update default editor

Updates mount-pxe-images.nix to mount pxe-boot/images from
ha-vip-lan.sweet.home (Pacemaker vip-lan, 192.168.2.229) instead of
server.sweet.home. Storage root changes from /tank to haStorageRoot
(/srv/ha-data). NFSv3+nolock options for LXC are unchanged.

Removes nfsServerHost and storageRoot from variables.nix — all NFS
clients now reference the HA cluster directly (docker via haStorageNfsFqdn
on VLAN 20, pxe-boot via ha-vip-lan on VLAN 2). Updates the nfsShares
comment to reflect the new single-source-of-truth role without the
dead server.nix references.

DNS records for server.sweet.home and server.storage.home were already
cleaned up automatically by IPA dynamic DNS when the VM was deleted.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8djTWdXVzXZc99iujU6T2

.gitea/workflows/check-nixos.yml

@@ -13,17 +13,17 @@ jobs:
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Install Nix
         uses: DeterminateSystems/nix-installer-action@v19
 
-      - name: Evaluate all NixOS hosts
+      # Scoped to files changed since the PR base / previous push -- see
-        run: |
+      # scripts/codex-maintenance.sh. CI never passes --full-check: that
-          set -euo pipefail
+      # full sweep is for local/manual use, since it's slow enough to time
-          hosts="$(nix --extra-experimental-features 'nix-command flakes' eval --json \
+      # out this runner.
-            .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]')"
+      - name: Run maintenance checks (secrets, fmt, lint, eval -- changed files only)
-          for host in $hosts; do
+        env:
-            echo "Evaluating ${host}"
+          MAINT_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
-            nix --extra-experimental-features 'nix-command flakes' eval \
+        run: bash scripts/codex-maintenance.sh
-              ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath" --raw
-          done

.github/workflows/check-nixos.yml

@@ -13,17 +13,17 @@ jobs:
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Install Nix
         uses: DeterminateSystems/nix-installer-action@v19
 
-      - name: Evaluate all NixOS hosts
+      # Scoped to files changed since the PR base / previous push -- see
-        run: |
+      # scripts/codex-maintenance.sh. CI never passes --full-check: that
-          set -euo pipefail
+      # full sweep is for local/manual use, since it's slow enough to time
-          hosts="$(nix --extra-experimental-features 'nix-command flakes' eval --json \
+      # out this runner.
-            .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]')"
+      - name: Run maintenance checks (secrets, fmt, lint, eval -- changed files only)
-          for host in $hosts; do
+        env:
-            echo "Evaluating ${host}"
+          MAINT_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
-            nix --extra-experimental-features 'nix-command flakes' eval \
+        run: bash scripts/codex-maintenance.sh
-              ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath" --raw
-          done

.gitignore

@@ -3,13 +3,25 @@
 result
 result-*
 
+# Disko's proxmox-* image-builder writes the finished .raw disk image
+# directly into the current directory, not into a result-* symlink (see
+# docs/proxmox-images.md, scripts/create-proxmox-resource.sh) — several GB
+# each, never meant to be committed.
+*.raw
+
 # Ignore automatically generated direnv output
 .direnv
 
-auto-installer/flake.lock
+# Python bytecode cache (scripts/lib/*.py)
-auto-installer/result
+__pycache__/
-auto-installer/nixos-auto.iso
+*.pyc
+
+# Locally-generated SSH host keys staged for transfer to a new machine
+# during install (see scripts/prepare-host-key.sh) — never commit these.
+host-keys/
 
 # Temporary Milestone 1 audit checklist (remove-sensetive-info-refactor.md)
 # - working notes only, never committed, deleted once every row is rotated.
 secrets-inventory.md
+.claude/worktrees/                                                                                                  
+.claude/settings.local.json 

.sops.yaml

@@ -1,8 +1,26 @@
 keys:
-  - &admin age10nd382a9klsn2mrs60emdtsxe43pht3a0m9p29phfrhy0wfyt3vsq9r667
+  - &admin age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
-  - &docker age19gfn2yedg76dmztm4hncr7vf3r3c9j0qpt4rap7y7gersjk4m3ks2lhd0e
+  - &proxmox-minimal age19m0m7vdfg86yqy8l5mmle5jdd0unrn3f55t232w8h5ey42cqw34sfpt32n
-  - &server age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
+  - &lxc-gui age1rrxqea6q6pn39sw8y5te63h2py8jgjl9v0jyper86w3ggtn67upqg3ah39
-  - &nix-cache age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
+  - &baremetal-gui age1adur9g330gua4l6ndk8cqjg35qc8yxwgme6wrl2hpylcc7vxm38q05ejuy
+  - &linode-docker age17e89ty6p0fw24daanen57wg8uald9s025t3wwxsw269svwpmgvrshfvfvt
+  - &linode-gui age1hrx8qj02fj2ea6d4g9vqhyj9hl7fppkjqfdx2l37py3h6pdkr95s8n8rvs
+  - &linode-minimal age1e7l8dusgmgfzd2cxrrzwepzjxt69hzqj4epee0cs27u6yg4kxcuqm34ncx
+  - &linode-nix-cache age1jcx3yajjhghn8qh8za3yeu8nxykzlg3p4nrv03vnfvzl0mzayg2qmg940e
+  - &linode-tailscale-router age1f7usptjx9rv4rxauasve200gxtdt9jkqhhdqstlf20wvlm7u75rsjfw50m
+  - &lxc-docker age17jqc66x9yeshfgd9v78mj483r4zzarqdtuxtrkxe4x5mw679gphshd94th
+  - &lxc-minimal age1px0h5l9zp2dww0m8fncrc82kfdmzplsfv2ltat7sna28xpg09pqqcl3s2k
+  - &lxc-nix-cache age1ufg390ydrmma849t9xfkxxl5xvdkk6mngnlzhmy7mvuaje8sgcmsmnq6l7
+  - &lxc-pxe-boot age16j42pdc5dr6wnj7xayhkqdj2rny9u68fcqejs50hqq42scssh4gsnrrnlt
+  - &lxc-tailscale-router age1k7d2du5mejsmv5rzavm4xwgpthqvcfsehduquv28nzs53zppa3kqngfxq2
+  - &lxc-tor-relay age16kqfmvz4e23hmdlqresnyw69ej604s320mmd49h4hm3fhqchtgyqrws0k2
+  - &proxmox-docker age1arhf2q45zw6wf2uevju4savp575x3m2tfvved5zzq3ay92ynua9s3cm92c
+  - &proxmox-gui age19mn8zrxl8zpps9yvrh4euquvygpp4fp8queg7xc6qhtnl4ng8c9qx02qwn
+  - &proxmox-nix-cache age1jlltcv5jcnm40z5k0q6hv053k2rqpqvemtuecdwn527uw8uqz4es3x7m68
+  - &proxmox-pxe-boot age1ug787sgt6st6k82fgkrug2lzltw4qsukrrqqs3w27ewwqj8rg4hsxcmylz
+  - &proxmox-tailscale-router age1zhfyuzlq40reuqlr34gf77852nhs3t6mqfzrqmas8z6sxk7tcfhsungrm0
+  - &proxmox-ha-server-1 age1k73g8x47hs93wcv7qh92n3htz8pl295g49hyvlrf3570mts0hgys5g04d6
+  - &proxmox-ha-server-2 age1fefy6dk8zn5c3edwmrs9vwx79quftnt784m628t9e34q3ft3cehqz8u72r
 
 creation_rules:
   # Shared across every currently-deployed host: root/nixos password hash,
@@ -13,24 +31,171 @@ creation_rules:
     key_groups:
       - age:
           - *admin
-          - *docker
+          - *proxmox-minimal
-          - *server
+          - *lxc-gui
-          - *nix-cache
+          - *baremetal-gui
+          - *linode-docker
+          - *linode-gui
+          - *linode-minimal
+          - *linode-nix-cache
+          - *linode-tailscale-router
+          - *lxc-docker
+          - *lxc-minimal
+          - *lxc-nix-cache
+          - *lxc-pxe-boot
+          - *lxc-tailscale-router
+          - *lxc-tor-relay
+          - *proxmox-docker
+          - *proxmox-gui
+          - *proxmox-nix-cache
+          - *proxmox-pxe-boot
+          - *proxmox-tailscale-router
+          - *proxmox-ha-server-1
+          - *proxmox-ha-server-2
 
   - path_regex: secrets/nix-cache\.yaml$
     key_groups:
       - age:
           - *admin
-          - *nix-cache
+          - *linode-nix-cache
+          - *lxc-nix-cache
+          - *proxmox-nix-cache
 
-  - path_regex: secrets/server\.yaml$
+  - path_regex: secrets/tor-relay\.yaml$
     key_groups:
       - age:
           - *admin
-          - *server
+          - *lxc-tor-relay
 
-  - path_regex: secrets/docker\.yaml$
+  - path_regex: secrets/tailscale-router\.yaml$
     key_groups:
       - age:
           - *admin
-          - *docker
+          - *linode-tailscale-router
+          - *lxc-tailscale-router
+          - *proxmox-tailscale-router
+
+  # HA file server per-node secrets (beszel-token).
+  # proxmox-ha-server-1 / proxmox-ha-server-2 keys are added automatically
+  # by scripts/secrets/sync-host-keys.sh once the hosts are provisioned;
+  # until then only the admin key can decrypt these files.
+  - path_regex: secrets/ha-server-1\.yaml$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-server-1
+          # proxmox-ha-server-1 added by sync-host-keys.sh
+
+  - path_regex: secrets/ha-server-2\.yaml$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-server-2
+          # proxmox-ha-server-2 added by sync-host-keys.sh
+
+  # Shared HA cluster corosync authkey (binary sops file).
+  # Encrypted for both HA nodes so either can decrypt on boot.
+  # Both host keys added by sync-host-keys.sh; admin key allows initial creation.
+  - path_regex: secrets/ha-corosync-authkey$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-server-1
+          - *proxmox-ha-server-2
+          # proxmox-ha-server-1 added by sync-host-keys.sh
+          # proxmox-ha-server-2 added by sync-host-keys.sh
+
+  # gui-host-specific secrets (currently: wifi-password, see
+  # modules/networking/wifi.nix). Only *lxc-gui has a registered key today
+  # -- proxmox-gui/linode-gui/baremetal-gui haven't been provisioned via
+  # scripts/secrets/sync-host-keys.sh yet, so whichever variant is actually
+  # deployed next needs its recipient added here (and `sops updatekeys` rerun)
+  # before it can decrypt this.
+  - path_regex: secrets/gui\.yaml$
+    key_groups:
+      - age:
+          - *admin
+          - *lxc-gui
+          - *baremetal-gui
+          - *linode-gui
+          - *proxmox-gui
+
+  # IPA host keytabs (binary sops files).
+  # Each keytab is encrypted for all platform variants of that host so any
+  # deployed variant can decrypt it at boot. Run
+  # scripts/ipa/create-nixos-ipa-host-account.sh <hostname> to enroll a new
+  # host and produce the keytab; this section is updated by that script.
+
+  - path_regex: secrets/nix-cache\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *linode-nix-cache
+          - *lxc-nix-cache
+          - *proxmox-nix-cache
+
+  - path_regex: secrets/tailscale-router\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *linode-tailscale-router
+          - *lxc-tailscale-router
+          - *proxmox-tailscale-router
+
+  - path_regex: secrets/pxe-boot\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *lxc-pxe-boot
+          - *proxmox-pxe-boot
+
+  # nixos = the workstation (hosts/nixos/host.nix). All gui platform variants
+  # share the hostname "nixos" and must be able to decrypt at boot.
+  - path_regex: secrets/nixos\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *baremetal-gui
+          - *lxc-gui
+          - *proxmox-gui
+          - *linode-gui
+
+  - path_regex: secrets/docker\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *linode-docker
+          - *lxc-docker
+          - *proxmox-docker
+
+  - path_regex: secrets/tor-relay\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *lxc-tor-relay
+
+  - path_regex: secrets/nix-minimal\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *lxc-minimal
+          - *proxmox-minimal
+          - *linode-minimal
+
+  # Host keytab for ha-server-1 FreeIPA enrollment (binary sops file).
+  # Generated by scripts/ipa/create-nixos-ipa-host-account.sh.
+  - path_regex: secrets/ha-server-1\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-server-1
+          # proxmox-ha-server-1 added by sync-host-keys.sh
+
+  # Host keytab for ha-server-2 FreeIPA enrollment (binary sops file).
+  # Generated by scripts/ipa/create-nixos-ipa-host-account.sh.
+  - path_regex: secrets/ha-server-2\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-server-2
+          # proxmox-ha-server-2 added by sync-host-keys.sh

AGENTS.md

@@ -6,12 +6,14 @@ This repository contains flake-based NixOS configurations for Wayne's LAN
 servers and workstation.
 
 The flake exposes NixOS configurations named `<platform>-<buildtype>`
-(platforms: `linode`, `proxmox`, `lxc`; build types: `minimal`, `nix-cache`,
+(platforms: `linode`, `proxmox`, `lxc`, `baremetal`; build types: `minimal`,
-`server`, `docker`, `gui`, `pxe-boot`), generated from `modules/platforms/*`
+`nix-cache`, `server`, `docker`, `gui`, `pxe-boot`, `tailscale-router`,
-and `modules/build-types/*` by the `mkTarget` function in `flake.nix`. Not
+`tor-relay`, `ha-server`), generated from `modules/platforms/*` and
-every combination is built — `pxe-boot` has no `linode` variant. See
+`modules/build-types/*` by the `mkTarget` function in `flake.nix`. Not every
-`README.md` for the full current target list; treat `flake.nix` as the
+combination is built — `pxe-boot` has no `linode` variant, `ha-server` only
-source of truth since this list can drift.
+exists on `proxmox`, and `tor-relay` only exists on `lxc`. See `README.md`
+for the full current target list; treat `flake.nix` as the source of truth
+since this list can drift.
 
 Do not deploy, switch, reboot, repartition, format disks, or run destructive
 install commands from this repository unless explicitly asked.
@@ -35,9 +37,14 @@ Use these commands when validating changes:
 ```bash
 bash scripts/codex-setup.sh
 bash scripts/codex-maintenance.sh
-bash scripts/codex-maintenance.sh dry-run
 ```
 
+With no flags, `codex-maintenance.sh` scopes fmt-check/statix/eval to files
+changed against a base ref — this is what CI runs on every push/PR. For the
+full sweep (every host, every package — slow; CI never runs this), use
+`bash scripts/codex-maintenance.sh --full-check` (add `--dry-run` for build
+planning on top of whichever scope is active).
+
 Host evaluation is safe when limited to drvPath checks:
 
 ```bash

AUDIT_REPORT.md

@@ -0,0 +1,150 @@
+# Flake End-to-End Audit Report
+
+**Date:** 2026-07-21
+**Scope:** Full static lint/eval sweep + live build/deploy/interrogate/destroy testing of every `lxc-*` and `proxmox-*` flake target against `pve.sweet.home`, plus an audit of the operator's ability to manage the flake/secrets tooling.
+**Branch:** `worktree-flake-e2e-audit` (this session's isolated worktree)
+
+## Executive Summary
+
+The flake itself is in good shape: `nixpkgs-fmt`, `statix`, and a full eval + dry-run build of every host and package are all clean. Every `lxc-*`/`proxmox-*` target's NixOS configuration builds successfully — no target has a broken derivation graph.
+
+The issues found are **operational, not code-level**:
+
+1. **pve.sweet.home is critically low on disk space** (91-95% full during this session) and cannot currently build the two largest closures (`gui`, `pxe-boot`) to completion — this actively blocks deploying/redeploying those hosts via the documented workflow.
+2. **A real, reproducible secrets-decryption failure** was caught live: a stale cached container image (built before a same-day sops-key fix) boots with sshd never starting and every secret failing to decrypt. This is a **general hazard in `create-proxmox-resource.sh`'s "reuse the cached image if present" default**, not a one-off.
+3. **sops key/anchor drift**: `proxmox-minimal` has a `.sops.yaml` recipient anchor with no corresponding private key anywhere in this environment; several `lxc-*`/`proxmox-*` targets have no sops registration at all yet.
+4. One concrete script bug was found and **fixed in this session**: `create-proxmox-resource.sh` never enabled the QEMU guest agent channel on VMs it creates, despite the guest OS already running it.
+5. A management-surface audit (of the operator's ability to run this repo day to day) found 5 process gaps, detailed below.
+
+Nothing here required or received a `nixos-rebuild switch/boot/test`, `nixos-install`, or any disk-formatting command — all validation was `nix build`/`nix eval`, plus disposable `pct`/`qm` create-then-destroy cycles via the repo's own `create-proxmox-resource.sh`.
+
+---
+
+## 1. Static Analysis Results — all clean
+
+`bash scripts/codex-maintenance.sh --full-check --dry-run` (whole-tree sweep, not just changed files):
+
+| Check | Result |
+|---|---|
+| Secret grep | Clean — only the documented exceptions (installer's own hashed passwords, `access-tokens` comment references) |
+| `nixpkgs-fmt --check` | 0/53 files would be reformatted |
+| `statix` | No lint warnings |
+| nix-cache host key drift check | Up to date |
+| Full eval of every host's `system.build.toplevel` | All 19 `nixosConfigurations` targets evaluate cleanly |
+| Dry-run build of every host + package | All succeed, no derivation errors |
+
+No drift, no formatting issues, no lint findings anywhere in the tree.
+
+---
+
+## 2. Per-Target Test Results
+
+Legend: **LIVE** = built on pve, `pct`/`qm` create → interrogated → destroyed. **BUILD-ONLY** = `nix build` validated the config (mostly `.config.system.build.toplevel`, occasionally `.tarball`), no resource created on pve.
+
+| Target | Test type | Result | Notes |
+|---|---|---|---|
+| `lxc-docker` | BUILD-ONLY | ✅ PASS | Live redeploy skipped — CT105 is already running this identity in production; `--allow-duplicate-host` would have destroyed it. |
+| `lxc-minimal` | **LIVE** | ✅ PASS (after retry) | First attempt reused a stale cached tarball predating a same-day sops-key commit → activation failed, sshd never started (see Finding #2). Redeployed with `--force-rebuild`: clean boot, `systemctl is-system-running` = `running`, secrets decrypted, sshd listening, users correct. |
+| `lxc-nix-cache` | BUILD-ONLY | ✅ PASS (after retry) | Live redeploy skipped — CT101 is already running this identity. First local build attempt appeared to hang on a remote-builder handoff to nix-cache; killed and retried with `--builders ""` (local-only), succeeded. |
+| `lxc-gui` | **LIVE (attempted)** | ⚠️ BLOCKED by pve disk space | Registered a fresh sops key (no prior registration existed), built successfully through the full NixOS system closure, then **failed packaging the tarball**: `No space left on device` on pve's root filesystem. Not a flake defect. |
+| `lxc-pxe-boot` | **LIVE (attempted)** | ⚠️ BLOCKED by pve disk space | Same failure as `lxc-gui` — this target additionally builds a full nested installer/netboot image (`stage-installer-artifacts.nix`), making it similarly large. Failed with the same `No space left on device` error, immediately after the gui attempt had already consumed pve's remaining headroom. |
+| `lxc-server` | BUILD-ONLY | ✅ PASS | No sops key registered yet; live deploy also would have hit `boot.zfs.extraPools` trying to import a real ZFS pool that doesn't exist in an isolated test container — an expected limitation of testing this build type outside its real hardware, not a bug. |
+| `lxc-tailscale-exit-node` | BUILD-ONLY | ✅ PASS | No sops key registered yet. |
+| `lxc-tor-relay` | BUILD-ONLY | ✅ PASS | Live redeploy skipped — CT106 already holds this identity in production. |
+| `proxmox-docker` | BUILD-ONLY | ✅ PASS (after retry) | Live redeploy skipped — both CT105 *and* VM103 already hold `docker` identities. Combined `toplevel` + `diskoImagesScript` build crashed with a **Nix-internal assertion failure** (`worker.cc:360`) under this session's memory pressure (see Finding #6) — not a flake bug. Retried with `toplevel` alone: clean. |
+| `proxmox-minimal` | **LIVE (attempted)** | ⚠️ BLOCKED by key drift → BUILD-ONLY | `.sops.yaml` has a registered `&proxmox-minimal` anchor but **no corresponding private key exists anywhere in this environment** — the script correctly refused to generate a mismatched replacement. Fell back to `toplevel` build: ✅ PASS. |
+| `proxmox-nix-cache` | BUILD-ONLY | ✅ PASS | No sops key registered yet. |
+| `proxmox-gui` | BUILD-ONLY | ⚠️ Killed after ~40min (resource-limited) | This session's local build machine has only 2GB RAM; swap filled completely (2.0/2.0GB) and the build stalled, so it was killed rather than risk destabilizing the session further. **Not a flake defect** — the equivalent `gui` NixOS configuration already proved fully buildable during the `lxc-gui` live attempt above (it built the entire system closure successfully and only failed at the pve-side tarball-packaging step due to disk space, not the config). |
+| `proxmox-pxe-boot` | BUILD-ONLY | ⚠️ Killed after ~35min (resource-limited) | Was deep into building the nested installer's kernel initrd (this build type bundles a full netboot installer image via `stage-installer-artifacts.nix`) when killed to keep the audit moving. **Not a flake defect** — this target's own module logic was already effectively validated via the earlier *live* pve deploy attempt (`lxc-pxe-boot` above), which built the complete image and only failed at the final tarball-packaging step due to pve's disk space (Finding 1). |
+| `proxmox-server` | BUILD-ONLY | ✅ PASS | No sops key registered yet; same ZFS-pool caveat as `lxc-server` would apply to a live deploy. |
+| `proxmox-tailscale-exit-node` | BUILD-ONLY | ✅ PASS | No sops key registered yet. |
+
+**Not tested at all:** `linode-*` targets (not deployable to Proxmox) and `installer` (not a normal host) — both were still covered by the static eval/dry-run-build sweep above.
+
+---
+
+## 3. Findings, Ranked by Severity
+
+### Finding 1 — pve.sweet.home is critically low on disk space (blocks real deployments)
+
+At session start: `/dev/mapper/pve-root` was **95% full, 5.3GB free** (of 94GB). After two failed large builds it recovered slightly to **91% full, 8.2GB free** (nix cleans up its own failed-build scratch space). `/nix/store` alone is 26GB; `nix-store --gc --print-dead` reports **zero** reclaimable garbage — everything currently in the store is a live GC root, so `nix-collect-garbage` won't help without first removing old roots.
+
+**Why it matters:** `create-proxmox-resource.sh` builds every VM/CT image **directly on pve**, not on a build machine and transferred over. With <10GB headroom, any closure approaching a few GB (the `gui` build type: full Cinnamon desktop + Firefox + LibreOffice + GIMP + VS Code + xrdp; the `pxe-boot` build type: nginx/atftpd *plus* an entire nested installer/netboot image) cannot currently be built there at all. Both `lxc-gui` and `lxc-pxe-boot` failed live with `No space left on device` during this audit.
+
+**Recommended action:** Expand `pve-root`'s LV, or free space by pruning old container templates in `/var/lib/vz/template/cache` (1.5GB) / old backups in `/var/lib/vz/dump` (306MB) / auditing what's pinning 26GB of `/nix/store` as live GC roots (likely `result-*` symlinks — see below). This is real production disk state; **not something this session touched or fixed** — it needs the operator's judgment on what's safe to remove.
+
+**Secondary, smaller finding:** every `create-proxmox-resource.sh` run leaves a `result-<target>` symlink in the node's repo checkout as a permanent GC root (`ls /root/nixos/result-*` on pve showed 3 from this session alone: `lxc-docker`, `lxc-minimal`, `lxc-nix-cache`). These accumulate forever and pin their entire closures in the store. Consider having the script clean up its own `result-*` link after staging the built artifact (or use a temp `--out-link` under `/tmp`), so `nix-collect-garbage` can actually reclaim old build outputs.
+
+### Finding 2 — Stale cached images can silently ship broken secrets (reproduced live)
+
+`create-proxmox-resource.sh`'s default behavior is: if the node already has `<target>.tar.xz`/`.raw` staged, **reuse it** — only `--force-rebuild` forces a fresh build. This session hit exactly the failure mode `docs/auto-installer.md` already warns about: `lxc-minimal`'s cached tarball (built 2026-07-20T15:57Z) predated a same-day sops-key fix commit (2026-07-20T17:49Z, "clean up in ailse 3"). The deployed container booted with:
+
+```
+sops-install-secrets: failed to decrypt '.../common.yaml': Error getting data key: 0 successful groups required, got 0
+Activation script snippet 'setupSecrets' failed (1)
+```
+
+— every secret permanently failed to decrypt, `sshd` never started (though the container otherwise looked "running"). This was **not a code bug**: the currently-committed `secrets/common.yaml` decrypts fine for that host's key when checked independently; the *cached artifact on pve* simply reflected an older commit's ciphertext. Redeploying with `--force-rebuild` fixed it immediately.
+
+**Why it matters:** this is silent and easy to trigger by accident — any operator who redeploys a host without remembering `--force-rebuild` after a secrets change gets a container that looks like it started (`pct start` succeeds, `pct status` = running) but is completely inaccessible.
+
+**Recommended action:** Have `create-proxmox-resource.sh` compare the cached image's build timestamp (or embed the source commit hash in the staged filename) against current HEAD, and warn (or refuse without `--force-rebuild`) if they differ — rather than silently trusting presence alone.
+
+### Finding 3 — sops key/anchor drift
+
+Two concrete instances hit live during this session:
+
+- **`proxmox-minimal`**: `.sops.yaml` already has a registered `&proxmox-minimal` age recipient, but this environment's `host-keys/` directory has no corresponding private key file. `sync-host-keys.sh` correctly refused to generate a replacement (it would silently mismatch whatever's already registered/deployed) — but this means **no environment currently has this host's private key**, unless it exists on some other machine that was never backed up here.
+- **`lxc-gui`**, and by the same logic `lxc-server`/`lxc-tailscale-exit-node`/most `proxmox-*` targets, have **no sops registration at all yet** — expected for undeployed hosts per `docs/auto-installer.md`, but this session's live-testing needed to register `lxc-gui`'s key on the fly, which immediately hit **Finding 3b**: registering a key locally does nothing for pve's build until it's pushed to `origin/main` (pve builds via `git pull`, not from this uncommitted worktree). This is exactly gap #4 the management-surface audit (below) already flagged in the abstract — this session hit it concretely.
+
+**Recommended action:** for `proxmox-minimal`, decide whether to regenerate its key (destroying old-key decrypt access, if anything still holds it) or track down wherever the original private key lives and back it up here. For the general pattern, see the management-surface audit's recommendation to pre-flight-check key registration before building.
+
+### Finding 4 — QEMU guest agent never wired up (found and fixed this session)
+
+`modules/common/configuration.nix:44` sets `services.qemuGuest.enable = true` on every host — the guest-side agent daemon is correctly enabled everywhere. But `scripts/proxmox/create-proxmox-resource.sh`'s `qm create` call never passed `--agent 1`, so **Proxmox never created the virtio-serial channel** the agent needs. Every `proxmox-*` VM this script ever created was silently missing `qm guest exec`/IP-address reporting in the Proxmox UI, despite the guest daemon actually running.
+
+**Status: fixed in this session's worktree** (`scripts/proxmox/create-proxmox-resource.sh`, `qm create` now includes `--agent enabled=1`) — see the diff, included in the PR from this session.
+
+### Finding 5 — Orphaned container on pve (CT102)
+
+`pve.sweet.home` has a stopped LXC container, **VMID 102**, with an essentially empty config (`lock: create` and nothing else — no hostname, no rootfs, no network) — the leftover of a `pct create` that started and never finished. It predates this session (not created by any of this audit's activity) and wasn't touched. **Recommend the operator confirm it's abandoned and remove it** (`pct destroy 102 --purge 1`) — left as-is it may be someone's genuine in-progress work, so it wasn't assumed safe to delete autonomously.
+
+### Finding 6 — Nix-internal crash under memory pressure (tooling, not flake)
+
+Building `proxmox-docker`'s `toplevel` and `diskoImagesScript` together crashed with a Nix-internal assertion failure (`Assertion '!awake.empty()' failed ... worker.cc:360`, a known class of bug in Nix's multi-goal build scheduler) while this session's 2GB-RAM build container was under heavy swap pressure (1.8-2.0/2GB swap in use) from a separate concurrent build. Retrying the same target alone (no concurrency) succeeded cleanly. **Not a flake defect** — purely an artifact of this session's constrained build environment; noted for completeness since it looked alarming in isolation.
+
+### Finding 7 — Management-surface audit: 5 operability gaps
+
+A focused audit of "can the operator actually run this repo day to day" (flake, home-manager, sops, related scripts) found:
+
+1. **No documented recovery path if the `&admin` sops age key is lost without a backup.** `scripts/secrets/backup-admin-key.sh` exists and works but is referenced nowhere in `README.md`/`docs/` — no forcing function ensures a backup was ever taken. `rotate-admin-key.sh` requires the *old* key to re-key; there's no bootstrap-from-nothing path documented (the real fallback — deriving an age identity from any still-live host's own SSH key — isn't written down anywhere).
+2. **home-manager has no standalone iteration path.** It's wired only inside `nixosConfigurations` (`flake.nix`) — no `homeConfigurations` output. The fastest real shortcut (`nix build .#nixosConfigurations.<target>.config.home-manager.users.nixos.home.activationPackage`) isn't documented anywhere, so the practical workflow is a full host rebuild to test one HM tweak.
+3. **Gitea's flake-lock-update workflow pushes straight to `main` with no pre-merge validation.** `.gitea/workflows/update-flake-lock.yml` commits and pushes `nix flake update`'s result directly; `codex-maintenance.sh` only runs *after*, on the resulting push — a genuinely broken lockfile bump lands on `main` before anything catches it. (The GitHub-side workflow is safer — PR-based — but has the opposite gap: nothing alerts if the PR sits unmerged.)
+4. **No pre-flight check that a build target has a registered sops key before building it.** `docs/auto-installer.md` documents the failure mode (silent, total secrets-decrypt failure) but nothing in `create-proxmox-resource.sh` refuses to proceed when it's about to build a target with no `.sops.yaml` anchor — it's on the operator to remember. This session's `lxc-gui` test hit close to this exact gap (needed the key added on the fly, mid-session).
+5. **`vars.remoteBuilderAuthorizedKeys` has the same drift risk as `vars.nixCacheHostKey`, but no checker script.** `sync-nix-cache-host-key.sh --check` guards the latter; the former (and `vars.pxeServerIp`/`vars.pbsIp`) has no equivalent — a rotated/revoked client key just silently stops working with no diagnostic pointing back here.
+
+---
+
+## 4. Action Plan (priority order)
+
+1. **Free up disk space on pve.sweet.home** (or expand `pve-root`). Blocking: `lxc-gui`, `proxmox-gui`, `lxc-pxe-boot`, `proxmox-pxe-boot` cannot currently be built/redeployed on this node at all.
+2. **Decide on `proxmox-minimal`'s orphaned sops key**: locate the original private key and back it up here, or accept regenerating it (breaks decrypt access for whoever/whatever currently holds the old one).
+3. **Merge this session's PR** (see below) to get the `--agent 1` fix and `lxc-gui`'s new sops registration onto `main` — required before `lxc-gui` can be live-redeployed with working secrets.
+4. **Add a staleness guard to `create-proxmox-resource.sh`'s cache-reuse path** (Finding 2) — highest-leverage fix, since it silently produces a broken-but-"running" host.
+5. **Add a pre-flight sops-anchor check to `create-proxmox-resource.sh`** (management-surface gap #4) — same root cause class as #4 above, catch it before building instead of at first boot.
+6. Investigate/clean up **CT102** on pve (Finding 5) — confirm abandoned, then remove.
+7. Document `backup-admin-key.sh` in `README.md`'s Security Notes and add the live-host-key bootstrap-recovery procedure to `docs/` (management-surface gap #1).
+8. Add pre-push validation to the Gitea flake-lock-update workflow (management-surface gap #3).
+9. Lower-priority: document the home-manager `activationPackage` shortcut (gap #2); extend `sync-nix-cache-host-key.sh`'s drift-check pattern to `remoteBuilderAuthorizedKeys` (gap #5).
+10. Follow-up session: finish build-validating `proxmox-gui` and `proxmox-pxe-boot` (both killed here after 35-40min on this session's 2GB-RAM machine — not failures, just unfinished) once pve has headroom (item 1) — ideally from a machine with more RAM. `proxmox-server` and `proxmox-tailscale-exit-node` already passed build-only validation in this session, no follow-up needed.
+
+---
+
+## 5. Uncommitted Changes From This Session
+
+This worktree (`worktree-flake-e2e-audit`) currently has:
+
+- `scripts/proxmox/create-proxmox-resource.sh` — the `--agent enabled=1` fix (Finding 4).
+- `.sops.yaml` / `secrets/common.yaml` — `lxc-gui`'s new age key registered as a recipient (generated live during this session's testing).
+
+Per this session's standard workflow, these will be committed, pushed, and opened as a draft PR rather than pushed to `main` directly — merging it is the operator's call, and is also **prerequisite to live-redeploying `lxc-gui` successfully** (its build will keep hitting the sops-staleness failure from Finding 2 on pve until this registration is on `origin/main`).

CLAUDE.md

@@ -17,11 +17,89 @@ machines when deployed.
 - Validation is limited to evaluation, linting, formatting checks, and
   `nix build --dry-run --no-link`.
 - Do not add secrets, tokens, private keys, or new password hashes to the repo.
-- This repo currently contains **committed password hashes** (e.g.
+- This repo currently contains **committed password hashes** in
-  `prepare.sh`, `hosts/nixos/configuration.nix`) and SSH public keys (e.g.
+  `modules/installer/common.nix` (the auto-installer's own root/nixos login —
-  `modules/nix-cache/server.nix`). The hashes are known tech debt — do not use
+  a deliberate, documented choice, see `docs/auto-installer.md`, not
-  them as a template for new hosts, and flag any *new* secret-like string you
+  accidental tech debt) and **SSH public keys** in `variables.nix`
-  encounter instead of committing it.
+  (`vars.adminSshKey`, `vars.remoteBuilderAuthorizedKeys`, `vars.beszelHubKey`). Don't use the installer's hardcoded hash as a
+  template for a *real* host — every other host uses sops-nix
+  (`hashedPasswordFile`, see "Security Notes" in `README.md`). Flag any *new*
+  secret-like string you encounter instead of committing it.
+- `host-keys/` is gitignored — used only by the auto-installer's own
+  environment for pre-seeding non-LXC host keys before first boot (see
+  `docs/auto-installer.md`). Never commit its contents; if `git status`
+  ever shows it as trackable, something is wrong. All deployed hosts use
+  clan vars (`vars/per-machine/<target>/openssh/`, committed and
+  sops-encrypted) for their SSH host keys — those ARE tracked by git and
+  belong in the repo.
+
+### Two Proxmox nodes: `pve1.sweet.home` (production) and `pve-test.sweet.home` (sandbox)
+
+There are two SSH-reachable Proxmox nodes on the LAN, both defined in
+`scripts/env.sh` (`PVE1_HOST` / `PVE_TEST_HOST`), individually targetable
+via `scripts/proxmox/create-proxmox-resource.sh --node <host>` or by
+overriding `PROXMOX_HOST`. `PROXMOX_HOST` itself still defaults to
+`PVE1_HOST` (production) — that default, and every other script behavior,
+is unchanged from before `pve-test` existed; the only thing new is that
+`pve-test` can now be reached at all. They are **not interchangeable** —
+one is real production infrastructure, the other exists specifically so
+there's somewhere safe to test. The restriction below is a policy for
+Claude specifically, not a change to the tooling's own default or
+anything the operator needs to opt into.
+
+#### `pve1.sweet.home` (production — off-limits to Claude)
+
+A real, live Proxmox node hosting production VMs/containers — not a
+sandbox, and not Claude's to touch by default.
+
+- **Off-limits at all times unless the operator has given explicit,
+  same-session instructions to act on this specific host.** That
+  authorization is scoped to the task it was given for — don't carry it
+  forward to unrelated later work in the same conversation, and never
+  assume it from a previous session.
+- **Read-only for existing state is always fine, authorization or not.**
+  You may SSH in (or use `pvesm`, `qm list`, `pct list`, `qm config`, `pct
+  config`, the Proxmox API, etc.) to inspect the node's config, storage,
+  and any existing VM/container — including ones this repo didn't create.
+- **Never** modify, stop, restart, delete, reconfigure, or create anything
+  on this node (`qm set`, `pct set`, `qm destroy`, `pct destroy`, `qm
+  stop`, `pct stop`, `qm create`, `pct create`, snapshot operations,
+  storage changes, etc.) — including scratch/test resources — without
+  that explicit go-ahead. Use `pve-test.sweet.home` for anything
+  exploratory instead; it exists precisely so `pve1` never has to be the
+  answer to "where do I test this."
+- **This is a Claude-specific policy, not something the scripts enforce.**
+  `scripts/env.sh`/`create-proxmox-resource.sh` default to `pve1` exactly
+  as they did before `pve-test` existed, with no extra flag or prompt
+  required — that's deliberate, so the operator's own existing workflows
+  don't change. Claude, however, must never rely on that default: every
+  Proxmox action Claude takes on its own initiative — not explicitly
+  pointed at `pve1` by the operator this session — targets `pve-test`
+  instead (e.g. `--node "$PVE_TEST_HOST"`, or `PROXMOX_HOST=$PVE_TEST_HOST`).
+  Claude's own default is `pve-test`, full stop, regardless of what the
+  tooling's own unqualified default happens to be.
+
+#### `pve-test.sweet.home` (sandbox — Claude's default target)
+
+A separate Proxmox node set aside for testing. The *tooling's* default is
+still production (`PROXMOX_HOST` → `PVE1_HOST`, see above) — but
+**Claude's own default is this node**: absent an explicit, same-session
+instruction to use `pve1`, every Proxmox action Claude initiates targets
+`pve-test`. Once targeted, it's safe to create, interrogate, and destroy
+resources on without asking first.
+
+- **Test VMs/containers are allowed, but must be torn down.** Create a
+  scratch VM or container here (e.g. via
+  `scripts/proxmox/create-proxmox-resource.sh` or raw `qm`/`pct create`)
+  to validate something. Anything created this way must be destroyed
+  again in the same session, before ending the task — never leave a test
+  resource running. Use a VMID/name that's obviously scratch (and doesn't
+  collide with a real flake target) so it's unambiguous what's safe to
+  remove.
+- **Node-level config is still not yours to change.** Creating/destroying
+  your own scratch guests is fine; Proxmox host config, storage pools, and
+  networking on `pve-test` itself are still the operator's call to make
+  manually, same as on `pve1`.
 
 ## Commands
 
@@ -29,11 +107,22 @@ machines when deployed.
 # One-time environment bootstrap (installs Nix if missing, prints hosts)
 bash scripts/codex-setup.sh
 
-# Full validation: secret grep, nixpkgs-fmt --check, statix lint, eval all hosts
+# Changed-files-only validation: secret grep (whole repo), nixpkgs-fmt --check
+# and statix on changed *.nix files, eval of the hosts/packages those changes
+# can affect. This is what CI runs on every push/PR.
 bash scripts/codex-maintenance.sh
 
-# Same, plus a dry-run build (no result symlink) of every host's toplevel
+# Full sweep: nixpkgs-fmt --check/statix over the whole tree, eval every host
-bash scripts/codex-maintenance.sh dry-run
+# and package. Slow (minutes) -- CI never runs this; use it locally before a
+# release or after touching modules/common/*, flake.nix, or variables.nix for
+# extra confidence beyond the automatic full-fallback those paths already
+# trigger in the default mode (see below).
+bash scripts/codex-maintenance.sh --full-check
+
+# Either mode, plus a dry-run build (no result symlink) of every host/package
+# in whichever scope is active
+bash scripts/codex-maintenance.sh --dry-run
+bash scripts/codex-maintenance.sh --full-check --dry-run
 
 # List the hosts the flake currently exposes
 nix eval --json .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]'
@@ -50,58 +139,313 @@ maintenance script pulls them via `nix run github:NixOS/nixpkgs/nixos-25.11#<too
 There is no test suite — "correctness" here means the flake evaluates and
 `nixpkgs-fmt`/`statix` are clean.
 
+With no flags, `codex-maintenance.sh` diffs against a base ref (env
+`MAINT_BASE_SHA`, else the PR base SHA in CI, else `HEAD^` locally) and scopes
+fmt-check/statix to the changed `*.nix` files and eval to the hosts/packages
+those changes can affect — a `hosts/<name>/host.nix` edit only evals that
+host's targets, a `modules/platforms/<platform>.nix` edit only evals that
+platform's hosts, and so on. A change to `flake.nix`, `flake.lock`,
+`variables.nix`, `modules/common/*`, or any other `modules/*.nix` file outside
+`platforms/`/`build-types/` (whose blast radius isn't safely inferable from
+the path alone) falls back to evaluating every host and package, same as
+`--full-check` would, just without the whole-tree fmt/statix sweep. This
+exists because the whole-tree sweep is what was timing out CI; **CI always
+runs the plain, no-flag form and never passes `--full-check`.**
+
+The default mode's diff is against the working tree (uncommitted and staged
+edits included, not just committed ones), so it's already the right tool for
+an interactive session too: after editing one or two hosts/modules, plain
+`bash scripts/codex-maintenance.sh` naturally scopes to just what you
+touched. Reserve `--full-check` for changes that plausibly affect every host
+(`modules/common/*`, `flake.nix`, `variables.nix` — though the default mode
+already falls back to evaluating everything for those paths, `--full-check`
+additionally re-checks fmt/statix over the whole tree) or as a final check
+before committing.
+
+## Scripts
+
+Beyond `codex-setup.sh`/`codex-maintenance.sh` above, `scripts/` is
+organized by purpose: `scripts/secrets/` (sops/age + SSH host-key
+management), `scripts/proxmox/` (Proxmox deployment), `scripts/installer/`
+(the auto-installer's own shell script, templated into the image — see
+below), `scripts/lib/` (shared helpers, sourced by the scripts below — not
+run directly), and a handful of repo-wide scripts left at the top level
+(`env.sh`, `bump-nixpkgs-release.sh`, plus `codex-setup.sh`/
+`codex-maintenance.sh` above). When adding a new script, put it in the
+matching subfolder rather than the top level, and if it duplicates logic
+another script already has, lift the shared part into `scripts/lib/`
+instead of copying it.
+
+### `scripts/installer/`
+
+- `scripts/installer/auto-install.sh` — the interactive install script
+  baked into the auto-installer image (see `docs/auto-installer.md`), kept
+  as a real, version-controlled shell file rather than inline in
+  `modules/installer/common.nix`'s Nix. It sources `scripts/env.sh` itself
+  for `LAN_DOMAIN` (`export LAN_DOMAIN`/`: "${LAN_DOMAIN:=...}"`, matching
+  `variables.nix`'s `lanDomain` — manually kept in sync, same pattern as
+  `NIX_CACHE_HOST` mirroring `nixCacheHost`), rather than Nix-level string
+  substitution — that's what makes it work identically whether run
+  straight from a git checkout or from inside the built installer image.
+  `common.nix` bakes `scripts/env.sh` in alongside it at a matching
+  relative path (`/etc/nixos-installer/env.sh` next to
+  `/etc/nixos-installer/installer/auto-install.sh`) so the script's own
+  `source "$(dirname ...)/../env.sh"` line resolves the same way in both
+  contexts — this is also why it's invoked from
+  `/etc/nixos-installer/installer/auto-install.sh` rather than a flat
+  `/etc/auto-install.sh`. `#!/usr/bin/env bash`, not
+  `#!/run/current-system/sw/bin/bash`: the latter only resolves on an
+  already-activated NixOS system, breaking the checked-out-file case
+  entirely (confirmed live: "cannot execute: required file not found" on
+  a non-NixOS box); `/usr/bin/env` is reliably present on both NixOS
+  (`environment.usrbinenv`'s own default) and any normal Linux distro.
+
+### `scripts/secrets/`
+
+- `scripts/secrets/sync-host-keys.sh` — generates/registers SSH host keys
+  and their `.sops.yaml`/`secrets/*.yaml` recipients for flake targets,
+  idempotently (`--all`, `<target>`, `--remove`, `--regenerate-all-keys`,
+  all with `--dry-run`). Stores keys as clan vars
+  (`vars/per-machine/<target>/openssh/`, committed and sops-encrypted) for
+  all flake targets. The primary tool for provisioning a new host's
+  secrets access — see "Creating a new machine" in
+  `docs/auto-installer.md`.
+- `scripts/secrets/prepare-host-key.sh` — narrower predecessor: generates a
+  key by an arbitrary name without touching `.sops.yaml`. Still useful to
+  pre-generate a key before its flake target exists yet, since
+  `sync-host-keys.sh` can only act on targets `nixosConfigurations` already
+  has.
+- `scripts/secrets/rotate-admin-key.sh <backup-admin-key> [--new-key-file
+  <path>] [--dry-run]` — rotates `.sops.yaml`'s `&admin` age key: decrypts
+  with a backed-up copy of the key currently trusted as `&admin` (verified
+  by deriving its public key and comparing, not taken on faith), replaces
+  the `&admin` line with a new key already present in the environment
+  (defaults to wherever sops/age itself would look), and runs
+  `sops updatekeys` on every `secrets/*.yaml`. One-way: the old key can no
+  longer decrypt anything re-encrypted this way. This is the automation
+  for the manual steps `sync-host-keys.sh`/`create-proxmox-resource.sh`
+  print when they bootstrap a brand-new, not-yet-trusted key on a machine
+  with no prior admin access.
+- `scripts/secrets/backup-admin-key.sh <dest-path> [--key-file <path>]
+  [--force] [--dry-run]` — copies the local sops age key (source
+  resolution matches sops/age itself: `$SOPS_AGE_KEY` inline, then
+  `--key-file`, then `$SOPS_AGE_KEY_FILE`, then the XDG default) to an
+  arbitrary destination path with `0600` permissions, validating it's a
+  real age identity and round-tripping the public key before and after the
+  write. Refuses to overwrite an existing `<dest-path>` without `--force`.
+  Purely a local filesystem copy — never touches `.sops.yaml`/
+  `secrets/*.yaml` or the repo at all. The resulting file is exactly what
+  `rotate-admin-key.sh` expects as its backup-key argument.
+- `scripts/secrets/sync-nix-cache-host-key.sh [--check] [--dry-run]
+  [--host <name>]` — detects drift between the ed25519 SSH host key
+  nix-cache is actually serving right now (via `ssh-keyscan`) and
+  `vars.nixCacheHostKey` (`variables.nix`), the value
+  `modules/nix-cache/remote-builder-client.nix` bakes into every real
+  client's declarative `programs.ssh.knownHosts` and
+  `configure-nix-cache-client.sh` hardcodes as its own default for
+  non-NixOS clients. That value has no automatic source of truth — it's
+  set once from whatever nix-cache's host key happened to be at the time,
+  and silently goes stale if the host is ever rebuilt/recreated with a new
+  key, breaking every client's distributed-build SSH trust with no error
+  that points back here. `--check` (used by `codex-maintenance.sh`, which
+  treats an unreachable nix-cache — e.g. from a non-LAN CI runner — as a
+  silent skip rather than a failure) only reports drift; the no-flags form
+  updates both files in place. Declarative clients still need a rebuild to
+  pick up the fix.
+
+### `scripts/proxmox/`
+
+- `scripts/proxmox/create-proxmox-resource.sh` — builds a `lxc-*`/
+  `proxmox-*` target's tarball/disk image and creates it on a real Proxmox
+  node (`pct create` against the tarball as a CT template / `qm create`+
+  `importdisk`), or reconfigures an existing resource's cores/memory/disk
+  size (`--modify`, always requires typing the VMID back to confirm).
+  Checks for an already-uploaded image on the node before building
+  (`--force-rebuild` to skip that and always rebuild), and probes
+  nix-cache's substituter/remote-builder reachability once up front rather
+  than letting every `nix build` call retry against it individually.
+  Refuses to create a target whose host identity already exists live on
+  the node (checked directly via `qm`/`pct`, not any file in this repo)
+  unless `--allow-duplicate-host` is passed. `--dry-run` throughout both
+  modes. The first time it has to bootstrap build tooling on a node (i.e.
+  `nix` wasn't already on its `PATH`), it also runs
+  `scripts/proxmox/configure-nix-cache-client.sh` there (non-fatally — a
+  failure just falls back to building from source / `cache.nixos.org`) so
+  the node substitutes from and can offload builds to nix-cache on every
+  subsequent run, not just this one.
+- `scripts/proxmox/configure-nix-cache-client.sh [--dry-run]
+  [--no-remote-builder] [--no-restart]` — the non-NixOS equivalent of
+  `modules/nix-cache/client.nix`/`remote-builder-client.nix`, for a plain
+  Debian machine with the Nix package manager (not NixOS) already
+  installed: run as root *on that machine* to add nix-cache as a
+  substituter in `/etc/nix/nix.conf` (`https://cache.nixos.org/` kept as
+  fallback) via `extra-substituters`/`extra-trusted-public-keys` so it
+  layers on top of whatever's already there instead of clobbering it, and,
+  if `/root/.ssh/nixremote` is already present (see docs/nix-cache.md
+  "Remote builder SSH keys"), configures it as a distributed-build
+  machine too and trusts nix-cache's SSH host key in
+  `/etc/ssh/ssh_known_hosts`. Idempotent (re-running replaces its own
+  marked block rather than duplicating it); restarts `nix-daemon` by
+  default so the change takes effect immediately.
+
+### `scripts/lib/`
+
+Sourced by the scripts above, never run directly:
+
+- `nix-bootstrap.sh` — `NIX_CONFIG`/`ensure_nix_profile`, shared by
+  `codex-setup.sh`/`codex-maintenance.sh` and the remote build commands
+  `create-proxmox-resource.sh` runs over SSH.
+- `nix-eval.sh` — `NIX_EVAL_FLAGS` plus `list_flake_targets`/
+  `flake_target_hostname` flake-introspection helpers.
+- `ssh-host-keys.sh` — `generate_host_ed25519_key`/`ssh_pubkey_to_age`,
+  shared by `sync-host-keys.sh` and `prepare-host-key.sh`.
+- `sops-age.sh` — `age_pubkey_from_identity_file`/`sops_yaml_admin_pubkey`/
+  `sops_updatekeys` plus the shared sops/age default key-file resolution,
+  shared by `backup-admin-key.sh`, `rotate-admin-key.sh`, and
+  `sync-host-keys.sh`.
+- `confirm.sh` — `confirm_typed`, the "type X back to confirm" destructive-
+  action prompt shared by `create-proxmox-resource.sh` and
+  `sync-host-keys.sh`.
+- `sync-host-keys-edit-sops.py` — the `.sops.yaml` anchor/key_groups editor
+  `sync-host-keys.sh` shells out to (see that script for why: precise,
+  idempotent YAML edits are impractical in bash).
+
+### Top level
+
+- `scripts/env.sh` — shared config (`PROXMOX_HOST`, storage pool, bridge,
+  default cores/memory, `NIX_CACHE_HOST`, `LAN_DOMAIN`) sourced by
+  `create-proxmox-resource.sh` and `scripts/installer/auto-install.sh`. Add
+  new cross-script config here instead of duplicating it per-script.
+- `scripts/bump-nixpkgs-release.sh` — bumps `flake.nix`'s `nixpkgs.url`/
+  `home-manager.url` in place. Exists because flake input URLs can't
+  reference `variables.nix` (confirmed empirically — `nix flake metadata`
+  errors on it), so this is the closest equivalent to a single source of
+  truth for the tracked release.
+
+`sync-host-keys.sh`, `create-proxmox-resource.sh`, and
+`rotate-admin-key.sh` genuinely mutate real state when run for real (not
+`--dry-run`): real `secrets/*.yaml` recipients, real Proxmox VMs/
+containers, real revocation of decrypt access. They require the
+operator's own SSH/sops access, which an agent session doesn't have — but
+don't suggest running any of them non-dry-run without the operator's
+explicit go-ahead even if it becomes technically reachable.
+`backup-admin-key.sh` only writes a key copy to a path the operator gives
+it — lower-stakes than the others, but it still handles a real private
+key, so treat its destination path choice as the operator's call too.
+
 ## Architecture
 
-`flake.nix` is the single entry point. It defines one `nixosConfigurations.<host>`
+`flake.nix` is the single entry point. It generates one
-attribute per machine, each built the same way:
+`nixosConfigurations.<platform>-<buildtype>` attribute per target via the
+`mkTarget` function, composed from:
 
