echo ============================================
 echo
 
-chain http://${params.serverIp}:${params.httpPort}/dispatch?mac=\${net0/mac}
+chain http://${params.serverIp}:${params.httpPort}/dispatch?mac=\${net0/mac}&arch=\${buildarch}
 `;
 }
 
@@ -31,7 +87,9 @@ export function renderDiscoverIpxe(params: {
   serverIp: string;
   httpPort: number;
   fedoraMirror: string;
+  arch: Arch;
 }): string {
+  const base = `http://${params.serverIp}:${params.httpPort}`;
   return `#!ipxe
 
 echo
@@ -42,8 +100,8 @@ echo   Collecting hardware info...
 echo =============================================
 echo
 
-kernel http://${params.serverIp}:${params.httpPort}/vmlinuz inst.ks=http://${params.serverIp}:${params.httpPort}/discover.ks inst.stage2=${params.fedoraMirror} inst.text nomodeset
-initrd http://${params.serverIp}:${params.httpPort}/initrd.img
+kernel ${base}${kernelPath(params.arch)} inst.ks=${base}/discover.ks inst.stage2=${params.fedoraMirror} ${installerArgs(params.arch)}
+initrd ${base}${initrdPath(params.arch)}
 boot
 `;
 }
@@ -58,7 +116,9 @@ export function renderInstallIpxe(params: {
   httpPort: number;
   fedoraVersion: string;
   fedoraMirror: string;
+  arch: Arch;
 }): string {
+  const base = `http://${params.serverIp}:${params.httpPort}`;
   return `#!ipxe
 
 echo
@@ -69,8 +129,8 @@ 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 nomodeset
-initrd http://${params.serverIp}:${params.httpPort}/initrd.img
+kernel ${base}${kernelPath(params.arch)} inst.ks=${base}/ks?mac=${params.mac} inst.repo=${params.fedoraMirror} ${installerArgs(params.arch)}
+initrd ${base}${initrdPath(params.arch)}
 boot
 `;
 }
@@ -78,6 +138,9 @@ 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.
+ *
+ * `notice` is shown before the boot line. dispatch uses it to explain why a requested
+ * --pxe-boot fell back to rescue.
  */
 export function renderDebugIpxe(params: {
   mac: string;
@@ -85,7 +148,11 @@ export function renderDebugIpxe(params: {
   serverIp: string;
   httpPort: number;
   fedoraMirror: string;
+  arch: Arch;
+  notice?: string[];
 }): string {
+  const base = `http://${params.serverIp}:${params.httpPort}`;
+  const notice = (params.notice ?? []).map((line) => `echo   ${line}\n`).join("");
   return `#!ipxe
 
 echo
@@ -93,15 +160,86 @@ echo =============================================
 echo   Lab PXE Bastion - DEBUG/RESCUE MODE
 echo   Target: ${params.hostname}
 echo   MAC:    ${params.mac}
+${notice}echo =============================================
+echo
+
+kernel ${base}${kernelPath(params.arch)} inst.rescue inst.text inst.sshd inst.ks=${base}/debug.ks?mac=${params.mac} inst.stage2=${params.fedoraMirror}${extraConsoleArgs(params.arch)}
+initrd ${base}${initrdPath(params.arch)}
+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.
+ *
+ * rootDevice/rootArgs come from the machine's record -- they are not assumed. Our
+ * Fedora installs use an LVM layout, but nothing guarantees any given machine does,
+ * and a wrong root= here means an unbootable machine. dispatch refuses to render this
+ * script without them.
+ */
+export function renderPxeBootDebugIpxe(params: {
+  mac: string;
+  hostname: string;
+  serverIp: string;
+  httpPort: number;
+  arch: Arch;
+  rootDevice: string;
+  rootArgs?: string;
+}): string {
+  const base = `http://${params.serverIp}:${params.httpPort}`;
+  const cmdline = joinArgs(
+    `root=${params.rootDevice}`,
+    "ro",
+    params.rootArgs,
+    CONSOLE_ARGS[params.arch],
+  );
+  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 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
+kernel ${base}${kernelPath(params.arch)} ${cmdline}
+initrd ${base}${initrdPath(params.arch)}
 boot
 `;
 }
 
+/**
+ * iPXE script for a request we refuse to serve.
+ *
+ * Better a machine that stops with a legible reason on its console than one handed a
+ * kernel it cannot execute, which fails much later and much less clearly.
+ */
+export function renderUnsupportedIpxe(params: {
+  mac: string;
+  hostname: string;
+  reason: string;
+  action?: string;
+}): string {
+  return `#!ipxe
+
+echo
+echo =============================================
+echo   Lab PXE Bastion - CANNOT BOOT THIS MACHINE
+echo   Target: ${params.hostname}
+echo   MAC:    ${params.mac}
+echo
+echo   ${params.reason}
+${params.action !== undefined ? `echo\necho   Try: ${params.action}\n` : ""}echo =============================================
+echo
+sleep 10
+exit 1
+`;
+}
+
 /**
  * iPXE script for already-installed machines -- exits to boot from local disk.
  */

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

@@ -1,25 +1,33 @@
 // Debug/rescue kickstart template.
-// Minimal: sets SSH access and network for Anaconda rescue mode.
-// No disk operations, no packages, no %post.
+// 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 sshpw = "sshpw --username=root --plaintext lab-root-pw";
   const sshkeyLine = params.sshKeys.length > 0
     ? `sshkey --username=root "${params.sshKeys[0]}"`
     : "";
 
   return `# Lab Bastion -- Debug/Rescue Kickstart
-# Minimal: only SSH + network for Anaconda rescue mode
+# 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}
+sshpw --username=root --plaintext debug
 ${sshkeyLine}
 `;
 }

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

@@ -48,15 +48,20 @@ enable-tftp
 tftp-root=${tftpDir}
 tftp-no-blocksize
 
-# Detect client architecture -- PXE (TFTP) clients
+# Detect client architecture -- PXE (TFTP) clients.
+# Values are DHCP option 93 (Client System Architecture), IANA "Processor Architecture
+# Types". Getting these wrong means the machine is handed a bootloader its firmware
+# cannot execute, and it loops or hangs with no console output.
 dhcp-match=set:bios,option:client-arch,0
 dhcp-match=set:efi-x86_64,option:client-arch,7
 dhcp-match=set:efi-x86_64,option:client-arch,9
 dhcp-match=set:efi-arm64,option:client-arch,11
 
-# Detect client architecture -- UEFI HTTP Boot clients (no TFTP size limit)
+# Detect client architecture -- UEFI HTTP Boot clients (no TFTP size limit).
+# 16 = x64 uefi boot from http, 19 = arm uefi 64 boot from http.
+# (20 is pc/at bios boot from http -- not arm64.)
 dhcp-match=set:httpboot-x86_64,option:client-arch,16
-dhcp-match=set:httpboot-arm64,option:client-arch,20
+dhcp-match=set:httpboot-arm64,option:client-arch,19
 
 # Detect iPXE clients (already chainloaded)
 dhcp-userclass=set:ipxe,iPXE

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

@@ -134,10 +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}
-# Disabled: syslog UDP port needs to be exposed in k3s service/hostPort first
+logging --host=${serverIp} --port=${syslogPort}
 
 url --mirrorlist=https://mirrors.fedoraproject.org/mirrorlist?repo=fedora-$releasever&arch=$basearch
 
@@ -342,17 +341,7 @@ echo "tmpfs /tmp tmpfs defaults,noatime,nosuid,nodev,size=4G 0 0" >> /etc/fstab
 
 ${isVanilla ? `# -- vanilla role: skip k3s kernel/sysctl/firewall setup --
 # -- Enable chronyd for time sync --
-systemctl enable chronyd || true
-
-# -- Serial console (for debugging — auto-login as root on ttyS0) --
-# AWS EC2 compatible: ttyS0 @ 115200n8
-systemctl enable serial-getty@ttyS0.service || true
-
-# -- Forward all system logs to serial console --
-cat > /etc/rsyslog.d/serial-console.conf << 'RSYSLOG'
-*.* /dev/ttyS0
-RSYSLOG
-systemctl enable rsyslog || true` : `# -- Kernel modules for k3s --
+systemctl enable chronyd || true` : `# -- Kernel modules for k3s --
 cat > /etc/modules-load.d/k3s.conf << 'MODULES'
 br_netfilter
 overlay
@@ -396,6 +385,9 @@ fi
 
 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}

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

@@ -0,0 +1,291 @@
+// aarch64 support in the PXE dispatch path.
+//
+// The x86_64 side is pinned separately by ipxe-x86-regression.test.ts.
+
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdirSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import type { BastionConfig, BastionState, HardwareInfo } from "@lab/shared";
+import { createApp } from "../src/server.js";
+import { resolveArch } from "../src/routes/dispatch.js";
+import { renderDnsmasqConf } from "../src/templates/dnsmasq.conf.js";
+import type { FastifyInstance } from "fastify";
+import type { StateManager } from "../src/services/state.js";
+
+function createTestConfig(testDir: string): BastionConfig {
+  return {
+    fedoraVersion: "43",
+    arch: "x86_64",
+    httpPort: 0,
+    timezone: "Europe/London",
+    locale: "en_GB.UTF-8",
+    bastionDir: testDir,
+    domain: "test.local",
+    dhcpMode: "proxy",
+    dhcpRangeStart: "",
+    dhcpRangeEnd: "",
+    ubuntuVersion: "26.04",
+    ubuntuMirror: "https://releases.ubuntu.com/26.04",
+    iface: "eth0",
+    serverIp: "10.0.0.1",
+    network: "10.0.0.0",
+    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",
+    tftpDir: join(testDir, "tftp"),
+    httpDir: join(testDir, "http"),
+    stateFile: join(testDir, "state.json"),
+  };
+}
+
+function hardware(mac: string, over: Partial<HardwareInfo> = {}): HardwareInfo {
+  return {
+    mac,
+    product: "TestBox",
+    board: "TestBoard",
+    serial: "SN123",
+    manufacturer: "TestCorp",
+    cpu_model: "Test CPU",
+    cpu_cores: 4,
+    memory_gb: 16,
+    arch: "x86_64",
+    disks: [],
+    nics: [],
+    first_seen: new Date().toISOString(),
+    last_seen: new Date().toISOString(),
+    ...over,
+  };
+}
+
+const emptyState = (): BastionState => ({
+  discovered: {}, install_queue: {}, installed: {}, debug: {},
+});
+
+describe("architecture resolution", () => {
+  const config = createTestConfig("/tmp/unused");
+  const mac = "aa:bb:cc:dd:ee:ff";
+
+  it("prefers the tracked record over what the client reports", () => {
+    const state = emptyState();
+    state.discovered[mac] = hardware(mac, { arch: "aarch64" });
+    // Client claims x86_64; the machine record says otherwise and wins.
+    expect(resolveArch(state, mac, "x86_64", config)).toBe("aarch64");
+  });
+
+  it("falls back to the architecture reported at boot", () => {
+    expect(resolveArch(emptyState(), mac, "arm64", config)).toBe("aarch64");
+  });
+
+  it("normalises iPXE's arm64 spelling to aarch64", () => {
+    expect(resolveArch(emptyState(), mac, "arm64", config)).toBe("aarch64");
+    expect(resolveArch(emptyState(), mac, "x86_64", config)).toBe("x86_64");
+  });
+
+  it("falls back to the configured default for unknown architectures", () => {
+    expect(resolveArch(emptyState(), mac, "riscv64", config)).toBe("x86_64");
+    expect(resolveArch(emptyState(), mac, undefined, config)).toBe("x86_64");
+  });
+
+  it("reads arch from the installed record for already-provisioned machines", () => {
+    const state = emptyState();
+    state.installed[mac] = {
+      hostname: "spark", role: "worker", ip: "10.0.0.5",
+      installed_at: new Date().toISOString(), arch: "aarch64",
+    };
+    expect(resolveArch(state, mac, undefined, config)).toBe("aarch64");
+  });
+});
+
+describe("aarch64 dispatch", () => {
+  let testDir: string;
+  let app: FastifyInstance;
+  let state: StateManager;
+  const mac = "aa:bb:cc:dd:ee:ff";
+
+  beforeEach(() => {
+    testDir = join(tmpdir(), `bastion-arch-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+    mkdirSync(join(testDir, "http"), { recursive: true });
+    mkdirSync(join(testDir, "tftp"), { recursive: true });
+    const result = createApp(createTestConfig(testDir));
+    app = result.app;
+    state = result.state;
+  });
+
+  afterEach(async () => {
+    await app.close();
+    rmSync(testDir, { recursive: true, force: true });
+  });
+
+  it("serves the aarch64 kernel and initrd to an arm64 client", async () => {
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}&arch=arm64` });
+    expect(res.statusCode).toBe(200);
+    expect(res.body).toContain("/vmlinuz-aarch64");
+    expect(res.body).toContain("/initrd-aarch64.img");
+    expect(res.body).not.toContain("/vmlinuz ");
+  });
+
+  it("points an arm64 client at the aarch64 Fedora mirror", async () => {
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}&arch=arm64` });
+    expect(res.body).toContain("Everything/aarch64/os");
+    expect(res.body).not.toContain("Everything/x86_64/os");
+  });
+
+  it("uses serial console arguments and not nomodeset on arm64", async () => {
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}&arch=arm64` });
+    expect(res.body).toContain("console=ttyAMA0,115200");
+    expect(res.body).not.toContain("nomodeset");
+  });
+
+  it("refuses to serve the x86-only Ubuntu kernel to an arm64 client", async () => {
+    // A machine queued for Ubuntu before it was discovered as aarch64 reaches dispatch
+    // with no guard having run. Serving it /ubuntu-vmlinuz is the original bug.
+    state.update((s) => {
+      s.install_queue[mac] = {
+        hostname: "arm-node", disk: "", role: "worker",
+        os: "ubuntu-26.04", queued_at: new Date().toISOString(),
+      };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}&arch=arm64` });
+    expect(res.statusCode).toBe(200);
+    expect(res.body).toContain("CANNOT BOOT THIS MACHINE");
+    expect(res.body).toContain("no aarch64 netboot artifacts");
+    expect(res.body).not.toContain("ubuntu-vmlinuz");
+  });
+
+  it("still serves Ubuntu to an x86_64 client", async () => {
+    state.update((s) => {
+      s.install_queue[mac] = {
+        hostname: "x86-node", disk: "", role: "worker",
+        os: "ubuntu-26.04", queued_at: new Date().toISOString(),
+      };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}&arch=x86_64` });
+    expect(res.body).toContain("ubuntu-vmlinuz");
+    expect(res.body).not.toContain("CANNOT BOOT");
+  });
+
+  it("serves a rescue kernel for the recorded architecture, not the requester's", async () => {
+    // The Spark case: machine known to be aarch64, queued for rescue.
+    state.update((s) => {
+      s.discovered[mac] = hardware(mac, { arch: "aarch64" });
+      s.debug[mac] = { hostname: "spark-2935", queued_at: new Date().toISOString() };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}` });
+    expect(res.body).toContain("DEBUG/RESCUE MODE");
+    expect(res.body).toContain("/vmlinuz-aarch64");
+    expect(res.body).toContain("inst.rescue");
+    expect(res.body).toContain("inst.sshd");
+  });
+});
+
+describe("--pxe-boot root device", () => {
+  let testDir: string;
+  let app: FastifyInstance;
+  let state: StateManager;
+  const mac = "aa:bb:cc:dd:ee:ff";
+
+  beforeEach(() => {
+    testDir = join(tmpdir(), `bastion-root-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+    mkdirSync(join(testDir, "http"), { recursive: true });
+    mkdirSync(join(testDir, "tftp"), { recursive: true });
+    const result = createApp(createTestConfig(testDir));
+    app = result.app;
+    state = result.state;
+  });
+
+  afterEach(async () => {
+    await app.close();
+    rmSync(testDir, { recursive: true, force: true });
+  });
+
+  it("uses the root device recorded on the machine", async () => {
+    state.update((s) => {
+      s.installed[mac] = {
+        hostname: "worker-1", role: "worker", ip: "10.0.0.50",
+        installed_at: new Date().toISOString(),
+        root_device: "/dev/mapper/otherVG-root",
+        root_args: "rd.lvm.lv=otherVG/root",
+      };
+      s.debug[mac] = { hostname: "worker-1", queued_at: new Date().toISOString(), pxeBoot: true };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}` });
+    expect(res.body).toContain("PXE BOOT (debug)");
+    expect(res.body).toContain("root=/dev/mapper/otherVG-root");
+    expect(res.body).toContain("rd.lvm.lv=otherVG/root");
+    // The old hardcoded layout must not leak back in.
+    expect(res.body).not.toContain("labvg");
+  });
+
+  it("falls back to rescue rather than guessing when no root device is known", async () => {
+    state.update((s) => {
+      s.installed[mac] = {
+        hostname: "spark-2935", role: "worker", ip: "192.168.8.12",
+        installed_at: new Date().toISOString(), arch: "aarch64",
+      };
+      s.debug[mac] = { hostname: "spark-2935", queued_at: new Date().toISOString(), pxeBoot: true };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${mac}` });
+    expect(res.body).toContain("DEBUG/RESCUE MODE");
+    expect(res.body).toContain("no root device is recorded");
+    expect(res.body).toContain("debug-setup.sh");
+    expect(res.body).not.toContain("root=");
+    // And it is still the right architecture.
+    expect(res.body).toContain("/vmlinuz-aarch64");
+  });
+
+  it("records a root device reported from a rescue shell without erasing hardware info", async () => {
+    state.update((s) => {
+      s.discovered[mac] = hardware(mac, { product: "DGX Spark", manufacturer: "NVIDIA", arch: "aarch64" });
+    });
+
+    const res = await app.inject({
+      method: "POST",
+      url: "/api/discover",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ mac, root_device: "/dev/nvme0n1p2" }),
+    });
+    expect(res.statusCode).toBe(200);
+
+    const hw = state.load().discovered[mac];
+    expect(hw?.root_device).toBe("/dev/nvme0n1p2");
+    // The partial report must not blank what we already knew.
+    expect(hw?.product).toBe("DGX Spark");
+    expect(hw?.cpu_cores).toBe(4);
+    expect(hw?.arch).toBe("aarch64");
+  });
+});
+
+describe("dnsmasq architecture detection", () => {
+  const conf = renderDnsmasqConf(createTestConfig("/tmp/unused"));
+
+  it("maps DHCP option 93 values to per-architecture bootloaders", () => {
+    // 11 = ARM 64-bit UEFI
+    expect(conf).toContain("dhcp-match=set:efi-arm64,option:client-arch,11");
+    expect(conf).toContain("dhcp-boot=tag:efi-arm64,tag:!ipxe,ipxe-arm64.efi");
+    // 7 / 9 = x64 UEFI, 0 = x86 BIOS
+    expect(conf).toContain("dhcp-match=set:efi-x86_64,option:client-arch,7");
+    expect(conf).toContain("dhcp-match=set:efi-x86_64,option:client-arch,9");
+    expect(conf).toContain("dhcp-match=set:bios,option:client-arch,0");
+  });
+
+  it("matches arm64 UEFI HTTP boot on 19, not 20", () => {
+    // IANA: 19 = arm uefi 64 boot from http, 20 = pc/at bios boot from http.
+    expect(conf).toContain("dhcp-match=set:httpboot-arm64,option:client-arch,19");
+    expect(conf).not.toContain("dhcp-match=set:httpboot-arm64,option:client-arch,20");
+    expect(conf).toContain("dhcp-match=set:httpboot-x86_64,option:client-arch,16");
+  });
+
+  it("offers an arm64 PXE service directive in proxy mode", () => {
+    expect(conf).toContain('pxe-service=tag:!ipxe,ARM64_EFI,"PXE Boot",ipxe-arm64.efi');
+  });
+});

bastion/src/bastion/tests/asahi.test.ts

@@ -0,0 +1,225 @@
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdirSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import type { BastionConfig } from "@lab/shared";
+import { createApp } from "../src/server.js";
+import type { FastifyInstance } from "fastify";
+import { renderFirstbootScript, renderFirstbootUnit } from "../src/templates/asahi-firstboot.sh.js";
+
+function createTestConfig(testDir: string): BastionConfig {
+  return {
+    fedoraVersion: "43",
+    arch: "x86_64",
+    httpPort: 0,
+    timezone: "Europe/London",
+    locale: "en_GB.UTF-8",
+    bastionDir: testDir,
+    domain: "test.local",
+    dhcpMode: "proxy",
+    dhcpRangeStart: "",
+    dhcpRangeEnd: "",
+    ubuntuVersion: "26.04",
+    ubuntuMirror: "https://releases.ubuntu.com/26.04",
+    iface: "eth0",
+    serverIp: "192.168.8.1",
+    network: "192.168.8.0",
+    gateway: "192.168.8.1",
+    sshKeys: ["ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAITEST test@lab"],
+    adminUser: "michal",
+    syslogPort: 15514,
+    skipDnsmasq: true,
+    skipArtifacts: true,
+    fedoraMirror: "https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os",
+    tftpDir: join(testDir, "tftp"),
+    httpDir: join(testDir, "http"),
+    stateFile: join(testDir, "state.json"),
+  };
+}
+
+describe("asahi routes", () => {
+  let testDir: string;
+  let app: FastifyInstance;
+
+  beforeEach(() => {
+    testDir = join(tmpdir(), `bastion-asahi-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+    mkdirSync(testDir, { recursive: true });
+    mkdirSync(join(testDir, "http"), { recursive: true });
+    mkdirSync(join(testDir, "tftp"), { recursive: true });
+
+    const config = createTestConfig(testDir);
+    const result = createApp(config);
+    app = result.app;
+  });
+
+  afterEach(async () => {
+    await app.close();
+    rmSync(testDir, { recursive: true, force: true });
+  });
+
+  it("GET /asahi returns wrapper shell script", async () => {
+    const resp = await app.inject({ method: "GET", url: "/asahi" });
+    expect(resp.statusCode).toBe(200);
+    expect(resp.headers["content-type"]).toContain("text/x-shellscript");
+    expect(resp.body).toContain("#!/bin/bash");
+    expect(resp.body).toContain("installer_data.json");
+    expect(resp.body).toContain("192.168.8.1");
+    expect(resp.body).toContain("install.sh");
+  });
+
+  it("GET /asahi/installer_data.json returns valid config", async () => {
+    const resp = await app.inject({ method: "GET", url: "/asahi/installer_data.json" });
+    expect(resp.statusCode).toBe(200);
+    const data = JSON.parse(resp.body);
+
+    expect(data.os_list).toHaveLength(1);
+    const os = data.os_list[0];
+    expect(os.name).toContain("Fedora Asahi Lab");
+
+    // 3 partitions (fallback) or 4 (built: EFI + Boot + Root + Data)
+    expect(os.partitions.length).toBeGreaterThanOrEqual(3);
+    expect(os.partitions[0].type).toBe("EFI");
+    // Last partition should be the expanding Data partition
+    const lastPart = os.partitions[os.partitions.length - 1];
+    expect(lastPart.type).toBe("Linux");
+    expect(lastPart.expand).toBe(true);
+    // Root partition (second-to-last) should NOT expand
+    const rootPart = os.partitions[os.partitions.length - 2];
+    expect(rootPart.expand).toBe(false);
+    expect(rootPart.image).toBe("root.img");
+  });
+
+  it("GET /asahi/firstboot.sh returns parameterized script", async () => {
+    const resp = await app.inject({
+      method: "GET",
+      url: "/asahi/firstboot.sh?hostname=mac-studio&role=infra&mac=00:11:22:33:44:55",
+    });
+    expect(resp.statusCode).toBe(200);
+    expect(resp.body).toContain("#!/bin/bash");
+    expect(resp.body).toContain("mac-studio");
+    expect(resp.body).toContain("labvg");
+    expect(resp.body).toContain("rancher");  // infra gets rancher LV
+    expect(resp.body).toContain("longhorn"); // infra also gets longhorn
+    expect(resp.body).toContain("ssh-ed25519"); // SSH key injected
+  });
+
+  it("GET /asahi/firstboot.service returns systemd unit", async () => {
+    const resp = await app.inject({ method: "GET", url: "/asahi/firstboot.service" });
+    expect(resp.statusCode).toBe(200);
+    expect(resp.body).toContain("[Unit]");
+    expect(resp.body).toContain("lab-firstboot.sh");
+    expect(resp.body).toContain("ConditionPathExists=!/etc/lab-lvm-setup-done");
+  });
+});
+
+describe("renderFirstbootScript", () => {
+  const baseParams = {
+    hostname: "test-node",
+    serverIp: "10.0.0.1",
+    httpPort: 8080,
+    sshKeys: ["ssh-ed25519 AAAA... user@host"],
+    adminUser: "testadmin",
+    mac: "aa:bb:cc:dd:ee:ff",
+  };
+
+  it("generates valid bash with shebang", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script.startsWith("#!/bin/bash")).toBe(true);
+  });
+
+  it("includes LVM creation commands", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("pvcreate");
+    expect(script).toContain("vgcreate labvg");
+    expect(script).toContain("lvcreate");
+  });
+
+  it("uses correct LV sizes from kickstart layout", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("27648M");  // swap
+    expect(script).toContain("102400M"); // /var
+    expect(script).toContain("10240M");  // /var/log and /home
+    expect(script).toContain("20480M");  // /srv and /rancher
+  });
+
+  it("includes rancher LV for infra role", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("rancher");
+    expect(script).toContain("/var/lib/rancher");
+  });
+
+  it("includes longhorn for worker role", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script).toContain("longhorn");
+    expect(script).toContain("/var/lib/longhorn");
+    // Worker should NOT have rancher
+    expect(script).not.toContain("rancher");
+  });
+
+  it("includes longhorn for infra role", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("longhorn");
+    expect(script).toContain("/var/lib/longhorn");
+  });
+
+  it("vanilla role gets no role-specific LVs", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "vanilla" });
+    expect(script).not.toContain("rancher");
+    expect(script).not.toContain("longhorn");
+  });
+
+  it("handles reprovision (existing labvg)", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("reprovision detected");
+    expect(script).toContain("vgchange -ay labvg");
+    expect(script).toContain("mount_lv var /var");
+  });
+
+  it("injects SSH keys for admin user and root", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script).toContain("ssh-ed25519 AAAA...");
+    expect(script).toContain("testadmin");
+    expect(script).toContain("/root/.ssh/authorized_keys");
+  });
+
+  it("sets hostname", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script).toContain('CONF_HOSTNAME="test-node"');
+    expect(script).toContain("hostnamectl set-hostname");
+  });
+
+  it("includes bastion self-registration", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script).toContain("/api/register");
+    expect(script).toContain("aa:bb:cc:dd:ee:ff");
+    expect(script).toContain("test-node");
+  });
+
+  it("writes provisioning metadata", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "infra" });
+    expect(script).toContain("/etc/lab-provisioned");
+    expect(script).toContain("method=asahi-firstboot");
+  });
+
+  it("creates marker file to prevent re-run", () => {
+    const script = renderFirstbootScript({ ...baseParams, role: "worker" });
+    expect(script).toContain("/etc/lab-lvm-setup-done");
+    expect(script).toContain('touch "$MARKER"');
+  });
+});
+
+describe("renderFirstbootUnit", () => {
+  it("generates valid systemd unit", () => {
+    const unit = renderFirstbootUnit();
+    expect(unit).toContain("[Unit]");
+    expect(unit).toContain("[Service]");
+    expect(unit).toContain("[Install]");
+    expect(unit).toContain("Type=oneshot");
+    expect(unit).toContain("WantedBy=multi-user.target");
+  });
+
+  it("only runs when marker is missing", () => {
+    const unit = renderFirstbootUnit();
+    expect(unit).toContain("ConditionPathExists=!/etc/lab-lvm-setup-done");
+  });
+});

