fix(deploy): remove sudo from docker commands; fix grep false-positive on inactive

nixos user is in the docker group so sudo is not needed (and breaks because
sudo requires a TTY for password input). Also grep -q 'active' matched
'inactive' causing ha-docker-2 to be seen as already joined.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DASH15okNvWeY1rVJmyJoJ

.gitignore

@@ -23,3 +23,5 @@ 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

@@ -1,18 +1,28 @@
 keys:
   - &admin age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
-  - &docker age19gfn2yedg76dmztm4hncr7vf3r3c9j0qpt4rap7y7gersjk4m3ks2lhd0e
-  - &server age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
-  - &nix-cache age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
-  - &nix-minimal age120whqj96g26lsgy4udvgsn8dc9lumh8jeu3a564fx79rjr5lxffqmrljuu
-  - &proxmox-minimal age10at8862478urh0eeuwh8hzln6ck78jgwtztgxatwqlzwagg77y5snm4xzg
-  - &lxc-nix-cache age1xjst4frdh0th6q8m7p7u9g5af7ty5jqeum0p6z8a52a9q7st7ewqw8yl9j
-  - &lxc-docker age1ezk9x53zt8kcnscdm80jcyf0xq97vndv7jsn3rl8cc0cwm2jmpmq372dzs
-  - &lxc-minimal age1jy444f9d9stygj4p3w9kh54cqcfr654tvr75tdvee5cxsgtdtc9q3v60ep
-  - &lxc-pxe-boot age1fxxzpnfse8nd9wz78ht3m0plrmraacf4cpga0pe8fm2tdnqcgy8q7qsyvp
-  - &lxc-gui age190htw7prp4vln076dxjx3gxxaq06h0zl0te7cqgpx79vl3lhkaes8suy05
-  - &proxmox-server age1ukpqxzl44mnjpy5r96sfuc5sqzm47u4k8ujjh5qdgy6jvl9uqgpspymqfk
-  - &vm-server age15kh7akxlx7zn00tey79rq2g8lgs4j5y77rcnyfxrxap8ckfu0a9sqvtdhh
-  - &baremetal-gui age1ehkswwz2pqaz4svzh7ela5tdnssl8kn6d4vwwxd6zwg8exfpd43syyrrjp
+  - &proxmox-minimal age19m0m7vdfg86yqy8l5mmle5jdd0unrn3f55t232w8h5ey42cqw34sfpt32n
+  - &lxc-gui age1rrxqea6q6pn39sw8y5te63h2py8jgjl9v0jyper86w3ggtn67upqg3ah39
+  - &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
+  - &proxmox-ha-docker-1 age16y0vfts5v2k20e2rj23qa5lc5gm96gm64uwsqsr0y688xl0ne46qcfr0sm
+  - &proxmox-ha-docker-2 age1tm3zj5lp3elw2j832az4nj9xxmhqd66ag3cqcv3vskvmd7qdmqmsdpdcn0
 
 creation_rules:
   # Shared across every currently-deployed host: root/nixos password hash,
@@ -23,40 +33,81 @@ creation_rules:
     key_groups:
       - age:
           - *admin
-          - *docker
-          - *server
-          - *nix-cache
-          - *lxc-minimal
-          - *nix-minimal
-          - *lxc-nix-cache
           - *proxmox-minimal
-          - *lxc-docker
-          - *lxc-pxe-boot
           - *lxc-gui
-          - *proxmox-server
-          - *vm-server
           - *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
+          - *proxmox-ha-docker-1
+          - *proxmox-ha-docker-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
-          - *proxmox-server
-          - *vm-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
@@ -70,3 +121,101 @@ creation_rules:
           - *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
+
+  # Host keytab for ha-docker-1 FreeIPA enrollment (binary sops file).
+  # Generated by scripts/ipa/create-nixos-ipa-host-account.sh.
+  - path_regex: secrets/ha-docker-1\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-docker-1
+
+  # Host keytab for ha-docker-2 FreeIPA enrollment (binary sops file).
+  # Generated by scripts/ipa/create-nixos-ipa-host-account.sh.
+  - path_regex: secrets/ha-docker-2\.keytab$
+    key_groups:
+      - age:
+          - *admin
+          - *proxmox-ha-docker-2

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`,
-`server`, `docker`, `gui`, `pxe-boot`, `tailscale-exit-node`, `tor-relay`), generated from `modules/platforms/*`
-and `modules/build-types/*` by the `mkTarget` function in `flake.nix`. Not
-every combination is built — `pxe-boot` has no `linode` variant. See
-`README.md` for the full current target list; treat `flake.nix` as the
-source of truth since this list can drift.
+(platforms: `linode`, `proxmox`, `lxc`, `baremetal`; build types: `minimal`,
+`nix-cache`, `docker`, `gui`, `pxe-boot`, `tailscale-router`,
+`tor-relay`, `ha-server`), generated from `modules/platforms/*` and
+`modules/build-types/*` by the `mkTarget` function in `flake.nix`. Not every
+combination is built — `pxe-boot` has no `linode` variant, `ha-server` only
+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.

AUDIT_REPORT.md

@@ -1,150 +0,0 @@
-# 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

@@ -21,15 +21,17 @@ machines when deployed.
   `modules/installer/common.nix` (the auto-installer's own root/nixos login —
   a deliberate, documented choice, see `docs/auto-installer.md`, not
   accidental tech debt) and **SSH public keys** in `variables.nix`
-  (`vars.adminSshKey`, `vars.remoteBuilderAuthorizedKeys`) plus a couple of
-  per-host `KEY` values for beszel-agent auth (`hosts/server/host.nix`,
-  `hosts/nix-cache/host.nix`). Don't use the installer's hardcoded hash as a
+  (`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 — locally-generated *private* SSH host keys for
-  the auto-installer (see `docs/auto-installer.md`). Never commit its
-  contents; if `git status` ever shows it as trackable, something is wrong.
+- `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)
 
@@ -203,8 +205,11 @@ instead of copying it.
 - `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`). The primary tool for provisioning a new host's
-  secrets access — see "Creating a new machine" in `docs/auto-installer.md`.
+  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
@@ -247,6 +252,14 @@ instead of copying it.
   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/secrets/push-host-keys.sh [--all | <target>] [--dry-run]
+  [--skip-git-check]` — pushes newly-generated SSH host keys from
+  `host-keys/` to already-running NixOS hosts, so they can decrypt sops
+  secrets after a rebuild following `sync-host-keys.sh
+  --regenerate-all-keys`. Verifies that `.sops.yaml` and `secrets/*.yaml`
+  are committed and pushed to the remote first (hosts rebuild from the
+  remote Gitea flake, so recipient changes must land there before any key
+  push).
 
 ### `scripts/proxmox/`
 
@@ -268,6 +281,16 @@ instead of copying it.
   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/clone-pve1-to-pve-test.sh <vmid> [--new-vmid <id>]
+  [--mode snapshot|suspend|stop] [--dry-run]` — ad-hoc clone of a single
+  VM or CT from pve1 (production) to pve-test (sandbox) via vzdump +
+  qmrestore/pct restore. Streams the archive directly between nodes (no
+  local staging copy). Always restores with `--unique 1` (fresh MAC
+  addresses) since the original is still running on the LAN. Cleans up
+  the vzdump archive from both nodes after a successful restore. The
+  script's own default is pve1 → pve-test, matching CLAUDE.md's policy
+  (unlike `create-proxmox-resource.sh`, which defaults to production for
+  the operator's own unqualified use).
 - `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
@@ -283,6 +306,50 @@ instead of copying it.
   marked block rather than duplicating it); restarts `nix-daemon` by
   default so the change takes effect immediately.
 
+### `scripts/ha/`
+
+HA cluster lifecycle and operational scripts. All mutate real cluster state
+when run for real — always run against pve-test first unless the operator
+explicitly targets pve1.
+
+- `scripts/ha/deploy.sh [--skip-*] [--destroy] [--dry-run]` — full
+  lifecycle manager: phases through bridge creation, key sync, VM creation
+  (via `create-proxmox-resource.sh`), NIC/disk attachment, and cluster
+  initialisation. `--destroy` tears it back down. Safe to rerun
+  idempotently; each phase can be individually skipped.
+- `scripts/ha/cluster-init.sh` — one-time cluster bootstrap run **as root
+  on ha-server-1** after both VMs are booted. Generates/distributes the
+  Corosync authkey, initialises DRBD metadata, creates XFS on `/dev/drbd0`,
+  configures LIO iSCSI, and registers all Pacemaker resources (DRBD → XFS
+  → iSCSI → NFS → VIPs).
+- `scripts/ha/health.sh` — read-only cluster health snapshot: SSH
+  reachability, quorum, DRBD state, Pacemaker resources, and VIP port
+  reachability. Safe to run from the workstation at any time.
+- `scripts/ha/failover.sh [--to node1|node2] [--force] [--timeout <s>]
+  [--dry-run]` — graceful failover by putting the active node into
+  Pacemaker standby and waiting for resources to appear on the target.
+- `scripts/ha/acceptance-tests.sh` — T1–T7 acceptance tests (failover,
+  NFS/iSCSI connectivity, DRBD sync, etc.) that must all pass before the
+  cluster is considered production-ready.
+- `scripts/ha/resize-data-disk.sh --size +NNg [--force] [--dry-run]` —
+  online data-disk resize: `qm resize` on both VMs, guest block-device
+  rescan, `drbdadm resize`, `xfs_growfs`. No downtime required.
+- `scripts/ha/cluster-enable-stonith.sh` — enables the `fence_pve_ssh`
+  STONITH resource after the fence SSH key is deployed to both nodes and
+  authorised on the Proxmox host. Run once after `cluster-init.sh`.
+- `scripts/ha/fence-pve-ssh.py` — Python STONITH fence agent for Pacemaker.
+  Deploy to `/etc/pacemaker/fence_pve_ssh` on both HA nodes (`chmod +x`).
+  SSHes to the Proxmox host and runs `qm stop/start <vmid>`.
+
+### `scripts/ipa/`
+
+- `scripts/ipa/create-nixos-ipa-host-account.sh [options] <hostname>` —
+  adds a NixOS host to the FreeIPA domain and produces a sops-encrypted
+  keytab at `secrets/<hostname>.keytab`, ready for `modules/ipa/client.nix`.
+  Replaces three error-prone manual steps: `ipa host-add`, `ipa-getkeytab`
+  (run on the DC, SCP'd back), and `sops encrypt` in the correct location
+  (must be at `secrets/<hostname>.keytab` for the creation rule to match).
+
 ### `scripts/lib/`
 