 ```
 nixosSystem {
   modules = [
     disko.nixosModules.disko
-    ./hosts/<host>/configuration.nix        # host-specific config
+    sops-nix.nixosModules.sops
-    ./modules/hardware-configuration/vm/<proxmox|linode>.nix
+    ./modules/common/configuration.nix
+    ./modules/platforms/${platform}.nix        # what it runs on
+    ./modules/build-types/${buildType}.nix     # what it's for
+    hostPath                                   # hosts/<name>/host.nix — per-machine identity
     home-manager.nixosModules.home-manager { ... }
-  ];
+  ] ++ (client-only modules, for every buildType except "nix-cache" itself)
 }
 ```
 
-Hosts currently defined in `flake.nix`: `nixos`, `docker`, `server`,
+Platforms: `linode`, `proxmox`, `lxc`, `baremetal`. Build types: `minimal`,
-`nix-cache`, `nix-minimal`, `pxe-boot`, `linode-minimal`. Treat `flake.nix` as
+`nix-cache`, `server`, `docker`, `gui`, `pxe-boot`, `tailscale-exit-node`,
-the source of truth for which hosts exist — `README.md`, `AGENTS.md`,
+`tor-relay`. Not every combination is built — e.g. `pxe-boot` has no `linode`
+variant (PXE/DHCP/TFTP need LAN L2 adjacency a Linode VPS doesn't have),
+`tor-relay` currently only exists as `lxc-tor-relay`, and `baremetal`
+currently only exists as `baremetal-gui` (the real gui-host hardware —
+see `hosts/nixos/host.nix` and `modules/platforms/baremetal.nix`). Treat
+`flake.nix`'s
+`generatedTargets` as the source
+of truth for which hosts exist — `README.md`, `AGENTS.md`,
 `docs/flake-lock-automation.md`, and the CI eval workflows
 (`.github/workflows/check-nixos.yml`, `.gitea/workflows/check-nixos.yml`) list
-hosts by hand and can drift from it, so re-check them against `flake.nix` when
+hosts by hand (or, for the CI workflows, evaluate the flake dynamically) and
-adding or removing a host.
+can drift from it, so re-check them against `flake.nix` when adding or
+removing a host.
 
 ### Composition pattern
 
-Every host's real configuration lives in `hosts/<host>/configuration.nix`,
+- `hosts/<name>/host.nix` — per-machine identity **only**: hostname, hostId,
-which is a thin list of `imports` pulling in reusable pieces from `modules/`:
+  per-machine secrets, `system.stateVersion`. These files carry no `imports`
-
+  of their own — all shared behavior comes from the platform/build-type modules
-- `modules/common/configuration.nix` — base NixOS config imported by (almost)
+  composed in `flake.nix`, not from the host file.
-  every host: locale, users, nix settings, git. Nearly always the first import.
+- `modules/platforms/{linode,proxmox,lxc,baremetal}.nix` — platform-specific
-- `modules/common/home.nix` / `hosts/<host>/home.nix` — Home Manager config for
+  config: boot method, guest tooling, and the hardware config, imported
-  the `nixos` user; the `nixos` workstation has its own, other hosts share
+  directly by the platform module itself — **not** wired in from
-  `modules/common/home.nix`.
+  `flake.nix`. VM platforms use `../hardware-configuration/vm/{proxmox,linode}.nix`;
+  `baremetal.nix` uses `../hardware-configuration/baremetal.nix` (adapted
+  from a real `nixos-generate-config` run on the actual hardware, not a
+  vm/ file, since it isn't a VM) plus `hardware.enableRedistributableFirmware
+  = true` for real wifi/GPU/microcode firmware that VMs never needed.
+  `lxc.nix` has no hardware-configuration counterpart since containers
+  share the host kernel; instead it imports nixpkgs' own
+  `virtualisation/proxmox-lxc.nix`, which gives every `lxc-*` host a
+  `config.system.build.tarball` output — a plain rootfs tarball, used as a
+  `pct create ... vztmpl` CT template (**not** `pct restore`, which expects
+  `vzdump` backup-archive metadata this doesn't have), no install step —
+  see `docs/auto-installer.md`.
+- `modules/build-types/*.nix` — what a system is for:
+  minimal/server/docker/gui/pxe-boot/nix-cache/tailscale-exit-node/tor-relay.
+- `modules/common/configuration.nix` — base NixOS config imported by every
+  host: locale, users, nix settings, git.
+- `modules/common/home.nix` / `hosts/nixos/home.nix` — Home Manager config for
+  the `nixos` user; the `nixos` workstation (`gui` build type) has its own,
+  other hosts share `modules/common/home.nix`.
 - `modules/disko/proxmox.nix` — declarative disk layout (GPT: ESP + swap +
-  ext4 root) via disko, used by all Proxmox-VM hosts.
+  ext4 root) via disko, used by all Proxmox-VM hosts (`proxmox-*`, not
+  `lxc-*`). Also carries `imageSize`/`imageName`, letting every `proxmox-*`
+  host be built as a standalone, `qm importdisk`-ready `.raw` image with no
+  install step — see `docs/proxmox-images.md`.
+- `modules/disko/linode.nix` — `linode-*`'s disko config, deliberately
+  different in kind from the Proxmox one: Linode provisions and sizes
+  `/dev/sda`/`/dev/sdb` itself as whole, unpartitioned devices before the OS
+  boots, so this declares them with `destroy = false` (disko never wipes
+  them) and a bare `filesystem`/`swap` content type instead of a partition
+  table — idempotent against an already-provisioned disk, never destructive.
+- `modules/disko/baremetal.nix` — `baremetal-gui`'s disko config: a ZFS
+  RAID0 (striped, no redundancy — disko's zpool `mode` defaults to `""`,
+  which is a plain stripe rather than `"mirror"`/`"raidz"`) root pool
+  across two disks, ESP + systemd-boot on the first. Device paths
+  (`vars.guiRootDisk1`/`guiRootDisk2`) are placeholders — fill in stable
+  `/dev/disk/by-id/...` paths before running disko for real.
+  `modules/platforms/baremetal.nix` also imports
+  `modules/services/zfs/enable-service.nix` for this (the `zfs_unstable`
+  package, autoScrub/autoSnapshot/trim) — the only other importer today is
+  `server`'s NFS data pool, an unrelated non-root ZFS use.
 - `modules/boot/efi.nix` — systemd-boot + EFI vars, paired with the disko module.
-- `modules/hardware-configuration/vm/{proxmox,linode}.nix` — hypervisor-specific
+- `modules/installer/` — the auto-installer environment (ISO, also served as
-  hardware config, wired in from `flake.nix` (not from the host file).
+  PXE netboot): `common.nix` (shared config + the generated
-- `modules/nix-cache/{client,server}.nix` + `modules/remote-builder-client.nix` —
+  `auto-install.sh`), `iso.nix`, `host-keys.nix` (optionally bakes
-  binary cache substituter + SSH remote-builder wiring; see `docs/nix-cache.md`
+  `host-keys/` into the image under `--impure`). See
-  for the full design (per-host local stores, no shared `/nix/store`, and how
+  `docs/auto-installer.md`.
-  the `nixremote` signing/SSH keys fit together).
+- `modules/pxe-boot/stage-installer-artifacts.nix` — builds the installer's
-- `modules/tailscale/`, `modules/docker/`, `modules/beszel/`,
+  netboot image and stages it on the `pxe-boot` host so its iPXE menu can
-  `modules/services/*` — single-purpose, single-host feature modules (e.g.
+  chain straight to it. See `docs/pxe-boot.md`.
-  `docker/enable-service.nix`, `services/zfs/enable-service.nix`,
+- `modules/nix-cache/{client,server,remote-builder-client}.nix` — binary cache
-  `beszel/enable-agent.nix` for monitoring). Grep `hosts/*/configuration.nix`
+  substituter + SSH remote-builder wiring; see `docs/nix-cache.md` for the
-  for the `imports` list to see which modules apply to a given host.
+  full design (per-host local stores, no shared `/nix/store`, and how the
+  `nixremote` signing/SSH keys fit together).
+- `modules/beszel/enable-agent.nix` — enables beszel-agent, sets `HUB_URL`,
+  fixes the upstream `StateDirectory` bug, and wires the universal
+  `beszel-token` sops secret (from `secrets/common.yaml`) into the agent's
+  `environmentFile`; see `docs/beszel.md` for the full setup guide.
+- `modules/tailscale/`, `modules/docker/`, `modules/networking/`,
+  `modules/traefik/`, `modules/tor/`, `modules/services/*` — single-purpose,
+  single-host
+  feature modules (e.g. `docker/enable-service.nix`,
+  `services/zfs/enable-service.nix`). Grep `modules/build-types/*.nix` for
+  each build type's `imports` list to see which modules apply where.
 
-New host = new `hosts/<name>/configuration.nix` + a matching block added to
+New host = new `hosts/<name>/host.nix` + a matching
-`flake.nix`'s `nixosConfigurations`, composed from existing `modules/*` pieces
+`mkTarget { platform; buildType; hostPath; }` entry added to `flake.nix`'s
-rather than duplicating config.
+`generatedTargets`, composed from existing `modules/*` pieces rather than
+duplicating config.
 
 ### Other docs worth reading before touching these areas
 
@@ -109,6 +453,12 @@ rather than duplicating config.
   handling.
 - `docs/pxe-boot.md` — the `pxe-boot` host's iPXE/TFTP/HTTP boot chain and
   directory layout under `/srv/pxe`.
+- `docs/auto-installer.md` — the installer environment (ISO/netboot/Proxmox
+  LXC), `host-keys/` and the sops-nix pre-seeding problem it solves, and why
+  `lxc-*` hosts are deliberately excluded from its menu.
+- `docs/proxmox-images.md` — building `proxmox-*` hosts as standalone `.raw`
+  disk images (disko's image builder) instead of installing, and deploying
+  the result to Proxmox.
 - `docs/flake-lock-automation.md` — how `flake.lock` updates flow through CI
   (scheduled `nix flake update` PR + host-eval-on-PR workflow) and why hosts
   should track the committed lock file rather than `nixos-rebuild --upgrade-all`.

README.md

@@ -8,29 +8,47 @@ workstation.
 Targets are named `<platform>-<buildtype>`, generated from two orthogonal
 pieces composed in `flake.nix`:
 
-- **Platforms** (what it runs on): `linode`, `proxmox`, `lxc`
+- **Platforms** (what it runs on): `linode`, `proxmox`, `lxc`, `baremetal`
 - **Build types** (what it's for): `minimal`, `nix-cache`, `server`, `docker`,
-  `gui`, `pxe-boot`
+  `gui`, `pxe-boot`, `tailscale-router`, `tor-relay`, `ha-server`
 
 Not every combination exists — `pxe-boot` has no `linode` variant, since
-PXE/DHCP/TFTP need LAN L2 adjacency that a Linode VPS doesn't have. The full
+PXE/DHCP/TFTP need LAN L2 adjacency that a Linode VPS doesn't have,
-list:
+`tor-relay` and `ha-server` currently only exist on `lxc`/`proxmox`, and
+`baremetal` currently only exists as `baremetal-gui` (the real gui-host
+hardware). The full list:
 
 | Target | Purpose |
 | --- | --- |
-| `linode-minimal` | Minimal NixOS host profile on a Linode VPS (real, deployed) |
+| `linode-minimal` | Minimal NixOS host profile on a Linode VPS |
-| `proxmox-minimal` | Minimal NixOS host profile on Proxmox (real, deployed — previously the flat `nix-minimal` target) |
+| `proxmox-minimal` | Minimal NixOS host profile on Proxmox — previously the flat `nix-minimal` target |
 | `lxc-minimal` | Minimal NixOS host profile in a Proxmox LXC container |
-| `linode-nix-cache` / `proxmox-nix-cache` / `lxc-nix-cache` | Local Nix binary cache and remote builder (`proxmox-nix-cache` is the real, deployed one — previously the flat `nix-cache` target) |
+| `linode-nix-cache` / `proxmox-nix-cache` / `lxc-nix-cache` | Local Nix binary cache and remote builder — previously the flat `nix-cache` target |
-| `linode-server` / `proxmox-server` / `lxc-server` | Storage, NFS, backup, and monitoring exporter host (`proxmox-server` is the real, deployed one — previously the flat `server` target) |
+| `linode-server` / `proxmox-server` / `lxc-server` | Storage, NFS, backup, and monitoring exporter host — previously the flat `server` target |
-| `linode-docker` / `proxmox-docker` / `lxc-docker` | Docker host for the main container stack (`proxmox-docker` is the real, deployed one — previously the flat `docker` target) |
+| `linode-docker` / `proxmox-docker` / `lxc-docker` | Docker host for the main container stack — previously the flat `docker` target |
-| `linode-gui` / `proxmox-gui` / `lxc-gui` | Cinnamon desktop workstation (`proxmox-gui` is the real, deployed one — previously the flat `nixos` target) |
+| `linode-gui` / `proxmox-gui` / `lxc-gui` | Cinnamon desktop workstation — previously the flat `nixos` target |
-| `proxmox-pxe-boot` / `lxc-pxe-boot` | HTTP/iPXE boot asset host (`proxmox-pxe-boot` is the real, deployed one — previously the flat `pxe-boot` target) |
+| `baremetal-gui` | Same Cinnamon desktop workstation, on the real gui-host hardware — ZFS RAID0 root, systemd-boot |
+| `proxmox-pxe-boot` / `lxc-pxe-boot` | HTTP/iPXE boot asset host — previously the flat `pxe-boot` target |
+| `linode-tailscale-router` / `proxmox-tailscale-router` / `lxc-tailscale-router` | Tailscale subnet router + MagicDNS forwarder for the LAN |
+| `lxc-tor-relay` | Tor middle relay |
+| `proxmox-ha-server-1` / `proxmox-ha-server-2` | HA file-server cluster nodes — DRBD + XFS + iSCSI + NFS, managed by Corosync + Pacemaker |
+
+Which variant of a given buildtype is actually deployed isn't tracked
+anywhere in this repo — that's live infrastructure state, not something a
+committed file can keep accurate, and it changes independently of the code.
+Check the Proxmox node itself, or `/etc/flake-target` on a running host (see
+below), if you need to know what's really out there right now.
+`scripts/proxmox/create-proxmox-resource.sh`'s duplicate-host guard works the same
+way: it checks the Proxmox node directly rather than any file here.
+Real, production deployments live on `pve1.sweet.home`; there's a second
+node, `pve-test.sweet.home`, set aside purely for scratch/test resources —
+see `scripts/env.sh` (`PVE1_HOST` / `PVE_TEST_HOST`, and the
+`--node`/`PROXMOX_HOST` targeting they feed into) and CLAUDE.md's Proxmox
+section for which is which.
 
 Each buildtype's `hosts/<name>/host.nix` carries the per-machine identity
 (hostname, hostId, per-machine secrets, `system.stateVersion`) that must stay
-fixed regardless of which platform it's built for — see
+fixed regardless of which platform it's built for. Every deployed host
-`flake-target-refactor-spec.md` for the full rationale. Every deployed host
 stamps its own active target name into `/etc/flake-target` at build time, so
 `nixos-rebuild switch --flake .#$(cat /etc/flake-target)` always picks up the
 right one even after a platform migration changes the flake attribute name.
@@ -46,14 +64,18 @@ nix eval --json .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]'
 | Path | Purpose |
 | --- | --- |
 | `flake.nix` | Flake inputs, the `mkTarget` platform × build-type generator, and `nixosConfigurations` outputs |
+| `variables.nix` | Single source of truth for shared values (LAN domain/CIDR, hostnames, timezone, primary username, storage root, NFS share subpaths/mountpoints, service ports, ...) — passed to every module and Home Manager config as the `vars` argument via `specialArgs`/`extraSpecialArgs` |
 | `hosts/<name>/host.nix` | Per-machine identity: hostname, hostId, per-machine secrets, `system.stateVersion` |
 | `hosts/nixos/home.nix` | Workstation-specific Home Manager config (used by the `gui` build type) |
-| `modules/platforms/` | Platform-specific config: virtualisation guest tools, boot method, hardware config (`linode.nix`, `proxmox.nix`, `lxc.nix`) |
+| `modules/platforms/` | Platform-specific config: virtualisation guest tools, boot method, hardware config (`linode.nix`, `proxmox.nix`, `lxc.nix`, `baremetal.nix`) |
 | `modules/build-types/` | Build-type-specific config: what makes a system minimal/server/docker/gui/pxe-boot/nix-cache |
 | `modules/common/` | Shared NixOS config, Home Manager, aliases imported by every host |
 | `modules/nix-cache/` | Binary cache and remote builder client/server modules |
-| `docs/` | Operational notes for cache, builders, lock updates, and boot services |
+| `modules/installer/` | Auto-installer environment (ISO, also served as PXE netboot) — see `docs/auto-installer.md` |
-| `scripts/` | Codex setup and validation helpers |
+| `host-keys/` | Gitignored; only used by the auto-installer environment for pre-seeding SSH host keys before first boot — see `docs/auto-installer.md`. All deployed hosts use clan vars (`vars/per-machine/<target>/openssh/`) instead |
+| `vars/per-machine/` | Clan vars: committed, sops-encrypted SSH host keys for all deployed hosts; read by `create-proxmox-resource.sh` at deploy time |
+| `docs/` | Operational notes for cache, builders, lock updates, boot services, the auto-installer, and Proxmox image builds |
+| `scripts/` | Codex setup, validation, host-key, release-bump, and Proxmox resource helpers |
 
 ## Validation
 
@@ -61,10 +83,19 @@ Safe validation commands for Codex and local review:
 
 ```bash
 bash scripts/codex-setup.sh
-bash scripts/codex-maintenance.sh dry-run
 bash scripts/codex-maintenance.sh
 ```
 
+`codex-maintenance.sh` with no flags (what CI runs on every push/PR) scopes
+fmt-check/statix/eval to files changed against a base ref — fast, but only
+as thorough as the diff. For the full sweep (every host, every package,
+fmt-check and statix over the whole tree — slow, CI never runs this):
+
+```bash
+bash scripts/codex-maintenance.sh --full-check
+bash scripts/codex-maintenance.sh --full-check --dry-run
+```
+
 For individual host evaluation:
 
 ```bash
@@ -84,6 +115,29 @@ review sessions.
   client hosts.
 - `pxe-boot` serves iPXE boot files over HTTP from `/srv/pxe`.
 
+### Deploying a new host
+
+Three different paths depending on target, none of them involving a manual
+`nixos-rebuild switch` from this repo:
+
+- Most hosts: boot the auto-installer, pick the target from its menu — see
+  `docs/auto-installer.md`. Every menu target has a Disko config the
+  installer formats unconditionally (`docs/auto-installer.md`'s "Storage"
+  section covers how this stays non-destructive for `linode-*`, whose disks
+  Linode itself provisions ahead of time).
+- `lxc-*` targets: not installed at all — build a ready-to-run container
+  tarball and `pct create` it as a CT template directly. `docs/auto-installer.md`
+  covers why (and the installer's menu excludes them for the same reason).
+- `proxmox-*` targets: can alternatively be built as a standalone `.raw`
+  disk image and attached to a new VM with no install step — see
+  `docs/proxmox-images.md`.
+
+`scripts/proxmox/create-proxmox-resource.sh --type lxc|vm --host <name>` automates
+either of the last two end to end (host-key registration, building the
+image directly on the Proxmox node itself, `pct create`/`qm create`), with
+`--dry-run` and a guard against duplicating an already-deployed host's
+identity. See its `--help`.
+
 ## Security Notes
 
 Do not commit tokens, private keys, live credentials, or new password hashes
@@ -104,7 +158,15 @@ enabled via `git config core.hooksPath .githooks`, done automatically by
 `scripts/codex-setup.sh`) runs `gitleaks protect --staged` to catch mistakes
 before they're committed.
 
-This repository's git *history* still contains secrets committed before this
+The auto-installer environment is the one deliberate exception to
-migration (see `remove-sensetive-info-refactor.md`) — those are being
+sops-nix-everywhere: it has a hardcoded login password instead (no stable
-scrubbed and rotated separately; don't treat the repo as safe to make public
+per-boot host key for sops-nix to derive from on ephemeral media) — see
-until that's finished.
+"Host keys" in `docs/auto-installer.md` for why, and how the private keys it
+*does* pre-seed for target hosts stay out of git via the gitignored
+`host-keys/` directory. All deployed hosts use clan vars
+(`vars/per-machine/<target>/openssh/`, committed and sops-encrypted) for
+their SSH host keys.
+
+This repository's git *history* still contains secrets committed before the
+sops-nix migration — those are being scrubbed and rotated separately; don't
+treat the repo as safe to make public until that's finished.

certs/ipa-ca.crt

@@ -0,0 +1,25 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

docs/auto-installer.md

@@ -0,0 +1,313 @@
+# Auto-installer
+
+This flake builds a self-contained NixOS installer environment that can
+install any host exposed by its own `nixosConfigurations`. It was migrated
+from a formerly-separate `nix-auto-installer` repo — everything it did now
+lives here.
+
+The installer provides a small NixOS install environment (ISO, or the same
+image netbooted via PXE) with SSH access, Git support, and an interactive
+installation script.
+Logging in as any user (root or `nixos`) runs
+`/etc/nixos-installer/installer/auto-install.sh` (the same file as
+`scripts/installer/auto-install.sh` in this repo — see "Installer process"
+below for why it's baked in at that path rather than a flat
+`/etc/auto-install.sh`), discovers available hosts from this same flake,
+lets the operator choose a target, applies that host's Disko storage
+configuration, installs NixOS, and reboots.
+
+**This applies to every `nixosConfigurations` target except `lxc-*` hosts —
+see "LXC hosts" immediately below for why those are different.**
+
+## LXC hosts
+
+`lxc-*` targets (`lxc-minimal`, `lxc-nix-cache`, `lxc-server`, `lxc-docker`,
+`lxc-gui`, `lxc-pxe-boot`, `lxc-tailscale-router`, `lxc-tor-relay`) are **not** installed via `auto-install.sh` — the
+interactive menu deliberately excludes them. Don't try to select one there;
+`nixos-install` would bind-mount `/` onto `/mnt` (LXC containers have no raw
+disk to partition) and then refuse to touch the filesystem it's currently
+running on — it's designed to protect exactly this case, so it just fails.
+
+`modules/platforms/lxc.nix` imports nixpkgs' own
+`virtualisation/proxmox-lxc.nix` module, which gives every `lxc-*` host a
+`config.system.build.tarball` output — a complete, directly Proxmox-importable
+container image, no install step at all:
+
+```sh
+nix build .#nixosConfigurations.lxc-minimal.config.system.build.tarball
+```
+
+This is a plain rootfs tarball, not a `vzdump` backup archive — restoring it
+with `pct restore` fails ("archive contains no configuration file"), since
+that command expects backup-archive metadata this tarball doesn't have. Use
+it as a CT *template* instead: drop it under Proxmox's template storage
+(conventionally `/var/lib/vz/template/cache/` for the `local` storage, or
+the GUI's "Create CT" → upload-as-template flow) and create a container
+from it, supplying all config on the command line since a template has none
+of its own:
+
+```sh
+pct create <vmid> local:vztmpl/<file>.tar.xz \
+  --unprivileged 1 --features nesting=1,keyctl=1 \
+  --rootfs local-lvm:8 --hostname <name> --cores 2 --memory 2048 --swap 2048 \
+  --net0 name=eth0,bridge=vmbr0,ip=dhcp
+pct start <vmid>
+```
+
+Every one of those extra flags is load-bearing, confirmed by actually
+booting one:
+
+- `--unprivileged 1` — `modules/platforms/lxc.nix` sets
+  `proxmoxLXC.privileged = false`, so the image assumes it's running
+  unprivileged. `pct create`'s own CLI default for this flag is
+  privileged (unlike the web UI, whose checkbox defaults the other way)
+  — omit it and you get a privileged container running a NixOS config
+  that assumes unprivileged, a real mismatch.
+- `--features nesting=1,keyctl=1` — required for a modern (v247+)
+  systemd guest to boot unprivileged at all. Without it, AppArmor denies
+  the nested user namespaces and credential mounts systemd routinely
+  uses (even plain getty units) — every getty crash-loops on a denied
+  `/run/credentials/*` mount every ~3s (this is what garbage on the
+  console turns out to be) while core services like `nsncd` fail the
+  same way, and the system never finishes activating.
+- `--swap 2048` — `--memory` doesn't touch swap; it silently stays at
+  Proxmox's own 512M default otherwise. Match it to `--memory` unless
+  you deliberately want otherwise.
+
+First boot runs `boot.postBootCommands` (registers the Nix store DB and
+system profile) — there's no separate activation step to run yourself.
+`scripts/proxmox/create-proxmox-resource.sh --type lxc --host <name>` automates all
+of this (host-key handling, building the tarball directly on the Proxmox
+node itself, `pct create` with the flags above) — see its `--help`.
+
+Host keys still need pre-seeding the same way as any other host — the
+sops-nix activation-vs-first-boot race is identical regardless of how the
+image reaches the machine. Unlike the ISO/PXE installer (where
+`modules/installer/host-keys.nix` bakes *every* `host-keys/` entry into
+`/etc/host-keys/` for `auto-install.sh` to pick from and copy at install
+time — see "Host keys" below), an `lxc-*` tarball has no install step to
+copy anything during, so `modules/platforms/lxc.nix` bakes this *one*
+target's key straight into `/etc/ssh/ssh_host_ed25519_key(.pub)` directly,
+keyed by its own exact flake target name (`config.environment.etc` can't
+be read back from within a module still contributing to it, so this comes
+in via `specialArgs.flakeTarget`, set by `flake.nix`'s `mkTarget`):
+
+```sh
+NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" \
+  nix build .#nixosConfigurations.lxc-nix-cache.config.system.build.tarball --impure
+```
+
+Confirmed the hard way: without this, the tarball's own built-in system
+just generates a fresh host key at first boot like any host would, which
+can never match whatever `.sops.yaml` actually trusts for that target —
+`sops-install-secrets` fails with `Error getting data key: 0 successful
+groups required, got 0`, and *every* secret (including this host's own
+login) permanently fails to decrypt, silently — no error in the boot log
+at all, since the activation step that would install secrets only runs on
+a from-scratch first activation and skips silently once `/run/current-system`
+already exists. `scripts/proxmox/create-proxmox-resource.sh` always builds with
+`NIXOS_HOST_KEYS_DIR` set for this reason.
+
+## Layout
+
+- `modules/installer/common.nix` — shared by every installer target: SSH
+  access, users, the generated `/etc/auto-install.sh` script, and the
+  `programs.bash.loginShellInit` hook that runs it on login.
+- `modules/installer/iso.nix` — ISO/netboot-specific: imports the stock
+  `installation-cd-minimal.nix` module plus `common.nix`. Also used, paired
+  with `netboot-minimal.nix`, to build the PXE netboot variant (see
+  `docs/pxe-boot.md`).
+- `modules/installer/host-keys.nix` — optionally bakes pre-generated SSH
+  host keys into the image; see "Host keys" below.
+- `scripts/secrets/sync-host-keys.sh` — admin-workstation tool that generates,
+  registers, and (via `--remove`/`--regenerate-all-keys`) retires host
+  keys; see "Creating a New Machine" below.
+- `scripts/secrets/prepare-host-key.sh` — narrower predecessor: generates a single
+  key by an arbitrary name without touching `.sops.yaml`. Still useful for
+  pre-generating a key *before* its flake target exists (`sync-host-keys.sh`
+  can only act on targets `nixosConfigurations` already has); otherwise
+  `sync-host-keys.sh` does the same thing and more.
+
+Flake outputs:
+
+```nix
+nixosConfigurations.installer   # ISO/netboot installer image
+
+packages.x86_64-linux.iso       # installer ISO/netboot image
+packages.x86_64-linux.pxe       # auto-installer netboot bundle (kernel + initrd + ipxe script)
+packages.x86_64-linux.pxe-minimal  # vanilla NixOS minimal netboot bundle (no installer wiring)
+```
+
+```sh
+nix build .#iso
+nix build .#pxe
+nix build .#pxe-minimal
+```
+
+There's no `nixosConfigurations.proxmox-lxc` (installer-boots-as-an-LXC-
+container) or `packages.x86_64-linux.lxc`/`.all` anymore. Both existed only
+to let the installer itself run as an LXC container so you could
+`nixos-install` some *other* host from within it — but LXC targets are
+excluded from the install menu (same bind-mount problem as any LXC
+`nixos-install`), and now have their own direct tarball path anyway (see
+"LXC hosts" above), which left the installer's own LXC form with no real
+use case.
+
+The `pxe` variant is also built automatically as part of the `pxe-boot` host
+itself (`modules/pxe-boot/stage-installer-artifacts.nix`) and served over
+iPXE as the menu's "NixOS Auto-Installer" entry — see `docs/pxe-boot.md`.
+That same host also builds and serves `packages.x86_64-linux.pxe-minimal`,
+a vanilla NixOS minimal netboot image with none of this auto-installer's
+wiring, as a separate "NixOS Minimal" menu entry — also documented in
+`docs/pxe-boot.md`, not covered further here since it's not this installer.
+
+## Host keys
+
+`sops-nix` derives each host's decryption key from its own
+`/etc/ssh/ssh_host_ed25519_key`, generated at **activation** time — before
+systemd would otherwise generate one on first boot. Without pre-seeding this
+key, secrets (including the root/nixos login password) fail to decrypt on a
+genuinely fresh install.
+
+Generated host keys live in `host-keys/` at the repo root (`ssh_host_ed25519_key`
++ `.pub` pairs per hostname). This directory is **gitignored on purpose** —
+private key material must never be committed — which also means flakes can't
+see it through a normal relative path. `modules/installer/host-keys.nix`
+reads it through `builtins.getEnv`, which Nix silently returns as an empty
+string under normal (non-`--impure`) evaluation, so the module is a no-op —
+safe by default, including in CI — unless explicitly opted into:
+
+```sh
+NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build .#iso --impure
+```
+
+When built this way, every key currently in `host-keys/` is baked into the
+image at `/etc/host-keys/<hostname>_ssh_host_ed25519_key(.pub)`, and
+`auto-install.sh` automatically installs whichever one matches the flake
+target selected at install time — no manual per-host scp step needed.
+
+**Trade-off, accepted deliberately for this LAN-only setup:** baking keys in
+means every key present in `host-keys/` at build time becomes readable by
+anyone who can reach the built image — including, for the PXE variant, anyone
+who can reach the `pxe-boot` host's unauthenticated HTTP server. This is
+considered acceptable here because `pxe-boot` sits behind LAN-only network
+infrastructure, not the open internet. If that ever changes, reconsider this
+default.
+
+`auto-install.sh` still supports the older manual path as a fallback: if a
+host's key isn't baked in (`/etc/host-keys`), it checks `/root/host-keys`
+next, where you can `scp` a key in after boot, same as before this migration.
+If neither has it and the script is running interactively (an actual
+operator at the other end of stdin, not an unattended run), it prompts for
+an arbitrary directory to check (a mounted USB stick, another filesystem,
+etc.) and copies the key pair into `/root/host-keys` from there if found.
+
+## Storage
+
+Disk partitioning is handled by Disko — the installer has no hardcoded
+`parted`/`mkfs`/`mkswap`/`mount` commands, and `auto-install.sh` runs
+`disko --mode destroy,format,mount` unconditionally, no branching on whether
+the target has a Disko config. Every host reachable through this menu has
+one:
+
+- `proxmox-*` (`modules/disko/proxmox.nix`): a real GPT partition table
+  (ESP + swap + root) on `/dev/sda`.
+- `linode-*` (`modules/disko/linode.nix`): Linode provisions and sizes
+  `/dev/sda`/`/dev/sdb` itself as whole, unpartitioned block devices before
+  the OS ever boots, so this declares them with `destroy = false` (skips
+  disko's wipe stage for these disks entirely — see the option's own docs)
+  and a bare `filesystem`/`swap` content type with no partition table, and
+  the format step it does run only calls `mkfs`/`mkswap` if `blkid` shows
+  the device isn't already formatted — a re-run against an
+  already-provisioned Linode disk is a no-op, not a wipe.
+
+`lxc-*` is the only category without one — it's excluded from this menu
+entirely (see "LXC hosts" above), so it never reaches this code path.
+
+## Installer process
+
+`scripts/installer/auto-install.sh` is a real, version-controlled shell
+script — not an inline Nix string. It sources `scripts/env.sh` for
+`LAN_DOMAIN` itself (same as every other script in `scripts/`), so it
+behaves identically whether it's run straight from a git checkout (e.g.
+manually, from a stock NixOS ISO that isn't this repo's own installer
+image) or from inside the built installer image. That's also why it's
+baked in at `/etc/nixos-installer/installer/auto-install.sh` rather than a
+flat `/etc/auto-install.sh` — `modules/installer/common.nix` bakes
+`scripts/env.sh` in alongside it at `/etc/nixos-installer/env.sh`,
+preserving the same relative layout (`installer/auto-install.sh` ->
+`../env.sh`) the checked-out repo has, so the script's own
+`source ".../env.sh"` line resolves correctly in both places without any
+Nix-level templating.
+
+Once running, it:
+
+1. Queries `nixosConfigurations` from this flake over the network (`git+https://<lanDomain>/beatzaplenty/nixos.git`) — this happens at *install* time, not build time, so a generic installer image always sees whatever hosts are currently committed, without needing a rebuild.
+2. Presents them as a menu; confirms the choice.
+3. Skips the `nix-cache` substituter when installing a `nix-cache` host itself (consistent with that host's own runtime config).
+4. Runs `disko --mode destroy,format,mount` (see "Storage" above — every host reachable through this menu has a Disko config, so this is unconditional).
+5. Installs the target's SSH host key from `/etc/host-keys` or `/root/host-keys` (see "Host keys" above).
+6. Runs `nixos-install --flake <url>#<choice> --no-root-password`.
+7. Cleans up and reboots.
+
+## Creating a new machine
+
+Do this instead of jumping straight to a plain install whenever the target
+host consumes any sops-nix secret — as of this writing, that's every host
+(`modules/common/configuration.nix` puts the root/nixos password hash and the
+GitHub token behind sops-nix for all of them).
+
+1. **Add the flake target** — `hosts/<name>/host.nix` plus the matching
+   `mkTarget { ... }` entry in `flake.nix`'s `generatedTargets` (see
+   "Composition pattern" in `CLAUDE.md`). No secrets involved yet, so this
+   is safe to commit on its own if you want a clean history.
+
+2. **On your admin workstation, generate and register its host key:**
+
+   ```sh
+   ./scripts/secrets/sync-host-keys.sh <flake-target>
+   ```
+
+   This generates `host-keys/<flake-target>_ssh_host_ed25519_key(.pub)`,
+   adds it as a new `.sops.yaml` anchor, works out which `secrets/*.yaml`
+   files this specific host actually references (from its own
+   `config.sops.secrets`, not guessed), adds it to each one's
+   `key_groups`, and re-encrypts them with `sops updatekeys` — no manual
+   YAML editing. Safe to re-run; it only fills in what's missing.
+
+   Doing this for every host that needs one at once — after adding several
+   new targets, or just to catch up any that were missed — is
+   `./scripts/secrets/sync-host-keys.sh --all`. See `scripts/secrets/sync-host-keys.sh --help`
+   for its other modes (`--remove`, `--regenerate-all-keys`).
+
+3. **Commit and push.** The flake build the installer uses has to see the
+   new recipient before you install, or decryption fails on first boot
+   regardless of the next step.
+
+4. **Build the installer image with keys baked in** (or reuse an already-serving `pxe-boot` host, which does this automatically once redeployed):
+
+   ```sh
+   NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build .#iso --impure
+   ```
+
+5. **Boot it on the target machine**, log in, select the new host's flake
+   target from the menu, confirm. `auto-install.sh` finds the baked-in key,
+   runs Disko + `nixos-install`, and reboots.
+
+6. **Verify after reboot:**
+
+   ```sh
+   ssh <new-host> ls /run/secrets/
+   ```
+
+   If that's empty or login fails, the host's age key most likely wasn't in
+   `.sops.yaml` (or wasn't re-encrypted into the secrets file it needs) when
+   `nixos-install` ran — fix `.sops.yaml`/`secrets/*.yaml`, push, then re-run
+   `nixos-install --flake .#<hostname> --no-root-password` from a rescue
+   environment against the existing `/mnt`, or just redo the install.
+
+## Safety
+
+This installer is destructive: `disko --mode destroy,format,mount` erases
+any disk defined by the selected host's Disko configuration. Always verify
+the selected host profile and target machine before confirming.

docs/beszel.md

@@ -0,0 +1,113 @@
+# Beszel agent
+
+[Beszel](https://github.com/henrygd/beszel) is the monitoring dashboard used
+in this LAN. The hub runs as a Docker container on `docker.sweet.home` (port
+`vars.ports.beszelHub`, 8090). Each monitored NixOS host runs a
+`beszel-agent` that connects back to the hub.
+
+---
+
+## How it works
+
+Everything is handled by a single module:
+
+**`modules/beszel/enable-agent.nix`** — imported by a build type. It:
+- Enables `beszel-agent`
+- Sets `HUB_URL` to `docker.sweet.home:8090`
+- Sets `KEY` from `vars.beszelHubKey` (`variables.nix`) — the hub's SSH
+  public key, shared by every agent. Update `beszelHubKey` if the docker
+  host is ever rebuilt and the hub generates a new keypair.
+- Reads the universal `beszel-token` from `secrets/common.yaml` via sops
+  and passes it to the agent as `TOKEN` in an env file
+- Fixes an upstream bug where the agent couldn't persist its hub-pairing
+  fingerprint across restarts (adds a real `StateDirectory`)
+
+A host file needs no beszel configuration at all — just import the module
+in the build type and add the system in the hub UI.
+
+---
+
+## Adding beszel to a new build type
+
+Add `../beszel/enable-agent.nix` to the `imports` list in
+`modules/build-types/<type>.nix`:
+
+```nix
+imports = [
+  ../beszel/enable-agent.nix
+  # ... other imports
+];
+```
+
+That's the only change required. The host file needs nothing.
+
+---
+
+## Adding a new system to the hub
+
+1. Rebuild and deploy the host with its build type importing `enable-agent.nix`.
+2. Open the beszel hub (`http://docker.sweet.home:8090`).
+3. Go to **Systems → Add system**, enter the host's IP and the default port
+   (45876). The agent will connect and the system will appear as active.
+
+---
+
+## One-time setup: add the token to `secrets/common.yaml`
+
+The universal token is stored once in the common secrets file, shared by all
+agents. Only needed once, not per-host:
+
+```sh
+sops secrets/common.yaml
+```
+
+Add:
+```yaml
+beszel-token: <token from the beszel hub Settings → Keys>
+```
+
+`secrets/common.yaml` is already a sops recipient for every host via their
+SSH host keys, so no additional sops recipient setup is needed.
+
+---
+
+## Optional: monitoring extra filesystems
+
+To report disk usage for a mount beyond the root filesystem, add
+`EXTRA_FILESYSTEMS` in the host file:
+
+```nix
+services.beszel.agent.environment = {
+  EXTRA_FILESYSTEMS = "/mnt/data";   # colon-separated for multiple paths
+};
+```
+
+The `server` host uses this to expose its ZFS data pool:
+
+```nix
+services.beszel.agent.environment = {
+  EXTRA_FILESYSTEMS = "${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
+  LOG_LEVEL = "debug";
+};
+```
+
+---
+
+## Optional: monitoring Docker containers
+
+`enable-agent.nix` has a commented-out line for Docker monitoring:
+
+```nix
+#DOCKER_HOST = "tcp://docker-socket-proxy:2375";
+```
+
+Uncomment it if the host runs docker-socket-proxy and you want per-container
+stats. Hosts without Docker should leave it commented out.
+
+---
+
+## If the hub key changes
+
+If the docker host is ever rebuilt and beszel generates a new SSH keypair,
+update `beszelHubKey` in `variables.nix` and rebuild all beszel-enabled hosts.
+The new key is visible in the beszel hub under **Settings → Keys**.

docs/flake-lock-automation.md

@@ -8,9 +8,14 @@ and to verify that declared NixOS hosts still evaluate after dependency updates.
 - A scheduled workflow runs `nix flake update` once per week.
 - On GitHub, any resulting `flake.lock` change is proposed through a pull request.
 - On Gitea, the workflow can commit and push `flake.lock` directly when PR automation is not configured.
-- A separate CI workflow evaluates every configured host before merge, listed
+- A separate CI workflow runs `scripts/codex-maintenance.sh` before merge.
-  dynamically via `nix eval --json .#nixosConfigurations --apply builtins.attrNames`
+  Its default mode scopes eval to the hosts/packages a change can affect,
-  rather than hand-enumerated, so it can't drift as `<platform>-<buildtype>`
+  determined from a git diff against the PR base — but a `flake.lock` change
+  is treated as repo-wide and always falls back to evaluating every host, so
+  a lock-file update PR still gets full coverage. Hosts are still listed
+  dynamically via
+  `nix eval --json .#nixosConfigurations --apply builtins.attrNames` rather
+  than hand-enumerated, so that fallback can't drift as `<platform>-<buildtype>`
   targets are added or removed. See `README.md` for the current target list.
 