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/fixtures/ipxe-x86_64-golden.json

@@ -0,0 +1,8 @@
+{
+  "boot": "#!ipxe\n\necho\necho ============================================\necho   Lab PXE Bastion\necho   Contacting server for instructions...\necho ============================================\necho\n\nchain http://10.0.0.1:8080/dispatch?mac=${net0/mac}\n",
+  "discover": "#!ipxe\n\necho\necho =============================================\necho   Lab PXE Bastion - DISCOVERY MODE\necho   MAC: aa:bb:cc:dd:ee:ff\necho   Collecting hardware info...\necho =============================================\necho\n\nkernel http://10.0.0.1:8080/vmlinuz inst.ks=http://10.0.0.1:8080/discover.ks inst.stage2=https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os inst.text nomodeset\ninitrd http://10.0.0.1:8080/initrd.img\nboot\n",
+  "install": "#!ipxe\n\necho\necho =============================================\necho   Lab PXE Bastion - INSTALLING Fedora 43\necho   Target: worker-1\necho   MAC:    aa:bb:cc:dd:ee:ff\necho =============================================\necho\n\nkernel http://10.0.0.1:8080/vmlinuz inst.ks=http://10.0.0.1:8080/ks?mac=aa:bb:cc:dd:ee:ff inst.repo=https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os inst.text nomodeset\ninitrd http://10.0.0.1:8080/initrd.img\nboot\n",
+  "debug": "#!ipxe\n\necho\necho =============================================\necho   Lab PXE Bastion - DEBUG/RESCUE MODE\necho   Target: worker-1\necho   MAC:    aa:bb:cc:dd:ee:ff\necho =============================================\necho\n\nkernel http://10.0.0.1:8080/vmlinuz inst.rescue inst.text inst.sshd inst.ks=http://10.0.0.1:8080/debug.ks?mac=aa:bb:cc:dd:ee:ff inst.stage2=https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os\ninitrd http://10.0.0.1:8080/initrd.img\nboot\n",
+  "pxeBoot": "#!ipxe\n\necho\necho =============================================\necho   Lab PXE Bastion - PXE BOOT (debug)\necho   Target: worker-1\necho   MAC:    aa:bb:cc:dd:ee:ff\necho   Kernel+initrd from PXE, root from NVMe\necho =============================================\necho\n\nkernel http://10.0.0.1:8080/vmlinuz root=/dev/mapper/labvg-root ro rd.lvm.lv=labvg/root rd.lvm.lv=labvg/swap console=tty0\ninitrd http://10.0.0.1:8080/initrd.img\nboot\n",
+  "localBoot": "#!ipxe\n\necho\necho =============================================\necho   Lab PXE Bastion - worker-1\necho   Already installed, booting from local disk\necho =============================================\necho\nsleep 3\nexit 1\n"
+}

bastion/src/bastion/tests/install-guard.test.ts

@@ -0,0 +1,194 @@
+// Installs must never reach a machine running a vendor OS we cannot restore.
+//
+// This is the guardrail that stops someone reinstalling a DGX Spark at 2am. Rescue is
+// deliberately still allowed for the same machines -- that is the whole point.
+
+import { describe, it, expect, beforeEach, afterEach } from "vitest";
+import { mkdirSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import type { BastionConfig, BastionState, HardwareInfo } from "@lab/shared";
+import { classifyOnboard } from "@lab/shared";
+import { createApp } from "../src/server.js";
+import { checkInstallAllowed } from "../src/services/install-guard.js";
+import type { FastifyInstance } from "fastify";
+import type { StateManager } from "../src/services/state.js";
+
+// The real machines this exists to protect.
+const SPARK_2935 = "4c:bb:47:7f:29:35";
+const SPARK_3A1C = "48:21:0b:96:3a:1c";
+const ORDINARY = "aa:bb:cc:dd:ee:ff";
+
+function createTestConfig(testDir: string): BastionConfig {
+  return {
+    fedoraVersion: "43", arch: "x86_64", httpPort: 0,
+    timezone: "Europe/London", locale: "en_GB.UTF-8", bastionDir: testDir,
+    domain: "test.local", dhcpMode: "proxy", dhcpRangeStart: "", dhcpRangeEnd: "",
+    ubuntuVersion: "26.04", ubuntuMirror: "https://releases.ubuntu.com/26.04",
+    iface: "eth0", serverIp: "10.0.0.1", network: "10.0.0.0", gateway: "10.0.0.1",
+    sshKeys: [], adminUser: "testadmin", syslogPort: 15514,
+    skipDnsmasq: true, skipArtifacts: true,
+    fedoraMirror: "https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os",
+    tftpDir: join(testDir, "tftp"), httpDir: join(testDir, "http"),
+    stateFile: join(testDir, "state.json"),
+  };
+}
+
+function hardware(mac: string, over: Partial<HardwareInfo> = {}): HardwareInfo {
+  return {
+    mac, product: "TestBox", board: "TestBoard", serial: "SN1",
+    manufacturer: "TestCorp", cpu_model: "Test CPU", cpu_cores: 4, memory_gb: 16,
+    arch: "x86_64", disks: [], nics: [],
+    first_seen: new Date().toISOString(), last_seen: new Date().toISOString(),
+    ...over,
+  };
+}
+
+const emptyState = (): BastionState => ({
+  discovered: {}, install_queue: {}, installed: {}, debug: {},
+});
+
+describe("classifyOnboard", () => {
+  it("recognises a DGX Spark from its DMI identity", () => {
+    expect(classifyOnboard({
+      mac: ORDINARY, manufacturer: "NVIDIA", product: "NVIDIA DGX Spark", board: "GB10",
+    })).toEqual({ onboard: "ssh", vendor_os: "dgx-os" });
+  });
+
+  it("recognises the known Sparks even with no DMI recorded", () => {
+    // Neither Spark has hardware info in bastion state today. A DMI-only rule would
+    // fail open on exactly the machines this protects.
+    expect(classifyOnboard({ mac: SPARK_2935 }).onboard).toBe("ssh");
+    expect(classifyOnboard({ mac: SPARK_3A1C }).onboard).toBe("ssh");
+  });
+
+  it("treats ordinary hardware as PXE-installable", () => {
+    expect(classifyOnboard({
+      mac: ORDINARY, manufacturer: "Beelink", product: "SER9", board: "SER9",
+    })).toEqual({ onboard: "pxe" });
+  });
+
+  it("does not override an explicit classification already on the record", () => {
+    expect(classifyOnboard({
+      mac: SPARK_2935, onboard: "pxe",
+    })).toEqual({ onboard: "pxe" });
+  });
+});
+
+describe("checkInstallAllowed", () => {
+  it("refuses a DGX Spark and explains why", () => {
+    const state = emptyState();
+    state.installed[SPARK_2935] = {
+      hostname: "spark-2935", role: "worker", ip: "192.168.8.12",
+      installed_at: new Date().toISOString(), arch: "aarch64",
+    };
+
+    const result = checkInstallAllowed(state, SPARK_2935, "fedora-43");
+    expect(result.allowed).toBe(false);
+    if (result.allowed === false) {
+      expect(result.error).toContain("spark-2935");
+      expect(result.error).toContain("DGX OS");
+      expect(result.error).toContain("provision debug");
+    }
+  });
+
+  it("refuses a Spark that is only known by MAC", () => {
+    expect(checkInstallAllowed(emptyState(), SPARK_3A1C, "fedora-43").allowed).toBe(false);
+  });
+
+  it("allows an ordinary discovered machine", () => {
+    const state = emptyState();
+    state.discovered[ORDINARY] = hardware(ORDINARY);
+    expect(checkInstallAllowed(state, ORDINARY, "fedora-43").allowed).toBe(true);
+  });
+
+  it("allows Fedora on aarch64", () => {
+    const state = emptyState();
+    state.discovered[ORDINARY] = hardware(ORDINARY, { arch: "aarch64" });
+    expect(checkInstallAllowed(state, ORDINARY, "fedora-43").allowed).toBe(true);
+  });
+
+  it("refuses Ubuntu on aarch64 -- no netboot artifacts are published", () => {
+    const state = emptyState();
+    state.discovered[ORDINARY] = hardware(ORDINARY, { arch: "aarch64" });
+    const result = checkInstallAllowed(state, ORDINARY, "ubuntu-26.04");
+    expect(result.allowed).toBe(false);
+    if (result.allowed === false) {
+      expect(result.error).toContain("aarch64");
+    }
+  });
+
+  it("allows Ubuntu on x86_64", () => {
+    const state = emptyState();
+    state.discovered[ORDINARY] = hardware(ORDINARY, { arch: "x86_64" });
+    expect(checkInstallAllowed(state, ORDINARY, "ubuntu-26.04").allowed).toBe(true);
+  });
+});
+
+describe("install route enforces the guard", () => {
+  let testDir: string;
+  let app: FastifyInstance;
+  let state: StateManager;
+
+  beforeEach(() => {
+    testDir = join(tmpdir(), `bastion-guard-test-${Date.now()}-${Math.random().toString(36).slice(2)}`);
+    mkdirSync(join(testDir, "http"), { recursive: true });
+    mkdirSync(join(testDir, "tftp"), { recursive: true });
+    const result = createApp(createTestConfig(testDir));
+    app = result.app;
+    state = result.state;
+  });
+
+  afterEach(async () => {
+    await app.close();
+    rmSync(testDir, { recursive: true, force: true });
+  });
+
+  it("rejects POST /api/install for a Spark and queues nothing", async () => {
+    const res = await app.inject({
+      method: "POST",
+      url: "/api/install",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ mac: SPARK_2935, hostname: "spark-2935", role: "worker" }),
+    });
+
+    expect(res.statusCode).toBe(409);
+    expect(JSON.parse(res.body).error).toContain("Refusing to install");
+    expect(state.load().install_queue[SPARK_2935]).toBeUndefined();
+  });
+
+  it("still serves rescue to a Spark -- debug is never guarded", async () => {
+    state.update((s) => {
+      s.installed[SPARK_2935] = {
+        hostname: "spark-2935", role: "worker", ip: "192.168.8.12",
+        installed_at: new Date().toISOString(), arch: "aarch64",
+      };
+      s.debug[SPARK_2935] = { hostname: "spark-2935", queued_at: new Date().toISOString() };
+    });
+
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${SPARK_2935}` });
+    expect(res.statusCode).toBe(200);
+    expect(res.body).toContain("DEBUG/RESCUE MODE");
+    expect(res.body).toContain("/vmlinuz-aarch64");
+  });
+
+  it("a Spark that PXE boots unqueued gets discovery, never an install", async () => {
+    const res = await app.inject({ method: "GET", url: `/dispatch?mac=${SPARK_2935}&arch=arm64` });
+    expect(res.body).toContain("DISCOVERY MODE");
+    expect(res.body).not.toContain("INSTALLING");
+  });
+
+  it("still accepts an ordinary machine", async () => {
+    state.update((s) => { s.discovered[ORDINARY] = hardware(ORDINARY); });
+
+    const res = await app.inject({
+      method: "POST",
+      url: "/api/install",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ mac: ORDINARY, hostname: "worker-1", role: "worker" }),
+    });
+
+    expect(res.statusCode).toBe(200);
+    expect(state.load().install_queue[ORDINARY]).toBeDefined();
+  });
+});

bastion/src/bastion/tests/ipxe-x86-regression.test.ts

@@ -0,0 +1,89 @@
+// x86_64 iPXE output regression gate.
+//
+// The aarch64 PXE work must not change what an x86_64 machine is served. The golden
+// fixture was dumped from the templates as they stood before that work started, so
+// any diff here is a regression, not an improvement.
+//
+// The one deliberate exception is renderBootIpxe: its chain URL gained
+// `&arch=${buildarch}` so the dispatch endpoint can observe the client's
+// architecture at boot time. That single change is asserted explicitly below
+// rather than being allowed to slip through the byte-for-byte comparison.
+
+import { describe, it, expect } from "vitest";
+import { readFileSync } from "node:fs";
+import { join } from "node:path";
+import { fileURLToPath } from "node:url";
+import { dirname } from "node:path";
+import {
+  renderBootIpxe,
+  renderDiscoverIpxe,
+  renderInstallIpxe,
+  renderDebugIpxe,
+  renderPxeBootDebugIpxe,
+  renderLocalBootIpxe,
+} from "../src/templates/boot.ipxe.js";
+
+const here = dirname(fileURLToPath(import.meta.url));
+const golden = JSON.parse(
+  readFileSync(join(here, "fixtures", "ipxe-x86_64-golden.json"), "utf-8"),
+) as Record<string, string>;
+
+// Exactly the parameters used to dump the fixture.
+const serverIp = "10.0.0.1";
+const httpPort = 8080;
+const mac = "aa:bb:cc:dd:ee:ff";
+const hostname = "worker-1";
+const fedoraVersion = "43";
+const fedoraMirror =
+  "https://download.fedoraproject.org/pub/fedora/linux/releases/43/Everything/x86_64/os";
+
+// The x86_64 LVM layout the fixture was captured with. Before this work the values
+// were hardcoded in the template; they are now supplied by the caller from machine
+// state, so the fixture pins the rendering, not the defaults.
+const x86Root = {
+  rootDevice: "/dev/mapper/labvg-root",
+  rootArgs: "rd.lvm.lv=labvg/root rd.lvm.lv=labvg/swap",
+};
+
+describe("x86_64 iPXE output is unchanged", () => {
+  it("discover script is byte-identical", () => {
+    const rendered = renderDiscoverIpxe({
+      mac, serverIp, httpPort, fedoraMirror, arch: "x86_64",
+    });
+    expect(rendered).toBe(golden["discover"]);
+  });
+
+  it("install script is byte-identical", () => {
+    const rendered = renderInstallIpxe({
+      mac, hostname, serverIp, httpPort, fedoraVersion, fedoraMirror, arch: "x86_64",
+    });
+    expect(rendered).toBe(golden["install"]);
+  });
+
+  it("debug/rescue script is byte-identical", () => {
+    const rendered = renderDebugIpxe({
+      mac, hostname, serverIp, httpPort, fedoraMirror, arch: "x86_64",
+    });
+    expect(rendered).toBe(golden["debug"]);
+  });
+
+  it("--pxe-boot script is byte-identical when state carries the Fedora LVM layout", () => {
+    const rendered = renderPxeBootDebugIpxe({
+      mac, hostname, serverIp, httpPort, arch: "x86_64", ...x86Root,
+    });
+    expect(rendered).toBe(golden["pxeBoot"]);
+  });
+
+  it("local boot script is byte-identical", () => {
+    expect(renderLocalBootIpxe(hostname)).toBe(golden["localBoot"]);
+  });
+
+  it("boot.ipxe differs only by the &arch= chain parameter", () => {
+    const rendered = renderBootIpxe({ serverIp, httpPort });
+    // The sole intended difference.
+    expect(rendered).toBe(golden["boot"].replace(
+      "/dispatch?mac=${net0/mac}",
+      "/dispatch?mac=${net0/mac}&arch=${buildarch}",
+    ));
+  });
+});

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

@@ -206,10 +206,8 @@ describe("renderInstallKickstart", () => {
     }
   });
 
-  it("forwards system logs to serial console", () => {
+  it("does not include serial console (causes 30s boot timeout on hardware without UART)", () => {
     const ks = renderInstallKickstart(baseParams({ role: "vanilla" }));
-    expect(ks).toContain("serial-console.conf");
-    expect(ks).toContain("/dev/ttyS0");
-    expect(ks).toContain("rsyslog");
+    expect(ks).not.toContain("ttyS0");
   });
 });

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

@@ -94,8 +94,25 @@ export class LabdClient {
     return this.request("POST", "/api/machines/install", { body: opts });
   }
 
-  async debugMachine(mac: string): Promise<{ status: string; data?: { mac: string; hostname: string }; error?: string }> {
-    return this.request("POST", "/api/machines/debug", { body: { mac } });
+  async registerMachine(opts: {
+    mac: string; hostname: string; role?: string; ip?: string;
+  }): Promise<{ status: string; data?: unknown; error?: string }> {
+    return this.request("POST", "/api/machines/register", { 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 discoverMachine(data: {
+    mac: string; product?: string; board?: string; serial?: string;
+    manufacturer?: string; cpu_model?: string; cpu_cores?: number;
+    memory_gb?: number; arch?: string;
+    disks?: Array<{ name: string; size_gb: number; model: string }>;
+    nics?: Array<{ name: string; mac: string; state: string }>;
+    root_device?: string; root_args?: string;
+  }): Promise<{ status: string; error?: string }> {
+    return this.request("POST", "/api/machines/discover", { body: data });
   }
 
   async forgetMachine(mac: string): Promise<{ status: string }> {

bastion/src/cli/src/commands/app.ts

@@ -1,9 +1,10 @@
 // CLI command: labctl app k3s install/health <target>
 // Install or check k3s on a target machine via SSH.
 
-import { existsSync } from "node:fs";
+import { existsSync, writeFileSync, mkdirSync } from "node:fs";
 import { homedir } from "node:os";
 import { join } from "node:path";
+import { execSync } from "node:child_process";
 import type { Command } from "commander";
 import type { BastionState } from "@lab/shared";
 import { K3sModule, sshExec } from "@lab/modules";
@@ -69,7 +70,7 @@ export function registerAppCommand(program: Command): void {
     .command("install <target>")
     .description("Install k3s on a target machine (hostname, IP, or MAC)")
     .option("--role <role>", "k3s role: infra (server) or worker (agent)", "infra")
-    .option("--user <user>", "SSH user", "michal")
+    .option("--user <user>", "SSH user", "root")
     .option("--k3s-server <url>", "k3s server URL (required for worker role)")
     .option("--k3s-token <token>", "k3s join token (required for worker role)")
     .action(async (target: string, opts: {
@@ -163,7 +164,7 @@ export function registerAppCommand(program: Command): void {
   k3sCmd
     .command("health [target]")
     .description("Check k3s health (all hosts if no target given)")
-    .option("--user <user>", "SSH user", "michal")
+    .option("--user <user>", "SSH user", "root")
     .action(async (target: string | undefined, opts: { user: string }) => {
       const sshKey = findSshKey();
 
@@ -303,7 +304,7 @@ export function registerAppCommand(program: Command): void {
   k3sCmd
     .command("list")
     .description("List installed machines and their k3s status")
-    .option("--user <user>", "SSH user", "michal")
+    .option("--user <user>", "SSH user", "root")
     .action(async (opts: { user: string }) => {
       let state: BastionState;
       try {
@@ -400,4 +401,88 @@ export function registerAppCommand(program: Command): void {
         );
       }
     });
+
+  k3sCmd
+    .command("kubeconfig <target>")
+    .description("Fetch kubeconfig from a target and merge into ~/.kube/config")
+    .option("--user <user>", "SSH user", "root")
+    .option("--context <name>", "Context name (defaults to hostname)")
+    .option("--print", "Print kubeconfig to stdout instead of merging")
+    .action(async (target: string, opts: {
+      user: string;
+      context?: string;
+      print?: boolean;
+    }) => {
+      const state = await fetchState();
+      const resolved = resolveTarget(target, state);
+
+      if (!resolved) {
+        console.error(`Cannot resolve target: ${target}`);
+        console.error("Provide an IP address, hostname, or MAC of an installed machine.");
+        process.exit(1);
+      }
+
+      const sshKey = findSshKey();
+
+      // Fetch kubeconfig via SSH
+      let raw: string;
+      try {
+        const result = await sshExec(resolved.ip, opts.user, "cat /etc/rancher/k3s/k3s.yaml", {
+          ...(sshKey ? { keyPath: sshKey } : {}),
+          timeoutMs: 10_000,
+        });
+        raw = result.stdout;
+      } catch (err) {
+        console.error(`Failed to fetch kubeconfig: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+      }
+
+      const contextName = opts.context ?? resolved.hostname;
+
+      // Rewrite: replace 127.0.0.1 with actual IP, rename cluster/user/context
+      const rewritten = raw
+        .replace(/server:\s*https:\/\/127\.0\.0\.1:/, `server: https://${resolved.ip}:`)
+        .replace(/name:\s*default/g, `name: ${contextName}`)
+        .replace(/cluster:\s*default/g, `cluster: ${contextName}`)
+        .replace(/user:\s*default/g, `user: ${contextName}`)
+        .replace(/current-context:\s*default/, `current-context: ${contextName}`);
+
+      if (opts.print) {
+        process.stdout.write(rewritten);
+        return;
+      }
+
+      // Merge into ~/.kube/config using kubectl
+      const kubeDir = join(homedir(), ".kube");
+      mkdirSync(kubeDir, { recursive: true });
+      const mainConfig = join(kubeDir, "config");
+      const tmpFile = join(kubeDir, `.labctl-${contextName}.tmp`);
+
+      writeFileSync(tmpFile, rewritten, { mode: 0o600 });
+
+      try {
+        if (existsSync(mainConfig)) {
+          const merged = execSync(
+            `KUBECONFIG="${mainConfig}:${tmpFile}" kubectl config view --flatten`,
+            { encoding: "utf-8" },
+          );
+          writeFileSync(mainConfig, merged, { mode: 0o600 });
+        } else {
+          writeFileSync(mainConfig, rewritten, { mode: 0o600 });
+        }
+
+        // Set current context
+        execSync(`kubectl config use-context ${contextName}`, { stdio: "pipe" });
+
+        console.log(`Merged kubeconfig for ${contextName} (${resolved.ip})`);
+        console.log(`Context set to: ${contextName}`);
+        console.log(`\nSwitch contexts: kubectl config use-context <name>`);
+      } catch (err) {
+        console.error(`Failed to merge kubeconfig: ${err instanceof Error ? err.message : String(err)}`);
+        console.error(`Standalone config saved at: ${tmpFile}`);
+        process.exit(1);
+      } finally {
+        try { const { unlinkSync } = await import("node:fs"); unlinkSync(tmpFile); } catch { /* ignore */ }
+      }
+    });
 }

bastion/src/cli/src/commands/asahi.ts

@@ -0,0 +1,69 @@
+// CLI command: provision asahi
+// Prints the curl command to run on the Mac Studio (macOS) to install
+// Fedora Asahi Remix with lab LVM layout.
+
+import type { Command } from "commander";
+import { getLabdClient } from "../api/config.js";
+
+export function registerAsahiCommand(parent: Command): void {
+  parent
+    .command("asahi")
+    .description("Show instructions to provision an Apple Silicon Mac with Asahi Linux")
+    .action(async () => {
+      // Try to get bastion info to determine the correct URL
+      let bastionUrl = "";
+      try {
+        const bastions = await getLabdClient().getBastions();
+        const online = bastions.find(b => b.status === "online");
+        if (online) {
+          bastionUrl = `http://${online.serverIp}:8080`;
+        }
+      } catch { /* labd not reachable */ }
+
+      if (!bastionUrl) {
+        // Fall back to config
+        const { loadConfig } = await import("../config/index.js");
+        const config = loadConfig();
+        bastionUrl = config.labdUrl ?? "http://<bastion-ip>:8080";
+        // Convert labd URL to bastion URL (labd is on different port/host)
+        bastionUrl = bastionUrl.replace(/:\d+$/, ":8080");
+      }
+
+      const BOLD = "\x1b[1m";
+      const CYAN = "\x1b[36m";
+      const DIM = "\x1b[2m";
+      const RESET = "\x1b[0m";
+
+      console.log("");
+      console.log(`${BOLD}  Asahi Linux Provisioning${RESET}`);
+      console.log(`${DIM}  For Apple Silicon Macs (Mac Studio, MacBook, etc.)${RESET}`);
+      console.log("");
+      console.log(`  Run this command ${BOLD}on the Mac${RESET} (from macOS Terminal):`);
+      console.log("");
+      console.log(`    ${CYAN}${BOLD}curl ${bastionUrl}/asahi | sh${RESET}`);
+      console.log("");
+      console.log(`  The installer will ask a few interactive questions:`);
+      console.log(`    ${BOLD}1.${RESET} Action: press ${BOLD}r${RESET} to resize macOS`);
+      console.log(`    ${BOLD}2.${RESET} How much space for Linux: choose maximum`);
+      console.log(`    ${BOLD}3.${RESET} Confirm the resize operation`);
+      console.log(`    ${BOLD}4.${RESET} macOS password for firmware authentication`);
+      console.log("");
+      console.log(`  After that, everything is automatic:`);
+      console.log(`    - Asahi boot infrastructure (m1n1 + U-Boot)`);
+      console.log(`    - Fedora Asahi Remix root partition`);
+      console.log(`    - LVM data partition (remaining space)`);
+      console.log("");
+      console.log(`  On first boot, LVM volumes are created automatically:`);
+      console.log(`    ${DIM}labvg/swap (27GB), labvg/var (100GB), labvg/varlog (10GB),`);
+      console.log(`    labvg/home (10GB), labvg/srv (20GB), labvg/rancher (20GB),`);
+      console.log(`    labvg/longhorn (remaining space)${RESET}`);
+      console.log("");
+      console.log(`  After first boot, SSH in and run the firstboot script:`);
+      console.log(`    ${BOLD}ssh root@<ip> 'curl -sf ${bastionUrl}/asahi/firstboot.sh | bash'${RESET}`);
+      console.log("");
+      console.log(`  This sets up LVM, detects hostname/MAC, and self-registers.`);
+      console.log(`  Then install k3s:`);
+      console.log(`    ${BOLD}labctl app k3s install <hostname> --role infra${RESET}`);
+      console.log("");
+    });
+}