 Sourced by the scripts above, never run directly:
@@ -292,6 +359,15 @@ Sourced by the scripts above, never run directly:
   `create-proxmox-resource.sh` runs over SSH.
 - `nix-eval.sh` — `NIX_EVAL_FLAGS` plus `list_flake_targets`/
   `flake_target_hostname` flake-introspection helpers.
+- `nix-parallel.sh` — `run_nix_parallel`: fans out independent `nix eval`/
+  `nix build --dry-run` calls across up to `NIX_PARALLEL_JOBS` processes,
+  capped by available memory (~1 GB/job) rather than raw `nproc` to avoid
+  OOM on constrained CI runners. Used by `codex-maintenance.sh`.
+- `clan-vars.sh` — helpers for reading/writing SSH host keys stored as clan
+  vars (`vars/per-machine/<target>/openssh/`, sops-encrypted) instead of
+  the gitignored `host-keys/` directory. Sourced by
+  `create-proxmox-resource.sh` and `sync-host-keys.sh`; depends on
+  `sops-age.sh` and `ssh-host-keys.sh` being sourced first.
 - `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`/
@@ -311,6 +387,17 @@ Sourced by the scripts above, never run directly:
   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/recover-hosts.sh [<hostname> ...]` — fixes sops/SSH-key/GitHub-token
+  issues on deployed NixOS hosts and triggers a `Switch-nix` rebuild on each.
+  With no args discovers every known hostname; with args checks only those.
+  Fixes applied automatically (prompts before rebuilding): SSH host key drift
+  (restores the registered key) and stale GitHub access tokens (empties the
+  rendered `nix-github-token.conf` so Nix falls back to unauthenticated requests
+  until sops-nix re-renders the correct token after the next successful rebuild).
+- `scripts/gc-hosts.sh [--dry-run]` — runs `nix-collect-garbage -d` on all live
+  NixOS hosts (workstation first, then pve1, then all Proxmox guests). Excludes
+  `nix-cache` (gc-ing the shared binary cache evicts store paths other hosts
+  depend on). Uses passwordless sudo where available; falls back to user-level gc.
 - `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`
@@ -349,12 +436,13 @@ nixosSystem {
 ```
 
 Platforms: `linode`, `proxmox`, `lxc`, `baremetal`. Build types: `minimal`,
-`nix-cache`, `server`, `docker`, `gui`, `pxe-boot`, `tailscale-exit-node`,
-`tor-relay`. Not every combination is built — e.g. `pxe-boot` has no `linode`
+`nix-cache`, `docker`, `gui`, `pxe-boot`, `tailscale-router`, `tor-relay`,
+`ha-server`. 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
+`tor-relay` only exists as `lxc-tor-relay`, `ha-server` only exists as
+`proxmox-ha-server-{1,2}`, and `baremetal` 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`,
@@ -368,9 +456,8 @@ removing a host.
 
 - `hosts/<name>/host.nix` — per-machine identity **only**: hostname, hostId,
   per-machine secrets, `system.stateVersion`. These files carry no `imports`
-  of their own beyond narrow parameterized helpers (see
-  `modules/beszel/host-token.nix` below) — all shared behavior comes from the
-  platform/build-type modules composed in `flake.nix`, not from the host file.
+  of their own — all shared behavior comes from the platform/build-type modules
+  composed in `flake.nix`, not from the host file.
 - `modules/platforms/{linode,proxmox,lxc,baremetal}.nix` — platform-specific
   config: boot method, guest tooling, and the hardware config, imported
   directly by the platform module itself — **not** wired in from
@@ -387,7 +474,7 @@ removing a host.
   `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.
+  minimal/docker/gui/pxe-boot/nix-cache/tailscale-router/tor-relay/ha-server.
 - `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
@@ -413,7 +500,7 @@ removing a host.
   `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.
+  `ha-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/installer/` — the auto-installer environment (ISO, also served as
   PXE netboot): `common.nix` (shared config + the generated
@@ -427,14 +514,21 @@ removing a host.
   substituter + SSH remote-builder wiring; see `docs/nix-cache.md` for the
   full design (per-host local stores, no shared `/nix/store`, and how the
   `nixremote` signing/SSH keys fit together).
-- `modules/beszel/host-token.nix` — parameterized helper module
-  (`{ name, sopsFile }`) that wires a host's beszel-agent sops secret/template
-  and `environmentFile`; used by `hosts/server/host.nix` and
-  `hosts/nix-cache/host.nix` to avoid duplicating that boilerplate.
+- `modules/ha/` — HA cluster NixOS modules: `cluster-config.nix` (DRBD,
+  Corosync, Pacemaker, firewall rules, cluster-wide NFS/iSCSI port
+  authorisation — shared by both ha-server nodes), `pacemaker-stack.nix`
+  (Pacemaker + Corosync service enablement), and supporting modules. See
+  `docs/ha.md` for the cluster operational guide.
+- `modules/ipa/client.nix` — FreeIPA client enrollment: sssd, Kerberos keytab,
+  and IPA host registration; imported by every real host via
+  `modules/common/configuration.nix`.
+- `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`,
+  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.
 
@@ -458,3 +552,5 @@ duplicating config.
 - `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`.
+- `docs/ha.md` — HA file-server cluster: DRBD + XFS + LIO iSCSI + NFS managed
+  by Corosync + Pacemaker; network topology; lifecycle scripts in `scripts/ha/`.

README.md

@@ -9,14 +9,14 @@ Targets are named `<platform>-<buildtype>`, generated from two orthogonal
 pieces composed in `flake.nix`:
 
 - **Platforms** (what it runs on): `linode`, `proxmox`, `lxc`, `baremetal`
-- **Build types** (what it's for): `minimal`, `nix-cache`, `server`, `docker`,
-  `gui`, `pxe-boot`, `tailscale-exit-node`, `tor-relay`
+- **Build types** (what it's for): `minimal`, `nix-cache`, `docker`, `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,
-`tor-relay` currently only exists as `lxc-tor-relay`, and `baremetal`
-currently only exists as `baremetal-gui` (the real gui-host hardware). The
-full 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 |
 | --- | --- |
@@ -24,13 +24,13 @@ full list:
 | `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 — previously the flat `nix-cache` 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 — previously the flat `docker` target |
 | `linode-gui` / `proxmox-gui` / `lxc-gui` | Cinnamon desktop workstation — previously the flat `nixos` 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-exit-node` / `proxmox-tailscale-exit-node` / `lxc-tailscale-exit-node` | Tailscale exit node |
+| `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
@@ -47,8 +47,7 @@ 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
-`flake-target-refactor-spec.md` for the full rationale. Every deployed host
+fixed regardless of which platform it's built for. 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.
@@ -72,7 +71,8 @@ nix eval --json .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]'
 | `modules/common/` | Shared NixOS config, Home Manager, aliases imported by every host |
 | `modules/nix-cache/` | Binary cache and remote builder client/server modules |
 | `modules/installer/` | Auto-installer environment (ISO, also served as PXE netboot) — see `docs/auto-installer.md` |
-| `host-keys/` | Gitignored, locally-generated SSH host keys for the auto-installer — see `docs/auto-installer.md` |
+| `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 |
 
@@ -162,9 +162,10 @@ sops-nix-everywhere: it has a hardcoded login password instead (no stable
 per-boot host key for sops-nix to derive from on ephemeral media) — see
 "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.
+`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 this
-migration (see `remove-sensetive-info-refactor.md`) — those are being
-scrubbed and rotated separately; don't treat the repo as safe to make public
-until that's finished.
+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-----
+MIIESDCCArCgAwIBAgIBATANBgkqhkiG9w0BAQsFADA1MRMwEQYDVQQKDApTV0VF
+VC5IT01FMR4wHAYDVQQDDBVDZXJ0aWZpY2F0ZSBBdXRob3JpdHkwHhcNMjYwNzI2
+MjExMzQxWhcNNDYwNzI2MjExMzQxWjA1MRMwEQYDVQQKDApTV0VFVC5IT01FMR4w
+HAYDVQQDDBVDZXJ0aWZpY2F0ZSBBdXRob3JpdHkwggGiMA0GCSqGSIb3DQEBAQUA
+A4IBjwAwggGKAoIBgQCzljYktbHdMGVJ6Wq0XQJuHLN6dkCSOgtoIzQtriPQkkNI
+uo28LwobaiQQ8sX4kGRH/BTKnH8QlId/jug4Uc+sDHnABYu++AiOhPbBX8gCpRQ0
+hebBjZiktHSBUEJR31siWOVdBoKBDJEoxehx7XUXvcxIJcaRN+LHYjO86nJN55HB
+VwFU2JcYDk98c+144dFJxXdr++MjWe4Z/oVVU8JHIOtNtKhVhvij6oOSWxcYoJO/
+S80LRj1vx/o6o/3G6bYug7PjY7JjZk/Oj61whijZkcsoO1MXSYI6UywJZGflv+ZB
+7HyufdYAsK3WhE8O2FX3/kq64Ol83HNtoR8Dt68rTg1xpW6K45jS6iDPKueYGkb0
+oSx7e++90VAW2PDhj6QQ3JJ4O5VQwrrecekJzUrAean0FOEbmgyi4PsEp1Vk6LDQ
+SsIn1x0euyxVivQMlzNX2XrZL3urn1BNPqAdntXQMkR0Wl8sbUiJPe0kxG52CGXs
+6yfNEXbPmVGcC0TBdGECAwEAAaNjMGEwHQYDVR0OBBYEFLh5QbI1UWMH0WR4z8bG
+lhrOX3X5MB8GA1UdIwQYMBaAFLh5QbI1UWMH0WR4z8bGlhrOX3X5MA8GA1UdEwEB
+/wQFMAMBAf8wDgYDVR0PAQH/BAQDAgHGMA0GCSqGSIb3DQEBCwUAA4IBgQCVodVN
+owwo53OQe02QhtEbIur2PL7zIfvhvCTRD4J8gwpbMIqT7JQK0tV6Mvsg2L8yTb2O
+KjrWeLKHGWaZZlhGSPTbkMFdb/Ls8M9FSnkc2bwcdWW3Z1lOiCjBYYqwLCG6JhvB
+5SXVwWNJwXeasL2m7oFTSwhsqPpARJ2t25u2N35o+tqIoCjijKwkmEOT66N9EAbu
+2VQjtYZWPkBtP4YCe0Ey6u4oy7sy8ThNAjOylZok+J4JW7QEFjK4Q/emhA4aQq5H
+gg9qgMuG+5oi6D1g2Wy+fMTRBaukJtLYZbBpQMQhMYWg44uPp/2bbNPTID/nV1KB
+GcPyHaskcVxPdYWxAPMwk3AeJXWyOq7atAPTF5sbk0kQQf2m+vyOqcli5CxRMUgV
+rcyi9l6+dZW4U+38Q0ET5M3OuxNI4hA7kVY2cfTakXWNqh97+TIHnstblDhAxECK
+6ZLMJQYUy7LqJTX84H27CBWLexEMjXwdr5HCV88Fj6mAK0fRufnIw5FeneA=
+-----END CERTIFICATE-----

docs/auto-installer.md

@@ -22,7 +22,7 @@ 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-exit-node`, `lxc-tor-relay`) are **not** installed via `auto-install.sh` — the
+`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
@@ -133,13 +133,15 @@ Flake outputs:
 ```nix
 nixosConfigurations.installer   # ISO/netboot installer image
 
-packages.x86_64-linux.iso   # installer ISO/netboot image
-packages.x86_64-linux.pxe   # netboot-ipxe + netboot-initrd + netboot-kernel, bundled
+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-

docs/beszel.md

@@ -0,0 +1,104 @@
+# 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
+};
+```
+
+---
+
+## 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/ha.md

@@ -0,0 +1,160 @@
+# HA File-Server Cluster
+
+Two `proxmox-ha-server-{1,2}` VMs form an active/passive file-server cluster:
+DRBD replicates a block device between nodes; Corosync + Pacemaker manage
+failover; XFS, LIO iSCSI, and NFS are brought up as a collocated resource
+group on whichever node holds the DRBD Primary role.
+
+NixOS modules: `modules/ha/`. Lifecycle scripts: `scripts/ha/`.
+Cluster-wide constants: `variables.nix` (`haServer*` vars).
+
+---
+
+## Network layout
+
+Three subnets — all internal to pve1 (`vmbr0`/`vmbr1`/`vmbr2`):
+
+| Subnet | VLAN | CIDR | Bridge | Purpose |
+|---|---|---|---|---|
+| LAN | 2 | `192.168.2.0/24` | `vmbr0` | Management, LAN NFS |
+| Cluster | 10 | `192.168.10.224/29` | `vmbr1` | Corosync ring0 + DRBD replication |
+| Storage-client | 20 | `192.168.20.0/24` | `vmbr2` | NFS + iSCSI for docker/swarm |
+
+Each HA VM has three NICs: `ens18` (LAN/vmbr0), `ens19` (cluster/vmbr1),
+`ens20` (storage-client/vmbr2). See `docs/ip-addressing.md` for all IPs.
+
+Corosync ring0 uses the cluster NIC; ring1 (backup heartbeat) uses the LAN
+NIC. DRBD replicates over the cluster NIC. No storage traffic crosses the LAN.
+
+---
+
+## Pacemaker resources
+
+All resources run collocated on whichever node is Primary, in this order:
+
+```
+ms-drbd0 (promotable DRBD clone)
+  → xfs-data   (XFS mount on /dev/drbd0 → /srv/ha-data)
+  → iscsi-target (targetctl)
+  → nfs-server  (nfs-server.service)
+  → vip-lan     (192.168.2.229/24 on vmbr0 — NFS for LAN clients)
+  → vip-storage (192.168.20.229/24 on vmbr2 — NFS + iSCSI for VLAN 20)
+```
+
+`vip-lan` serves pxe-boot and other LAN-only NFS clients.
+`vip-storage` serves docker and any future swarm nodes; iSCSI is available on
+VLAN 20 but NFS is preferred for multi-host volume sharing.
+
+---
+
+## DRBD fencing
+
+`fencing resource-only` with `crm-fence-peer.sh`/`crm-unfence-peer.sh`
+wrappers (`modules/ha/cluster-config.nix`). The DRBD kernel module invokes
+these via the User Mode Helper with a minimal PATH; the wrappers prepend
+`/run/current-system/sw/bin` before exec-ing the real handlers so Pacemaker
+tools (`cibadmin`, `crm_mon`, etc.) are found.
+
+STONITH is initially disabled (`stonith-enabled: false`,
+`no-quorum-policy: ignore`). Enable it once the `fence_pve_ssh` fence agent
+(`scripts/ha/fence-pve-ssh.py`) is deployed and authorised:
+
+```bash
+scripts/ha/cluster-enable-stonith.sh   # run as root on ha-server-1
+```
+
+---
+
+## Deploying the cluster from scratch
+
+Use `scripts/ha/deploy.sh` — it orchestrates all phases:
+
+```bash
+# Against pve-test (safe — Claude's default target):
+scripts/ha/deploy.sh --node "$PVE_TEST_HOST" [--dry-run]
+
+# Against pve1 (production — requires explicit operator go-ahead):
+scripts/ha/deploy.sh --node "$PVE1_HOST"
+```
+
+Phases (each skippable with `--skip-<phase>`):
+1. `ensure-bridge` — creates `vmbr1`/`vmbr2` on the Proxmox node if absent
+2. `sync-keys` — generates SSH host keys for both nodes; registers sops recipients
+3. `create-vms` — builds disk images, creates VMs via `create-proxmox-resource.sh`
+4. `add-hardware` — attaches storage NIC and DRBD data disk to each VM
+5. `init-cluster` — runs `scripts/ha/cluster-init.sh` on ha-server-1
+
+`--destroy` runs the teardown sequence.
+
+---
+
+## Day-to-day operations
+
+```bash
+# Read-only health check (safe from workstation):
+scripts/ha/health.sh
+
+# Graceful failover (prompts for confirmation):
+scripts/ha/failover.sh [--to node1|node2]
+
+# Online data-disk growth (no downtime):
+scripts/ha/resize-data-disk.sh --size +20G
+
+# Acceptance tests (run after any significant change):
+scripts/ha/acceptance-tests.sh
+```
+
+---
+
+## Adding FreeIPA host accounts
+
+IPA host registration is automated:
+
+```bash
+scripts/ipa/create-nixos-ipa-host-account.sh <hostname>
+```
+
+This runs `ipa host-add`, fetches a keytab from the domain controller, and
+writes a sops-encrypted `secrets/<hostname>.keytab` in one step. The module
+`modules/ipa/client.nix` (imported by every host via
+`modules/common/configuration.nix`) consumes the keytab via sops-nix.
+
+---
+
+## Storage layout
+
+```
+/srv/ha-data/
+  docker/
+    config/          NFS → docker:/mnt/docker/config
+    databases/       NFS → docker:/mnt/docker/databases
+    volumes/         NFS → docker:/mnt/docker/volumes
+    nextcloud-data/  NFS → docker:/mnt/docker/nextcloud-data
+  proxmox/
+    iso/             NFS → pve1 ISO storage
+    lxc/             NFS → pve1 CT template storage
+  pxe-boot/
+    images/          NFS → pxe-boot:/srv/pxe/http/images (PXE assets)
+  raspi/
+    volumes/         NFS → raspi NFS mounts
+  iscsi-lun.img      iSCSI fileio backstore (VLAN 20 only, not in active use)
+```
+
+All shares are defined in `variables.nix` (`vars.nfsShares.*`). The NFS
+export list lives in `modules/ha/nfs-exports.nix`.
+
+---
+
+## Key variables
+
+| Variable | Description |
+|---|---|
+| `vars.haServer1Ip` / `vars.haServer2Ip` | LAN management IPs |
+| `vars.haServer1StorageIp` / `vars.haServer2StorageIp` | Cluster NIC IPs (DRBD/Corosync ring0) |
+| `vars.haServerLanVip` | Pacemaker `vip-lan` — NFS for LAN (192.168.2.229) |
+| `vars.haServerVip` | Pacemaker `vip-storage` — NFS + iSCSI for VLAN 20 (192.168.20.229) |
+| `vars.haLanNfsFqdn` | FQDN of `vip-lan`: `ha-vip-lan.sweet.home` |
+| `vars.haStorageRoot` | XFS mount point: `/srv/ha-data` |
+| `vars.haServerDrbdDisk` | Block device for DRBD backing store |
+| `vars.haStorageCidr` | Cluster subnet CIDR (`192.168.10.224/29`) |
+| `vars.haClientCidr` | Storage-client subnet CIDR (`192.168.20.0/24`) |