 ## Why hosts should stop using `--upgrade-all`

docs/ha-network-audit.md

@@ -0,0 +1,261 @@
+# Storage/Cluster Network Segmentation Audit — pve1.sweet.home
+
+**Date:** 2026-07-29  
+**Scope:** Read-only discovery of pve1.sweet.home host networking, HA cluster VMs (200/201), and Docker CT (105). No changes made.
+
+> **Implementation status — 2026-07-29:** All recommendations from this audit have been
+> implemented in the same session. See `docs/ip-addressing.md` for the current state.
+> Key decisions that diverged from the original recommendations:
+> - VLAN IDs renumbered: cluster → VLAN 10 (192.168.10.x), storage-client → VLAN 20 (192.168.20.x)
+> - Two Pacemaker VIPs: `vip-lan` (192.168.2.229, NFS for LAN) and `vip-storage` (192.168.20.229, NFS + iSCSI for VLAN 20)
+> - NFS served on **both** VIPs (each firewalled to its own subnet); iSCSI available on VLAN 20 but NFS is preferred for docker to support future Docker Swarm multi-host access
+> - `corosync.conf` ring1 added using LAN IPs (RF-1 resolved)
+> - `vmbr2` created and NICs added to HA VMs and docker CT (RF-6/RF-7 resolved)
+> - iSCSI portal remains on `[::0]`; firewall enforces VLAN 20 restriction (RF-4 mitigated)
+> - STONITH still disabled (RF-3 deferred — accepted risk during development phase)
+> - iSCSI ACLs not configured (RF-5 deferred — iSCSI not in active use)
+
+---
+
+## 1. Current State Summary
+
+### pve1.sweet.home Host — Physical NICs
+
+| Interface | Speed/Duplex | Notes |
+|-----------|-------------|-------|
+| `nic0` | 2500 Mb/s / Full (2.5GbE) | Only active physical NIC; sole bridge port for vmbr0 |
+| `nic1` | (not connected / no data) | Present in config, not UP |
+| `wlp4s0` | DOWN | WiFi, unused |
+
+No bonding configured. Every guest's traffic ultimately funnels through the single 2.5GbE `nic0`.
+
+### Proxmox Bridges
+
+| Bridge | Physical NIC | Host IP | Subnet | VLAN-aware | Purpose (current) |
+|--------|-------------|---------|--------|------------|-------------------|
+| `vmbr0` | `nic0` (2.5GbE) | 192.168.2.245/24 | 192.168.2.0/24 | No | General LAN, management, **iSCSI/NFS VIP** |
+| `vmbr1` | **none** (internal-only) | — | 192.168.4.224/29 | No | Corosync heartbeat + DRBD replication |
+
+`vmbr1` has `bridge-ports none` in `/etc/network/interfaces.d/vmbr1.conf` — it is a purely software bridge with zero physical uplink. All traffic on it stays inside the hypervisor's memory.
+
+### Guest NIC Assignments
+
+| Guest | VMID | Role | NIC | Bridge | IP | Traffic type |
+|-------|------|------|-----|--------|----|--------------|
+| nix-cache | CT 102 | Build cache | eth0 | vmbr0 | DHCP/LAN | LAN |
+| pxe-boot | CT 103 | PXE/TFTP | eth0 | vmbr0 | DHCP/LAN | LAN |
+| tor-relay | CT 104 | Tor | eth0 | vmbr0 | DHCP/LAN | LAN |
+| **docker** | **CT 105** | **Docker host** | **eth0** | **vmbr0** | **192.168.2.225/24** | **LAN only** |
+| pdm | CT 106 | Proxmox mgmt | eth0 | vmbr0 | 192.168.2.220/24 | LAN |
+| server | VM 101 | General server | net0 | vmbr0 | DHCP/LAN | LAN |
+| tailscale-router | VM 107 | Tailscale exit | net0 | vmbr0 | DHCP/LAN | LAN |
+| domain-controller | VM 108 | FreeIPA | net0 | vmbr0 | 192.168.2.253/24 | LAN |
+| **ha-server-1** | **VM 200** | **HA primary** | **net0** | **vmbr0** | **192.168.2.228/24 + VIP 192.168.2.229/24** | **LAN + VIP** |
+| **ha-server-1** | **VM 200** | **HA primary** | **net1** | **vmbr1** | **192.168.4.228/29** | **Corosync + DRBD** |
+| **ha-server-2** | **VM 201** | **HA secondary** | **net0** | **vmbr0** | **192.168.2.227/24** | **LAN** |
+| **ha-server-2** | **VM 201** | **HA secondary** | **net1** | **vmbr1** | **192.168.4.227/29** | **Corosync + DRBD** |
+
+### Corosync/Pacemaker State
+
+- **Transport:** knet/UDP
+- **Rings:** 1 only — ring0 on `192.168.4.228` / `192.168.4.227` (vmbr1/ens19)
+- **Cluster status:** Both nodes online, DC = ha-server-1, quorum achieved
+- **STONITH:** `stonith-enabled: false`
+- **no-quorum-policy:** `ignore`
+- **Resources (all active on ha-server-1):**
+  - `ms-drbd0` — promotable DRBD clone (Primary: ha-server-1, Secondary: ha-server-2)
+  - `xfs-data` — XFS on `/dev/drbd0` → `/srv/ha-data`
+  - `iscsi-target` — targetctl service
+  - `nfs-server` — nfs-server service
+  - `vip` — IPaddr2 at **192.168.2.229/24** (no `nic=` parameter specified; floats to ens18/vmbr0 automatically based on subnet match)
+- **Resource ordering:** ha-group starts only after DRBD is promoted; collocated with Promoted DRBD clone.
+
+### DRBD State
+
+- **Resource:** `ha-data` (DRBD 8.4.11 kernel module, config in `/etc/drbd.conf`)
+- **Protocol:** C (synchronous)
+- **Replication endpoints:**
+  - ha-server-1: `192.168.4.228:7789` (ens19 / vmbr1)
+  - ha-server-2: `192.168.4.227:7789` (ens19 / vmbr1)
+- **State at audit time:** Initial sync in progress — ~20% complete, ~40 MB/s, ~34 min remaining (100 GB disk)
+- **Fencing config:** `fencing resource-only` + fence-peer/unfence-peer handlers
+
+### iSCSI Target
+
+- **IQN:** `iqn.2026-01.home.sweet:ha-storage`
+- **Portal:** `[::0]:3260` — confirmed listening on all interfaces (`ss -tnlp` shows `*:3260 *:*`)
+- **LUN 0:** fileio backstore — `/srv/ha-data/iscsi-lun.img` (10 GiB, write-thru)
+- **ACLs:** **None** (`no-gen-acls`, `no-auth`)
+- **VIP (intended portal):** 192.168.2.229 — on vmbr0/LAN, no storage-NIC-specific binding
+
+### NFS Exports
+
+Served from the same `ha-group` as iSCSI (starts/stops together):
+
+| Export path | Client subnet |
+|------------|---------------|
+| `/srv/ha-data/docker/{config,databases,volumes,nextcloud-data}` | 192.168.2.0/24 |
+| `/srv/ha-data/proxmox/{iso,lxc}` | 192.168.2.0/24 |
+| `/srv/ha-data/pxe-boot/images` | 192.168.2.0/24 |
+| `/srv/ha-data/raspi/volumes` | 192.168.2.0/24 |
+
+All NFS exports restrict to 192.168.2.0/24 and are served via the VIP at 192.168.2.229. `rw,sync,no_subtree_check,no_root_squash`.
+
+### Docker Host Current State
+
+- **Single NIC:** eth0 on vmbr0, 192.168.2.225/24, gateway 192.168.2.254
+- **Route to storage network (192.168.4.x):** none — no NIC and no route
+- **iSCSI sessions:** none
+- **iSCSI nodes discovered:** none
+- **Docker networks:** several active compose-project networks (core_traefik, core_nextcloud, core_passbolt, core_gramps, core_docker-socket-proxy, plus CI isolation networks)
+
+---
+
+## 2. Risk Flags
+
+### RF-1: Corosync has only one ring (no heartbeat path redundancy)
+
+`corosync.conf` defines only `ring0_addr` for each node, using 192.168.4.x on vmbr1. No `ring1_addr` / second knet link is configured. On a single Proxmox host, vmbr1 is a software bridge (no physical NIC), so physical link failure is not the concern — but a kernel network stack hiccup, a `pveproxy` restart dropping bridge state, or vmbr1 getting disrupted during heavy DRBD sync all leave corosync with zero fallback path. Missed heartbeats on a two-node cluster with `no-quorum-policy: ignore` do not cause a clean shutdown; they cause a false failover or split-brain.
+
+Adding the LAN addresses (192.168.2.228 / 192.168.2.227 via ens18/vmbr0) as a second knet link would provide a backup path with no infrastructure changes needed.
+
+### RF-2: Corosync heartbeat and DRBD replication share vmbr1 — no isolation between them
+
+Both corosync (knet/UDP, ~1 kB heartbeat packets every ~100 ms) and DRBD replication (protocol C, synchronous, syncing at ~40 MB/s on a 100 GB initial fill at audit time) traverse the same `vmbr1` virtual bridge and terminate on the same ens19 NIC pair inside each HA VM. Under heavy DRBD write load, the guest-kernel scheduler's NIC transmit queue processes both flows together. While corosync's heartbeat is tiny, the absence of QoS/priority marking on vmbr1 means a DRBD burst can delay a heartbeat enough to trigger a ring fault warning. This is a latent risk that grows under high-write workloads.
+
+### RF-3: STONITH disabled — split-brain protection relies solely on DRBD's resource-only fencing
+
+`stonith-enabled: false` in the CIB. With `no-quorum-policy: ignore`, both nodes will continue running if corosync loses communication. DRBD's `fencing resource-only` does call `fence-peer` before allowing a Primary promotion, which provides some protection, but there is no hard external power fence to guarantee the other node actually stops. In a real split-brain (both nodes believe they are Primary), data corruption on the shared XFS filesystem is possible. **This is the highest-severity risk in the current setup.**
+
+Getting STONITH to work on Proxmox-hosted VMs requires either a `fence_pve` agent (Proxmox API fencing) or `fence_virtd` (QEMU guest agent fencing). Neither is configured.
+
+### RF-4: iSCSI portal bound to `[::0]:3260` — listens on every interface, not just the VIP
+
+The targetcli portal is `[::0]:3260` (confirmed: `*:3260 *:*` in ss). This means the target is reachable on:
+- 192.168.2.229 (VIP — correct, failover-safe)
+- 192.168.2.228 (ha-server-1 LAN IP — does **not** move during failover; an initiator session connecting here would break on failover)
+- 192.168.4.228 (storage NIC — not reachable by the Docker host today, but unintentionally exposed)
+
+Binding the portal explicitly to the VIP IP instead of wildcard eliminates the non-VIP reachability risks.
+
+### RF-5: iSCSI has zero ACLs and no authentication
+
+`targetcli ls` shows `acls: 0`, `no-gen-acls`, `no-auth`. Any host that can reach port 3260 on any of the above IPs can log into the LUN with no credentials. The Docker host is not yet configured as an initiator — but neither is it blocked.
+
+### RF-6: Docker host has no path to the storage network — iSCSI would traverse vmbr0/nic0
+
+CT 105 (docker, 192.168.2.225) has one NIC, on vmbr0. To reach the VIP at 192.168.2.229, iSCSI traffic would travel:
+
+```
+docker (eth0/vmbr0) → nic0 (2.5GbE) → vmbr0 → tap200i0 (VM 200 net0/ens18)
+```
+
+All of the following share this same path over vmbr0 → nic0:
+- Docker container traffic (outbound and inter-container)
+- CI/CD runner traffic (Gitea Actions jobs visible in `docker network ls`)
+- NFS mounts from pxe-boot, proxmox host itself, and other LAN clients
+- iSCSI block traffic (protocol-sensitive to latency and retransmit)
+
+A Nextcloud upload or a CI `nix build` job can saturate nic0 and starve the iSCSI session, causing command timeouts and filesystem errors on the Docker host.
+
+### RF-7: VIP is on the LAN interface with no storage-specific binding
+
+The Pacemaker `vip` resource specifies `ip=192.168.2.229, cidr_netmask=24` with no `nic=` parameter. Pacemaker's IPaddr2 agent selects the interface by longest-prefix match, landing it on ens18 (vmbr0/LAN). There is no way to keep this VIP from competing with general LAN traffic on nic0 without moving the VIP to a separate subnet on a different virtual bridge.
+
+---
+
+## 3. Recommended Target Layout
+
+### Design constraints
+
+- Single Proxmox host: all traffic ultimately shares nic0's bandwidth. The goal is QoS partitioning via separate bridges and subnets, not true physical isolation.
+- Future physical split: bridge/VLAN IDs chosen here should map cleanly to physical uplink VLAN tags when the HA nodes move to separate hardware.
+
+### Proposed bridge layout
+
+| Bridge | Physical port | VLAN tag (future) | Subnet | Purpose |
+|--------|-------------|-------------------|--------|---------|
+| `vmbr0` | nic0 | untagged / VLAN 1 | 192.168.2.0/24 | **LAN/management only** — no storage traffic |
+| `vmbr1` | (none / VLAN 10 on future trunk) | VLAN 10 | 192.168.4.224/29 | **Corosync heartbeat + DRBD replication** (current, keep) |
+| `vmbr2` *(new)* | (none / VLAN 20 on future trunk) | VLAN 20 | 192.168.5.0/24 | **Storage: iSCSI + NFS client access** |
+
+This is the minimum-disruption path: vmbr1 stays as-is (no DRBD reconfiguration needed), and the new vmbr2 gives the Docker host a direct path to the storage VIP without crossing vmbr0.
+
+If stricter isolation is later desired, DRBD can be migrated from vmbr1 to vmbr2 in a separate maintenance window (see §5), leaving vmbr1 as corosync-only.
+
+### Per-guest NIC assignments in target layout
+
+| Guest | VMID | NIC | Bridge | Proposed IP | Purpose |
+|-------|------|-----|--------|-------------|---------|
+| ha-server-1 | VM 200 | net0 | vmbr0 | 192.168.2.228/24 | LAN/management (keep) |
+| ha-server-1 | VM 200 | net1 | vmbr1 | 192.168.4.228/29 | Corosync + DRBD (keep) |
+| ha-server-1 | VM 200 | **net2 (new)** | **vmbr2** | **192.168.5.1/24** | iSCSI + NFS storage client |
+| ha-server-2 | VM 201 | net0 | vmbr0 | 192.168.2.227/24 | LAN/management (keep) |
+| ha-server-2 | VM 201 | net1 | vmbr1 | 192.168.4.227/29 | Corosync + DRBD (keep) |
+| ha-server-2 | VM 201 | **net2 (new)** | **vmbr2** | **192.168.5.2/24** | iSCSI + NFS storage client |
+| docker | CT 105 | net0 | vmbr0 | 192.168.2.225/24 | LAN/management (keep) |
+| docker | CT 105 | **net1 (new)** | **vmbr2** | **192.168.5.10/24** | iSCSI + NFS |
+
+**VIP target:** `192.168.5.100/24` on vmbr2. The Pacemaker `vip` resource changes from `ip=192.168.2.229` to `ip=192.168.5.100, nic=<ens20>` (whichever name the new NIC gets inside the HA VMs). The existing `192.168.2.229` LAN VIP can optionally be retained as a separate static alias on ens18 for management-plane access, but should not be the iSCSI portal target.
+
+**iSCSI portal:** Bind to `192.168.5.100:3260` instead of `[::0]:3260`. In targetcli: remove the wildcard portal, add `portals/ create 192.168.5.100`.
+
+**NFS exports:** NFS is a file-level protocol and is fine being accessed over a routed path. After the VIP moves, non-docker LAN clients (proxmox host, pxe-boot, raspi) can reach NFS either via a static route to 192.168.5.0/24 or by keeping a secondary static alias at 192.168.2.229 on ens18 dedicated to NFS. Either approach works — NFS handles reconnect gracefully in ways iSCSI block I/O cannot.
+
+**Corosync second ring (independent, low-disruption improvement):**
+
+Add a second knet link using the LAN addresses as a backup heartbeat path. Edit `corosync.conf` on both nodes:
+
+```
+node { ring0_addr: 192.168.4.228; ring1_addr: 192.168.2.228; name: ha-server-1; nodeid: 1; }
+node { ring0_addr: 192.168.4.227; ring1_addr: 192.168.2.227; name: ha-server-2; nodeid: 2; }
+```
+
+Requires a corosync service restart (brief cluster pause, ~5 seconds), no interface or bridge changes.
+
+**Future physical-host split:**  
+When ha-server-1 and ha-server-2 move to separate physical machines, vmbr1 and vmbr2 become VLAN-tagged sub-interfaces on a physical trunk (e.g. VLAN 10 → cluster, VLAN 20 → storage). The bridge/subnet/IP layout above is designed so the tag numbers can be layered onto the existing addresses without renumbering.
+
+---
+
+## 4. Gap List
+
+| Gap | Action needed |
+|-----|--------------|
+| `vmbr2` does not exist on pve1 | Create internal bridge: `/etc/network/interfaces.d/vmbr2.conf` with `bridge-ports none`, `inet manual` |
+| VM 200 and VM 201 have no net2 | `qm set 200 --net2 virtio,bridge=vmbr2` / `qm set 201 --net2 virtio,bridge=vmbr2` (hot-plug, no reboot needed) |
+| CT 105 has no net1 | `pct set 105 --net1 name=eth1,bridge=vmbr2,ip=192.168.5.10/24` |
+| HA VMs have no OS config for the new NIC | NixOS `networking.interfaces.<ens20>` with `ipv4.addresses = [{address="192.168.5.1"; prefixLength=24;}]` per host (name may differ — check `ip link` after hotplug) |
+| VIP needs to move to 192.168.5.100 on vmbr2 | `pcs resource update vip ip=192.168.5.100 cidr_netmask=24 nic=<ens20>` |
+| iSCSI portal bound to `[::0]` | `targetcli /iscsi/iqn.2026-01.home.sweet:ha-storage/tpg1/portals delete ::0 3260` then `create 192.168.5.100`; save and restart via `pcs resource restart iscsi-target` |
+| iSCSI ACLs empty | Get Docker initiator IQN via `iscsiadm -m iface` on CT 105, then add via targetcli `acls/ create <iqn>` |
+| Docker host has no iSCSI initiator config | `iscsiadm -m discoverydb -t sendtargets -p 192.168.5.100 -D` then `iscsiadm -m node -l` once ACLs are set |
+| Corosync single ring | Add `ring1_addr` entries in `corosync.conf` using LAN IPs; restart corosync cluster-wide (one node at a time) |
+| STONITH not configured | Evaluate `fence_pve` (Proxmox API agent); document accepted risk if deferred |
+| DRBD still on vmbr1 (optional, separate window) | Stop ms-drbd0 via pcs, edit `/etc/drbd.conf` on both nodes (change `192.168.4.x` → `192.168.5.x`), restart DRBD, re-enable via pcs |
+
+---
+
+## 5. Migration Notes
+
+### Non-disruptive (no service impact)
+
+- **Create vmbr2 on pve1:** Bridge definition edit only; no effect on existing bridges or guests.
+- **Hot-add net2 to VMs 200/201:** Proxmox allows adding a NIC without reboot (`qm set 200 --net2 ...`). The NIC appears inside the VM immediately via QEMU hotplug but will be unconfigured (down) inside NixOS until the NixOS config is deployed — no impact on running services.
+- **Add net1 to CT 105:** LXC NIC hotplug works similarly; CT does not need to restart.
+- **Add corosync ring1:** Requires `systemctl restart corosync` on both nodes (one at a time). Pacemaker briefly sees corosync go offline and recover; with two nodes and `wait_for_all: 0`, this typically completes in under 5 seconds and resources stay running.
+
+### Disruptive — requires maintenance window
+
+- **Move VIP from 192.168.2.229 to 192.168.5.100:** `pcs resource update vip ip=192.168.5.100` causes Pacemaker to immediately stop the old VIP and start the new one. Any NFS mounts referencing 192.168.2.229 will stall until remounted at the new address (or a static alias is added at 192.168.2.229 on ens18). No iSCSI sessions exist yet, so no iSCSI disruption.
+
+- **Change iSCSI portal from `[::0]` to VIP-specific:** Requires `pcs resource restart iscsi-target` after the targetcli portal change — brief target unavailability. Any initiator sessions (once configured) will need to re-login.
+
+- **Migrate DRBD replication from 192.168.4.x to 192.168.5.x** (optional — only needed to give corosync sole ownership of vmbr1):
+  1. `pcs resource disable ms-drbd0` — demotes DRBD Primary, stops ha-group (unmounts XFS, stops iSCSI + NFS + VIP)
+  2. `drbdadm down ha-data` on both nodes
+  3. Edit `/etc/drbd.conf` on both nodes (change `address` lines)
+  4. `drbdadm up ha-data` on both nodes
+  5. `pcs resource enable ms-drbd0` — Pacemaker re-promotes, mounts, starts services
+
+  DRBD does **not** require a full resync when only the address changes — the disk data and metadata are unchanged; only the TCP connection endpoint changes. However, the initial sync was in progress at audit time (~20% at ~40 MB/s). Recommend waiting for that sync to complete before scheduling this migration.

docs/ip-addressing.md

@@ -0,0 +1,225 @@
+# IP Addressing Scheme
+
+## Subnets
+
+| Subnet | VLAN | CIDR | Purpose | Routed? |
+|---|---|---|---|---|
+| LAN | 2 (native/untagged) | `192.168.2.0/24` | General LAN — clients and infrastructure | Yes (gateway .254) |
+| Cluster | 10 | `192.168.10.224/29` | HA file server DRBD replication + Corosync heartbeat | No — internal `vmbr1` only, no uplink |
+| Storage client | 20 | `192.168.20.0/24` | HA file server NFS (and iSCSI if needed) — docker and swarm nodes mount from VIP here | No — internal `vmbr2` only, no uplink |
+
+The cluster and storage-client subnets never leave pve1. `vmbr1` and `vmbr2` are Proxmox Linux
+bridges with no physical port attached; traffic between guests on each bridge stays in-kernel.
+
+VLAN IDs match the third octet of each subnet (VLAN 2 → 192.168.**2**.x, VLAN 10 → 192.168.**10**.x,
+VLAN 20 → 192.168.**20**.x). The host octet is consistent across all subnets — e.g. ha-node1
+is always `.228`: `192.168.2.228` (LAN), `192.168.10.228` (cluster), `192.168.20.228` (storage client).
+
+**Protocol separation** (enforced by firewall on HA nodes):
+- NFS (ports 111, 2049, 20048): both subnets, each restricted to its own CIDR
+  - VLAN 2 only → `vip-lan` (192.168.2.229) — pxe-boot and other LAN clients
+  - VLAN 20 only → `vip-storage` (192.168.20.229) — docker, future swarm nodes
+- iSCSI (port 3260): VLAN 20 only — available but not in active use; NFS is preferred
+  for multi-host access (shared volumes across a Docker Swarm require a shared filesystem,
+  not per-host block devices)
+
+---
+
+## DNS Zones
+
+FreeIPA (domain-controller.sweet.home) is authoritative for all zones. Three
+zones correspond to the three subnets — one per VLAN. All zones are internal
+only; no external delegation.
+
+### sweet.home — VLAN 2 (192.168.2.x)
+
+General LAN zone. All infrastructure hostnames live here.
+
+| Hostname | A record | Notes |
+|---|---|---|
+| `domain-controller.sweet.home` | `192.168.2.253` | FreeIPA / KDC / DNS |
+| `ha-vip-lan.sweet.home` | `192.168.2.229` | Pacemaker `vip-lan` — NFS for LAN clients |
+| `ha-server-1.sweet.home` | `192.168.2.228` | HA node 1 management NIC |
+| `ha-server-2.sweet.home` | `192.168.2.227` | HA node 2 management NIC |
+| `server.sweet.home` | `192.168.2.226` | Current ZFS/NFS server (retiring) |
+| `docker.sweet.home` | `192.168.2.225` | Docker/Traefik host |
+| `nix-cache.sweet.home` | `192.168.2.224` | Nix binary cache + remote builder |
+| `pxe-boot.sweet.home` | `192.168.2.223` | PXE / TFTP / HTTP netboot |
+| `tailscale-router.sweet.home` | `192.168.2.222` | Tailscale exit node |
+| `tor-relay.sweet.home` | `192.168.2.221` | Tor relay |
+| `pdm.sweet.home` | `192.168.2.220` | Proxmox Deploy Manager |
+| `nixos.sweet.home` | `192.168.2.39` | Bare-metal workstation (DHCP) |
+| `pve1.sweet.home` | `192.168.2.245` | Proxmox VE hypervisor |
+| `pbs.sweet.home` | `192.168.2.244` | Proxmox Backup Server |
+
+PTR records exist for all static hosts. The workstation (`nixos.sweet.home`) is
+DHCP-assigned; its PTR is omitted.
+
+### cluster.home — VLAN 10 (192.168.10.x)
+
+Internal only — Corosync ring0 heartbeat and DRBD replication between HA nodes.
+No VIP exists on this subnet (DRBD/Corosync endpoints are static per-node IPs).
+
+| Hostname | A record | Notes |
+|---|---|---|
+| `ha-server-1.cluster.home` | `192.168.10.228` | HA node 1 cluster NIC (ens19 / vmbr1) |
+| `ha-server-2.cluster.home` | `192.168.10.227` | HA node 2 cluster NIC (ens19 / vmbr1) |
+
+PTR records exist for both. DNS here is for debugging convenience — DRBD and
+Corosync use the IPs from the NixOS config directly, not DNS.
+
+### storage.home — VLAN 20 (192.168.20.x)
+
+Internal only — NFS (and iSCSI) client access to the HA storage VIP. NFS clients
+mount from **`nfs.storage.home`** (the Pacemaker floating VIP) so mounts survive
+failover transparently without reconfiguration.
+
+| Hostname | A record | Notes |
+|---|---|---|
+| `nfs.storage.home` | `192.168.20.229` | Pacemaker `vip-storage` — NFS + iSCSI VIP |
+| `ha-server-1.storage.home` | `192.168.20.228` | HA node 1 storage-client NIC (ens20 / vmbr2) |
+| `ha-server-2.storage.home` | `192.168.20.227` | HA node 2 storage-client NIC (ens20 / vmbr2) |
+| `docker.storage.home` | `192.168.20.225` | Docker host storage-client NIC (eth1 / vmbr2) |
+| `server.storage.home` | `192.168.20.226` | server VM storage-client NIC (decommissioned — remove DNS record after VM is destroyed) |
+
+PTR records exist for all five. Remove `server.storage.home`, `server.sweet.home`,
+and their PTRs from FreeIPA DNS once the server VM is destroyed.
+
+---
+
+## LAN — 192.168.2.0/24
+
+### Address map
+
+| Range | Purpose |
+|---|---|
+| .1–.9 | Reserved, never assign |
+| .10–.59 | Client DHCP pool (router-assigned) |
+| .60–.219 | Unallocated buffer |
+| .220–.229 | Virtual nodes (VMs / LXC containers) |
+| .230–.239 | Expansion buffer (reserved, unallocated) |
+| .240–.249 | Physical nodes (bare-metal hosts) |
+| .250–.253 | Network services |
+| .254 | Router / gateway |
+
+### Network services (.250–.253)
+
+| IP | Hostname | Role |
+|---|---|---|
+| `192.168.2.254` | router | Gateway (TP-Link) |
+| `192.168.2.253` | domain-controller | FreeIPA — authoritative DNS for `sweet.home`, Kerberos, LDAP |
+| `192.168.2.250`–`.252` | — | Reserved for future network services |
+
+### Physical nodes (.240–.249)
+
+| IP | Hostname | Role |
+|---|---|---|
+| `192.168.2.245` | pve1 | Proxmox VE hypervisor |
+| `192.168.2.244` | pbs | Proxmox Backup Server |
+| `192.168.2.243` | nixos | Bare-metal workstation (`baremetal-gui`) |
+| `192.168.2.246`–`.249` | — | Reserved — second Proxmox node and associated services |
+| `192.168.2.240`–`.242` | — | Reserved |
+
+pve1 sits mid-range deliberately so a second Proxmox node can slot in on either side.
+
+### Virtual nodes (.220–.229)
+
+All VMs and LXC containers run on pve1.
+
+| IP | Hostname | Role | Status |
+|---|---|---|---|
+| `192.168.2.229` | ha-vip-lan | HA file server LAN floating VIP (Pacemaker `vip-lan`) — LAN iSCSI + NFS | Active |
+| `192.168.2.228` | ha-node1 | HA file server node 1 — management NIC | Active |
+| `192.168.2.227` | ha-node2 | HA file server node 2 — management NIC | Active |
+| `192.168.2.226` | server | Former NFS/ZFS file server — decommissioned | Removed from flake |
+| `192.168.2.225` | docker | Docker / Traefik stack | Active |
+| `192.168.2.224` | nix-cache | Nix binary cache + remote builder | Active |
+| `192.168.2.223` | pxe-boot | PXE / TFTP / HTTP netboot server | Active |
+| `192.168.2.222` | tailscale-router | Tailscale exit node / router | Active |
+| `192.168.2.221` | tor-relay | Tor relay | Active |
+| `192.168.2.220` | pdm | Proxmox Deploy Manager | Active |
+
+### Client DHCP pool (.10–.59)
+
+Assigned by the router. DNS option points to `192.168.2.253` (domain-controller).
+
+Devices in this range: phones, laptops, IoT, Canon printer, any non-infrastructure host.
+No static reservations for infrastructure hosts — all infra uses static IP configuration
+on the guest itself (not DHCP reservations), so IPs survive VM recreation regardless of
+MAC address churn.
+
+---
+
+## Cluster network — VLAN 10 — 192.168.10.224/29
+
+Internal to pve1 only. Proxmox bridge `vmbr1`, no physical NIC attached.
+
+| IP | Hostname | Interface role |
+|---|---|---|
+| `192.168.10.228` | ha-node1 | DRBD replication + Corosync ring0 (primary heartbeat) |
+| `192.168.10.227` | ha-node2 | DRBD replication + Corosync ring0 (primary heartbeat) |
+| — | no gateway | Isolated — not routed to LAN or internet |
+
+Corosync ring1 (backup heartbeat only) uses the LAN IPs (`192.168.2.228` / `192.168.2.227`)
+over `vmbr0` — no additional bridge needed, and DRBD traffic never crosses ring1.
+
+---
+
+## Storage-client network — VLAN 20 — 192.168.20.0/24
+
+Internal to pve1 only. Proxmox bridge `vmbr2`, no physical NIC attached.
+
+| IP | Hostname | Interface / role |
+|---|---|---|
+| `192.168.20.229` | ha-vip-storage | Pacemaker floating VIP — NFS + iSCSI endpoint |
+| `192.168.20.228` | ha-node1 | Storage-client NIC (ens20 / vmbr2) |
+| `192.168.20.227` | ha-node2 | Storage-client NIC (ens20 / vmbr2) |
+| `192.168.20.226` | server | Storage-client NIC (ens19 / vmbr2) — decommissioned |
+| `192.168.20.225` | docker | Storage-client NIC (eth1 / vmbr2) — NFS client |
+| — | no gateway | Isolated — not routed to LAN or internet |
+
+NFS clients mount from `192.168.20.229` (surviving failover transparently via the VIP).
+Firewall on each HA node restricts NFS and iSCSI ports to `192.168.20.0/24` — LAN hosts
+cannot reach either service on this VIP. The `vip-storage` endpoint is not reachable
+from the workstation directly (internal bridge only); health checks proxy through the
+active HA node.
+
+---
+
+## Migration reference
+
+Current → target IP for every host being renumbered.
+
+| Host | Current IP | New IP | Config location |
+|---|---|---|---|
+| router | `192.168.2.254` | `192.168.2.254` | unchanged |
+| domain-controller | `192.168.2.138` | `192.168.2.253` | `/etc/sysconfig/network-scripts/ifcfg-eth0` on guest |
+| pve1 | `192.168.2.250` | `192.168.2.245` | `/etc/network/interfaces` on Proxmox host |
+| pbs | `192.168.2.108` | `192.168.2.244` | static config on PBS host |
+| nixos workstation | `192.168.2.119` | `192.168.2.243` | `networking.interfaces` / NetworkManager on guest |
+| ha-node1 | — | `192.168.2.228` (LAN), `192.168.10.228` (cluster/VLAN 10), `192.168.20.228` (storage/VLAN 20) | active |
+| ha-node2 | — | `192.168.2.227` (LAN), `192.168.10.227` (cluster/VLAN 10), `192.168.20.227` (storage/VLAN 20) | active |
+| ha-vip-lan | — | `192.168.2.229` (vmbr0 / Pacemaker `vip-lan`) — NFS endpoint for LAN clients | active |
+| ha-vip-storage | — | `192.168.20.229` (vmbr2 / Pacemaker `vip-storage`) — iSCSI endpoint for VLAN 20 clients | active |
+| server | `192.168.2.252` | `192.168.2.226` | static config on guest |
+| docker | `192.168.2.249` | `192.168.2.225` | static config on guest |
+| nix-cache | `192.168.2.120` | `192.168.2.224` | static config on guest |
+| pxe-boot | `192.168.2.247` | `192.168.2.223` | static config on guest; update `vars.pxeServerIp` in `variables.nix` ✓ |
+| tailscale-router | `192.168.2.121` | `192.168.2.222` | static config on guest |
+| tor-relay | `192.168.2.107` | `192.168.2.221` | static config on guest |
+| pdm | `192.168.2.248` | `192.168.2.220` | static config on guest |
+
+### Cutover notes
+
+- **Do domain-controller first** — it becomes the DNS server; everything else depends on it
+  having its new IP and FreeIPA DNS configured before Pi-hole is retired.
+- **pve1 last among physical hosts** — changing the Proxmox management IP drops the web UI
+  briefly; all guests keep running.
+- **Update Pi-hole custom.list / FreeIPA DNS A records** to new IPs before flipping any host,
+  so name resolution stays valid throughout the migration.
+- **variables.nix already updated** for `pxeServerIp` (.247→.223), `pbsIp` (.108→.244), and
+  new `domainControllerIp` (.253). Rebuild affected hosts after renumbering.
+- **Router DHCP**: once domain-controller is at .253 and FreeIPA DNS is serving `sweet.home`,
+  switch router DHCP on with pool .10–.59 and DNS option pointing to .253; retire Pi-hole CT.
+- **Pi-hole's iPXE dnsmasq config** (`99-ipxe-chainload.conf`) moves to the pxe-boot CT as a
+  dnsmasq proxy-mode config before Pi-hole is decommissioned.

docs/network-cutover.md

@@ -0,0 +1,448 @@
+# Network Cutover Plan
+
+Moves the LAN from the current flat/Pi-hole-managed state to the new IP scheme
+defined in `docs/ip-addressing.md`. Works in five independent stages — each
+stage is safe to pause after and resume later. Rollback steps are given at
+every point where something can break.
+
+**Before starting anything:** confirm you have
+- SSH access to `192.168.2.138` (domain-controller, current IP)
+- SSH access to `192.168.2.250` (pve1)
+- Browser access to Pi-hole admin at `http://192.168.2.253`
+- Browser access to router admin at `http://192.168.2.254`
+- The FreeIPA `admin` password to hand
+
+---
+
+## Stage 1 — Prepare FreeIPA DNS (zero downtime)
+
+Everything here is additive. Pi-hole keeps running. Nothing breaks if you stop
+mid-stage.
+
+### 1a. Add NextDNS forwarders
+
+```bash
+ssh wayne@192.168.2.138
+kinit admin          # enter FreeIPA admin password when prompted
+ipa dnsconfig-mod \
+  --forwarder=45.90.28.142 \
+  --forwarder=45.90.30.142 \
+  --forward-policy=only
+```
+
+**Verify external resolution works through FreeIPA before continuing:**
+```bash
+dig @127.0.0.1 google.com +short   # must return an IP, not SERVFAIL
+```
+
+### 1b. Add A records for every host at their CURRENT IPs
+
+These represent the live state now. You'll update each record to the new IP
+when you renumber that host in Stage 5.
+
+```bash
+ipa dnsrecord-add sweet.home pve1             --a-rec 192.168.2.250
+ipa dnsrecord-add sweet.home pbs              --a-rec 192.168.2.108
+ipa dnsrecord-add sweet.home nixos            --a-rec 192.168.2.119
+ipa dnsrecord-add sweet.home server           --a-rec 192.168.2.252
+ipa dnsrecord-add sweet.home docker           --a-rec 192.168.2.249
+ipa dnsrecord-add sweet.home nix-cache        --a-rec 192.168.2.120
+ipa dnsrecord-add sweet.home pxe-boot         --a-rec 192.168.2.247
+ipa dnsrecord-add sweet.home tailscale-router --a-rec 192.168.2.121
+ipa dnsrecord-add sweet.home tor-relay        --a-rec 192.168.2.107
+ipa dnsrecord-add sweet.home pdm              --a-rec 192.168.2.248
+ipa dnsrecord-add sweet.home router           --a-rec 192.168.2.254
+```
+
+### 1c. Clean up stale reverse-zone PTR records
+
+FreeIPA already has PTR records from an earlier import but some are wrong.
+Fix them now so reverse DNS is accurate from day one.
+
+```bash
+# Remove stale "win11" entry at .250 (should be pve1)
+ipa dnsrecord-del 2.168.192.in-addr.arpa 250 --ptr-rec win11.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 250 --ptr-rec pve1.sweet.home.
+
+# Fix unqualified PTR records (missing .sweet.home. suffix)
+ipa dnsrecord-mod 2.168.192.in-addr.arpa 108 --ptr-rec pbs.sweet.home.
+ipa dnsrecord-mod 2.168.192.in-addr.arpa 248 --ptr-rec pdm.sweet.home.
+ipa dnsrecord-mod 2.168.192.in-addr.arpa 249 --ptr-rec docker.sweet.home.
+ipa dnsrecord-mod 2.168.192.in-addr.arpa 252 --ptr-rec server.sweet.home.
+
+# Add any missing PTR records
+ipa dnsrecord-add 2.168.192.in-addr.arpa 119 --ptr-rec nixos.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 120 --ptr-rec nix-cache.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 121 --ptr-rec tailscale-router.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 247 --ptr-rec pxe-boot.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 254 --ptr-rec router.sweet.home.
+```
+
+### 1d. Point domain-controller's own DNS at itself
+
+```bash
+sudo nmcli connection modify "System eth0" ipv4.dns "127.0.0.1"
+sudo nmcli connection up "System eth0"
+```
+
+**Verify:**
+```bash
+dig pve1.sweet.home +short          # must return 192.168.2.250
+dig google.com +short               # must return an IP (NextDNS forwarding)
+```
+
+**Rollback 1d:** `sudo nmcli connection modify "System eth0" ipv4.dns "192.168.2.253" && sudo nmcli connection up "System eth0"`
+
+---
+
+## Stage 2 — Move pxe-boot DHCP options off Pi-hole (zero downtime)
+
+Pi-hole's dnsmasq currently serves the iPXE boot options via
+`99-ipxe-chainload.conf`. Before Pi-hole is retired, that config must move to
+the pxe-boot CT running dnsmasq in proxy mode so PXE boot keeps working.
+
+### 2a. Add dnsmasq proxy config to the pxe-boot NixOS module
+
+In `modules/build-types/pxe-boot.nix`, add:
+
+```nix
+services.dnsmasq = {
+  enable = true;
+  settings = {
+    # Proxy mode: respond only to PXE DHCP requests, leave normal leases to router
+    dhcp-range = [ "192.168.2.0,proxy" ];
+    # iPXE client detection
+    dhcp-match = [
+      "set:ipxe,175"
+      "set:efi64,option:client-arch,7"
+      "set:efi64,option:client-arch,9"
+    ];
+    dhcp-userclass = "set:ipxe,iPXE";
+    # Boot file selection
+    dhcp-boot = [
+      "tag:ipxe,tag:efi64,http://${vars.pxeServerIp}/boot.ipxe"
+      "tag:ipxe,http://${vars.pxeServerIp}/boot.ipxe"
+      "tag:efi64,ipxe.efi,,${vars.pxeServerIp}"
+      "undionly.kpxe,,${vars.pxeServerIp}"
+    ];
+  };
+};
+```
+
+### 2b. Rebuild and deploy the pxe-boot CT
+
+```bash
+# On pve1 — build the new tarball
+nix build .#lxc-pxe-boot.config.system.build.tarball
+
+# Verify dnsmasq starts correctly in the CT after deploy
+ssh nixos@192.168.2.247 systemctl status dnsmasq
+```
+
+### 2c. Remove the iPXE config from Pi-hole
+
+In the Pi-hole CT, remove `/etc/dnsmasq.d/99-ipxe-chainload.conf` and
+restart the FTL service:
+
+```bash
+ssh wayne@pve1.sweet.home \
+  "sudo pct exec 100 -- bash -c 'rm /etc/dnsmasq.d/99-ipxe-chainload.conf && systemctl restart pihole-FTL'"
+```
+
+**Verify:** PXE boot a test machine — it should still get an iPXE response and
+reach the boot menu.
+
+**Rollback 2c:** restore the file from the Pi-hole config backup at
+`/etc/pihole/config_backups/` and restart pihole-FTL.
+
+---
+
+## Stage 3 — DHCP migration: Pi-hole → router (brief maintenance window)
+
+**Do this in the evening.** Existing DHCP leases stay valid during the
+switchover so connected devices don't drop — only new lease requests fail
+during the gap, which is under 60 seconds if you follow the steps in order.
+
+The key: configure the router's DHCP DNS option to point at `.253` (Pi-hole's
+current IP). This way, all new leases issued by the router still get the same
+DNS server address — clients never need to change their DNS config. When Pi-hole
+is retired and the DC takes `.253` in Stage 4, `.253` just starts answering
+differently. No client reconfiguration.
+
+### 3a. Pre-configure router DHCP (do not enable yet)
+
+Log into `http://192.168.2.254`, find the DHCP settings and fill in — but
+leave DHCP **disabled** until step 3b:
+
+| Setting | Value |
+|---|---|
+| Start IP | 192.168.2.10 |
+| End IP | 192.168.2.59 |
+| Subnet mask | 255.255.255.0 |
+| Gateway | 192.168.2.254 |
+| Primary DNS | 192.168.2.253 |
+| Secondary DNS | *(leave blank)* |
+| Lease time | 24h |
+
+Save without enabling.
+
+### 3b. Switchover (do steps in quick succession)
+
+1. **Disable Pi-hole DHCP:** Pi-hole admin UI → Settings → DHCP → uncheck
+   "DHCP server enabled" → Save
+2. **Enable router DHCP** immediately after step 1
+
+### 3c. Verify router DHCP is working
+
+On a phone or laptop, disconnect from WiFi and reconnect (or run
+`sudo dhclient -r && sudo dhclient` on a Linux host):
+
+```bash
+ip addr show        # IP should be in 192.168.2.10–59 range
+dig google.com      # should resolve (Pi-hole DNS still running at .253)
+dig pve1.sweet.home # should resolve via FreeIPA at .138 (relayed via Pi-hole)
+```
+
+Wait 10–15 minutes for the most active devices to renew their leases. There's
+no need to wait for all leases to expire before proceeding.
+
+**Rollback 3b:** Re-enable Pi-hole DHCP. Disable router DHCP. Done — existing
+leases remain valid so most devices are unaffected.
+
+---
+
+## Stage 4 — Move domain-controller from .138 to .253
+
+Pi-hole lives at `.253`. The DC must take `.253` the moment Pi-hole stops so
+clients that still have `.253` as their DNS server don't notice the change.
+Script these commands in advance and run them in rapid succession.
+
+**Pre-stage: have this SSH command ready before running step 4a:**
+```bash
+ssh wayne@192.168.2.138 "
+  sudo nmcli connection modify 'System eth0' \
+    ipv4.addresses '192.168.2.253/24' \
+    ipv4.gateway '192.168.2.254' \
+    ipv4.dns '127.0.0.1' \
+    ipv4.method manual && \
+  sudo nmcli connection up 'System eth0'
+"
+```
+
+**Also update the Proxmox VM config to match (run from pve1):**
+```bash
+sudo qm set 108 \
+  --ipconfig0 ip=192.168.2.253/24,gw=192.168.2.254 \
+  --nameserver 192.168.2.253
+```
+
+### 4a. Stop Pi-hole
+
+```bash
+ssh wayne@pve1.sweet.home "sudo pct stop 100"
+```
+
+### 4b. Immediately: change DC's IP to .253
+
+Run the pre-staged SSH command from above. You have ~30 seconds before any
+client notices Pi-hole is gone. If SSH to `.138` refuses (the IP is already
+changing), open a Proxmox console to VM 108 and run the `nmcli` commands
+there.
+
+### 4c. Update Proxmox VM config
+
+Run the pre-staged `qm set 108` command from above.
+
+### 4d. Verify
+
+```bash
+ssh wayne@192.168.2.253   # must connect (new DC IP)
+dig @192.168.2.253 pve1.sweet.home +short   # must return 192.168.2.250
+dig @192.168.2.253 google.com +short        # must return an IP
+```
+
+From a client device that renewed its DHCP lease in Stage 3:
+```bash
+cat /etc/resolv.conf    # should show 192.168.2.253
+dig pve1.sweet.home     # should resolve
+```
+
+**Rollback 4:** `ssh wayne@pve1.sweet.home "sudo pct start 100"`. Change DC IP
+back to .138 via Proxmox console. This restores full Pi-hole DNS/DHCP service.
+Leave Pi-hole CT stopped-but-intact for 48 hours before deleting it.
+
+---
+
+## Stage 5 — Host renumbering (one at a time, any order)
+
+For each host:
+1. Update FreeIPA DNS A record and PTR record to the new IP
+2. Change the static IP on the host itself
+3. Verify SSH to new IP
+4. Update `variables.nix` if that host has an IP variable (pxe-boot, pbs — already done in this PR)
+
+**FreeIPA record update template** (run as admin on domain-controller):
+```bash
+ipa dnsrecord-mod sweet.home <hostname> --a-rec <new-ip>
+ipa dnsrecord-del 2.168.192.in-addr.arpa <old-last-octet> --ptr-rec <hostname>.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa <new-last-octet> --ptr-rec <hostname>.sweet.home.
+```
+
+### Renumbering order
+
+| # | Host | Old IP | New IP | How to change IP |
+|---|---|---|---|---|
+| 1 | nixos workstation | .119 | .243 | NetworkManager on guest; or `nmcli connection modify` |
+| 2 | nix-cache | .120 | .224 | `pct set 102 --net0 name=eth0,bridge=vmbr0,ip=192.168.2.224/24,gw=192.168.2.254` then `pct reboot 102` |
+| 3 | tailscale-router | .121 | .222 | Static config on guest; check Tailscale ACLs if IP is referenced there |
+| 4 | tor-relay | .107 | .221 | `pct set 104 --net0 name=eth0,bridge=vmbr0,ip=192.168.2.221/24,gw=192.168.2.254` then `pct reboot 104` |
+| 5 | pdm | .248 | .220 | `pct set 106 --net0 name=eth0,bridge=vmbr0,ip=192.168.2.220/24,gw=192.168.2.254` then `pct reboot 106` |
+| 6 | pxe-boot | .247 | .223 | `pct set 103 --net0 name=eth0,bridge=vmbr0,ip=192.168.2.223/24,gw=192.168.2.254` then rebuild NixOS (already updated in variables.nix) |
+| 7 | server | .252 | .226 | Static config on guest; NFS clients (docker) lose mounts briefly — they remount automatically |
+| 8 | docker | .249 | .225 | Static config on guest; do this after server is at .226 |
+| 9 | pbs | .108 | .244 | Static config on PBS host itself; update in `pbsIp` already done in variables.nix |
+| 10 | pve1 | .250 | .245 | Edit `/etc/network/interfaces` on the Proxmox host — see below |
+
+### pve1 renumber (step 10 — do last)
+
+All guests keep running; only the Proxmox web UI is briefly unreachable.
+
+```bash
+ssh wayne@pve1.sweet.home
+
+# Edit /etc/network/interfaces: change address from .250 to .245
+sudo nano /etc/network/interfaces
+# Change:  address 192.168.2.250/24
+# To:      address 192.168.2.245/24
+
+sudo systemctl restart networking
+# SSH will drop here — reconnect to new IP
+```
+
+```bash
+ssh wayne@192.168.2.245    # verify
+```
+
+Update FreeIPA DNS:
+```bash
+ipa dnsrecord-mod sweet.home pve1 --a-rec 192.168.2.245
+ipa dnsrecord-del 2.168.192.in-addr.arpa 250 --ptr-rec pve1.sweet.home.
+ipa dnsrecord-add 2.168.192.in-addr.arpa 245 --ptr-rec pve1.sweet.home.
+```
+
+**Rollback any step 5 host:** change the IP back on the guest and update the
+FreeIPA record back to the old IP. The old IP is unoccupied so you can
+temporarily use either.
+
+---
+
+## Stage 6 — HA storage cutover (docker NFS remount)
+
+> **Prerequisites:**
+> - HA cluster fully deployed and `vip-storage` (`nfs.storage.home` → 192.168.20.229) serving NFS ✓
+> - DNS configured: `storage.home` zone populated, `nfs.storage.home` resolves to 192.168.20.229 ✓
+> - docker CT has eth1 on vmbr2 (`docker.storage.home` → 192.168.20.225) ✓
+> - Final rsync from server.sweet.home to `/srv/ha-data` complete before step 6b
+
+docker.sweet.home currently NFS-mounts its persistent volumes from `server.sweet.home`
+(`192.168.2.226:/tank/docker/...`). This stage moves those mounts to the HA cluster's
+storage VIP so server can be decommissioned.
+
+### 6a. Final rsync from server to HA cluster
+
+Run from server.sweet.home (or over SSH from the workstation) to sync any data written
+since the initial rsync:
+
+```bash
+# Confirm active HA node and mount point
+ssh wayne@192.168.2.228 'sudo findmnt /srv/ha-data'  # check which node is active
+
+# rsync each dataset (adjust source paths to match /tank layout on server)
+sudo rsync -av --delete /tank/docker/config/    wayne@<active-node-ip>:/srv/ha-data/docker/config/
+sudo rsync -av --delete /tank/docker/databases/ wayne@<active-node-ip>:/srv/ha-data/docker/databases/
+sudo rsync -av --delete /tank/docker/volumes/   wayne@<active-node-ip>:/srv/ha-data/docker/volumes/
+sudo rsync -av --delete /tank/docker/nextcloud-data/ wayne@<active-node-ip>:/srv/ha-data/docker/nextcloud-data/
+```
+
+### 6b. Update docker NixOS config to mount from vip-storage
+
+In `hosts/docker/host.nix` (or wherever the NFS mount fileSystems are declared), change
+the NFS server from `server.sweet.home` / `192.168.2.226` to `nfs.storage.home`:
+
+```nix
+# Before:
+fileSystems."/mnt/docker/config" = {
+  device = "server:/tank/docker/config";   # or 192.168.2.226:...
+  ...
+};
+
+# After:
+fileSystems."/mnt/docker/config" = {
+  device = "nfs.storage.home:/srv/ha-data/docker/config";
+  ...
+};
+```
+
+Using the DNS name (`nfs.storage.home`) rather than the VIP IP means the mount
+config survives a future VIP renumber without touching the NixOS config.
+Repeat for all four docker shares (`config`, `databases`, `volumes`, `nextcloud-data`).
+Then rebuild docker:
+
+```bash
+# On the workstation — or via Switch-nix on docker itself
+sudo nixos-rebuild switch --no-write-lock-file --refresh \
+  --flake "git+https://gitea.lan.ddnsgeek.com/beatzaplenty/nixos.git#lxc-docker"
+```
+
+### 6c. Verify mounts and container health
+
+```bash
+ssh wayne@192.168.2.225 'findmnt | grep 192.168.20'   # mounts should show vip-storage
+ssh wayne@192.168.2.225 'docker ps'                    # all containers running
+```
+
+Spot-check Nextcloud, Traefik, and any database containers for connectivity.
+
+### 6d. Decommission server.sweet.home
+
+Once docker is confirmed healthy on the HA NFS mounts:
+
+```bash
+# Stop server VM on pve1
+ssh wayne@192.168.2.245 'sudo qm stop 101'
+
+# (Optional) Archive the ZFS pool snapshot before destroying
+# Then after a settling period:
+ssh wayne@192.168.2.245 'sudo qm destroy 101 --destroy-unreferenced-disks 1'
+```
+
+---
+
+## Stage 7 — Final cleanup
+
+Once all hosts are at their new IPs and verified:
+
+```bash
+# Delete the Pi-hole CT (already stopped since Stage 4)
+ssh wayne@pve1.sweet.home "sudo pct destroy 100"
+
+# Remove stale FreeIPA records for retired addresses
+ipa dnsrecord-del sweet.home pihole --del-all
+ipa dnsrecord-del 2.168.192.in-addr.arpa 253 --ptr-rec pihole.sweet.home.
+
+# Rebuild any NixOS hosts that reference pbsIp or pxeServerIp to pick up
+# the updated variables.nix values (pxe-boot mandatory; others as convenient)
+```
+
+---
+
+## Rollback summary
+
+| What broke | How to roll back |
+|---|---|
+| FreeIPA DNS not resolving | Check `systemctl status named` on DC; restart if failed |
+| FreeIPA DNS unreachable | `pct start 100` on pve1 (restores Pi-hole) |
+| Router DHCP not handing out leases | Re-enable Pi-hole DHCP; disable router DHCP |
+| DC unreachable after IP change | Proxmox console on VM 108 → `nmcli connection up "System eth0"` with old IP |
+| Host unreachable after renumber | Proxmox console → revert IP; or `pct set <id> --net0 ...` old IP and reboot CT |
+| pve1 web UI gone after renumber | SSH to .245 and check `/etc/network/interfaces`; if wrong, fix and restart networking |

docs/nix-cache.md

@@ -8,37 +8,73 @@ This repository configures `nix-cache` as a **binary cache server** and a **remo
 - Every machine still keeps and uses its own local `/nix/store`.
 - Clients prefer `http://nix-cache` for substitutes and keep `https://cache.nixos.org/` as fallback.
 - Clients can offload builds to `nix-cache` through SSH (`nix.distributedBuilds`).
-- Client hosts import `modules/nix/cache-client.nix` and, when remote building is enabled, `modules/nix/remote-builder-client.nix`.
+- Client hosts import `modules/nix-cache/client.nix` and, when remote building is enabled, `modules/nix-cache/remote-builder-client.nix`.
-- The `nix-cache` host imports `modules/nix/cache-server.nix`.
+- The `nix-cache` host imports `modules/nix-cache/server.nix`.
 
-## Binary cache signing keys (on nix-cache)
+## Binary cache signing key
+
+`modules/nix-cache/client.nix` hardcodes every client's trust in one
+specific public key (`cache.local-1:usoWYanY3Kpq2+kDIS2nhWoLZiRxanmdysdzqCFBHW4=`).
+That means whichever host is currently playing the `nix-cache` role has to
+use that *exact* keypair — not a freshly generated one — or no client will
+accept substitutes from it (they'd just silently fall back to building
+from source). So unlike most per-host secrets, this one can't be
+self-generated on first boot; it's managed via sops-nix like every other
+secret in this repo, sourced from `secrets/nix-cache.yaml`'s
+`cache-priv-key` entry (`modules/nix-cache/server.nix`).
+
+**Adding or rotating the value:**
 
 ```bash
-sudo install -d -m 0700 /etc/nix
+nix-shell -p sops --run 'sops secrets/nix-cache.yaml'
-sudo nix-store --generate-binary-cache-key nix-cache-1   /etc/nix/cache-priv.pem   /etc/nix/cache-pub.pem
-sudo chmod 0600 /etc/nix/cache-priv.pem
-sudo chmod 0644 /etc/nix/cache-pub.pem
-cat /etc/nix/cache-pub.pem
 ```
 
-Do not commit private keys.
+Add (or replace) a `cache-priv-key` entry with the private key file's exact
-Do not commit new password hashes or live credentials. Existing committed hashes
+contents. If you don't have it yet, generate a keypair once:
-should be rotated and moved to host-local secret management.
+
+```bash
+nix-store --generate-binary-cache-key nix-cache-1 cache-priv.pem cache-pub.pem
+```
+
+— paste `cache-priv.pem`'s contents into the `cache-priv-key` entry above,
+delete both local files afterward, and update
+`trusted-public-keys` in `modules/nix-cache/client.nix` (and every already-built
+client) to match `cache-pub.pem` if this is a genuine rotation rather than
+a first-time bootstrap. Any `nixos-configurations.*-nix-cache` host picks
+the new key up automatically on next activation — no more manual
+`/etc/nix/cache-priv.pem` install step.
 