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

@@ -8,6 +8,7 @@ import { join } from "node:path";
 import { Command } from "commander";
 import type { BastionState } from "@lab/shared";
 import { getLabdClient } from "../api/config.js";
+import { ROOT_DEVICE_PROBE, parseRootProbe } from "../utils/hardware-probe.js";
 
 /** Resolve a target (hostname, MAC, or IP) to {mac, hostname, ip} from state. */
 function resolveTarget(
@@ -44,12 +45,61 @@ function resolveTarget(
   return null;
 }
 
+/** The local admin account to SSH as (root is not usable — it has no key here). */
+function sshUser(): string {
+  const adminUser = process.env["SUDO_USER"] ?? process.env["USER"] ?? "";
+  return adminUser === "root" ? "" : adminUser;
+}
+
+/** Common ssh arguments, ending with user@host. Null when there is no usable user. */
+function sshBaseArgs(ip: string): string[] | null {
+  const user = sshUser();
+  if (user === "") return null;
+
+  const sudoUser = process.env["SUDO_USER"];
+  const realHome = sudoUser !== undefined ? join("/home", sudoUser) : homedir();
+  const sshKey = ["id_ed25519", "id_rsa", "id_ecdsa"]
+    .map((name) => join(realHome, ".ssh", name))
+    .find((k) => existsSync(k));
+
+  return [
+    "-o", "StrictHostKeyChecking=no",
+    "-o", "UserKnownHostsFile=/dev/null",
+    "-o", "ConnectTimeout=10",
+    ...(sshKey !== undefined ? ["-i", sshKey] : []),
+    `${user}@${ip}`,
+  ];
+}
+
+/**
+ * Run a shell script on the target as root and return its stdout, or null.
+ *
+ * The script goes over stdin rather than the command line so it can contain quotes
+ * without a second round of shell escaping. `sudo -n` fails fast instead of hanging on
+ * a password prompt that would then eat the script.
+ */
+function sshCapture(ip: string, script: string): string | null {
+  const base = sshBaseArgs(ip);
+  if (base === null) return null;
+  try {
+    return execFileSync("ssh", [...base, "sudo", "-n", "sh", "-s"], {
+      input: script,
+      encoding: "utf-8",
+      stdio: ["pipe", "pipe", "pipe"],
+      timeout: 30_000,
+    });
+  } catch {
+    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) => {
+    .action(async (target: string, opts: { pxeBoot?: boolean }) => {
       const client = getLabdClient();
 
       // Resolve target from labd aggregated state
@@ -70,10 +120,35 @@ export function registerDebugCommand(parent: Command): void {
       }
 
       const { mac, hostname, ip } = resolved;
+
+      // --pxe-boot needs a root= for the installed system. If the machine is still
+      // reachable, observe it now rather than assuming a disk layout: a wrong root=
+      // leaves the machine unbootable. If it isn't reachable, dispatch falls back to
+      // rescue and the operator reports the real one from there.
+      if (opts.pxeBoot === true && ip !== "") {
+        const known = state.installed[mac]?.root_device ?? state.discovered[mac]?.root_device;
+        if (known === undefined || known === "") {
+          console.log(`No root device recorded for ${hostname}. Probing over SSH...`);
+          const probe = sshCapture(ip, ROOT_DEVICE_PROBE);
+          const root = probe === null ? {} : parseRootProbe(probe);
+          if (root.root_device !== undefined) {
+            console.log(`  root=${root.root_device}${root.root_args !== undefined ? ` ${root.root_args}` : ""}`);
+            try {
+              await client.discoverMachine({ mac, ...root });
+            } catch (err) {
+              console.error(`  Could not record it: ${err instanceof Error ? err.message : String(err)}`);
+            }
+          } else {
+            console.log("  Probe failed. Booting rescue instead; report the root device with:");
+            console.log("    curl http://<bastion>:8080/debug-setup.sh | bash");
+          }
+        }
+      }
+
       console.log(`Queuing debug mode for ${hostname} (${mac})...`);
 
       try {
-        const result = await client.debugMachine(mac);
+        const result = await client.debugMachine(mac, { pxeBoot: opts.pxeBoot === true });
         if (result.error) {
           console.error(`Failed: ${result.error}`);
           process.exit(1);
@@ -85,69 +160,54 @@ export function registerDebugCommand(parent: Command): void {
 
       // 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 "$PXE_ENTRY" && echo "PXE set as next boot" && sudo reboot; else echo "No PXE boot entry found, rebooting anyway..." && sudo reboot; fi',
-          ];
+        const base = sshBaseArgs(ip);
+        if (base !== null) {
+          console.log(`\nAttempting SSH reboot into PXE (${sshUser()}@${ip})...`);
 
           try {
-            execFileSync("ssh", sshArgs, { stdio: "inherit" });
+            execFileSync("ssh", [
+              ...base,
+              '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',
+            ], { 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
-  vgchange -ay labvg
-
-  # Mount root + other volumes
+  # Activate LVM and mount installed system
+  vgchange -ay
   mkdir -p /mnt/sysroot
-  mount /dev/labvg/root /mnt/sysroot
-  cat /mnt/sysroot/etc/fstab   # check what else to mount
-  mount /dev/labvg/var  /mnt/sysroot/var
-  mount /dev/labvg/home /mnt/sysroot/home
+  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 the installed system in a container
+  # Boot installed system in a container
   /mnt/sysroot/usr/bin/systemd-nspawn -D /mnt/sysroot --boot
 
-  # Or just chroot for quick fixes
+  # 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
-
-  # Check initramfs size
-  ls -lh /mnt/sysroot/boot/initramfs-*.img
-
-  # Rebuild initramfs without amdgpu
-  chroot /mnt/sysroot
-  echo 'omit_drivers+=" amdgpu "' > /etc/dracut.conf.d/omit-amdgpu.conf
-  dracut -f --regenerate-all
 `);
     });
 }

bastion/src/cli/src/commands/labcontroller.ts

@@ -38,7 +38,7 @@ export function registerLabcontrollerCommands(appCmd: Command): void {
   lcCmd
     .command("deploy <target>")
     .description("Deploy labcontroller stack to a k3s node")
-    .option("--user <user>", "SSH user", "michal")
+    .option("--user <user>", "SSH user", "root")
     .option("--crdb-replicas <n>", "CockroachDB replicas", "1")
     .action(async (target: string, opts: {
       user: string;
@@ -193,7 +193,7 @@ export function registerLabcontrollerCommands(appCmd: Command): void {
   lcCmd
     .command("status [target]")
     .description("Check labcontroller deployment status (all hosts if no target)")
-    .option("--user <user>", "SSH user", "michal")
+    .option("--user <user>", "SSH user", "root")
     .action(async (target: string | undefined, opts: { user: string }) => {
       const sshKey = findSshKey();
       const sshOpts = sshKey ? { keyPath: sshKey } : {};

bastion/src/cli/src/commands/list.ts

@@ -69,10 +69,10 @@ export function registerListCommand(parent: Command): void {
         const hostname = inst?.hostname ?? queued?.hostname ?? "-";
         const role = inst?.role ?? queued?.role ?? "-";
         const ip = inst?.ip ?? "-";
-        const cpu = hw?.cpu_model ?? "-";
-        const cores = hw?.cpu_cores != null ? String(hw.cpu_cores) : "-";
-        const ram = hw?.memory_gb != null ? `${hw.memory_gb}GB` : "-";
-        const product = hw?.product ?? "-";
+        const cpu = hw?.cpu_model ?? inst?.cpu_model ?? "-";
+        const cores = (hw?.cpu_cores ?? inst?.cpu_cores) != null ? String(hw?.cpu_cores ?? inst?.cpu_cores) : "-";
+        const ram = (hw?.memory_gb ?? inst?.memory_gb) != null ? `${hw?.memory_gb ?? inst?.memory_gb}GB` : "-";
+        const product = hw?.product ?? inst?.product ?? "-";
 
         const color = statusColor(status);
 

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:     ${data["role"]}`);
@@ -83,3 +89,64 @@ export function registerLogsCommand(parent: Command): void {
       }
     });
 }
+
+/** Follow logs by polling labd. */
+async function followLogs(
+  mac: string,
+  colors: { BOLD: string; GREEN: string; YELLOW: string; RED: string; DIM: string; RESET: string },
+): Promise<void> {
+  const { BOLD, GREEN, YELLOW, RED, DIM, RESET } = colors;
+  const client = getLabdClient();
+
+  console.log(`${DIM}Following logs for ${mac} (Ctrl+C to stop)${RESET}`);
+  console.log("");
+
+  let lastStageCount = 0;
+  let lastStatus = "";
+  let sawInstalling = false;
+
+  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;
+      }
+
+      if (status === "installing" || status === "queued") {
+        sawInstalling = true;
+      }
+
+      // 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;
+      }
+
+      // Only exit on "installed" if we actually saw the install happen
+      // (avoids exiting immediately when following a reprovision that hasn't started yet)
+      if (status === "installed" && sawInstalling) {
+        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/commands/recheck.ts

@@ -0,0 +1,100 @@
+// CLI command: provision recheck
+// SSH into all installed machines, collect hardware info, update bastion state.
+
+import type { Command } from "commander";
+import { sshExec } from "@lab/modules";
+import { getLabdClient } from "../api/config.js";
+import { ROOT_DEVICE_PROBE } from "../utils/hardware-probe.js";
+
+const BOLD = "\x1b[1m";
+const GREEN = "\x1b[0;32m";
+const RED = "\x1b[0;31m";
+const DIM = "\x1b[2m";
+const RESET = "\x1b[0m";
+
+const SSH_OPTS = { timeoutMs: 30_000 };
+
+// Shell script that collects hardware info as JSON.
+// Kept simple — no Python, pure shell + awk.
+const HW_COLLECT_SCRIPT = [
+  'P=$(cat /sys/class/dmi/id/product_name 2>/dev/null || echo unknown)',
+  'B=$(cat /sys/class/dmi/id/board_name 2>/dev/null || echo unknown)',
+  'S=$(cat /sys/class/dmi/id/product_serial 2>/dev/null || echo unknown)',
+  'M=$(cat /sys/class/dmi/id/sys_vendor 2>/dev/null || echo unknown)',
+  'C=$(grep -m1 "model name" /proc/cpuinfo 2>/dev/null | cut -d: -f2 | sed "s/^ //" || grep -m1 Model /proc/cpuinfo 2>/dev/null | cut -d: -f2 | sed "s/^ //" || echo unknown)',
+  'N=$(grep -c "^processor" /proc/cpuinfo 2>/dev/null || echo 0)',
+  'R=$(awk "/MemTotal/ {printf \\"%d\\", \\$2/1024/1024}" /proc/meminfo 2>/dev/null || echo 0)',
+  'A=$(uname -m)',
+  // Root filesystem, so --pxe-boot has a root= to use instead of assuming our layout.
+  ROOT_DEVICE_PROBE,
+  'printf \'{"product":"%s","board":"%s","serial":"%s","manufacturer":"%s","cpu_model":"%s","cpu_cores":%s,"memory_gb":%s,"arch":"%s","root_device":"%s","root_args":"%s"}\\n\' "$P" "$B" "$S" "$M" "$C" "$N" "$R" "$A" "$RD" "$RA"',
+].join("; ");
+
+export function registerRecheckCommand(parent: Command): void {
+  parent
+    .command("recheck")
+    .description("Refresh hardware info for all installed machines via SSH")
+    .option("--user <user>", "SSH user", "root")
+    .option("--target <hostname>", "Only recheck a specific machine (by hostname or MAC)")
+    .action(async (opts: { user: string; target?: string }) => {
+      const client = getLabdClient();
+      let state;
+      try {
+        state = await client.getMachines();
+      } catch (err) {
+        console.error(`Cannot reach labd: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+      }
+
+      // Build list of machines to check
+      const targets: Array<{ mac: string; hostname: string; ip: string }> = [];
+      for (const [mac, info] of Object.entries(state.installed)) {
+        if (!info.ip) continue;
+        if (opts.target && info.hostname !== opts.target && mac !== opts.target) continue;
+        targets.push({ mac, hostname: info.hostname, ip: info.ip });
+      }
+
+      if (targets.length === 0) {
+        console.log("No installed machines with IPs to check.");
+        return;
+      }
+
+      console.log(`\n${BOLD}Rechecking ${targets.length} machine(s)...${RESET}\n`);
+
+      let updated = 0;
+      let failed = 0;
+
+      for (const { mac, hostname, ip } of targets) {
+        process.stdout.write(`  ${hostname.padEnd(24)} ${DIM}(${ip})${RESET}  `);
+
+        try {
+          const t0 = Date.now();
+          const result = await sshExec(ip, opts.user, HW_COLLECT_SCRIPT, SSH_OPTS);
+          const elapsed = Date.now() - t0;
+          if (result.exitCode !== 0) {
+            console.log(`${RED}SSH failed (exit ${result.exitCode}, ${elapsed}ms)${RESET}`);
+            if (result.stderr) console.log(`    ${DIM}${result.stderr.substring(0, 200)}${RESET}`);
+            console.log(`${RED}SSH failed (exit ${result.exitCode})${RESET}`);
+            failed++;
+            continue;
+          }
+
+          const hwData = JSON.parse(result.stdout.trim());
+          await client.discoverMachine({ mac, ...hwData });
+          const cpu = hwData.cpu_model || "?";
+          const cores = hwData.cpu_cores || "?";
+          const mem = hwData.memory_gb || "?";
+          const root = typeof hwData.root_device === "string" && hwData.root_device !== ""
+            ? `, root=${hwData.root_device}`
+            : "";
+          console.log(`${GREEN}OK${RESET} ${DIM}${cpu}, ${cores} cores, ${mem}GB${root}${RESET}`);
+          updated++;
+        } catch (err) {
+          console.log(`${RED}FAIL${RESET} ${DIM}${err instanceof Error ? err.message : String(err)}${RESET}`);
+          failed++;
+        }
+      }
+
+      console.log(`\n${BOLD}Done:${RESET} ${updated} updated, ${failed} failed\n`);
+    });
+}

bastion/src/cli/src/commands/register.ts

@@ -0,0 +1,37 @@
+// CLI command: provision register
+// Register an already-installed machine that is missing from bastion state.
+
+import { Command, Option } from "commander";
+import { SUPPORTED_ROLES } from "@lab/shared";
+import { getLabdClient } from "../api/config.js";
+
+export function registerRegisterCommand(parent: Command): void {
+  parent
+    .command("register <mac> <hostname>")
+    .description("Register an already-installed machine (e.g. after state loss)")
+    .addOption(new Option("--role <role>", "Machine role").choices([...SUPPORTED_ROLES]).default("worker"))
+    .option("--ip <address>", "Machine IP address")
+    .action(async (mac: string, hostname: string, opts: {
+      role: string;
+      ip?: string;
+    }) => {
+      try {
+        const result = await getLabdClient().registerMachine({
+          mac,
+          hostname,
+          role: opts.role,
+          ...(opts.ip ? { ip: opts.ip } : {}),
+        });
+
+        if (result.error) {
+          console.error(`Failed: ${result.error}`);
+          process.exit(1);
+        }
+
+        console.log(`Registered ${mac} as ${hostname} (role=${opts.role}${opts.ip ? `, ip=${opts.ip}` : ""})`);
+      } catch (err) {
+        console.error(`Failed: ${err instanceof Error ? err.message : String(err)}`);
+        process.exit(1);
+      }
+    });
+}

bastion/src/cli/src/commands/reprovision.ts

@@ -144,6 +144,7 @@ export function registerReprovisionCommand(parent: Command): void {
 
       const sshArgs = [
         "-o", "StrictHostKeyChecking=no",
+        "-o", "UserKnownHostsFile=/dev/null",
         "-o", "ConnectTimeout=10",
         ...(sshKey !== undefined ? ["-i", sshKey] : []),
         `${effectiveUser}@${ip}`,

bastion/src/cli/src/commands/serve.ts

@@ -11,7 +11,7 @@ export function registerStartCommand(parent: Command): void {
     .command("start")
     .description("Start the bastion server (HTTP + dnsmasq PXE)")
     .option("--port <port>", "HTTP port", "8080")
-    .option("--dir <dir>", "Bastion data directory", "/tmp/lab-bastion")
+    .option("--dir <dir>", "Bastion data directory", process.env["BASTION_DIR"] ?? "/tmp/lab-bastion")
     .option("--domain <domain>", "Internal domain for hostnames", "ad.itaz.eu")
     .option("--dhcp-mode <mode>", "DHCP mode: proxy or full", "proxy")
     .option("--fedora <version>", "Fedora version", "43")

bastion/src/cli/src/commands/stop.ts

@@ -8,7 +8,7 @@ export function registerStopCommand(parent: Command): void {
   parent
     .command("stop")
     .description("Stop a running bastion server")
-    .option("--dir <dir>", "Bastion data directory", "/tmp/lab-bastion")
+    .option("--dir <dir>", "Bastion data directory", process.env["BASTION_DIR"] ?? "/tmp/lab-bastion")
     .action((opts: { dir: string }) => {
       const pidFile = `${opts.dir}/bastion.pid`;
 

bastion/src/cli/src/index.ts

@@ -2,7 +2,7 @@
 // CLI entry point for lab-bastion.
 // Commands:
 //   init bastion standalone start/stop/status
-//   provision list/install/reprovision/forget
+//   provision list/install/reprovision/forget/register
 
 import { fileURLToPath } from "node:url";
 import { Command, Option } from "commander";
@@ -16,8 +16,11 @@ 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 { registerRegisterCommand } from "./commands/register.js";
+import { registerAsahiCommand } from "./commands/asahi.js";
 import { registerLogsCommand } from "./commands/logs.js";
 import { registerMakeIsoCommand } from "./commands/makeiso.js";
+import { registerRecheckCommand } from "./commands/recheck.js";
 import { registerConfigCommand } from "./commands/config.js";
 import { registerLoginCommand } from "./commands/login.js";
 import { registerDoctorCommand } from "./commands/doctor.js";
@@ -98,8 +101,11 @@ export function createProgram(): Command {
   registerReprovisionCommand(provisionCmd);
   registerDebugCommand(provisionCmd);
   registerForgetCommand(provisionCmd);
+  registerRegisterCommand(provisionCmd);
+  registerAsahiCommand(provisionCmd);
   registerLogsCommand(provisionCmd);
   registerMakeIsoCommand(provisionCmd);
+  registerRecheckCommand(provisionCmd);
 
   // config list/get/set/path
   registerConfigCommand(program);

bastion/src/cli/src/utils/hardware-probe.ts

@@ -0,0 +1,59 @@
+// Shell snippets for observing a machine's hardware over SSH.
+//
+// Pure shell + awk, no Python: these run on whatever the target happens to be,
+// including a minimal rescue environment.
+
+/**
+ * Report the root filesystem and any dracut arguments needed to assemble it.
+ *
+ * Emits two lines:
+ *   ROOT_DEVICE=<device>
+ *   ROOT_ARGS=<args>
+ *
+ * Used by `--pxe-boot`, which boots the installed system with a kernel and initrd from
+ * the network. Getting root= wrong there leaves the machine unbootable, so this observes
+ * the machine rather than assuming our Fedora LVM layout.
+ *
+ * Device form is chosen for stability across reboots: LVM logical volumes keep their
+ * /dev/mapper path, anything else is reported by UUID, which survives device renumbering.
+ */
+export const ROOT_DEVICE_PROBE = [
+  'RD=$(findmnt -no SOURCE / 2>/dev/null | head -1)',
+  'RA=""',
+  'RT=$(lsblk -no TYPE "$RD" 2>/dev/null | head -1)',
+  'if [ "$RT" = "lvm" ]; then',
+  '  VGLV=$(lvs --noheadings -o vg_name,lv_name "$RD" 2>/dev/null | awk \'{print $1"/"$2}\')',
+  '  [ -n "$VGLV" ] && RA="rd.lvm.lv=$VGLV"',
+  // Swap must be assembled too or resume= stalls the boot waiting for it.
+  '  SW=$(awk \'NR>1 {print $1; exit}\' /proc/swaps 2>/dev/null)',
+  '  if [ -n "$SW" ] && [ "$(lsblk -no TYPE "$SW" 2>/dev/null | head -1)" = "lvm" ]; then',
+  '    SWVGLV=$(lvs --noheadings -o vg_name,lv_name "$SW" 2>/dev/null | awk \'{print $1"/"$2}\')',
+  '    [ -n "$SWVGLV" ] && [ "$SWVGLV" != "$VGLV" ] && RA="$RA rd.lvm.lv=$SWVGLV"',
+  '  fi',
+  'elif [ -n "$RD" ]; then',
+  '  U=$(findmnt -no UUID / 2>/dev/null | head -1)',
+  '  [ -n "$U" ] && RD="UUID=$U"',
+  'fi',
+  'printf \'ROOT_DEVICE=%s\\nROOT_ARGS=%s\\n\' "$RD" "$RA"',
+].join("; ");
+
+export interface RootInfo {
+  root_device?: string;
+  root_args?: string;
+}
+
+/** Parse the ROOT_DEVICE/ROOT_ARGS lines emitted by ROOT_DEVICE_PROBE. */
+export function parseRootProbe(stdout: string): RootInfo {
+  const out: RootInfo = {};
+  for (const line of stdout.split("\n")) {
+    const trimmed = line.trim();
+    if (trimmed.startsWith("ROOT_DEVICE=")) {
+      const v = trimmed.slice("ROOT_DEVICE=".length).trim();
+      if (v !== "") out.root_device = v;
+    } else if (trimmed.startsWith("ROOT_ARGS=")) {
+      const v = trimmed.slice("ROOT_ARGS=".length).trim();
+      if (v !== "") out.root_args = v;
+    }
+  }
+  return out;
+}

bastion/src/cli/tests/smoke-bastion.test.ts

@@ -137,7 +137,7 @@ describe("bastion smoke tests", () => {
 
     // Wait for the server to start (look for the banner)
     const startedAt = Date.now();
-    const maxWait = 10_000;
+    const maxWait = 15_000;
     while (Date.now() - startedAt < maxWait) {
       if (stdout.includes("Waiting for PXE boot requests")) break;
       await sleep(200);

bastion/src/core/package.json

@@ -0,0 +1,23 @@
+{
+  "name": "@lab/core",
+  "version": "0.1.0",
+  "private": true,
+  "type": "module",
+  "main": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "import": "./dist/index.js",
+      "types": "./dist/index.d.ts"
+    }
+  },
+  "scripts": {
+    "build": "tsc --build",
+    "clean": "rimraf dist",
+    "test": "vitest",
+    "test:run": "vitest run"
+  },
+  "dependencies": {
+    "@pulumi/pulumi": "^3.0.0"
+  }
+}

bastion/src/core/src/audit.ts

@@ -0,0 +1,75 @@
+// Audit event types for the labctl platform.
+// Every mutation is tracked with correlation IDs for causal chains.
+
+export type AuditEventKind =
+  | "resource_created"
+  | "resource_updated"
+  | "resource_deleted"
+  | "resource_state_change"
+  | "plan_generated"
+  | "apply_started"
+  | "apply_step"
+  | "apply_completed"
+  | "driver_translate"
+  | "driver_execute"
+  | "driver_error"
+  | "fleet_discovery"
+  | "fleet_classification"
+  | "fleet_approval"
+  | "fleet_auto_approve"
+  | "pipeline_started"
+  | "pipeline_step_started"
+  | "pipeline_step_completed"
+  | "pipeline_completed"
+  | "deploy_started"
+  | "deploy_completed"
+  | "deploy_failed"
+  | "drift_detected"
+  | "drift_corrected"
+  | "sync_triggered"
+  | "sync_completed"
+  | "auth_login"
+  | "auth_logout"
+  | "auth_bootstrap"
+  | "rbac_decision"
+  | "impersonation"
+  | "server_started"
+  | "controller_started"
+  | "agent_connected"
+  | "agent_disconnected"
+  | "bastion_registered";
+
+export type AuditSource =
+  | "cli"
+  | "labd"
+  | "agent"
+  | "driver"
+  | "fleet-controller"
+  | "sync-controller";
+
+export type AuditResult = "success" | "failure" | "denied" | "skipped";
+
+export interface AuditEvent {
+  id: string;
+  timestamp: Date;
+  eventKind: AuditEventKind;
+  source: AuditSource;
+  verified: boolean;
+
+  userId?: string;
+  userName?: string;
+  sessionId?: string;
+  environmentName?: string;
+  accountName?: string;
+
+  resourceKind?: string;
+  resourceName?: string;
+
+  correlationId: string;
+  parentEventId?: string;
+
+  details: Record<string, unknown>;
+  result: AuditResult;
+  error?: string;
+  durationMs?: number;
+}