docs/internal/docker-swarm-cutover.md

@@ -0,0 +1,330 @@
+# Docker Swarm Cutover Plan
+
+Migration guide for moving containerised services from the existing single-host
+Docker LXC container (CT 105, `docker.sweet.home`, 192.168.2.225) to the new
+Docker Swarm cluster (`ha-docker-1` / `ha-docker-2`, 192.168.2.230–231).
+
+CT 105 stays running throughout.  Services migrate one stack at a time.
+Roll back any stack by restarting it on CT 105 if anything goes wrong.
+
+---
+
+## Prerequisites
+
+- Swarm cluster deployed and healthy (`scripts/docker-swarm/deploy.sh`).
+- Both nodes show `Ready / Active / Manager` in `docker node ls`.
+- NFS mounts healthy on both swarm nodes (`/mnt/docker/config`, `/mnt/docker/databases`, `/mnt/docker/volumes`).
+- Access to FreeIPA DNS admin to update A records during cutover.
+
+---
+
+## 1. Traefik — switch to Docker log rotation
+
+**Current state (CT 105):** Traefik writes access logs to the NFS volume at
+`/mnt/docker/volumes/traefik-data/logs/`.  `modules/traefik/rotate-logs.nix`
+rotates those files via `logrotate`.
+
+**Swarm approach:** Remove file-based access logging from Traefik's static
+config and rely on Docker's json-file log driver with built-in rotation.
+Traefik container logs (including access events) then live under
+`/var/lib/docker/containers/<id>/` on the node running Traefik.
+
+### Steps
+
+**1a.** In the Traefik stack definition, add logging config to the service:
+
+```yaml
+services:
+  traefik:
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "100m"
+        max-file: "20"
+```
+
+**1b.** In `traefik.yml` (Traefik's static config), remove the `accessLog`
+file path if present.  To keep structured access logs, use Traefik's
+`accessLog.format: json` with no `filePath` — logs then go to stdout and are
+captured by the json-file driver above.
+
+**1c.** Deploy Traefik to the swarm:
+
+```bash
+# On either swarm manager:
+docker stack deploy -c /mnt/docker/config/traefik/docker-compose.yml traefik
+```
+
+Traefik should be deployed as a **global mode** service so it runs on all
+swarm nodes and handles ingress on whichever node a request arrives at:
+
+```yaml
+services:
+  traefik:
+    deploy:
+      mode: global
+      placement:
+        constraints:
+          - node.role == manager
+```
+
+**1d.** After confirming Traefik works on the swarm, remove
+`traefik/rotate-logs.nix` from the `docker` build type in
+`modules/build-types/docker.nix` and rebuild CT 105.
+
+**DNS:** Update `docker.sweet.home` and any service FQDNs that point at
+192.168.2.225 to a swarm VIP or round-robin A records once Traefik is running
+on the swarm.  See section 8 (DNS cutover).
+
+---
+
+## 2. Nextcloud — migrate cron job to sidecar container
+
+**Current state (CT 105):** `modules/docker/nextcloud-cron-job.nix` runs a
+systemd timer every 5 minutes that calls:
+```bash
+docker exec nextcloud-webapp php ./cron.php
+```
+
+**Swarm problem:** `docker exec` only works against the local daemon.  If
+Nextcloud is scheduled on the other swarm node, the exec fails silently and
+cron never runs.
+
+**Swarm approach:** Add a `nextcloud-cron` sidecar container to the Nextcloud
+stack definition, pinned to the same node as the main Nextcloud container via
+placement constraints.
+
+### Steps
+
+**2a.** Choose which swarm node will host Nextcloud (e.g. `ha-docker-1`).
+Label that node:
+
+```bash
+# On either swarm manager:
+docker node update --label-add nextcloud=true ha-docker-1
+```
+
+**2b.** In the Nextcloud stack compose file, add the sidecar and pin both
+services to the labelled node:
+
+```yaml
+services:
+  nextcloud-webapp:
+    image: nextcloud:production   # pin same version as CT 105
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.labels.nextcloud == true
+    # ... existing volumes, env, networks ...
+
+  nextcloud-cron:
+    image: nextcloud:production   # same image, different entrypoint
+    entrypoint: /cron.sh
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.labels.nextcloud == true   # must co-locate with webapp
+    volumes:
+      # Same data volume as nextcloud-webapp so cron sees the same files.
+      - nextcloud-data:/var/www/html
+    # No ports exposed — cron only runs PHP inside the container.
+```
+
+`/cron.sh` is Nextcloud's built-in cron entrypoint.  It runs
+`php -f /var/www/html/cron.php` in a loop, sleeping for 5 minutes between
+runs — identical to the current systemd timer.
+
+**2c.** Migrate Nextcloud's data volume to the swarm:
+
+```
+/mnt/docker/volumes/nextcloud-data/  →  already on NFS, no migration needed
+/mnt/docker/databases/nextcloud/     →  already on NFS, no migration needed
+```
+
+The NFS paths are identical on the swarm nodes (`mount-data.nix` mounts the
+same shares from the same VIP).  Stop Nextcloud on CT 105, deploy on the
+swarm, confirm it starts cleanly.
+
+**2d.** Remove `nextcloud-cron-job.nix` from `modules/build-types/docker.nix`
+and rebuild CT 105 after confirming Nextcloud works on the swarm.
+
+---
+
+## 3. docker-health-to-gotify — update for swarm awareness
+
+**Current state (CT 105):** The script at
+`/home/nixos/docker/monitoring/gotify/docker-health-to-gotify.sh` runs every
+minute, calls `docker ps --filter health=unhealthy`, and notifies Gotify.
+
+**Swarm behaviour:** The same script runs on both swarm nodes independently,
+each monitoring its own local Docker daemon.  This gives per-node coverage
+across the swarm.
+
+**Changes needed in the script** (edit the copy on the NFS volume — it takes
+effect on both nodes simultaneously on the next timer fire):
+
+### 3a. Strip the Swarm task suffix from service names
+
+In swarm mode, `docker ps --format '{{.Names}}'` returns names like
+`nextcloud-webapp.1.abc123xyz`.  The notification should show `nextcloud-webapp`,
+not the full task name.
+
+```bash
+# Before:
+CONTAINER_NAME=$(docker ps --format '{{.Names}}' ...)
+
+# After:
+CONTAINER_NAME=$(docker ps --format '{{.Names}}' ... | cut -d. -f1)
+```
+
+### 3b. Include the reporting node in the Gotify message
+
+Add `$(hostname)` to the notification payload so you know which swarm node
+detected the problem:
+
+```bash
+MESSAGE="[$(hostname)] ${CONTAINER_NAME} is unhealthy"
+```
+
+### 3c. Extend to catch swarm service replica failures
+
+`docker ps` only shows what's running locally.  If a service has zero healthy
+replicas (task crash-looping) it may not show up on either node's `docker ps`
+at the same moment.  Add a swarm-level check:
+
+```bash
+# Run only on managers (both ha-docker nodes are managers):
+if docker info --format '{{.Swarm.ControlAvailable}}' 2>/dev/null | grep -q true; then
+  # Find services where running replicas < desired replicas
+  docker service ls --format '{{.Name}}\t{{.Replicas}}' | \
+    awk -F'\t' '$2 !~ /^[0-9]+\/[0-9]+$/ || split($2,a,"/") && a[1] < a[2] { print $1, $2 }' | \
+    while read -r svc_name replicas; do
+      # Send Gotify notification for degraded service
+      curl -s -X POST "${GOTIFY_URL}/message" \
+        -H "X-Gotify-Key: ${GOTIFY_TOKEN}" \
+        -d "title=Swarm service degraded" \
+        -d "message=[$(hostname)] ${svc_name}: ${replicas} replicas"
+    done
+fi
+```
+
+This catches the case where a service's desired replicas are not running
+(e.g. OOM kill, image pull failure) — a failure mode that doesn't produce a
+Docker health event on any node.
+
+---
+
+## 4. Passbolt migration
+
+Passbolt has strict data integrity requirements.  Migrate with care:
+
+1. **Backup first** — `docker exec passbolt-webapp php /usr/share/php/passbolt/bin/cake passbolt export_keys` and a database dump.
+2. Database is on NFS (`/mnt/docker/databases/passbolt/`) — no data copy needed.
+3. Pin Passbolt to a specific node: `docker node update --label-add passbolt=true ha-docker-1`
+4. Add placement constraint `node.labels.passbolt == true` to the Passbolt stack.
+5. Stop on CT 105, deploy on swarm, verify login works.
+6. Test email delivery and 2FA.
+
+---
+
+## 5. Gitea migration
+
+Gitea's data directory is on NFS (`/mnt/docker/volumes/gitea-data/`).
+
+1. Stop Gitea on CT 105: `docker stop gitea`
+2. Deploy to swarm with placement constraint (pin to `ha-docker-1` initially).
+3. Verify web UI and SSH clone/push work.
+4. Update DNS: `gitea.lan.ddnsgeek.com` → swarm Traefik endpoint.
+5. Update the flake remote URL in `variables.nix` (`giteaDomain`) if the address changes.
+
+---
+
+## 6. Other services
+
+Deploy remaining services (Grafana, InfluxDB, NodeRed, Prometheus, etc.)
+as swarm stacks.  Most have no special migration concern — they use NFS
+volumes already on the shared storage.
+
+Services with stateful databases (PostgreSQL, MariaDB) should follow the
+pattern: stop on CT 105, confirm NFS database directory is intact, deploy on
+swarm, verify.
+
+---
+
+## 7. Monitoring — Beszel
+
+The Beszel hub runs on CT 105 (`docker.sweet.home:8090`).  Both swarm nodes
+run `beszel-agent` (from `modules/beszel/enable-agent.nix`), pointing at the
+existing hub URL.
+
+No migration needed for Beszel itself during the container migration.  Once
+all services are on the swarm, you may wish to move the Beszel hub too (as a
+swarm service with a placement constraint) but this is optional.
+
+---
+
+## 8. DNS cutover
+
+When a service is confirmed working on the swarm, update the FreeIPA DNS
+A record from the CT 105 IP (192.168.2.225) to a swarm node IP or, when a
+shared Traefik frontend is in place, to a round-robin record across both nodes.
+
+**Recommended approach — Traefik as the single entry point:**
+
+```
+service.lan.ddnsgeek.com  →  Traefik on swarm (global mode)
+docker.sweet.home         →  keep as 192.168.2.225 (CT 105) until fully decommissioned
+```
+
+For LAN-only services using `*.sweet.home` names, update FreeIPA directly:
+
+```bash
+# On domain-controller (or via SSH):
+ipa dnsrecord-mod sweet.home nextcloud --a-rec=192.168.2.230
+# Add 192.168.2.231 as a second A record for round-robin (optional):
+ipa dnsrecord-add sweet.home nextcloud --a-rec=192.168.2.231
+```
+
+Services behind Traefik don't need their own DNS updates — only Traefik's
+own entry point IPs need to change.
+
+---
+
+## 9. NixOS cleanup — CT 105
+
+Once all services are migrated:
+
+**Remove from `modules/build-types/docker.nix`:**
+- `../docker/nextcloud-cron-job.nix` — replaced by sidecar container
+- `../traefik/rotate-logs.nix` — replaced by Docker log driver
+
+**Keep in `modules/build-types/docker.nix` until CT 105 is decommissioned:**
+- `../docker/docker-health-to-gotify.nix` — still monitors CT 105's own daemon
+- Everything else
+
+**When decommissioning CT 105:**
+1. Confirm all NFS volumes are in use only by swarm services (not CT 105).
+2. Stop CT 105: `pct stop 105` on pve1.
+3. Archive/remove the `lxc-docker` and `proxmox-docker` targets from `flake.nix`.
+4. Remove `hosts/docker/`, `modules/build-types/docker.nix`, and `modules/docker/`.
+5. Update `variables.nix` to remove `dockerIp`, `dockerStorageIp`, `dockerHost`
+   (or reassign `dockerHost` to point at a swarm node for Beszel hub resolution).
+
+---
+
+## Rollback
+
+Any stack can be rolled back to CT 105 independently:
+
+```bash
+# On CT 105:
+docker start <service-name>
+# Update DNS A record back to 192.168.2.225
+ipa dnsrecord-mod sweet.home <service> --a-rec=192.168.2.225
+```
+
+CT 105 remains running throughout the cutover.  Only decommission it after
+every service is confirmed stable on the swarm and you have run one full
+backup cycle from the new hosts.