 ## Remote builder SSH keys
 
-On each client, install the private key used to authenticate as `nixremote`:
+Each client authenticates as `nixremote` using its **own default root SSH
+identity** (`/root/.ssh/id_ed25519`) — not a separately-named or shared
+keypair. If a client doesn't have one yet:
 
 ```bash
-sudo install -d -m 0700 /root/.ssh
+sudo ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519
-sudo install -m 0600 ./nixremote /root/.ssh/nixremote
-sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
 ```
 
-On `nix-cache`, install the matching public key used by `nixremote` authorized keys.
+Then add its `.pub` contents as a new entry in `vars.remoteBuilderAuthorizedKeys`
+(`variables.nix`) and rebuild `nix-cache` to pick it up (that list is
+declarative — an imperative `ssh-copy-id nixremote@nix-cache` won't stick;
+it gets overwritten on every rebuild). Verify with:
 
-The committed `nixremote` authorized keys are public SSH keys only. Keep the
+```bash
-matching private keys on client hosts and out of the repository.
+sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache nix-store --version
+```
+
+The committed `remoteBuilderAuthorizedKeys` entries are public SSH keys
+only. Keep the matching private keys on client hosts and out of the
+repository.
+
+nix-cache's own SSH *host* key is trusted declaratively via
+`programs.ssh.knownHosts` in `modules/nix-cache/remote-builder-client.nix`,
+sourced from `vars.nixCacheHostKey` (`variables.nix`) — every client rebuild
+picks it up automatically, so distributed builds don't fail with "Host key
+verification failed" on a client that has never manually SSH'd to nix-cache
+before. If nix-cache's host key is ever rotated or the host rebuilt from
+scratch, update `vars.nixCacheHostKey` to match its new
+`/etc/ssh/ssh_host_ed25519_key.pub`.
 
 ## Manual verification
 
@@ -48,8 +84,8 @@ After deployment:
 curl http://nix-cache/nix-cache-info
 nix store ping --store http://nix-cache
 nix show-config | grep -E 'substituters|trusted-public-keys|builders-use-substitutes'
-sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
+sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache nix-store --version
-nix build nixpkgs#hello --builders 'ssh://nixremote@nix-cache x86_64-linux /root/.ssh/nixremote 4 2 big-parallel,kvm,nixos-test,benchmark' -L
+nix build nixpkgs#hello --builders 'ssh://nixremote@nix-cache x86_64-linux /root/.ssh/id_ed25519 4 2 big-parallel,kvm,nixos-test,benchmark' -L
 nix path-info -r nixpkgs#hello
 curl -I "http://nix-cache/$(basename "$(nix path-info nixpkgs#hello)").narinfo"
 ```

docs/proxmox-images.md

@@ -0,0 +1,116 @@
+# Proxmox VM disk images
+
+`proxmox-*` hosts (VM platform, not `lxc-*`) can be built as standalone,
+ready-to-attach `.raw` disk images via disko's own image-builder — no
+`nixos-install`, no live installer boot. This uses the same `disko.devices`
+config (`modules/disko/proxmox.nix`) already used to format a real disk on
+install, so there's nothing host-specific to write; it's available for every
+`proxmox-*` target automatically.
+
+`scripts/proxmox/create-proxmox-resource.sh --type vm --host <name>` automates the
+whole walkthrough below (and the equivalent LXC one) end to end, including
+host-key handling and building the image directly on the Proxmox node
+itself (no local build, no image transfer) — see its `--help`. The steps
+here are what it runs under the hood, useful for doing any of it by hand
+or understanding what it does before you trust it against real
+infrastructure.
+
+## Building
+
+```sh
+nix build .#nixosConfigurations.proxmox-server.config.system.build.diskoImagesScript
+sudo ./result --build-memory 2048
+```
+
+This produces `<hostname>.raw` in the current directory (e.g. `server.raw`
+for `proxmox-server`, matching `networking.hostName`, not the flake attribute
+name — every `proxmox-*` host gets a distinctly named image instead of all
+of them producing an identical `main.raw`). The script builds inside a
+temporary QEMU VM and moves the finished image out to the working directory
+when done; `--build-memory` controls how much RAM that build VM gets.
+
+`disko.devices.disk.main.imageSize` (currently `20G`, in
+`modules/disko/proxmox.nix`) sets the image's total size — disko doesn't
+support auto-resizing, so this needs to comfortably fit ESP + swap + root at
+build time. Grow the virtual disk (and resize the filesystem) in Proxmox
+after attaching if a host needs more than that; this is the normal way to
+size these images, not a one-time decision to get exactly right up front.
+
+## Host keys
+
+The disko image script runs a real activation pass inside its temporary
+build VM while constructing the image — the same sops-nix
+activation-before-first-boot problem the installer and LXC tarball workflows
+have (see `docs/auto-installer.md`) applies here too, unmodified. Disko has
+a native mechanism for it:
+
+```sh
+sudo ./result \
+  --pre-format-files host-keys/server_ssh_host_ed25519_key /etc/ssh/ssh_host_ed25519_key \
+  --pre-format-files host-keys/server_ssh_host_ed25519_key.pub /etc/ssh/ssh_host_ed25519_key.pub \
+  --build-memory 2048
+```
+
+Generate the key first with `scripts/secrets/sync-host-keys.sh <hostname>`, same
+as any other host — see `docs/auto-installer.md` for the full walkthrough
+(it registers the new key in `.sops.yaml` and re-encrypts the affected
+`secrets/*.yaml` files too, no manual editing needed).
+
+## Deploying to Proxmox
+
+The image needs **UEFI (OVMF)**, not Proxmox's default SeaBIOS —
+`modules/boot/efi.nix` uses `systemd-boot`, which only works with UEFI
+firmware. `virtio-scsi` is safe to use as the disk bus:
+`hardware-configuration/vm/proxmox.nix` already includes `virtio_scsi` in
+its initrd kernel modules.
+
+1. Copy the image to the Proxmox host:
+
+   ```sh
+   scp server.raw root@<proxmox-host>:/var/lib/vz/import/
+   ```
+
+2. Create an empty VM shell (no disk yet) — replace `<vmid>` with a free ID
+   and `<storage>` with your storage pool's name (`pvesm status` or
+   Datacenter → Storage in the web UI):
+
+   ```sh
+   qm create <vmid> --name proxmox-server --memory 2048 --cores 2 \
+     --net0 virtio,bridge=vmbr0 \
+     --bios ovmf --machine q35 \
+     --scsihw virtio-scsi-pci \
+     --efidisk0 <storage>:1,efitype=4m,pre-enrolled-keys=0
+   ```
+
+   (`--efidisk0` is required for UEFI — it's where OVMF persists boot-entry
+   NVRAM; without it, systemd-boot's boot entry may not survive a reboot.)
+
+3. Import the raw disk into storage:
+
+   ```sh
+   qm importdisk <vmid> /var/lib/vz/import/server.raw <storage>
+   ```
+
+   This prints the resulting disk identifier (e.g. `vm-<vmid>-disk-1`).
+
+4. Attach it and set it as the boot disk:
+
+   ```sh
+   qm set <vmid> --scsi0 <storage>:vm-<vmid>-disk-1
+   qm set <vmid> --boot order=scsi0
+   ```
+
+5. Boot it:
+
+   ```sh
+   qm start <vmid>
+   ```
+
+No install step — it boots straight into the already-activated system.
+
+## Why not `nix build .#nixosConfigurations.<host>.config.system.build.vm`?
+
+That's a different, unrelated feature — `system.build.vm` (`nixos-rebuild
+build-vm`) produces an ephemeral QEMU script for locally testing a
+configuration, not a distributable disk image. It's not part of this
+workflow.

docs/pxe-boot.md

@@ -1,6 +1,10 @@
 # pxe-boot
 
-The `pxe-boot` host serves HTTP boot assets for iPXE clients.
+The `pxe-boot` host serves HTTP boot assets for iPXE clients — including
+self-staged copies of both this flake's own auto-installer netboot image
+(see `docs/auto-installer.md` for what that image actually is and does once
+booted) and a vanilla, unmodified NixOS minimal netboot image for plain
+rescue/inspection use.
 
 ## Host Role
 
@@ -11,6 +15,7 @@ The `pxe-boot` host serves HTTP boot assets for iPXE clients.
 - TFTP root for first-stage bootloaders: `/srv/pxe/tftp`
 - iPXE entry script: `/srv/pxe/http/boot.ipxe`
 - Generated iPXE menu: `/srv/pxe/http/menu.ipxe`
+- Debian Minimal iPXE script: `/srv/pxe/http/debian.ipxe`
 - SystemRescue iPXE script: `/srv/pxe/http/systemrescue.ipxe`
 - TFTP fallback script: `/srv/pxe/tftp/autoexec.ipxe`
 - Boot binaries copied from the Nix `ipxe` package:
@@ -24,36 +29,140 @@ The host creates these directories with systemd tmpfiles:
 ```text
 /srv/pxe
 /srv/pxe/http
-/srv/pxe/http/images
+/srv/pxe/http/images  -> /mnt/pxe-images  (symlink to NFS share)
-/srv/pxe/http/nixos
+/srv/pxe/http/auto-installer
+/srv/pxe/http/nixos-minimal
+/srv/pxe/http/debian
 /srv/pxe/http/systemrescue
 /srv/pxe/http/ubuntu
 /srv/pxe/http/rescue
 /srv/pxe/tftp
 ```
 
-Mount shared image storage under `/srv/pxe/http`, preferably
+`/srv/pxe/http/images` is a symlink to `/mnt/pxe-images`, which is an NFS
-`/srv/pxe/http/images` unless a menu entry expects files in a specific
+mount of `server.sweet.home:/tank/pxe-boot/images`
-directory such as `/srv/pxe/http/nixos`.
+(`modules/pxe-boot/mount-pxe-images.nix`). Place large images there (ISOs,
+disk images) rather than on the pxe-boot host's own root disk. For an LXC
+pxe-boot container the mount uses NFSv3+nolock with `nofail` (eager,
+non-blocking on server unavailability); for a Proxmox VM it uses NFSv4.2
+with `x-systemd.automount` (lazy, triggered on first access).
+
+When running as `lxc-pxe-boot`, the Proxmox container must have
+`features: nesting=1,mount=nfs` (at minimum) in its Proxmox config. `nesting=1`
+is required by systemd 260+ for credential isolation (user namespace creation
+and internal move-mounts); without it, AppArmor denies both, and every
+systemd service that uses `PrivateUsers`, `PrivateDevices`, or credential
+passing fails on boot. `mount=nfs` allows the NFSv3 mount. Both are set
+automatically by `scripts/proxmox/create-proxmox-resource.sh` (via
+`PROXMOX_DEFAULT_LXC_FEATURES` in `scripts/env.sh` which defaults to
+`nesting=1,keyctl=1,mount=nfs;nfs4`). If you ever change these features
+manually via `pct set`, be sure to include both — `pct set` replaces the
+entire features string, it does not append to it.
 
 The HTTP iPXE chain is:
 
 ```text
 undionly.kpxe or ipxe.efi
   -> autoexec.ipxe from the TFTP root, when iPXE requests it
-  -> http://192.168.2.247/boot.ipxe
+  -> http://192.168.2.223/boot.ipxe
-  -> http://192.168.2.247/menu.ipxe
+  -> http://192.168.2.223/menu.ipxe
 ```
 
 The generated menu currently exposes entries for:
 
-- NixOS installer
+- NixOS Auto-Installer
+- NixOS Minimal
+- Debian Minimal
+- FreeIPA Server (Rocky Linux 9)
 - SystemRescue environment
 - iPXE shell
 - Reboot
 
-Kernel and initrd artifacts for the NixOS installer entry must be placed under
+Both NixOS entries chain-load a `netboot.ipxe` staged into their own
-`/srv/pxe/http/nixos` by an operator or a separate build process.
+directory (`/srv/pxe/http/auto-installer/netboot.ipxe` and
+`/srv/pxe/http/nixos-minimal/netboot.ipxe`), each nixpkgs' own generated
+netboot iPXE script (correct `init=`/`initrd=` kernel parameters included)
+rather than a hand-rolled boot line — that script in turn expects its
+kernel/initrd siblings in the same directory. Each directory's three files
+(`bzImage`, `initrd`, `netboot.ipxe`) are built from source and staged
+automatically by `modules/pxe-boot/stage-installer-artifacts.nix` via
+`systemd.tmpfiles.rules` — no manual operator step required:
+
+- `auto-installer` is this flake's own `netbootSystem` (`flake.nix`) — the
+  same auto-installer image `nix build .#pxe` produces. See
+  `docs/auto-installer.md`.
+- `nixos-minimal` is `netbootMinimalSystem` (`flake.nix`) — nixpkgs'
+  `netboot-minimal.nix` composed on its own, with none of this flake's
+  auto-installer wiring (no `common.nix`, no `auto-install.sh`, no baked
+  host keys or custom users). Same `nix build .#pxe-minimal` mechanism as
+  the auto-installer image, just a different module composition. Useful
+  as a plain rescue/inspection shell that doesn't assume anything about
+  this flake.
+
+Both images set `networking.hostName` to match their menu entry/staged
+directory name (`auto-installer` / `nixos-minimal`), so each one's
+generated system name (`nixos-system-<name>-*`) is self-describing rather
+than the nixpkgs default of `nixos-system-nixos-*` for both.
+
+The Debian Minimal entry chains `http://<pxeServerIp>/debian.ipxe`, which loads
+the Debian bookworm netboot kernel and initrd from `/srv/pxe/http/debian/`. The
+`fetch-debian-netboot.service` oneshot downloads these files from
+`deb.debian.org` on first boot (idempotent — skips if files are already
+present):
+
+```text
+/srv/pxe/http/debian/linux      (Debian bookworm netboot kernel)
+/srv/pxe/http/debian/initrd.gz  (Debian bookworm netboot initrd)
+```
+
+The service requires outbound internet access on the pxe-boot host. To
+re-download (e.g. after a Debian point release), delete the files and restart
+the service:
+
+```bash
+rm /srv/pxe/http/debian/linux /srv/pxe/http/debian/initrd.gz
+systemctl restart fetch-debian-netboot.service
+```
+
+To update to a different Debian release, change `debianRelease` in
+`modules/build-types/pxe-boot.nix` and redeploy.
+
+The **FreeIPA Server (Rocky Linux 9)** entry chains
+`http://<pxeServerIp>/rocky-freeipa.ipxe`, which boots the Rocky Linux 9
+Anaconda installer with a Kickstart file (`rocky-freeipa.ks`) hosted on the
+same server. The `fetch-rocky-pxeboot.service` oneshot downloads the pxeboot
+kernel and initrd from the Rocky Linux mirror on first boot (idempotent):
+
+```text
+/srv/pxe/http/rocky/vmlinuz     (Rocky Linux 9 Anaconda pxeboot kernel)
+/srv/pxe/http/rocky/initrd.img  (Rocky Linux 9 Anaconda pxeboot initrd)
+```
+
+The Kickstart file is generated from the NixOS module and staged at
+`/srv/pxe/http/rocky-freeipa.ks`. It performs a fully unattended install:
+
+1. Installs Rocky Linux 9 with `ipa-server` + `ipa-server-dns` packages
+2. Configures static IP `192.168.2.138`, hostname `domain-controller.sweet.home`
+3. Creates user `wayne` with the `adminSshKey` from `variables.nix`
+4. Generates random IPA passwords and writes them to `/root/ipa-credentials.txt`
+5. Creates a `freeipa-first-boot.service` oneshot that runs `ipa-server-install`
+   on first reboot (~20 minutes)
+
+After the install completes:
+- SSH in as `wayne@domain-controller` using the admin key
+- Monitor FreeIPA install progress: `sudo tail -f /root/freeipa-install.log`
+- Retrieve credentials: `sudo cat /root/ipa-credentials.txt` (save to password manager)
+- Configure Pi-hole: `server=/sweet.home/192.168.2.138` in dnsmasq
+
+To refresh the pxeboot files (e.g. after a Rocky point release):
+
+```bash
+rm /srv/pxe/http/rocky/vmlinuz /srv/pxe/http/rocky/initrd.img
+systemctl restart fetch-rocky-pxeboot.service
+```
+
+To update to a different Rocky release, change `rockyRelease` in
+`modules/build-types/pxe-boot.nix` and redeploy.
 
 The SystemRescue entry expects the source ISO at:
 
@@ -61,13 +170,16 @@ The SystemRescue entry expects the source ISO at:
 /srv/pxe/http/images/systemrescue.iso
 ```
 
+Since `/srv/pxe/http/images` is the NFS-backed symlink, place the ISO on the
+NFS share at `server.sweet.home:/tank/pxe-boot/images/systemrescue.iso`.
+
 The `stage-systemrescue.service` oneshot extracts that ISO into:
 
 ```text
 /srv/pxe/http/systemrescue
 ```
 
-The rescue menu entry then chains `http://192.168.2.247/systemrescue.ipxe`,
+The rescue menu entry then chains `http://192.168.2.223/systemrescue.ipxe`,
 which loads the SystemRescue kernel and initramfs from the extracted tree and
 uses `archiso_http_srv` to fetch the squashfs payload over HTTP.
 
@@ -76,7 +188,7 @@ uses `archiso_http_srv` to fetch the squashfs payload over HTTP.
 Safe evaluation check:
 
 ```bash
-nix eval .#nixosConfigurations.pxe-boot.config.system.build.toplevel.drvPath --raw
+nix eval .#nixosConfigurations.proxmox-pxe-boot.config.system.build.toplevel.drvPath --raw
 ```
 