bastion/src/core/src/auth.ts

@@ -0,0 +1,50 @@
+// Auth types for the labctl platform.
+// Bearer token auth for CLI/SDK. mTLS stays for agent/bastion.
+
+export type UserRole = "USER" | "ADMIN";
+
+export interface User {
+  id: string;
+  email: string;
+  name?: string;
+  role: UserRole;
+  createdAt: Date;
+}
+
+export interface Session {
+  id: string;
+  userId: string;
+  token: string;
+  expiresAt: Date;
+  createdAt: Date;
+}
+
+export interface Group {
+  id: string;
+  name: string;
+  description?: string;
+}
+
+export type SubjectKind = "User" | "Group" | "ServiceAccount";
+
+export interface RoleBinding {
+  role: "view" | "edit" | "create" | "delete" | "run" | "admin";
+  resource: string;
+  name?: string;
+  environment?: string;
+  action?: string;
+}
+
+export interface RbacSubject {
+  kind: SubjectKind;
+  name: string;
+}
+
+export interface RbacDefinition {
+  id: string;
+  name: string;
+  subjects: RbacSubject[];
+  roleBindings: RoleBinding[];
+  createdAt: Date;
+  updatedAt: Date;
+}

bastion/src/core/src/environment.ts

@@ -0,0 +1,24 @@
+// Environment and Account types.
+// An Environment is a logical boundary (production, staging, dev).
+// An Account is a configured driver instance with credentials.
+
+export interface Environment {
+  id: string;
+  name: string;
+  status: "active" | "archived";
+  createdAt: Date;
+}
+
+export interface Account {
+  id: string;
+  name: string;
+  driver: string;
+  config: Record<string, unknown>;
+  createdAt: Date;
+}
+
+export interface Binding {
+  id: string;
+  environmentId: string;
+  accountId: string;
+}

bastion/src/core/src/index.ts

@@ -0,0 +1,9 @@
+// @lab/core — foundation types for the labctl platform.
+// Phase 1 stub: resource types, auth types, audit types, Output<T>.
+// Phase 5 adds: CompositeResource, evaluator integration, full SDK.
+
+export * from "./resource.js";
+export * from "./environment.js";
+export * from "./audit.js";
+export * from "./auth.js";
+export { Output, output, all, interpolate, secret } from "./output.js";

bastion/src/core/src/output.ts

@@ -0,0 +1,5 @@
+// Re-export Pulumi's Output<T> type for use across the platform.
+// Cloud drivers use this for future values (endpoints, IPs, kubeconfigs).
+// Phase 1: type re-export only. Phase 5 adds full evaluator integration.
+
+export { Output, output, all, interpolate, secret } from "@pulumi/pulumi";

bastion/src/core/src/resource.ts

@@ -0,0 +1,83 @@
+// Core resource types for the labctl platform.
+// Every managed thing (Server, Database, App, Cluster) is a Resource.
+
+export type ResourceOrigin = "file" | "cli" | "fleet" | "imported";
+export type ResourceManagedBy = "gitops" | "manual" | "auto";
+
+export type ResourceStatus =
+  | "pending"
+  | "creating"
+  | "ready"
+  | "updating"
+  | "deleting"
+  | "error"
+  | "unknown";
+
+export interface ResourceMetadata {
+  kind: string;
+  name: string;
+  environmentId: string;
+  accountId: string;
+  origin: ResourceOrigin;
+  managedBy: ResourceManagedBy;
+  sourceRef?: string;
+}
+
+export interface ResourceState {
+  status: ResourceStatus;
+  message?: string;
+  lastReconciled?: Date;
+  platformRef?: string;
+}
+
+export interface Resource<TSpec = Record<string, unknown>> {
+  id: string;
+  metadata: ResourceMetadata;
+  desiredSpec: TSpec;
+  actualSpec?: TSpec;
+  state: ResourceState;
+  createdAt: Date;
+  updatedAt: Date;
+}
+
+// Well-known resource kinds. Drivers register additional kinds.
+export const RESOURCE_KINDS = {
+  SERVER: "server",
+  DATABASE: "database",
+  CACHE: "cache",
+  CLUSTER: "cluster",
+  APP: "app",
+  SERVICE: "service",
+  CRONJOB: "cronjob",
+  NETWORK: "network",
+  LOADBALANCER: "loadbalancer",
+  DNSZONE: "dnszone",
+  CERTIFICATE: "certificate",
+  OBJECTSTORE: "objectstore",
+  QUEUE: "queue",
+  SECRET: "secret",
+  FLEET: "fleet",
+} as const;
+
+export type ResourceKind = (typeof RESOURCE_KINDS)[keyof typeof RESOURCE_KINDS];
+
+// Resource aliases for CLI (kubectl-style shortnames)
+export const RESOURCE_ALIASES: Record<string, string> = {
+  srv: "server",
+  db: "database",
+  cl: "cluster",
+  svc: "service",
+  cj: "cronjob",
+  lb: "loadbalancer",
+  dns: "dnszone",
+  cert: "certificate",
+  os: "objectstore",
+  mq: "queue",
+  sec: "secret",
+  fl: "fleet",
+};
+
+export function resolveResourceKind(input: string): string {
+  const lower = input.toLowerCase();
+  return RESOURCE_ALIASES[lower] ?? lower;
+}

bastion/src/core/tsconfig.json

@@ -0,0 +1,8 @@
+{
+  "extends": "../../tsconfig.base.json",
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "dist"
+  },
+  "include": ["src/**/*.ts"]
+}

bastion/src/labd/package.json

@@ -26,8 +26,10 @@
   "dependencies": {
     "@fastify/rate-limit": "^10.3.0",
     "@fastify/websocket": "^11.0.2",
+    "@lab/core": "workspace:^",
     "@lab/shared": "workspace:*",
     "@prisma/client": "^6.9.0",
+    "bcryptjs": "^3.0.3",
     "fastify": "^5.3.3",
     "winston": "^3.17.0",
     "ws": "^8.19.0",
@@ -37,6 +39,7 @@
     "seed": "tsx prisma/seed.ts"
   },
   "devDependencies": {
+    "@types/bcryptjs": "^3.0.0",
     "@types/node": "^22.14.1",
     "@types/ws": "^8.18.1",
     "prisma": "^6.9.0",

bastion/src/labd/prisma/schema.prisma

@@ -7,23 +7,241 @@ datasource db {
   url      = env("DATABASE_URL")
 }
 
+// ── Auth (mcpctl pattern: email/password + bearer token sessions) ──
+
+model User {
+  id        String   @id @default(cuid())
+  email     String   @unique
+  password  String   // bcrypt
+  name      String?
+  role      UserRole @default(USER)
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+
+  sessions  Session[]
+  auditLogs AuditEvent[]
+  groups    GroupMember[]
+}
+
+enum UserRole {
+  USER
+  ADMIN
+}
+
+model Session {
+  id        String   @id @default(cuid())
+  userId    String
+  user      User     @relation(fields: [userId], references: [id], onDelete: Cascade)
+  token     String   @unique
+  expiresAt DateTime
+  createdAt DateTime @default(now())
+
+  @@index([userId])
+  @@index([token])
+}
+
+model Group {
+  id          String        @id @default(cuid())
+  name        String        @unique
+  description String?
+  createdAt   DateTime      @default(now())
+  members     GroupMember[]
+}
+
+model GroupMember {
+  id      String @id @default(cuid())
+  groupId String
+  group   Group  @relation(fields: [groupId], references: [id], onDelete: Cascade)
+  userId  String
+  user    User   @relation(fields: [userId], references: [id], onDelete: Cascade)
+
+  @@unique([groupId, userId])
+}
+
+model ServiceAccount {
+  id        String   @id @default(cuid())
+  name      String   @unique
+  token     String   @unique
+  createdAt DateTime @default(now())
+}
+
+// ── RBAC (mcpctl pattern: named definitions with JSON subjects/bindings) ──
+
+model RbacDefinition {
+  id           String   @id @default(cuid())
+  name         String   @unique
+  subjects     Json     // [{kind: "User"|"Group"|"ServiceAccount", name: string}]
+  roleBindings Json     // [{role, resource, name?, environment?, action?}]
+  createdAt    DateTime @default(now())
+  updatedAt    DateTime @updatedAt
+}
+
+// ── Audit (mcpctl pattern: fire-and-forget with correlation IDs) ──
+
+model AuditEvent {
+  id              String   @id @default(cuid())
+  timestamp       DateTime @default(now())
+  eventKind       String
+  source          String   // cli | labd | agent | driver | fleet-controller | sync-controller
+  verified        Boolean  @default(false)
+
+  userId          String?
+  user            User?    @relation(fields: [userId], references: [id])
+  userName        String?
+  sessionId       String?
+  environmentName String?
+  accountName     String?
+
+  resourceKind    String?
+  resourceName    String?
+
+  correlationId   String
+  parentEventId   String?
+
+  details         Json     @default("{}")
+  result          String   // success | failure | denied | skipped
+  error           String?
+  durationMs      Int?
+
+  @@index([correlationId])
+  @@index([eventKind, timestamp])
+  @@index([environmentName, timestamp])
+  @@index([resourceKind, resourceName])
+  @@index([userId, timestamp])
+}
+
+// ── Core infrastructure ──
+
+model Environment {
+  id        String   @id @default(cuid())
+  name      String   @unique
+  status    String   @default("active") // active | archived
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+
+  bindings  Binding[]
+  resources Resource[]
+}
+
+model Account {
+  id        String   @id @default(cuid())
+  name      String   @unique
+  driver    String   // baremetal-pxe | aws | gcp | kubernetes | ovh
+  config    Json     @default("{}")
+  // Credentials stored in Infisical, referenced by secretPath
+  secretPath String?
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+
+  bindings  Binding[]
+  resources Resource[]
+}
+
+model Binding {
+  id            String      @id @default(cuid())
+  environmentId String
+  environment   Environment @relation(fields: [environmentId], references: [id], onDelete: Cascade)
+  accountId     String
+  account       Account     @relation(fields: [accountId], references: [id], onDelete: Cascade)
+
+  @@unique([environmentId, accountId])
+}
+
+model Resource {
+  id             String       @id @default(cuid())
+  kind           String
+  name           String
+  environmentId  String
+  environment    Environment  @relation(fields: [environmentId], references: [id])
+  accountId      String
+  account        Account      @relation(fields: [accountId], references: [id])
+  origin         String       @default("cli")    // file | cli | fleet | imported
+  managedBy      String       @default("manual")  // gitops | manual | auto
+  sourceRef      String?
+  desiredSpec    Json         @default("{}")
+  actualSpec     Json?
+  platformRef    String?
+  status         String       @default("pending") // pending | creating | ready | updating | deleting | error
+  statusMessage  String?
+  lastReconciled DateTime?
+  createdAt      DateTime     @default(now())
+  updatedAt      DateTime     @updatedAt
+
+  @@unique([kind, name, environmentId])
+  @@index([environmentId])
+  @@index([accountId])
+  @@index([kind, status])
+}
+
+model Secret {
+  id        String   @id @default(cuid())
+  name      String   @unique
+  // Encrypted data — application-layer encryption as fallback if Infisical unavailable
+  data      Json     @default("{}")
+  version   Int      @default(1)
+  createdAt DateTime @default(now())
+  updatedAt DateTime @updatedAt
+}
+
+// ── Fleet ──
+
+model Fleet {
+  id               String        @id @default(cuid())
+  name             String
+  environmentId    String
+  accountId        String
+  selector         Json          // fact-matching rules
+  onboardPipeline  Json          // step definitions
+  offboardPipeline Json?
+  approvalConfig   Json?
+  status           String        @default("active")
+  createdAt        DateTime      @default(now())
+  updatedAt        DateTime      @updatedAt
+
+  members          FleetMember[]
+}
+
+model FleetMember {
+  id       String   @id @default(cuid())
+  fleetId  String
+  fleet    Fleet    @relation(fields: [fleetId], references: [id], onDelete: Cascade)
+  serverId String
+  status   String   // discovered | pending | onboarding | active | offboarding | removed
+  joinedAt DateTime @default(now())
+
+  @@index([fleetId])
+}
+
+// ── Git sources (for sync controller) ──
+
+model GitSource {
+  id       String    @id @default(cuid())
+  name     String    @unique
+  repo     String
+  branch   String    @default("main")
+  path     String    @default("environments/")
+  lastSync DateTime?
+  createdAt DateTime @default(now())
+}
+
+// ── Existing v1.0 models (kept for bastion/agent compatibility) ──
+
 model Server {
-  id            String   @id @default(uuid())
-  hostname      String   @unique
-  mac           String?  @unique
-  cloud         String   @default("baremetal")
-  environment   String   @default("default")
-  role          String   @default("worker")
-  labels        Json     @default("{}")
+  id            String    @id @default(uuid())
+  hostname      String    @unique
+  mac           String?   @unique
+  cloud         String    @default("baremetal")
+  environment   String    @default("default")
+  role          String    @default("worker")
+  labels        Json      @default("{}")
   ip            String?
   agentVersion  String?
-  status        String   @default("unknown") // unknown, online, offline, provisioning
+  status        String    @default("unknown")
   lastHeartbeat DateTime?
-  createdAt     DateTime @default(now())
-  updatedAt     DateTime @updatedAt
+  createdAt     DateTime  @default(now())
+  updatedAt     DateTime  @updatedAt
 
-  agent         Agent?
-  auditLogs     AuditLog[]
+  agent     Agent?
 }
 
 model Agent {
@@ -33,112 +251,29 @@ model Agent {
   certificatePem String?
   enrolledAt     DateTime @default(now())
   lastSeen       DateTime?
+  facts          Json?    // hardware facts reported by agent
 
   @@index([serverId])
 }
 
-model User {
-  id              String   @id @default(uuid())
-  username        String   @unique
-  displayName     String?
-  certFingerprint String?  @unique
-  createdAt       DateTime @default(now())
-  updatedAt       DateTime @updatedAt
-
-  roleBindings UserRole[]
-  auditLogs    AuditLog[]
-}
-
-model Role {
-  id          String   @id @default(uuid())
-  name        String   @unique
-  description String?
-  createdAt   DateTime @default(now())
-
-  permissions  Permission[]
-  userBindings UserRole[]
-}
-
-model Permission {
-  id          String @id @default(uuid())
-  roleId      String
-  role        Role   @relation(fields: [roleId], references: [id], onDelete: Cascade)
-  type        String @default("allow") // allow or deny
-  action      String // read, exec, apply, destroy, manage, admin, kubectl, *
-  cloud       String @default("*")
-  environment String @default("*")
-  server      String @default("*")
-
-  @@index([roleId])
-}
-
-model UserRole {
-  id     String @id @default(uuid())
-  userId String
-  user   User   @relation(fields: [userId], references: [id], onDelete: Cascade)
-  roleId String
-  role   Role   @relation(fields: [roleId], references: [id], onDelete: Cascade)
-
-  @@unique([userId, roleId])
-  @@index([userId])
-  @@index([roleId])
-}
-
 model JoinToken {
   id        String    @id @default(uuid())
   token     String    @unique
-  type      String    @default("one-time") // one-time or reusable
+  type      String    @default("one-time")
   label     String?
-  usedBy    String? // server hostname that used it
+  usedBy    String?
   usedAt    DateTime?
   revokedAt DateTime?
   createdAt DateTime  @default(now())
   expiresAt DateTime?
 }
 
-model AuditLog {
-  id           String   @id @default(uuid())
-  userId       String?
-  user         User?    @relation(fields: [userId], references: [id])
-  serverId     String?
-  server       Server?  @relation(fields: [serverId], references: [id])
-  sessionId    String?
-  action       String // exec, kubectl, apply, login, rbac-denied, etc.
-  resourceType String?  // server, cluster, role, app, etc.
-  resourceName String?
-  args         String? // sanitized command args
-  result       String   @default("success") // success, denied, error
-  durationMs   Int?
-  sourceIp     String?
-  timestamp    DateTime @default(now())
-
-  @@index([userId])
-  @@index([serverId])
-  @@index([sessionId])
-  @@index([timestamp])
-  @@index([action])
-}
-
-model PulumiRun {
-  id          String    @id @default(uuid())
-  userId      String
-  stackName   String
-  action      String // up, preview, destroy
-  status      String    @default("pending") // pending, running, succeeded, failed
-  output      String?
-  startedAt   DateTime  @default(now())
-  completedAt DateTime?
-
-  @@index([userId])
-  @@index([stackName])
-}
-
 model Bastion {
   id            String    @id @default(uuid())
   hostname      String    @unique
   network       String
   serverIp      String
-  status        String    @default("offline") // online, offline
+  status        String    @default("offline")
   lastHeartbeat DateTime?
   createdAt     DateTime  @default(now())
   updatedAt     DateTime  @updatedAt
@@ -149,7 +284,7 @@ model Cluster {
   name          String   @unique
   cloud         String   @default("baremetal")
   environment   String   @default("default")
-  kubeconfigEnc String? // encrypted kubeconfig
+  kubeconfigEnc String?
   labels        Json     @default("{}")
   createdAt     DateTime @default(now())
   updatedAt     DateTime @updatedAt

bastion/src/labd/src/middleware/bearer-auth.ts

@@ -0,0 +1,65 @@
+// Bearer token auth middleware for Fastify.
+// Validates Authorization header, resolves user identity, attaches to request.
+
+import type { FastifyRequest, FastifyReply } from "fastify";
+import type { AuthService } from "../services/auth.js";
+
+declare module "fastify" {
+  interface FastifyRequest {
+    userId?: string;
+    userEmail?: string;
+    userRole?: string;
+  }
+}
+
+// Paths that don't require authentication
+const PUBLIC_PATHS = new Set([
+  "/health",
+  "/api/auth/login",
+  "/ws/bastion",
+  "/ws/agent",
+  "/api/auth/enroll",
+]);
+
+export function createBearerAuthMiddleware(authService: AuthService) {
+  return async function bearerAuth(
+    request: FastifyRequest,
+    reply: FastifyReply,
+  ): Promise<void> {
+    // Skip auth for public paths
+    if (PUBLIC_PATHS.has(request.url.split("?")[0] ?? "")) {
+      return;
+    }
+
+    // Skip auth for WebSocket upgrade requests (handled by their own auth)
+    if (request.headers.upgrade === "websocket") {
+      return;
+    }
+
+    const authHeader = request.headers.authorization;
+    if (!authHeader) {
+      void reply.code(401).send({ error: "Authorization header required" });
+      return;
+    }
+
+    if (!authHeader.startsWith("Bearer ")) {
+      void reply.code(401).send({ error: "Invalid authorization format, expected: Bearer <token>" });
+      return;
+    }
+
+    const token = authHeader.slice(7);
+    if (token.length === 0) {
+      void reply.code(401).send({ error: "Empty bearer token" });
+      return;
+    }
+
+    try {
+      const identity = await authService.validateToken(token);
+      request.userId = identity.userId;
+      request.userEmail = identity.email;
+      request.userRole = identity.role;
+    } catch {
+      void reply.code(401).send({ error: "Invalid or expired token. Run: labctl login" });
+    }
+  };
+}

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

@@ -84,7 +84,6 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
   app.get("/api/machines", async () => {
     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;
@@ -93,9 +92,49 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
       for (const s of dbServers) {
         if (!s.mac) continue;
         const mac = s.mac.toLowerCase();
-        // Only add from DB if not already in live state
+
+        // DB knows this machine has been installed at some point if it has a real
+        // hostname+role (not just product-name-as-hostname and role="unknown").
+        // Status alone is unreliable: a rediscovery can re-set it without erasing the
+        // install identity. If the bastion restarted and lost its installed map, the
+        // machine will only show up in live.discovered — promote it here so the CLI
+        // still sees hostname/role/IP.
+        const dbKnowsInstalled =
+          s.role !== "unknown" && s.role !== "" &&
+          s.hostname !== "" && s.hostname !== s.mac;
+
+        if (dbKnowsInstalled && !(mac in live.installed) && !(mac in live.install_queue)) {
+          const hw = live.discovered[mac];
+          live.installed[mac] = {
+            hostname: s.hostname,
+            role: s.role,
+            ip: s.ip ?? "",
+            installed_at: "",
+            bastionId: hw?.bastionId ?? "db",
+            ...(hw ? {
+              product: hw.product,
+              manufacturer: hw.manufacturer,
+              cpu_model: hw.cpu_model,
+              cpu_cores: hw.cpu_cores,
+              memory_gb: hw.memory_gb,
+              arch: hw.arch,
+            } : {}),
+          };
+          delete live.discovered[mac];
+          continue;
+        }
+
+        // Unknown-to-live MAC: fall back to whatever the DB says.
         if (!(mac in live.discovered) && !(mac in live.install_queue) && !(mac in live.installed)) {
-          if (s.status === "discovered") {
+          if (s.status === "online" || s.status === "offline") {
+            live.installed[mac] = {
+              hostname: s.hostname,
+              role: s.role,
+              ip: s.ip ?? "",
+              installed_at: "",
+              bastionId: "db",
+            };
+          } else {
             live.discovered[mac] = {
               mac,
               product: String(s.labels?.product ?? "unknown"),
@@ -112,14 +151,6 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
               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",
-            };
           }
         }
       }
@@ -151,7 +182,7 @@ 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) {
@@ -164,7 +195,44 @@ 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) {
+      return reply.code(500).send({ error: err instanceof Error ? err.message : String(err) });
+    }
+  });
+
+  // Register an already-installed machine — route to correct bastion (or single bastion)
+  app.post<{
+    Body: { mac?: string; hostname?: string; role?: string; ip?: string };
+  }>("/api/machines/register", async (request, reply) => {
+    const { mac, hostname, role, ip } = request.body ?? {};
+    if (!mac || !hostname) {
+      return reply.code(400).send({ error: "mac and hostname are required" });
+    }
+
+    const normalized = mac.toLowerCase().replace(/-/g, ":");
+
+    // Find bastion that knows this MAC, or use single connected bastion
+    const bastion = bastionRegistry.findBastionByMac(normalized);
+    const target = bastion ?? (bastionRegistry.getAll().length === 1 ? bastionRegistry.getAll()[0] : null);
+
+    if (!target) {
+      const all = bastionRegistry.getAll();
+      if (all.length === 0) {
+        return reply.code(503).send({ error: "No bastions connected" });
+      }
+      return reply.code(404).send({ error: `MAC ${normalized} not found on any bastion and multiple bastions connected` });
+    }
+
+    try {
+      const result = await sendCommand(target.bastionId, {
+        type: "command-register",
+        mac: normalized,
+        hostname,
+        role: role ?? "worker",
+        ip: ip ?? "",
       });
       return reply.code(result.status === "ok" ? 200 : 500).send(result);
     } catch (err) {
@@ -174,9 +242,10 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
 
   // Queue debug/rescue mode — route to correct bastion by MAC
   app.post<{
-    Body: { mac?: string };
+    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" });
     }
@@ -189,7 +258,7 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
       }
       if (all.length === 1) {
         try {
-          const result = await sendCommand(all[0]!.bastionId, { type: "command-debug", mac });
+          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) });
@@ -199,7 +268,7 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     }
 
     try {
-      const result = await sendCommand(bastion.bastionId, { type: "command-debug", mac });
+      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) });
@@ -222,6 +291,38 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     }
   });
 
+  // Update hardware info (discovery data) for a machine
+  app.post<{
+    Body: {
+      mac?: string; product?: string; board?: string; serial?: string;
+      manufacturer?: string; cpu_model?: string; cpu_cores?: number;
+      memory_gb?: number; arch?: string;
+      disks?: Array<{ name: string; size_gb: number; model: string }>;
+      nics?: Array<{ name: string; mac: string; state: string }>;
+      root_device?: string; root_args?: string;
+    };
+  }>("/api/machines/discover", async (request, reply) => {
+    const data = request.body ?? {};
+    const mac = (data.mac ?? "").toLowerCase().replace(/-/g, ":");
+    if (!mac) {
+      return reply.code(400).send({ error: "mac is required" });
+    }
+
+    const bastion = bastionRegistry.findBastionByMac(mac);
+    const target = bastion ?? (bastionRegistry.getAll().length === 1 ? bastionRegistry.getAll()[0] : null);
+
+    if (!target) {
+      return reply.code(503).send({ error: "No bastion found for this MAC" });
+    }
+
+    try {
+      const result = await sendCommand(target.bastionId, { type: "command-discover", ...data, mac });
+      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) });
+    }
+  });
+
   // Update role
   app.post<{
     Body: { mac?: string; role?: string };
@@ -256,17 +357,7 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
     const queued = bastion.state.install_queue[mac];
     const installed = bastion.state.installed[mac];
 
-    if (installed) {
-      return {
-        mac,
-        hostname: installed.hostname,
-        status: "installed",
-        role: installed.role,
-        ip: installed.ip,
-        installed_at: installed.installed_at,
-      };
-    }
-
+    // Active install takes priority over old installed state (reprovision case)
     if (queued) {
       return {
         mac,
@@ -281,6 +372,17 @@ export function registerBastionRoutes(app: FastifyInstance, db: DbClient): void
       };
     }
 