docs/ip-addressing.md

@@ -0,0 +1,228 @@
+# 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 |
+| Swarm cluster | 30 | `192.168.30.0/24` | Docker Swarm gossip (TCP/UDP 7946) + VXLAN overlay (UDP 4789) | No — internal `vmbr3` only, no uplink |
+
+When expanded to a second Proxmox node, VLAN 10 (cluster), VLAN 20 (storage-client), and VLAN 30 (swarm) all share
+the same inter-node trunk NIC via 802.1q VLAN tagging — different VLAN IDs, same physical cable.
+
+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.
+
+Four zones correspond to the four subnets. 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 (CT 105 — existing single-host) | 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 |
+| `192.168.2.231` | ha-docker-2 | Docker Swarm node 2 — management NIC | Active |
+| `192.168.2.230` | ha-docker-1 | Docker Swarm node 1 — management NIC | 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 (CT 105) |
+| `192.168.20.231` | ha-docker-2 | Storage-client NIC (ens19 / vmbr2) — NFS client |
+| `192.168.20.230` | ha-docker-1 | Storage-client NIC (ens19 / 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.
+
+---
+
+## Swarm cluster network — VLAN 30 — 192.168.30.0/24
+
+Internal to pve1 only. Proxmox bridge `vmbr3`, no physical NIC attached.
+Carries Docker Swarm inter-node traffic only: Raft consensus (TCP 2377),
+Serf gossip (TCP/UDP 7946), and VXLAN overlay data path (UDP 4789).
+Docker Swarm is initialised with `--advertise-addr` and `--data-path-addr`
+both pointing to this subnet so all cluster traffic stays on `vmbr3` and
+never crosses the LAN.
+
+| IP | Hostname | Interface / role |
+|---|---|---|
+| `192.168.30.231` | ha-docker-2 | Swarm cluster NIC (ens20 / vmbr3) |
+| `192.168.30.230` | ha-docker-1 | Swarm cluster NIC (ens20 / vmbr3) |
+| — | no gateway | Isolated — not routed to LAN or internet |
+
+### DNS zone: `swarm.home` — VLAN 30 (192.168.30.x)
+
+| Hostname | A record | Notes |
+|---|---|---|
+| `ha-docker-1.swarm.home` | `192.168.30.230` | Swarm NIC — debugging only |
+| `ha-docker-2.swarm.home` | `192.168.30.231` | Swarm NIC — debugging only |
+
+Operators reach the Docker API on the LAN IPs (`192.168.2.230`/`.231`), not these addresses.
+The `swarm.home` records exist for diagnostic convenience (e.g. confirming `vmbr3` routing).
+
+### Multi-node Proxmox expansion
+
+When a second Proxmox node (pve2) is added, VLAN 10 (cluster), VLAN 20 (storage-client),
+and VLAN 30 (swarm) all extend to pve2 via 802.1q VLAN tagging on the inter-node trunk
+link. All three internal networks share the same physical NIC between hypervisors —
+VLAN tags provide the logical separation.
+

docs/pxe-boot.md

@@ -15,6 +15,7 @@ rescue/inspection use.
 - 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:
@@ -28,32 +29,51 @@ 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/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` unless a menu entry expects files in a specific
-directory such as `/srv/pxe/http/auto-installer`.
+`/srv/pxe/http/images` is a symlink to `/mnt/pxe-images`, which is an NFS
+mount of `server.sweet.home:/tank/pxe-boot/images`
+(`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://192.168.2.247/menu.ipxe
+  -> http://192.168.2.223/boot.ipxe
+  -> http://192.168.2.223/menu.ipxe
 ```
 
 The generated menu currently exposes entries for:
 
 - NixOS Auto-Installer
 - NixOS Minimal
+- Debian Minimal
+- FreeIPA Server (Rocky Linux 9)
 - SystemRescue environment
 - iPXE shell
 - Reboot
@@ -84,19 +104,82 @@ 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:
 
 ```text
 /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.
 
@@ -113,6 +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.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": 1784350909,
-        "narHash": "sha256-ZWyzLbS1yKUTeFJLmdVuWNnHttL333/ldJbEE+KzCrM=",
+        "lastModified": 1785119570,
+        "narHash": "sha256-Rgs2xKnGLFWQscxUaXX07oyZeuMDOHEbqDOsgliLFGM=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "4ce190229c73d44536caa7072f6308fb2d8feeb3",
+        "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": 1784432872,
-        "narHash": "sha256-n3gKTBIV4ZA5VQpUakffBe3KGu4+mhPoA34rrqS0GkA=",
+        "lastModified": 1785133411,
+        "narHash": "sha256-Yjv0WEg39KRYS0rBdTbu6Fc/or/ihAKk13W9sQ6VWd0=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "fd1462031fdee08f65fd0b4c6b64e22239a77870",
+        "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:
@@ -32,15 +45,31 @@
       # (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}";
+          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
@@ -80,9 +109,6 @@
         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; };
@@ -96,11 +122,17 @@
         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-exit-node = mkTarget { platform = "linode"; buildType = "tailscale-exit-node"; hostPath = ./hosts/tailscale-exit-node/host.nix; };
-        proxmox-tailscale-exit-node = mkTarget { platform = "proxmox"; buildType = "tailscale-exit-node"; hostPath = ./hosts/tailscale-exit-node/host.nix; };
-        lxc-tailscale-exit-node = mkTarget { platform = "lxc"; buildType = "tailscale-exit-node"; hostPath = ./hosts/tailscale-exit-node/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"; };
+
+        proxmox-ha-docker-1 = mkTarget { platform = "proxmox"; buildType = "ha-docker"; hostPath = ./hosts/ha-docker-1/host.nix; nameSuffix = "-1"; };
+        proxmox-ha-docker-2 = mkTarget { platform = "proxmox"; buildType = "ha-docker"; hostPath = ./hosts/ha-docker-2/host.nix; nameSuffix = "-2"; };
       };
 
       # Auto-install environments (migrated from the former nix-auto-installer
@@ -171,7 +203,11 @@
               (modulesPath + "/installer/netboot/netboot-minimal.nix")
             ];
           })
-          { networking.hostName = "nixos-minimal"; }
+          {
+            networking.hostName = "nixos-minimal";
+            system.stateVersion = "26.05";
+            boot.zfs.forceImportRoot = false;
+          }
         ];
       };
 

hosts/docker/host.nix

@@ -1,10 +1,24 @@
-_:
+{ vars, ... }:
 
 {
-  networking.hostName = "docker";
-  networking.hostId = "007f0200";
+  networking = {
+    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-docker-1/host.nix

@@ -0,0 +1,34 @@
+{ vars, ... }:
+{
+  networking = {
+    hostName = vars.haDocker1Host;
+    hostId   = "a1d0c4e1";
+    useDHCP  = false;
+    interfaces = {
+      # ens18 — LAN management NIC (vmbr0, 192.168.2.0/24)
+      ${vars.vmLanInterface}.ipv4.addresses = [{
+        address      = vars.haDocker1Ip;
+        prefixLength = vars.lanPrefixLength;
+      }];
+      # ens19 — storage-client NIC (vmbr2, 192.168.20.0/24) — NFS from HA cluster
+      ${vars.haDockerStorageInterface}.ipv4.addresses = [{
+        address      = vars.haDocker1StorageIp;
+        prefixLength = vars.haClientPrefixLength;
+      }];
+      # ens20 — swarm cluster NIC (vmbr3, 192.168.30.0/24) — Docker gossip + VXLAN
+      ${vars.haDockerSwarmInterface}.ipv4.addresses = [{
+        address      = vars.haDocker1SwarmIp;
+        prefixLength = vars.haDockerSwarmPrefixLength;
+      }];
+    };
+    defaultGateway = { address = vars.lanGateway; interface = vars.vmLanInterface; };
+    nameservers    = [ vars.domainControllerIp ];
+  };
+
+  # Only register the LAN IP with IPA DNS.  Without this, sssd dyndns
+  # would also register Docker bridge IPs (172.x.x.x) and the storage/swarm
+  # NIC IPs as A records for ha-docker-1.sweet.home.
+  security.ipa.dyndns.interface = vars.vmLanInterface;
+
+  system.stateVersion = "26.05";
+}

hosts/ha-docker-2/host.nix

@@ -0,0 +1,32 @@
+{ vars, ... }:
+{
+  networking = {
+    hostName = vars.haDocker2Host;
+    hostId   = "a2d0c4e2";
+    useDHCP  = false;
+    interfaces = {
+      # ens18 — LAN management NIC (vmbr0, 192.168.2.0/24)
+      ${vars.vmLanInterface}.ipv4.addresses = [{
+        address      = vars.haDocker2Ip;
+        prefixLength = vars.lanPrefixLength;
+      }];
+      # ens19 — storage-client NIC (vmbr2, 192.168.20.0/24) — NFS from HA cluster
+      ${vars.haDockerStorageInterface}.ipv4.addresses = [{
+        address      = vars.haDocker2StorageIp;
+        prefixLength = vars.haClientPrefixLength;
+      }];
+      # ens20 — swarm cluster NIC (vmbr3, 192.168.30.0/24) — Docker gossip + VXLAN
+      ${vars.haDockerSwarmInterface}.ipv4.addresses = [{
+        address      = vars.haDocker2SwarmIp;
+        prefixLength = vars.haDockerSwarmPrefixLength;
+      }];
+    };
+    defaultGateway = { address = vars.lanGateway; interface = vars.vmLanInterface; };
+    nameservers    = [ vars.domainControllerIp ];
+  };
+
+  # Only register the LAN IP with IPA DNS — same reasoning as ha-docker-1.
+  security.ipa.dyndns.interface = vars.vmLanInterface;
+
+  system.stateVersion = "26.05";
+}

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/nix-cache/host.nix

@@ -1,18 +1,15 @@
 { vars, ... }:
 
 {
-  imports = [
-    (import ../../modules/beszel/host-token.nix {
-      name = "nix-cache";
-      sopsFile = ../../secrets/nix-cache.yaml;
-    })
-  ];
-
-  networking.hostName = vars.nixCacheHost;
-
-  services.beszel.agent.environment = {
-    #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
-    KEY = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFPR9kwtC4TAeTRu46A7+opZsYpxqkRJ+x/ZyB2GWCeG";
+  networking = {
+    hostName = vars.nixCacheHost;
+    useDHCP = false;
+    interfaces.${vars.lxcLanInterface}.ipv4.addresses = [{
+      address = vars.nixCacheIp;
+      prefixLength = vars.lanPrefixLength;
+    }];
+    defaultGateway = { address = vars.lanGateway; interface = vars.lxcLanInterface; };
+    nameservers = [ vars.domainControllerIp ];
   };
 
   # Preserved from the pre-refactor `nix-cache` target — stateVersion must

hosts/nixos/home.nix

@@ -20,12 +20,14 @@
       #    vscode
       chromium
       claude-code
+      fish
+      sops
     ];
 
     # Optional: set environment vars
     sessionVariables = {
-      EDITOR = "vim";
-      SOPS_AGE_KEY_FILE = "/home/nixos/Nextcloud/Filing Cabinet/keys/nixos-sops-age-key-txt";
+      EDITOR = "nano";
+      SOPS_AGE_KEY_FILE = "${config.home.homeDirectory}/.config/sops/age/keys.txt";
     };
 
     file = {

hosts/pxe-boot/host.nix

@@ -1,8 +1,17 @@
-_:
+{ 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 = { };
   # 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 @@
-{ vars, ... }:
-
-{
-  imports = [
-    (import ../../modules/beszel/host-token.nix {
-      name = "server";
-      sopsFile = ../../secrets/server.yaml;
-    })
-  ];
-
-  networking.hostName = vars.nfsServerHost;
-  networking.hostId = "6689f93e";
-
-  services.beszel.agent.environment = {
-    #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
-    KEY = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFPR9kwtC4TAeTRu46A7+opZsYpxqkRJ+x/ZyB2GWCeG";
-    EXTRA_FILESYSTEMS = "${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
-    LOG_LEVEL = "debug";
-  };
-
-  # Preserved from the pre-refactor `server` target — stateVersion must never
-  # be bumped on an already-installed machine.
-  system.stateVersion = "25.05";
-}

hosts/tailscale-exit-node/host.nix

@@ -1,12 +0,0 @@
-_:
-
-{
-  networking.hostName = "exit-node";
-
-  # No networking.hostId: only ZFS-touching hosts (server, docker) 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";
-}

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

@@ -1,10 +1,19 @@
-_:
+{ vars, ... }:
 
 {
-  networking.hostName = "tor-relay";
+  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 (server, docker) need one
-  # for pool-import safety, and this host does neither.
+  # 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.

modules/beszel/enable-agent.nix

@@ -1,10 +1,23 @@
-{ vars, ... }:
+{ config, vars, ... }:
 
 {
-  services.beszel.agent.enable = true;
-  services.beszel.agent.environment = {
-    #DOCKER_HOST = "tcp://docker-socket-proxy:2375";
-    HUB_URL = "http://${vars.dockerHost}.${vars.homeDomain}:${toString vars.ports.beszelHub}";
+  # Universal token shared by all beszel agents. Add to secrets/common.yaml:
+  #   sops secrets/common.yaml
+  #   beszel-token: <value from the beszel hub UI>
+  sops.secrets."beszel-token" = { };
+
+  sops.templates."beszel.env".content = ''
+    TOKEN=${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

modules/beszel/host-token.nix

@@ -1,11 +0,0 @@
-{ name, sopsFile }:
-
-{ config, ... }:
-
-{
-  sops.secrets."beszel-token".sopsFile = sopsFile;
-  sops.templates."${name}-beszel.env".content = ''
-    TOKEN=${config.sops.placeholder."beszel-token"}
-  '';
-  services.beszel.agent.environmentFile = config.sops.templates."${name}-beszel.env".path;
-}

modules/build-types/docker.nix

@@ -15,7 +15,6 @@
     ../docker/enable-service.nix
     ../docker/nextcloud-cron-job.nix
     ../docker/docker-health-to-gotify.nix
-    ../tailscale/enable-service.nix
     ../traefik/rotate-logs.nix
     ../raspi/mount-data.nix
     ../services/enable-rpcbind.nix

modules/build-types/gui.nix

@@ -1,6 +1,17 @@
 { 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.stdenv.hostPlatform.system}.nixos-conf-editor
     nodejs
@@ -18,7 +29,7 @@
   ];
 
   boot.loader.grub.useOSProber = true;
-programs.direnv.enable = true;
+  programs.direnv.enable = true;
   services = {
     xserver = {
       enable = true;
@@ -70,4 +81,70 @@ programs.direnv.enable = true;
   programs.firefox.enable = true;
 
   nixpkgs.config.allowUnfree = true;
+
+  # GUI-specific Home Manager additions for the IPA primary user, extending
+  # the baseline in modules/ipa/client.nix with desktop apps and services
+  # that only make sense on a graphical workstation.
+  home-manager.users.${vars.ipaUser} = { pkgs, ... }: {
+    home = {
+      packages = with pkgs; [
+        git
+        vim
+        nextcloud-client
+        chromium
+        claude-code
+        fish
+        sops
+      ];
+      sessionVariables = {
+        EDITOR = "nano";
+        SOPS_AGE_KEY_FILE = "/home/${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-docker.nix