 After deployment by an operator, basic service checks are:
@@ -84,6 +196,13 @@ After deployment by an operator, basic service checks are:
 ```bash
 curl http://pxe-boot/boot.ipxe
 curl http://pxe-boot/menu.ipxe
+curl http://pxe-boot/debian.ipxe
+curl -I http://pxe-boot/debian/linux
+curl -I http://pxe-boot/debian/initrd.gz
+curl http://pxe-boot/rocky-freeipa.ipxe
+curl http://pxe-boot/rocky-freeipa.ks
+curl -I http://pxe-boot/rocky/vmlinuz
+curl -I http://pxe-boot/rocky/initrd.img
 curl http://pxe-boot/systemrescue.ipxe
 curl -I http://pxe-boot/systemrescue/sysresccd/boot/x86_64/vmlinuz
 curl -I http://pxe-boot/systemrescue/sysresccd/boot/x86_64/sysresccd.img

flake-target-refactor-spec.md

@@ -1,143 +0,0 @@
-# Spec: Refactor Flake Targets into Platform × Build-Type Matrix
-
-## Context
-
-The flake at `~/nixos` currently defines these output targets (flat, ad-hoc naming):
-
-- `docker`
-- `linode-minimal`
-- `nix-cache`
-- `nix-minimal`
-- `nixos`
-- `server`
-- `pxe-boot`
-
-Some already follow a `platform-buildtype` convention (`linode-minimal`), most don't.
-`~/nix-auto-installer` is a related repo and should be checked for any coupling to
-these target names (scripts, docs, CI, or install automation that reference them by
-name) before renaming anything.
-
-## Goal
-
-Restructure the flake so targets are generated from two orthogonal concepts:
-
-**Build types** (what the system is for):
-- `minimal`
-- `nix-cache`
-- `server`
-- `docker`
-- `pxe-boot`
-- `gui`
-
-**Platforms** (what it's deployed on):
-- `linode` (Linode VM)
-- `proxmox` (Proxmox VM)
-- `lxc` (Proxmox LXC container)
-
-Final targets should be named consistently as `<platform>-<buildtype>`, e.g.:
-
-```
-linode-minimal    proxmox-minimal    lxc-minimal
-linode-nix-cache  proxmox-nix-cache  lxc-nix-cache
-linode-server     proxmox-server     lxc-server
-linode-docker     proxmox-docker     lxc-docker
-linode-pxe-boot   proxmox-pxe-boot   lxc-pxe-boot
-linode-gui        proxmox-gui        lxc-gui
-```
-
-That's the full matrix (18 targets) if every build type applies to every platform.
-See **Open Questions** below — some combinations may not make sense and should be
-confirmed with me before being built out, not silently included or dropped.
-
-## Migration mapping (old → new)
-
-| Old target        | New target                                          | Notes |
-|--------------------|------------------------------------------------------|-------|
-| `linode-minimal`   | `linode-minimal`                                      | Already correct, keep as-is |
-| `nix-minimal`      | likely `proxmox-minimal` or a platform-less base module | Ambiguous — see Open Questions |
-| `nix-cache`        | base module consumed by `linode-nix-cache`, `proxmox-nix-cache`, `lxc-nix-cache` | Currently platform-less; needs to become a build-type module, not a standalone target |
-| `server`           | base module consumed by `linode-server`, `proxmox-server`, `lxc-server` | Same as above |
-| `docker`           | base module consumed by `linode-docker`, `proxmox-docker`, `lxc-docker` | Confirm docker actually makes sense as an LXC/VM guest build vs. a standalone container image — see Open Questions |
-| `pxe-boot`         | TBD — may stay a single target rather than a per-platform one | See Open Questions |
-| `nixos`            | TBD — unclear what this maps to in the new scheme | See Open Questions |
-
-## Open Questions (Claude Code: raise these with me before implementing, don't guess)
-
-1. **`nixos` target** — what is this currently used for (bare metal install, dev
-   shell, template)? It doesn't obviously map to any of the six build types.
-2. **`nix-minimal` vs `linode-minimal`** — are these two different things, or is
-   `nix-minimal` a leftover/duplicate?
-3. **`pxe-boot` and `gui` across all three platforms** — does PXE boot make sense
-   for an LXC container or a cloud VM (Linode), or is it inherently bare-metal/
-   network-boot only and should remain a single non-platform target? Does `gui`
-   make sense inside an LXC container?
-4. **`docker` as a build type** — is this "a NixOS host configured to run Docker"
-   (which would sensibly have linode/proxmox/lxc variants), or "a Docker container
-   image built by the flake" (which wouldn't take a platform prefix at all, since
-   it doesn't run on Linode/Proxmox/LXC as a guest OS)? These are structurally
-   different and change how it should be wired in.
-5. Confirm whether all 18 combinations should actually exist, or whether this is
-   meant to produce only the combinations that are genuinely useful (e.g. maybe no
-   one needs `lxc-pxe-boot`).
-
-## Implementation approach
-
-1. **Inventory first.** Read the current `flake.nix` and any `nixosConfigurations`/
-   `modules` structure. Map every existing target to what module(s) it actually
-   pulls in. Don't assume — confirm against the real file contents.
-2. **Separate build-type and platform into their own module directories**, e.g.:
-   ```
-   modules/build-types/minimal.nix
-   modules/build-types/nix-cache.nix
-   modules/build-types/server.nix
-   modules/build-types/docker.nix
-   modules/build-types/pxe-boot.nix
-   modules/build-types/gui.nix
-
-   modules/platforms/linode.nix
-   modules/platforms/proxmox.nix
-   modules/platforms/lxc.nix
-   ```
-   Build-type modules should contain only what makes a system "minimal" vs
-   "server" vs "gui", etc. Platform modules should contain only what's specific
-   to running as a Linode VM vs Proxmox VM vs LXC container (virtualisation
-   guest tools, boot method, filesystem/image format, LXC-specific constraints
-   like no kernel modules, etc).
-3. **Generate the target matrix programmatically** in `flake.nix` rather than
-   hand-writing 18 near-identical `nixosConfigurations` entries — e.g. a small
-   function that takes a platform name and build-type name, composes the two
-   modules plus any shared base module, and produces the named output. This
-   keeps future build types/platforms a one-line addition rather than a copy-paste
-   job.
-4. **Only build combinations we've confirmed make sense** (see Open Questions) —
-   don't emit all 18 by default if some are structurally invalid.
-5. **Preserve existing working configs during the transition.** Don't delete the
-   old target names until their replacements build successfully — rename/alias
-   at the end, not the start, so there's no window where the flake is broken.
-
-## Verification
-
-For every new target produced:
-```bash
-nix flake check
-nix build .#nixosConfigurations.<target>.config.system.build.toplevel
-```
-Confirm each builds without evaluation errors before considering it done. If a
-target fails to build, report which one and why rather than silently skipping it.
-
-## Deliverables
-
-- Refactored `flake.nix` using the composed module + generated-matrix approach.
-- New `modules/build-types/*.nix` and `modules/platforms/*.nix` files.
-- Old flat target names removed only after their replacements are verified.
-- A short `README.md` (or section in existing docs) listing the final target
-  names and what each one is for.
-- A summary at the end of what changed, what was removed, and any of the Open
-  Questions above that got resolved differently than expected.
-
-## Out of scope
-
-- Don't touch `~/nix-auto-installer` contents beyond checking it for references
-  to the old target names — if changes there are needed, flag them, don't make
-  them without confirming.
-- Don't add new build types or platforms beyond the ones listed here.

flake.lock

@@ -1,5 +1,62 @@
 {
   "nodes": {
+    "clan-core": {
+      "inputs": {
+        "data-mesher": "data-mesher",
+        "disko": [
+          "disko"
+        ],
+        "flake-parts": "flake-parts",
+        "nix-darwin": "nix-darwin",
+        "nix-select": "nix-select",
+        "nixpkgs": [
+          "nixpkgs"
+        ],
+        "sops-nix": [
+          "sops-nix"
+        ],
+        "systems": "systems",
+        "treefmt-nix": "treefmt-nix"
+      },
+      "locked": {
+        "lastModified": 1783497933,
+        "narHash": "sha256-TxmwEews6URFPqOWEHNychtXbFDgLZjbOfEXtvtOm6U=",
+        "rev": "3dc0221ca09033599fe98055e9bbc81bdf32732a",
+        "type": "tarball",
+        "url": "https://git.clan.lol/api/v1/repos/clan/clan-core/archive/3dc0221ca09033599fe98055e9bbc81bdf32732a.tar.gz"
+      },
+      "original": {
+        "type": "tarball",
+        "url": "https://git.clan.lol/clan/clan-core/archive/26.05.tar.gz"
+      }
+    },
+    "data-mesher": {
+      "inputs": {
+        "flake-parts": [
+          "clan-core",
+          "flake-parts"
+        ],
+        "nixpkgs": [
+          "clan-core",
+          "nixpkgs"
+        ],
+        "treefmt-nix": [
+          "clan-core",
+          "treefmt-nix"
+        ]
+      },
+      "locked": {
+        "lastModified": 1778718524,
+        "narHash": "sha256-pXLoI6Ax0EnUK6r34UM1vibVC7CfTu6j72R2692ZzPs=",
+        "rev": "12c552ad547d87254f33f33bddd1a2cdbeac754d",
+        "type": "tarball",
+        "url": "https://git.clan.lol/api/v1/repos/clan/data-mesher/archive/12c552ad547d87254f33f33bddd1a2cdbeac754d.tar.gz"
+      },
+      "original": {
+        "type": "tarball",
+        "url": "https://git.clan.lol/clan/data-mesher/archive/main.tar.gz"
+      }
+    },
     "disko": {
       "inputs": {
         "nixpkgs": [
@@ -51,9 +108,30 @@
         "type": "github"
       }
     },
+    "flake-parts": {
+      "inputs": {
+        "nixpkgs-lib": [
+          "clan-core",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1778716662,
+        "narHash": "sha256-m1Yf0wZ8j1OHjTc2UwHwyQRSnNeSgLJOd7q5Y45hzi4=",
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "rev": "f7c1a2d347e4c52d5fb8d10cb4d94b5884e546fb",
+        "type": "github"
+      },
+      "original": {
+        "owner": "hercules-ci",
+        "repo": "flake-parts",
+        "type": "github"
+      }
+    },
     "flake-utils": {
       "inputs": {
-        "systems": "systems"
+        "systems": "systems_2"
       },
       "locked": {
         "lastModified": 1694529238,
@@ -95,11 +173,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1783740085,
+        "lastModified": 1785119570,
-        "narHash": "sha256-qajyHfZY29G2oEQk+uHxmsJcRoBUBXP9maTpFlwP/dI=",
+        "narHash": "sha256-Rgs2xKnGLFWQscxUaXX07oyZeuMDOHEbqDOsgliLFGM=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "3cd22efe6471dc7365c822bd9ad73a21e55f38fb",
+        "rev": "d4fd24667c8cbef124bb70a20380cab75ec8474d",
         "type": "github"
       },
       "original": {
@@ -109,6 +187,40 @@
         "type": "github"
       }
     },
+    "nix-darwin": {
+      "inputs": {
+        "nixpkgs": [
+          "clan-core",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1779036909,
+        "narHash": "sha256-zXcwYQGCT6pzinK+1dBB2ekTVtfxGZAapb3Evdcu4fY=",
+        "owner": "nix-darwin",
+        "repo": "nix-darwin",
+        "rev": "56c666e108467d87d13508936aade6d567f2a501",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-darwin",
+        "repo": "nix-darwin",
+        "type": "github"
+      }
+    },
+    "nix-select": {
+      "locked": {
+        "lastModified": 1763303120,
+        "narHash": "sha256-yxcNOha7Cfv2nhVpz9ZXSNKk0R7wt4AiBklJ8D24rVg=",
+        "rev": "3d1e3860bef36857a01a2ddecba7cdb0a14c35a9",
+        "type": "tarball",
+        "url": "https://git.clan.lol/api/v1/repos/clan/nix-select/archive/3d1e3860bef36857a01a2ddecba7cdb0a14c35a9.tar.gz"
+      },
+      "original": {
+        "type": "tarball",
+        "url": "https://git.clan.lol/clan/nix-select/archive/main.tar.gz"
+      }
+    },
     "nixos-conf-editor": {
       "inputs": {
         "flake-compat": "flake-compat",
@@ -147,11 +259,11 @@
     },
     "nixpkgs_2": {
       "locked": {
-        "lastModified": 1784011430,
+        "lastModified": 1785133411,
-        "narHash": "sha256-lDebytrYdd47IBLwvNOD+6AGeoqZ78CIKlp70hzW280=",
+        "narHash": "sha256-Yjv0WEg39KRYS0rBdTbu6Fc/or/ihAKk13W9sQ6VWd0=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "8eeec934ae0dbeca3d7868c059568a65c08b2fc3",
+        "rev": "2f5a153c270b70cb0f8c11f46d96d6d3bc39f4e3",
         "type": "github"
       },
       "original": {
@@ -163,6 +275,7 @@
     },
     "root": {
       "inputs": {
+        "clan-core": "clan-core",
         "disko": "disko",
         "home-manager": "home-manager",
         "nixos-conf-editor": "nixos-conf-editor",
@@ -214,6 +327,22 @@
       }
     },
     "systems": {
+      "locked": {
+        "lastModified": 1774449309,
+        "narHash": "sha256-brhZ8DmuGtzkCYHJg4HEd602amKm89Y9ytsFZ5uWD1w=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "c29398b59d2048c4ab79345812849c9bd15e9150",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "ref": "future-26.11",
+        "repo": "default",
+        "type": "github"
+      }
+    },
+    "systems_2": {
       "locked": {
         "lastModified": 1681028828,
         "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
@@ -227,6 +356,27 @@
         "repo": "default",
         "type": "github"
       }
+    },
+    "treefmt-nix": {
+      "inputs": {
+        "nixpkgs": [
+          "clan-core",
+          "nixpkgs"
+        ]
+      },
+      "locked": {
+        "lastModified": 1780220602,
+        "narHash": "sha256-eynAfOmbmxJnkp7YewvCEbShNnnYJ9gLLqkzsYtBPeM=",
+        "owner": "numtide",
+        "repo": "treefmt-nix",
+        "rev": "db947814a175b7ca6ded66e21383d938df01c227",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "treefmt-nix",
+        "type": "github"
+      }
     }
   },
   "root": "root",

flake.nix

@@ -16,6 +16,19 @@
       url = "github:Mic92/sops-nix";
       inputs.nixpkgs.follows = "nixpkgs";
     };
+    clan-core = {
+      url = "https://git.clan.lol/clan/clan-core/archive/26.05.tar.gz";
+      # Deduplicate modules: clan-core bundles its own disko and sops-nix
+      # (both imported by nixosModules.clanCore). Without follows, we'd get
+      # two different versions of each, and disko's _module.args.diskoLib
+      # unique option would conflict. With follows, clan-core uses the same
+      # store paths as us, so NixOS deduplicates the imports.
+      inputs = {
+        nixpkgs.follows = "nixpkgs";
+        disko.follows = "disko";
+        sops-nix.follows = "sops-nix";
+      };
+    };
   };
 
   outputs = { self, nixpkgs, nixos-conf-editor, home-manager, sops-nix, ... } @ inputs:
@@ -23,6 +36,8 @@
     let
       system = "x86_64-linux";
       inherit (nixpkgs) lib;
+      pkgs = nixpkgs.legacyPackages.${system};
+      vars = import ./variables.nix;
 
       # Generates a nixosConfiguration from a platform (what it runs on) and
       # a build type (what it's for), plus the per-identity host.nix that
@@ -30,47 +45,70 @@
       # (hostName, hostId, per-machine secrets). Every build type except
       # nix-cache itself consumes the nix-cache substituter and remote
       # builder.
-      mkTarget = { platform, buildType, hostPath, homeFile ? ./modules/common/home.nix }:
+      mkTarget = { platform, buildType, hostPath, homeFile ? ./modules/common/home.nix, nameSuffix ? "" }:
+        let
+          flakeTarget = "${platform}-${buildType}${nameSuffix}";
+        in
         nixpkgs.lib.nixosSystem {
           inherit system;
           modules = [
             inputs.disko.nixosModules.disko
             sops-nix.nixosModules.sops
+            inputs.clan-core.nixosModules.clanCore
+            {
+              # Required clan settings. directory is the flake root (where
+              # vars/ and sops/ directories live); machine.name is the flake
+              # target name (matches what clan vars generate uses as the key
+              # under vars/per-machine/). enableRecommendedDefaults = false
+              # is mandatory: without it, clan unconditionally enables
+              # networking.useNetworkd, adds packages, and tweaks nix settings
+              # -- none of which belong here.
+              clan.core = {
+                settings.directory = self;
+                settings.machine.name = flakeTarget;
+                enableRecommendedDefaults = false;
+              };
+            }
+            ./modules/clan/ssh-host-key.nix
             ./modules/common/configuration.nix
             ./modules/platforms/${platform}.nix
             ./modules/build-types/${buildType}.nix
             hostPath
-            { environment.etc."flake-target".text = "${platform}-${buildType}"; }
+            { environment.etc."flake-target".text = flakeTarget; }
             home-manager.nixosModules.home-manager
             {
               home-manager = {
                 useGlobalPkgs = true;
                 useUserPackages = true;
+                extraSpecialArgs = { inherit vars; };
                 users.nixos = import homeFile;
               };
             }
           ] ++ lib.optionals (buildType != "nix-cache") [
             ./modules/nix-cache/client.nix
-            ./modules/remote-builder-client.nix
+            ./modules/nix-cache/remote-builder-client.nix
           ];
-          specialArgs = { inherit inputs; };
+          # flakeTarget is passed via specialArgs (not read back from
+          # config.environment.etc."flake-target" above) specifically so
+          # modules/platforms/lxc.nix can use it to select its own host key
+          # file without a same-option circular dependency (a module
+          # contributing to environment.etc can't read the merged
+          # environment.etc it's itself contributing to).
+          specialArgs = { inherit inputs vars netbootSystem netbootMinimalSystem flakeTarget; };
         };
 
       # Generated platform x build-type matrix. pxe-boot has no linode
       # variant (PXE/DHCP/TFTP need LAN L2 adjacency, which a Linode VPS
       # doesn't have).
       generatedTargets = {
-        linode-minimal = mkTarget { platform = "linode"; buildType = "minimal"; hostPath = ./hosts/linode-minimal/host.nix; };
+        linode-minimal = mkTarget { platform = "linode"; buildType = "minimal"; hostPath = ./hosts/nix-minimal/host.nix; };
-        proxmox-minimal = mkTarget { platform = "proxmox"; buildType = "minimal"; hostPath = ./hosts/proxmox-minimal/host.nix; };
+        proxmox-minimal = mkTarget { platform = "proxmox"; buildType = "minimal"; hostPath = ./hosts/nix-minimal/host.nix; };
-        lxc-minimal = mkTarget { platform = "lxc"; buildType = "minimal"; hostPath = ./hosts/lxc-minimal/host.nix; };
+        lxc-minimal = mkTarget { platform = "lxc"; buildType = "minimal"; hostPath = ./hosts/nix-minimal/host.nix; };
 
         linode-nix-cache = mkTarget { platform = "linode"; buildType = "nix-cache"; hostPath = ./hosts/nix-cache/host.nix; };
         proxmox-nix-cache = mkTarget { platform = "proxmox"; buildType = "nix-cache"; hostPath = ./hosts/nix-cache/host.nix; };
         lxc-nix-cache = mkTarget { platform = "lxc"; buildType = "nix-cache"; hostPath = ./hosts/nix-cache/host.nix; };
 
-        linode-server = mkTarget { platform = "linode"; buildType = "server"; hostPath = ./hosts/server/host.nix; };
-        proxmox-server = mkTarget { platform = "proxmox"; buildType = "server"; hostPath = ./hosts/server/host.nix; };
-        lxc-server = mkTarget { platform = "lxc"; buildType = "server"; hostPath = ./hosts/server/host.nix; };
 
         linode-docker = mkTarget { platform = "linode"; buildType = "docker"; hostPath = ./hosts/docker/host.nix; };
         proxmox-docker = mkTarget { platform = "proxmox"; buildType = "docker"; hostPath = ./hosts/docker/host.nix; };
@@ -79,14 +117,123 @@
         linode-gui = mkTarget { platform = "linode"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
         proxmox-gui = mkTarget { platform = "proxmox"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
         lxc-gui = mkTarget { platform = "lxc"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
+        baremetal-gui = mkTarget { platform = "baremetal"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
 
         proxmox-pxe-boot = mkTarget { platform = "proxmox"; buildType = "pxe-boot"; hostPath = ./hosts/pxe-boot/host.nix; };
         lxc-pxe-boot = mkTarget { platform = "lxc"; buildType = "pxe-boot"; hostPath = ./hosts/pxe-boot/host.nix; };
+
+        linode-tailscale-router = mkTarget { platform = "linode"; buildType = "tailscale-router"; hostPath = ./hosts/tailscale-router/host.nix; };
+        proxmox-tailscale-router = mkTarget { platform = "proxmox"; buildType = "tailscale-router"; hostPath = ./hosts/tailscale-router/host.nix; };
+        lxc-tailscale-router = mkTarget { platform = "lxc"; buildType = "tailscale-router"; hostPath = ./hosts/tailscale-router/host.nix; };
+
+        lxc-tor-relay = mkTarget { platform = "lxc"; buildType = "tor-relay"; hostPath = ./hosts/tor-relay/host.nix; };
+
+        proxmox-ha-server-1 = mkTarget { platform = "proxmox"; buildType = "ha-server"; hostPath = ./hosts/ha-server-1/host.nix; nameSuffix = "-1"; };
+        proxmox-ha-server-2 = mkTarget { platform = "proxmox"; buildType = "ha-server"; hostPath = ./hosts/ha-server-2/host.nix; nameSuffix = "-2"; };
+      };
+
+      # Auto-install environments (migrated from the former nix-auto-installer
+      # flake): a self-contained NixOS installer that boots, discovers this
+      # flake's own nixosConfigurations over the network, and runs
+      # nixos-install against whichever one the operator picks. These are
+      # deliberately not part of the platform x build-type matrix above —
+      # they're throwaway boot media, not persistent hosts, so they skip
+      # disko/sops-nix/home-manager and just need `vars`.
+      installerTargets = {
+        installer = nixpkgs.lib.nixosSystem {
+          inherit system;
+          modules = [ ./modules/installer/iso.nix ];
+          specialArgs = { inherit vars; };
+        };
+      };
+
+      # Same installer environment, built as netboot (kernel + initrd +
+      # iPXE script) instead of an ISO — this is what packages.pxe bundles.
+      #
+      # Deliberately imports common.nix directly, NOT ./modules/installer/iso.nix
+      # (which pulls in nixpkgs' installation-cd-minimal.nix) -- confirmed live
+      # that composing the ISO module together with netboot-minimal.nix hangs
+      # every boot waiting for a device that can never exist on a netboot
+      # client ("A start job is running for /dev/disk/by-label/nixos-minimal-...").
+      # Both installation-cd-base.nix and netboot.nix set fileSystems."/" via
+      # the identical lib.mkImageMediaOverride (mkOverride 60) priority --
+      # genuinely conflicting root-filesystem strategies (ISO-by-label vs.
+      # netboot-tmpfs) at the same priority, and the ISO one was winning.
+      # netboot-minimal.nix's own chain (netboot-base.nix) already imports
+      # profiles/installation-device.nix independently, so common.nix's
+      # initialHashedPassword override (which assumes that profile is
+      # present) still applies correctly without iso.nix in the mix.
+      #
+      # networking.hostName is set explicitly (rather than left at nixpkgs'
+      # own "nixos" default) so this image's generated system name
+      # (nixos-system-auto-installer-*) matches its iPXE menu entry —
+      # see modules/build-types/pxe-boot.nix's :auto-installer item — and
+      # its staged directory, /srv/pxe/http/auto-installer.
+      netbootSystem = nixpkgs.lib.nixosSystem {
+        inherit system;
+        modules = [
+          ./modules/installer/common.nix
+          ({ modulesPath, ... }: {
+            imports = [
+              (modulesPath + "/installer/netboot/netboot-minimal.nix")
+            ];
+          })
+          { networking.hostName = "auto-installer"; }
+        ];
+        specialArgs = { inherit vars; };
+      };
+
+      # A genuinely vanilla NixOS minimal netboot image: nixpkgs'
+      # netboot-minimal.nix on its own, with none of this flake's
+      # auto-installer wiring (no common.nix — no auto-install.sh, no
+      # baked host keys, no custom users/passwords). Built from source via
+      # the same nixosSystem + netboot-minimal.nix path as netbootSystem
+      # above, so both go through an identical build mechanism; the only
+      # difference is what's composed in. hostName again matches this
+      # image's iPXE menu entry (:nixos-minimal) and staged directory
+      # (/srv/pxe/http/nixos-minimal).
+      netbootMinimalSystem = nixpkgs.lib.nixosSystem {
+        inherit system;
+        modules = [
+          ({ modulesPath, ... }: {
+            imports = [
+              (modulesPath + "/installer/netboot/netboot-minimal.nix")
+            ];
+          })
+          { networking.hostName = "nixos-minimal"; }
+        ];
       };
 
     in
     {
 
-      nixosConfigurations = generatedTargets;
+      nixosConfigurations = generatedTargets // installerTargets;
+
+      # Buildable auto-installer artifacts (`nix build .#<name>`). No `lxc`
+      # variant (installer-boots-as-an-LXC-container) or `all` bundle
+      # anymore — lxc-* and proxmox-* hosts deploy via their own tarball/
+      # disk-image outputs instead (see docs/auto-installer.md and
+      # docs/proxmox-images.md), which left the installer's own LXC form
+      # with no real use case: it's excluded from the install menu (same
+      # bind-mount problem as any LXC nixos-install target) and nothing
+      # else needed booting the installer itself as a container.
+      packages.${system} = {
+        iso = installerTargets.installer.config.system.build.isoImage;
+
+        pxe = pkgs.linkFarm "pxe" [
+          { name = "netboot.ipxe"; path = netbootSystem.config.system.build.netbootIpxeScript; }
+          { name = "initrd"; path = netbootSystem.config.system.build.netbootRamdisk; }
+          { name = "kernel"; path = netbootSystem.config.system.build.kernel; }
+        ];
+
+        # Vanilla NixOS minimal netboot bundle — see netbootMinimalSystem
+        # above. Staged onto the pxe-boot host alongside packages.pxe by
+        # modules/pxe-boot/stage-installer-artifacts.nix.
+        pxe-minimal = pkgs.linkFarm "pxe-minimal" [
+          { name = "netboot.ipxe"; path = netbootMinimalSystem.config.system.build.netbootIpxeScript; }
+          { name = "initrd"; path = netbootMinimalSystem.config.system.build.netbootRamdisk; }
+          { name = "kernel"; path = netbootMinimalSystem.config.system.build.kernel; }
+        ];
+      };
     };
 }

hosts/docker/host.nix

@@ -1,10 +1,24 @@
-{ ... }:
+{ vars, ... }:
 
 {
-  networking.hostName = "docker";
+  networking = {
-  networking.hostId = "007f0200";
+    hostName = "docker";
+    hostId = "007f0200";
+    useDHCP = false;
+    interfaces = {
+      ${vars.vmLanInterface}.ipv4.addresses = [{ address = vars.dockerIp; prefixLength = vars.lanPrefixLength; }];
+      ${vars.lxcStorageInterface}.ipv4.addresses = [{ address = vars.dockerStorageIp; prefixLength = vars.haClientPrefixLength; }];
+    };
+    defaultGateway = { address = vars.lanGateway; interface = vars.vmLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
   boot.zfs.forceImportRoot = false;
 
+  # Only advertise the LAN interface to IPA DNS. Without this, SSSD registers
+  # every Docker bridge (172.x.x.x) as an A record for docker.sweet.home —
+  # the default dyndns.interface = "*" catches them all.
+  security.ipa.dyndns.interface = vars.lxcLanInterface; # eth0
+
   # Preserved from the pre-refactor `docker` target — stateVersion must never
   # be bumped on an already-installed machine.
   system.stateVersion = "25.05";

hosts/ha-server-1/host.nix

@@ -0,0 +1,17 @@
+{ vars, ... }:
+{
+  networking = {
+    hostName = vars.haServer1Host;
+    hostId = "3a4b5c6d";
+    useDHCP = false;
+    interfaces = {
+      ${vars.vmLanInterface}.ipv4.addresses = [{ address = vars.haServer1Ip; prefixLength = vars.lanPrefixLength; }];
+      ${vars.vmStorageInterface}.ipv4.addresses = [{ address = vars.haServer1StorageIp; prefixLength = vars.haStoragePrefixLength; }];
+      ${vars.vmStorageClientInterface}.ipv4.addresses = [{ address = vars.haServer1ClientIp; prefixLength = vars.haClientPrefixLength; }];
+    };
+    defaultGateway = { address = vars.lanGateway; interface = vars.vmLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
+
+  system.stateVersion = "26.05";
+}

hosts/ha-server-2/host.nix

@@ -0,0 +1,17 @@
+{ vars, ... }:
+{
+  networking = {
+    hostName = vars.haServer2Host;
+    hostId = "7e8f9a0b";
+    useDHCP = false;
+    interfaces = {
+      ${vars.vmLanInterface}.ipv4.addresses = [{ address = vars.haServer2Ip; prefixLength = vars.lanPrefixLength; }];
+      ${vars.vmStorageInterface}.ipv4.addresses = [{ address = vars.haServer2StorageIp; prefixLength = vars.haStoragePrefixLength; }];
+      ${vars.vmStorageClientInterface}.ipv4.addresses = [{ address = vars.haServer2ClientIp; prefixLength = vars.haClientPrefixLength; }];
+    };
+    defaultGateway = { address = vars.lanGateway; interface = vars.vmLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
+
+  system.stateVersion = "26.05";
+}

hosts/linode-minimal/host.nix

@@ -1,9 +0,0 @@
-{ ... }:
-
-{
-  networking.hostName = "linode-minimal";
-
-  # Preserved from the pre-refactor `linode-minimal` target — stateVersion
-  # must never be bumped on an already-installed machine.
-  system.stateVersion = "26.05";
-}

hosts/lxc-minimal/host.nix

@@ -1,9 +0,0 @@
-{ ... }:
-
-{
-  networking.hostName = "lxc-minimal";
-
-  # No pre-existing deployed machine to preserve — pin explicitly to the
-  # current release rather than let it silently default.
-  system.stateVersion = "26.05";
-}

hosts/nix-cache/host.nix

@@ -1,19 +1,16 @@
-{ config, ... }:
+{ vars, ... }:
 
 {
-  networking.hostName = "nix-cache";
+  networking = {
-
+    hostName = vars.nixCacheHost;
-  sops.secrets."beszel-token".sopsFile = ../../secrets/nix-cache.yaml;
+    useDHCP = false;
-  sops.templates."nix-cache-beszel.env".content = ''
+    interfaces.${vars.lxcLanInterface}.ipv4.addresses = [{
-    TOKEN=${config.sops.placeholder."beszel-token"}
+      address = vars.nixCacheIp;
-  '';
+      prefixLength = vars.lanPrefixLength;
-
+    }];
-  services.beszel.agent.environment = {
+    defaultGateway = { address = vars.lanGateway; interface = vars.lxcLanInterface; };
-    #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
+    nameservers = [ vars.domainControllerIp ];
-    #HUB_URL = "http://docker.sweet.home:8090";
-    KEY = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFPR9kwtC4TAeTRu46A7+opZsYpxqkRJ+x/ZyB2GWCeG";
   };
-  services.beszel.agent.environmentFile = config.sops.templates."nix-cache-beszel.env".path;
 
   # Preserved from the pre-refactor `nix-cache` target — stateVersion must
   # never be bumped on an already-installed machine.

hosts/nix-minimal/host.nix

@@ -1,4 +1,4 @@
-{ ... }:
+_:
 
 {
   # Preserves the hostname of the existing, already-deployed machine

hosts/nixos/home.nix

@@ -1,79 +1,86 @@
-{ config, pkgs, lib, ... }:
+{ config, pkgs, lib, vars, ... }:
 
 {
 
-    imports = [
+  imports = [
     ../../modules/common/aliases.nix
   ];
 
-  home.username = "nixos";         # your actual username
+  home = {
-  home.homeDirectory = "/home/nixos";
+    username = vars.primaryUser;
-  home.stateVersion = "25.05";        # match your NixOS stateVersion
+    homeDirectory = "/home/${vars.primaryUser}";
+    stateVersion = "25.05"; # match your NixOS stateVersion
 
-  programs.home-manager.enable = true;  # mandatory to activate HM
+    # Optional: packages
+    packages = with pkgs; [
+      git
+      vim
+      tmux
+      nextcloud-client
+      #    vscode
+      chromium
+      claude-code
+      fish
+      sops
+    ];
 
-  # Optional: packages
+    # Optional: set environment vars
-  home.packages = with pkgs; [
+    sessionVariables = {
-    git
+      EDITOR = "nano";
-    vim
+      SOPS_AGE_KEY_FILE = "${config.home.homeDirectory}/.config/sops/age/keys.txt";
-    tmux
+    };
-    nextcloud-client
-#    vscode
-    chromium
-  ];
 
-  # Optional: set environment vars
+    file = {
-  home.sessionVariables = {
+      ".local/share/applications/proxmox-chromium-app.desktop".text = ''
-    EDITOR = "vim";
+        [Desktop Entry]
+        Type=Application
+        Name=Proxmox (Chromium)
+        Exec=chromium --app=https://pve.${vars.homeDomain}:${toString vars.ports.pveWeb} --window-size=1920,1080 --window-position=0,0
+        Icon=${config.home.homeDirectory}/.local/share/icons/proxmox.png
+        Terminal=false
+        Categories=Hypervisor;
+        StartupWMClass=PVE
+      '';
+      ".local/share/applications/pbs-chromium-app.desktop".text = ''
+        [Desktop Entry]
+        Type=Application
+        Name=Proxmox Backup Server (Chromium)
+        Exec=chromium --app=https://${vars.pbsIp}:${toString vars.ports.pbsWeb} --window-size=1920,1080 --window-position=0,0
+        Icon=${config.home.homeDirectory}/.local/share/icons/proxmox.png
+        Terminal=false
+        Categories=backup;
+
+      '';
+      ".local/share/applications/proxmox-firefox-app.desktop".text = ''
+        [Desktop Entry]
+        Type=Application
+        Name=Proxmox (Firefox)
+        Exec=firefox --new-instance https://pve.${vars.homeDomain}:${toString vars.ports.pveWeb} --profile ProxmoxWebApp --window-size=1920,1080 --class ProxmoxWebApp
+        Icon=${config.home.homeDirectory}/.local/share/icons/proxmox.png
+        Terminal=false
+        Categories=Hypervisor;
+        StartupWMClass=PVE
+      '';
+      ".local/share/applications/pbs-firefox-app.desktop".text = ''
+        [Desktop Entry]
+        Type=Application
+        Name=Proxmox Backup Server (Firefox)
+        Exec=firefox --new-window https://${vars.pbsIp}:${toString vars.ports.pbsWeb} --profile PbsWebApp --window-size=1920,1080 --class PbsWebApp
+        Icon=${config.home.homeDirectory}/.local/share/icons/proxmox.png
+        Terminal=false
+        Categories=backup;
+        StartupWMClass=PBS
+      '';
+    };
   };
 
+  programs.home-manager.enable = true; # mandatory to activate HM
+
   # Optional: enable bash (or zsh, fish...)
   programs.bash.enable = true;
-    services.nextcloud-client = {
+  services.nextcloud-client = {
     enable = true;
     # Optionally start in background directly
     startInBackground = true;
   };
-home.file = {
-  ".local/share/applications/proxmox-chromium-app.desktop".text = ''
-    [Desktop Entry]
-    Type=Application
-    Name=Proxmox (Chromium)
-    Exec=chromium --app=https://pve.sweet.home:8006 --window-size=1920,1080 --window-position=0,0
-    Icon=/home/nixos/.local/share/icons/proxmox.png
-    Terminal=false
-    Categories=Hypervisor;
-    StartupWMClass=PVE
-  '';
-  ".local/share/applications/pbs-chromium-app.desktop".text = ''
-    [Desktop Entry]
-    Type=Application
-    Name=Proxmox Backup Server (Chromium)
-    Exec=chromium --app=https://192.168.2.108:8007 --window-size=1920,1080 --window-position=0,0
-    Icon=/home/nixos/.local/share/icons/proxmox.png
-    Terminal=false
-    Categories=backup;
-
-  '';
-  ".local/share/applications/proxmox-firefox-app.desktop".text = ''
-    [Desktop Entry]
-    Type=Application
-    Name=Proxmox (Firefox)
-    Exec=firefox --new-instance https://pve.sweet.home:8006 --profile ProxmoxWebApp --window-size=1920,1080 --class ProxmoxWebApp
-    Icon=/home/nixos/.local/share/icons/proxmox.png
-    Terminal=false
-    Categories=Hypervisor;
-    StartupWMClass=PVE
-  '';
-  ".local/share/applications/pbs-firefox-app.desktop".text = ''
-    [Desktop Entry]
-    Type=Application
-    Name=Proxmox Backup Server (Firefox)
-    Exec=firefox --new-window https://192.168.2.108:8007 --profile PbsWebApp --window-size=1920,1080 --class PbsWebApp
-    Icon=/home/nixos/.local/share/icons/proxmox.png
-    Terminal=false
-    Categories=backup;
-    StartupWMClass=PBS
-  '';
-};
 }

hosts/nixos/host.nix

@@ -1,8 +1,17 @@
-{ ... }:
+_:
 
 {
+  imports = [
+    ../../modules/networking/wifi.nix
+  ];
+
   networking.hostName = "nixos";
 
+  # Only needed now that baremetal-gui exists (ZFS root) -- harmless on the
+  # ext4-rooted linode/proxmox/lxc-gui variants, so set unconditionally
+  # rather than only on the baremetal platform.
+  networking.hostId = "de6a9ffc";
+
   # Preserved from the pre-refactor `nixos` target — stateVersion must never
   # be bumped on an already-installed machine.
   system.stateVersion = "25.05";

hosts/pxe-boot/host.nix

@@ -1,8 +1,19 @@
-{ ... }:
+{ vars, ... }:
 
 {
-  networking.hostName = "pxe-boot";
+  networking = {
-
+    hostName = "pxe-boot";
+    useDHCP = false;
+    interfaces.${vars.lxcLanInterface}.ipv4.addresses = [{
+      address = vars.pxeServerIp;
+      prefixLength = vars.lanPrefixLength;
+    }];
+    defaultGateway = { address = vars.lanGateway; interface = vars.lxcLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
+services.beszel.agent.environment = {
+#    KEY = "";
+  };
   # Preserved from the pre-refactor `pxe-boot` target — stateVersion must
   # never be bumped on an already-installed machine.
   system.stateVersion = "25.05";

hosts/server/host.nix

@@ -1,24 +0,0 @@
-{ config, ... }:
-
-{
-  networking.hostName = "server";
-  networking.hostId = "6689f93e";
-
-  sops.secrets."beszel-token".sopsFile = ../../secrets/server.yaml;
-  sops.templates."server-beszel.env".content = ''
-    TOKEN=${config.sops.placeholder."beszel-token"}
-  '';
-
-  services.beszel.agent.environment = {
-    #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
-    #HUB_URL = "http://docker.sweet.home:8090";
-    KEY = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFPR9kwtC4TAeTRu46A7+opZsYpxqkRJ+x/ZyB2GWCeG";
-    EXTRA_FILESYSTEMS = "/tank/docker/volumes";
-    LOG_LEVEL = "debug";
-  };
-  services.beszel.agent.environmentFile = config.sops.templates."server-beszel.env".path;
-
-  # Preserved from the pre-refactor `server` target — stateVersion must never
-  # be bumped on an already-installed machine.
-  system.stateVersion = "25.05";
-}

hosts/tailscale-router/host.nix

@@ -0,0 +1,19 @@
+{ vars, ... }:
+
+{
+  networking = {
+    hostName = "tailscale-router";
+    useDHCP = false;
+    interfaces.${vars.lxcLanInterface}.ipv4.addresses = [{
+      address = vars.tailscaleRouterIp;
+      prefixLength = vars.lanPrefixLength;
+    }];
+    defaultGateway = { address = vars.lanGateway; interface = vars.lxcLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
+
+  # No networking.hostId: only ZFS-touching hosts (server, docker) need one
+  # for pool-import safety, and this host does neither.
+
+  system.stateVersion = "26.05";
+}

hosts/tor-relay/host.nix

@@ -0,0 +1,21 @@
+{ vars, ... }:
+
+{
+  networking = {
+    hostName = "tor-relay";
+    useDHCP = false;
+    interfaces.${vars.lxcLanInterface}.ipv4.addresses = [{
+      address = vars.torRelayIp;
+      prefixLength = vars.lanPrefixLength;
+    }];
+    defaultGateway = { address = vars.lanGateway; interface = vars.lxcLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
+  };
+
+  # No networking.hostId: only ZFS-touching hosts need one for pool-import
+  # safety, and this host does neither.
+
+  # A genuinely new host (not a pre-refactor carry-over), so it tracks the
+  # flake's current nixpkgs release rather than being pinned to an older one.
+  system.stateVersion = "26.05";
+}

modules/beszel/enable-agent.nix

@@ -1,9 +1,31 @@
-{ ... }:
+{ config, vars, ... }:
 
 {
-services.beszel.agent.enable = true;
+  # Universal token shared by all beszel agents. Add to secrets/common.yaml:
-services.beszel.agent.environment = {
+  #   sops secrets/common.yaml
-#DOCKER_HOST = "tcp://docker-socket-proxy:2375";
+  #   beszel-token: <value from the beszel hub UI>
-HUB_URL = "http://docker.sweet.home:8090";
+  sops.secrets."beszel-token" = { };
-};
+
+  sops.templates."beszel.env".content = ''
+    TOKEN=${config.sops.placeholder."beszel-token"}
+  '';
+
+  services.beszel.agent = {
+    enable = true;
+    environmentFile = config.sops.templates."beszel.env".path;
+    environment = {
+      #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
+      HUB_URL = "http://${vars.dockerHost}.${vars.homeDomain}:${toString vars.ports.beszelHub}";
+      KEY = vars.beszelHubKey;
+    };
+  };
+
+  # The upstream module runs beszel-agent under DynamicUser with
+  # ProtectSystem = "strict" and no StateDirectory, so /var/lib/beszel-agent
+  # (where the agent persists its hub-pairing fingerprint, per
+  # https://github.com/henrygd/beszel/discussions/1542) isn't writable --
+  # every restart silently fails to save it and regenerates a fresh one in
+  # memory, permanently desyncing from whatever the hub has on record after
+  # the very first successful pairing. Give it real persistent storage.
+  systemd.services.beszel-agent.serviceConfig.StateDirectory = "beszel-agent";
 }

modules/boot/efi.nix

@@ -1,4 +1,4 @@
-{ ... }:
+_:
 
 {
   boot.loader.systemd-boot.enable = true;

modules/build-types/docker.nix

@@ -1,4 +1,4 @@
-{ pkgs, ... }:
+{ pkgs, vars, ... }:
 
 {
   # Pins the Docker Engine version, carried forward from the pre-refactor
@@ -13,11 +13,10 @@
   imports = [
     ../docker/mount-data.nix
     ../docker/enable-service.nix
-    ../tailscale/enable-service.nix
+    ../docker/nextcloud-cron-job.nix
-    ../rotate-traefik-logs.nix
+    ../docker/docker-health-to-gotify.nix
+    ../traefik/rotate-logs.nix
     ../raspi/mount-data.nix
-    ../services/nextcloud-cron-job.nix
-    ../services/docker-health-to-gotify.nix
     ../services/enable-rpcbind.nix
   ];
 
@@ -28,13 +27,18 @@
   boot.supportedFilesystems = [ "nfs" ];
 
   systemd.tmpfiles.rules = [
-    "L+ /home/nixos/docker - - - - /mnt/docker/config"
+    "L+ /home/${vars.primaryUser}/docker - - - - ${vars.nfsShares.dockerConfig.mountpoint}"
-    "d /mnt/docker 0755 nixos users -"
+    "d /mnt/docker 0755 ${vars.primaryUser} users -"
-    "d /mnt/raspi-backup 0755 nixos users -"
+    "d ${vars.nfsShares.raspiVolumes.mountpoint} 0755 ${vars.primaryUser} users -"
   ];
 
-  users.users.nixos.extraGroups = [ "docker" ];
+  users.users.${vars.primaryUser}.extraGroups = [ "docker" ];
   services.openssh.settings.PermitRootLogin = "yes";
 
-  networking.firewall.allowedTCPPorts = [ 80 8080 443 8090 ];
+  networking.firewall.allowedTCPPorts = [
+    vars.ports.dockerHttp
+    vars.ports.dockerExtra
+    vars.ports.dockerHttps
+    vars.ports.beszelHub
+  ];
 }

modules/build-types/gui.nix

@@ -1,8 +1,19 @@
-{ config, pkgs, lib, inputs, ... }:
+{ config, pkgs, lib, inputs, vars, ... }:
 
 {
+  imports = [
+    ../docker/enable-service.nix
+  ];
+
+  nixpkgs.overlays = [
+    (final: prev: {
+      docker = prev.docker_29;
+      docker_cli = prev.docker_29;
+    })
+  ];
+
   environment.systemPackages = with pkgs; [
-    inputs.nixos-conf-editor.packages.${pkgs.system}.nixos-conf-editor
+    inputs.nixos-conf-editor.packages.${pkgs.stdenv.hostPlatform.system}.nixos-conf-editor
     nodejs
     appimage-run
     seahorse
@@ -18,40 +29,122 @@
   ];
 
   boot.loader.grub.useOSProber = true;
+  programs.direnv.enable = true;
+  services = {
+    xserver = {
+      enable = true;
 
-  services.xserver.enable = true;
+      displayManager = {
-  services.xserver.displayManager.lightdm.enable = true;
+        lightdm.enable = true;
-  services.xserver.desktopManager.cinnamon.enable = true;
+        sessionCommands = ''
+          eval $(gnome-keyring-daemon --start --components=secrets,ssh)
+          export SSH_AUTH_SOCK
+        '';
+      };
 
-  services.xserver.xkb = {
+      desktopManager.cinnamon.enable = true;
-    layout = "au";
+
-    variant = "";
+      xkb = {
+        layout = "au";
+        variant = "";
+      };
+    };
+
+    printing.enable = true;
+
+    pipewire = {
+      enable = true;
+      alsa.enable = true;
+      alsa.support32Bit = true;
+      pulse.enable = true;
+    };
+
+    xrdp = {
+      enable = true;
+      defaultWindowManager = "cinnamon-session";
+      openFirewall = true;
+    };
+
+    gnome.gnome-keyring.enable = true;
   };
 
-  services.printing.enable = true;
+  security = {
-
+    rtkit.enable = true;
-  security.rtkit.enable = true;
+    pam.services.login.enableGnomeKeyring = true;
-  services.pipewire = {
-    enable = true;
-    alsa.enable = true;
-    alsa.support32Bit = true;
-    pulse.enable = true;
   };
 
-  users.users.nixos.extraGroups = [ "networkmanager" ];
+  # The networkmanager group only exists when NM is actually enabled — the
+  # lxc platform module force-disables it, so don't add the user to a group
+  # that won't exist there.
+  users.users.${vars.primaryUser}.extraGroups = lib.mkIf config.networking.networkmanager.enable [ "networkmanager" ];
 
   programs.firefox.enable = true;
 
-  services.xrdp.enable = true;
-  services.xrdp.defaultWindowManager = "cinnamon-session";
-  services.xrdp.openFirewall = true;
   nixpkgs.config.allowUnfree = true;
 
-  services.gnome.gnome-keyring.enable = true;
+  # GUI-specific Home Manager additions for the IPA primary user, extending
-  security.pam.services.login.enableGnomeKeyring = true;
+  # the baseline in modules/ipa/client.nix with desktop apps and services
-
+  # that only make sense on a graphical workstation.
-  services.xserver.displayManager.sessionCommands = ''
+  home-manager.users.${vars.ipaUser} = { pkgs, ... }: {
-    eval $(gnome-keyring-daemon --start --components=secrets,ssh)
+    home = {
-    export SSH_AUTH_SOCK
+      packages = with pkgs; [
-  '';
+        git
+        vim
+        nextcloud-client
+        chromium
+        claude-code
+        fish
+        sops
+      ];
+      sessionVariables = {
+        EDITOR = "nano";
+        SOPS_AGE_KEY_FILE = "/home/${vars.ipaUser}/.config/sops/age/keys.txt";
+      };
+      file = {
+        ".local/share/applications/proxmox-chromium-app.desktop".text = ''
+          [Desktop Entry]
+          Type=Application
+          Name=Proxmox (Chromium)
+          Exec=chromium --app=https://pve.${vars.homeDomain}:${toString vars.ports.pveWeb} --window-size=1920,1080 --window-position=0,0
+          Icon=/home/${vars.ipaUser}/.local/share/icons/proxmox.png
+          Terminal=false
+          Categories=Hypervisor;
+          StartupWMClass=PVE
+        '';
+        ".local/share/applications/pbs-chromium-app.desktop".text = ''
+          [Desktop Entry]
+          Type=Application
+          Name=Proxmox Backup Server (Chromium)
+          Exec=chromium --app=https://${vars.pbsIp}:${toString vars.ports.pbsWeb} --window-size=1920,1080 --window-position=0,0
+          Icon=/home/${vars.ipaUser}/.local/share/icons/proxmox.png
+          Terminal=false
+          Categories=backup;
+        '';
+        ".local/share/applications/proxmox-firefox-app.desktop".text = ''
+          [Desktop Entry]
+          Type=Application
+          Name=Proxmox (Firefox)
+          Exec=firefox --new-instance https://pve.${vars.homeDomain}:${toString vars.ports.pveWeb} --profile ProxmoxWebApp --window-size=1920,1080 --class ProxmoxWebApp
+          Icon=/home/${vars.ipaUser}/.local/share/icons/proxmox.png
+          Terminal=false
+          Categories=Hypervisor;
+          StartupWMClass=PVE
+        '';
+        ".local/share/applications/pbs-firefox-app.desktop".text = ''
+          [Desktop Entry]
+          Type=Application
+          Name=Proxmox Backup Server (Firefox)
+          Exec=firefox --new-window https://${vars.pbsIp}:${toString vars.ports.pbsWeb} --profile PbsWebApp --window-size=1920,1080 --class PbsWebApp
+          Icon=/home/${vars.ipaUser}/.local/share/icons/proxmox.png
+          Terminal=false
+          Categories=backup;
+          StartupWMClass=PBS
+        '';
+      };
+    };
+    services.nextcloud-client = {
+      enable = true;
+      startInBackground = true;
+    };
+  };
 }

modules/build-types/ha-server.nix

@@ -0,0 +1,54 @@
+# HA file server build type: DRBD + XFS + LIO iSCSI + NFS, managed by
+# Corosync + Pacemaker.  Both ha-server-1 and ha-server-2 use this type.
+#
+# NFS start/stop:
+#   services.nfs.server.enable = true configures /etc/exports, wires up
+#   rpcbind, and loads kernel modules — but nfs-server.service.wantedBy is
+#   force-cleared so systemd does NOT auto-start it at boot.  Pacemaker's
+#   ha-group resource group (configured by scripts/ha/cluster-init.sh)
+#   starts and stops nfs-server as part of the failover sequence after the
+#   XFS mount and iSCSI target are brought up on the new Active node.
+#
+# Beszel agent:
+#   Enabled here via enable-agent.nix.  The agent KEY (used to pair with
+#   the Beszel hub) is not set yet — add it to hosts/ha-server-{1,2}/host.nix
+#   under services.beszel.agent.environment.KEY once the hub accepts the
+#   new agents, following the pattern in hosts/server/host.nix.
+{ lib, pkgs, vars, ... }:
+
+let
+  # Generates /etc/exports lines for all nfsShares data entries.
+  # LAN (VLAN 2): NFS via vip-lan (192.168.2.229) for pxe-boot and other LAN clients.
+  # Storage-client (VLAN 20): NFS via vip-storage (192.168.20.229) for docker and
+  # future swarm nodes; firewall restricts these ports to haClientCidr only.
+  mkNfsExports = storageRoot:
+    lib.concatMapStrings
+      (share:
+        "  ${storageRoot}/${share.subpath} ${vars.lanCidr}${vars.nfsShares.options}\n" +
+        "  ${storageRoot}/${share.subpath} ${vars.haClientCidr}${vars.nfsShares.options}\n")
+      (lib.filter builtins.isAttrs (lib.attrValues vars.nfsShares));
+in
+{
+  imports = [
+    ../ha/pacemaker-stack.nix
+    ../ha/iscsi-target.nix
+    ../ha/cluster-config.nix
+    ../beszel/enable-agent.nix
+  ];
+
+  # xfsprogs: mkfs.xfs/xfs_info needed by cluster-init.sh.
+  # openiscsi: iscsiadm needed by acceptance-tests.sh T4 (iSCSI discovery check).
+  environment.systemPackages = [ pkgs.xfsprogs pkgs.openiscsi ];
+
+  services.nfs.server = {
+    enable = true;
+    exports = mkNfsExports vars.haStorageRoot;
+  };
+
+  # Pacemaker controls nfs-server — prevent systemd from starting it at boot
+  # on both nodes (only the Active node should be serving NFS).
+  systemd.services.nfs-server.wantedBy = lib.mkForce [ ];
+
+  # Same reason as server.nix: exports use standard auth, not Kerberos.
+  systemd.services.rpc-svcgssd.enable = false;
+}

modules/build-types/minimal.nix

@@ -1,9 +1,12 @@
-{ pkgs, ... }:
+{ lib, pkgs, config, vars, ... }:
 
 {
   networking.networkmanager.enable = true;
 
-  users.users.nixos.extraGroups = [ "networkmanager" ];
+  # The networkmanager group only exists when NM is actually enabled — the
+  # lxc platform module force-disables it, so don't add the user to a group
+  # that won't exist there.
+  users.users.${vars.primaryUser}.extraGroups = lib.mkIf config.networking.networkmanager.enable [ "networkmanager" ];
 
   environment.systemPackages = with pkgs; [
     inetutils

modules/build-types/pxe-boot.nix

@@ -1,10 +1,10 @@
-{ config, lib, pkgs, inputs, ... }:
+{ config, lib, pkgs, inputs, vars, ... }:
 
 let
   pxeRoot = "/srv/pxe";
   httpRoot = "${pxeRoot}/http";
   tftpRoot = "${pxeRoot}/tftp";
-  pxeBaseUrl = "http://192.168.2.247";
+  pxeBaseUrl = "http://${vars.pxeServerIp}";
 
   bootIpxe = pkgs.writeText "boot.ipxe" ''
     #!ipxe
@@ -21,6 +21,216 @@ let
     chain ${pxeBaseUrl}/boot.ipxe
   '';
 
+  debianRelease = "bookworm";
+  debianMirror = "https://deb.debian.org/debian";
+  debianNetbootBase = "${debianMirror}/dists/${debianRelease}/main/installer-amd64/current/images/netboot/debian-installer/amd64";
+
+  rockyRelease = "9";
+  rockyArch = "x86_64";
+  rockyMirror = "https://dl.rockylinux.org/pub/rocky/${rockyRelease}";
+  rockyPxebootBase = "${rockyMirror}/BaseOS/${rockyArch}/os/images/pxeboot";
+
+  debianIpxe = pkgs.writeText "debian.ipxe" ''
+    #!ipxe
+
+    set base ${pxeBaseUrl}
+
+    kernel ''${base}/debian/linux
+    initrd ''${base}/debian/initrd.gz
+    boot
+  '';
+
+  fetchDebianNetboot = pkgs.writeShellScript "fetch-debian-netboot" ''
+    set -eu
+
+    dir="${httpRoot}/debian"
+    mirror="${debianNetbootBase}"
+
+    if [ -f "$dir/linux" ] && [ -f "$dir/initrd.gz" ]; then
+      echo "Debian ${debianRelease} netboot files already present; skipping download."
+      exit 0
+    fi
+
+    echo "Downloading Debian ${debianRelease} netboot kernel and initrd from $mirror ..."
+    ${pkgs.curl}/bin/curl -fsSL -o "$dir/linux.tmp" "$mirror/linux"
+    ${pkgs.curl}/bin/curl -fsSL -o "$dir/initrd.gz.tmp" "$mirror/initrd.gz"
+    mv "$dir/linux.tmp" "$dir/linux"
+    mv "$dir/initrd.gz.tmp" "$dir/initrd.gz"
+    echo "Debian ${debianRelease} netboot files staged."
+  '';
+
+  # Rocky Linux 9 iPXE script — boots vmlinuz+initrd.img from the staged
+  # /rocky/ directory and hands Anaconda the hosted Kickstart URL.
+  # net.ifnames=0 biosdevname=0 ensures the NIC is eth0 in both the
+  # installer and the installed system (matches the Kickstart NM config).
+  rockyFreeIpaIpxe = pkgs.writeText "rocky-freeipa.ipxe" ''
+    #!ipxe
+
+    set base ${pxeBaseUrl}
+
+    kernel ''${base}/rocky/vmlinuz inst.ks=''${base}/rocky-freeipa.ks inst.repo=${rockyMirror}/BaseOS/${rockyArch}/os/ net.ifnames=0 biosdevname=0 ip=dhcp quiet
+    initrd ''${base}/rocky/initrd.img
+    boot
+  '';
+
+  # Kickstart file for domain-controller.sweet.home.
+  # Installs Rocky Linux 9, sets a static IP, creates wayne with the
+  # admin SSH key, then on first reboot runs ipa-server-install via a
+  # systemd oneshot service.  Passwords are generated at %post time,
+  # written to /root/ipa-credentials.txt (chmod 600), and read back by