+    if (installed) {
+      return {
+        mac,
+        hostname: installed.hostname,
+        status: "installed",
+        role: installed.role,
+        ip: installed.ip,
+        installed_at: installed.installed_at,
+      };
+    }
+
     return reply.code(404).send({ error: `MAC ${mac} not found in install queue or installed` });
   });
 }

bastion/src/labd/src/routes/environments.ts

@@ -0,0 +1,191 @@
+// Environment and Account management routes.
+// GET/POST /api/environments       — list/create environments
+// GET/POST /api/accounts           — list/create accounts
+// POST     /api/accounts/bind      — bind account to environment
+// GET      /api/bindings           — list bindings
+
+import type { FastifyInstance } from "fastify";
+import type { PrismaClient, Prisma } from "@prisma/client";
+import type { RbacService } from "../services/rbac.js";
+import type { AuditService } from "../services/audit.js";
+
+export function registerEnvironmentRoutes(
+  app: FastifyInstance,
+  db: PrismaClient,
+  rbacService: RbacService,
+  auditService: AuditService,
+): void {
+  // List environments
+  app.get("/api/environments", async (_request, reply) => {
+    const envs = await db.environment.findMany({ orderBy: { name: "asc" } });
+    return reply.send(envs);
+  });
+
+  // Create environment
+  app.post<{
+    Body: { name?: string };
+  }>("/api/environments", async (request, reply) => {
+    const { name } = request.body ?? {};
+    if (!name) {
+      return reply.code(400).send({ error: "name is required" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "admin",
+      resource: "environments",
+    });
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    try {
+      const env = await db.environment.create({ data: { name } });
+      auditService.emit({
+        eventKind: "resource_created",
+        source: "labd",
+        verified: true,
+        userId: request.userId ?? null,
+        resourceKind: "environment",
+        resourceName: name,
+        result: "success",
+      });
+      return reply.code(201).send(env);
+    } catch (err) {
+      if (err instanceof Error && err.message.includes("Unique constraint")) {
+        return reply.code(409).send({ error: `Environment '${name}' already exists` });
+      }
+      throw err;
+    }
+  });
+
+  // List accounts
+  app.get("/api/accounts", async (_request, reply) => {
+    const accounts = await db.account.findMany({
+      orderBy: { name: "asc" },
+      select: { id: true, name: true, driver: true, config: true, createdAt: true, updatedAt: true },
+    });
+    return reply.send(accounts);
+  });
+
+  // Create account
+  app.post<{
+    Body: { name?: string; driver?: string; config?: Record<string, unknown> };
+  }>("/api/accounts", async (request, reply) => {
+    const { name, driver, config } = request.body ?? {};
+    if (!name || !driver) {
+      return reply.code(400).send({ error: "name and driver are required" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "admin",
+      resource: "accounts",
+    });
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    try {
+      const account = await db.account.create({
+        data: { name, driver, config: (config ?? {}) as Prisma.InputJsonValue },
+      });
+      auditService.emit({
+        eventKind: "resource_created",
+        source: "labd",
+        verified: true,
+        userId: request.userId ?? null,
+        resourceKind: "account",
+        resourceName: name,
+        result: "success",
+        details: { driver },
+      });
+      return reply.code(201).send(account);
+    } catch (err) {
+      if (err instanceof Error && err.message.includes("Unique constraint")) {
+        return reply.code(409).send({ error: `Account '${name}' already exists` });
+      }
+      throw err;
+    }
+  });
+
+  // Bind account to environment
+  app.post<{
+    Body: { environmentId?: string; accountId?: string };
+  }>("/api/accounts/bind", async (request, reply) => {
+    const { environmentId, accountId } = request.body ?? {};
+    if (!environmentId || !accountId) {
+      return reply.code(400).send({ error: "environmentId and accountId are required" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "admin",
+      resource: "accounts",
+    });
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    try {
+      const binding = await db.binding.create({
+        data: { environmentId, accountId },
+      });
+      return reply.code(201).send(binding);
+    } catch (err) {
+      if (err instanceof Error && err.message.includes("Unique constraint")) {
+        return reply.code(409).send({ error: "This account is already bound to this environment" });
+      }
+      throw err;
+    }
+  });
+
+  // List bindings
+  app.get("/api/bindings", async (_request, reply) => {
+    const bindings = await db.binding.findMany({
+      include: { environment: true, account: true },
+    });
+    return reply.send(bindings);
+  });
+
+  // Audit event query
+  app.get<{
+    Querystring: {
+      last?: string;
+      kind?: string;
+      env?: string;
+      correlation?: string;
+      limit?: string;
+    };
+  }>("/api/events", async (request, reply) => {
+    const { last, kind, env, correlation, limit } = request.query as { last?: string; kind?: string; env?: string; correlation?: string; limit?: string };
+
+    const where: Record<string, unknown> = {};
+
+    if (last) {
+      const match = last.match(/^(\d+)(h|d|m)$/);
+      if (match) {
+        const [, num, unit] = match;
+        const ms = { h: 3_600_000, d: 86_400_000, m: 60_000 }[unit!]!;
+        where.timestamp = { gte: new Date(Date.now() - parseInt(num!) * ms) };
+      }
+    }
+    if (kind) where.eventKind = kind;
+    if (env) where.environmentName = env;
+    if (correlation) where.correlationId = correlation;
+
+    const events = await db.auditEvent.findMany({
+      where,
+      orderBy: { timestamp: "desc" },
+      take: Math.min(parseInt(limit ?? "100"), 500),
+    });
+
+    return reply.send(events);
+  });
+}

bastion/src/labd/src/routes/resources.ts

@@ -0,0 +1,196 @@
+// Resource CRUD routes with RBAC enforcement.
+// GET    /api/resources          — list (filtered by RBAC scope)
+// GET    /api/resources/:id      — get
+// POST   /api/resources          — create
+// PUT    /api/resources/:id      — update
+// DELETE /api/resources/:id      — delete (marks as deleting)
+
+import type { FastifyInstance } from "fastify";
+import type { ResourceStore, CreateResourceInput } from "../services/resource-store.js";
+import type { RbacService } from "../services/rbac.js";
+import type { AuditService } from "../services/audit.js";
+import { resolveResourceKind } from "@lab/core";
+
+export function registerResourceRoutes(
+  app: FastifyInstance,
+  resourceStore: ResourceStore,
+  rbacService: RbacService,
+  auditService: AuditService,
+): void {
+  // List resources (filtered by kind, environment, status)
+  app.get<{
+    Querystring: { kind?: string; environment?: string; status?: string };
+  }>("/api/resources", async (request, reply) => {
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "view",
+      resource: request.query.kind ? resolveResourceKind(request.query.kind) : undefined,
+    });
+
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    const resources = await resourceStore.list({
+      kind: request.query.kind ? resolveResourceKind(request.query.kind) : undefined,
+      environmentId: request.query.environment,
+      status: request.query.status,
+    });
+
+    return reply.send(resources);
+  });
+
+  // Get single resource
+  app.get<{
+    Params: { id: string };
+  }>("/api/resources/:id", async (request, reply) => {
+    const resource = await resourceStore.get(request.params.id);
+    if (!resource) {
+      return reply.code(404).send({ error: "Resource not found" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "view",
+      resource: resource.kind,
+      name: resource.name,
+    });
+
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    return reply.send(resource);
+  });
+
+  // Create resource
+  app.post<{
+    Body: CreateResourceInput;
+  }>("/api/resources", async (request, reply) => {
+    const input = request.body;
+    if (!input?.kind || !input?.name || !input?.environmentId || !input?.accountId) {
+      return reply.code(400).send({ error: "kind, name, environmentId, and accountId are required" });
+    }
+
+    const kind = resolveResourceKind(input.kind);
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "create",
+      resource: kind,
+    });
+
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    const correlationId = auditService.createCorrelation();
+
+    try {
+      const resource = await resourceStore.create({ ...input, kind });
+
+      auditService.emit({
+        eventKind: "resource_created",
+        source: "labd",
+        verified: true,
+        userId: request.userId ?? null,
+        userName: request.userEmail ?? null,
+        resourceKind: kind,
+        resourceName: input.name,
+        correlationId,
+        result: "success",
+      });
+
+      return reply.code(201).send(resource);
+    } catch (err) {
+      // Prisma unique constraint violation
+      if (err instanceof Error && err.message.includes("Unique constraint")) {
+        return reply.code(409).send({ error: `Resource ${kind}/${input.name} already exists in this environment` });
+      }
+      throw err;
+    }
+  });
+
+  // Update resource
+  app.put<{
+    Params: { id: string };
+    Body: { desiredSpec?: Record<string, unknown>; status?: string };
+  }>("/api/resources/:id", async (request, reply) => {
+    const resource = await resourceStore.get(request.params.id);
+    if (!resource) {
+      return reply.code(404).send({ error: "Resource not found" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "edit",
+      resource: resource.kind,
+      name: resource.name,
+    });
+
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    const updated = await resourceStore.update(request.params.id, request.body);
+
+    auditService.emit({
+      eventKind: "resource_updated",
+      source: "labd",
+      verified: true,
+      userId: request.userId ?? null,
+      userName: request.userEmail ?? null,
+      resourceKind: resource.kind,
+      resourceName: resource.name,
+      result: "success",
+    });
+
+    return reply.send(updated);
+  });
+
+  // Delete resource (marks as deleting)
+  app.delete<{
+    Params: { id: string };
+  }>("/api/resources/:id", async (request, reply) => {
+    const resource = await resourceStore.get(request.params.id);
+    if (!resource) {
+      return reply.code(404).send({ error: "Resource not found" });
+    }
+
+    const rbac = await rbacService.check({
+      userId: request.userId!,
+      userEmail: request.userEmail!,
+      userRole: request.userRole!,
+      action: "delete",
+      resource: resource.kind,
+      name: resource.name,
+    });
+
+    if (!rbac.allowed) {
+      return reply.code(403).send({ error: rbac.reason });
+    }
+
+    await resourceStore.delete(request.params.id);
+
+    auditService.emit({
+      eventKind: "resource_deleted",
+      source: "labd",
+      verified: true,
+      userId: request.userId ?? null,
+      userName: request.userEmail ?? null,
+      resourceKind: resource.kind,
+      resourceName: resource.name,
+      result: "success",
+    });
+
+    return reply.send({ status: "deleting", id: request.params.id });
+  });
+}

bastion/src/labd/src/routes/v2-auth.ts

@@ -0,0 +1,81 @@
+// v2 Auth routes: bearer token login/logout.
+// POST /api/auth/login  — email + password → session token
+// POST /api/auth/logout — revoke session
+
+import type { FastifyInstance } from "fastify";
+import type { AuthService } from "../services/auth.js";
+import type { AuditService } from "../services/audit.js";
+import { AuthError } from "../services/auth.js";
+
+export function registerV2AuthRoutes(
+  app: FastifyInstance,
+  authService: AuthService,
+  auditService: AuditService,
+): void {
+  app.post<{
+    Body: { email?: string; password?: string };
+  }>("/api/auth/login", async (request, reply) => {
+    const { email, password } = request.body ?? {};
+
+    if (!email || !password) {
+      return reply.code(400).send({ error: "email and password are required" });
+    }
+
+    try {
+      const result = await authService.login(email, password);
+
+      auditService.emit({
+        eventKind: result.isBootstrap ? "auth_bootstrap" : "auth_login",
+        source: "labd",
+        verified: true,
+        userId: result.userId,
+        userName: email,
+        result: "success",
+        details: { isBootstrap: result.isBootstrap },
+      });
+
+      return reply.send({
+        token: result.token,
+        expiresAt: result.expiresAt.toISOString(),
+        isBootstrap: result.isBootstrap,
+      });
+    } catch (err) {
+      if (err instanceof AuthError) {
+        auditService.emit({
+          eventKind: "auth_login",
+          source: "labd",
+          verified: true,
+          userName: email,
+          result: "failure",
+          error: err.message,
+        });
+        return reply.code(401).send({ error: err.message });
+      }
+      return reply.code(500).send({ error: "Login failed" });
+    }
+  });
+
+  app.post("/api/auth/logout", async (request, reply) => {
+    const token = request.headers.authorization?.slice(7);
+    if (!token) {
+      return reply.code(400).send({ error: "Authorization header required" });
+    }
+
+    try {
+      await authService.logout(token);
+      auditService.emit({
+        eventKind: "auth_logout",
+        source: "labd",
+        verified: true,
+        userId: request.userId ?? null,
+        result: "success",
+      });
+      return reply.send({ status: "logged_out" });
+    } catch (err) {
+      if (err instanceof AuthError) {
+        return reply.code(400).send({ error: err.message });
+      }
+      return reply.code(500).send({ error: "Logout failed" });
+    }
+  });
+}

bastion/src/labd/src/server.ts

@@ -2,6 +2,7 @@
 
 import Fastify from "fastify";
 import websocket from "@fastify/websocket";
+import type { PrismaClient } from "@prisma/client";
 import type { LabdConfig } from "./config.js";
 import { logger } from "./services/logger.js";
 import { registerHealthRoutes } from "./routes/health.js";
@@ -9,8 +10,16 @@ import { registerServerRoutes } from "./routes/servers.js";
 import { registerAuthRoutes } from "./routes/auth.js";
 import { registerAgentRoutes } from "./routes/agents.js";
 import { registerBastionRoutes } from "./routes/bastions.js";
+import { registerV2AuthRoutes } from "./routes/v2-auth.js";
+import { registerEnvironmentRoutes } from "./routes/environments.js";
+import { registerResourceRoutes } from "./routes/resources.js";
 import { setupRateLimiting } from "./middleware/rate-limit.js";
+import { createBearerAuthMiddleware } from "./middleware/bearer-auth.js";
 import { bastionRegistry } from "./services/bastion-registry.js";
+import { AuthService } from "./services/auth.js";
+import { RbacService } from "./services/rbac.js";
+import { ResourceStore } from "./services/resource-store.js";
+import { AuditService } from "./services/audit.js";
 import { isBastionMessage } from "@lab/shared";
 
 export interface DbClient {
@@ -37,6 +46,7 @@ export interface DbClient {
 
 export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
   app: ReturnType<typeof Fastify>;
+  auditService: AuditService;
 }> {
   const app = Fastify({
     logger: false, // We use winston instead
@@ -48,13 +58,39 @@ export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
   // Register WebSocket support
   void app.register(websocket);
 
-  // Register route handlers
+  // v2 services. The structural DbClient is a subset of the real PrismaClient;
+  // at runtime db IS the PrismaClient instance, so the cast is safe. Tests that
+  // exercise v2 routes provide a PrismaClient-shaped mock (see auth-bootstrap,
+  // rbac-deny, audit-correlation tests).
+  const prisma = db as unknown as PrismaClient;
+  const authService = new AuthService(prisma);
+  const rbacService = new RbacService(prisma);
+  const resourceStore = new ResourceStore(prisma);
+  const auditService = new AuditService(prisma);
+  auditService.start();
+
+  // Register v1 (legacy) route handlers
   registerHealthRoutes(app, db);
   registerServerRoutes(app, db);
   registerAuthRoutes(app, db);
   registerAgentRoutes(app);
   registerBastionRoutes(app, db);
 
+  // v2 routes live in a scope with bearer-auth as preHandler. Public paths
+  // (login, /health, websockets) are skipped inside the middleware itself.
+  // v1 routes above are unaffected — they're registered on the root scope.
+  await app.register(async (scope) => {
+    scope.addHook("preHandler", createBearerAuthMiddleware(authService));
+    registerV2AuthRoutes(scope, authService, auditService);
+    registerEnvironmentRoutes(scope, prisma, rbacService, auditService);
+    registerResourceRoutes(scope, resourceStore, rbacService, auditService);
+  });
+
+  // Flush pending audit events on shutdown so we never lose the last batch.
+  app.addHook("onClose", async () => {
+    auditService.stop();
+  });
+
   // WebSocket handler for agent connections
   app.register(async (fastify) => {
     fastify.get("/ws/agent", { websocket: true }, (socket, _request) => {
@@ -192,7 +228,9 @@ export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
                           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",
+                          // Leave status alone — a previously "online"/"offline" record
+                          // must not be downgraded to "discovered" just because the bastion
+                          // restarted and re-discovered the MAC via DHCP/PXE.
                           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 },
                         },
@@ -265,5 +303,5 @@ export async function createApp(_config: LabdConfig, db: DbClient): Promise<{
     logger.info(`HTTP: ${request.ip} ${request.method} ${request.url}`);
   });
 
-  return { app };
+  return { app, auditService };
 }

bastion/src/labd/src/services/audit.ts

@@ -0,0 +1,106 @@
+// Audit service: fire-and-forget event collection with batching.
+// Batches 50 events or flushes every 5 seconds, whichever comes first.
+// Failures never block the operation being audited.
+
+import { randomBytes } from "node:crypto";
+import type { PrismaClient, Prisma } from "@prisma/client";
+import { logger } from "./logger.js";
+
+const BATCH_SIZE = 50;
+const FLUSH_INTERVAL_MS = 5_000;
+
+export interface AuditEventInput {
+  eventKind: string;
+  source: string;
+  verified?: boolean;
+  userId?: string | null;
+  userName?: string | null;
+  sessionId?: string | null;
+  environmentName?: string | null;
+  accountName?: string | null;
+  resourceKind?: string | null;
+  resourceName?: string | null;
+  correlationId?: string | null;
+  parentEventId?: string | null;
+  details?: Record<string, unknown>;
+  result: string;
+  error?: string | null;
+  durationMs?: number | null;
+}
+
+export class AuditService {
+  private batch: AuditEventInput[] = [];
+  private timer: ReturnType<typeof setInterval> | null = null;
+
+  constructor(private readonly db: PrismaClient) {}
+
+  start(): void {
+    this.timer = setInterval(() => {
+      void this.flush();
+    }, FLUSH_INTERVAL_MS);
+  }
+
+  stop(): void {
+    if (this.timer) {
+      clearInterval(this.timer);
+      this.timer = null;
+    }
+    void this.flush();
+  }
+
+  emit(event: AuditEventInput): void {
+    // Generate correlation ID if not provided
+    if (!event.correlationId) {
+      event.correlationId = `corr_${randomBytes(8).toString("hex")}`;
+    }
+
+    this.batch.push(event);
+
+    if (this.batch.length >= BATCH_SIZE) {
+      void this.flush();
+    }
+  }
+
+  /** Create a correlation context for a chain of related events. */
+  createCorrelation(): string {
+    return `corr_${randomBytes(8).toString("hex")}`;
+  }
+
+  /** Flush all pending events synchronously. Tests await this; production
+   * relies on the interval timer or stop() during shutdown. */
+  async flushPending(): Promise<void> {
+    await this.flush();
+  }
+
+  private async flush(): Promise<void> {
+    if (this.batch.length === 0) return;
+
+    const events = this.batch.splice(0);
+    try {
+      await this.db.auditEvent.createMany({
+        data: events.map((e) => ({
+          eventKind: e.eventKind,
+          source: e.source,
+          verified: e.verified ?? false,
+          userId: e.userId ?? null,
+          userName: e.userName ?? null,
+          sessionId: e.sessionId ?? null,
+          environmentName: e.environmentName ?? null,
+          accountName: e.accountName ?? null,
+          resourceKind: e.resourceKind ?? null,
+          resourceName: e.resourceName ?? null,
+          correlationId: e.correlationId ?? `corr_${randomBytes(8).toString("hex")}`,
+          parentEventId: e.parentEventId ?? null,
+          details: (e.details ?? {}) as Prisma.InputJsonValue,
+          result: e.result,
+          error: e.error ?? null,
+          durationMs: e.durationMs ?? null,
+        })),
+      });
+      logger.info(`AUDIT: flushed ${events.length} events`);
+    } catch (err) {
+      // Fire-and-forget: audit failures never block operations
+      logger.warn(`AUDIT: failed to flush ${events.length} events: ${err instanceof Error ? err.message : String(err)}`);
+    }
+  }
+}

bastion/src/labd/src/services/auth.ts

@@ -0,0 +1,119 @@
+// Auth service: bearer token authentication with bootstrap flow.
+// First login creates the admin user. Subsequent logins return session tokens.
+
+import { randomBytes } from "node:crypto";
+import bcrypt from "bcryptjs";
+import type { PrismaClient } from "@prisma/client";
+import { logger } from "./logger.js";
+
+const SESSION_EXPIRY_DAYS = 30;
+const BCRYPT_ROUNDS = 12;
+
+export interface LoginResult {
+  token: string;
+  expiresAt: Date;
+  userId: string;
+  isBootstrap: boolean;
+}
+
+export class AuthService {
+  constructor(private readonly db: PrismaClient) {}
+
+  async login(email: string, password: string): Promise<LoginResult> {
+    const userCount = await this.db.user.count();
+
+    // Bootstrap: first login creates admin user
+    if (userCount === 0) {
+      return this.bootstrap(email, password);
+    }
+
+    const user = await this.db.user.findUnique({ where: { email } });
+    if (!user) {
+      // Same error for unknown user and wrong password (no enumeration)
+      throw new AuthError("Invalid email or password");
+    }
+
+    const valid = await bcrypt.compare(password, user.password);
+    if (!valid) {
+      throw new AuthError("Invalid email or password");
+    }
+
+    const session = await this.createSession(user.id);
+    logger.info(`AUTH LOGIN: ${email} (${user.id.slice(0, 8)}...)`);
+
+    return {
+      token: session.token,
+      expiresAt: session.expiresAt,
+      userId: user.id,
+      isBootstrap: false,
+    };
+  }
+
+  async logout(token: string): Promise<void> {
+    const session = await this.db.session.findUnique({ where: { token } });
+    if (!session) {
+      throw new AuthError("Invalid session");
+    }
+    await this.db.session.delete({ where: { id: session.id } });
+    logger.info(`AUTH LOGOUT: session ${session.id.slice(0, 8)}...`);
+  }
+
+  async validateToken(token: string): Promise<{ userId: string; email: string; role: string }> {
+    const session = await this.db.session.findUnique({
+      where: { token },
+      include: { user: true },
+    });
+
+    if (!session) {
+      throw new AuthError("Invalid token");
+    }
+    if (session.expiresAt < new Date()) {
+      await this.db.session.delete({ where: { id: session.id } });
+      throw new AuthError("Token expired");
+    }
+
+    return {
+      userId: session.user.id,
+      email: session.user.email,
+      role: session.user.role,
+    };
+  }
+
+  private async bootstrap(email: string, password: string): Promise<LoginResult> {
+    const hashed = await bcrypt.hash(password, BCRYPT_ROUNDS);
+    const user = await this.db.user.create({
+      data: {
+        email,
+        password: hashed,
+        role: "ADMIN",
+        name: email.split("@")[0] ?? null,
+      },
+    });
+
+    const session = await this.createSession(user.id);
+    logger.info(`AUTH BOOTSTRAP: created admin user ${email} (${user.id.slice(0, 8)}...)`);
+
+    return {
+      token: session.token,
+      expiresAt: session.expiresAt,
+      userId: user.id,
+      isBootstrap: true,
+    };
+  }
+
+  private async createSession(userId: string) {
+    const token = randomBytes(32).toString("hex");
+    const expiresAt = new Date(Date.now() + SESSION_EXPIRY_DAYS * 24 * 60 * 60 * 1000);
+
+    return this.db.session.create({
+      data: { userId, token, expiresAt },
+    });
+  }
+}
+
+export class AuthError extends Error {
+  constructor(message: string) {
+    super(message);
+    this.name = "AuthError";
+  }
+}

bastion/src/labd/src/services/rbac.ts

@@ -0,0 +1,123 @@
+// RBAC service: environment-scoped permission checks.
+// Uses named RbacDefinition records with JSON subjects and roleBindings.
+//
+// Resolution flow:
+//   1. Find all RbacDefinitions where subjects match the current user/groups
+//   2. Collect all roleBindings from matching definitions
+//   3. Check if any binding grants the requested action on the requested resource
+
+import type { PrismaClient } from "@prisma/client";
+import { logger } from "./logger.js";
+
+export interface RbacCheck {
+  userId: string;
+  userEmail: string;
+  userRole: string;
+  action: string;       // "view" | "edit" | "create" | "delete" | "run" | "admin"
+  resource?: string | undefined;    // "servers" | "databases" | "clusters" | "*"
+  name?: string | undefined;        // specific resource name
+  environment?: string | undefined; // specific environment name
+}
+
+export interface RbacResult {
+  allowed: boolean;
+  reason: string;
+  matchedDefinition?: string;
+}
+
+interface StoredSubject {
+  kind: string;
+  name: string;
+}
+
+interface StoredBinding {
+  role: string;
+  resource?: string;
+  name?: string;
+  environment?: string;
+  action?: string;
+}
+
+export class RbacService {
+  constructor(private readonly db: PrismaClient) {}
+
+  async check(req: RbacCheck): Promise<RbacResult> {
+    // Admin users bypass RBAC
+    if (req.userRole === "ADMIN") {
+      return { allowed: true, reason: "admin role" };
+    }
+
+    // Collect user's group memberships
+    const memberships = await this.db.groupMember.findMany({
+      where: { userId: req.userId },
+      include: { group: true },
+    });
+    const groupNames = memberships.map((m) => m.group.name);
+
+    // Find all RBAC definitions
+    const definitions = await this.db.rbacDefinition.findMany();
+
+    for (const def of definitions) {
+      const subjects = def.subjects as unknown as StoredSubject[];
+      const bindings = def.roleBindings as unknown as StoredBinding[];
+
+      // Check if this definition's subjects match the user
+      const subjectMatch = subjects.some((s) => {
+        if (s.kind === "User" && s.name === req.userEmail) return true;
+        if (s.kind === "Group" && groupNames.includes(s.name)) return true;
+        return false;
+      });
+
+      if (!subjectMatch) continue;
+
+      // Check if any binding grants the requested permission
+      for (const binding of bindings) {
+        if (this.bindingMatches(binding, req)) {
+          logger.info(`RBAC ALLOW: ${req.userEmail} ${req.action} ${req.resource ?? "*"}${req.name ? `/${req.name}` : ""} via ${def.name}`);
+          return {
+            allowed: true,
+            reason: `granted by ${def.name}`,
+            matchedDefinition: def.name,
+          };
+        }
+      }
+    }
+
+    logger.info(`RBAC DENY: ${req.userEmail} ${req.action} ${req.resource ?? "*"}${req.name ? `/${req.name}` : ""}`);
+    return {
+      allowed: false,
+      reason: `no matching role binding for ${req.action} on ${req.resource ?? "*"}`,
+    };
+  }
+
+  private bindingMatches(binding: StoredBinding, req: RbacCheck): boolean {
+    // Check role grants the action
+    if (!this.roleGrantsAction(binding.role, req.action)) return false;
+
+    // Check resource scope
+    if (binding.resource && binding.resource !== "*" && binding.resource !== req.resource) return false;
+
+    // Check name scope
+    if (binding.name && binding.name !== req.name) return false;
+
+    // Check environment scope
+    if (binding.environment && binding.environment !== req.environment) return false;
+
+    // Check operation scope (for "run" role with specific actions)
+    if (binding.action && binding.action !== "*" && binding.action !== req.action) return false;
+
+    return true;
+  }
+
+  private roleGrantsAction(role: string, action: string): boolean {
+    const grants: Record<string, string[]> = {
+      admin: ["view", "edit", "create", "delete", "run", "admin"],
+      edit: ["view", "edit", "create", "delete"],
+      create: ["create"],
+      delete: ["delete"],
+      view: ["view"],
+      run: ["run"],
+    };
+    return grants[role]?.includes(action) ?? false;
+  }
+}