@@ -0,0 +1,84 @@
+# Docker Swarm node build type.
+#
+# Produces NixOS hosts that form a Docker Swarm manager cluster.  Two nodes
+# (ha-docker-1, ha-docker-2) are both managers so either can accept Docker
+# API and `docker stack` commands.
+#
+# Key differences from the existing `docker` build type (used by CT 105):
+#   - nextcloud-cron-job.nix is EXCLUDED — `docker exec` breaks in swarm
+#     because the target container may be on the other node.  The cron job
+#     is replaced by a nextcloud-cron sidecar in the Nextcloud stack.
+#     See docs/internal/docker-swarm-cutover.md.
+#   - traefik/rotate-logs.nix is EXCLUDED — log rotation moves to Docker's
+#     json-file log driver (max-size/max-file on the Traefik service
+#     definition).  See docs/internal/docker-swarm-cutover.md.
+#   - raspi/mount-data.nix is EXCLUDED — specific to CT 105's backup role.
+#   - Swarm firewall ports (2377/tcp, 7946/tcp+udp, 4789/udp) are opened
+#     on the swarm NIC (ens20/vmbr3) only.
+#   - checkReversePath = "loose" is required for the Swarm ingress routing
+#     mesh: VXLAN return traffic is asymmetric (arrives ens20, exits ens18).
+#   - beszel-agent is enabled for host-level monitoring.
+{ pkgs, vars, ... }:
+
+{
+  # Pin Docker Engine to version 29, matching CT 105, so image layers cached
+  # on NFS volumes remain compatible across old and new hosts.
+  nixpkgs.overlays = [
+    (final: prev: {
+      docker     = prev.docker_29;
+      docker_cli = prev.docker_29;
+    })
+  ];
+
+  imports = [
+    ../docker/enable-service.nix
+    ../docker/mount-data.nix
+    ../docker/docker-health-to-gotify.nix
+    ../beszel/enable-agent.nix
+    ../services/enable-rpcbind.nix
+  ];
+
+  environment.systemPackages = with pkgs; [
+    nfs-utils
+  ];
+
+  boot.supportedFilesystems = [ "nfs" ];
+
+  systemd.tmpfiles.rules = [
+    # Symlink ~/docker → NFS config mount so the docker-health-to-gotify
+    # script (and operator convenience) resolves ~/docker/... correctly.
+    "L+ /home/${vars.primaryUser}/docker - - - - ${vars.nfsShares.dockerConfig.mountpoint}"
+    "d /mnt/docker 0755 ${vars.primaryUser} users -"
+  ];
+
+  users.users.${vars.primaryUser}.extraGroups = [ "docker" ];
+
+  networking.firewall = {
+    # LAN-facing service ports — same as the existing docker build type.
+    allowedTCPPorts = [
+      vars.ports.dockerHttp
+      vars.ports.dockerHttps
+      vars.ports.dockerExtra
+      vars.ports.beszelHub
+    ];
+
+    # Swarm inter-node ports restricted to the swarm NIC (ens20/vmbr3).
+    # vmbr3 is an isolated internal bridge — no LAN reachability.
+    interfaces.${vars.haDockerSwarmInterface} = {
+      allowedTCPPorts = [
+        vars.ports.dockerSwarmMgmt  # 2377 — Raft + cluster management
+        vars.ports.dockerSwarmDisc  # 7946 — Serf gossip (TCP half)
+      ];
+      allowedUDPPorts = [
+        vars.ports.dockerSwarmDisc  # 7946 — Serf gossip (UDP half)
+        vars.ports.dockerSwarmVxlan # 4789 — VXLAN overlay data path
+      ];
+    };
+
+    # Docker Swarm ingress routing mesh creates asymmetric routes: a request
+    # arrives on ens18 (LAN) for a container that lives on ens20's VXLAN
+    # overlay; the return path differs from the incoming interface.  Strict
+    # rp_filter drops these packets.  "loose" allows them.
+    checkReversePath = "loose";
+  };
+}

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/pxe-boot.nix

@@ -6,6 +6,10 @@ let
   tftpRoot = "${pxeRoot}/tftp";
   pxeBaseUrl = "http://${vars.pxeServerIp}";
 
+  # Base network address extracted from lanCidr (e.g. "192.168.2.0" from
+  # "192.168.2.0/24") — used by dnsmasq's proxy DHCP range directive.
+  lanBaseAddr = lib.head (lib.splitString "/" vars.lanCidr);
+
   bootIpxe = pkgs.writeText "boot.ipxe" ''
     #!ipxe
 
@@ -21,6 +25,216 @@ 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 ${vars.ipaServer}.
+  # Installs Rocky Linux 9, sets a static IP, creates ${vars.ipaUser} 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: ${vars.ipaServer}  ${vars.domainControllerIp}
+
+    url --url=${rockyMirror}/BaseOS/${rockyArch}/os/
+    repo --name=appstream --baseurl=${rockyMirror}/AppStream/${rockyArch}/os/
+
+    lang en_US.UTF-8
+    keyboard us
+    timezone UTC --utc
+
+    # DHCP during install; static IP configured in %post via NM config file
+    network --bootproto=dhcp --device=link --activate
+    network --hostname=${vars.ipaServer}
+
+    selinux --enforcing
+    firewall --enabled --service=ssh
+
+    rootpw --lock
+    user --name=${vars.ipaUser} --groups=wheel --shell=/bin/bash
+    sshkey --username=${vars.ipaUser} "${vars.adminSshKey}"
+
+    zerombr
+    clearpart --all --initlabel --drives=sda
+    # Keep net.ifnames=0 biosdevname=0 in the installed GRUB so the NIC
+    # stays eth0 after reboot (matches the NM connection file below).
+    bootloader --location=mbr --boot-drive=sda --append="net.ifnames=0 biosdevname=0"
+
+    part /boot --fstype=xfs --size=1024 --ondisk=sda
+    part swap  --fstype=swap --size=2048 --ondisk=sda
+    part /     --fstype=xfs  --grow --size=1 --ondisk=sda --asprimary
+
+    %packages
+    @^minimal-environment
+    ipa-server
+    ipa-server-dns
+    %end
+
+    reboot
+
+    %post --log=/root/ks-post.log
+    set -euo pipefail
+
+    # -- Static IP: write NM connection file directly (NM not running in chroot) --
+    mkdir -p /etc/NetworkManager/system-connections
+    cat > /etc/NetworkManager/system-connections/eth0.nmconnection << 'NMCONN'
+    [connection]
+    id=eth0
+    type=ethernet
+    interface-name=eth0
+    autoconnect=true
+
+    [ethernet]
+
+    [ipv4]
+    method=manual
+    addresses=${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} ${vars.ipaServer} domain-controller' >> /etc/hosts
+
+    # -- Generate IPA passwords and store securely --
+    DM_PASS=$(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 $NF}')
+
+    ipa-server-install \
+      --realm=${lib.strings.toUpper vars.homeDomain} \
+      --domain=${vars.homeDomain} \
+      --hostname=${vars.ipaServer} \
+      --ds-password="$DM_PASS" \
+      --admin-password="$ADMIN_PASS" \
+      --setup-dns \
+      --forwarder=${vars.domainControllerIp} \
+      --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
 
@@ -68,11 +282,13 @@ let
     set base ${pxeBaseUrl}
 
     menu PXE Boot Menu
-    item auto-installer NixOS Auto-Installer
-    item nixos-minimal NixOS Minimal
-    item rescue Rescue Environment
-    item shell iPXE Shell
-    item reboot Reboot
+    item auto-installer    NixOS Auto-Installer
+    item nixos-minimal     NixOS Minimal
+    item debian            Debian Minimal
+    item rocky-freeipa     FreeIPA Server (Rocky Linux 9)
+    item rescue            Rescue Environment
+    item shell             iPXE Shell
+    item reboot            Reboot
 
     choose target && goto ''${target}
 
@@ -82,6 +298,12 @@ let
     :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
 
@@ -95,6 +317,8 @@ in
 {
   imports = [
     ../pxe-boot/stage-installer-artifacts.nix
+    ../pxe-boot/mount-pxe-images.nix
+    ../beszel/enable-agent.nix
   ];
 
   environment.systemPackages = with pkgs; [
@@ -121,45 +345,107 @@ in
     atftpd = {
       enable = true;
       root = tftpRoot;
-      extraOptions = [
-        "--verbose=5"
-      ];
+      extraOptions = [ "--verbose=5" ];
     };
 
     openssh.settings.PermitRootLogin = "yes";
   };
 
-  systemd.tmpfiles.rules = [
-    "d ${pxeRoot} 0755 root root -"
-    "d ${httpRoot} 0755 root root -"
-    "d ${httpRoot}/images 0755 root root -"
-    "d ${httpRoot}/auto-installer 0755 root root -"
-    "d ${httpRoot}/nixos-minimal 0755 root root -"
-    "d ${httpRoot}/systemrescue 0755 root root -"
-    "d ${httpRoot}/ubuntu 0755 root root -"
-    "d ${httpRoot}/rescue 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}/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"
+  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"
     ];
-    wantedBy = [ "multi-user.target" ];
-    serviceConfig = {
-      Type = "oneshot";
-      ExecStart = stageSystemRescue;
+
+    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 ${rockyRelease} pxeboot kernel and initrd for HTTP PXE boot";
+        after = [
+          "local-fs.target"
+          "systemd-tmpfiles-setup.service"
+          "network-online.target"
+        ];
+        wants = [ "network-online.target" ];
+        wantedBy = [ "multi-user.target" ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = fetchRockyPxeboot;
+          RemainAfterExit = true;
+        };
+      };
+
+      stage-systemrescue = {
+        description = "Stage SystemRescue ISO contents for HTTP PXE boot";
+        after = [
+          "local-fs.target"
+          "systemd-tmpfiles-setup.service"
+        ];
+        wantedBy = [ "multi-user.target" ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = stageSystemRescue;
+        };
+      };
+    };
+  };
+
+  services.dnsmasq = {
+    enable = true;
+    settings = {
+      # Disable DNS listener — only proxy DHCP is needed here.
+      # Without this dnsmasq tries to bind port 53 which systemd-resolved
+      # already owns, causing startup failure.
+      port = 0;
+      dhcp-range = [ "${lanBaseAddr},proxy" ];
+      dhcp-match = [
+        "set:ipxe,175"
+        "set:efi64,option:client-arch,7"
+        "set:efi64,option:client-arch,9"
+      ];
+      dhcp-userclass = "set:ipxe,iPXE";
+      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}"
+      ];
     };
   };
 
   networking.firewall.allowedTCPPorts = [ vars.ports.pxeBootHttp ];
-  networking.firewall.allowedUDPPorts = [ vars.ports.pxeBootTftp ];
+  networking.firewall.allowedUDPPorts = [ vars.ports.pxeBootTftp vars.ports.dhcp ];
 }

modules/build-types/server.nix

@@ -1,28 +0,0 @@
-{ vars, lib, ... }:
-
-{
-  imports = [
-    ../beszel/enable-agent.nix
-    ../services/zfs/enable-service.nix
-  ];
-
-  boot.zfs.extraPools = [ (lib.removePrefix "/" vars.storageRoot) ];
-
-  systemd.services.nfs-server = {
-    after = [ "zfs-mount.service" ];
-    requires = [ "zfs-mount.service" ];
-  };
-
-  services.nfs.server = {
-    enable = true;
-    exports = ''
-      ${vars.storageRoot}/${vars.nfsShares.dockerConfig.subpath} ${vars.lanCidr}(rw,sync,no_subtree_check,no_root_squash)
-      ${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath} ${vars.lanCidr}(rw,sync,no_subtree_check,no_root_squash)
-      ${vars.storageRoot}/${vars.nfsShares.dockerDatabases.subpath} ${vars.lanCidr}(rw,sync,no_subtree_check,no_root_squash)
-      ${vars.storageRoot}/${vars.nfsShares.nextcloudData.subpath} ${vars.lanCidr}(rw,sync,no_subtree_check,no_root_squash)
-      ${vars.storageRoot}/${vars.nfsShares.raspiVolumes.subpath} ${vars.lanCidr}(rw,sync,no_subtree_check,no_root_squash)
-    '';
-  };
-
-  networking.firewall.allowedTCPPorts = [ vars.ports.nfsRpcbind vars.ports.nfsd ];
-}

modules/build-types/tailscale-exit-node.nix

@@ -1,21 +0,0 @@
-{ ... }:
-
-{
-  imports = [
-    ../tailscale/exit-node.nix
-  ];
-
-  # "server", not "both": this build type only ever advertises itself as an
-  # exit node (see ../tailscale/exit-node.nix) -- it doesn't advertise LAN
-  # subnet routes, so it doesn't need the "client"-side loose reverse-path
-  # filtering that "both" would also turn on. Deliberately left unbundled
-  # from LAN-subnet-route advertisement so this build type stays valid on
-  # every platform, including linode (a remote VPS with no network path to
-  # the home LAN at all).
-  services.tailscale.useRoutingFeatures = "server";
-
-  # Forwarded exit-node traffic arrives on tailscale0 already
-  # tailscale-authenticated -- the firewall's normal per-port allow-list
-  # would otherwise drop it. Standard NixOS/Tailscale exit-node guidance.
-  networking.firewall.trustedInterfaces = [ "tailscale0" ];
-}

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

@@ -3,5 +3,6 @@
 {
   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

@@ -1,50 +1,7 @@
-{ config, pkgs, lib, vars, ... }:
+_:
 