+  # the first-boot script — never hardcoded here or in the repo.
+  rockyFreeIpaKs = pkgs.writeText "rocky-freeipa.ks" ''
+    #version=RHEL9
+    # Unattended Rocky Linux 9 + FreeIPA install
+    # Target: domain-controller.${vars.homeDomain}  ${vars.domainControllerIp}
+
+    url --url=${rockyMirror}/BaseOS/${rockyArch}/os/
+    repo --name=appstream --baseurl=${rockyMirror}/AppStream/${rockyArch}/os/
+
+    lang en_US.UTF-8
+    keyboard us
+    timezone UTC --utc
+
+    # DHCP during install; static IP configured in %post via NM config file
+    network --bootproto=dhcp --device=link --activate
+    network --hostname=domain-controller.sweet.home
+
+    selinux --enforcing
+    firewall --enabled --service=ssh
+
+    rootpw --lock
+    user --name=wayne --groups=wheel --shell=/bin/bash
+    sshkey --username=wayne "${vars.adminSshKey}"
+
+    zerombr
+    clearpart --all --initlabel --drives=sda
+    # Keep net.ifnames=0 biosdevname=0 in the installed GRUB so the NIC
+    # stays eth0 after reboot (matches the NM connection file below).
+    bootloader --location=mbr --boot-drive=sda --append="net.ifnames=0 biosdevname=0"
+
+    part /boot --fstype=xfs --size=1024 --ondisk=sda
+    part swap  --fstype=swap --size=2048 --ondisk=sda
+    part /     --fstype=xfs  --grow --size=1 --ondisk=sda --asprimary
+
+    %packages
+    @^minimal-environment
+    ipa-server
+    ipa-server-dns
+    %end
+
+    reboot
+
+    %post --log=/root/ks-post.log
+    set -euo pipefail
+
+    # -- Static IP: write NM connection file directly (NM not running in chroot) --
+    mkdir -p /etc/NetworkManager/system-connections
+    cat > /etc/NetworkManager/system-connections/eth0.nmconnection << 'NMCONN'
+    [connection]
+    id=eth0
+    type=ethernet
+    interface-name=eth0
+    autoconnect=true
+
+    [ethernet]
+
+    [ipv4]
+    method=manual
+    addresses=${vars.domainControllerIp}/${toString vars.lanPrefixLength}
+    gateway=${vars.lanGateway}
+    dns=${vars.domainControllerIp};
+    dns-search=${vars.homeDomain};
+
+    [ipv6]
+    method=auto
+    NMCONN
+    chmod 600 /etc/NetworkManager/system-connections/eth0.nmconnection
+
+    # -- /etc/hosts: FQDN must resolve to the real IP (not loopback) for IPA --
+    sed -i '/domain-controller/d' /etc/hosts
+    echo '${vars.domainControllerIp} domain-controller.${vars.homeDomain} domain-controller' >> /etc/hosts
+
+    # -- Generate IPA passwords and store securely --
+    DM_PASS=$(openssl rand -base64 24 | tr -dc 'A-Za-z0-9' | head -c 24)
+    ADMIN_PASS=$(openssl rand -base64 24 | tr -dc 'A-Za-z0-9' | head -c 24)
+    printf 'Directory Manager: %s\nIPA Admin: %s\n' "$DM_PASS" "$ADMIN_PASS" \
+      > /root/ipa-credentials.txt
+    chmod 600 /root/ipa-credentials.txt
+
+    # -- First-boot script: reads passwords back, runs ipa-server-install --
+    cat > /usr/local/sbin/freeipa-first-boot.sh << 'FIRSTBOOT'
+    #!/bin/bash
+    set -euo pipefail
+    exec >> /root/freeipa-install.log 2>&1
+    echo "=== FreeIPA first-boot install started at $(date) ==="
+
+    DM_PASS=$(grep '^Directory Manager:' /root/ipa-credentials.txt | awk '{print $NF}')
+    ADMIN_PASS=$(grep '^IPA Admin:' /root/ipa-credentials.txt | awk '{print $NF}')
+
+    ipa-server-install \
+      --realm=SWEET.HOME \
+      --domain=sweet.home \
+      --hostname=domain-controller.sweet.home \
+      --ds-password="$DM_PASS" \
+      --admin-password="$ADMIN_PASS" \
+      --setup-dns \
+      --forwarder=192.168.2.253 \
+      --no-dnssec-validation \
+      --no-ntp \
+      --unattended
+
+    echo "=== FreeIPA install complete at $(date) ==="
+    echo "Credentials: /root/ipa-credentials.txt (save to password manager)"
+    echo "CA backup:   /root/cacert.p12 (encrypted with Directory Manager password)"
+    systemctl disable freeipa-first-boot.service
+    FIRSTBOOT
+    chmod 700 /usr/local/sbin/freeipa-first-boot.sh
+
+    # -- Systemd oneshot service: runs freeipa-first-boot.sh on first real boot --
+    cat > /etc/systemd/system/freeipa-first-boot.service << 'UNIT'
+    [Unit]
+    Description=FreeIPA first-boot installation
+    After=network-online.target
+    Wants=network-online.target
+    ConditionPathExists=/root/ipa-credentials.txt
+
+    [Service]
+    Type=oneshot
+    ExecStart=/usr/local/sbin/freeipa-first-boot.sh
+    TimeoutStartSec=1800
+    RemainAfterExit=yes
+
+    [Install]
+    WantedBy=multi-user.target
+    UNIT
+
+    mkdir -p /etc/systemd/system/multi-user.target.wants
+    ln -sf /etc/systemd/system/freeipa-first-boot.service \
+      /etc/systemd/system/multi-user.target.wants/freeipa-first-boot.service
+
+    echo "Kickstart %post complete. FreeIPA installs on first reboot (~20 min)."
+    %end
+  '';
+
+  fetchRockyPxeboot = pkgs.writeShellScript "fetch-rocky-pxeboot" ''
+    set -eu
+
+    dir="${httpRoot}/rocky"
+    base="${rockyPxebootBase}"
+
+    if [ -f "$dir/vmlinuz" ] && [ -f "$dir/initrd.img" ]; then
+      echo "Rocky Linux ${rockyRelease} pxeboot files already present; skipping download."
+      exit 0
+    fi
+
+    echo "Downloading Rocky Linux ${rockyRelease} pxeboot kernel and initrd from $base ..."
+    ${pkgs.curl}/bin/curl -fsSL -o "$dir/vmlinuz.tmp"   "$base/vmlinuz"
+    ${pkgs.curl}/bin/curl -fsSL -o "$dir/initrd.img.tmp" "$base/initrd.img"
+    mv "$dir/vmlinuz.tmp"   "$dir/vmlinuz"
+    mv "$dir/initrd.img.tmp" "$dir/initrd.img"
+    echo "Rocky Linux ${rockyRelease} pxeboot files staged."
+  '';
+
   systemRescueIpxe = pkgs.writeText "systemrescue.ipxe" ''
     #!ipxe
 
@@ -68,17 +278,27 @@ let
     set base ${pxeBaseUrl}
 
     menu PXE Boot Menu
-    item nixos NixOS Installer
+    item auto-installer    NixOS Auto-Installer
-    item rescue Rescue Environment
+    item nixos-minimal     NixOS Minimal
-    item shell iPXE Shell
+    item debian            Debian Minimal
-    item reboot Reboot
+    item rocky-freeipa     FreeIPA Server (Rocky Linux 9)
+    item rescue            Rescue Environment
+    item shell             iPXE Shell
+    item reboot            Reboot
 
     choose target && goto ''${target}
 
-    :nixos
+    :auto-installer
-    kernel ''${base}/nixos/bzImage ip=dhcp
+    chain ''${base}/auto-installer/netboot.ipxe
-    initrd ''${base}/nixos/initrd
+
-    boot
+    :nixos-minimal
+    chain ''${base}/nixos-minimal/netboot.ipxe
+
+    :debian
+    chain ''${base}/debian.ipxe
+
+    :rocky-freeipa
+    chain ''${base}/rocky-freeipa.ipxe
 
     :rescue
     chain ''${base}/systemrescue.ipxe
@@ -91,66 +311,139 @@ let
   '';
 in
 {
+  imports = [
+    ../pxe-boot/stage-installer-artifacts.nix
+    ../pxe-boot/mount-pxe-images.nix
+    ../beszel/enable-agent.nix
+  ];
+
   environment.systemPackages = with pkgs; [
     ipxe
   ];
 
-  services.nginx = {
+  services = {
-    enable = true;
+    nginx = {
+      enable = true;
 
-    virtualHosts."pxe-boot" = {
+      virtualHosts."pxe-boot" = {
-      default = true;
+        default = true;
-      root = httpRoot;
+        root = httpRoot;
-      locations."/" = {
+        locations."/" = {
-        extraConfig = ''
+          extraConfig = ''
-          autoindex on;
+            autoindex on;
-        '';
+          '';
+        };
+      };
+    };
+
+    # TFTP is only used to deliver the initial iPXE bootloader. After iPXE
+    # starts, all further assets are fetched via nginx over HTTP.
+    atftpd = {
+      enable = true;
+      root = tftpRoot;
+      extraOptions = [
+        "--verbose=5"
+      ];
+    };
+
+    openssh.settings.PermitRootLogin = "yes";
+  };
+
+  systemd = {
+    tmpfiles.rules = [
+      "d ${pxeRoot} 0755 root root -"
+      "d ${httpRoot} 0755 root root -"
+      "L+ ${httpRoot}/images - - - - ${vars.nfsShares.pxebootImages.mountpoint}"
+      "d ${httpRoot}/auto-installer 0755 root root -"
+      "d ${httpRoot}/nixos-minimal 0755 root root -"
+      "d ${httpRoot}/systemrescue 0755 root root -"
+      "d ${httpRoot}/debian 0755 root root -"
+      "d ${httpRoot}/ubuntu 0755 root root -"
+      "d ${httpRoot}/rescue 0755 root root -"
+      "d ${httpRoot}/rocky 0755 root root -"
+      "d ${tftpRoot} 0755 root root -"
+      "C+ ${httpRoot}/boot.ipxe 0644 root root - ${bootIpxe}"
+      "C+ ${httpRoot}/menu.ipxe 0644 root root - ${menuIpxe}"
+      "C+ ${httpRoot}/debian.ipxe 0644 root root - ${debianIpxe}"
+      "C+ ${httpRoot}/rocky-freeipa.ipxe 0644 root root - ${rockyFreeIpaIpxe}"
+      "C+ ${httpRoot}/rocky-freeipa.ks 0644 root root - ${rockyFreeIpaKs}"
+      "C+ ${httpRoot}/systemrescue.ipxe 0644 root root - ${systemRescueIpxe}"
+      "C+ ${tftpRoot}/autoexec.ipxe 0644 root root - ${autoexecIpxe}"
+      "C+ ${tftpRoot}/ipxe.efi 0644 root root - ${pkgs.ipxe}/ipxe.efi"
+      "C+ ${tftpRoot}/undionly.kpxe 0644 root root - ${pkgs.ipxe}/undionly.kpxe"
+    ];
+
+    services = {
+      fetch-debian-netboot = {
+        description = "Download Debian ${debianRelease} netboot kernel and initrd for HTTP PXE boot";
+        after = [
+          "local-fs.target"
+          "systemd-tmpfiles-setup.service"
+          "network-online.target"
+        ];
+        wants = [ "network-online.target" ];
+        wantedBy = [ "multi-user.target" ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = fetchDebianNetboot;
+          RemainAfterExit = true;
+        };
+      };
+
+      fetch-rocky-pxeboot = {
+        description = "Download Rocky Linux ${rockyRelease} pxeboot kernel and initrd for HTTP PXE boot";
+        after = [
+          "local-fs.target"
+          "systemd-tmpfiles-setup.service"
+          "network-online.target"
+        ];
+        wants = [ "network-online.target" ];
+        wantedBy = [ "multi-user.target" ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = fetchRockyPxeboot;
+          RemainAfterExit = true;
+        };
+      };
+
+      stage-systemrescue = {
+        description = "Stage SystemRescue ISO contents for HTTP PXE boot";
+        after = [
+          "local-fs.target"
+          "systemd-tmpfiles-setup.service"
+        ];
+        wantedBy = [ "multi-user.target" ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = stageSystemRescue;
+        };
       };
     };
   };
 
-  # TFTP is only used to deliver the initial iPXE bootloader. After iPXE
+  services.dnsmasq = {
-  # starts, all further assets are fetched via nginx over HTTP.
-  services.atftpd = {
     enable = true;
-    root = tftpRoot;
+    settings = {
-    extraOptions = [
+      # Disable DNS listener — only proxy DHCP is needed here.
-      "--verbose=5"
+      # Without this dnsmasq tries to bind port 53 which systemd-resolved
-    ];
+      # already owns, causing startup failure.
-  };
+      port = 0;
-
+      dhcp-range = [ "192.168.2.0,proxy" ];
-  systemd.tmpfiles.rules = [
+      dhcp-match = [
-    "d ${pxeRoot} 0755 root root -"
+        "set:ipxe,175"
-    "d ${httpRoot} 0755 root root -"
+        "set:efi64,option:client-arch,7"
-    "d ${httpRoot}/images 0755 root root -"
+        "set:efi64,option:client-arch,9"
-    "d ${httpRoot}/nixos 0755 root root -"
+      ];
-    "d ${httpRoot}/systemrescue 0755 root root -"
+      dhcp-userclass = "set:ipxe,iPXE";
-    "d ${httpRoot}/ubuntu 0755 root root -"
+      dhcp-boot = [
-    "d ${httpRoot}/rescue 0755 root root -"
+        "tag:ipxe,tag:efi64,http://${vars.pxeServerIp}/boot.ipxe"
-    "d ${tftpRoot} 0755 root root -"
+        "tag:ipxe,http://${vars.pxeServerIp}/boot.ipxe"
-    "C+ ${httpRoot}/boot.ipxe 0644 root root - ${bootIpxe}"
+        "tag:efi64,ipxe.efi,,${vars.pxeServerIp}"
-    "C+ ${httpRoot}/menu.ipxe 0644 root root - ${menuIpxe}"
+        "undionly.kpxe,,${vars.pxeServerIp}"
-    "C+ ${httpRoot}/systemrescue.ipxe 0644 root root - ${systemRescueIpxe}"
+      ];
-    "C+ ${tftpRoot}/autoexec.ipxe 0644 root root - ${autoexecIpxe}"
-    "C+ ${tftpRoot}/ipxe.efi 0644 root root - ${pkgs.ipxe}/ipxe.efi"
-    "C+ ${tftpRoot}/undionly.kpxe 0644 root root - ${pkgs.ipxe}/undionly.kpxe"
-  ];
-
-  systemd.services.stage-systemrescue = {
-    description = "Stage SystemRescue ISO contents for HTTP PXE boot";
-    after = [
-      "local-fs.target"
-      "systemd-tmpfiles-setup.service"
-    ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      Type = "oneshot";
-      ExecStart = stageSystemRescue;
     };
   };
 
-  services.openssh.settings.PermitRootLogin = "yes";
+  networking.firewall.allowedTCPPorts = [ vars.ports.pxeBootHttp ];
-
+  networking.firewall.allowedUDPPorts = [ vars.ports.pxeBootTftp 67 ];
-  networking.firewall.allowedTCPPorts = [ 80 ];
-  networking.firewall.allowedUDPPorts = [ 69 ];
 }

modules/build-types/server.nix

@@ -1,28 +0,0 @@
-{ ... }:
-
-{
-  imports = [
-    ../beszel/enable-agent.nix
-    ../services/zfs/enable-service.nix
-  ];
-
-  boot.zfs.extraPools = [ "tank" ];
-
-  systemd.services.nfs-server = {
-    after = [ "zfs-mount.service" ];
-    requires = [ "zfs-mount.service" ];
-  };
-
-  services.nfs.server = {
-    enable = true;
-    exports = ''
-      /tank/docker/config 192.168.2.0/24(rw,sync,no_subtree_check,no_root_squash)
-      /tank/docker/volumes 192.168.2.0/24(rw,sync,no_subtree_check,no_root_squash)
-      /tank/docker/databases 192.168.2.0/24(rw,sync,no_subtree_check,no_root_squash)
-      /tank/docker/nextcloud-data 192.168.2.0/24(rw,sync,no_subtree_check,no_root_squash)
-      /tank/raspi/volumes 192.168.2.0/24(rw,sync,no_subtree_check,no_root_squash)
-    '';
-  };
-
-  networking.firewall.allowedTCPPorts = [ 111 2049 ];
-}

modules/build-types/tailscale-router.nix

@@ -0,0 +1,44 @@
+{ vars, ... }:
+
+{
+  imports = [
+    ../tailscale/subnet-router.nix
+    ../tailscale/ts-dns-forwarder.nix
+    ../beszel/enable-agent.nix
+  ];
+
+  # "server", not "both": this build type advertises LAN subnet routes but
+  # doesn't use another tailscale exit node itself, so it doesn't need the
+  # "client"-side loose reverse-path filtering that "both" would also enable.
+  # Deliberately kept explicit here (not just relying on subnet-router.nix's
+  # own setting) so the intent is clear at the build-type level.
+  services.tailscale.useRoutingFeatures = "server";
+
+  # Advertise the LAN subnet so Tailscale peers can route back to LAN machines.
+  # Must also be approved in the Tailscale admin console (Machines → Edit route settings).
+  services.tailscale.extraUpFlags = [ "--advertise-routes=${vars.lanCidr}" ];
+
+  networking.firewall = {
+    # Forwarded subnet-router traffic arrives on tailscale0 already
+    # tailscale-authenticated -- the firewall's normal per-port allow-list
+    # would otherwise drop it. Standard NixOS/Tailscale subnet-router guidance.
+    trustedInterfaces = [ "tailscale0" ];
+
+    # SNAT LAN traffic going into Tailscale so the remote peer sees it as
+    # coming from this router's Tailscale IP rather than a raw LAN IP.
+    # Without this, Tailscale drops forwarded packets whose source is not a
+    # recognised Tailscale address.
+    #
+    # We target POSTROUTING directly (always-existing built-in chain) rather
+    # than nixos-nat-post: extraCommands runs after the old nixos-nat-post is
+    # deleted but before the new one is created, so -A nixos-nat-post silently
+    # fails.  The -C check makes the rule idempotent across firewall reloads.
+    extraCommands = ''
+      iptables -t nat -C POSTROUTING -s ${vars.lanCidr} -o tailscale0 -j MASQUERADE 2>/dev/null || \
+        iptables -t nat -A POSTROUTING -s ${vars.lanCidr} -o tailscale0 -j MASQUERADE
+    '';
+    extraStopCommands = ''
+      iptables -t nat -D POSTROUTING -s ${vars.lanCidr} -o tailscale0 -j MASQUERADE 2>/dev/null || true
+    '';
+  };
+}

modules/build-types/tor-relay.nix

@@ -0,0 +1,8 @@
+{ ... }:
+
+{
+  imports = [
+    ../tor/enable-relay.nix
+    ../beszel/enable-agent.nix
+  ];
+}

modules/clan/ssh-host-key.nix

@@ -0,0 +1,30 @@
+{ pkgs, ... }: {
+  # Defines the SSH host key as a clan vars generator so that:
+  #   - `clan vars generate <target>` creates and encrypts the key pair
+  #   - The private key lives at vars/per-machine/<target>/openssh/ssh_host_ed25519_key/secret
+  #     (sops binary-encrypted, admin-key-only; decrypted by the build script)
+  #   - The public key lives at vars/per-machine/<target>/openssh/ssh_host_ed25519_key.pub/value
+  #     (plaintext; used by sync-host-keys.sh to derive the sops age fingerprint)
+  #
+  # neededFor = "activation" means clan's deployment tool would upload this
+  # before running nixos-rebuild/nixos-install (for VM/baremetal via
+  # nixos-anywhere). For lxc-* hosts, the build script bakes it into the
+  # tarball directly via NIXOS_HOST_KEYS_DIR -- the neededFor value here
+  # simply ensures it is NOT mapped to sops.secrets (which would try to
+  # decrypt it at runtime as a regular service secret, which is wrong: the
+  # SSH host key reaches the container via the tarball, not sops).
+  clan.core.vars.generators.openssh = {
+    files."ssh_host_ed25519_key" = {
+      secret = true;
+      neededFor = "activation";
+    };
+    files."ssh_host_ed25519_key.pub" = {
+      secret = false;
+      neededFor = "activation";
+    };
+    runtimeInputs = [ pkgs.openssh ];
+    script = ''
+      ssh-keygen -t ed25519 -N "" -C "" -f "$out/ssh_host_ed25519_key"
+    '';
+  };
+}

modules/common/aliases.nix

@@ -1,29 +1,7 @@
-{ config, pkgs, lib, ... }:
+_:
 
-let
-  # Flake attribute names are now <platform>-<buildtype> (e.g. proxmox-docker)
-  # and no longer match networking.hostName, since a host's hostname stays
-  # fixed while the platform backing it can change. Each nixosConfiguration
-  # stamps its own active target name into /etc/flake-target at build time.
-  mySwitchCmd = ''
-    sudo nixos-rebuild switch \
-      --no-write-lock-file \
-      --refresh \
-      --flake git+https://gitea.lan.ddnsgeek.com/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-  myTestCmd = ''
-    sudo nixos-rebuild test \
-      --no-write-lock-file \
-      --refresh \
-      --flake git+https://gitea.lan.ddnsgeek.com/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-in
 {
-  programs.bash = {
+  # Switch-nix, Test-nix, and buildImage are defined system-wide in
-    enable = true;
+  # modules/common/configuration.nix so all users (including IPA accounts)
-    shellAliases = {
+  # get them. Add any Home-Manager-only per-user shell config here.
-      "Switch-nix" = mySwitchCmd;
-      "Test-nix" = myTestCmd;
-    };
-  };
 }

modules/common/configuration.nix

@@ -1,29 +1,65 @@
-{ config, lib, pkgs, ... }:
+{ config, lib, pkgs, vars, ... }:
 
+let
+  switchCmd = ''
+    sudo nixos-rebuild switch \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
+  '';
+  testCmd = ''
+    sudo nixos-rebuild test \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
+  '';
+  buildImageFn = ''
+    buildImage() {
+      if [ -z "$1" ]; then
+        echo "usage: buildImage <flake-target>  (e.g. lxc-docker)" >&2
+        return 1
+      fi
+      NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
+        ".#nixosConfigurations.$1.config.system.build.tarball"
+    }
+  '';
+in
 {
-    imports =
+  imports = [
-    [ # Include the results of the hardware scan.
+    ./set-locale.nix
-#      ./hardware-configuration.nix
+    ../ipa/client.nix
-      ../set-locale.nix
+  ];
-    ];
-  # Use the GRUB 2 boot loader.
-  # boot.loader.grub.enable = true;
-  #boot.loader.grub.device = "/dev/sda"; # or "nodev" for efi only
 
-  networking.networkmanager.enable = true;  # Easiest to use and most distros use this by default.
+  # System-wide shell config so all users (including IPA accounts) get the
+  # same management aliases as the local nixos user's Home Manager provides.
+  programs.bash = {
+    shellAliases = {
+      "Switch-nix" = switchCmd;
+      "Test-nix" = testCmd;
+    };
+    interactiveShellInit = buildImageFn;
+  };
+  networking.networkmanager.enable = true;
+
+  # Recommended over the true default (bypasses ZFS's own import safeguards)
+  # per the option's own docs; matches hosts/docker/host.nix and
+  # modules/services/zfs/enable-service.nix, which already set this
+  # explicitly. Harmless no-op on hosts that don't use ZFS at all.
+  boot.zfs.forceImportRoot = false;
 
   # Set your time zone.
-  time.timeZone = "Australia/Brisbane";
+  time.timeZone = vars.timeZone;
 
   # Enable QEMU agent
   services.qemuGuest.enable = true;
 
-    # Enable docker-compose
+  # Enable docker-compose
   environment.systemPackages = with pkgs; [
-  vim
+    vim
-  btop
+    btop
-  git
+    git
-  gcr
+    gcr
+    jq
   ];
 
   # Secrets shared by every host, decrypted at activation via each host's
@@ -32,38 +68,53 @@
   # or docs/ for the sops workflow). hashedPassword/hashedPasswordFile need
   # neededForUsers so they're available before the normal secret-activation
   # step, since user creation happens very early in boot.
-  sops.defaultSopsFile = ../../secrets/common.yaml;
+  sops = {
-  sops.secrets."root-hashedPassword".neededForUsers = true;
+    defaultSopsFile = ../../secrets/common.yaml;
-  sops.secrets."nixos-hashedPassword".neededForUsers = true;
+
-  sops.secrets."nix-github-token" = { };
+    secrets = {
+      "root-hashedPassword".neededForUsers = true;
+      "nixos-hashedPassword".neededForUsers = true;
+      "nix-github-token" = { };
+    };
+
+    # nix.conf doesn't support a *File-style option for access-tokens, so the
+    # token is rendered into a runtime-only file (never touches the Nix store)
+    # and pulled in via nix.conf's native !include directive.
+    templates."nix-github-token.conf".content = ''
+      access-tokens = github.com=${config.sops.placeholder."nix-github-token"}
+    '';
+  };
 
-  # nix.conf doesn't support a *File-style option for access-tokens, so the
-  # token is rendered into a runtime-only file (never touches the Nix store)
-  # and pulled in via nix.conf's native !include directive.
-  sops.templates."nix-github-token.conf".content = ''
-    access-tokens = github.com=${config.sops.placeholder."nix-github-token"}
-  '';
   nix.extraOptions = ''
     !include ${config.sops.templates."nix-github-token.conf".path}
   '';
 
-#Set root password
+  users = {
-users.users.root = {
+    # With mutableUsers = false, update-users-groups.pl enforces hashedPasswordFile
-  hashedPasswordFile = config.sops.secrets."root-hashedPassword".path;
+    # on every activation regardless of whether the account already exists in
-};
+    # /etc/shadow. The default (true) only applies hashedPasswordFile to newly-
+    # created accounts — which means a freshly-built proxmox disk image (where
+    # activation runs without a usable sops key, so both accounts land in shadow
+    # with ‘!’) will never have its passwords fixed by subsequent boots.
+    mutableUsers = false;
 
-  # Define a user account. Don't forget to set a password with ‘passwd’.
+    users.root = {
-  users.users.nixos = {
+      hashedPasswordFile = config.sops.secrets."root-hashedPassword".path;
-    isNormalUser = true;
+    };
-    extraGroups = [ "wheel" ]; # Enable ‘sudo’ for the user.
+
-    packages = with pkgs; [
+    users.${vars.primaryUser} = {
-      tree
+      isNormalUser = true;
-    ];
+      extraGroups = [ "wheel" ]; # Enable ‘sudo’ for the user.
-    hashedPasswordFile = config.sops.secrets."nixos-hashedPassword".path;
+      packages = with pkgs; [
-    openssh.authorizedKeys.keys = [
+        tree
-    "ssh-rsa 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 wayne@stream"
+      ];
-    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+      hashedPasswordFile = config.sops.secrets."nixos-hashedPassword".path;
-    ];
+      openssh.authorizedKeys.keys = [
+        vars.adminSshKey
+        "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+        "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGygkCljN6uKpdJbHTOQtn8ZnH+wKXDLAwrDFbLrE/65 nixos@nixos"
+      ];
+    };
   };
 
 

modules/common/home.nix

@@ -1,65 +1,69 @@
-{ config, pkgs, lib, ... }:
+{ config, pkgs, lib, vars, ... }:
 
 let
   remote = "root@proxmox-ip:/var/lib/vz/template/iso";
   localMount = "${config.home.homeDirectory}/proxmox-iso";
-in {
+in
+{
 
   imports = [
     ./aliases.nix
   ];
 
-  home.username = "nixos";         # your actual username
+  home = {
-  home.homeDirectory = "/home/nixos";
+    username = vars.primaryUser;
-  home.stateVersion = "25.11";        # match your NixOS stateVersion
+    homeDirectory = "/home/${vars.primaryUser}";
+    stateVersion = "25.11"; # match your NixOS stateVersion
 
-  programs.home-manager.enable = true;  # mandatory to activate HM
+    # Optional: packages
+    packages = with pkgs; [
+      git
+      vim
+      tmux
+      nano
+      sshfs
+    ];
 
-programs.bash.enable = true;
+    # Optional: set environment vars
+    sessionVariables = {
+      EDITOR = "nano";
+    };
+  };
+
+  programs.home-manager.enable = true; # mandatory to activate HM
+
+  programs.bash.enable = true;
 
   # GitHub access-tokens setting used to live here in plaintext; it's now
   # rendered system-wide from a sops-nix secret via nix.extraOptions in
   # modules/common/configuration.nix instead (covers the daemon for every
   # user, not just this one).
 
-  # Optional: packages
+  #  systemd.user.services.mount-proxmox-iso = {
-  home.packages = with pkgs; [
+  #    Unit = {
-    git
+  #      Description = "Mount Proxmox ISO dir via SSHFS";
-    vim
+  #      After = [ "network-online.target" ];
-    tmux
+  #      Wants = [ "network-online.target" ];
-    nano
+  #    };
-    sshfs
-  ];
 
-  # Optional: set environment vars
+  #    Service = {
-  home.sessionVariables = {
+  #      Type = "simple";
-    EDITOR = "nano";
+  #      ExecStartPre = "${pkgs.coreutils}/bin/mkdir -p ${localMount}";
-  };
+  #      ExecStart = "${pkgs.sshfs}/bin/sshfs -o IdentityFile=${config.home.homeDirectory}/.ssh/id_ed25519,allow_other,reconnect,ServerAliveInterval=15,ServerAliveCountMax=3 root@proxmox-ip:/var/lib/vz/template/iso ${localMount}";
-#  systemd.user.services.mount-proxmox-iso = {
+  #      ExecStop = "${pkgs.fuse3}/bin/fusermount3 -u ${localMount}";
-#    Unit = {
+  #      Restart = "on-failure";
-#      Description = "Mount Proxmox ISO dir via SSHFS";
+  #    };
-#      After = [ "network-online.target" ];
-#      Wants = [ "network-online.target" ];
-#    };
 
-#    Service = {
+  #    Install = {
-#      Type = "simple";
+  #      WantedBy = [ "default.target" ];
-#      ExecStartPre = "${pkgs.coreutils}/bin/mkdir -p ${localMount}";
+  #    };
-#      ExecStart = "${pkgs.sshfs}/bin/sshfs -o IdentityFile=${config.home.homeDirectory}/.ssh/id_ed25519,allow_other,reconnect,ServerAliveInterval=15,ServerAliveCountMax=3 root@proxmox-ip:/var/lib/vz/template/iso ${localMount}";
+  #  };
-#      ExecStop = "${pkgs.fuse3}/bin/fusermount3 -u ${localMount}";
-#      Restart = "on-failure";
-#    };
-
-#    Install = {
-#      WantedBy = [ "default.target" ];
-#    };
-#  };
   # Optional: enable bash (or zsh, fish...)
-#  programs.bash.enable = true;
+  #  programs.bash.enable = true;
 
   # Optional: manage dotfiles via symlinks
-#  home.file = {
+  #  home.file = {
-#    ".tmux.conf".source = ./dotfiles/tmux.conf;
+  #    ".tmux.conf".source = ./dotfiles/tmux.conf;
-#    ".config/nvim/init.vim".source = ./dotfiles/init.vim;
+  #    ".config/nvim/init.vim".source = ./dotfiles/init.vim;
-#  };
+  #  };
 }

modules/common/preserve-ssh-host-key.nix

@@ -0,0 +1,35 @@
+# Shared activation-script logic to preserve the SSH host key across
+# nixos-rebuild on platforms that embed the key via environment.etc (lxc and
+# proxmox).  When NIXOS_HOST_KEYS_DIR is not set the key is absent from
+# environment.etc, and NixOS's etc activation removes any /etc file not in
+# the new generation — which would destroy the live key and break sops-nix
+# decryption permanently.  These scripts save the key to /run before etc
+# removes it, then restore it afterward.
+#
+# Explicit deps enforce the correct ordering: without them the topological
+# sort places preserveSshHostKey after etc (confirmed live on lxc-tor-relay:
+# position 7 vs etc's position 5), so the key is gone before it can be saved.
+_: {
+  system.activationScripts = {
+    preserveSshHostKey = ''
+      if [ -f /etc/ssh/ssh_host_ed25519_key ]; then
+        cp /etc/ssh/ssh_host_ed25519_key /run/sshd-host-key-preserve.tmp
+        cp /etc/ssh/ssh_host_ed25519_key.pub /run/sshd-host-key-preserve.pub.tmp
+      fi
+    '';
+
+    restoreSshHostKey = {
+      deps = [ "etc" ];
+      text = ''
+        if [ ! -f /etc/ssh/ssh_host_ed25519_key ] && [ -f /run/sshd-host-key-preserve.tmp ]; then
+          install -m 0600 /run/sshd-host-key-preserve.tmp /etc/ssh/ssh_host_ed25519_key
+          install -m 0644 /run/sshd-host-key-preserve.pub.tmp /etc/ssh/ssh_host_ed25519_key.pub
+        fi
+        rm -f /run/sshd-host-key-preserve.tmp /run/sshd-host-key-preserve.pub.tmp
+      '';
+    };
+
+    etc = { deps = [ "preserveSshHostKey" ]; };
+    setupSecrets = { deps = [ "restoreSshHostKey" ]; };
+  };
+}

modules/common/set-locale.nix

@@ -1,4 +1,4 @@
-{ ... }:
+_:
 
 {
   i18n.defaultLocale = "en_AU.UTF-8";

modules/disko/baremetal.nix

@@ -0,0 +1,87 @@
+{ vars, ... }:
+
+{
+  # ZFS RAID0 (striped, no redundancy) root pool for the bare-metal gui
+  # host — two disks, each contributing its own top-level vdev. disko's
+  # zpool `mode` defaults to "" (plain stripe) when left unset, which is
+  # what gives RAID0 semantics here rather than mirror/raidz.
+  #
+  # Device paths are placeholders until the real hardware profile lands —
+  # fill in vars.guiRootDisk1/guiRootDisk2 (stable /dev/disk/by-id/...
+  # paths, not /dev/sdX) before running disko against real hardware. Swap
+  # is deliberately left out for now — sizing that sensibly needs the
+  # box's actual RAM size, which comes with the hardware profile too.
+  #
+  # Not yet imported anywhere: this awaits the new bare-metal platform
+  # module (alongside modules/boot/efi.nix for systemd-boot, matching
+  # modules/platforms/proxmox.nix's pattern) once the hardware config is
+  # in hand.
+  disko.devices = {
+    disk = {
+      disk1 = {
+        type = "disk";
+        device = vars.guiRootDisk1;
+
+        content = {
+          type = "gpt";
+
+          partitions = {
+            esp = {
+              priority = 1;
+              name = "ESP";
+              size = "512M";
+              type = "EF00";
+
+              content = {
+                type = "filesystem";
+                format = "vfat";
+                mountpoint = "/boot";
+                mountOptions = [ "umask=0077" ];
+              };
+            };
+
+            zfs = {
+              size = "100%";
+
+              content = {
+                type = "zfs";
+                pool = "rpool";
+              };
+            };
+          };
+        };
+      };
+
+      disk2 = {
+        type = "disk";
+        device = vars.guiRootDisk2;
+
+        content = {
+          type = "gpt";
+
+          partitions = {
+            zfs = {
+              size = "100%";
+
+              content = {
+                type = "zfs";
+                pool = "rpool";
+              };
+            };
+          };
+        };
+      };
+    };
+
+    zpool.rpool = {
+      type = "zpool";
+
+      rootFsOptions = {
+        compression = "zstd";
+        "com.sun:auto-snapshot" = "false";
+      };
+      mountpoint = "/";
+      options.ashift = "12";
+    };
+  };
+}

modules/disko/linode.nix

@@ -0,0 +1,35 @@
+_:
+
+{
+  # Linode provisions and sizes these disks itself (via the Linode
+  # dashboard/API) before the OS ever boots, and presents them as whole,
+  # unpartitioned block devices — /dev/sda is the root filesystem directly,
+  # /dev/sdb is swap directly, no partition table on either. Nothing here
+  # should ever repartition or resize them:
+  #   - `destroy = false` skips each disk entirely during disko's destroy
+  #     stage (see disko's disk.destroy option) — no wipefs, ever.
+  #   - the filesystem content type's own create step only runs mkfs if the
+  #     device isn't already formatted (checked via `blkid`), so re-running
+  #     this against an already-provisioned Linode disk is a no-op.
+  disko.devices.disk = {
+    main = {
+      device = "/dev/sda";
+      destroy = false;
+
+      content = {
+        type = "filesystem";
+        format = "ext4";
+        mountpoint = "/";
+      };
+    };
+
+    swap = {
+      device = "/dev/sdb";
+      destroy = false;
+
+      content = {
+        type = "swap";
+      };
+    };
+  };
+}

modules/disko/proxmox.nix

@@ -1,4 +1,4 @@
-{ ... }:
+{ config, vars, ... }:
 
 {
   disko.devices = {
@@ -6,6 +6,16 @@
       type = "disk";
       device = "/dev/sda";
 
+      # Only used when building a standalone disk image directly (`nix build
+      # .#nixosConfigurations.<host>.config.system.build.diskoImagesScript`)
+      # rather than formatting a real device — see docs/proxmox-images.md.
+      # imageSize sets the .raw file's total size (root's "100%" below fills
+      # whatever's left after ESP + swap within it); imageName keeps each
+      # host's image distinctly named instead of every proxmox-* host
+      # producing an identical "main.raw".
+      imageSize = vars.proxmoxImageSize;
+      imageName = config.networking.hostName;
+
       content = {
         type = "gpt";
 

modules/docker/docker-health-to-gotify.nix

@@ -1,4 +1,4 @@
-{ pkgs, ... }:
+{ pkgs, vars, ... }:
 
 {
   systemd.services.docker-health-to-gotify = {
@@ -7,9 +7,9 @@
     serviceConfig = {
       Type = "oneshot";
       # Run as root so it can read /etc/secrets and access docker socket
-     # User = "root";
+      # User = "root";
       #EnvironmentFile = "-/etc/secrets/docker-health-alert.env";
-      ExecStart = "${pkgs.bash}/bin/bash /home/nixos/docker/monitoring/gotify/docker-health-to-gotify.sh";
+      ExecStart = "${pkgs.bash}/bin/bash /home/${vars.primaryUser}/docker/monitoring/gotify/docker-health-to-gotify.sh";
       StandardOutput = "journal";
       StandardError = "journal";
     };

modules/docker/enable-service.nix

@@ -1,23 +1,45 @@
-{ pkgs, ... }:
+{ lib, pkgs, vars, ... }:
 
+let
+  gid = toString vars.dockerAccessGid;
+in
 {
-    #  virtualisation.docker.enable = true;
   virtualisation.docker = {
-  enable = true;
+    enable = true;
-  package = pkgs.docker;
+    package = pkgs.docker;
-#  listenOptions = [
+  };
-#  "unix:///var/run/docker.sock"
+  # Pin the docker group GID to match the IPA "docker-access" group so that
-#  "tcp://0.0.0.0:2375"
+  # IPA group membership alone grants access to the Docker socket. Any user
-#];
+  # whose supplementary groups (resolved by SSSD from IPA) include GID
+  # vars.dockerAccessGid will pass the socket group-permission check without
+  # any per-host users.groups.docker.members entry.
+  users.groups.docker.gid = lib.mkForce vars.dockerAccessGid;
+  users.users.${vars.primaryUser}.extraGroups = [ "docker" ];
+  environment.systemPackages = with pkgs; [
+    docker-compose
+    docker-buildx
+  ];
 
-#  daemon.settings = {
+  # NixOS's group activation uses plain `groupmod` without --non-unique.
-#    metrics-addr = "0.0.0.0:9323";
+  # When SSSD is active it exposes the IPA "docker-access" group at
-#    experimental = true;
+  # vars.dockerAccessGid via NSS, so groupmod sees that GID as already in
-#  };
+  # use and silently skips the change (warning: "not applying GID change").
-};
+  # This script runs after the normal "groups" step and applies the change
-
+  # with --non-unique (which lets the local docker group share the GID with
-environment.systemPackages = with pkgs; [
+  # the SSSD-provided IPA group). If the GID actually changed it also
-  docker-compose
+  # restarts docker.socket so the socket is recreated with the new GID.
-  docker-buildx
+  system.activationScripts.docker-group-gid = {
-];
+    deps = [ "groups" ];
+    text = ''
+      current=$(grep "^docker:" /etc/group | cut -d: -f3)
+      if [ "$current" != "${gid}" ]; then
+        ${pkgs.shadow}/bin/groupmod --non-unique -g ${gid} docker
+        if ${pkgs.systemd}/bin/systemctl is-active --quiet docker.socket; then
+          ${pkgs.systemd}/bin/systemctl stop docker.service docker.socket
+          rm -f /var/run/docker.sock
+          ${pkgs.systemd}/bin/systemctl start docker.socket docker.service
+        fi
+      fi
+    '';
+  };
 }

modules/docker/mount-data.nix

@@ -1,63 +1,79 @@
-{ config, lib, pkgs, ... }:
+{ config, lib, pkgs, vars, ... }:
 
+let
+  # `x-systemd.automount` never works inside a Linux container (LXC
+  # included, regardless of privilege) -- confirmed live on lxc-docker:
+  # systemd logs "Starting of <unit>.automount unsupported" for every
+  # share and never mounts them. Mount eagerly there instead, with
+  # `nofail` so a boot with the NFS server unreachable doesn't hang
+  # (the VM platforms rely on automount itself to get that same
+  # non-blocking behavior, so they don't need `nofail` too).
+  automountOpts = if config.boot.isContainer then [ "nofail" ] else [ "x-systemd.automount" ];
+
+  # FQDN in the storage.home zone — resolves to the Pacemaker vip-storage
+  # (192.168.20.229) on docker's eth1/vmbr2 interface. Using the DNS name
+  # rather than the raw IP means a future VIP renumber only requires a DNS
+  # update, not a NixOS rebuild. The storage.home zone is served by the same
+  # FreeIPA nameserver (domainControllerIp) that docker already uses, so
+  # resolution reaches it over eth0 without any extra routing.
+  nfsServer = vars.haStorageNfsFqdn;
+  storageRoot = vars.haStorageRoot;
+in
 {
-  fileSystems."/mnt/docker/config" = {
+  fileSystems = {
-    device = "server:/tank/docker/config";
+    ${vars.nfsShares.dockerConfig.mountpoint} = {
-    fsType = "nfs";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerConfig.subpath}";
+      fsType = "nfs";
 
-    options = [
+      options = [
-      "nfsvers=4.2"
+        "nfsvers=4.2"
-      "_netdev"
+        "_netdev"
-      "x-systemd.automount"
+        "noatime"
-      "noatime"
+      ] ++ automountOpts;
-    ];
+    };
-  };
 
-  fileSystems."/mnt/docker/databases" = {
+    ${vars.nfsShares.dockerDatabases.mountpoint} = {
-    device = "server:/tank/docker/databases";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerDatabases.subpath}";
-    fsType = "nfs";
+      fsType = "nfs";
 
-    options = [
+      options = [
-      "nfsvers=4.2"
+        "nfsvers=4.2"
-      "_netdev"
+        "_netdev"
-      "x-systemd.automount"
+        "noatime"
-      "noatime"
+      ] ++ automountOpts;
-    ];
+    };
-  };
 
-  fileSystems."/mnt/docker/volumes" = {
+    ${vars.nfsShares.dockerVolumes.mountpoint} = {
-    device = "server:/tank/docker/volumes";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
-    fsType = "nfs";
+      fsType = "nfs";
 
-    options = [
+      options = [
-      "nfsvers=4.2"
+        "nfsvers=4.2"
-      "_netdev"
+        "_netdev"
-      "x-systemd.automount"
+        "noatime"
-      "noatime"
+      ] ++ automountOpts;
-    ];
+    };
-  };
 
- fileSystems."/mnt/nextcloud-data" = {
+    ${vars.nfsShares.nextcloudData.mountpoint} = {
-    device = "server:/tank/docker/nextcloud-data";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.nextcloudData.subpath}";
-    fsType = "nfs";
+      fsType = "nfs";
 
-    options = [
+      options = [
-      "nfsvers=4.2"
+        "nfsvers=4.2"
-      "_netdev"
+        "_netdev"
-      "x-systemd.automount"
+        "noatime"
-      "noatime"
+      ] ++ automountOpts;
-    ];
+    };
-  };
 
- fileSystems."/mnt/raspi-backup" = {
+    ${vars.nfsShares.raspiVolumes.mountpoint} = {
-    device = "server:/tank/raspi/volumes";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.raspiVolumes.subpath}";
-    fsType = "nfs";
+      fsType = "nfs";
 
-    options = [
+      options = [
-      "nfsvers=4.2"
+        "nfsvers=4.2"
-      "_netdev"
+        "_netdev"
-      "x-systemd.automount"
+        "noatime"
-      "noatime"
+      ] ++ automountOpts;
-    ];
+    };
   };
 }

modules/docker/nextcloud-cron-job.nix

@@ -0,0 +1,22 @@
+{ pkgs, vars, ... }:
+
+{
+  # Create nextcloud cron scheduled task
+  systemd.services.nextcloud = {
+    description = "Nextcloud scheduled task";
+    script = ''${pkgs.bash}/bin/bash ~/docker/services-up.sh --profile nextcloud exec -u 33 nextcloud-webapp php ./cron.php'';
+    serviceConfig = {
+      Type = "oneshot";
+      User = vars.primaryUser;
+    };
+    path = with pkgs; [ docker docker-compose ];
+  };
+
+  systemd.timers.nextcloud = {
+    wantedBy = [ "timers.target" ];
+    timerConfig = {
+      OnCalendar = "*:0/5";
+      Persistent = true;
+    };
+  };
+}

modules/ha/cluster-config.nix

@@ -0,0 +1,168 @@
+# Cluster-wide HA config shared by both ha-server nodes.
+#
+# Covers everything that is identical on both nodes and references cluster
+# topology (node IPs, hostnames, DRBD resource).  Per-node identity
+# (hostname, static IP, stateVersion) lives in hosts/ha-server-{1,2}/host.nix.
+#
+# Corosync authkey:
+#   /etc/corosync/authkey (mode 0400) is managed by sops-nix below.
+#   Bootstrap: run scripts/ha/cluster-init.sh on node1 to generate the key,
+#   then encrypt it with: sops -e --input-type binary /etc/corosync/authkey > secrets/ha-corosync-authkey
+#   Both host keys must be registered via sync-host-keys.sh first so both nodes can decrypt it.
+#
+# DRBD fencing:
+#   resource-only with crm-fence-peer.sh: DRBD calls the Pacemaker-aware
+#   crm-fence-peer.sh handler before promoting.  The handler checks the CIB
+#   to confirm the peer's DRBD resource is stopped and returns 7 (successfully
+#   fenced), allowing safe promotion without requiring power-fencing (STONITH).
+#   The unfence handler crm-unfence-peer.sh clears the outdate flag when the
+#   peer reconnects.  This is the correct setting for Pacemaker+DRBD clusters
+#   with STONITH disabled; crm-fence-peer.sh replaces the need for a separate
+#   STONITH device during the testing phase.  Switch to resource-and-stonith
+#   once the fence_pve_ssh STONITH resource is active (see
+#   scripts/ha/cluster-enable-stonith.sh).
+#
+#   PATH wrapper: when the DRBD kernel module invokes the fence-peer handler
+#   via the UMH (User Mode Helper) mechanism it provides a minimal PATH that
+#   omits /run/current-system/sw/bin.  crm-fence-peer.sh calls cibadmin,
+#   crm_mon etc.; if those aren't found a pipeline in the script breaks with
+#   SIGPIPE.  A process killed by signal has WEXITSTATUS() == 0, so the kernel
+#   sees exit code 0 and logs "fence-peer helper broken, returned 0", looping
+#   forever.  The writeShellScript wrappers below prepend the NixOS sw path
+#   before exec-ing the real handler, giving it a working Pacemaker toolchain.
+{ lib, pkgs, vars, ... }:
+let
+  fencePeerWrapper = pkgs.writeShellScript "drbd-fence-peer" ''
+    export PATH="/run/current-system/sw/bin:/run/current-system/sw/sbin:$PATH"
+    exec /run/current-system/sw/lib/drbd/crm-fence-peer.sh "$@"
+  '';
+  unfencePeerWrapper = pkgs.writeShellScript "drbd-unfence-peer" ''
+    export PATH="/run/current-system/sw/bin:/run/current-system/sw/sbin:$PATH"
+    exec /run/current-system/sw/lib/drbd/crm-unfence-peer.sh "$@"
+  '';
+in
+{
+  # Root SSH access — same key set as nixos user so all admin keys can reach root.
+  users.users.root.openssh.authorizedKeys.keys = [
+    vars.adminSshKey
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGygkCljN6uKpdJbHTOQtn8ZnH+wKXDLAwrDFbLrE/65 nixos@nixos"
+  ];
+
+  # Passwordless sudo for wheel — operator SSHes as nixos and uses sudo for
+  # cluster management commands (drbdadm, crm*, pcs, etc.)
+  security.sudo.wheelNeedsPassword = lib.mkForce false;
+
+  # DRBD lock-file directory (drbd-utils checks for it; missing → harmless but noisy warnings).
+  systemd.tmpfiles.rules = [ "d /var/lib/drbd 0750 root root -" ];
+
+  # Prevent drbd.service from auto-starting at boot / nixos-rebuild switch.
+  # Pacemaker's OCF drbd agent calls drbdadm up/down directly when managing
+  # the resource.  If drbd.service also runs drbdadm up all while DRBD is
+  # already Primary under Pacemaker, apply-al fails with "device busy" (exit 20).
+  systemd.services.drbd.wantedBy = lib.mkForce [ ];
+
+  services.drbd = {
+    enable = true;
+    config = ''
+      global {
+        usage-count yes;
+      }
+
+      common {
+        net {
+          protocol C;
+          ping-int 1;
+          verify-alg sha256;
+          after-sb-0pri discard-zero-changes;
+          after-sb-1pri discard-secondary;
+        }
+        disk {
+          fencing resource-only;
+        }
+        handlers {
+          fence-peer   "${fencePeerWrapper}";
+          unfence-peer "${unfencePeerWrapper}";
+        }
+      }
+
+      resource ha-data {
+        volume 0 {
+          device    /dev/drbd0;
+          disk      ${vars.haServerDrbdDisk};
+          meta-disk internal;
+        }
+
+        on ${vars.haServer1Host} {
+          address ${vars.haServer1StorageIp}:${toString vars.ports.haServerDrbd};
+        }
+
+        on ${vars.haServer2Host} {
+          address ${vars.haServer2StorageIp}:${toString vars.ports.haServerDrbd};
+        }
+      }
+    '';
+  };
+
+  # /etc/corosync/authkey — sops binary secret, identical on both nodes.
+  # Decryptable by both ha-server host keys (added by sync-host-keys.sh).
+  sops.secrets.corosync_authkey = {
+    sopsFile = ../../secrets/ha-corosync-authkey;
+    format = "binary";
+    path = "/etc/corosync/authkey";
+    mode = "0400";
+    restartUnits = [ "corosync.service" ];
+  };
+
+  # NixOS common config enables NetworkManager by default; HA cluster nodes
+  # need stable static IPs with predictable interface names — NM is not suitable.
+  networking.networkmanager.enable = lib.mkForce false;
+
+  # services.corosync.enable is set by modules/ha/pacemaker-stack.nix.
+  services.corosync = {
+    clusterName = "ha-cluster";
+    nodelist = [
+      # ring0: cluster-internal vmbr1 (primary heartbeat + DRBD path)
+      # ring1: LAN vmbr0 (backup heartbeat only — never carries DRBD)
+      { nodeid = 1; name = vars.haServer1Host; ring_addrs = [ vars.haServer1StorageIp vars.haServer1Ip ]; }
+      { nodeid = 2; name = vars.haServer2Host; ring_addrs = [ vars.haServer2StorageIp vars.haServer2Ip ]; }
+    ];
+  };
+
+  networking.firewall = {
+    allowedTCPPorts = [
+      vars.ports.haServerPacemakerRemoted
+      vars.ports.haServerPcsd
+      vars.ports.haServerDrbd
+    ];
+    allowedUDPPorts = [
+      vars.ports.haServerCorosync1
+      vars.ports.haServerCorosync2
+      vars.ports.haServerCorosyncCrypto
+    ];
+    # Protocol separation: iSCSI (VLAN 20 / storage clients only),
+    # NFS (VLAN 2 / LAN only).  Cluster-internal subnets accepted wholesale
+    # since they are isolated bridges with no external uplink.
+    extraCommands = ''
+      iptables -A nixos-fw -s ${vars.haServer1Ip}/32 -j nixos-fw-accept
+      iptables -A nixos-fw -s ${vars.haServer2Ip}/32 -j nixos-fw-accept
+      iptables -A nixos-fw -s ${vars.haStorageCidr} -j nixos-fw-accept
+
+      iptables -A nixos-fw -p tcp -s ${vars.haClientCidr} --dport ${toString vars.ports.haServerIscsi} -j nixos-fw-accept
+
+      iptables -A nixos-fw -p tcp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsRpcbind} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsRpcbind} -j nixos-fw-accept
+      iptables -A nixos-fw -p tcp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsd} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsd} -j nixos-fw-accept
+      iptables -A nixos-fw -p tcp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsMountd} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.lanCidr} --dport ${toString vars.ports.nfsMountd} -j nixos-fw-accept
+
+      iptables -A nixos-fw -p tcp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsRpcbind} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsRpcbind} -j nixos-fw-accept
+      iptables -A nixos-fw -p tcp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsd} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsd} -j nixos-fw-accept
+      iptables -A nixos-fw -p tcp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsMountd} -j nixos-fw-accept
+      iptables -A nixos-fw -p udp -s ${vars.haClientCidr} --dport ${toString vars.ports.nfsMountd} -j nixos-fw-accept
+    '';
+  };
+}

modules/ha/iscsi-target.nix

@@ -0,0 +1,99 @@
+# LIO iSCSI target service (targetctl) for NixOS HA clusters.
+#
+# Provides the targetctl.service that saves/restores LIO configuration from
+# /etc/target/saveconfig.json.  Pacemaker manages this service via its
+# systemd resource agent (class="systemd" type="targetctl").
+#
+# Why ExecStop is not simply "targetctl save":
+#   targetctl save writes the LIO config to JSON but does NOT remove the LIO
+#   target from the kernel's configfs.  As a result, any fileio backing store
+#   that LIO has open (e.g. iscsi-lun.img on an XFS-over-DRBD filesystem)
+#   stays referenced in the kernel.  The subsequent XFS umount from the
+#   Filesystem OCF resource then returns EBUSY and either hangs for the full
+#   op-stop timeout or fails outright, blocking the entire failover.
+#
+#   The ExecStop script here additionally tears down the kernel LIO state
+#   via rtslib_fb after saving, so the backing-store file descriptor is
+#   released and umount succeeds immediately.
+#
+# Empty-config guard:
+#   The save step is skipped when no iSCSI targets are currently active.
+#   This prevents the secondary node (where LIO was never started) from
+#   overwriting a valid saveconfig.json with an empty one when Pacemaker
+#   stops the iscsi-target resource as part of a failover or cleanup.
+{ pkgs, ... }:
+
+let
+  python3 = pkgs.python3.withPackages (ps: [ ps.rtslib-fb ]);
+  targetctl = "${python3}/bin/targetctl";
+
+  targetctlStop = pkgs.writeScript "targetctl-stop" ''
+    #!${python3}/bin/python3
+    import subprocess, sys
+    import rtslib_fb
+
+    root = rtslib_fb.RTSRoot()
+    targets = list(root.targets)
+    if targets:
+        subprocess.run(
+            ["${targetctl}", "save", "/etc/target/saveconfig.json"],
+            capture_output=True,
+        )
+        print(f"saved {len(targets)} iSCSI target(s)")
+    else:
+        print("no active LIO targets — saveconfig.json unchanged")
+
+    for target in targets:
+        try:
+            for tpg in list(target.tpgs):
+                tpg.enable = False
+            target.delete()
+        except Exception as e:
+            print(f"warn (target): {e}", file=sys.stderr)
+    for so in list(root.storage_objects):
+        try:
+            so.delete()
+        except Exception as e:
+            print(f"warn (backstore): {e}", file=sys.stderr)
+    print("LIO kernel target cleared")
+  '';
+in
+{
+  boot.kernelModules = [
+    "target_core_mod"
+    "iscsi_target_mod"
+    "target_core_file"
+    "target_core_pscsi"
+    "target_core_user"
+    "configfs"
+  ];
+
+  systemd = {
+    mounts = [{
+      where = "/sys/kernel/config";
+      what = "configfs";
+      type = "configfs";
+      wantedBy = [ "multi-user.target" ];
+      before = [ "targetctl.service" ];
+    }];
+    services.targetctl = {
+      description = "LIO iSCSI target config save/restore";
+      wantedBy = [ "multi-user.target" ];
+      after = [ "sys-kernel-config.mount" "network.target" ];
+      requires = [ "sys-kernel-config.mount" ];
+      serviceConfig = {
+        Type = "oneshot";
+        RemainAfterExit = true;
+        ExecStart = "${targetctl} restore /etc/target/saveconfig.json";
+        ExecStop = "${targetctlStop}";
+      };
+      unitConfig.ConditionFileNotEmpty = "/etc/target/saveconfig.json";
+    };
+    tmpfiles.rules = [
+      "d /etc/target 0750 root root -"
+      "f /etc/target/saveconfig.json 0640 root root -"
+    ];
+  };
+
+  environment.systemPackages = [ pkgs.targetcli-fb ];
+}

modules/ha/pacemaker-stack.nix

@@ -0,0 +1,94 @@
+# Pacemaker + Corosync HA stack for NixOS with known-good workarounds.
+#
+# Issues fixed here (confirmed through live testing on NixOS 25.11):
+#
+# 1. StateDirectory ownership reset: systemd's StateDirectory=pacemaker
+#    creates /var/lib/pacemaker owned root:root.  pacemaker-based (the CIB
+#    daemon) runs as the hacluster user and calls pcmk__daemon_can_write,
+#    which requires the CIB directory to be owned by hacluster or be
+#    group-writable by haclient.  Workaround: remove StateDirectory and let
+#    ExecStartPre create every required subdirectory with correct ownership.
+#
+# 2. HA_SBIN_DIR wrong path: ocf-shellfuncs sets HA_SBIN_DIR to the Nix
+#    store path of the resource-agents derivation's /sbin, which doesn't
+#    exist.  The DRBD OCF agent uses ${HA_SBIN_DIR}/crm_master, so it exits
+#    127 without this override.  Fix: export HA_SBIN_DIR=/run/current-system/sw/bin.
+#
+# 3. Broad PATH for OCF agents: the resource executor (pacemaker-execd) runs
+#    OCF agent scripts as children.  NixOS provides no implicit PATH for
+#    system services; without an explicit PATH the agents can't find ip, ss,
+#    mount, umount, drbdadm, etc.
+#
+# 4. FUSER=true: the Filesystem OCF agent calls check_binary $FUSER (default:
+#    fuser from psmisc), which is not installed.  Setting FUSER=true makes
+#    check_binary succeed (true is always in PATH) and the subsequent
+#    "$FUSER -km $mountpoint" becomes a no-op.  Pair with force_unmount=false
+#    on each Filesystem resource unless you want lazy unmount behaviour.
+{ lib, pkgs, ... }:
+
+let