bastion/src/labd/src/services/resource-store.ts

@@ -0,0 +1,108 @@
+// Resource store: CRUD for generic resources with origin/managedBy tracking.
+// All mutations go through this service so RBAC and audit are applied consistently.
+
+import type { PrismaClient, Resource as PrismaResource, Prisma } from "@prisma/client";
+import { logger } from "./logger.js";
+
+export interface CreateResourceInput {
+  kind: string;
+  name: string;
+  environmentId: string;
+  accountId: string;
+  origin?: string;
+  managedBy?: string;
+  sourceRef?: string;
+  desiredSpec: Record<string, unknown>;
+}
+
+export interface UpdateResourceInput {
+  desiredSpec?: Record<string, unknown>;
+  status?: string;
+  statusMessage?: string;
+  actualSpec?: Record<string, unknown>;
+  platformRef?: string;
+}
+
+export interface ListResourcesFilter {
+  kind?: string | undefined;
+  environmentId?: string | undefined;
+  accountId?: string | undefined;
+  status?: string | undefined;
+}
+
+export class ResourceStore {
+  constructor(private readonly db: PrismaClient) {}
+
+  async create(input: CreateResourceInput): Promise<PrismaResource> {
+    const resource = await this.db.resource.create({
+      data: {
+        kind: input.kind,
+        name: input.name,
+        environmentId: input.environmentId,
+        accountId: input.accountId,
+        origin: input.origin ?? "cli",
+        managedBy: input.managedBy ?? "manual",
+        sourceRef: input.sourceRef ?? null,
+        desiredSpec: input.desiredSpec as Prisma.InputJsonValue,
+        status: "pending",
+      },
+    });
+
+    logger.info(`RESOURCE CREATED: ${input.kind}/${input.name} in env ${input.environmentId.slice(0, 8)}...`);
+    return resource;
+  }
+
+  async get(id: string): Promise<PrismaResource | null> {
+    return this.db.resource.findUnique({ where: { id } });
+  }
+
+  async getByKindNameEnv(kind: string, name: string, environmentId: string): Promise<PrismaResource | null> {
+    return this.db.resource.findUnique({
+      where: { kind_name_environmentId: { kind, name, environmentId } },
+    });
+  }
+
+  async list(filter: ListResourcesFilter = {}): Promise<PrismaResource[]> {
+    return this.db.resource.findMany({
+      where: {
+        ...(filter.kind ? { kind: filter.kind } : {}),
+        ...(filter.environmentId ? { environmentId: filter.environmentId } : {}),
+        ...(filter.accountId ? { accountId: filter.accountId } : {}),
+        ...(filter.status ? { status: filter.status } : {}),
+      },
+      orderBy: { createdAt: "desc" },
+    });
+  }
+
+  async update(id: string, input: UpdateResourceInput): Promise<PrismaResource> {
+    const data: Prisma.ResourceUpdateInput = {};
+    if (input.desiredSpec !== undefined) data.desiredSpec = input.desiredSpec as Prisma.InputJsonValue;
+    if (input.status !== undefined) data.status = input.status;
+    if (input.statusMessage !== undefined) data.statusMessage = input.statusMessage;
+    if (input.actualSpec !== undefined) data.actualSpec = input.actualSpec as Prisma.InputJsonValue;
+    if (input.platformRef !== undefined) data.platformRef = input.platformRef;
+    if (input.status === "ready") data.lastReconciled = new Date();
+
+    const resource = await this.db.resource.update({ where: { id }, data });
+
+    logger.info(`RESOURCE UPDATED: ${resource.kind}/${resource.name} -> ${input.status ?? "spec change"}`);
+    return resource;
+  }
+
+  async delete(id: string): Promise<void> {
+    const resource = await this.db.resource.findUnique({ where: { id } });
+    if (!resource) return;
+
+    // Mark as deleting first (driver handles actual deletion)
+    await this.db.resource.update({
+      where: { id },
+      data: { status: "deleting" },
+    });
+
+    logger.info(`RESOURCE DELETING: ${resource.kind}/${resource.name}`);
+  }
+
+  async hardDelete(id: string): Promise<void> {
+    await this.db.resource.delete({ where: { id } });
+  }
+}

bastion/src/labd/tests/bastions-machines.test.ts

@@ -0,0 +1,144 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import Fastify from "fastify";
+import { registerBastionRoutes } from "../src/routes/bastions.js";
+import { bastionRegistry } from "../src/services/bastion-registry.js";
+import type { DbClient } from "../src/server.js";
+import type { BastionState } from "@lab/shared";
+
+function createMockDb(servers: unknown[] = []): DbClient {
+  return {
+    $queryRaw: vi.fn().mockResolvedValue([{ "?column?": 1 }]),
+    server: {
+      findMany: vi.fn().mockResolvedValue(servers),
+      findUnique: vi.fn().mockResolvedValue(null),
+      upsert: vi.fn().mockResolvedValue({}),
+    },
+    joinToken: {
+      findUnique: vi.fn().mockResolvedValue(null),
+      findMany: vi.fn().mockResolvedValue([]),
+      create: vi.fn().mockResolvedValue({ id: "t" }),
+      update: vi.fn().mockResolvedValue({}),
+    },
+    bastion: {
+      upsert: vi.fn().mockResolvedValue({}),
+      findMany: vi.fn().mockResolvedValue([]),
+      findUnique: vi.fn().mockResolvedValue(null),
+      update: vi.fn().mockResolvedValue({}),
+    },
+  };
+}
+
+function registerFakeBastion(bastionId: string, state: BastionState): void {
+  bastionRegistry.register({
+    bastionId,
+    hostname: "fake",
+    network: "192.168.8.0/24",
+    serverIp: "192.168.8.11",
+    // socket is referenced only on commands, not during aggregation
+    socket: { on: () => undefined, off: () => undefined, send: () => undefined, close: () => undefined } as never,
+    connectedAt: new Date(),
+    lastHeartbeat: new Date(),
+    state,
+  });
+}
+
+describe("GET /api/machines aggregation", () => {
+  beforeEach(() => {
+    for (const b of bastionRegistry.getAll()) bastionRegistry.unregister(b.bastionId);
+  });
+
+  it("promotes a live-discovered MAC to installed when the DB has a real hostname+role for it", async () => {
+    // Simulates the worker0-k8s0 bug: bastion restarted, lost its installed map,
+    // rediscovered the machine via DHCP/PXE. DB still has hostname=worker0-k8s0,
+    // role=infra, ip=192.168.8.23. Without the fix, the CLI sees a "discovered"
+    // row with no hostname/role/IP. With the fix, the row is promoted to
+    // "installed" with full identity preserved.
+    const mac = "78:55:36:08:28:fb";
+    registerFakeBastion("b1", {
+      discovered: {
+        [mac]: {
+          mac, product: "SER", board: "SER", serial: "x", manufacturer: "AZW",
+          cpu_model: "AMD Ryzen 7 255", cpu_cores: 16, memory_gb: 58, arch: "x86_64",
+          disks: [], nics: [], first_seen: "", last_seen: "",
+        },
+      },
+      install_queue: {},
+      installed: {},
+      debug: {},
+    });
+
+    const app = Fastify({ logger: false });
+    const db = createMockDb([
+      { mac, hostname: "worker0-k8s0", role: "infra", ip: "192.168.8.23", status: "discovered", labels: {} },
+    ]);
+    registerBastionRoutes(app, db);
+
+    const res = await app.inject({ method: "GET", url: "/api/machines" });
+    expect(res.statusCode).toBe(200);
+    const body = JSON.parse(res.body);
+
+    expect(body.discovered[mac]).toBeUndefined();
+    expect(body.installed[mac]).toMatchObject({
+      hostname: "worker0-k8s0",
+      role: "infra",
+      ip: "192.168.8.23",
+      cpu_model: "AMD Ryzen 7 255",
+      cpu_cores: 16,
+      memory_gb: 58,
+    });
+
+    await app.close();
+  });
+
+  it("leaves a fresh-discovery MAC in discovered when DB only has a discovery-shaped record", async () => {
+    const mac = "aa:bb:cc:dd:ee:ff";
+    registerFakeBastion("b1", {
+      discovered: {
+        [mac]: {
+          mac, product: "SER", board: "SER", serial: "x", manufacturer: "AZW",
+          cpu_model: "AMD Ryzen 7", cpu_cores: 8, memory_gb: 32, arch: "x86_64",
+          disks: [], nics: [], first_seen: "", last_seen: "",
+        },
+      },
+      install_queue: {},
+      installed: {},
+      debug: {},
+    });
+
+    const app = Fastify({ logger: false });
+    // Matches what labd writes on first discovery: hostname=product, role="unknown"
+    const db = createMockDb([
+      { mac, hostname: "SER", role: "unknown", ip: null, status: "discovered", labels: {} },
+    ]);
+    registerBastionRoutes(app, db);
+
+    const res = await app.inject({ method: "GET", url: "/api/machines" });
+    const body = JSON.parse(res.body);
+
+    expect(body.discovered[mac]).toBeDefined();
+    expect(body.installed[mac]).toBeUndefined();
+
+    await app.close();
+  });
+
+  it("falls back to DB for MACs not in any live bucket", async () => {
+    const mac = "11:22:33:44:55:66";
+    // No bastions connected
+    const app = Fastify({ logger: false });
+    const db = createMockDb([
+      { mac, hostname: "worker1-k8s0", role: "infra", ip: "192.168.8.13", status: "online", labels: {} },
+    ]);
+    registerBastionRoutes(app, db);
+
+    const res = await app.inject({ method: "GET", url: "/api/machines" });
+    const body = JSON.parse(res.body);
+
+    expect(body.installed[mac]).toMatchObject({
+      hostname: "worker1-k8s0",
+      role: "infra",
+      ip: "192.168.8.13",
+    });
+
+    await app.close();
+  });
+});

bastion/src/labd/tests/v2-smoke.test.ts

@@ -0,0 +1,425 @@
+// End-to-end smoke tests for the v2.0 Phase 1 surface (auth bootstrap, RBAC,
+// audit correlation). These exercise the wiring in createApp(): the bearer
+// auth middleware, the v2 routes scope, and the AuditService lifecycle.
+//
+// We don't spin up CockroachDB. Instead we provide a PrismaClient-shaped
+// in-memory mock that matches the surface the v2 services actually touch.
+// Tests follow the project convention of using mock DBs + Fastify.inject().
+
+import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
+import bcrypt from "bcryptjs";
+import { createApp } from "../src/server.js";
+import type { DbClient } from "../src/server.js";
+import type { AuditService } from "../src/services/audit.js";
+
+const TEST_CONFIG = { port: 0, host: "127.0.0.1", databaseUrl: "", caDir: "/tmp", logLevel: "silent" };
+
+interface UserRow { id: string; email: string; password: string; role: string; name: string | null; }
+interface SessionRow { id: string; userId: string; token: string; expiresAt: Date; user?: UserRow; }
+interface RbacDefRow { id: string; name: string; subjects: unknown; roleBindings: unknown; }
+interface AuditEventRow {
+  id: string;
+  eventKind: string;
+  source: string;
+  verified: boolean;
+  userId: string | null;
+  userName: string | null;
+  environmentName: string | null;
+  resourceKind: string | null;
+  correlationId: string | null;
+  parentEventId: string | null;
+  details: unknown;
+  result: string;
+  error: string | null;
+  durationMs: number | null;
+  timestamp: Date;
+}
+
+interface Stores {
+  users: Map<string, UserRow>;
+  sessions: Map<string, SessionRow>;
+  groupMembers: Array<{ userId: string; group: { name: string } }>;
+  rbacDefs: RbacDefRow[];
+  auditEvents: AuditEventRow[];
+  resources: Array<Record<string, unknown>>;
+}
+
+function makeStores(): Stores {
+  return {
+    users: new Map(),
+    sessions: new Map(),
+    groupMembers: [],
+    rbacDefs: [],
+    auditEvents: [],
+    resources: [],
+  };
+}
+
+function makeMockDb(s: Stores): DbClient {
+  let idCounter = 0;
+  const newId = (prefix: string): string => `${prefix}-${++idCounter}`;
+
+  return {
+    $queryRaw: vi.fn(async () => [{ "?column?": 1 }]),
+    server: { findMany: vi.fn(async () => []), findUnique: vi.fn(), upsert: vi.fn() },
+    joinToken: { findUnique: vi.fn(), findMany: vi.fn(), create: vi.fn(), update: vi.fn() },
+    bastion: { upsert: vi.fn(), findMany: vi.fn(), findUnique: vi.fn(), update: vi.fn() },
+
+    user: {
+      count: vi.fn(async () => s.users.size),
+      findUnique: vi.fn(async (args: { where: { email?: string; id?: string } }) => {
+        if (args.where.email) {
+          for (const u of s.users.values()) if (u.email === args.where.email) return u;
+        }
+        if (args.where.id) return s.users.get(args.where.id) ?? null;
+        return null;
+      }),
+      create: vi.fn(async (args: { data: Omit<UserRow, "id"> }) => {
+        const id = newId("user");
+        const row: UserRow = { id, ...args.data };
+        s.users.set(id, row);
+        return row;
+      }),
+    },
+    session: {
+      findUnique: vi.fn(async (args: { where: { token?: string; id?: string }; include?: { user?: boolean } }) => {
+        let session: SessionRow | undefined;
+        if (args.where.token) {
+          for (const sess of s.sessions.values()) if (sess.token === args.where.token) { session = sess; break; }
+        } else if (args.where.id) {
+          session = s.sessions.get(args.where.id);
+        }
+        if (!session) return null;
+        if (args.include?.user) {
+          return { ...session, user: s.users.get(session.userId)! };
+        }
+        return session;
+      }),
+      create: vi.fn(async (args: { data: { userId: string; token: string; expiresAt: Date } }) => {
+        const id = newId("sess");
+        const row: SessionRow = { id, ...args.data };
+        s.sessions.set(id, row);
+        return row;
+      }),
+      delete: vi.fn(async (args: { where: { id: string } }) => {
+        s.sessions.delete(args.where.id);
+        return null;
+      }),
+    },
+    groupMember: {
+      findMany: vi.fn(async (args: { where: { userId: string } }) =>
+        s.groupMembers.filter((m) => m.userId === args.where.userId),
+      ),
+    },
+    rbacDefinition: {
+      findMany: vi.fn(async () => s.rbacDefs),
+    },
+    auditEvent: {
+      createMany: vi.fn(async (args: { data: Array<Omit<AuditEventRow, "id" | "timestamp">> }) => {
+        const ts = new Date();
+        for (const e of args.data) {
+          s.auditEvents.push({ id: newId("evt"), timestamp: ts, ...e });
+        }
+        return { count: args.data.length };
+      }),
+      findMany: vi.fn(async (args: { where?: Record<string, unknown>; orderBy?: unknown; take?: number }) => {
+        const where = args.where ?? {};
+        const filtered = s.auditEvents.filter((e) => {
+          if (where["eventKind"] && e.eventKind !== where["eventKind"]) return false;
+          if (where["correlationId"] && e.correlationId !== where["correlationId"]) return false;
+          if (where["environmentName"] && e.environmentName !== where["environmentName"]) return false;
+          return true;
+        });
+        return filtered.slice(0, args.take ?? 100);
+      }),
+    },
+    resource: {
+      findMany: vi.fn(async () => s.resources),
+      findUnique: vi.fn(),
+      create: vi.fn(),
+      update: vi.fn(),
+      delete: vi.fn(),
+    },
+    environment: { findMany: vi.fn(async () => []), findUnique: vi.fn(), create: vi.fn() },
+    account: { findMany: vi.fn(async () => []), findUnique: vi.fn(), create: vi.fn() },
+    binding: { findMany: vi.fn(async () => []), create: vi.fn() },
+  } as unknown as DbClient;
+}
+
+async function buildApp(s: Stores) {
+  const db = makeMockDb(s);
+  const result = await createApp(TEST_CONFIG, db);
+  await result.app.ready();
+  return result;
+}
+
+describe("v2 auth: bootstrap flow", () => {
+  let stores: Stores;
+  let app: Awaited<ReturnType<typeof buildApp>>["app"];
+  let auditService: AuditService;
+
+  beforeEach(async () => {
+    stores = makeStores();
+    const built = await buildApp(stores);
+    app = built.app;
+    auditService = built.auditService;
+  });
+
+  afterEach(async () => {
+    await app.close(); // triggers auditService.stop()
+  });
+
+  it("first login with no users seeds the admin and returns a session token", async () => {
+    expect(stores.users.size).toBe(0);
+
+    const resp = await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "s3cret-pw" },
+    });
+
+    expect(resp.statusCode).toBe(200);
+    const body = resp.json();
+    expect(body.isBootstrap).toBe(true);
+    expect(body.token).toMatch(/^[a-f0-9]{64}$/);
+    expect(typeof body.expiresAt).toBe("string");
+
+    expect(stores.users.size).toBe(1);
+    const created = [...stores.users.values()][0]!;
+    expect(created.email).toBe("admin@itaz.eu");
+    expect(created.role).toBe("ADMIN");
+    // Password is hashed, not stored plaintext.
+    expect(created.password).not.toBe("s3cret-pw");
+    expect(await bcrypt.compare("s3cret-pw", created.password)).toBe(true);
+
+    // Bootstrap emits an audit event.
+    await auditService.flushPending();
+    const bootstrapEvents = stores.auditEvents.filter((e) => e.eventKind === "auth_bootstrap");
+    expect(bootstrapEvents).toHaveLength(1);
+    expect(bootstrapEvents[0]!.result).toBe("success");
+    expect(bootstrapEvents[0]!.userName).toBe("admin@itaz.eu");
+  });
+
+  it("returns 400 for missing credentials", async () => {
+    const resp = await app.inject({ method: "POST", url: "/api/auth/login", payload: {} });
+    expect(resp.statusCode).toBe(400);
+  });
+
+  it("second login uses normal flow (no isBootstrap)", async () => {
+    // Bootstrap once
+    await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "s3cret-pw" },
+    });
+    expect(stores.users.size).toBe(1);
+
+    // Login again
+    const resp = await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "s3cret-pw" },
+    });
+
+    expect(resp.statusCode).toBe(200);
+    expect(resp.json().isBootstrap).toBe(false);
+    expect(stores.users.size).toBe(1); // no new user
+  });
+
+  it("rejects wrong password with 401", async () => {
+    // Seed admin
+    await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "s3cret-pw" },
+    });
+
+    const resp = await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "wrong" },
+    });
+    expect(resp.statusCode).toBe(401);
+
+    // Failed login is also audited.
+    await auditService.flushPending();
+    const fails = stores.auditEvents.filter((e) => e.eventKind === "auth_login" && e.result === "failure");
+    expect(fails).toHaveLength(1);
+  });
+});
+
+describe("v2 RBAC: env-scoped denial", () => {
+  let stores: Stores;
+  let app: Awaited<ReturnType<typeof buildApp>>["app"];
+
+  async function seedSession(role: string): Promise<string> {
+    stores.users.set("u-1", {
+      id: "u-1",
+      email: `${role.toLowerCase()}@itaz.eu`,
+      password: "x",
+      role,
+      name: null,
+    });
+    const token = "test-token-" + role;
+    stores.sessions.set("s-1", {
+      id: "s-1",
+      userId: "u-1",
+      token,
+      expiresAt: new Date(Date.now() + 86_400_000),
+    });
+    return token;
+  }
+
+  beforeEach(async () => {
+    stores = makeStores();
+    app = (await buildApp(stores)).app;
+  });
+
+  afterEach(async () => {
+    await app.close();
+  });
+
+  it("non-admin user with no role bindings gets 403 on /api/resources", async () => {
+    const token = await seedSession("EDITOR"); // not admin, no bindings
+
+    const resp = await app.inject({
+      method: "GET",
+      url: "/api/resources",
+      headers: { authorization: `Bearer ${token}` },
+    });
+
+    expect(resp.statusCode).toBe(403);
+    expect(resp.json().error).toMatch(/no matching role binding/);
+  });
+
+  it("missing/empty bearer token gets 401 (auth, not RBAC)", async () => {
+    const r1 = await app.inject({ method: "GET", url: "/api/resources" });
+    expect(r1.statusCode).toBe(401);
+
+    const r2 = await app.inject({
+      method: "GET",
+      url: "/api/resources",
+      headers: { authorization: "Bearer " },
+    });
+    expect(r2.statusCode).toBe(401);
+  });
+
+  it("invalid bearer token gets 401", async () => {
+    const resp = await app.inject({
+      method: "GET",
+      url: "/api/resources",
+      headers: { authorization: "Bearer not-a-real-token" },
+    });
+    expect(resp.statusCode).toBe(401);
+  });
+
+  it("admin role bypasses RBAC", async () => {
+    const token = await seedSession("ADMIN");
+
+    const resp = await app.inject({
+      method: "GET",
+      url: "/api/resources",
+      headers: { authorization: `Bearer ${token}` },
+    });
+
+    expect(resp.statusCode).toBe(200);
+    expect(resp.json()).toEqual([]);
+  });
+
+  it("user with binding for env A is denied for resources in env B", async () => {
+    const token = await seedSession("EDITOR");
+    stores.groupMembers.push({ userId: "u-1", group: { name: "team-a" } });
+    stores.rbacDefs.push({
+      id: "rbac-1",
+      name: "team-a-edit-on-env-a",
+      subjects: [{ kind: "Group", name: "team-a" }],
+      roleBindings: [{ role: "edit", environment: "env-a" }],
+    });
+
+    // List in env-a → should pass RBAC (no env query so it's global view, but
+    // the binding scope is environment-specific → for global list the binding
+    // doesn't apply when an environment scope is set on the binding).
+    // Smoke test the targeted denial: trying to create in env-b is rejected.
+    const respB = await app.inject({
+      method: "POST",
+      url: "/api/resources",
+      headers: { authorization: `Bearer ${token}` },
+      payload: { kind: "database", name: "x", environmentId: "env-b", accountId: "acc-1" },
+    });
+
+    expect(respB.statusCode).toBe(403);
+    expect(respB.json().error).toMatch(/no matching role binding/);
+  });
+});
+
+describe("v2 audit: correlation chain visible via /api/events", () => {
+  let stores: Stores;
+  let app: Awaited<ReturnType<typeof buildApp>>["app"];
+  let auditService: AuditService;
+
+  beforeEach(async () => {
+    stores = makeStores();
+    const built = await buildApp(stores);
+    app = built.app;
+    auditService = built.auditService;
+  });
+
+  afterEach(async () => {
+    await app.close();
+  });
+
+  it("emitted audit events are queryable by correlation id", async () => {
+    // Seed admin so /api/events is accessible (it sits behind bearer auth)
+    const loginResp = await app.inject({
+      method: "POST",
+      url: "/api/auth/login",
+      payload: { email: "admin@itaz.eu", password: "pw" },
+    });
+    const token = loginResp.json().token;
+
+    // Force flush so the bootstrap event is in the DB
+    await auditService.flushPending();
+
+    expect(stores.auditEvents.length).toBeGreaterThan(0);
+    const bootstrap = stores.auditEvents.find((e) => e.eventKind === "auth_bootstrap")!;
+    expect(bootstrap.correlationId).toMatch(/^corr_[a-f0-9]{16}$/);
+
+    // Query /api/events filtered by correlation id
+    const queryResp = await app.inject({
+      method: "GET",
+      url: `/api/events?correlation=${bootstrap.correlationId}`,
+      headers: { authorization: `Bearer ${token}` },
+    });
+
+    expect(queryResp.statusCode).toBe(200);
+    const events = queryResp.json() as Array<{ correlationId: string; eventKind: string }>;
+    expect(events.length).toBe(1);
+    expect(events[0]!.eventKind).toBe("auth_bootstrap");
+    expect(events[0]!.correlationId).toBe(bootstrap.correlationId);
+  });
+
+  it("explicit parent/child correlation chain is preserved across emits", async () => {
+    const correlationId = auditService.createCorrelation();
+
+    auditService.emit({
+      eventKind: "test_parent",
+      source: "test",
+      result: "success",
+      correlationId,
+    });
+    auditService.emit({
+      eventKind: "test_child",
+      source: "test",
+      result: "success",
+      correlationId,
+      parentEventId: "evt-1",
+    });
+
+    await auditService.flushPending();
+
+    const chain = stores.auditEvents.filter((e) => e.correlationId === correlationId);
+    expect(chain).toHaveLength(2);
+    expect(chain.map((e) => e.eventKind).sort()).toEqual(["test_child", "test_parent"]);
+    expect(chain.find((e) => e.eventKind === "test_child")!.parentEventId).toBe("evt-1");
+  });
+});

bastion/src/modules/modules/k3s/src/groups/hardening.ts

@@ -1,18 +1,22 @@
-// Hardening: Pod Security Standards, certificate check, log rotation.
+// Hardening: Pod Security Standards, certificate check, journald cap, storage.
 