-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://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-  myTestCmd = ''
-    sudo nixos-rebuild test \
-      --no-write-lock-file \
-      --refresh \
-      --flake git+https://${vars.lanDomain}/beatzaplenty/nixos.git#$(cat /etc/flake-target)
-  '';
-
-  # lxc-* hosts pre-seed their SSH host key at build time (see
-  # modules/platforms/lxc.nix) so sops-nix's .sops.yaml recipient matches on
-  # first boot -- without it, secrets permanently fail to decrypt (see that
-  # file's comment for the confirmed failure). That requires --impure plus
-  # NIXOS_HOST_KEYS_DIR pointing at the repo's host-keys/ dir, same pattern
-  # docs/auto-installer.md uses for the installer ISO. A function, not a
-  # shellAlias, since the target name has to interpolate into the middle of
-  # the flake attribute path, not just append after it. Must be run from the
-  # repo root, same as every other host-keys/ command in this repo.
-  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
 {
-  programs.bash = {
-    enable = true;
-    shellAliases = {
-      "Switch-nix" = mySwitchCmd;
-      "Test-nix" = myTestCmd;
-    };
-    initExtra = buildImageFn;
-  };
+  # Switch-nix, Test-nix, and buildImage are defined system-wide in
+  # modules/common/configuration.nix so all users (including IPA accounts)
+  # get them. Add any Home-Manager-only per-user shell config here.
 }

modules/common/configuration.nix

@@ -1,31 +1,56 @@
 { config, lib, pkgs, vars, ... }:
 
+let
+  switchCmd = ''
+    sudo nixos-rebuild switch \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.giteaDomain}/${vars.giteaRepoPath}.git?dir=${vars.giteaRepoFlakePath}#$(cat /etc/flake-target)
+  '';
+  testCmd = ''
+    sudo nixos-rebuild test \
+      --no-write-lock-file \
+      --refresh \
+      --flake git+https://${vars.giteaDomain}/${vars.giteaRepoPath}.git?dir=${vars.giteaRepoFlakePath}#$(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 =
-    [
-      # Include the results of the hardware scan.
-      #      ./hardware-configuration.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
+  imports = [
+    ./set-locale.nix
+    ../ipa/client.nix
+  ];
 
-  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.
+  # modules/services/zfs/enable-service.nix. Harmless no-op on hosts without ZFS.
   boot.zfs.forceImportRoot = false;
 
-  # Set your time zone.
   time.timeZone = vars.timeZone;
 
-  # Enable QEMU agent
   services.qemuGuest.enable = true;
 
-  # Enable docker-compose
   environment.systemPackages = with pkgs; [
     vim
     btop
@@ -35,11 +60,10 @@
   ];
 
   # Secrets shared by every host, decrypted at activation via each host's
-  # existing SSH host key (sops-nix derives the age key from
-  # /etc/ssh/ssh_host_ed25519_key automatically — see modules/common/README
-  # or docs/ for the sops workflow). hashedPassword/hashedPasswordFile need
+  # SSH host key (sops-nix derives the age key from
+  # /etc/ssh/ssh_host_ed25519_key automatically). hashedPassword secrets need
   # neededForUsers so they're available before the normal secret-activation
-  # step, since user creation happens very early in boot.
+  # step — user creation happens very early in boot.
   sops = {
     defaultSopsFile = ../../secrets/common.yaml;
 
@@ -47,59 +71,52 @@
       "root-hashedPassword".neededForUsers = true;
       "nixos-hashedPassword".neededForUsers = true;
       "nix-github-token" = { };
+      "nix-gitea-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=${config.sops.placeholder."nix-github-token"}
+    # nix.conf has no *File-style option for access-tokens, so tokens are
+    # rendered into a runtime-only file (never touches the Nix store) and
+    # pulled in via nix.conf's native !include directive.
+    templates."nix-access-tokens.conf".content = ''
+      access-tokens = github.com=${config.sops.placeholder."nix-github-token"} ${vars.giteaDomain}=${config.sops.placeholder."nix-gitea-token"}
     '';
   };
 
   nix.extraOptions = ''
-    !include ${config.sops.templates."nix-github-token.conf".path}
+    !include ${config.sops.templates."nix-access-tokens.conf".path}
   '';
 
-  #Set root password
-  users.users.root = {
-    hashedPasswordFile = config.sops.secrets."root-hashedPassword".path;
+  users = {
+    # mutableUsers = false makes update-users-groups.pl enforce hashedPasswordFile
+    # on every activation, not just on newly-created accounts. Without this, a
+    # freshly-built proxmox disk image (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;
+
+    users.root = {
+      hashedPasswordFile = config.sops.secrets."root-hashedPassword".path;
+    };
+
+    users.${vars.primaryUser} = {
+      isNormalUser = true;
+      extraGroups = [ "wheel" ];
+      packages = with pkgs; [ tree ];
+      hashedPasswordFile = config.sops.secrets."nixos-hashedPassword".path;
+      openssh.authorizedKeys.keys = [ vars.adminSshKey ] ++ vars.extraAdminSshKeys;
+    };
   };
 
-  # Define a user account. Don't forget to set a password with ‘passwd’.
-  users.users.${vars.primaryUser} = {
-    isNormalUser = true;
-    extraGroups = [ "wheel" ]; # Enable ‘sudo’ for the user.
-    packages = with pkgs; [
-      tree
-    ];
-    hashedPasswordFile = config.sops.secrets."nixos-hashedPassword".path;
-    openssh.authorizedKeys.keys = [
-      vars.adminSshKey
-      "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
-    ];
-  };
-
-
-  # Enable the OpenSSH daemon.
   services.openssh.enable = true;
 
-  #Enable flakes
-
   nix.settings = {
     experimental-features = [ "nix-command" "flakes" ];
     auto-optimise-store = true;
   };
 
-
   programs.git = {
     enable = true;
     package = pkgs.git;
-    config = {
-      credential.helper = "store";
-    };
+    config.credential.helper = "store";
   };
-
-
-
 }

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/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;
     package = pkgs.docker;
-    #  listenOptions = [
-    #  "unix:///var/run/docker.sock"
-    #  "tcp://0.0.0.0:2375"
-    #];
-
-    #  daemon.settings = {
-    #    metrics-addr = "0.0.0.0:9323";
-    #    experimental = true;
-    #  };
   };
-
+  # Pin the docker group GID to match the IPA "docker-access" group so that
+  # 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.${vars.primaryUser}.extraGroups = [ "docker" ];
   environment.systemPackages = with pkgs; [
     docker-compose
     docker-buildx
   ];
+
+  # NixOS's group activation uses plain `groupmod` without --non-unique.
+  # When SSSD is active it exposes the IPA "docker-access" group at
+  # vars.dockerAccessGid via NSS, so groupmod sees that GID as already in
+  # use and silently skips the change (warning: "not applying GID change").
+  # This script runs after the normal "groups" step and applies the change
+  # with --non-unique (which lets the local docker group share the GID with
+  # the SSSD-provided IPA group). If the GID actually changed it also
+  # restarts docker.socket so the socket is recreated with the new GID.
+  system.activationScripts.docker-group-gid = {
+    deps = [ "groups" ];
+    text = ''
+      current=$(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

@@ -10,24 +10,19 @@ let
   # non-blocking behavior, so they don't need `nofail` too).
   automountOpts = if config.boot.isContainer then [ "nofail" ] else [ "x-systemd.automount" ];
 
-  # A bare hostname here never resolves reliably: systemd-resolved only
-  # ever tries LLMNR for single-label names (never DNS, regardless of any
-  # configured search domain), and a *global* search domain (the first fix
-  # attempted here) backfires worse -- confirmed live on lxc-docker, adding
-  # `networking.search` made systemd-resolved prioritize its domain-matched
-  # but server-less global scope over eth0's correctly-configured one for
-  # every "*.sweet.home" query, silently sending them to public fallback
-  # DNS instead. `resolvectl query --interface=eth0 server.sweet.home`
-  # resolved fine throughout, proving the LAN DNS server was never the
-  # problem -- only the ambient, unqualified device string was. Using the
-  # FQDN directly sidesteps all of that, matching the pattern
-  # ../raspi/mount-data.nix already uses for the same reason.
-  nfsServer = "${vars.nfsServerHost}.${vars.homeDomain}";
+  # 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 = {
     ${vars.nfsShares.dockerConfig.mountpoint} = {
-      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerConfig.subpath}";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerConfig.subpath}";
       fsType = "nfs";
 
       options = [
@@ -38,7 +33,7 @@ in
     };
 
     ${vars.nfsShares.dockerDatabases.mountpoint} = {
-      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerDatabases.subpath}";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerDatabases.subpath}";
       fsType = "nfs";
 
       options = [
@@ -49,7 +44,7 @@ in
     };
 
     ${vars.nfsShares.dockerVolumes.mountpoint} = {
-      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
       fsType = "nfs";
 
       options = [
@@ -60,7 +55,7 @@ in
     };
 
     ${vars.nfsShares.nextcloudData.mountpoint} = {
-      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.nextcloudData.subpath}";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.nextcloudData.subpath}";
       fsType = "nfs";
 
       options = [
@@ -71,7 +66,7 @@ in
     };
 
     ${vars.nfsShares.raspiVolumes.mountpoint} = {
-      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.raspiVolumes.subpath}";
+      device = "${nfsServer}:${storageRoot}/${vars.nfsShares.raspiVolumes.subpath}";
       fsType = "nfs";
 
       options = [

modules/ha/cluster-config.nix

@@ -0,0 +1,164 @@
+# 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 the nixos user so all admin keys can reach root.
+  users.users.root.openssh.authorizedKeys.keys = [ vars.adminSshKey ] ++ vars.extraAdminSshKeys;
+
+  # 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/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/nix-cache/client.nix

@@ -3,7 +3,7 @@
 {
   nix.settings = {
     substituters = [
-      "http://${vars.nixCacheHost}"
+      "http://${vars.nixCacheHost}.${vars.homeDomain}"
       "https://cache.nixos.org/"
     ];
     trusted-public-keys = [

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

@@ -8,12 +8,12 @@
   # 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 nix-store --version
+  #   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.${vars.nixCacheHost} = {
-    hostNames = [ vars.nixCacheHost ];
+  programs.ssh.knownHosts."${vars.nixCacheHost}.${vars.homeDomain}" = {
+    hostNames = [ "${vars.nixCacheHost}.${vars.homeDomain}" ];
     publicKey = vars.nixCacheHostKey;
   };
 
@@ -22,7 +22,7 @@
 
     buildMachines = [
       {
-        hostName = vars.nixCacheHost;
+        hostName = "${vars.nixCacheHost}.${vars.homeDomain}";
         sshUser = vars.remoteBuilderUser;
         sshKey = "/root/.ssh/id_ed25519";
         inherit (pkgs.stdenv.hostPlatform) system;

modules/nix-cache/server.nix

@@ -20,7 +20,7 @@
     nginx = {
       enable = true;
       recommendedProxySettings = true;
-      virtualHosts.${vars.nixCacheHost} = {
+      virtualHosts."${vars.nixCacheHost}.${vars.homeDomain}" = {
         locations."/" = {
           proxyPass = "http://${config.services.nix-serve.bindAddress}:${toString config.services.nix-serve.port}";
         };

modules/platforms/lxc.nix

@@ -52,6 +52,7 @@ in
   # LXC container does).
   imports = [
     (modulesPath + "/virtualisation/proxmox-lxc.nix")
+    ../common/preserve-ssh-host-key.nix
   ];
 
   proxmoxLXC = {
@@ -63,23 +64,22 @@ in
     # back to decide `pct create`'s --unprivileged flag, so the two stay
     # in sync).
     #
-    # lxc-docker is the one exception: 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). Keying off
-    # hostName rather than something docker-build-type-specific because
-    # modules/build-types/docker.nix is also composed for linode-docker/
-    # proxmox-docker, which don't import proxmox-lxc.nix at all --setting
-    # this option there would break their eval with "option does not
-    # exist" regardless of any mkIf guard, since mkIf only makes a value
-    # conditional, not whether the option needs to exist somewhere.
-    privileged = config.networking.hostName == "docker";
+    # 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 = {
@@ -112,9 +112,12 @@ in
   # 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. Regular secrets
-  # (nix-serve's key, beszel's token, etc.) work anyway because sops-nix
-  # provides its own systemd service for those.
+  # 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,
@@ -165,4 +168,41 @@ in
       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). Defined in
+  # variables.nix as haLanNfsFqdn; using the FQDN avoids systemd-resolved
+  # LLMNR quirks and survives a future VIP renumber via a DNS-only update.
+  nfsServer = vars.haLanNfsFqdn;
+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/tailscale/exit-node.nix

@@ -1,27 +0,0 @@
-_:
-
-{
-  imports = [ ./enable-service.nix ];
-
-  services.tailscale = {
-    # Enables the sysctl forwarding settings exit nodes/subnet routers need;
-    # without this, --advertise-exit-node has no effect.
-    useRoutingFeatures = "server";
-
-    # Lets peers reach this node directly over the tailscale UDP port
-    # instead of relaying through DERP.
-    openFirewall = true;
-
-    # extraSetFlags (tailscale set, via the always-on tailscaled-set
-    # service), not extraUpFlags -- extraUpFlags is only ever applied by
-    # tailscaled-autoconnect, which itself only runs when
-    # services.tailscale.authKeyFile is set (nothing in this repo sets one,
-    # so tailscale up is a manual, one-time operator step on every host that
-    # uses this service). extraSetFlags has no such gate, so
-    # --advertise-exit-node self-reapplies on every boot once the operator
-    # has authenticated the node once.
-    extraSetFlags = [
-      "--advertise-exit-node"
-    ];
-  };
-}

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 +1,53 @@
+{ 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 vars.tailscaleResolverIp directly because the DC is not a
+  # Tailscale node. This host IS a Tailscale node and can reach it via
+  # tailscale0, 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;
+
+      # Forward *.tailnetDomain to Tailscale's internal resolver, scoped to
+      # the tailnet-specific subdomain rather than all of ts.net (FreeIPA
+      # refuses to shadow ts.net, a real public TLD).
+      server = [ "/${vars.tailnetDomain}/${vars.tailscaleResolverIp}" ];
+    };
+  };
+
+  networking.firewall.allowedUDPPorts = [ vars.ports.dns ];
+  networking.firewall.allowedTCPPorts = [ vars.ports.dns ];
+}

scripts/codex-maintenance.sh

@@ -37,6 +37,17 @@ source "${script_dir}/lib/nix-parallel.sh"
 repo_root="$(cd "${script_dir}/.." && pwd)"
 cd "$repo_root"
 