+  ocfBinPath = lib.concatStringsSep ":" [
+    "${pkgs.iproute2}/bin"
+    "${pkgs.iproute2}/sbin"
+    "${pkgs.iputils}/bin"
+    "${pkgs.util-linux}/bin"
+    "${pkgs.util-linux}/sbin"
+    "${pkgs.gawk}/bin"
+    "${pkgs.gnugrep}/bin"
+    "${pkgs.gnused}/bin"
+    "${pkgs.coreutils}/bin"
+    "${pkgs.bash}/bin"
+    "${pkgs.procps}/bin"
+    "${pkgs.xfsprogs}/bin"
+    "${pkgs.drbd}/bin"
+    "${pkgs.python3}/bin"
+    "/run/current-system/sw/bin"
+    "/run/current-system/sw/sbin"
+    "/usr/local/sbin"
+    "/usr/local/bin"
+    "/usr/sbin"
+    "/usr/bin"
+    "/sbin"
+    "/bin"
+  ];
+
+  # Single pre-start script: schemas symlink + directory ownership.
+  # Runs before pacemakerd so pacemaker-based finds hacluster-owned dirs.
+  preStartCmd = "${pkgs.bash}/bin/bash -c '"
+    + "ln -sfn ${pkgs.pacemaker}/share/pacemaker /var/lib/pacemaker/schemas; "
+    + "for d in /var/lib/pacemaker /var/lib/pacemaker/cib /var/lib/pacemaker/cores "
+    + "/var/lib/pacemaker/pengine /var/lib/pacemaker/blackbox "
+    + "/var/lib/pacemaker/hostcache; do "
+    + "mkdir -p \"\\$d\" && chown hacluster:pacemaker \"\\$d\" && chmod 2770 \"\\$d\"; "
+    + "done'";
+
+  ocfEnv = {
+    PATH = lib.mkForce ocfBinPath;
+    OCF_ROOT = "${pkgs.ocf-resource-agents}/usr/lib/ocf";
+    HA_SBIN_DIR = "/run/current-system/sw/bin";
+    FUSER = "true";
+  };
+in
+{
+  users.groups.haclient = { };
+
+  services.corosync.enable = true;
+  services.pacemaker.enable = true;
+
+  systemd.services = {
+    pacemaker = {
+      serviceConfig = {
+        StateDirectory = lib.mkForce "";
+        ExecStartPre = lib.mkBefore [ preStartCmd ];
+      };
+      environment = ocfEnv;
+    };
+    pacemaker-execd.environment = ocfEnv;
+  };
+
+  environment.systemPackages = with pkgs; [
+    corosync
+    pacemaker
+    ocf-resource-agents
+  ];
+}

modules/hardware-configuration/baremetal.nix

@@ -0,0 +1,23 @@
+# Adapted from the output of `nixos-generate-config`, run from a live GUI
+# ISO boot on the actual gui-host hardware (AMD CPU). fileSystems and
+# swapDevices are deliberately omitted -- the live ISO had no formatted
+# disks to detect, and disko (modules/disko/baremetal.nix) generates both
+# from the declarative zpool layout anyway.
+{ config, lib, pkgs, modulesPath, ... }:
+
+{
+  imports =
+    [
+      (modulesPath + "/installer/scan/not-detected.nix")
+    ];
+
+  boot = {
+    initrd.availableKernelModules = [ "xhci_pci" "ahci" "usbhid" "usb_storage" "sd_mod" ];
+    initrd.kernelModules = [ ];
+    kernelModules = [ "kvm-amd" ];
+    extraModulePackages = [ ];
+  };
+
+  nixpkgs.hostPlatform = lib.mkDefault "x86_64-linux";
+  hardware.cpu.amd.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
+}

modules/hardware-configuration/vm/linode.nix

@@ -5,36 +5,39 @@
 
 {
   imports =
-    [ (modulesPath + "/profiles/qemu-guest.nix")
+    [
+      (modulesPath + "/profiles/qemu-guest.nix")
     ];
 
-  boot.initrd.availableKernelModules = [ "virtio_pci" "virtio_scsi" "ahci" "sd_mod" ];
+  boot = {
-  boot.initrd.kernelModules = [ ];
+    initrd.availableKernelModules = [ "virtio_pci" "virtio_scsi" "ahci" "sd_mod" ];
-  boot.kernelModules = [ ];
+    initrd.kernelModules = [ ];
-  boot.extraModulePackages = [ ];
+    kernelModules = [ ];
-  boot.loader.grub.device = "/dev/sda";
+    extraModulePackages = [ ];
 
-  fileSystems."/" =
+    # Enable LISH
-    { device = "/dev/sda";
+    kernelParams = [ "console=ttyS0,19200n8" ];
-      fsType = "ext4";
+
+    loader = {
+      grub = {
+        device = "/dev/sda";
+        extraConfig = ''
+          serial --speed=19200 --unit=0 --word=8 --parity=no --stop=1;
+          terminal_input serial;
+          terminal_output serial;
+        '';
+        forceInstall = true;
+        # device = "nodev";
+      };
+      timeout = 10;
     };
+  };
 
-  swapDevices =
+  # fileSystems."/" and swapDevices are now owned by disko
-    [ { device = "/dev/sdb"; }
+  # (../disko/linode.nix, imported from ../platforms/linode.nix) — same
-    ];
+  # /dev/sda root + /dev/sdb swap layout, declared there instead so disko's
-
+  # (idempotent, non-destructive — see that file) format/mount scripts stay
-# Enable LISH
+  # in sync with what NixOS actually mounts.
-boot.kernelParams = [ "console=ttyS0,19200n8" ];
-boot.loader.grub.extraConfig = ''
-  serial --speed=19200 --unit=0 --word=8 --parity=no --stop=1;
-  terminal_input serial;
-  terminal_output serial;
-'';
-
-boot.loader.grub.forceInstall = true;
-# boot.loader.grub.device = "nodev";
-boot.loader.timeout = 10;
-
 
   nixpkgs.hostPlatform = lib.mkDefault "x86_64-linux";
 }

modules/hardware-configuration/vm/proxmox.nix

@@ -5,13 +5,16 @@
 
 {
   imports =
-    [ (modulesPath + "/profiles/qemu-guest.nix")
+    [
+      (modulesPath + "/profiles/qemu-guest.nix")
     ];
 
-  boot.initrd.availableKernelModules = [ "ata_piix" "uhci_hcd" "virtio_pci" "virtio_scsi" "sd_mod" "sr_mod" ];
+  boot = {
-  boot.initrd.kernelModules = [ ];
+    initrd.availableKernelModules = [ "ata_piix" "uhci_hcd" "virtio_pci" "virtio_scsi" "sd_mod" "sr_mod" ];
-  boot.kernelModules = [ "kvm-amd" ];
+    initrd.kernelModules = [ ];
-  boot.extraModulePackages = [ ];
+    kernelModules = [ "kvm-amd" ];
+    extraModulePackages = [ ];
+  };
   # boot.loader.grub.device = "/dev/sda2"; # or "nodev" for efi only
 
   # fileSystems."/" =

modules/installer/common.nix

@@ -0,0 +1,121 @@
+{ pkgs, lib, vars, ... }:
+
+{
+  imports = [
+    ./host-keys.nix
+  ];
+
+  networking.useDHCP = lib.mkDefault true;
+
+  # Recommended over the true default (bypasses ZFS's own import safeguards)
+  # per the option's own docs. This installer environment has no ZFS pools
+  # of its own to import, so this is a no-op here — just silences the
+  # eval-time warning, matching modules/common/configuration.nix.
+  boot.zfs.forceImportRoot = false;
+
+  time.timeZone = vars.timeZone;
+
+  # Without this, the installer only ever sees cache.nixos.org, which
+  # doesn't carry sops-install-secrets (it's built straight from the
+  # sops-nix flake's own Go source, not part of nixpkgs) — every install
+  # would otherwise compile it from scratch, which is what ran an 8GB LXC
+  # container's disk out of space. Push a built copy to nix-cache once
+  # (from a machine with real disk headroom) and every future install,
+  # of any type, fetches instead of rebuilding.
+  nix.settings = {
+    substituters = [
+      "http://nix-cache"
+      "https://cache.nixos.org/"
+    ];
+    trusted-public-keys = [
+      "cache.local-1:usoWYanY3Kpq2+kDIS2nhWoLZiRxanmdysdzqCFBHW4="
+      "cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
+    ];
+  };
+
+  environment = {
+    systemPackages = with pkgs; [
+      git
+      curl
+      jq
+      parted
+      e2fsprogs
+      btrfs-progs
+      util-linux
+      disko
+    ];
+
+    # Auto-install script, kept as a real, version-controlled shell file at
+    # scripts/installer/auto-install.sh rather than an inline Nix string.
+    # It sources scripts/env.sh itself (for LAN_DOMAIN, same as every other
+    # script in this repo) rather than relying on Nix-level templating, so
+    # it behaves identically whether it's run straight from a git checkout
+    # or from here -- baking scripts/env.sh in alongside it at a matching
+    # relative path (installer/auto-install.sh -> ../env.sh) is what makes
+    # that resolve correctly in both places.
+    etc = {
+      "nixos-installer/env.sh".source = ../../scripts/env.sh;
+
+      "nixos-installer/installer/auto-install.sh" = {
+        source = ../../scripts/installer/auto-install.sh;
+        mode = "0755";
+      };
+    };
+  };
+
+  programs.git.enable = true;
+
+  # Run the installer on first login. Previously this copied an /etc file
+  # into the nixos user's ~/.bash_profile via an activation script that
+  # got dropped in a refactor (and only ever worked for that one user
+  # anyway) — loginShellInit is NixOS's native hook for this, applies to
+  # any user's login shell (root included), and needs no home-directory
+  # file-copying/chown.
+  programs.bash.loginShellInit = ''
+    if [ -n "$PS1" ] && [ ! -e "$HOME/.auto_install_ran" ]; then
+      sudo /etc/nixos-installer/installer/auto-install.sh
+      touch "$HOME/.auto_install_ran"
+    fi
+  '';
+
+  services.openssh.enable = true;
+
+  services.openssh.settings = {
+    PermitRootLogin = "yes";
+    PasswordAuthentication = true;
+  };
+
+  # nixpkgs' own installer profile (profiles/installation-device.nix, pulled
+  # in via installation-cd-minimal.nix) sets initialHashedPassword = "" for
+  # both users — its own passwordless-login convention for install media.
+  # That's a second, non-null password option alongside our hashedPassword
+  # below, which NixOS warns about as ambiguous precedence. Force it null
+  # rather than adopting passwordless login: this image now also boots over
+  # LAN PXE with PasswordAuthentication enabled, so passwordless root SSH
+  # would be reachable by anyone on the LAN, not just local console.
+  users.users.root = {
+    hashedPassword =
+      "$6$Kwv9KAyvcurAViQF$H4.u3feqGE7lVoNgkFXhE3n2Pmo//9JYDTCz8ifrVHBxPjwa1xMby7tEZ8Bpt5MXs9Rkx6/YbZWxs5CpH0s/70";
+    initialHashedPassword = lib.mkForce null;
+  };
+
+  users.users.${vars.primaryUser} = {
+    isNormalUser = true;
+
+    extraGroups = [
+      "wheel"
+    ];
+
+    shell = pkgs.bashInteractive;
+
+    hashedPassword =
+      "$6$Kwv9KAyvcurAViQF$H4.u3feqGE7lVoNgkFXhE3n2Pmo//9JYDTCz8ifrVHBxPjwa1xMby7tEZ8Bpt5MXs9Rkx6/YbZWxs5CpH0s/70";
+    initialHashedPassword = lib.mkForce null;
+
+    openssh.authorizedKeys.keys = [
+      vars.adminSshKey
+    ];
+  };
+
+  system.stateVersion = "26.05";
+}

modules/installer/host-keys.nix

@@ -0,0 +1,37 @@
+{ lib, ... }:
+
+let
+  # host-keys/ is gitignored (private key material must never be committed),
+  # which means flakes' git-filtered source tree can never see it via a
+  # normal relative path — referencing it at all requires stepping outside
+  # pure evaluation. builtins.getEnv is neutered to "" under normal
+  # `nix build`/`nix eval` (no error, just empty), so this whole module is a
+  # silent no-op unless the operator explicitly opts in with --impure and
+  # the env var set — safe by default, including in CI.
+  #
+  #   NIXOS_HOST_KEYS_DIR=$(pwd)/host-keys nix build .#iso --impure
+  #
+  # See docs/auto-installer.md.
+  hostKeysDirStr = builtins.getEnv "NIXOS_HOST_KEYS_DIR";
+  hasHostKeysDir = hostKeysDirStr != "" && builtins.pathExists hostKeysDirStr;
+  hostKeysDir = /. + hostKeysDirStr;
+
+  keyFileNames =
+    if hasHostKeysDir
+    then
+      lib.filter
+        (name: lib.hasSuffix "_ssh_host_ed25519_key" name || lib.hasSuffix "_ssh_host_ed25519_key.pub" name)
+        (lib.attrNames (builtins.readDir hostKeysDir))
+    else [ ];
+in
+{
+  environment.etc = lib.listToAttrs (map
+    (name: {
+      name = "host-keys/${name}";
+      value = {
+        source = hostKeysDir + "/${name}";
+        mode = "0400";
+      };
+    })
+    keyFileNames);
+}

modules/installer/iso.nix

@@ -0,0 +1,8 @@
+{ modulesPath, ... }:
+
+{
+  imports = [
+    "${modulesPath}/installer/cd-dvd/installation-cd-minimal.nix"
+    ./common.nix
+  ];
+}

modules/ipa/client.nix

@@ -0,0 +1,210 @@
+# Fully declarative FreeIPA domain membership.
+#
+# Imported by modules/common/configuration.nix — no per-host wiring needed.
+# Enables itself automatically on any host that has a sops-encrypted keytab
+# at secrets/<hostname>.keytab; is a no-op for all other hosts.
+#
+# To enroll a new host:
+#   0. scripts/secrets/sync-host-keys.sh <flake-target>
+#   1. scripts/ipa/create-nixos-ipa-host-account.sh [--ip <addr>] <hostname>
+#      (adds .sops.yaml rule, runs ipa host-add, encrypts keytab in one step)
+#   2. git add secrets/<hostname>.keytab .sops.yaml && git commit
+#   3. Deploy — no further steps required.
+#
+# Manual fallback (if the script isn't usable):
+#   a. On the FreeIPA server: ipa host-add <fqdn> [--ip-address=<ip>] --force
+#   b. On the FreeIPA server: ipa-getkeytab -s <ipa-server> -p host/<fqdn> -k /tmp/<host>.keytab
+#   c. From the repo root (path must match for sops creation rule to apply):
+#        cp /tmp/<host>.keytab secrets/<host>.keytab
+#        sops -e --input-type binary -i secrets/<host>.keytab
+#   d. Commit secrets/<host>.keytab and the updated .sops.yaml, then deploy.
+#
+# vars dependencies: homeDomain, ipaServer, domainControllerIp, ipaUser
+
+{ config, lib, pkgs, vars, ... }:
+
+let
+  keytabPath = ../../secrets + "/${config.networking.hostName}.keytab";
+  enabled = builtins.pathExists keytabPath;
+
+  realm = lib.strings.toUpper vars.homeDomain;
+  fqdn = "${config.networking.hostName}.${vars.homeDomain}";
+  # "sweet.home" -> "dc=sweet,dc=home"
+  basedn = lib.strings.concatMapStringsSep "," (c: "dc=${c}") (lib.strings.splitString "." vars.homeDomain);
+  # security.ipa.certificate expects a derivation (package), not a raw path.
+  caCertPkg = pkgs.writeText "ipa-ca.crt" (builtins.readFile ../../certs/ipa-ca.crt);
+in
+lib.mkIf enabled {
+  networking.domain = lib.mkDefault vars.homeDomain;
+  networking.nameservers = lib.mkDefault [ vars.domainControllerIp ];
+
+  security = {
+    ipa = {
+      enable = true;
+      domain = vars.homeDomain;
+      inherit realm;
+      server = vars.ipaServer;
+      certificate = caCertPkg;
+      inherit basedn;
+      ipaHostname = fqdn;
+      offlinePasswords = true;
+      cacheCredentials = true;
+    };
+
+    # Create the home directory on first login if it doesn't exist yet.
+    # IPA users have no pre-created home on the host; without this sshd
+    # opens a session to a non-existent directory and resets the connection.
+    # lightdm also needs this so the GUI login path can create the home dir
+    # if it was not pre-seeded by the tmpfiles rule above (e.g. on first boot
+    # before SSSD has resolved the user).
+    pam.services = {
+      sshd.makeHomeDir = true;
+      lightdm.makeHomeDir = true;
+
+      # pam_unix returns PAM_AUTHINFO_UNAVAIL without prompting when the local
+      # stub has "!" in shadow (account locked), so PAM_AUTHTOK is never set
+      # and pam_sss's use_first_pass fails with "No authentication token".
+      # Changing to try_first_pass makes pam_sss prompt independently when no
+      # prior module has set the token, restoring IPA password login via
+      # LightDM and su.
+      login.rules.auth.sss.settings = lib.mkForce { try_first_pass = true; };
+      su.rules.auth.sss.settings = lib.mkForce { try_first_pass = true; };
+    };
+
+    # HM with useUserPackages = true (flake.nix) sets users.users.${ipaUser}.packages,
+    # which forces the stub into /etc/passwd. pam_sss.so with the "localusers" flag
+    # (added by NixOS when SSSD is enabled) then skips SSSD for any user it finds in
+    # local /etc/passwd — including this stub — falling through to pam_unix, which has
+    # no password for the stub → sudo auth always fails.
+    #
+    # Fix: NOPASSWD for the IPA user. The IPA user already authenticated to reach a
+    # shell (SSH public key from IPA or Kerberos), so re-prompting via a broken PAM
+    # path is security theater on a single-admin homelab.
+    sudo.extraRules = [{
+      users = [ vars.ipaUser ];
+      commands = [{ command = "ALL"; options = [ "NOPASSWD" ]; }];
+    }];
+  };
+
+  systemd = {
+    # Fetch SSH public keys from IPA so users can log in with the key stored
+    # in their IPA profile rather than needing ~/.ssh/authorized_keys on every
+    # host. sss_ssh_authorizedkeys queries SSSD (which queries IPA LDAP).
+    #
+    # /nix/store is 1775 (group-writable by nixbld). OpenSSH 10.0+ rejects
+    # AuthorizedKeysCommand binaries whose path contains any group-writable
+    # component, silently skipping the command. Copy to /usr/local/bin (all
+    # components root-owned, 755) so the path passes sshd's safety check.
+    tmpfiles.rules = [
+      "d /usr/local 0755 root root - -"
+      "d /usr/local/bin 0755 root root - -"
+      "C+ /usr/local/bin/sss_ssh_authorizedkeys 0555 root root - ${pkgs.sssd}/bin/sss_ssh_authorizedkeys"
+      # Pre-create the IPA user's home dir so Home Manager activation succeeds
+      # even before their first login. On a fresh system SSSD may not have
+      # resolved the user yet — tmpfiles warns and skips in that case (non-fatal),
+      # and pam_mkhomedir covers the first-login path as a fallback.
+      "d /home/${vars.ipaUser} 0700 ${vars.ipaUser} ${vars.ipaUser} - -"
+    ];
+
+    # security.ipa enables Kerberos (security.krb5) which causes systemd to
+    # start auth-rpcgss-module.service and rpc-gssd.service for Kerberos NFS
+    # authentication. LXC containers can't load the auth_rpcgss kernel module
+    # and don't have /var/lib/nfs/rpc_pipefs, so both services fail.
+    #
+    # The NixOS IPA module already adds a drop-in for auth-rpcgss-module.service
+    # with ConditionPathExists=/etc/krb5.keytab. We use lib.mkForce to win the
+    # text conflict and add ConditionVirtualization=!container alongside it so
+    # the service is skipped (not failed) in containers that do have a keytab.
+    # Same fix for rpc-gssd.service which also fails in containers.
+    units = lib.mkIf config.boot.isContainer {
+      "auth-rpcgss-module.service" = {
+        overrideStrategy = "asDropinIfExists";
+        text = lib.mkForce ''
+          [Unit]
+          ConditionPathExists=
+          ConditionPathExists=/etc/krb5.keytab
+          ConditionVirtualization=!container
+        '';
+      };
+      # rpc-gssd also has ConditionPathExists from the NixOS IPA module (and an
+      # X-Restart-Triggers store path from systemd.nix). Use mkForce to win;
+      # omit X-Restart-Triggers since this service is skipped in containers anyway.
+      "rpc-gssd.service" = {
+        overrideStrategy = "asDropinIfExists";
+        text = lib.mkForce ''
+          [Unit]
+          ConditionPathExists=
+          ConditionPathExists=/etc/krb5.keytab
+          ConditionVirtualization=!container
+        '';
+      };
+    };
+
+    # home-manager-<user>.service fails on first enrollment because /home/wayne
+    # doesn't exist until the user's first login (pam_mkhomedir creates it then).
+    # ConditionPathExists makes systemd skip the service (exit 0, condition not
+    # met) instead of failing. After first login the dir exists and subsequent
+    # rebuilds activate HM normally.
+    services."home-manager-${vars.ipaUser}".unitConfig.ConditionPathExists =
+      "/home/${vars.ipaUser}";
+  };
+
+  services.openssh.extraConfig = ''
+    AuthorizedKeysCommand /usr/local/bin/sss_ssh_authorizedkeys %u
+    AuthorizedKeysCommandUser nobody
+  '';
+
+  # Host keytab: pre-provisioned on the IPA server, sops-encrypted binary.
+  # Placed at /etc/krb5.keytab before SSSD starts so the host authenticates
+  # to IPA without running ipa-client-install.
+  sops.secrets."ipa-host-keytab" = {
+    sopsFile = keytabPath;
+    format = "binary";
+    path = "/etc/krb5.keytab";
+    owner = "root";
+    group = "root";
+    mode = "0600";
+    restartUnits = [ "sssd.service" ];
+  };
+
+  # NixOS requires isNormalUser/isSystemUser + group on any entry in
+  # users.users. HM with useUserPackages = true (set in flake.nix) adds a stub
+  # entry for each HM user so it can install packages to
+  # /etc/profiles/per-user/<name>/. This definition satisfies those assertions.
+  # With security.ipa setting "passwd: sss files" in nsswitch, SSSD's IPA entry
+  # takes priority for NSS lookups — this local stub is only a fallback when
+  # SSSD is unreachable (at which point auth fails anyway).
+  users.users.${vars.ipaUser} = {
+    isNormalUser = true;
+    group = "users";
+    extraGroups = [ "wheel" ];
+    createHome = false;
+    # "!" is not a password hash — it is the standard "account locked" marker.
+    # It cannot authenticate anyone locally. It exists solely so NixOS generates
+    # a shadow entry for this stub user; without one pam_unix returns
+    # PAM_AUTHINFO_UNAVAIL before prompting, which means PAM_AUTHTOK is never
+    # set and the subsequent pam_sss use_first_pass call has nothing to work
+    # with — blocking LightDM and su logins even when IPA/SSSD auth succeeds.
+    hashedPassword = "!";
+  };
+
+  # Home Manager config for the IPA primary user, applied on every enrolled
+  # host. Manages what IPA doesn't: dotfiles, user-scoped packages, session
+  # variables. Switch-nix/Test-nix/buildImage are system-wide (configuration.nix)
+  # so they don't need to be repeated here.
+  #
+  # homeDirectory uses mkForce because HM's NixOS integration module sets it to
+  # "/var/empty" for users not found in config.users.users at eval time (SSSD
+  # users aren't visible there).
+  home-manager.users.${vars.ipaUser} = { pkgs, ... }: {
+    home = {
+      username = vars.ipaUser;
+      homeDirectory = lib.mkForce "/home/${vars.ipaUser}";
+      stateVersion = "26.05";
+      packages = with pkgs; [ tmux sshfs ];
+      sessionVariables.EDITOR = lib.mkDefault "nano";
+    };
+    programs.home-manager.enable = true;
+    programs.bash.enable = true;
+  };
+}

modules/networking/wifi.nix

@@ -0,0 +1,43 @@
+{ config, lib, vars, ... }:
+
+{
+  # Prestages a NetworkManager connection profile for vars.wifiSsid so the
+  # host associates on first boot with no manual nmtui/nmcli step. Guarded
+  # on a non-empty SSID so leaving the placeholder blank in variables.nix
+  # is a no-op rather than an empty, broken profile — fill it in once the
+  # network is known.
+  #
+  # The password itself lives in secrets/gui.yaml, not variables.nix --
+  # NetworkManager's ensureProfiles renders `psk = "$WIFI_PASSWORD"`
+  # literally into the store (see nixpkgs' own ensureProfiles example,
+  # which does the same for exactly this reason) and its systemd service
+  # envsubst-expands it from environmentFiles at activation time, so the
+  # real value only ever touches /run (root-only, UMask 0177), never the
+  # Nix store.
+  sops.secrets."wifi-password" = lib.mkIf (vars.wifiSsid != "") {
+    sopsFile = ../../secrets/gui.yaml;
+  };
+
+  sops.templates."wifi-password.env" = lib.mkIf (vars.wifiSsid != "") {
+    content = "WIFI_PASSWORD=${config.sops.placeholder."wifi-password"}";
+  };
+
+  networking.networkmanager.ensureProfiles = lib.mkIf (vars.wifiSsid != "") {
+    environmentFiles = [ config.sops.templates."wifi-password.env".path ];
+
+    profiles.${vars.wifiSsid} = {
+      connection = {
+        id = vars.wifiSsid;
+        type = "wifi";
+      };
+      wifi = {
+        mode = "infrastructure";
+        ssid = vars.wifiSsid;
+      };
+      wifi-security = {
+        key-mgmt = "wpa-psk";
+        psk = "$WIFI_PASSWORD";
+      };
+    };
+  };
+}

modules/nix-cache/client.nix

@@ -1,9 +1,9 @@
-{ ... }:
+{ vars, ... }:
 
 {
   nix.settings = {
     substituters = [
-      "http://nix-cache"
+      "http://${vars.nixCacheHost}.${vars.homeDomain}"
       "https://cache.nixos.org/"
     ];
     trusted-public-keys = [

modules/nix-cache/remote-builder-client.nix

@@ -0,0 +1,40 @@
+{ pkgs, vars, ... }:
+
+{
+  # Authenticate as nixremote using the client host's own default root SSH
+  # identity (/root/.ssh/id_ed25519) rather than a separately-named key --
+  # matches vars.remoteBuilderAuthorizedKeys, which already authorizes
+  # each host's own default key (one entry per host, not a shared
+  # dedicated keypair). If this host doesn't have one yet:
+  #   sudo -u root ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519
+  #   # then add its .pub to vars.remoteBuilderAuthorizedKeys and rebuild nix-cache
+  #   sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache.sweet.home nix-store --version
+  # Trust nix-cache's SSH host key declaratively so the nix-daemon (root)
+  # can connect the first time without a manual ssh-keyscan/known_hosts
+  # step on every new client.
+  programs.ssh.knownHosts."${vars.nixCacheHost}.${vars.homeDomain}" = {
+    hostNames = [ "${vars.nixCacheHost}.${vars.homeDomain}" ];
+    publicKey = vars.nixCacheHostKey;
+  };
+
+  nix = {
+    distributedBuilds = true;
+
+    buildMachines = [
+      {
+        hostName = "${vars.nixCacheHost}.${vars.homeDomain}";
+        sshUser = vars.remoteBuilderUser;
+        sshKey = "/root/.ssh/id_ed25519";
+        inherit (pkgs.stdenv.hostPlatform) system;
+        maxJobs = 4;
+        speedFactor = 2;
+        supportedFeatures = [ "nixos-test" "benchmark" "big-parallel" "kvm" ];
+      }
+    ];
+
+    settings = {
+      builders-use-substitutes = true;
+      max-jobs = "auto";
+    };
+  };
+}

modules/nix-cache/server.nix

@@ -1,54 +1,53 @@
-{ config, pkgs, ... }:
+{ config, pkgs, vars, ... }:
 
 {
-  # Generate the binary cache key pair on the nix-cache host:
+  # nix-serve's signing key has to be the *same* key on every host that
-  #   sudo install -d -m 0700 /etc/nix
+  # ever plays the nix-cache role -- modules/nix-cache/client.nix hardcodes
-  #   sudo nix-store --generate-binary-cache-key nix-cache-1 \
+  # every client's trust in one specific public key ("cache.local-1:..."),
-  #     /etc/nix/cache-priv.pem \
+  # so a freshly self-generated key here wouldn't be trusted by anyone.
-  #     /etc/nix/cache-pub.pem
+  # Managed via sops-nix like every other secret in this repo instead of
-  #   sudo chmod 0600 /etc/nix/cache-priv.pem
+  # the old manual `nix-store --generate-binary-cache-key` step -- see
-  #   sudo chmod 0644 /etc/nix/cache-pub.pem
+  # "Binary cache signing key" in docs/nix-cache.md for how to add/rotate
-  #   cat /etc/nix/cache-pub.pem
+  # the value in secrets/nix-cache.yaml.
-  services.nix-serve = {
+  sops.secrets."cache-priv-key".sopsFile = ../../secrets/nix-cache.yaml;
-    enable = true;
-    secretKeyFile = "/etc/nix/cache-priv.pem";
-  };
 
-  services.nginx = {
+  services = {
-    enable = true;
+    nix-serve = {
-    recommendedProxySettings = true;
+      enable = true;
-    virtualHosts."nix-cache" = {
+      secretKeyFile = config.sops.secrets."cache-priv-key".path;
-      locations."/" = {
+    };
-        proxyPass = "http://${config.services.nix-serve.bindAddress}:${toString config.services.nix-serve.port}";
+
+    nginx = {
+      enable = true;
+      recommendedProxySettings = true;
+      virtualHosts."${vars.nixCacheHost}.${vars.homeDomain}" = {
+        locations."/" = {
+          proxyPass = "http://${config.services.nix-serve.bindAddress}:${toString config.services.nix-serve.port}";
+        };
       };
     };
+
+    openssh.enable = true;
   };
 
-  networking.firewall.allowedTCPPorts = [ 80 ];
+  networking.firewall.allowedTCPPorts = [ vars.ports.nixCacheHttp ];
 
-  users.groups.nixremote = {};
+  users.groups.${vars.remoteBuilderUser} = { };
 
-  users.users.nixremote = {
+  users.users.${vars.remoteBuilderUser} = {
     isSystemUser = true;
-    group = "nixremote";
+    group = vars.remoteBuilderUser;
     createHome = true;
     home = "/var/lib/nixremote";
     shell = pkgs.bashInteractive;
-    # Provide remote builder public keys here (safe to commit public keys only):
+    # Client public keys allowed to use this host as a remote builder —
-    # openssh.authorizedKeys.keys = [ "ssh-ed25519 AAAA... client@host" ];
+    # single source of truth is vars.remoteBuilderAuthorizedKeys (safe to
-    #
+    # commit public keys only).
-    # Avoid absolute keyFiles paths here because they break pure flake evaluation.
+    openssh.authorizedKeys.keys = vars.remoteBuilderAuthorizedKeys;
-    openssh.authorizedKeys.keys = ["ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFDEA1S2ikpObREgbP5uVBWMxIOGbY8B+Wx7VTZK1m6t root@server"
-					"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPAYIT9ormlmxZ0SziyDQaUntnKI8HK9/s3Qac1ZKjP2 root@docker" 
-					"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIKKKzoEPl/ZW9KBRHBcp6/ThOngGpwMv5EhkTlgC4aDf root@nixos"
-					"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIGtOWOCS+ImHc7NehguoyD7PbonGosKMZqc9+QR3v/h root@nixos"
-					"ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHxXTQxFnArK5HXG7czeoybZebCGfxpUdusJkPn+BCSp root@server"];
   };
 
-  services.openssh.enable = true;
-
   nix.settings = {
-    trusted-users = [ "root" "nixremote" ];
+    trusted-users = [ "root" vars.remoteBuilderUser ];
     experimental-features = [ "nix-command" "flakes" ];
     auto-optimise-store = true;
     builders-use-substitutes = true;
@@ -57,6 +56,6 @@
   nix.gc = {
     automatic = true;
     dates = "weekly";
-    options = "--delete-older-than 30d";
+    options = "--delete-older-than ${vars.nixCacheGcMaxAge}";
   };
 }

modules/platforms/baremetal.nix

@@ -0,0 +1,38 @@
+{ ... }:
+
+{
+  imports = [
+    ../hardware-configuration/baremetal.nix
+    ../boot/efi.nix
+    ../disko/baremetal.nix
+    ../services/zfs/enable-service.nix
+  ];
+
+  # Needed for real wifi/bluetooth/GPU firmware blobs and CPU microcode
+  # updates (hardware-configuration/baremetal.nix's amd.updateMicrocode
+  # keys off this) -- irrelevant on the linode/proxmox/lxc platforms,
+  # which are all VMs with no real hardware to load firmware for.
+  hardware.enableRedistributableFirmware = true;
+
+  # AMD GPU: the amdgpu kernel driver autoloads from the PCI ID with no
+  # extra boot.kernelModules entry needed; this is the userspace half --
+  # the dedicated Xorg driver (not just the generic modesetting fallback)
+  # plus Mesa OpenGL/Vulkan (amdgpu/RADV), same firmware blobs as above.
+  # 32-bit support is for compatibility with 32-bit apps/games.
+  services.xserver.videoDrivers = [ "amdgpu" ];
+
+  hardware.graphics = {
+    enable = true;
+    enable32Bit = true;
+  };
+
+  # The systemd-based initrd (default here since this host has a ZFS root --
+  # see modules/disko/baremetal.nix) locks the root account by default, so
+  # sulogin refuses to hand over a shell if something in the initrd (e.g.
+  # the ZFS pool import) fails and it drops to emergency mode -- confirmed
+  # live: it just loops re-entering the target instead of prompting. This
+  # only affects the pre-switch-root initrd shell, not the installed
+  # system's own login, and is worth the tradeoff on a box already reachable
+  # at the physical console.
+  boot.initrd.systemd.emergencyAccess = true;
+}

modules/platforms/linode.nix

@@ -3,6 +3,7 @@
 {
   imports = [
     ../hardware-configuration/vm/linode.nix
+    ../disko/linode.nix
   ];
 
   networking = {

modules/platforms/lxc.nix

@@ -1,8 +1,208 @@
-{ ... }:
+{ config, lib, modulesPath, flakeTarget, ... }:
 
+let
+  # Bakes this exact flake target's pre-generated SSH host key straight
+  # into /etc/ssh/ -- mirrors modules/installer/host-keys.nix's
+  # builtins.getEnv pattern (impure and empty under normal `nix
+  # build`/`nix eval`, so this is a no-op unless explicitly opted into
+  # with NIXOS_HOST_KEYS_DIR=... --impure), but places the key directly
+  # rather than staging it under /etc/host-keys/ for a later manual copy
+  # -- this is the whole system for a `lxc-*` host, built straight to a
+  # pct-restorable tarball with no install step, so there's no later copy
+  # step to stage for.
+  #
+  # Without this, config.system.build.tarball's built-in system just
+  # generates a fresh host key at first boot like any other host would --
+  # but sops-nix derives its decryption key from *this* file, and
+  # .sops.yaml only trusts whatever key scripts/secrets/sync-host-keys.sh already
+  # registered for this exact target name. A freshly-generated key can
+  # never match that, so every secret (including this host's own login)
+  # permanently fails to decrypt. Confirmed live: sops-install-secrets
+  # errored with "Error getting data key: 0 successful groups required,
+  # got 0" -- the container's actual host key's age fingerprint didn't
+  # match the one registered in .sops.yaml at all.
+  hostKeysDirStr = builtins.getEnv "NIXOS_HOST_KEYS_DIR";
+  hasHostKeysDir = hostKeysDirStr != "" && builtins.pathExists hostKeysDirStr;
+  hostKeysDir = /. + hostKeysDirStr;
+
+  # flakeTarget ("${platform}-${buildType}") comes in via specialArgs from
+  # flake.nix's mkTarget -- exactly the name scripts/secrets/sync-host-keys.sh
+  # registers keys under. Deliberately not read back from
+  # config.environment.etc."flake-target" (which is set to the same value)
+  # -- this module also *contributes* to environment.etc below, and a
+  # module reading the merged value of an option it's still defining is a
+  # circular dependency (confirmed: "infinite recursion encountered").
+  privKeyFile = hostKeysDir + "/${flakeTarget}_ssh_host_ed25519_key";
+  pubKeyFile = hostKeysDir + "/${flakeTarget}_ssh_host_ed25519_key.pub";
+  hasKeyForThisTarget =
+    hasHostKeysDir
+    && builtins.pathExists privKeyFile
+    && builtins.pathExists pubKeyFile;
+in
 {
-  boot.isContainer = true;
+  # LXC containers share the host kernel — Proxmox starts them by exec'ing
+  # /sbin/init directly, no bootloader/initrd involved — and Proxmox has its
+  # own container hostname/network provisioning outside Nix. nixpkgs' own
+  # virtualisation/proxmox-lxc.nix module already handles all of this
+  # correctly (boot.isContainer, loader.initScript, systemd-networkd) and,
+  # critically, provides config.system.build.tarball — a directly
+  # `pct restore`-able container image, no nixos-install/bind-mount needed
+  # (nixos-install refuses to touch the filesystem it's currently running
+  # on, which is exactly what bind-mounting / onto /mnt for an installer
+  # LXC container does).
+  imports = [
+    (modulesPath + "/virtualisation/proxmox-lxc.nix")
+    ../common/preserve-ssh-host-key.nix
+  ];
 
-  boot.loader.grub.enable = false;
+  proxmoxLXC = {
-  boot.loader.systemd-boot.enable = false;
+    # host.nix declares each host's real hostname (networking.hostName);
+    # keep that instead of letting Proxmox's ambient container config win.
+    manageHostName = true;
+    # Unprivileged by default -- matches how these containers are actually
+    # created (scripts/proxmox/create-proxmox-resource.sh reads this value
+    # back to decide `pct create`'s --unprivileged flag, so the two stay
+    # in sync).
+    #
+    # Any lxc-* host with an NFS fileSystem must be privileged: the kernel's
+    # NFS client doesn't set FS_USERNS_MOUNT, so mounting NFS from inside
+    # *any* non-init user namespace -- which is exactly what an unprivileged
+    # container's UID-mapped root runs in -- is rejected at the VFS layer
+    # with EPERM, no matter what Proxmox's own `mount=nfs;nfs4` container
+    # feature allows at the AppArmor layer (confirmed live: TCP to the NFS
+    # server succeeds, the server's export table matches the container's IP,
+    # and `mount.nfs: Operation not permitted` still fires immediately with
+    # no corresponding denial anywhere in the server's logs -- a kernel-level
+    # rejection, not a network or export-permission one). Deriving this from
+    # fileSystems rather than a per-host override keeps it self-consistent:
+    # any new lxc-* host that declares an NFS mount automatically gets the
+    # privilege level it needs without a separate manual flag.
+    privileged = builtins.any
+      (fs: fs.fsType == "nfs" || fs.fsType == "nfs4")
+      (builtins.attrValues config.fileSystems);
+  };
+
+  boot.loader = {
+    grub.enable = false;
+    systemd-boot.enable = false;
+  };
+
+  # NetworkManager depends on a running udevd to enumerate/classify devices,
+  # which boot.isContainer disables (see nixpkgs' container-config.nix) —
+  # that's what broke DHCP-hostname registration in Pi-hole. The imported
+  # proxmox-lxc.nix module already switches networking to systemd-networkd
+  # for the same reason; it just doesn't disable NetworkManager itself,
+  # which modules/common/configuration.nix enables for every host.
+  networking.networkmanager.enable = lib.mkForce false;
+
+  environment.etc = lib.mkIf hasKeyForThisTarget {
+    "ssh/ssh_host_ed25519_key" = {
+      source = privKeyFile;
+      mode = "0600";
+    };
+    "ssh/ssh_host_ed25519_key.pub" = {
+      source = pubKeyFile;
+      mode = "0644";
+    };
+  };
+
+  # virtualisation/proxmox-lxc.nix (imported above) registers the Nix
+  # store DB via a systemd service (register-nix-paths) -- it never runs
+  # an activation script at all. Confirmed live this means neither
+  # sops-nix's "for users" secrets (password hashes -- installed by the
+  # activation script itself, not a systemd service, since they need to
+  # exist *before* user creation) nor the user-creation step that
+  # consumes them ever run on a real lxc-* boot. In this config sops-nix
+  # does NOT generate its own boot-time service (confirmed live: no
+  # sops-nix.service in systemctl list-unit-files on a deployed
+  # lxc-tor-relay container); /run/secrets is a tmpfs cleared on every
+  # reboot, so secrets must be reinstalled on each non-first boot by
+  # nixos-lxc-sops-reinstall (below).
+  #
+  # A systemd service, not boot.postBootCommands: tried that first (it's
+  # a genuine, generally-invoked hook -- nixos/modules/system/boot/stage-2-init.sh,
+  # which becomes this container's actual /sbin/init, unconditionally
+  # runs it) but switch-to-configuration behaves differently that early in
+  # boot (raw stage-2-init.sh, before systemd itself has even started) --
+  # confirmed live it silently failed to rewrite /etc/shadow from there
+  # even in "test" mode, despite the exact same command working reliably
+  # every time when run post-boot (i.e. as a normal systemd service, which
+  # is what this is). Not fully root-caused why the early context
+  # specifically breaks it; a real systemd service sidesteps needing to.
+  #
+  # /etc/shadow already has PLACEHOLDER entries for every declared user
+  # baked in at build time (part of constructing the system closure).
+  # update-users-groups.pl deliberately never overwrites an *existing*
+  # shadow entry -- a correct safety property in general (don't clobber a
+  # real user's real password on a config rebuild) -- but on a genuine
+  # first boot that only means the real hashedPasswordFile-derived hash
+  # never gets the chance to be applied either, since the placeholder is
+  # already "seen". Safe to clear here specifically: there is no real
+  # password yet to protect on a first boot.
+  #
+  # "test" mode, not "boot": confirmed live "boot" mode aborts partway
+  # through (before rewriting /etc/shadow) on a warning that "/boot" is on
+  # a different filesystem -- a real check for a host with a bootloader to
+  # update, meaningless for a container that has none
+  # (boot.loader.{grub,systemd-boot}.enable are both false above), but it
+  # still aborts the script. "test" runs every activation step without
+  # touching boot-loader state at all.
+  #
+  # ConditionPathExists (systemd-native, not a bash-level check) means
+  # this only ever runs once, on the genuine first boot -- systemd itself
+  # skips even starting it on every later boot once the marker exists.
+  # switch-to-configuration is otherwise the operator's call per this
+  # repo's own safety rules, not something to run on every boot.
+  systemd.services.nixos-lxc-first-boot-activate = {
+    description = "Complete first-boot NixOS activation (users, secrets) for this LXC container";
+    wantedBy = [ "multi-user.target" ];
+    unitConfig.ConditionPathExists = "!/var/lib/nixos-lxc-first-boot-activated";
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+    };
+    script = ''
+      rm -f /etc/shadow
+      /run/current-system/bin/switch-to-configuration test
+      mkdir -p /var/lib
+      touch /var/lib/nixos-lxc-first-boot-activated
+    '';
+  };
+
+  # Reinstalls sops secrets on every non-first boot. /run/secrets is a
+  # tmpfs that is cleared on each reboot; without this service, secrets
+  # are permanently absent after the first boot and every service that
+  # reads from /run/secrets fails on start.
+  #
+  # wantedBy/before network.target: switch-to-configuration test requires
+  # D-Bus to restart systemd targets after running activation scripts. D-Bus
+  # is available once basic.target completes (the default After=basic.target
+  # that DefaultDependencies would otherwise add). Placing the service before
+  # network.target ensures secrets are ready before any network-dependent
+  # service (including beszel-agent and nix-serve) starts, while running late
+  # enough that D-Bus is already up.
+  #
+  # ConditionPathExists=... skips this service on the genuine first boot
+  # (the marker doesn't exist yet); nixos-lxc-first-boot-activate handles
+  # that case. On every subsequent boot the condition passes and secrets
+  # are reinstalled before user services start.
+  #
+  # SuccessExitStatus=11: switch-to-configuration exits 11 when it cannot
+  # acquire the activation lock (another switch is already in progress).
+  # During a nixos-rebuild switch the activation already installs secrets, so
+  # treating the lock-held case as success is correct.
+  systemd.services.nixos-lxc-sops-reinstall = {
+    description = "Reinstall sops secrets on each non-first boot (LXC, /run is tmpfs)";
+    wantedBy = [ "network.target" ];
+    before = [ "network.target" ];
+    unitConfig.ConditionPathExists = "/var/lib/nixos-lxc-first-boot-activated";
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+      SuccessExitStatus = "11";
+    };
+    script = ''
+      /run/current-system/bin/switch-to-configuration test
+    '';
+  };
 }

modules/platforms/proxmox.nix

@@ -1,9 +1,50 @@
-{ ... }:
+{ lib, flakeTarget, ... }:
 
+let
+  # Bakes this exact flake target's pre-generated SSH host key straight
+  # into /etc/ssh/ -- mirrors lxc.nix's builtins.getEnv pattern (impure
+  # and empty under normal `nix build`/`nix eval`, so this is a no-op
+  # unless explicitly opted into with NIXOS_HOST_KEYS_DIR=... --impure).
+  #
+  # Unlike --pre-format-files (which places files on the QEMU builder VM's
+  # rootfs, not the target disk), embedding via environment.etc here means
+  # nixos-install's own activation step installs the key onto the target
+  # disk. sshd-keygen then finds it already present and skips generation,
+  # so the disk image boots with the clan-registered key and sops can
+  # decrypt on first boot.
+  #
+  # Without this, nixos-install's sshd-keygen activation generates a fresh
+  # key (unregistered in .sops.yaml), sops decryption fails permanently,
+  # and password hashes are never applied -- confirmed live: passwords
+  # stayed '!' even with mutableUsers = false because hashedPasswordFile
+  # pointed to a path that sops never wrote.
+  hostKeysDirStr = builtins.getEnv "NIXOS_HOST_KEYS_DIR";
+  hasHostKeysDir = hostKeysDirStr != "" && builtins.pathExists hostKeysDirStr;
+  hostKeysDir = /. + hostKeysDirStr;
+
+  privKeyFile = hostKeysDir + "/${flakeTarget}_ssh_host_ed25519_key";
+  pubKeyFile = hostKeysDir + "/${flakeTarget}_ssh_host_ed25519_key.pub";
+  hasKeyForThisTarget =
+    hasHostKeysDir
+    && builtins.pathExists privKeyFile
+    && builtins.pathExists pubKeyFile;
+in
 {
   imports = [
     ../hardware-configuration/vm/proxmox.nix
     ../boot/efi.nix
     ../disko/proxmox.nix
+    ../common/preserve-ssh-host-key.nix
   ];
+
+  environment.etc = lib.mkIf hasKeyForThisTarget {
+    "ssh/ssh_host_ed25519_key" = {
+      source = privKeyFile;
+      mode = "0600";
+    };
+    "ssh/ssh_host_ed25519_key.pub" = {
+      source = pubKeyFile;
+      mode = "0644";
+    };
+  };
 }

modules/pxe-boot/mount-pxe-images.nix

@@ -0,0 +1,42 @@
+{ config, lib, vars, ... }:
+
+let
+  # FQDN of the LAN NFS VIP (Pacemaker vip-lan, 192.168.2.229). Using the
+  # FQDN rather than a raw IP or bare hostname avoids systemd-resolved LLMNR
+  # quirks and survives a future VIP renumber via a DNS-only update.
+  nfsServer = "ha-vip-lan.${vars.homeDomain}";
+in
+{
+  fileSystems.${vars.nfsShares.pxebootImages.mountpoint} = {
+    device = "${nfsServer}:${vars.haStorageRoot}/${vars.nfsShares.pxebootImages.subpath}";
+    fsType = "nfs";
+    options = [
+      "_netdev"
+      "noatime"
+    ] ++ (if config.boot.isContainer
+    # NFSv4 requires rpc_pipefs (sunrpc filesystem), which Proxmox LXC
+    # containers block unless `features: mount=nfs` is set. Use NFSv3+nolock
+    # instead: no rpc_pipefs dependency at the protocol level, and rpcbind
+    # on the server handles port resolution without needing client-side
+    # sunrpc infrastructure. nofail keeps boot clean if server is unreachable.
+    then [ "nfsvers=3" "proto=tcp" "nolock" "nofail" ]
+    else [ "nfsvers=4.2" "x-systemd.automount" ]);
+  };
+
+  # NixOS pulls var-lib-nfs-rpc_pipefs.mount (the sunrpc filesystem) into
+  # nfs-client.target for any nfs fileSystems entry. In LXC containers the
+  # sunrpc mount is blocked by Proxmox's AppArmor profile, causing it to fail
+  # and the activation to report an error even though our mount uses nofail.
+  # Add ConditionVirtualization=!container via drop-in so systemd skips the
+  # unit entirely in containers (skip = inactive, not failed), which keeps
+  # nfs-client.target green and activation clean.
+  systemd.units = lib.mkIf config.boot.isContainer {
+    "var-lib-nfs-rpc_pipefs.mount" = {
+      overrideStrategy = "asDropin";
+      text = ''
+        [Unit]
+        ConditionVirtualization=!container
+      '';
+    };
+  };
+}

modules/pxe-boot/stage-installer-artifacts.nix

@@ -0,0 +1,32 @@
+{ netbootSystem, netbootMinimalSystem, ... }:
+
+let
+  # config.system.build.kernel and .netbootRamdisk are directories, not the
+  # files themselves — nixpkgs' own system.build.kexecTree does the same
+  # ${...}/<file> dereference for the same reason.
+  mkStageRules = { dirName, system }:
+    let
+      inherit (system.config.system.boot.loader) kernelFile;
+      dir = "/srv/pxe/http/${dirName}";
+    in
+    [
+      # Declared here too (not just in build-types/pxe-boot.nix) so this
+      # module's C+ rules don't depend on cross-module list-merge ordering —
+      # tmpfiles' C type needs the target directory to already exist.
+      "d ${dir} 0755 root root -"
+      "C+ ${dir}/${kernelFile} 0644 root root - ${system.config.system.build.kernel}/${kernelFile}"
+      "C+ ${dir}/initrd 0644 root root - ${system.config.system.build.netbootRamdisk}/initrd"
+      "C+ ${dir}/netboot.ipxe 0644 root root - ${system.config.system.build.netbootIpxeScript}/netboot.ipxe"
+    ];
+in
+{
+  # Builds this flake's own installer netboot image (the same one
+  # `nix build .#pxe` produces) plus the vanilla NixOS minimal netboot image
+  # (`nix build .#pxe-minimal`), and stages both where menu.ipxe's
+  # :auto-installer / :nixos-minimal entries expect them, so the pxe-boot
+  # host is self-contained — no manual operator step to populate
+  # /srv/pxe/http after deploy.
+  systemd.tmpfiles.rules =
+    mkStageRules { dirName = "auto-installer"; system = netbootSystem; }
+    ++ mkStageRules { dirName = "nixos-minimal"; system = netbootMinimalSystem; };
+}

modules/raspi/mount-data.nix

@@ -1,26 +1,32 @@
-{ ... }:
+{ config, lib, vars, ... }:
 
 {
-fileSystems."/mnt/raspi" = {
+  fileSystems.${vars.raspiMountpoint} = {
-  device = "raspberrypi.tail13f623.ts.net:/home/raspi/raspi";
+    device = "${vars.raspberryPiHost}.${vars.tailnetDomain}:${vars.raspiNfsPath}";
-  fsType = "nfs4";
+    fsType = "nfs4";
-  options = [
+    options = [
-    "nofail"
+      "nofail"
-    "_netdev"
+      "_netdev"
-    "noatime"
+      "noatime"
 
-    # Don't mount until first access
+      # Explicitly use NFSv4.2 if supported
-    "x-systemd.automount"
+      "nfsvers=4.2"
+    ] ++ lib.optionals (!config.boot.isContainer) [
+      # `x-systemd.automount` never works inside a Linux container (LXC
+      # included) -- confirmed live on lxc-docker: systemd logs "Starting
+      # of <unit>.automount unsupported" and never mounts it. `nofail`
+      # above already keeps boot non-blocking there, so plain eager
+      # mounting is fine.
 
-    # Unmount after 10 min idle
+      # Don't mount until first access
-    "x-systemd.idle-timeout=600"
+      "x-systemd.automount"
 
-    # Give the Pi/Tailscale a little time to appear
+      # Unmount after 10 min idle
-    "x-systemd.device-timeout=10s"
+      "x-systemd.idle-timeout=600"
 
-    # Explicitly use NFSv4.2 if supported
+      # Give the Pi/Tailscale a little time to appear
-    "nfsvers=4.2"
+      "x-systemd.device-timeout=10s"
-  ];
+    ];
-};
+  };
 
 }

modules/remote-builder-client.nix

@@ -1,26 +0,0 @@
-{ pkgs, ... }:
-
-{
-  # Install the remote builder key on each client host (do not commit private keys):
-  #   sudo install -d -m 0700 /root/.ssh
-  #   sudo install -m 0600 ./nixremote /root/.ssh/nixremote
-  #   sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
-  nix.distributedBuilds = true;
-
-  nix.buildMachines = [
-    {
-      hostName = "nix-cache";
-      sshUser = "nixremote";
-      sshKey = "/root/.ssh/nixremote";
-      system = pkgs.stdenv.hostPlatform.system;
-      maxJobs = 4;
-      speedFactor = 2;
-      supportedFeatures = [ "nixos-test" "benchmark" "big-parallel" "kvm" ];
-    }
-  ];
-
-  nix.settings = {
-    builders-use-substitutes = true;
-    max-jobs = "auto";
-  };
-}

modules/rotate-traefik-logs.nix

@@ -1,20 +0,0 @@
-{ ... }:
-
-{
-      services.logrotate = {
-    enable = true;
-
-    settings = {
-      "/mnt/docker/volumes/traefik-data/logs/*.log" = {
-        daily = true;
-        size = "100M";
-        rotate = 20;
-        compress = true;
-        missingok = true;
-        notifempty = true;
-        copytruncate = true;
-      };
-
-     };
-  };
-}

modules/services/enable-rpcbind.nix

@@ -1,5 +1,5 @@
- { ... }:
+_:
 
- {
+{
- services.rpcbind.enable = true;
+  services.rpcbind.enable = true;
- }
+}

modules/services/nextcloud-cron-job.nix

@@ -1,22 +0,0 @@
-{ pkgs, ... }:
-
-{
-# Create nextcloud cron scheduled task
-systemd.services.nextcloud = {
-  description = "Nextcloud scheduled task";
-  script = ''${pkgs.bash}/bin/bash ~/docker/services-up.sh --profile nextcloud exec -u 33 nextcloud-webapp php ./cron.php'';
-  serviceConfig = {
-    Type = "oneshot";
-    User = "nixos";
-  };
-  path = with pkgs; [ docker docker-compose ];
-};
-
-systemd.timers.nextcloud = {
-  wantedBy = [ "timers.target" ];
-  timerConfig = {
-    OnCalendar = "*:0/5";
-    Persistent = true;
-  };
-};
-}

modules/services/zfs/auto-mount-volumes.nix

@@ -1,12 +1,12 @@
 { pkgs, boot, ... }:
 
 {
-boot.postBootCommands = ''
+  boot.postBootCommands = ''
-  echo "=== STARTING ZPOOL IMPORT ==="
+    echo "=== STARTING ZPOOL IMPORT ==="
-  ${pkgs.zfs_unstable}/bin/zpool import -a -N -d /dev/disk/by-path
+    ${pkgs.zfs_unstable}/bin/zpool import -a -N -d /dev/disk/by-path
-  ${pkgs.zfs_unstable}/bin/zpool status
+    ${pkgs.zfs_unstable}/bin/zpool status
-  ${pkgs.zfs_unstable}/bin/zfs mount -a
+    ${pkgs.zfs_unstable}/bin/zfs mount -a
-  ${pkgs.zfs_unstable}/bin/zfs list
+    ${pkgs.zfs_unstable}/bin/zfs list
-    echo "=== ZPOOL IMPORT COMPLETE ==="
+      echo "=== ZPOOL IMPORT COMPLETE ==="
-'';
+  '';
- }
+}

modules/services/zfs/enable-service.nix

@@ -1,16 +1,21 @@
 { pkgs, ... }:
 
- {
+{
-boot.supportedFilesystems = [ "zfs" ];
+  boot = {
-  boot.zfs.forceImportRoot = false;
+    supportedFilesystems = [ "zfs" ];
-  boot.zfs.package = pkgs.zfs_unstable;
+    zfs = {
-      services.zfs = {
+      forceImportRoot = false;
+      package = pkgs.zfs_unstable;
+      devNodes = "/dev/disk/by-id";
+    };
+  };
+
+  services.zfs = {
     autoScrub.enable = true;
     autoSnapshot.enable = true;
     trim.enable = true;
   };
 
-#systemd.services.zfs-import-cache.enable = true;
+  #systemd.services.zfs-import-cache.enable = true;
-systemd.services.zfs-mount.enable = true;
+  systemd.services.zfs-mount.enable = true;
-boot.zfs.devNodes = "/dev/disk/by-id";
+}
- }

modules/tailscale/enable-service.nix

@@ -1,5 +1,5 @@
-{ ... }:
+_:
 
 {
-    services.tailscale.enable = true;
+  services.tailscale.enable = true;
 }

modules/tailscale/exit-node.nix

@@ -1,12 +0,0 @@
-{ ... }:
-
-{
-  services.tailscale = {
-    enable = true;
-
-    extraUpFlags = [
-      "--advertise-exit-node"
-      "--advertise-routes=192.168.2.0/24"
-    ];
-  };
-}

modules/tailscale/subnet-router.nix

@@ -0,0 +1,35 @@
+{ pkgs, ... }:
+
+{
+  imports = [ ./enable-service.nix ];
+
+  services.tailscale = {
+    # Enables the sysctl forwarding settings subnet routers need;
+    # without this, --advertise-routes has no effect.
+    useRoutingFeatures = "server";
+
+    # Lets peers reach this node directly over the tailscale UDP port
+    # instead of relaying through DERP.
+    openFirewall = true;
+  };
+
+  # Tailscale recommends these ethtool flags on the uplink interface to get
+  # full UDP GRO throughput on subnet routers (https://tailscale.com/s/ethtool-config-udp-gro).
+  # The interface is derived from the default route so it works regardless of
+  # what the NIC is named on a given host.
+  systemd.services.tailscale-udp-gro = {
+    description = "Enable UDP GRO forwarding on uplink for Tailscale subnet router";
+    after = [ "network-online.target" ];
+    wants = [ "network-online.target" ];
+    wantedBy = [ "multi-user.target" ];
+    path = [ pkgs.ethtool pkgs.iproute2 ];
+    serviceConfig = {
+      Type = "oneshot";
+      RemainAfterExit = true;
+      ExecStart = pkgs.writeShellScript "tailscale-udp-gro" ''
+        NETDEV=$(ip -o route get 8.8.8.8 | cut -f 5 -d " ")
+        ethtool -K "$NETDEV" rx-udp-gro-forwarding on rx-gro-list off