 import type { OperationContext, OperationResult, OperationGroup } from "../types.js";
 import { runSequential } from "../utils.js";
 import { applyPodSecurityStandards } from "../operations/pod-security.js";
 import { checkCertExpiry } from "../operations/cert-check.js";
 import { configureLogRotation } from "../operations/log-rotation.js";
+import { configureJournaldLimits } from "../operations/journald-limits.js";
+import { configureLonghornDisk } from "../operations/longhorn-disk.js";
 
 export const hardeningGroup: OperationGroup = {
   name: "hardening",
-  description: "Pod security, certificate check, log rotation",
+  description: "Pod security, certificate check, journald cap, storage",
   operations: [
     { name: "Apply Pod Security Standards", fn: applyPodSecurityStandards },
     { name: "Check certificate expiry", fn: checkCertExpiry },
-    { name: "Configure log rotation", fn: configureLogRotation },
+    { name: "Decommission file-based audit logs", fn: configureLogRotation },
+    { name: "Configure journald disk cap", fn: configureJournaldLimits },
+    { name: "Configure Longhorn disk", fn: configureLonghornDisk },
   ],
 };
 

bastion/src/modules/modules/k3s/src/groups/host-prep.ts

@@ -7,16 +7,18 @@ import { applyCisHardening } from "../operations/sysctl.js";
 import { disableSwap } from "../operations/swap.js";
 import { disableFirewall } from "../operations/firewall.js";
 import { setSelinuxPermissive } from "../operations/selinux.js";
+import { enableIscsi } from "../operations/iscsi.js";
 
 export const hostPrepGroup: OperationGroup = {
   name: "host-prep",
-  description: "Prepare host for k3s: kernel modules, sysctl, swap, firewall, SELinux",
+  description: "Prepare host for k3s: kernel modules, sysctl, swap, firewall, SELinux, iSCSI",
   operations: [
     { name: "Load kernel modules", fn: loadKernelModules },
     { name: "Apply CIS sysctl", fn: applyCisHardening },
     { name: "Disable swap", fn: disableSwap },
     { name: "Disable firewall", fn: disableFirewall },
     { name: "Set SELinux permissive", fn: setSelinuxPermissive },
+    { name: "Enable iSCSI", fn: enableIscsi },
   ],
 };
 

bastion/src/modules/modules/k3s/src/groups/networking.ts

@@ -3,6 +3,8 @@
 import type { OperationContext, OperationResult, OperationGroup } from "../types.js";
 import { runSequential } from "../utils.js";
 import { installCilium } from "../operations/cilium.js";
+import { installMultus } from "../operations/multus.js";
+import { installVlanSetup } from "../operations/vlan-setup.js";
 import { fixCoreDnsUpstream } from "../operations/dns-fix.js";
 import { applyDefaultNetworkPolicies } from "../operations/network-policy.js";
 
@@ -11,6 +13,11 @@ export const networkingGroup: OperationGroup = {
   description: "Install Cilium CNI, fix DNS, apply network policies",
   operations: [
     { name: "Install Cilium CNI", fn: installCilium },
+    // Multus + vlan-setup: give pods a second interface on VLAN 10 (macvlan)
+    // for LAN device discovery (Matter/HomeKit mDNS). Must follow Cilium
+    // (needs cni.exclusive=false + bpf.vlanBypass={10} from installCilium).
+    { name: "Install Multus CNI", fn: installMultus },
+    { name: "Install vlan-setup (lan10 + CNI plugins)", fn: installVlanSetup },
     { name: "Fix CoreDNS upstream", fn: fixCoreDnsUpstream },
     { name: "Apply network policies", fn: applyDefaultNetworkPolicies },
   ],

bastion/src/modules/modules/k3s/src/install.ts

@@ -76,7 +76,6 @@ sed -i 's/^SELINUX=enforcing/SELINUX=permissive/' /etc/selinux/config 2>/dev/nul
 # ── 5b. Create k3s config directory ──
 echo "[5/10] Writing k3s server configuration..."
 mkdir -p /etc/rancher/k3s
-mkdir -p /var/log/kubernetes
 
 cat > /etc/rancher/k3s/config.yaml << 'K3S_CONFIG'
 # k3s server configuration — CIS hardened
@@ -91,13 +90,10 @@ disable:
   - servicelb
   - traefik
 
-# API server hardening
+# API server hardening (audit-log-path=- routes audit to journald via stdout)
 kube-apiserver-arg:
   - "anonymous-auth=false"
-  - "audit-log-path=/var/log/kubernetes/audit.log"
-  - "audit-log-maxage=30"
-  - "audit-log-maxbackup=10"
-  - "audit-log-maxsize=100"
+  - "audit-log-path=-"
   - "audit-policy-file=/etc/rancher/k3s/audit-policy.yaml"
   - "enable-admission-plugins=NodeRestriction,PodSecurity"
   - "request-timeout=300s"

bastion/src/modules/modules/k3s/src/k3s-module.ts

@@ -78,9 +78,10 @@ export class K3sModule implements Module {
       return toModuleResult("install", [...prepResults, ...k3sResults], start);
     }
 
-    // Phase 3: Networking (server only — agents don't install Cilium)
+    // Phase 3: Networking (initial server only — joining servers get Cilium via daemonset)
     let netResults: OperationResult[] = [];
-    if (isServer) {
+    const isJoiningServer = isServer && !!opCtx.config.k3sServerUrl;
+    if (isServer && !isJoiningServer) {
       netResults = await runNetworking(opCtx);
     }
 

bastion/src/modules/modules/k3s/src/operations/cilium.ts

@@ -35,21 +35,23 @@ export const installCilium: Operation = async (ctx): Promise<OperationResult> =>
   }
   details.push(`Installed cilium CLI ${version} (${cliArch})`);
 
-  // Detect default network device (avoid tailscale/wireguard)
-  const devResult = await ctx.ssh.exec(
-    "ip -4 route show default | awk '{print $5}' | head -1",
-    sshOpts(ctx),
-  );
-  const defaultDev = devResult.stdout.trim();
-  details.push(`Network device: ${defaultDev}`);
-
   // Install Cilium
+  // - No hardcoded devices: Cilium auto-detects per node (heterogeneous NICs like eno1 vs enP7s7)
+  // - k8sServiceHost/Port: k3s agents proxy the API on 127.0.0.1:6444 (not 6443)
+  // - cni.exclusive=false: required so Multus can install its CNI config alongside
+  //   Cilium (Cilium otherwise deletes any non-Cilium CNI conf).
+  // - bpf.vlanBypass={10}: allow VLAN 10 (LoT) tagged traffic through the eBPF
+  //   host VLAN filter, so pods on a macvlan/VLAN-10 interface receive multicast
+  //   (Matter/mDNS ff02::fb + 224.0.0.251). Without this Cilium drops it
+  //   ("VLAN traffic disallowed by VLAN filter", bpf_host.c).
   const installResult = await ctx.ssh.exec(
     `KUBECONFIG=/etc/rancher/k3s/k3s.yaml cilium install \
       --set kubeProxyReplacement=true \
       --set ipam.mode=kubernetes \
-      --set devices="${defaultDev}" \
-      --set nodePort.directRoutingDevice="${defaultDev}"`,
+      --set k8sServiceHost=127.0.0.1 \
+      --set k8sServicePort=6444 \
+      --set cni.exclusive=false \
+      --set bpf.vlanBypass="{10}"`,
     { timeoutMs: 300_000 },
   );
   if (installResult.exitCode !== 0) {

bastion/src/modules/modules/k3s/src/operations/etcd-recover.ts

@@ -0,0 +1,194 @@
+// Recover a broken etcd member by removing it from the cluster, wiping its
+// local state, and restarting k3s so it rejoins as a fresh member.
+//
+// Use case: a node panics on startup with
+//   "tocommit(N+1) is out of range [lastIndex(N)]. Was the raft log corrupted,
+//    truncated, or lost?"
+// This means the local raft WAL is missing the last entry the leader thinks
+// the follower acknowledged (lost write, unclean shutdown, etc). The fix is
+// always the same and well-documented; this codifies it so we don't fumble
+// the procedure under pressure.
+//
+// Preconditions:
+//   - At least one healthy peer is reachable so the cluster has quorum after
+//     we remove the broken member. (For a 3-node cluster: 2 healthy. For a
+//     5-node: 3 healthy.) If quorum would be lost, this function refuses.
+//   - SSH access to both the broken node and a healthy peer.
+//   - etcdctl available on the healthy peer (k3s does not bundle it; the
+//     procedure installs it on demand on Fedora).
+
+import type { SshClient } from "../types.js";
+
+const ETCD_TLS = {
+  ca: "/var/lib/rancher/k3s/server/tls/etcd/server-ca.crt",
+  cert: "/var/lib/rancher/k3s/server/tls/etcd/server-client.crt",
+  key: "/var/lib/rancher/k3s/server/tls/etcd/server-client.key",
+} as const;
+
+const SSH_TIMEOUT = 60_000;
+
+export interface RecoverEtcdMemberOptions {
+  /** SSH client for the broken node (the one panicking). */
+  broken: SshClient;
+  /** SSH client for any healthy server peer in the same cluster. */
+  peer: SshClient;
+  /** Hostname (k8s node name) of the broken node. Used to find its etcd member id. */
+  brokenHostname: string;
+  /** Logger for progress output. */
+  log?: (msg: string) => void;
+}
+
+export interface RecoverEtcdMemberResult {
+  success: boolean;
+  changed: boolean;
+  message: string;
+  /** New etcd member id assigned after rejoin (when known). */
+  newMemberId?: string;
+  /** Old etcd member id that was removed. */
+  removedMemberId?: string;
+  error?: string;
+}
+
+function etcdctl(subcmd: string): string {
+  return [
+    "ETCDCTL_API=3 etcdctl",
+    `--cacert=${ETCD_TLS.ca}`,
+    `--cert=${ETCD_TLS.cert}`,
+    `--key=${ETCD_TLS.key}`,
+    "--endpoints=https://127.0.0.1:2379",
+    "--command-timeout=10s",
+    subcmd,
+  ].join(" ");
+}
+
+async function ensureEtcdctl(peer: SshClient): Promise<void> {
+  const probe = await peer.exec("command -v etcdctl 2>/dev/null", { timeoutMs: 5_000 });
+  if (probe.exitCode === 0 && probe.stdout.trim()) return;
+  // Best-effort install on Fedora. If the host isn't dnf-based, surface the
+  // error to the caller via the next etcdctl invocation.
+  await peer.exec("dnf install -y etcd 2>&1", { timeoutMs: 120_000 });
+}
+
+async function getMemberList(peer: SshClient): Promise<Array<{ id: string; name: string }>> {
+  const result = await peer.exec(etcdctl("member list"), { timeoutMs: SSH_TIMEOUT });
+  if (result.exitCode !== 0) {
+    throw new Error(`etcdctl member list failed: ${result.stderr || result.stdout}`);
+  }
+  // Format: <hex-id>, started, <name>, <peer-urls>, <client-urls>, <isLearner>
+  return result.stdout
+    .split("\n")
+    .map((line) => line.trim())
+    .filter(Boolean)
+    .map((line) => {
+      const [id, , name] = line.split(",").map((p) => p.trim());
+      return { id: id ?? "", name: name ?? "" };
+    })
+    .filter((m) => m.id);
+}
+
+export async function recoverEtcdMember(
+  opts: RecoverEtcdMemberOptions,
+): Promise<RecoverEtcdMemberResult> {
+  const log = opts.log ?? (() => {});
+
+  try {
+    log(`Looking up etcd member id for ${opts.brokenHostname} via peer...`);
+    await ensureEtcdctl(opts.peer);
+
+    const members = await getMemberList(opts.peer);
+    if (members.length < 3) {
+      return {
+        success: false,
+        changed: false,
+        message: "Refusing to remove a member from a cluster with <3 members (quorum would be lost)",
+        error: `member count = ${members.length}`,
+      };
+    }
+
+    // Member names are <hostname>-<random-suffix>; match by hostname prefix.
+    const broken = members.find((m) => m.name.startsWith(opts.brokenHostname));
+    if (!broken) {
+      return {
+        success: false,
+        changed: false,
+        message: `No etcd member found matching hostname ${opts.brokenHostname}`,
+        error: `members: ${members.map((m) => m.name).join(", ")}`,
+      };
+    }
+    log(`Broken member: ${broken.id} (${broken.name})`);
+
+    log("Step 1/4: stopping k3s on broken node");
+    await opts.broken.exec("systemctl stop k3s 2>&1", { timeoutMs: SSH_TIMEOUT });
+
+    log("Step 2/4: removing broken etcd member from cluster");
+    const remove = await opts.peer.exec(
+      etcdctl(`member remove ${broken.id}`),
+      { timeoutMs: SSH_TIMEOUT },
+    );
+    if (remove.exitCode !== 0) {
+      return {
+        success: false,
+        changed: false,
+        message: "etcdctl member remove failed",
+        error: remove.stderr || remove.stdout,
+        removedMemberId: broken.id,
+      };
+    }
+
+    log("Step 3/4: archiving corrupt etcd state and stale TLS/cred dirs on broken node");
+    const ts = Math.floor(Date.now() / 1000);
+    await opts.broken.exec(
+      [
+        `mv /var/lib/rancher/k3s/server/db /var/lib/rancher/k3s/server/db.corrupt-${ts} 2>/dev/null || true`,
+        "rm -rf /var/lib/rancher/k3s/server/tls /var/lib/rancher/k3s/server/cred",
+      ].join(" && "),
+      { timeoutMs: SSH_TIMEOUT },
+    );
+
+    log("Step 4/4: starting k3s on broken node — it will rejoin");
+    await opts.broken.exec("systemctl start k3s 2>&1", { timeoutMs: SSH_TIMEOUT });
+
+    // Poll for rejoin. The new member-id is what the cluster assigns on join.
+    let newMemberId: string | undefined;
+    for (let i = 0; i < 60; i++) {
+      await new Promise((r) => setTimeout(r, 5_000));
+      try {
+        const after = await getMemberList(opts.peer);
+        const rejoined = after.find(
+          (m) => m.name.startsWith(opts.brokenHostname) && m.id !== broken.id,
+        );
+        if (rejoined) {
+          newMemberId = rejoined.id;
+          break;
+        }
+      } catch {
+        // peer may briefly be unreachable mid-rejoin — keep polling
+      }
+    }
+
+    if (!newMemberId) {
+      return {
+        success: false,
+        changed: true,
+        message: "k3s started but new member did not appear in cluster within 5 minutes",
+        removedMemberId: broken.id,
+      };
+    }
+
+    log(`Rejoined as ${newMemberId}`);
+    return {
+      success: true,
+      changed: true,
+      message: `Recovered: removed ${broken.id}, rejoined as ${newMemberId}`,
+      removedMemberId: broken.id,
+      newMemberId,
+    };
+  } catch (err) {
+    return {
+      success: false,
+      changed: false,
+      message: "Recovery failed",
+      error: err instanceof Error ? err.message : String(err),
+    };
+  }
+}

bastion/src/modules/modules/k3s/src/operations/index.ts

@@ -1,6 +1,7 @@
 export { loadKernelModules } from "./kernel-modules.js";
 export { applyCisHardening } from "./sysctl.js";
 export { disableSwap } from "./swap.js";
+export { enableIscsi } from "./iscsi.js";
 export { disableFirewall } from "./firewall.js";
 export { setSelinuxPermissive } from "./selinux.js";
 export { writeK3sConfig } from "./k3s-config.js";
@@ -8,8 +9,17 @@ export { writeAuditPolicy } from "./audit-policy.js";
 export { cleanupStaleCni } from "./cni-cleanup.js";
 export { installK3sBinary } from "./k3s-install.js";
 export { installCilium } from "./cilium.js";
+export { installMultus } from "./multus.js";
+export { installVlanSetup } from "./vlan-setup.js";
 export { fixCoreDnsUpstream } from "./dns-fix.js";
 export { configureLogRotation } from "./log-rotation.js";
+export { configureJournaldLimits } from "./journald-limits.js";
 export { applyDefaultNetworkPolicies } from "./network-policy.js";
 export { applyPodSecurityStandards } from "./pod-security.js";
 export { checkCertExpiry } from "./cert-check.js";
+export { configureLonghornDisk } from "./longhorn-disk.js";
+export { recoverEtcdMember } from "./etcd-recover.js";
+export type {
+  RecoverEtcdMemberOptions,
+  RecoverEtcdMemberResult,
+} from "./etcd-recover.js";

bastion/src/modules/modules/k3s/src/operations/iscsi.ts

@@ -0,0 +1,31 @@
+// Install and enable iSCSI initiator (required by Longhorn storage).
+// Fedora: iscsi-initiator-utils, Ubuntu: open-iscsi
+
+import type { Operation, OperationResult } from "../types.js";
+import { sshOpts } from "../utils.js";
+
+export const enableIscsi: Operation = async (ctx): Promise<OperationResult> => {
+  // Check if iscsid is already running
+  const check = await ctx.ssh.exec("systemctl is-active iscsid 2>/dev/null", sshOpts(ctx));
+  if (check.stdout.trim() === "active") {
+    return { success: true, changed: false, message: "iSCSI already active" };
+  }
+
+  // Install the package (detect distro)
+  const osRelease = await ctx.ssh.exec("cat /etc/os-release", sshOpts(ctx));
+  const osLower = osRelease.stdout.toLowerCase();
+  const isFedora = osLower.includes("fedora") || osLower.includes("rhel") || osLower.includes("centos");
+
+  const pkg = isFedora ? "iscsi-initiator-utils" : "open-iscsi";
+  const installCmd = isFedora ? `sudo dnf install -y ${pkg}` : `sudo apt-get install -y ${pkg}`;
+
+  const install = await ctx.ssh.exec(installCmd, { timeoutMs: 120_000 });
+  if (install.exitCode !== 0) {
+    return { success: false, changed: false, message: `Failed to install ${pkg}`, error: install.stderr.trim() };
+  }
+
+  // Enable and start
+  await ctx.ssh.exec("sudo systemctl enable --now iscsid", sshOpts(ctx));
+
+  return { success: true, changed: true, message: `Installed ${pkg} and enabled iscsid` };
+};

bastion/src/modules/modules/k3s/src/operations/journald-limits.ts

@@ -0,0 +1,33 @@
+// Cap journald disk usage so audit logs (which now flow through journald via
+// kube-apiserver's stdout) cannot fill /var/log. Default journald uses up to
+// 10% of the filesystem, capped at 4 GB. In a /var/log of ~10 GB shared with
+// other services, that's still room for audit volume to evict useful logs.
+// 2 GB / 200 MB-per-file is a comfortable middle.
+
+import type { Operation, OperationResult } from "../types.js";
+import { sshOpts, writeRemoteFile } from "../utils.js";
+
+const DROPIN_CONTENT = `[Journal]
+SystemMaxUse=2G
+SystemKeepFree=1G
+SystemMaxFileSize=200M
+`;
+
+const DROPIN_PATH = "/etc/systemd/journald.conf.d/10-k3s-audit-cap.conf";
+
+export const configureJournaldLimits: Operation = async (ctx): Promise<OperationResult> => {
+  const changed = await writeRemoteFile(ctx, DROPIN_PATH, DROPIN_CONTENT);
+  if (changed) {
+    // Reload journald so the new limit applies without a reboot.
+    await ctx.ssh.exec(
+      "systemctl kill --signal=SIGUSR2 systemd-journald 2>/dev/null; " +
+      "systemctl restart systemd-journald 2>&1 || true",
+      sshOpts(ctx),
+    );
+  }
+  return {
+    success: true,
+    changed,
+    message: changed ? "journald limits configured (2 GB cap)" : "journald limits already configured",
+  };
+};

bastion/src/modules/modules/k3s/src/operations/k3s-config.ts

@@ -9,7 +9,18 @@ function isServerRole(role: string): boolean {
 
 function generateServerConfig(config: K3sConfig): string {
   const tlsSans = [config.hostname, config.ip, ...(config.tlsSans ?? [])];
-  return `# k3s server configuration — CIS hardened
+  const isJoining = !!config.k3sServerUrl;
+  const clusterLines = isJoining
+    ? `server: "${config.k3sServerUrl}"\ntoken: "${config.k3sToken}"`
+    : "cluster-init: true";
+  // audit-log-path=- routes audit events to k3s.service's stdout, which systemd
+  // forwards to journald. journald enforces its own size caps (see
+  // configureJournaldLimits) so audit volume cannot fill the disk. File-based
+  // audit logs led to /var/log/kubernetes growing to 7+ GB because apiserver's
+  // own rotation produced files that any logrotate glob would double-rotate
+  // and never expire.
+  return `# k3s server configuration — CIS hardened, etcd HA
+${clusterLines}
 protect-kernel-defaults: true
 secrets-encryption: true
 write-kubeconfig-mode: "0640"
@@ -20,12 +31,12 @@ disable:
   - servicelb
   - traefik
 
+node-label:
+  - "node.longhorn.io/create-default-disk=config"
+
 kube-apiserver-arg:
   - "anonymous-auth=false"
-  - "audit-log-path=/var/log/kubernetes/audit.log"
-  - "audit-log-maxage=30"
-  - "audit-log-maxbackup=10"
-  - "audit-log-maxsize=100"
+  - "audit-log-path=-"
   - "audit-policy-file=/etc/rancher/k3s/audit-policy.yaml"
   - "enable-admission-plugins=NodeRestriction,PodSecurity"
   - "request-timeout=300s"
@@ -42,6 +53,9 @@ ${tlsSans.map((s) => `  - "${s}"`).join("\n")}
 
 function generateAgentConfig(): string {
   return `protect-kernel-defaults: true
+node-label:
+  - "node-role.kubernetes.io/worker=true"
+  - "node.longhorn.io/create-default-disk=config"
 kubelet-arg:
   - "protect-kernel-defaults=true"
   - "streaming-connection-idle-timeout=5m"
@@ -50,7 +64,7 @@ kubelet-arg:
 }
 
 export const writeK3sConfig: Operation = async (ctx): Promise<OperationResult> => {
-  await ctx.ssh.exec("mkdir -p /etc/rancher/k3s /var/log/kubernetes", sshOpts(ctx));
+  await ctx.ssh.exec("mkdir -p /etc/rancher/k3s", sshOpts(ctx));
 
   const content = isServerRole(ctx.config.role)
     ? generateServerConfig(ctx.config)

bastion/src/modules/modules/k3s/src/operations/k3s-install.ts

@@ -15,8 +15,21 @@ export const installK3sBinary: Operation = async (ctx): Promise<OperationResult>
   const alreadyInstalled = version.exitCode === 0;
 
   if (isServer) {
+    // Clean stale server state when joining an existing cluster
+    // (TLS certs from a previous run cause "newer than datastore" fatal error)
+    if (ctx.config.k3sServerUrl && ctx.config.k3sToken) {
+      await ctx.ssh.exec(
+        "rm -rf /var/lib/rancher/k3s/server/tls /var/lib/rancher/k3s/server/cred /var/lib/rancher/k3s/server/db",
+        sshOpts(ctx),
+      );
+    }
+
+    // If joining an existing cluster, pass K3S_URL and K3S_TOKEN
+    const joinEnv = ctx.config.k3sServerUrl && ctx.config.k3sToken
+      ? `K3S_URL="${ctx.config.k3sServerUrl}" K3S_TOKEN="${ctx.config.k3sToken}"`
+      : "";
     const result = await ctx.ssh.exec(
-      'curl -sfL https://get.k3s.io | INSTALL_K3S_EXEC="server" INSTALL_K3S_SKIP_SELINUX_RPM=true sh -',
+      `curl -sfL https://get.k3s.io | INSTALL_K3S_EXEC="server" INSTALL_K3S_SKIP_SELINUX_RPM=true ${joinEnv} sh -`,
       { timeoutMs: 300_000 },
     );
     if (result.exitCode !== 0) {

bastion/src/modules/modules/k3s/src/operations/log-rotation.ts

@@ -1,25 +1,44 @@
-// Configure log rotation for k3s.
+// Decommission file-based k8s audit logging in favor of journald.
+//
+// Earlier versions wrote audit events to /var/log/kubernetes/audit.log and
+// rotated them with a logrotate rule. Two failure modes followed: kube-apiserver
+// rotated internally (audit-{ts}.log), the *.log glob in logrotate
+// double-rotated those (-{date}), and the resulting filename matched no
+// retention policy, so the directory grew unbounded (we observed 7+ GB).
+//
+// k3s now sets audit-log-path=- so audit goes to stdout → journald, which
+// enforces SystemMaxUse caps. This operation removes the obsolete logrotate
+// rule and reaps any audit files left behind by the old setup. Idempotent: on
+// fresh installs everything is already absent and the operation is a no-op.
 
 import type { Operation, OperationResult } from "../types.js";
-import { writeRemoteFile } from "../utils.js";
+import { sshOpts } from "../utils.js";
 