+# When this repo is a subdirectory of a larger git repo (e.g. a mono-repo
+# subtree), `git diff --name-only` outputs paths relative to the outer git
+# root, not this directory. Compute a prefix to strip so pattern matching
+# below works correctly regardless of nesting depth.
+_git_root="$(git rev-parse --show-toplevel 2>/dev/null || echo "$repo_root")"
+if [[ "$repo_root" != "$_git_root" ]]; then
+  _subtree_prefix="${repo_root#"$_git_root"/}/"
+else
+  _subtree_prefix=""
+fi
+
 full_check=false
 dry_run=false
 
@@ -120,7 +131,7 @@ if ! $full_check; then
   base_ref="$(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)
+  mapfile -t changed_files < <(git diff --name-only --diff-filter=ACMR "$base_ref" -- . | sort -u | sed "s|^${_subtree_prefix}||")
 
   if [[ ${#changed_files[@]} -eq 0 ]]; then
     echo "No changed files detected."

scripts/docker-swarm/deploy.sh

@@ -0,0 +1,595 @@
+#!/usr/bin/env bash
+# deploy.sh — Full lifecycle management for the Docker Swarm HA cluster.
+#
+# Provisions two NixOS Proxmox VMs (ha-docker-1, ha-docker-2) as dual-manager
+# Docker Swarm nodes sharing NFS storage from the existing HA file-server
+# cluster.  Both nodes are managers so either can accept Docker API and
+# `docker stack` commands.
+#
+# Usage:
+#   scripts/docker-swarm/deploy.sh [options]
+#   scripts/docker-swarm/deploy.sh --destroy [options]
+#
+# Phases (all run by default; skip any with --skip-<phase>):
+#   1. ensure-bridge     Create vmbr3 (swarm cluster bridge) on the Proxmox node.
+#   2. sync-keys         Generate SSH host keys for both nodes (clan vars).
+#   3. ipa-hosts         Create IPA host objects + sops-encrypted keytabs.
+#   4. create-vms        Build NixOS disk images and create VMs via create-proxmox-resource.sh.
+#   5. add-hardware      Attach vmbr2 (storage) and vmbr3 (swarm) NICs; start VMs.
+#   6. boot-wait         Wait for SSH on both LAN IPs.
+#   7. refresh-sops-keys Detect disko key drift; re-encrypt secrets; commit.
+#   8. init-swarm        docker swarm init on node1; manager join on node2; label nodes.
+#   9. dns               Register storage.home and swarm.home A records in FreeIPA.
+#  10. verify            docker node ls; NFS mount check; swarm health.
+#
+# Options:
+#   --node <host>            Proxmox host (default: pve1.sweet.home)
+#   --vmid1 <n>              VMID for ha-docker-1 (default: 202)
+#   --vmid2 <n>              VMID for ha-docker-2 (default: 203)
+#   --storage <pool>         Proxmox storage pool (default: local-zfs)
+#   --swarm-bridge <br>      Bridge for Docker Swarm cluster network (default: vmbr3)
+#   --storage-bridge <br>    Bridge for NFS storage network (default: vmbr2)
+#   --memory <MB>            RAM per node (default: 4096)
+#   --cores <n>              vCPUs per node (default: 4)
+#   --skip-ensure-bridge     Skip vmbr3 creation/check
+#   --skip-sync-keys         Skip sync-host-keys.sh (clan vars already exist)
+#   --skip-ipa-hosts         Skip IPA host account creation (keytabs already exist)
+#   --skip-create-vms        Skip VM creation (VMs already exist)
+#   --skip-add-hardware      Skip NIC attachment (already attached)
+#   --skip-boot-wait         Skip boot/SSH wait (VMs already running)
+#   --skip-refresh-sops-keys Skip sops host-key drift fix
+#   --skip-init-swarm        Skip swarm initialisation (already initialised)
+#   --skip-dns               Skip FreeIPA DNS record creation
+#   --skip-verify            Skip post-deploy health checks
+#   --force-rebuild          Pass --force-rebuild to create-proxmox-resource.sh
+#   --destroy                Stop and delete both VMs (skip all other phases)
+#   --dry-run                Print what would run without executing
+#   -h|--help                Show this message
+#
+# Prerequisites:
+#   - SSH access to the Proxmox node as $PROXMOX_SSH_USER (wayne).
+#   - sops age key in the standard location (used by sync-host-keys.sh).
+#   - SSH access to domain-controller.sweet.home as $PROXMOX_SSH_USER for DNS phase.
+#   - For --skip-sync-keys: clan vars already in vars/per-machine/proxmox-ha-docker-{1,2}/.
+#   - For --skip-ipa-hosts: secrets/ha-docker-{1,2}.keytab already exist and are committed.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/../.." && pwd)"
+
+# shellcheck source=../env.sh
+source "${REPO_ROOT}/scripts/env.sh"
+
+# ── Defaults ──────────────────────────────────────────────────────────────────
+
+NODE="${PVE1_HOST}"   # deploy.sh targets pve1 by default (authorised for this cluster)
+VMID1=202
+VMID2=203
+STORAGE="${PROXMOX_STORAGE:-local-zfs}"
+SWARM_BRIDGE="vmbr3"
+STORAGE_BRIDGE="vmbr2"
+MEMORY_MB=4096
+CORES=4
+
+SKIP_ENSURE_BRIDGE=false
+SKIP_SYNC_KEYS=false
+SKIP_IPA_HOSTS=false
+SKIP_CREATE_VMS=false
+SKIP_ADD_HARDWARE=false
+SKIP_BOOT_WAIT=false
+SKIP_REFRESH_SOPS_KEYS=false
+SKIP_INIT_SWARM=false
+SKIP_DNS=false
+SKIP_VERIFY=false
+FORCE_REBUILD=false
+DESTROY=false
+DRY_RUN=false
+
+# ── Variables from repo (mirrors variables.nix) ───────────────────────────────
+
+NODE1_HOST="ha-docker-1"
+NODE2_HOST="ha-docker-2"
+NODE1_LAN_IP="192.168.2.230"
+NODE2_LAN_IP="192.168.2.231"
+NODE1_SWARM_IP="192.168.30.230"
+NODE2_SWARM_IP="192.168.30.231"
+NODE1_STORAGE_IP="192.168.20.230"
+NODE2_STORAGE_IP="192.168.20.231"
+SWARM_CIDR="192.168.30.0/24"
+STORAGE_CIDR="192.168.20.0/24"
+STORAGE_ZONE="storage.home"
+SWARM_ZONE="swarm.home"
+SSH_USER="${PROXMOX_SSH_USER:-wayne}"
+DC_HOST="${IPA_SERVER:-domain-controller.sweet.home}"
+
+# ── Argument parsing ──────────────────────────────────────────────────────────
+
+usage() {
+  sed -n '/^# Usage:/,/^[^#]/{ /^#/{ s/^# \?//; p } }' "$0"
+  exit "${1:-0}"
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --node)               NODE="$2";           shift 2 ;;
+    --vmid1)              VMID1="$2";          shift 2 ;;
+    --vmid2)              VMID2="$2";          shift 2 ;;
+    --storage)            STORAGE="$2";        shift 2 ;;
+    --swarm-bridge)       SWARM_BRIDGE="$2";   shift 2 ;;
+    --storage-bridge)     STORAGE_BRIDGE="$2"; shift 2 ;;
+    --memory)             MEMORY_MB="$2";      shift 2 ;;
+    --cores)              CORES="$2";          shift 2 ;;
+    --skip-ensure-bridge)     SKIP_ENSURE_BRIDGE=true;     shift ;;
+    --skip-sync-keys)         SKIP_SYNC_KEYS=true;         shift ;;
+    --skip-ipa-hosts)         SKIP_IPA_HOSTS=true;         shift ;;
+    --skip-create-vms)        SKIP_CREATE_VMS=true;        shift ;;
+    --skip-add-hardware)      SKIP_ADD_HARDWARE=true;      shift ;;
+    --skip-boot-wait)         SKIP_BOOT_WAIT=true;         shift ;;
+    --skip-refresh-sops-keys) SKIP_REFRESH_SOPS_KEYS=true; shift ;;
+    --skip-init-swarm)        SKIP_INIT_SWARM=true;        shift ;;
+    --skip-dns)               SKIP_DNS=true;               shift ;;
+    --skip-verify)            SKIP_VERIFY=true;            shift ;;
+    --force-rebuild)          FORCE_REBUILD=true;          shift ;;
+    --destroy)                DESTROY=true;                shift ;;
+    --dry-run)                DRY_RUN=true;                shift ;;
+    -h|--help) usage 0 ;;
+    *) echo "Unknown option: $1" >&2; usage 1 ;;
+  esac
+done
+
+# ── Helpers ───────────────────────────────────────────────────────────────────
+
+log()  { echo "==> $*"; }
+logn() { echo "    $*"; }
+err()  { echo "ERROR: $*" >&2; exit 1; }
+
+run() {
+  if $DRY_RUN; then
+    echo "[dry-run] $*"
+  else
+    "$@"
+  fi
+}
+
+pve() {
+  if $DRY_RUN; then
+    echo "[dry-run] ssh ${SSH_USER}@${NODE} sudo $*"
+  else
+    ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "sudo $*"
+  fi
+}
+
+pve_check() {
+  # Read-only probe — always executes even in dry-run.
+  ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "sudo $*"
+}
+
+SWARM_USER="nixos"
+
+n1() {
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+    "${SWARM_USER}@${NODE1_LAN_IP}" "$@" 2>/dev/null
+}
+
+n2() {
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+    "${SWARM_USER}@${NODE2_LAN_IP}" "$@" 2>/dev/null
+}
+
+dc() {
+  # Run ipa commands on domain-controller as $SSH_USER.
+  if $DRY_RUN; then
+    echo "[dry-run] ssh ${SSH_USER}@${DC_HOST} $*"
+    return 0
+  fi
+  ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${DC_HOST}" "$@"
+}
+
+wait_for_ssh() {
+  local ip="$1" label="$2"
+  if $DRY_RUN; then
+    logn "[dry-run] Skipping SSH wait for ${label} (${ip})"
+    return 0
+  fi
+  local deadline=$(( $(date +%s) + 300 ))
+  log "Waiting for SSH on ${label} (${ip}) — up to 5 min..."
+  while [[ $(date +%s) -lt $deadline ]]; do
+    if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=3 \
+        -o BatchMode=yes "${SWARM_USER}@${ip}" true 2>/dev/null; then
+      logn "${label} is up."
+      return 0
+    fi
+    sleep 5
+  done
+  err "Timed out waiting for SSH on ${label} (${ip})"
+}
+
+# ── Destroy mode ──────────────────────────────────────────────────────────────
+
+if $DESTROY; then
+  log "Destroying Docker Swarm VMs (${VMID1}=${NODE1_HOST}, ${VMID2}=${NODE2_HOST}) on ${NODE}"
+  for vmid in "$VMID1" "$VMID2"; do
+    STATUS=$(pve "qm status ${vmid} 2>/dev/null" 2>/dev/null || true)
+    if echo "$STATUS" | grep -q "running"; then
+      log "Stopping VMID ${vmid}..."
+      pve "qm stop ${vmid} --skiplock 1"
+      sleep 5
+    fi
+    if $DRY_RUN || pve "qm config ${vmid} >/dev/null 2>&1"; then
+      log "Deleting VMID ${vmid}..."
+      run pve "qm destroy ${vmid} --purge 1"
+    else
+      logn "VMID ${vmid} not found — already gone."
+    fi
+  done
+  log "Done — swarm VMs destroyed."
+  exit 0
+fi
+
+# ── Phase 1: Ensure swarm bridge ──────────────────────────────────────────────
+
+if ! $SKIP_ENSURE_BRIDGE; then
+  log "Phase 1: Ensuring swarm bridge ${SWARM_BRIDGE} on ${NODE}"
+  if pve_check "test -d /sys/class/net/${SWARM_BRIDGE}" &>/dev/null; then
+    logn "${SWARM_BRIDGE} already exists — skipping."
+  else
+    logn "Creating isolated internal bridge ${SWARM_BRIDGE} (no upstream port, ${SWARM_CIDR})"
+    BRIDGE_CONF="auto ${SWARM_BRIDGE}
+iface ${SWARM_BRIDGE} inet manual
+    bridge-ports none
+    bridge-stp off
+    bridge-fd 0"
+    if $DRY_RUN; then
+      echo "[dry-run] Would write /etc/network/interfaces.d/${SWARM_BRIDGE}.conf and ifup it"
+    else
+      ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+        "echo '${BRIDGE_CONF}' | sudo tee /etc/network/interfaces.d/${SWARM_BRIDGE}.conf > /dev/null && sudo ifup ${SWARM_BRIDGE}"
+      logn "${SWARM_BRIDGE} created and brought up."
+    fi
+  fi
+fi
+
+# ── Phase 2: Sync host keys ───────────────────────────────────────────────────
+
+if ! $SKIP_SYNC_KEYS; then
+  log "Phase 2: Syncing SSH host keys for both swarm targets"
+  for target in proxmox-ha-docker-1 proxmox-ha-docker-2; do
+    CLAN_DIR="${REPO_ROOT}/vars/per-machine/${target}/openssh"
+    if [[ -d "$CLAN_DIR" ]]; then
+      logn "Clan vars for ${target} already exist — skipping."
+    else
+      logn "Generating host keys for ${target}..."
+      run bash "${REPO_ROOT}/scripts/secrets/sync-host-keys.sh" "$target"
+    fi
+  done
+fi
+
+# ── Phase 3: IPA host accounts ────────────────────────────────────────────────
+
+if ! $SKIP_IPA_HOSTS; then
+  log "Phase 3: Creating IPA host accounts and keytabs"