+      '';
+    };
+  };
+}

modules/tailscale/ts-dns-forwarder.nix

@@ -0,0 +1,60 @@
+{ vars, ... }:
+
+{
+  # Run dnsmasq on the LAN interface as a forwarding-only resolver for
+  # *.ts.net (Tailscale MagicDNS names). FreeIPA's bind-dyndb-ldap
+  # cannot reach 100.100.100.100 (Tailscale's internal resolver) directly
+  # because the DC is not a Tailscale node. This host IS a Tailscale node
+  # and can reach 100.100.100.100 via its tailscale0 interface, so it
+  # acts as an intermediary: FreeIPA has a conditional forward zone for
+  # ts.net pointing here (vars.tailscaleRouterIp), and this dnsmasq
+  # instance forwards those queries onward to Tailscale's resolver.
+  #
+  # Configure FreeIPA once after deploying this host:
+  #   kinit admin
+  #   ipa dnsforwardzone-add ${vars.tailnetDomain} \
+  #     --forwarder=${vars.tailscaleRouterIp} \
+  #     --forward-policy=only
+  # Note: IPA refuses to shadow ts.net (a real public TLD); use the
+  # tailnet-specific subdomain (vars.tailnetDomain) instead.
+  services.dnsmasq = {
+    enable = true;
+    # NixOS's dnsmasq module defaults resolveLocalQueries to true, which adds
+    # 127.0.0.1 to networking.nameservers and makes dnsmasq bind to
+    # listen-address=127.0.0.1. This instance is not the host's local
+    # resolver — it only serves IPA's conditional forwarder for tailnet names.
+    # The host uses domainControllerIp directly (networking.nameservers in
+    # host.nix). Without this, all host DNS goes through dnsmasq, which has
+    # no upstream for general queries (no-resolv=true), breaking resolution.
+    resolveLocalQueries = false;
+    settings = {
+      # Listen only on the LAN interface — not tailscale0 or loopback.
+      # bind-interfaces prevents dnsmasq from binding to 0.0.0.0 and
+      # then filtering by interface later; combined with `interface` this
+      # ensures it genuinely listens only on eth0.
+      bind-interfaces = true;
+      interface = [ vars.lxcLanInterface ];
+
+      # Forward-only: no local /etc/hosts or /etc/resolv.conf reading,
+      # no negative caching of NXDOMAIN for names this instance doesn't
+      # serve. All ts.net queries come from FreeIPA's conditional forwarder
+      # and must be answered by Tailscale's resolver.
+      no-hosts = true;
+      no-resolv = true;
+
+      # Tailscale's internal "Quad100" resolver — reachable from any
+      # Tailscale node via the tailscale0 interface. Scoped to the
+      # specific tailnet subdomain (vars.tailnetDomain) rather than
+      # all of ts.net: FreeIPA refuses to shadow ts.net (a real public
+      # TLD with DNSimple nameservers) so the conditional forward zone
+      # in FreeIPA must use the tailnet-specific subdomain instead:
+      #   ipa dnsforwardzone-add ${vars.tailnetDomain} \
+      #     --forwarder=${vars.tailscaleRouterIp} \
+      #     --forward-policy=only
+      server = [ "/${vars.tailnetDomain}/100.100.100.100" ];
+    };
+  };
+
+  networking.firewall.allowedUDPPorts = [ 53 ];
+  networking.firewall.allowedTCPPorts = [ 53 ];
+}

modules/tor/enable-relay.nix

@@ -0,0 +1,35 @@
+{ pkgs, vars, ... }:
+
+{
+  services.tor = {
+    enable = true;
+
+    # Opens settings.ORPort (and DirPort, unset here) in the firewall —
+    # see the nixpkgs tor module's own networking.firewall.mkIf block.
+    openFirewall = true;
+
+    relay = {
+      enable = true;
+      # Plain middle/guard relay, not "exit" — relays onion traffic between
+      # other Tor nodes without ever making requests to the public internet
+      # on a user's behalf, avoiding the abuse complaints and legal exposure
+      # an exit node invites.
+      role = "relay";
+    };
+
+    settings.ORPort = vars.ports.torRelayOrPort;
+
+    # Unix control socket at /run/tor/control (GroupWritable, group "tor")
+    # -- what nyx below actually monitors the relay through. Nyx's own
+    # default control-socket path (/var/run/tor/control) resolves to the
+    # same place, so no extra nyx config is needed.
+    controlSocket.enable = true;
+  };
+
+  # Lets the primary user's shell session read/write the control socket
+  # above without being root -- otherwise nyx fails to authenticate against
+  # it at all.
+  users.users.${vars.primaryUser}.extraGroups = [ "tor" ];
+
+  environment.systemPackages = [ pkgs.nyx ];
+}

modules/traefik/rotate-logs.nix

@@ -0,0 +1,20 @@
+{ vars, ... }:
+
+{
+  services.logrotate = {
+    enable = true;
+
+    settings = {
+      "${vars.nfsShares.dockerVolumes.mountpoint}/traefik-data/logs/*.log" = {
+        daily = true;
+        size = vars.traefikLogRotate.maxSize;
+        rotate = vars.traefikLogRotate.keep;
+        compress = true;
+        missingok = true;
+        notifempty = true;
+        copytruncate = true;
+      };
+
+    };
+  };
+}

prepare.sh

@@ -1,30 +0,0 @@
-#create MBR table
-parted /dev/sda -- mklabel msdos
-#create nixos partition
-parted /dev/sda -- mkpart primary 1MB -8GB
-#set nixos partition to bootable
-parted /dev/sda -- set 1 boot on
-# create swap partition
-parted /dev/sda -- mkpart primary linux-swap -8GB 100%
-
-#format OS partition
-mkfs.ext4 -L nixos /dev/sda1
-#format swap
-mkswap -L swap /dev/sda2
-
-#activate swap
-swapon /dev/sda2
-
-#mount nixos partition
-mount /dev/disk/by-label/nixos /mnt
-export TMPDIR=/mnt/install-tmp
-mkdir -p /mnt/install-tmp
-#Generate config
-#nixos-generate-config --root /mnt/
-
-#copy customised configuration over
-#cp configuration.nix /mnt/etc/nixos/configuration.nix
-
-#nixos-install --no-root-passwd
-
-#reboot

remove-sensetive-info-refactor.md

@@ -1,134 +0,0 @@
-# Spec: Remove Sensitive Information from NixOS Flake
-
-## Goal
-
-Every secret currently readable in plaintext anywhere in this repo (working tree *and* git history) gets removed, replaced with `sops-nix`-managed encrypted references, and rotated. When this is done, the repo should be safe to make public without exposing anything about the systems it configures.
-
-Treat this as three sequential milestones. Do not start git history rewriting (Milestone 3) until Milestones 1 and 2 are fully verified and the flake still builds. This should be its own branch (`refactor/secrets`) until fully verified, then merged.
-
----
-
-## Milestone 1 — Audit
-
-Before touching anything, produce a complete inventory. Do not guess at scope — grep the whole tree and the whole history.
-
-1. Run a secret scanner across the working tree and full history. Use both, since they catch different things:
-   - `gitleaks detect --source . -v --log-opts="--all"` (scans history too)
-   - `trufflehog git file://. --since-commit=$(git rev-list --max-parents=0 HEAD) --only-verified=false`
-   If neither is installed, add them via a temporary `nix-shell -p gitleaks trufflehog` — don't install anything globally on the host.
-
-2. Manually grep for the categories below, since scanners miss config-specific patterns:
-   - `hashedPassword`, `password`, `initialPassword`, `initialHashedPassword` in any `users.users.*` block
-   - `age.secrets`, `sops.secrets` (if any partial secrets work already exists — check for it)
-   - PSK / `preSharedKey`, `privateKeyFile` inline values (vs. file references) for WireGuard
-   - `authKey`, `apiToken`, `api_key`, `token =`, `secret =` in service modules (Tailscale, Cloudflare, backup tools, etc.)
-   - SSH private key material: search for `BEGIN OPENSSH PRIVATE KEY` / `BEGIN RSA PRIVATE KEY` literals
-   - TLS cert/key pairs committed under e.g. `secrets/`, `certs/`, `pki/`
-   - Real name, personal email, home address, or anything in comments/hostnames that maps a machine to your physical identity or network layout (e.g. hostnames like `wayne-desktop`, static LAN IPs, ISP-identifying info)
-   - `.env` files, `secrets.nix`, `secrets.yaml`, or any file that looks like it was meant to be gitignored but wasn't
-
-3. Produce `secrets-inventory.md` (temporary, delete before finishing) listing: file path, line, secret type, and which host/service it belongs to. This becomes the checklist for Milestone 2 — every row must be either migrated to sops or deleted, with nothing left unaccounted for.
-
----
-
-## Milestone 2 — Migrate to sops-nix
-
-### 2.1 Set up sops-nix
-
-1. Add the flake input:
-   ```nix
-   sops-nix.url = "github:Mic92/sops-nix";
-   sops-nix.inputs.nixpkgs.follows = "nixpkgs";
-   ```
-2. Import `sops-nix.nixosModules.sops` into each host's module list (or into a shared `common.nix` if all hosts use it).
-3. Generate an age keypair **per host** (not one shared key for everything — a compromised host shouldn't decrypt every other host's secrets):
-   ```
-   nix-shell -p age --run "age-keygen -o /var/lib/sops-nix/key.txt"
-   ```
-   Print the public key (`age-keygen -y`) for each host — you'll need it for `.sops.yaml`.
-4. Also generate one age key for yourself (your admin workstation) so you can edit secrets without needing to SSH into a host: store it at `~/.config/sops/age/keys.txt`, back it up somewhere outside this repo (password manager, offline). **If this key is lost, every secret encrypted with it is unrecoverable — losing the age key is equivalent to losing the secrets.**
-5. Create `.sops.yaml` at the repo root defining creation rules: which age public keys can decrypt which secrets files, keyed by path regex, so e.g. `secrets/hostA.yaml` is decryptable by your admin key + hostA's key, `secrets/hostB.yaml` by your admin key + hostB's key.
-
-### 2.2 Migrate each secret category from the inventory
-
-For each row in `secrets-inventory.md`:
-
-- **Password hashes**: generate hash with `mkpasswd -m sha-512` (or `bcrypt` if your setup wants that), store under `sops.secrets."<name>/hashedPassword"`, reference via `users.users.<name>.hashedPasswordFile = config.sops.secrets."<name>/hashedPassword".path;`. Do not put the *plaintext* password anywhere, only the hash, and only the hash goes into the encrypted sops file.
-- **API tokens / auth keys**: move the raw value into the per-host sops YAML, reference in the module via `config.sops.secrets."<service>/token".path` — most NixOS service modules that take a token also accept a `*File` variant (e.g. `environmentFile`, `tokenFile`); use that instead of passing the value directly.
-- **Private keys / certs**: move the PEM/key content wholesale into a sops secret, output as a file with appropriate `sops.secrets.<name>.path`, `owner`, `mode`, `restartUnits` so the depending service (sshd, wireguard, nginx) reloads when the secret changes.
-- **Personal/identifying info**: this doesn't belong in sops (it's not "secret," it's just information you don't want public). Replace real names/emails with placeholders or move to a small untracked `local.nix` that's `.gitignore`'d and imported conditionally, with a documented template (`local.nix.example`) committed instead.
-
-### 2.3 Verify before moving on
-
-- `nixos-rebuild dry-build --flake .#<host>` succeeds for every host.
-- `sudo nixos-rebuild switch --flake .#<host>` on at least one real machine (or a VM) confirms secrets decrypt and services start.
-- Confirm decrypted secrets land under `/run/secrets/` (not the Nix store — anything placed in `/nix/store` is world-readable by design, so sops-nix's runtime-only placement is the whole point; double check no module accidentally pulls a secret path into a store-built config file).
-- Re-run the grep/scanner sweep from Milestone 1 against the *working tree only* (not history yet) — it should now come back clean.
-
----
-
-## Milestone 3 — Scrub git history
-
-Do this only after Milestone 2 is merged to your main branch and confirmed working, since it rewrites every commit SHA from the point of the earliest offending commit onward.
-
-**This is destructive and irreversible on your local clone. Back up first:**
-```
-cp -r /path/to/nixos-repo /path/to/nixos-repo-backup-$(date +%F)
-```
-
-1. Install `git-filter-repo` (not the older `git filter-branch` / BFG — filter-repo is the currently maintained, faster, safer tool):
-   ```
-   nix-shell -p git-filter-repo
-   ```
-2. Use the `secrets-inventory.md` list to build a list of literal strings/paths to strip. Two approaches, use both:
-   - Path-based: if whole files were secret (e.g. `secrets.nix`, a `.env`, a private key file), remove them entirely from history:
-     ```
-     git filter-repo --path secrets.nix --path .env --invert-paths
-     ```
-   - Value-based: for secrets embedded inline in files you're keeping (not deleting the whole file), use `--replace-text` with a file listing each literal secret string to replace with `***REMOVED***`:
-     ```
-     git filter-repo --replace-text expressions.txt
-     ```
-3. After filtering, verify: run the Milestone 1 scanners again against full history (`--log-opts="--all"`). They must come back clean.
-4. Force-push the rewritten history:
-   ```
-   git push origin --force --all
-   git push origin --force --tags
-   ```
-5. **Every other clone of this repo (other machines, WSL instances, CI) must be deleted and re-cloned fresh** — a `git pull` against rewritten history will not work cleanly and risks resurrecting the old commits. Don't try to reconcile old clones; throw them away and re-clone.
-6. If this repo has ever been pushed to a public host (GitHub, etc.) or a fork/mirror exists, treat every secret that was ever in history as **permanently compromised regardless of the rewrite** — caches, forks, and Wayback-style archives can retain old commits indefinitely. History scrubbing prevents *future* exposure via `git clone`; it does not undo past exposure.
-
----
-
-## Milestone 4 — Rotate everything
-
-Because the secrets were exposed in history (even briefly, even in a private repo), the migration is not complete until every credential in the inventory has been **rotated**, not just re-encrypted. Re-encrypting an already-leaked value protects it going forward but doesn't undo the leak.
-
-For each row in the original inventory:
-- Password hashes → change the actual account password, regenerate the hash, update the sops file.
-- API tokens/auth keys → revoke the old token in the issuing service's dashboard (Cloudflare, Tailscale, backup provider, etc.) and generate a new one.
-- SSH/WireGuard private keys → generate new keypairs, update the corresponding public key wherever it's trusted (authorized_keys, peer configs, etc.), retire the old ones.
-- TLS certs → reissue if the private key was exposed.
-
-Keep `secrets-inventory.md` open during this step and check off each row as rotated. Delete the file only once every row is checked off — it should not be committed.
-
----
-
-## Ongoing prevention
-
-Add a pre-commit hook (or a `nix flake check` step) running `gitleaks protect --staged` so a secret can't be committed again by accident. Document in the repo README (briefly) that new secrets go through `sops <file>` to edit, never as plaintext in a tracked file.
-
----
-
-## Definition of done
-
-- [ ] Milestone 1 inventory complete and reviewed
-- [ ] All hosts have per-host age keys; admin key backed up outside the repo
-- [ ] Every inventoried secret migrated to sops-nix, referenced via `*File`/`sops.secrets.*.path`, nothing plaintext in the working tree
-- [ ] `nixos-rebuild dry-build` and at least one real `switch` verified per host
-- [ ] Working-tree scanner sweep clean
-- [ ] History rewritten with `git-filter-repo`, force-pushed, full-history scanner sweep clean
-- [ ] All other clones deleted and re-cloned from the rewritten history
-- [ ] Every credential in the original inventory rotated (not just re-encrypted)
-- [ ] Pre-commit secret scanning hook added
-- [ ] `secrets-inventory.md` deleted from the working directory (never committed)

scripts/bump-nixpkgs-release.sh

@@ -0,0 +1,134 @@
+#!/usr/bin/env bash
+# Bumps the NixOS release branch this flake tracks — flake.nix's
+# `nixpkgs.url` and `home-manager.url` — in one place, via targeted
+# substitution of just those two lines. Deliberately does NOT touch any
+# `system.stateVersion` anywhere in the repo: per NixOS's own docs, that
+# value must stay fixed at whatever it was on a host's first install (it
+# pins on-disk data-format defaults, not "which nixpkgs release am I on"),
+# so it's never something a channel bump should follow.
+#
+# scripts/codex-maintenance.sh's own `nixos-25.11` pin (used only to fetch
+# nixpkgs-fmt/statix — see CLAUDE.md) is a separate, independently-versioned
+# reference on purpose: it doesn't have to track the flake's own nixpkgs
+# input, since the tooling just needs to build, not match. Bump it with
+# --tooling if you want it moved too; the default run leaves it alone.
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/.." && pwd)"
+flake_nix="${repo_root}/flake.nix"
+maintenance_sh="${repo_root}/scripts/codex-maintenance.sh"
+claude_md="${repo_root}/CLAUDE.md"
+
+usage() {
+  cat <<EOF
+Usage: $0 <release> [--tooling <release>]
+
+  <release>            New NixOS release for flake.nix's nixpkgs.url and
+                        home-manager.url, e.g. 26.11
+  --tooling <release>  Also bump scripts/codex-maintenance.sh's separate
+                        nixpkgs-fmt/statix pin (and its mention in
+                        CLAUDE.md) to this release. Independent of the
+                        first argument — pass the same value if you want
+                        both in sync, a different one if you don't.
+
+Examples:
+  $0 26.11
+  $0 26.11 --tooling 26.11
+EOF
+}
+
+release_re='^[0-9]{2}\.(05|11)$'
+
+if [[ $# -eq 0 || "$1" == "-h" || "$1" == "--help" ]]; then
+  usage
+  exit 0
+fi
+
+new_release="$1"
+shift
+
+tooling_release=""
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+  --tooling)
+    tooling_release="${2:?--tooling requires a release argument}"
+    shift 2
+    ;;
+  *)
+    echo "Unknown argument: $1" >&2
+    usage >&2
+    exit 1
+    ;;
+  esac
+done
+
+check_release_format() {
+  local release="$1"
+  if [[ ! "$release" =~ $release_re ]]; then
+    echo "ERROR: '$release' doesn't look like a NixOS release (expected e.g. 26.11)" >&2
+    exit 1
+  fi
+}
+
+check_branch_exists() {
+  local repo_url="$1" branch="$2"
+  echo "Checking '$branch' exists on $repo_url..."
+  if ! git ls-remote --exit-code --heads "$repo_url" "$branch" >/dev/null; then
+    echo "ERROR: branch '$branch' not found on $repo_url. Typo, or not cut yet?" >&2
+    exit 1
+  fi
+}
+
+check_release_format "$new_release"
+
+current_release="$(grep -oE 'nixos-[0-9]{2}\.[0-9]{2}' "$flake_nix" | head -1 | sed 's/^nixos-//')"
+if [[ -z "$current_release" ]]; then
+  echo "ERROR: couldn't find flake.nix's current nixpkgs release" >&2
+  exit 1
+fi
+
+if [[ "$current_release" == "$new_release" ]]; then
+  echo "flake.nix is already on $new_release."
+else
+  echo "Bumping flake.nix's nixpkgs/home-manager release: $current_release -> $new_release"
+  check_branch_exists "https://github.com/NixOS/nixpkgs.git" "nixos-$new_release"
+  check_branch_exists "https://github.com/nix-community/home-manager.git" "release-$new_release"
+
+  sed -i \
+    -e "s|github:NixOS/nixpkgs/nixos-${current_release}|github:NixOS/nixpkgs/nixos-${new_release}|" \
+    -e "s|github:nix-community/home-manager/release-${current_release}|github:nix-community/home-manager/release-${new_release}|" \
+    "$flake_nix"
+
+  echo "Updated:"
+  grep -n "nixos-${new_release}\|release-${new_release}" "$flake_nix"
+fi
+
+if [[ -n "$tooling_release" ]]; then
+  check_release_format "$tooling_release"
+
+  current_tooling_release="$(grep -oE 'nixos-[0-9]{2}\.[0-9]{2}' "$maintenance_sh" | head -1 | sed 's/^nixos-//')"
+
+  if [[ "$current_tooling_release" == "$tooling_release" ]]; then
+    echo "codex-maintenance.sh's tooling pin is already on $tooling_release."
+  else
+    echo "Bumping codex-maintenance.sh's nixpkgs-fmt/statix pin: $current_tooling_release -> $tooling_release"
+    check_branch_exists "https://github.com/NixOS/nixpkgs.git" "nixos-$tooling_release"
+
+    sed -i "s|github:NixOS/nixpkgs/nixos-${current_tooling_release}|github:NixOS/nixpkgs/nixos-${tooling_release}|g" \
+      "$maintenance_sh"
+    sed -i "s|nixos-${current_tooling_release}|nixos-${tooling_release}|g" \
+      "$claude_md"
+
+    echo "Updated:"
+    grep -n "nixos-${tooling_release}" "$maintenance_sh" "$claude_md"
+  fi
+fi
+
+echo
+echo "flake.lock still points at the old input revisions until refreshed. Either:"
+echo "  nix flake update nixpkgs home-manager   # just these two inputs"
+echo "  nix flake update                        # everything — see docs/flake-lock-automation.md"
+echo
+echo "Then run 'bash scripts/codex-maintenance.sh --full-check --dry-run' before"
+echo "committing — a channel bump can shift option defaults across every host,"
+echo "and only --dry-run actually builds anything to catch that."

scripts/codex-maintenance.sh

@@ -1,22 +1,73 @@
 #!/usr/bin/env bash
+# Validation entry point for CI and local/agent review.
+#
+# Default mode (what CI runs on every push/PR): fmt-check, statix, and eval
+# are scoped to files that actually changed against a base ref, plus
+# whichever hosts/packages those changes can affect. This exists because
+# the unscoped sweep below is slow enough to time out CI runners -- see
+# --full-check.
+#
+# --full-check: the historical full sweep (every host, every package,
+# fmt --check ./statix check . over the whole tree). Slow -- minutes, not
+# seconds. CI never passes this; run it locally before a release or after
+# touching modules/common/*, flake.nix, or variables.nix if you want extra
+# confidence beyond what the changed-files scope already covers for those
+# paths (see below).
+#
+# --dry-run: adds `nix build --dry-run --no-link` for whatever scope is
+# active (changed-files scope by default, full scope under --full-check).
+#
+# Per-host/per-package eval and dry-run build calls run concurrently (see
+# scripts/lib/nix-parallel.sh) since they're independent of each other.
+# Concurrency defaults to core count capped by available memory (~1GB/job)
+# rather than plain core count, since each concurrent `nix eval` evaluates a
+# whole NixOS system closure and can OOM a small/memory-constrained CI
+# runner otherwise; override via NIX_PARALLEL_JOBS if a runner has more (or
+# less) room than that estimate assumes.
 set -euo pipefail
 
-export NIX_CONFIG="${NIX_CONFIG:-}
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-experimental-features = nix-command flakes
+# shellcheck source=lib/nix-bootstrap.sh
-accept-flake-config = false
+source "${script_dir}/lib/nix-bootstrap.sh"
-warn-dirty = false
+# shellcheck source=lib/nix-eval.sh
-"
+source "${script_dir}/lib/nix-eval.sh"
+# shellcheck source=lib/nix-parallel.sh
+source "${script_dir}/lib/nix-parallel.sh"
 
-MODE="${1:-validate}"
+repo_root="$(cd "${script_dir}/.." && pwd)"
+cd "$repo_root"
 
-ensure_nix_profile() {
+full_check=false
-  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+dry_run=false
-    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+
-  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+usage() {
-    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
+  cat <<'EOF'
-  fi
+Usage: scripts/codex-maintenance.sh [--full-check] [--dry-run]
+
+  --full-check  Run the full sweep: fmt-check and statix over the whole
+                repo, eval every host and package. Slow. Never run by CI.
+  --dry-run     Additionally run `nix build --dry-run --no-link` for
+                whatever scope is active.
+
+With neither flag (the CI default), fmt-check/statix/eval are scoped to
+files changed against a base ref (env MAINT_BASE_SHA, else the PR base,
+else HEAD^), plus the hosts/packages those changes can affect.
+EOF
 }
 
+for arg in "$@"; do
+  case "$arg" in
+    --full-check) full_check=true ;;
+    --dry-run) dry_run=true ;;
+    -h|--help) usage; exit 0 ;;
+    *)
+      echo "Unknown argument: $arg" >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+done
+
 ensure_nix_profile
 
 if ! command -v nix >/dev/null 2>&1; then
@@ -24,13 +75,6 @@ if ! command -v nix >/dev/null 2>&1; then
   exit 127
 fi
 
-hosts_json="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames)"
-hosts="$(echo "$hosts_json" | jq -r '.[]')"
-
-echo "Hosts:"
-echo "$hosts"
-
-echo
 echo "Checking for obvious committed secrets..."
 if grep -RInE 'github_pat_|ghp_|access-tokens|hashedPassword[[:space:]]*=' \
   --exclude-dir=.git \
@@ -42,28 +86,235 @@ else
   echo "No obvious token patterns found."
 fi
 
+mapfile -t all_hosts < <(list_flake_targets .)
+mapfile -t all_packages < <(nix eval --json "${NIX_EVAL_FLAGS[@]}" .#packages.x86_64-linux --apply builtins.attrNames | jq -r '.[]')
+
+# host_targets_for_dir <hosts-subdir-name>
+# Prints the nixosConfigurations target names whose hostPath is
+# ./hosts/<dir>/host.nix, derived straight from flake.nix's generatedTargets
+# (one mkTarget { ... } call per line) rather than a hand-maintained table,
+# so it can't drift the way a copied mapping would.
+host_targets_for_dir() {
+  local dir="$1"
+  grep -oE '^[[:space:]]*[A-Za-z0-9_-]+ = mkTarget \{[^}]*hostPath = \./hosts/'"${dir}"'/host\.nix;[^}]*\};' flake.nix \
+    | sed -E 's/^[[:space:]]*([A-Za-z0-9_-]+) = mkTarget.*/\1/' \
+    || true
+}
+
+declare -a changed_files=()
+scope_desc="full repo"
+
+if ! $full_check; then
+  resolve_base_ref() {
+    if [[ -n "${MAINT_BASE_SHA:-}" ]] && git cat-file -e "${MAINT_BASE_SHA}^{commit}" 2>/dev/null; then
+      echo "$MAINT_BASE_SHA"
+      return
+    fi
+    if git rev-parse --verify -q HEAD^ >/dev/null 2>&1; then
+      echo "HEAD^"
+      return
+    fi
+    git hash-object -t tree /dev/null
+  }
+
+  base_ref="$(resolve_base_ref)"
+  echo
+  echo "Changed-files scope: diffing against ${base_ref}"
+  mapfile -t changed_files < <(git diff --name-only --diff-filter=ACMR "$base_ref" -- . | sort -u)
+
+  if [[ ${#changed_files[@]} -eq 0 ]]; then
+    echo "No changed files detected."
+  else
+    printf '  %s\n' "${changed_files[@]}"
+  fi
+  scope_desc="changed files only (base: ${base_ref})"
+fi
+
+# Whole-tree fmt/lint always run under --full-check; otherwise scoped below.
+declare -a changed_nix_files=()
+for f in "${changed_files[@]:-}"; do
+  [[ "$f" == *.nix && -f "$f" ]] && changed_nix_files+=("$f")
+done
+
 echo
 echo "Checking Nix formatting with nixpkgs-fmt..."
-nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .
+if $full_check; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .
+elif [[ ${#changed_nix_files[@]} -gt 0 ]]; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check "${changed_nix_files[@]}"
+else
+  echo "No changed .nix files; skipping."
+fi
 
 echo
 echo "Running statix lint..."
-nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#statix -- check .
+if $full_check; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#statix -- check .
+elif [[ ${#changed_nix_files[@]} -gt 0 ]]; then
+  for f in "${changed_nix_files[@]}"; do
+    nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#statix -- check "$f"
+  done
+else
+  echo "No changed .nix files; skipping."
+fi
+
+# Figure out which hosts/packages this run needs to eval (and, under
+# --dry-run, build). full_check always means "everything"; otherwise a
+# change to flake.nix/flake.lock/variables.nix/modules/common/* (repo-wide
+# inputs) or to any other modules/*.nix outside platforms//build-types
+# (whose blast radius isn't safely inferable from the path alone -- see
+# CLAUDE.md's "Grep modules/build-types/*.nix for each build type's imports
+# list") also falls back to everything, on the same reasoning CLAUDE.md
+# already gives interactive sessions for when to run the full sweep.
+# Anything more targeted -- a host.nix, a platform module, a build-type
+# module -- narrows to just the hosts it can affect.
+declare -A affected_hosts=()
+eval_packages=false
+
+if $full_check; then
+  for h in "${all_hosts[@]}"; do affected_hosts[$h]=1; done
+  eval_packages=true
+else
+  full_fallback=false
+  for f in "${changed_files[@]:-}"; do
+    case "$f" in
+      flake.nix|flake.lock|variables.nix|modules/common/*)
+        full_fallback=true
+        ;;
+    esac
+  done
+
+  if ! $full_fallback; then
+    for f in "${changed_files[@]:-}"; do
+      case "$f" in
+        hosts/*/*)
+          hostdir="${f#hosts/}"
+          hostdir="${hostdir%%/*}"
+          while IFS= read -r t; do
+            [[ -n "$t" ]] && affected_hosts[$t]=1
+          done < <(host_targets_for_dir "$hostdir")
+          ;;
+        modules/platforms/*.nix)
+          platform="$(basename "$f" .nix)"
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == "${platform}-"* ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/build-types/*.nix)
+          buildtype="$(basename "$f" .nix)"
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == *"-${buildtype}" ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/installer/*)
+          # iso.nix (imported by both the "installer" nixosConfigurations
+          # target and netbootSystem, which backs packages.pxe) pulls in
+          # common.nix, so a common.nix change reaches all three.
+          affected_hosts[installer]=1
+          eval_packages=true
+          ;;
+        modules/pxe-boot/*)
+          # stage-installer-artifacts.nix is imported by
+          # modules/build-types/pxe-boot.nix only -- same blast radius as a
+          # build-types/*.nix change, not a packages one.
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == *"-pxe-boot" ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/*)
+          full_fallback=true
+          ;;
+      esac
+    done
+  fi
+
+  if $full_fallback; then
+    echo
+    echo "Changed files affect shared config; falling back to evaluating every host/package."
+    for h in "${all_hosts[@]}"; do affected_hosts[$h]=1; done
+    eval_packages=true
+  fi
+fi
+
+mapfile -t hosts < <(for h in "${!affected_hosts[@]}"; do echo "$h"; done | sort)
 
 echo
-echo "Evaluating host toplevel derivations..."
+echo "Checking nix-cache host key for drift..."
-for host in $hosts; do
+if bash "${script_dir}/secrets/sync-nix-cache-host-key.sh" --check; then
-  echo "==> $host"
+  :
-  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
+else
-done
+  drift_status=$?
+  if [[ "$drift_status" -eq 2 ]]; then
+    echo "nix-cache unreachable from here -- skipping host-key drift check."
+  else
+    echo "WARNING: nix-cache's host key has drifted from variables.nix (see above)." >&2
+    echo "  Run 'bash scripts/secrets/sync-nix-cache-host-key.sh' to fix." >&2
+  fi
+fi
 
-if [[ "$MODE" == "dry-run" ]]; then
+echo
-  echo
+if [[ ${#hosts[@]} -eq 0 ]]; then
-  echo "Running dry-run builds for all hosts. This will not create result symlinks."
+  echo "No hosts affected by changed files; skipping host eval."
-  for host in $hosts; do
+else
-    echo "==> Dry-run build: $host"
+  echo "Evaluating host toplevel derivations (${scope_desc}, up to ${NIX_PARALLEL_JOBS} at a time)..."
-    nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel"
+  # lxc-* hosts deploy via a directly pct-restore-able tarball instead of
+  # nixos-install (see docs/auto-installer.md); proxmox-* hosts can
+  # alternatively be built as a standalone disk image (see
+  # docs/proxmox-images.md). Both are otherwise-unvalidated buildable
+  # surface, easy to silently break without this.
+  declare -a host_eval_jobs=()
+  for host in "${hosts[@]}"; do
+    host_eval_jobs+=("${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel.drvPath")
+    case "$host" in
+      lxc-*)
+        host_eval_jobs+=("${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball.drvPath")
+        ;;
+      proxmox-*)
+        host_eval_jobs+=("${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath")
+        ;;
+    esac
   done
+  run_nix_parallel host_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+fi
+
+echo
+if ! $eval_packages; then
+  echo "No packages affected by changed files; skipping package eval."
+else
+  echo "Evaluating buildable packages (up to ${NIX_PARALLEL_JOBS} at a time)..."
+  declare -a package_eval_jobs=()
+  for pkg in "${all_packages[@]}"; do
+    package_eval_jobs+=("packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
+  done
+  run_nix_parallel package_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+fi
+
+if $dry_run; then
+  echo
+  echo "Running dry-run builds for the active scope (up to ${NIX_PARALLEL_JOBS} at a time). This will not create result symlinks."
+  declare -a host_build_jobs=()
+  for host in "${hosts[@]:-}"; do
+    host_build_jobs+=("Dry-run build: ${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel")
+    case "$host" in
+      lxc-*)
+        host_build_jobs+=("Dry-run build: ${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball")
+        ;;
+      proxmox-*)
+        host_build_jobs+=("Dry-run build: ${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript")
+        ;;
+    esac
+  done
+  run_nix_parallel host_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+
+  if $eval_packages; then
+    echo
+    echo "Running dry-run builds for packages."
+    declare -a package_build_jobs=()
+    for pkg in "${all_packages[@]}"; do
+      package_build_jobs+=("Dry-run build: packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
+    done
+    run_nix_parallel package_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+  fi
 fi
 
 echo

scripts/codex-setup.sh

@@ -1,19 +1,11 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-export NIX_CONFIG="${NIX_CONFIG:-}
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-experimental-features = nix-command flakes
+# shellcheck source=lib/nix-bootstrap.sh
-accept-flake-config = false
+source "${script_dir}/lib/nix-bootstrap.sh"
-warn-dirty = false
+# shellcheck source=lib/nix-eval.sh
-"
+source "${script_dir}/lib/nix-eval.sh"
-
-ensure_nix_profile() {
-  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
-    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
-  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
-    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
-  fi
-}
 
 install_nix_if_missing() {
   if command -v nix >/dev/null 2>&1; then
@@ -49,6 +41,17 @@ warn-dirty = false
 build-users-group = nixbld
 EOF
 
+    # The official installer's single-user root path still shells out to
+    # `sudo` to create /nix even though it already knows it's running as
+    # root -- confirmed live against a sudo-less minimal Debian/Proxmox
+    # node, where it fails with "sudo: not found" and prints this exact
+    # mkdir/chown as the manual fix. Pre-create it so that branch of the
+    # installer is skipped entirely.
+    if [ ! -d /nix ]; then
+      mkdir -m 0755 /nix
+      chown root /nix
+    fi
+
     sh <(curl -L https://nixos.org/nix/install) --no-daemon
   else
     sh <(curl -L https://nixos.org/nix/install) --no-daemon
@@ -65,6 +68,7 @@ cat > "$HOME/.config/nix/nix.conf" <<'EOF'
 experimental-features = nix-command flakes
 accept-flake-config = false
 warn-dirty = false
+build-users-group =
 EOF
 
 echo "Nix version:"
@@ -79,13 +83,6 @@ if ! command -v jq >/dev/null 2>&1; then
 fi
 
 echo "Available NixOS hosts:"
-hosts="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]')"
+list_flake_targets .
-echo "$hosts"
 
-echo "Evaluating all host toplevel derivations..."
+echo "Codex setup complete. Run bash scripts/codex-maintenance.sh to validate changes."
-for host in $hosts; do
-  echo "==> Evaluating $host"
-  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
-done
-
-echo "Codex setup complete."

scripts/create-linode-installer-disk.sh

@@ -1,9 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-#boot to rescue mode
-# set root password
-scp $RESULT_ISO root@$LINODE_IP:/tmp/nixos-auto.iso
-
-#in LISH or ssh to rescue mode
-dd if=/tmp/nixos.iso of=/dev/sda bs=4M status=progress conv=fsync

scripts/env.sh

@@ -0,0 +1,191 @@
+#!/usr/bin/env bash
+# Shared config for scripts/*.sh. Source this instead of hardcoding a
+# second copy of these values in every script:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/env.sh"
+# Every variable can still be overridden per-invocation via the
+# environment (e.g. PROXMOX_STORAGE=tank-nvme ./scripts/proxmox/create-proxmox-resource.sh ...)
+# since each one only sets a default if unset.
+
+# Two SSH-reachable Proxmox nodes exist on the LAN:
+#   - pve1.sweet.home      -- production. Real, live VMs/containers.
+#   - pve-test.sweet.home  -- sandbox/test node, for scratch VMs/containers
+#     that don't belong on production.
+#
+# PROXMOX_HOST is what scripts/proxmox/create-proxmox-resource.sh actually
+# targets by default -- overridable per-invocation with --node <hostname>,
+# or per-variable as usual (e.g. PROXMOX_HOST=$PVE_TEST_HOST). It defaults
+# to production, matching this repo's behavior before pve-test existed --
+# see CLAUDE.md's "Two Proxmox nodes" section for the policy on which
+# situations should target which node (in particular: Claude defaults to
+# pve-test, not this variable's own default, unless explicitly told
+# otherwise).
+: "${PVE1_HOST:=pve1.sweet.home}"
+: "${PVE_TEST_HOST:=pve-test.sweet.home}"
+: "${PROXMOX_HOST:=$PVE1_HOST}"
+: "${PROXMOX_SSH_USER:=wayne}"
+
+# Where this flake repo lives on the Proxmox node itself.
+# scripts/proxmox/create-proxmox-resource.sh builds images directly on the node
+# instead of transferring them over the network -- it clones the repo here
+# (from this checkout's own `origin` remote) the first time it doesn't
+# find it, installing build tooling via scripts/codex-setup.sh, then
+# `git pull`s it before every subsequent build.
+: "${PROXMOX_REMOTE_REPO_DIR:=/home/${PROXMOX_SSH_USER}/nixos}"
+
+# Storage pool names -- Proxmox's own stock-install defaults, but this
+# varies a lot by setup (ZFS pool name, custom LVM-thin volume, etc.).
+# Verify with `pvesm status` on the node and correct these if wrong.
+: "${PROXMOX_STORAGE:=local-zfs}"     # VM disks / CT rootfs
+: "${PROXMOX_ISO_STORAGE:=local}"     # uploaded images/ISOs/CT templates
+
+: "${PROXMOX_BRIDGE:=vmbr0}"
+
+# Fallback resource sizing when a script doesn't get --cores/--memory.
+: "${PROXMOX_DEFAULT_CORES:=2}"
+: "${PROXMOX_DEFAULT_MEMORY_MB:=2048}"
+
+# `pct create` (unlike `pct restore`) requires an explicit rootfs size --
+# no backup metadata to infer it from. Matches Proxmox's own GUI default.
+: "${PROXMOX_DEFAULT_LXC_DISK_GB:=8}"
+
+# `pct create --memory` only sets RAM -- swap is a wholly separate
+# parameter that otherwise silently stays at Proxmox's own 512M default
+# regardless of --memory (confirmed: creating with --memory 2048 left
+# swap at 512). create-proxmox-resource.sh defaults --swap to whatever
+# --memory resolves to at runtime rather than a static value here, so it
+# tracks a --memory picked at the CLI too, not just the default above.
+
+# Required for a modern (v247+) systemd guest to actually boot as an
+# unprivileged container: systemd's routine use of nested user namespaces
+# and credential mounts (LoadCredential=, DynamicUser=, etc. -- used even
+# by plain getty units) gets denied by AppArmor's default LXC confinement
+# without these. Confirmed live: without them, every getty unit
+# crash-loops on a denied `/run/credentials/*` mount every ~3s (visible
+# as garbage on the console) and core services like nsncd fail the same
+# way on userns_create; system.build.tarball never finishes activating.
+#
+# mount=nfs;nfs4: without it, AppArmor blanket-denies the `nfs`/
+# `rpc_pipefs` mount syscalls any NFS client share needs -- confirmed
+# live on lxc-docker (which mounts several, see modules/docker/mount-data.nix
+# and modules/raspi/mount-data.nix): `mount: /var/lib/nfs/rpc_pipefs:
+# permission denied`. Harmless to grant on lxc targets that don't mount
+# NFS at all -- it only widens what the container is *allowed* to mount,
+# nothing here forces a mount to happen.
+: "${PROXMOX_DEFAULT_LXC_FEATURES:=nesting=1,keyctl=1,mount=nfs;nfs4}"
+
+export PVE1_HOST PVE_TEST_HOST PROXMOX_HOST PROXMOX_SSH_USER PROXMOX_STORAGE \
+  PROXMOX_ISO_STORAGE PROXMOX_BRIDGE PROXMOX_DEFAULT_CORES \
+  PROXMOX_DEFAULT_MEMORY_MB PROXMOX_DEFAULT_LXC_DISK_GB \
+  PROXMOX_DEFAULT_LXC_FEATURES PROXMOX_REMOTE_REPO_DIR
+
+# Matches variables.nix's nixCacheHost -- update both if it ever changes.
+: "${NIX_CACHE_HOST:=nix-cache}"
+export NIX_CACHE_HOST
+
+# Matches variables.nix's lanDomain (the Gitea host this flake's own repo
+# is served from -- see scripts/installer/auto-install.sh's FLAKE_BASE_URL)
+# -- update both if it ever changes.
+: "${LAN_DOMAIN:=gitea.lan.ddnsgeek.com}"
+export LAN_DOMAIN
+
+# Matches variables.nix's homeDomain -- the base LAN domain for service
+# subdomains, FreeIPA Kerberos realm, and host FQDNs.
+: "${HOME_DOMAIN:=sweet.home}"
+export HOME_DOMAIN
+
+# Matches variables.nix's ipaServer -- the FreeIPA server hostname.
+# scripts/ipa/create-nixos-ipa-host-account.sh SSHes here to run
+# ipa host-add and ipa-getkeytab.
+: "${IPA_SERVER:=domain-controller.sweet.home}"
+export IPA_SERVER
+
+# nix_extra_opts: call as a plain statement (NOT inside $(...)/<(...) --
+# that forks a subshell, and the whole point is exporting a decision back
+# into *this* shell) to populate the global NIX_OPTS array with whatever
+# extra `nix`/`nix-shell` CLI options are needed to avoid nix-cache when
+# it's unreachable:
+#   nix_extra_opts
+#   nix build "${NIX_OPTS[@]}" ...
+#
+# Without this, every single `nix eval`/`nix build` call retries each
+# store path against a dead substituter up to 5 times with backoff
+# (confirmed: ~15s+ per lookup even with a short connect-timeout, because
+# nix's own retry count isn't controllable that way), and separately
+# tries it as a remote builder too -- both fail independently, so both
+# are checked.
+#
+# Checked with a single fast `curl`/TCP probe (bypassing nix's retry logic
+# entirely) the first time this is called in a given process, and the
+# result is exported as NIX_EXTRA_OPTS so a script that shells out to
+# another script in this repo (e.g. create-proxmox-resource.sh calling
+# sync-host-keys.sh) reuses the same decision instead of probing twice.
+declare -a NIX_OPTS=()
+
+nix_extra_opts() {
+  if [[ -n "${NIX_EXTRA_OPTS_DECIDED:-}" ]]; then
+    if [[ -n "${NIX_EXTRA_OPTS:-}" ]]; then
+      eval "NIX_OPTS=(${NIX_EXTRA_OPTS})"
+    else
+      NIX_OPTS=()
+    fi
+    return
+  fi
+  export NIX_EXTRA_OPTS_DECIDED=1
+  NIX_OPTS=()
+
+  # Retry a couple of times, 1s apart, before believing either check --
+  # belt-and-suspenders against a genuine multi-second blip (nix-cache
+  # restarting), on top of the fix below. Worst case (~11s total, host
+  # genuinely gone) is still nowhere near the 15s+ *per lookup* nix's own
+  # substituter retries would cost if this check didn't exist at all.
+  local attempt cache_up=0 builder_up=0
+  for attempt in 1 2 3; do
+    if curl --silent --fail --max-time 3 "http://${NIX_CACHE_HOST}/nix-cache-info" >/dev/null 2>&1; then
+      cache_up=1
+      break
+    fi
+    [[ "$attempt" -lt 3 ]] && sleep 1
+  done
+
+  if [[ "$cache_up" -eq 0 ]]; then
+    echo "nix-cache (http://${NIX_CACHE_HOST}) is unreachable -- skipping it (substituter + remote builder) for the rest of this run." >&2
+    NIX_OPTS=(--option substituters "https://cache.nixos.org/" --builders "")
+  else
+    for attempt in 1 2 3; do
+      # `exec 3<>/dev/tcp/...` just opens the fd and returns -- it does NOT
+      # read from it. Confirmed live this is load-bearing, not stylistic:
+      # the previous `cat < /dev/tcp/.../22` blocked forever and always hit
+      # the timeout even against a perfectly healthy nix-cache, because
+      # sshd sends its banner and then holds the connection open waiting
+      # for the client to speak next -- `cat` never sees EOF, so this
+      # check reported "unreachable" unconditionally, 100% of the time,
+      # regardless of whether the remote builder was actually up.
+      if timeout 3 bash -c "exec 3<>/dev/tcp/${NIX_CACHE_HOST}/22" 2>/dev/null; then
+        builder_up=1
+        break
+      fi
+      [[ "$attempt" -lt 3 ]] && sleep 1
+    done
+    if [[ "$builder_up" -eq 0 ]]; then
+      echo "nix-cache's SSH remote builder (nixremote@${NIX_CACHE_HOST}:22) is unreachable -- disabling remote builds for the rest of this run." >&2
+      NIX_OPTS=(--builders "")
+    fi
+  fi
+
+  # `printf '%q '` with a genuinely empty NIX_OPTS still runs one format
+  # pass over a missing argument and yields the literal `'' ` rather than
+  # an empty string (confirmed live) -- a subprocess that later does
+  # `eval "NIX_OPTS=(${NIX_EXTRA_OPTS})"` (the branch above, for e.g.
+  # sync-host-keys.sh reusing this process's decision) would then rebuild
+  # a 1-element array holding an empty string instead of a 0-element
+  # array, and `nix-shell "${NIX_OPTS[@]}" -p <pkg>` chokes on that stray
+  # element as a bogus positional argument. Guard the empty case
+  # explicitly so nix-cache being reachable (NIX_OPTS legitimately empty)
+  # round-trips as truly empty instead.
+  if [[ ${#NIX_OPTS[@]} -gt 0 ]]; then
+    printf -v NIX_EXTRA_OPTS '%q ' "${NIX_OPTS[@]}"
+  else
+    NIX_EXTRA_OPTS=""
+  fi
+  export NIX_EXTRA_OPTS
+}

scripts/gc-hosts.sh

@@ -0,0 +1,237 @@
+#!/usr/bin/env bash
+# gc-hosts.sh — Run nix-collect-garbage -d on all live NixOS hosts.
+#
+# The host list is rebuilt on every run:
+#   1. This workstation (nixos) — always first
+#   2. pve1 — always second (non-NixOS Proxmox node with Nix installed)
+#   3. Every NixOS guest currently running on pve1 (discovered via pct/qm list)
+#
+# nix-cache is excluded: gc-ing the shared binary cache evicts store paths
+# that other hosts depend on for substitution.
+#
+# NixOS hosts: tries "sudo -n nix-collect-garbage -d" first (works when
+# wheelNeedsPassword = false, e.g. the HA cluster).  Falls back to user-level
+# "nix-collect-garbage -d" if sudo needs a password — still collects
+# unreferenced store paths and old nixos-user profile generations, but leaves
+# old system generations in place.
+# pve1: runs "bash -l -c nix-collect-garbage -d" as the login user so
+# /etc/profile is sourced and the Nix daemon's PATH is set up automatically.
+#
+# Usage (from repo root):
+#   bash scripts/gc-hosts.sh [--dry-run]
+
+set -euo pipefail
+cd "$(dirname "$0")/.."
+source scripts/env.sh 2>/dev/null || true
+source scripts/lib/nix-eval.sh 2>/dev/null || true
+
+# ── config ────────────────────────────────────────────────────────────────────
+
+: "${MAX_JOBS:=8}"
+: "${NIXOS_USER:=nixos}"
+: "${PVE1_SSH_USER:=${PROXMOX_SSH_USER:-wayne}}"
+
+# GC connections use BatchMode — no interactive prompts, just succeed or fail.
+SSH_OPTS=(-o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=10)
+# Discovery connections do NOT use BatchMode so that sudo can prompt if needed
+# (pct/qm list require root access on Proxmox).
+SSH_QUERY_OPTS=(-o StrictHostKeyChecking=no -o ConnectTimeout=10)
+
+DRY_RUN=0
+for arg in "$@"; do
+  case "$arg" in
+    --dry-run) DRY_RUN=1 ;;
+    *) echo "Unknown option: $arg" >&2; exit 1 ;;
+  esac
+done
+
+# ── build the host list ───────────────────────────────────────────────────────
+
+# ORDERED_HOSTS: names in display/execution order.
+# HOST_TARGET[name]: SSH target string (user@host).
+# HOST_TYPE[name]: "nixos" (try sudo gc, fallback user) | "nix" (login-shell gc).
+declare -a  ORDERED_HOSTS=()
+declare -A  HOST_TARGET=()
+declare -A  HOST_TYPE=()
+declare -A  _SEEN_HOSTNAMES=()   # dedup tracker
+
+_add_host() {
+  local name="$1" target="$2" type="$3"
+  if [[ -n "${_SEEN_HOSTNAMES[$name]+_}" ]]; then return; fi
+  _SEEN_HOSTNAMES[$name]=1
+  ORDERED_HOSTS+=("$name")
+  HOST_TARGET[$name]="$target"
+  HOST_TYPE[$name]="$type"
+}
+
+# 1. Workstation (hard-wired first)
+_add_host "nixos" "${NIXOS_USER}@nixos" "nixos"
+
+# 2. pve1 (hard-wired second; non-NixOS, no system generations)
+_add_host "pve1" "${PVE1_SSH_USER}@${PVE1_HOST}" "nix"
+
+# 3. Dynamically discover running NixOS guests on pve1
+#
+# create-proxmox-resource.sh names every guest after its NixOS hostname:
+#   pct create ... --hostname <nixos-hostname>  (LXC)
+#   qm  create ... --name    <nixos-hostname>   (VM)
+# So pct/qm list output already contains the NixOS hostname directly.
+# We validate against the flake to filter out non-NixOS guests on pve1
+# (e.g. FreeIPA, Proxmox Backup Server) that share the same Proxmox node.
+echo "Discovering running guests on ${PVE1_HOST}..."
+
+# Eval the flake once to get the set of hostnames that are actually NixOS.
+# Values are NixOS hostnames (e.g. "docker"); keys are flake targets ("lxc-docker").
+nixos_hostnames=""
+nixos_hostnames="$(
+  nix eval --json "${NIX_EVAL_FLAGS[@]}" .#nixosConfigurations \
+    --apply 'cfgs: builtins.attrValues (builtins.mapAttrs (_: cfg: cfg.config.networking.hostName) cfgs)' \
+    2>/dev/null | jq -r '.[]' | sort -u
+)" || { echo "  warning: flake eval failed — non-NixOS guests will not be filtered" >&2; }
+
+# SSH_QUERY_OPTS (no BatchMode) so sudo can prompt if needed for pct/qm.
+if ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" "true" 2>/dev/null; then
+  running_guests="$(
+    ssh "${SSH_QUERY_OPTS[@]}" "${PVE1_SSH_USER}@${PVE1_HOST}" bash -s <<'DISCOVER'
+sudo pct list 2>/dev/null | awk 'NR>1 && $2=="running" { print $NF }'
+sudo qm  list 2>/dev/null | awk 'NR>1 && $3=="running" { print $2  }'
+DISCOVER
+  )" || running_guests=""
+
+  while IFS= read -r hostname; do
+    [[ -z "$hostname" ]] && continue
+    # Exclude nix-cache.
+    case "$hostname" in *nix-cache*) continue ;; esac
+    # Skip if not a flake-managed NixOS host (filters non-NixOS pve1 guests).
+    if [[ -n "$nixos_hostnames" ]] && ! grep -qxF "$hostname" <<< "$nixos_hostnames"; then
+      continue
+    fi
+    # Skip if already in the list (e.g. a proxmox-gui guest whose hostname is nixos).
+    if [[ -n "${_SEEN_HOSTNAMES[$hostname]+_}" ]]; then continue; fi
+
+    echo "  + $hostname"
+    _add_host "$hostname" "${NIXOS_USER}@${hostname}" "nixos"
+  done <<< "$(echo "$running_guests" | sort -u)"
+else
+  echo "  warning: ${PVE1_HOST} unreachable — skipping dynamic host discovery" >&2
+fi
+
+echo ""
+echo "Hosts: ${ORDERED_HOSTS[*]}"
+echo ""
+
+# ── dry-run ───────────────────────────────────────────────────────────────────
+
+if [[ "$DRY_RUN" -eq 1 ]]; then
+  echo "[dry-run] commands that would run:"
+  for host in "${ORDERED_HOSTS[@]}"; do
+    target="${HOST_TARGET[$host]}"
+    type="${HOST_TYPE[$host]}"
+    if [[ "$type" == "nixos" ]]; then
+      echo "  ssh ${SSH_OPTS[*]} $target 'sudo -n nix-collect-garbage -d'"
+      echo "  # fallback: ssh ... $target 'nix-collect-garbage -d'"
+    else
+      echo "  ssh ${SSH_OPTS[*]} $target 'bash -l -c nix-collect-garbage -d'"
+    fi
+  done
+  exit 0
+fi
+
+# ── gc worker ─────────────────────────────────────────────────────────────────
+
+gc_one() {
+  local host="$1" target="${HOST_TARGET[$1]}" type="${HOST_TYPE[$1]}" logfile="$2"
+
+  if ! ssh "${SSH_OPTS[@]}" "$target" "true" 2>>"$logfile"; then
+    echo "unreachable"; return
+  fi
+
+  if [[ "$type" == "nixos" ]]; then
+    if ssh "${SSH_OPTS[@]}" "$target" "sudo -n nix-collect-garbage -d" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok(sudo)"; return
+    fi
+    echo "[sudo needs password — falling back to user-level gc]" >>"$logfile"
+    if ssh "${SSH_OPTS[@]}" "$target" "nix-collect-garbage -d" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok(user)"; return
+    fi
+  else
+    # Non-NixOS node: use a login shell so /etc/profile is sourced and the
+    # Nix daemon's bin dir is on PATH (set up by /etc/profile.d/nix-daemon.sh
+    # which the Nix installer adds to /etc/profile).
+    if ssh "${SSH_OPTS[@]}" "$target" "bash -l -c 'nix-collect-garbage -d'" \
+        >>"$logfile" 2>>"$logfile"; then
+      echo "ok"; return
+    fi
+  fi
+
+  echo "failed:$?"
+}
+
+# ── parallel execution ────────────────────────────────────────────────────────
+
+echo "Running gc on ${#ORDERED_HOSTS[@]} hosts (up to ${MAX_JOBS} parallel)..."
+echo ""
+
+TMPDIR_GC="$(mktemp -d)"
+trap 'rm -rf "$TMPDIR_GC"' EXIT
+
+declare -A LOGS=()
+job_count=0
+
+for host in "${ORDERED_HOSTS[@]}"; do
+  logfile="${TMPDIR_GC}/${host}.log"
+  resultfile="${TMPDIR_GC}/${host}.result"
+  LOGS[$host]="$logfile"
+  : > "$logfile"
+
+  ( result="$(gc_one "$host" "$logfile")"; echo "$result" > "$resultfile" ) &
+
+  (( job_count++ )) || true
+  if [[ "$job_count" -ge "$MAX_JOBS" ]]; then
+    wait -n 2>/dev/null || wait
+    (( job_count-- )) || true
+  fi
+done
+
+wait
+
+# ── summary ───────────────────────────────────────────────────────────────────
+
+echo "Results:"
+echo "──────────────────────────────"
+
+ok_hosts=()
+warn_hosts=()
+fail_hosts=()
+
+for host in "${ORDERED_HOSTS[@]}"; do
+  result="$(cat "${TMPDIR_GC}/${host}.result" 2>/dev/null || echo "failed:missing")"
+  case "$result" in
+    ok|"ok(sudo)"|"ok(user)")
+      printf "  %-22s  %s\n" "$host" "$result"
+      ok_hosts+=("$host") ;;
+    unreachable)
+      printf "  %-22s  UNREACHABLE\n" "$host"
+      warn_hosts+=("$host") ;;
+    *)
+      printf "  %-22s  FAILED (%s)\n" "$host" "$result"
+      fail_hosts+=("$host") ;;
+  esac
+done
+
+echo ""
+echo "  ${#ok_hosts[@]} succeeded, ${#warn_hosts[@]} unreachable, ${#fail_hosts[@]} failed"
+
+for host in "${warn_hosts[@]+"${warn_hosts[@]}"}" "${fail_hosts[@]+"${fail_hosts[@]}"}"; do
+  logfile="${LOGS[$host]}"
+  if [[ -s "$logfile" ]]; then
+    echo ""
+    echo "── $host ──"
+    cat "$logfile"
+  fi
+done
+
+echo ""
+[[ "${#fail_hosts[@]}" -eq 0 ]]