-const LOGROTATE_CONFIG = `/var/log/kubernetes/*.log {
-  daily
-  rotate 14
-  compress
-  delaycompress
-  missingok
-  notifempty
-  copytruncate
-  maxsize 100M
-}`;
+const REMOVE_LOGROTATE = "rm -f /etc/logrotate.d/k3s";
+
+// Bounded by a max-depth and explicit name pattern so we never reach outside
+// the deprecated audit-log directory.
+const REAP_OLD_AUDIT_FILES =
+  "find /var/log/kubernetes -maxdepth 1 -type f " +
+  "\\( -name 'audit*.log*' -o -name 'audit-*.log' \\) " +
+  "-delete 2>/dev/null; " +
+  "rmdir /var/log/kubernetes 2>/dev/null; true";
 
 export const configureLogRotation: Operation = async (ctx): Promise<OperationResult> => {
-  const changed = await writeRemoteFile(ctx, "/etc/logrotate.d/k3s", LOGROTATE_CONFIG);
+  const before = await ctx.ssh.exec(
+    "test -e /etc/logrotate.d/k3s -o -d /var/log/kubernetes && echo present || echo absent",
+    sshOpts(ctx),
+  );
+  const wasPresent = before.stdout.trim() === "present";
+
+  await ctx.ssh.exec(REMOVE_LOGROTATE, sshOpts(ctx));
+  await ctx.ssh.exec(REAP_OLD_AUDIT_FILES, sshOpts(ctx));
 
   return {
     success: true,
-    changed,
-    message: changed ? "Log rotation configured" : "Log rotation already configured",
+    changed: wasPresent,
+    message: wasPresent
+      ? "Removed legacy file-based audit logging (now via journald)"
+      : "No legacy audit log artifacts present",
   };
 };

bastion/src/modules/modules/k3s/src/operations/longhorn-disk.ts

@@ -0,0 +1,50 @@
+// Annotate nodes with Longhorn default disk config when /var/lib/longhorn exists.
+// The label is set in k3s config (node-label), but the annotation must be applied via kubectl.
+
+import type { Operation, OperationResult } from "../types.js";
+import { sshOpts } from "../utils.js";
+import { sshExec as remoteSshExec } from "../../../../src/ssh.js";
+
+export const configureLonghornDisk: Operation = async (ctx): Promise<OperationResult> => {
+  // Check if /var/lib/longhorn exists on this node
+  const check = await ctx.ssh.exec("test -d /var/lib/longhorn && echo yes || echo no", sshOpts(ctx));
+  if (check.stdout.trim() !== "yes") {
+    return { success: true, changed: false, message: "No /var/lib/longhorn directory — skipping Longhorn disk config" };
+  }
+
+  // Find the node name (hostname as registered in k3s)
+  const nodeNameResult = await ctx.ssh.exec("hostname -f 2>/dev/null || hostname", sshOpts(ctx));
+  const nodeName = nodeNameResult.stdout.trim();
+
+  const annotation = JSON.stringify([{ path: "/var/lib/longhorn", allowScheduling: true }]);
+
+  // Try kubectl locally first (works on server nodes)
+  const result = await ctx.ssh.exec(
+    `k3s kubectl annotate node "${nodeName}" "node.longhorn.io/default-disks-config=${annotation}" --overwrite 2>&1 || true`,
+    sshOpts(ctx),
+  );
+
+  if (result.stdout.includes("annotated") || result.stdout.includes("unchanged")) {
+    return { success: true, changed: true, message: `Longhorn disk annotation applied to ${nodeName}` };
+  }
+
+  // For worker/agent nodes without local kubectl: apply via the server
+  if (ctx.config.k3sServerUrl) {
+    // The CLI has SSH access to the server — use sshExec from there
+    const serverHost = new URL(ctx.config.k3sServerUrl).hostname;
+    try {
+      const remoteResult = await remoteSshExec(
+        serverHost, "root",
+        `k3s kubectl annotate node "${nodeName}" "node.longhorn.io/default-disks-config=${annotation}" --overwrite`,
+        { ...(ctx.ssh.keyPath ? { keyPath: ctx.ssh.keyPath } : {}), timeoutMs: 15_000 },
+      );
+      if (remoteResult.stdout.includes("annotated") || remoteResult.stdout.includes("unchanged")) {
+        return { success: true, changed: true, message: `Longhorn disk annotation applied to ${nodeName} (via server)` };
+      }
+    } catch {
+      // Fall through to manual instruction
+    }
+  }
+
+  return { success: true, changed: false, message: "Longhorn disk label set (annotation requires server kubectl)" };
+};

bastion/src/modules/modules/k3s/src/operations/multus.ts

@@ -0,0 +1,34 @@
+// Install Multus CNI (thick plugin) — the meta-CNI that lets pods attach an
+// extra interface (macvlan on VLAN 10) alongside Cilium, via a
+// NetworkAttachmentDefinition. Required for Home Assistant's LAN presence
+// (Matter/HomeKit mDNS discovery). Cilium must be installed with
+// cni.exclusive=false first (see cilium.ts) or it deletes Multus's CNI conf.
+
+import type { Operation, OperationResult } from "../types.js";
+import { sshOpts } from "../utils.js";
+
+const MULTUS_VERSION = "v4.1.4";
+const MULTUS_MANIFEST = `https://raw.githubusercontent.com/k8snetworkplumbingwg/multus-cni/${MULTUS_VERSION}/deployments/multus-daemonset-thick.yml`;
+
+export const installMultus: Operation = async (ctx): Promise<OperationResult> => {
+  const K = "KUBECONFIG=/etc/rancher/k3s/k3s.yaml";
+
+  // Idempotent: skip if the Multus DaemonSet is already present.
+  const check = await ctx.ssh.exec(
+    `${K} kubectl -n kube-system get ds kube-multus-ds -o name 2>/dev/null`,
+    sshOpts(ctx),
+  );
+  if (check.exitCode === 0 && check.stdout.includes("kube-multus-ds")) {
+    return { success: true, changed: false, message: `Multus already installed (${MULTUS_VERSION})` };
+  }
+
+  const apply = await ctx.ssh.exec(
+    `${K} kubectl apply -f ${MULTUS_MANIFEST}`,
+    { ...sshOpts(ctx), timeoutMs: 120_000 },
+  );
+  if (apply.exitCode !== 0) {
+    return { success: false, changed: false, message: "Failed to apply Multus manifest", error: apply.stderr };
+  }
+
+  return { success: true, changed: true, message: `Installed Multus ${MULTUS_VERSION} (thick)` };
+};

bastion/src/modules/modules/k3s/src/operations/vlan-setup.ts

@@ -0,0 +1,96 @@
+// vlan-setup DaemonSet — the node-level half of the macvlan/VLAN-10 story.
+// On every node it (1) installs the reference CNI plugins (macvlan/ipvlan/
+// static/host-local/vlan/tuning) into /opt/cni/bin if missing, and (2) creates
+// a `lan10` VLAN-10 sub-interface on the primary NIC that macvlan
+// NetworkAttachmentDefinitions use as their master. Idempotent + self-healing
+// (re-creates lan10 if it disappears). Paired with Multus (multus.ts) + Cilium
+// bpf.vlanBypass={10} (cilium.ts).
+
+import type { Operation, OperationResult } from "../types.js";
+import { sshOpts } from "../utils.js";
+
+const MANIFEST = `apiVersion: v1
+kind: Namespace
+metadata:
+  name: macvlan-sys
+  labels:
+    pod-security.kubernetes.io/enforce: privileged
+    pod-security.kubernetes.io/audit: privileged
+    pod-security.kubernetes.io/warn: privileged
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: vlan-setup
+  namespace: macvlan-sys
+spec:
+  selector:
+    matchLabels: { app: vlan-setup }
+  template:
+    metadata:
+      labels: { app: vlan-setup }
+    spec:
+      hostNetwork: true
+      tolerations:
+      - operator: Exists
+      containers:
+      - name: vlan
+        image: nicolaka/netshoot
+        securityContext:
+          privileged: true
+        command:
+        - sh
+        - -c
+        - |
+          set -x
+          # install reference CNI plugins (macvlan/ipvlan/static/host-local) if missing
+          if [ ! -f /host/opt/cni/bin/macvlan ] || [ ! -f /host/opt/cni/bin/ipvlan ]; then
+            case "$(uname -m)" in x86_64) A=amd64;; aarch64) A=arm64;; *) A=amd64;; esac
+            curl -sSL "https://github.com/containernetworking/plugins/releases/download/v1.5.1/cni-plugins-linux-$A-v1.5.1.tgz" -o /tmp/cni.tgz
+            tar -xzf /tmp/cni.tgz -C /host/opt/cni/bin ./macvlan ./ipvlan ./static ./host-local ./vlan ./tuning
+          fi
+          # detect the primary NIC (default route dev, else the one holding 192.168.8.x)
+          NIC="$(ip -o -4 route show default 2>/dev/null | awk '{print $5; exit}')"
+          [ -z "$NIC" ] && NIC="$(ip -o -4 addr show 2>/dev/null | awk '/192\\.168\\.8\\./{print $2; exit}')"
+          echo "primary NIC = $NIC"
+          while true; do
+            if [ -n "$NIC" ]; then
+              ip link show lan10 >/dev/null 2>&1 || ip link add link "$NIC" name lan10 type vlan id 10
+              ip link set lan10 up
+              # NIC-driver workarounds for VLAN multicast RX
+              ip link set "$NIC" allmulticast on 2>/dev/null
+              ethtool -K "$NIC" rxvlan off rx-vlan-filter off 2>/dev/null
+            fi
+            sleep 30
+          done
+        volumeMounts:
+        - name: cnibin
+          mountPath: /host/opt/cni/bin
+      volumes:
+      - name: cnibin
+        hostPath:
+          path: /opt/cni/bin
+`;
+
+export const installVlanSetup: Operation = async (ctx): Promise<OperationResult> => {
+  const K = "KUBECONFIG=/etc/rancher/k3s/k3s.yaml";
+
+  const check = await ctx.ssh.exec(
+    `${K} kubectl -n macvlan-sys get ds vlan-setup -o name 2>/dev/null`,
+    sshOpts(ctx),
+  );
+  if (check.exitCode === 0 && check.stdout.includes("vlan-setup")) {
+    return { success: true, changed: false, message: "vlan-setup DaemonSet already installed" };
+  }
+
+  const b64 = Buffer.from(MANIFEST).toString("base64");
+  const apply = await ctx.ssh.exec(
+    `echo ${b64} | base64 -d | ${K} kubectl apply -f -`,
+    { ...sshOpts(ctx), timeoutMs: 60_000 },
+  );
+  if (apply.exitCode !== 0) {
+    return { success: false, changed: false, message: "Failed to apply vlan-setup DaemonSet", error: apply.stderr };
+  }
+
+  return { success: true, changed: true, message: "Installed vlan-setup DaemonSet (lan10 + CNI plugins)" };
+};

bastion/src/modules/modules/k3s/tests/install.test.ts

@@ -71,9 +71,14 @@ describe("k3s install script — server role", () => {
     expect(script).toContain("enable-admission-plugins=NodeRestriction,PodSecurity");
   });
 
-  it("configures audit logging", () => {
-    expect(script).toContain("audit-log-path=/var/log/kubernetes/audit.log");
-    expect(script).toContain("audit-log-maxage=30");
+  it("configures audit logging via journald (stdout)", () => {
+    expect(script).toContain("audit-log-path=-");
+    // file-based fields and the now-obsolete log directory must be gone
+    expect(script).not.toContain("/var/log/kubernetes/audit.log");
+    expect(script).not.toContain("audit-log-maxage");
+    expect(script).not.toContain("audit-log-maxbackup");
+    expect(script).not.toContain("audit-log-maxsize");
+    expect(script).not.toContain("mkdir -p /var/log/kubernetes");
   });
 
   it("cleans stale flannel vxlan before Cilium install", () => {

bastion/src/modules/modules/k3s/tests/operations.test.ts

@@ -348,3 +348,143 @@ describe("applyPodSecurityStandards", () => {
     expectCommand(ctx.ssh, "pod-security.kubernetes.io/audit=restricted");
   });
 });
+
+// --- Audit Logging Decommission (file-based → journald) ---
+
+import { configureLogRotation } from "../src/operations/log-rotation.js";
+import { configureJournaldLimits } from "../src/operations/journald-limits.js";
+
+describe("configureLogRotation (decommission file-based audit logs)", () => {
+  it("removes the legacy logrotate rule and reaps obsolete audit files", async () => {
+    const ctx = mockCtx();
+    ctx.ssh.exec.mockResolvedValueOnce(stdout("present")); // probe: legacy artifacts exist
+    ctx.ssh.exec.mockResolvedValue(OK);
+
+    const result = await configureLogRotation(ctx);
+
+    expect(result.success).toBe(true);
+    expect(result.changed).toBe(true);
+    expectCommand(ctx.ssh, "rm -f /etc/logrotate.d/k3s");
+    expectCommand(ctx.ssh, /find \/var\/log\/kubernetes.*audit.*-delete/);
+    expectCommand(ctx.ssh, "rmdir /var/log/kubernetes");
+  });
+
+  it("is a no-op when nothing legacy is present", async () => {
+    const ctx = mockCtx();
+    ctx.ssh.exec.mockResolvedValueOnce(stdout("absent"));
+    ctx.ssh.exec.mockResolvedValue(OK);
+
+    const result = await configureLogRotation(ctx);
+    expect(result.success).toBe(true);
+    expect(result.changed).toBe(false);
+  });
+});
+
+describe("configureJournaldLimits", () => {
+  it("writes a 2 GB SystemMaxUse drop-in and reloads journald when changed", async () => {
+    const ctx = mockCtx();
+    ctx.ssh.exec.mockResolvedValueOnce(stdout("__LABCTL_NOT_FOUND__")); // no existing drop-in
+    ctx.ssh.exec.mockResolvedValue(OK);
+
+    const result = await configureJournaldLimits(ctx);
+
+    expect(result.success).toBe(true);
+    expect(result.changed).toBe(true);
+    const writeCall = ctx.ssh.exec.mock.calls.find((c) => {
+      const cmd = c[0] as string;
+      return cmd.includes("10-k3s-audit-cap.conf") && cmd.includes("LABCTL_EOF");
+    });
+    expect(writeCall).toBeTruthy();
+    const written = writeCall?.[0] as string;
+    expect(written).toContain("SystemMaxUse=2G");
+    expect(written).toContain("SystemKeepFree=1G");
+    expectCommand(ctx.ssh, "systemctl restart systemd-journald");
+  });
+
+  it("does not restart journald when the drop-in is already correct", async () => {
+    const ctx = mockCtx();
+    const existing =
+      "[Journal]\nSystemMaxUse=2G\nSystemKeepFree=1G\nSystemMaxFileSize=200M\n";
+    ctx.ssh.exec.mockResolvedValueOnce(stdout(existing));
+    ctx.ssh.exec.mockResolvedValue(OK);
+
+    const result = await configureJournaldLimits(ctx);
+
+    expect(result.success).toBe(true);
+    expect(result.changed).toBe(false);
+    expectNoCommand(ctx.ssh, "systemctl restart systemd-journald");
+  });
+});
+
+// --- Etcd Recovery ---
+
+import { recoverEtcdMember } from "../src/operations/etcd-recover.js";
+import { mockSsh } from "./helpers.js";
+
+describe("recoverEtcdMember", () => {
+  it("refuses to operate when cluster is below 3 members (quorum risk)", async () => {
+    const broken = mockSsh();
+    const peer = mockSsh();
+    peer.exec.mockResolvedValueOnce(stdout("/usr/bin/etcdctl")); // etcdctl present
+    peer.exec.mockResolvedValueOnce(stdout(
+      "111, started, host-a-aaa, https://10.0.0.1:2380, https://10.0.0.1:2379, false\n" +
+      "222, started, host-b-bbb, https://10.0.0.2:2380, https://10.0.0.2:2379, false",
+    ));
+
+    const result = await recoverEtcdMember({ broken, peer, brokenHostname: "host-b" });
+
+    expect(result.success).toBe(false);
+    expect(result.message).toMatch(/quorum/i);
+    // Critically: must NOT have stopped k3s or removed anything
+    expect(broken.exec).not.toHaveBeenCalledWith(expect.stringContaining("systemctl stop k3s"), expect.anything());
+  });
+
+  it("performs full procedure when quorum is preserved", async () => {
+    const broken = mockSsh();
+    const peer = mockSsh();
+    // ensureEtcdctl: present
+    peer.exec.mockResolvedValueOnce(stdout("/usr/bin/etcdctl"));
+    // member list (3 members, target = host-b)
+    peer.exec.mockResolvedValueOnce(stdout(
+      "111, started, host-a-aaa, https://10.0.0.1:2380, https://10.0.0.1:2379, false\n" +
+      "222, started, host-b-bbb, https://10.0.0.2:2380, https://10.0.0.2:2379, false\n" +
+      "333, started, host-c-ccc, https://10.0.0.3:2380, https://10.0.0.3:2379, false",
+    ));
+    // member remove
+    peer.exec.mockResolvedValueOnce(stdout("Member 222 removed"));
+    // post-rejoin member list — new id 444 for host-b
+    peer.exec.mockResolvedValueOnce(stdout(
+      "111, started, host-a-aaa, https://10.0.0.1:2380, https://10.0.0.1:2379, false\n" +
+      "333, started, host-c-ccc, https://10.0.0.3:2380, https://10.0.0.3:2379, false\n" +
+      "444, started, host-b-zzz, https://10.0.0.2:2380, https://10.0.0.2:2379, false",
+    ));
+
+    const result = await recoverEtcdMember({ broken, peer, brokenHostname: "host-b" });
+
+    expect(result.success).toBe(true);
+    expect(result.removedMemberId).toBe("222");
+    expect(result.newMemberId).toBe("444");
+    expectCommand(broken,"systemctl stop k3s");
+    expectCommand(peer,"member remove 222");
+    expectCommand(broken,/db\.corrupt-/);
+    expectCommand(broken,/rm -rf .*\/server\/tls/);
+    expectCommand(broken,"systemctl start k3s");
+  });
+
+  it("fails clearly when no member matches the broken hostname", async () => {
+    const broken = mockSsh();
+    const peer = mockSsh();
+    peer.exec.mockResolvedValueOnce(stdout("/usr/bin/etcdctl"));
+    peer.exec.mockResolvedValueOnce(stdout(
+      "111, started, host-a-aaa, https://10.0.0.1:2380, https://10.0.0.1:2379, false\n" +
+      "222, started, host-b-bbb, https://10.0.0.2:2380, https://10.0.0.2:2379, false\n" +
+      "333, started, host-c-ccc, https://10.0.0.3:2380, https://10.0.0.3:2379, false",
+    ));
+
+    const result = await recoverEtcdMember({ broken, peer, brokenHostname: "host-d" });
+
+    expect(result.success).toBe(false);
+    expect(result.message).toMatch(/No etcd member found/);
+    expect(broken.exec).not.toHaveBeenCalledWith(expect.stringContaining("systemctl stop k3s"), expect.anything());
+  });
+});

bastion/src/shared/src/hardware/index.ts

@@ -0,0 +1,154 @@
+// Architecture normalisation and machine classification.
+//
+// Both are derived from what the system already observes about a machine -- never from
+// an operator-supplied flag.
+
+import type { Arch, HardwareInfo, OnboardMethod, OsId } from "../types/index.js";
+
+export const SUPPORTED_ARCHES: readonly Arch[] = ["x86_64", "aarch64"] as const;
+
+/**
+ * Normalise an architecture string to one we serve boot artifacts for.
+ *
+ * Sources and their spellings:
+ *   uname -m         -> "x86_64" / "aarch64"
+ *   iPXE ${buildarch}-> "x86_64" / "arm64"
+ *   dpkg/Debian      -> "amd64"  / "arm64"
+ *
+ * Returns undefined for anything we don't serve, so callers fall back rather than
+ * inventing a kernel path that would 404.
+ */
+export function normalizeArch(value: string | undefined | null): Arch | undefined {
+  switch ((value ?? "").trim().toLowerCase()) {
+    case "x86_64":
+    case "x86-64":
+    case "amd64":
+      return "x86_64";
+    case "aarch64":
+    case "arm64":
+      return "aarch64";
+    default:
+      return undefined;
+  }
+}
+
+/** Fedora pxeboot artifact base URL for an architecture. */
+export function fedoraMirrorFor(fedoraVersion: string, arch: Arch): string {
+  return `https://download.fedoraproject.org/pub/fedora/linux/releases/${fedoraVersion}/Everything/${arch}/os`;
+}
+
+/**
+ * Which architectures each OS in the pipeline can actually be installed on.
+ *
+ * Fedora publishes pxeboot vmlinuz/initrd for both. Ubuntu does not: as of 26.04,
+ * releases.ubuntu.com publishes amd64 artifacts only, so there is nothing to netboot an
+ * arm64 machine with. Claiming support would fail at download time with a 404 instead
+ * of a useful message.
+ */
+const OS_ARCH_SUPPORT: Record<OsId, readonly Arch[]> = {
+  "fedora-43": ["x86_64", "aarch64"],
+  "ubuntu-26.04": ["x86_64"],
+};
+
+export function osSupportsArch(os: OsId, arch: Arch): boolean {
+  return (OS_ARCH_SUPPORT[os] ?? []).includes(arch);
+}
+
+export function archesForOs(os: OsId): readonly Arch[] {
+  return OS_ARCH_SUPPORT[os] ?? [];
+}
+
+/**
+ * Machines that run a vendor OS we have no image for.
+ *
+ * These are SSH-onboard: we manage userspace, but reinstalling destroys a driver and
+ * firmware stack our pipeline cannot rebuild. Matched on DMI identity, which is what
+ * discovery and `provision recheck` both collect.
+ *
+ * This is deliberately a property of the machine ("it runs DGX OS"), not a blocklist
+ * ("never install this MAC"). When a DGX OS image joins the pipeline, teaching the
+ * installer about vendor_os "dgx-os" is what unblocks these machines -- no entry here
+ * needs deleting.
+ */
+interface VendorOsRule {
+  vendorOs: string;
+  description: string;
+  matches: (hw: DmiIdentity) => boolean;
+}
+
+interface DmiIdentity {
+  manufacturer: string;
+  product: string;
+  board: string;
+}
+
+const VENDOR_OS_RULES: readonly VendorOsRule[] = [
+  {
+    vendorOs: "dgx-os",
+    description: "NVIDIA DGX OS (proprietary driver + firmware stack, no image in our pipeline)",
+    matches: ({ manufacturer, product, board }) =>
+      (manufacturer.includes("nvidia") || product.includes("nvidia")) &&
+      (product.includes("dgx") || product.includes("spark") ||
+       board.includes("gb10") || product.includes("gb10")),
+  },
+];
+
+/**
+ * Machines known to run a vendor OS, by MAC.
+ *
+ * The DMI rules above only fire once discovery or `provision recheck` has populated a
+ * hardware record. Machines onboarded over SSH may sit in state for a long time with no
+ * DMI at all -- which is exactly the state both DGX Sparks are in today -- so a
+ * DMI-only classifier would fail open on the machines this guard exists to protect.
+ *
+ * This is a statement of fact about known hardware ("this box runs DGX OS"), not an
+ * install policy. Whether that means "refuse" is decided by whether the pipeline has an
+ * image for that vendor OS.
+ */
+const KNOWN_VENDOR_OS_MACS: Record<string, string> = {
+  "4c:bb:47:7f:29:35": "dgx-os",  // spark-2935
+  "48:21:0b:96:3a:1c": "dgx-os",  // spark-3a1c
+};
+
+/**
+ * Classify how a machine should be onboarded, from its hardware record.
+ *
+ * An explicit `onboard` already on the record wins: it may have been set by an operator
+ * or by a rule that has since changed, and silently overriding it would be worse than
+ * leaving it.
+ */
+export function classifyOnboard(
+  hw: Partial<Pick<HardwareInfo, "mac" | "manufacturer" | "product" | "board">>
+    & { onboard?: OnboardMethod; vendor_os?: string },
+): { onboard: OnboardMethod; vendor_os?: string } {
+  if (hw.onboard !== undefined) {
+    return hw.vendor_os !== undefined
+      ? { onboard: hw.onboard, vendor_os: hw.vendor_os }
+      : { onboard: hw.onboard };
+  }
+
+  const knownVendorOs = KNOWN_VENDOR_OS_MACS[(hw.mac ?? "").toLowerCase().replace(/-/g, ":")];
+  if (knownVendorOs !== undefined) {
+    return { onboard: "ssh", vendor_os: knownVendorOs };
+  }
+
+  const identity: DmiIdentity = {
+    manufacturer: (hw.manufacturer ?? "").toLowerCase(),
+    product: (hw.product ?? "").toLowerCase(),
+    board: (hw.board ?? "").toLowerCase(),
+  };
+
+  for (const rule of VENDOR_OS_RULES) {
+    if (rule.matches(identity)) {
+      return { onboard: "ssh", vendor_os: rule.vendorOs };
+    }
+  }
+
+  return { onboard: "pxe" };
+}
+
+/** Human-readable reason a vendor-OS machine must not be reinstalled. */
+export function vendorOsDescription(vendorOs: string | undefined): string {
+  const rule = VENDOR_OS_RULES.find((r) => r.vendorOs === vendorOs);
+  return rule?.description ?? "a vendor OS with no image in our pipeline";
+}

bastion/src/shared/src/index.ts

@@ -1,6 +1,8 @@
 export type {
   OsId,
   Arch,
+  OnboardMethod,
+  RootCandidate,
   Role,
   HardwareInfo,
   InstallConfig,
@@ -10,6 +12,16 @@ export type {
   BastionConfig,
 } from "./types/index.js";
 
+export {
+  SUPPORTED_ARCHES,
+  normalizeArch,
+  fedoraMirrorFor,
+  osSupportsArch,
+  archesForOs,
+  classifyOnboard,
+  vendorOsDescription,
+} from "./hardware/index.js";
+
 export { SUPPORTED_OS, SUPPORTED_ROLES, ROLE_REGISTRY, isValidOsId } from "./types/index.js";
 export type { RoleInfo } from "./types/index.js";
 

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

@@ -111,7 +111,9 @@ 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 }
+  | { type: "command-debug"; requestId: string; mac: string; pxeBoot?: boolean }
+  | { type: "command-register"; requestId: string; mac: string; hostname: string; role: string; ip: string }
+  | { type: "command-discover"; requestId: string; mac: string; product?: string; board?: string; serial?: string; manufacturer?: string; cpu_model?: string; cpu_cores?: number; memory_gb?: number; arch?: string; disks?: Array<{ name: string; size_gb: number; model: string }>; nics?: Array<{ name: string; mac: string; state: string }>; root_device?: string; root_args?: string }
   | { type: "server-shutdown"; reconnectAfter: number };
 
 export type BastionMessageType = BastionMessage["type"];
@@ -126,7 +128,7 @@ const BASTION_MESSAGE_TYPES = new Set<string>([
 
 const LABD_BASTION_MESSAGE_TYPES = new Set<string>([
   "bastion-enrolled", "bastion-heartbeat-ack", "command-install",
-  "command-forget", "command-role-update", "command-debug", "server-shutdown",
+  "command-forget", "command-role-update", "command-debug", "command-register", "command-discover", "server-shutdown",
 ]);
 
 export function isBastionMessage(msg: unknown): msg is BastionMessage {