+  IPA_SCRIPT="${REPO_ROOT}/scripts/ipa/create-nixos-ipa-host-account.sh"
+  for host in "${NODE1_HOST}" "${NODE2_HOST}"; do
+    KEYTAB="${REPO_ROOT}/secrets/${host}.keytab"
+    if [[ -f "$KEYTAB" ]]; then
+      logn "Keytab for ${host} already exists — skipping."
+    else
+      logn "Creating IPA host account and keytab for ${host}..."
+      run bash "$IPA_SCRIPT" "$host"
+    fi
+  done
+
+  if ! $DRY_RUN; then
+    # Keytabs must be committed and pushed before VMs rebuild from Gitea.
+    CURRENT_BRANCH="$(git -C "$REPO_ROOT" rev-parse --abbrev-ref HEAD)"
+    logn "Committing keytabs and pushing to Gitea (branch: ${CURRENT_BRANCH})..."
+    (cd "${REPO_ROOT}" && \
+      git add secrets/ha-docker-1.keytab secrets/ha-docker-2.keytab .sops.yaml && \
+      git commit -m "secrets(ha-docker): add IPA keytabs for ha-docker-1 and ha-docker-2" || true && \
+      git push origin "${CURRENT_BRANCH}")
+    logn "Pushed."
+  fi
+fi
+
+# ── Phase 3.5: Prepare Proxmox node for building ─────────────────────────────
+
+if ! $SKIP_CREATE_VMS && ! $DRY_RUN; then
+  CURRENT_BRANCH="$(git -C "$REPO_ROOT" rev-parse --abbrev-ref HEAD)"
+
+  local_ssh() { ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "$*"; }
+  if local_ssh "test -d /nix" &>/dev/null && ! local_ssh "test -w /nix" &>/dev/null; then
+    logn "/nix exists but not writable by ${SSH_USER} — fixing ownership with sudo..."
+    local_ssh "sudo chown -R ${SSH_USER} /nix"
+    logn "Done."
+  fi
+  unset -f local_ssh
+
+  # Use PROXMOX_REMOTE_REPO_DIR (from env.sh) so the build path is consistent
+  # with what create-proxmox-resource.sh will use.  The default is
+  # /home/<user>/nixos (the standalone nixos repo clone on pve1), but can be
+  # overridden to e.g. /home/<user>/infrastructure/nixos when the infrastructure
+  # mono-repo is checked out on pve1 instead.
+  REMOTE_REPO="${PROXMOX_REMOTE_REPO_DIR:-/home/${SSH_USER}/nixos}"
+  if pve_check "test -d ${REMOTE_REPO}/.git" &>/dev/null; then
+    REMOTE_BRANCH=$(ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+      "cd ${REMOTE_REPO} && git rev-parse --abbrev-ref HEAD 2>/dev/null")
+    if [[ "$REMOTE_BRANCH" != "$CURRENT_BRANCH" ]]; then
+      logn "Remote repo (${REMOTE_REPO}) is on '${REMOTE_BRANCH}', switching to '${CURRENT_BRANCH}'..."
+      if ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+          "cd ${REMOTE_REPO} && git fetch origin && git checkout '${CURRENT_BRANCH}' && git pull --ff-only" 2>&1; then
+        logn "Done."
+      else
+        logn "WARNING: branch switch failed — proceeding anyway (create-proxmox-resource.sh will retry)"
+      fi
+    fi
+  else
+    logn "Remote repo ${REMOTE_REPO} not found on ${NODE} — create-proxmox-resource.sh will clone it."
+  fi
+fi
+
+# ── Phase 4: Create VMs ───────────────────────────────────────────────────────
+
+if ! $SKIP_CREATE_VMS; then
+  log "Phase 4: Building and creating swarm VMs on ${NODE}"
+  CREATE="${REPO_ROOT}/scripts/proxmox/create-proxmox-resource.sh"
+  REBUILD_FLAG=""
+  $FORCE_REBUILD && REBUILD_FLAG="--force-rebuild"
+
+  for spec in "${VMID1}:${NODE1_HOST}:proxmox-ha-docker-1" "${VMID2}:${NODE2_HOST}:proxmox-ha-docker-2"; do
+    IFS=: read -r vmid host_name flake_target <<< "$spec"
+    log "Creating ${flake_target} (VMID ${vmid}) on ${NODE}..."
+    # --force-rebuild is always passed: create-proxmox-resource.sh only calls
+    # sync_remote_host_keys (which bakes the clan-var SSH key into the disk
+    # image) when it actually builds.  Reusing a cached image skips that step
+    # and leaves the VM unable to decrypt sops secrets on first boot.
+    run bash "$CREATE" \
+      --type vm \
+      --host "$host_name" \
+      --vmid "$vmid" \
+      --node "$NODE" \
+      --storage "$STORAGE" \
+      --memory "$MEMORY_MB" \
+      --cores "$CORES" \
+      --force-rebuild
+  done
+fi
+
+# ── Phase 5: Add NICs and start VMs ──────────────────────────────────────────
+
+if ! $SKIP_ADD_HARDWARE; then
+  log "Phase 5: Attaching storage (${STORAGE_BRIDGE}) and swarm (${SWARM_BRIDGE}) NICs"
+  for vmid in "$VMID1" "$VMID2"; do
+    logn "VMID ${vmid}: stopping to add NICs..."
+    pve "qm stop ${vmid} --skiplock 1 2>/dev/null; sleep 3" || true
+
+    logn "Adding net1 (${STORAGE_BRIDGE} — NFS storage)..."
+    pve "qm set ${vmid} --net1 virtio,bridge=${STORAGE_BRIDGE},firewall=0"
+
+    logn "Adding net2 (${SWARM_BRIDGE} — Docker Swarm)..."
+    pve "qm set ${vmid} --net2 virtio,bridge=${SWARM_BRIDGE},firewall=0"
+
+    logn "Starting VMID ${vmid}..."
+    pve "qm start ${vmid}"
+  done
+fi
+
+# ── Phase 6: Wait for SSH ─────────────────────────────────────────────────────
+
+if ! $SKIP_BOOT_WAIT; then
+  log "Phase 6: Waiting for both nodes to come up on LAN IPs"
+  wait_for_ssh "$NODE1_LAN_IP" "$NODE1_HOST"
+  wait_for_ssh "$NODE2_LAN_IP" "$NODE2_HOST"
+  logn "Both nodes are SSHable."
+  sleep 10  # let systemd finish activation
+fi
+
+# ── Phase 7: Refresh sops host-key registrations ─────────────────────────────
+#
+# Disko builds raw disk images: each new VM boots with a freshly-generated SSH
+# host key, not the one pre-seeded in clan vars.  Scan the running VMs; if
+# their ed25519 keys differ from the clan var, update the clan var, rewrite
+# the .sops.yaml anchor, and re-encrypt all affected sops files.
+
+if ! $SKIP_REFRESH_SOPS_KEYS; then
+  if $DRY_RUN; then
+    logn "[dry-run] Would scan VM host keys and refresh .sops.yaml / secrets if needed"
+  else
+    log "Phase 7: Refreshing sops host-key registrations (disko key drift fix)"
+    SOPS_UPDATED=false
+
+    for spec in \
+      "${NODE1_LAN_IP}:proxmox-ha-docker-1:${NODE1_HOST}" \
+      "${NODE2_LAN_IP}:proxmox-ha-docker-2:${NODE2_HOST}"; do
+      IFS=: read -r node_ip flake_target host_name <<< "$spec"
+      CLAN_PUB="${REPO_ROOT}/vars/per-machine/${flake_target}/openssh/ssh_host_ed25519_key.pub/value"
+
+      logn "Scanning ed25519 host key from ${host_name} (${node_ip})..."
+      RAW=$(ssh-keyscan -t ed25519 "${node_ip}" 2>/dev/null | grep -v "^#") || true
+      if [[ -z "$RAW" ]]; then
+        logn "WARNING: no ed25519 key returned for ${node_ip} — skipping"
+        continue
+      fi
+      SCANNED_TYPE=$(awk '{print $2}' <<< "$RAW")
+      SCANNED_KEY=$(awk  '{print $3}' <<< "$RAW")
+      SCANNED_PUBKEY="${SCANNED_TYPE} ${SCANNED_KEY} ${host_name}"
+
+      CURRENT=$(tr -d '\n' < "$CLAN_PUB" 2>/dev/null || true)
+      if [[ "$SCANNED_PUBKEY" == "$CURRENT" ]]; then
+        logn "${host_name}: clan var matches running key — no update needed"
+        continue
+      fi
+
+      logn "${host_name}: key drift detected — updating clan var"
+      logn "  old: ${CURRENT}"
+      logn "  new: ${SCANNED_PUBKEY}"
+      echo "$SCANNED_PUBKEY" > "$CLAN_PUB"
+      SOPS_UPDATED=true
+
+      ANCHOR="${flake_target}"
+      NEW_AGE=$(echo "$SCANNED_PUBKEY" | \
+        nix run --quiet --no-warn-dirty nixpkgs#ssh-to-age 2>/dev/null)
+      [[ -z "$NEW_AGE" ]] && err "ssh-to-age produced no output for ${host_name}"
+      logn "  new age key: ${NEW_AGE}"
+      sed -i "/&${ANCHOR} /s| age[a-z0-9]*$| ${NEW_AGE}|" "${REPO_ROOT}/.sops.yaml"
+    done
+
+    if $SOPS_UPDATED; then
+      logn "Running sops updatekeys on affected secrets..."
+      SOPS="nix run --quiet --no-warn-dirty nixpkgs#sops --"
+      (cd "${REPO_ROOT}" && \
+        $SOPS updatekeys -y secrets/common.yaml && \
+        $SOPS updatekeys -y secrets/ha-docker-1.keytab && \
+        $SOPS updatekeys -y secrets/ha-docker-2.keytab)
+
+      logn "Committing refreshed host keys and re-encrypted secrets..."
+      (cd "${REPO_ROOT}" && \
+        git add \
+          vars/per-machine/proxmox-ha-docker-1/openssh/ssh_host_ed25519_key.pub/value \
+          vars/per-machine/proxmox-ha-docker-2/openssh/ssh_host_ed25519_key.pub/value \
+          .sops.yaml \
+          secrets/common.yaml \
+          secrets/ha-docker-1.keytab \
+          secrets/ha-docker-2.keytab && \
+        git commit -m "secrets(ha-docker): refresh sops host-key registrations for new VM instances" || true)
+      logn "Sops keys refreshed and committed."
+    fi
+  fi
+fi
+
+# ── Phase 8: Initialise Docker Swarm ─────────────────────────────────────────
+
+if ! $SKIP_INIT_SWARM; then
+  log "Phase 8: Initialising Docker Swarm"
+
+  if $DRY_RUN; then
+    logn "[dry-run] Would run: docker swarm init --advertise-addr ${NODE1_SWARM_IP} --data-path-addr ${NODE1_SWARM_IP} on ${NODE1_HOST}"
+    logn "[dry-run] Would join ${NODE2_HOST} as manager"
+    logn "[dry-run] Would label both nodes"
+  else
+    # Check if node1 is already a swarm manager.
+    if n1 "docker info --format '{{.Swarm.LocalNodeState}}'" 2>/dev/null | grep -qx "active"; then
+      logn "${NODE1_HOST} is already in a swarm — skipping init."
+    else
+      logn "Initialising swarm on ${NODE1_HOST} (advertise: ${NODE1_SWARM_IP})..."
+      n1 "docker swarm init \
+        --advertise-addr ${NODE1_SWARM_IP} \
+        --data-path-addr ${NODE1_SWARM_IP}"
+      logn "Swarm initialised on ${NODE1_HOST}."
+    fi
+
+    # Check if node2 is already joined.
+    if n2 "docker info --format '{{.Swarm.LocalNodeState}}'" 2>/dev/null | grep -qx "active"; then
+      logn "${NODE2_HOST} is already in the swarm — skipping join."
+    else
+      logn "Fetching manager join token from ${NODE1_HOST}..."
+      JOIN_TOKEN=$(n1 "docker swarm join-token manager -q")
+      [[ -z "$JOIN_TOKEN" ]] && err "Failed to get swarm manager join token from ${NODE1_HOST}"
+
+      logn "Joining ${NODE2_HOST} as manager (advertise: ${NODE2_SWARM_IP})..."
+      n2 "docker swarm join \
+        --token ${JOIN_TOKEN} \
+        --advertise-addr ${NODE2_SWARM_IP} \
+        --data-path-addr ${NODE2_SWARM_IP} \
+        ${NODE1_SWARM_IP}:2377"
+      logn "${NODE2_HOST} joined as manager."
+    fi
+
+    # Label nodes for service placement constraints.
+    logn "Labelling swarm nodes..."
+    n1 "docker node update --label-add node=${NODE1_HOST} ${NODE1_HOST}" || true
+    n1 "docker node update --label-add node=${NODE2_HOST} ${NODE2_HOST}" || true
+    logn "Labels applied."
+  fi
+fi
+
+# ── Phase 9: DNS registration ─────────────────────────────────────────────────
+
+if ! $SKIP_DNS; then
+  log "Phase 9: Registering DNS records in FreeIPA"
+
+  if $DRY_RUN; then
+    logn "[dry-run] Would create/verify ${SWARM_ZONE} zone and add A records"
+  else
+    # Check for and create the swarm.home zone if absent.
+    if ! dc "ipa dnszone-show ${SWARM_ZONE}" >/dev/null 2>&1; then
+      logn "Creating ${SWARM_ZONE} DNS zone..."
+      dc "ipa dnszone-add ${SWARM_ZONE} \
+        --name-server=${DC_HOST}. \
+        --admin-email=hostmaster@${SWARM_ZONE}"
+      # Reverse zone for 192.168.30.x
+      dc "ipa dnszone-add 30.168.192.in-addr.arpa \
+        --name-server=${DC_HOST}. \
+        --admin-email=hostmaster@${SWARM_ZONE}" 2>/dev/null || \
+        logn "  (reverse zone 30.168.192.in-addr.arpa already exists or skipped)"
+    else
+      logn "${SWARM_ZONE} zone already exists."
+    fi
+
+    # storage.home A records (zone already exists from HA cluster setup).
+    for spec in "${NODE1_HOST}:${NODE1_STORAGE_IP}" "${NODE2_HOST}:${NODE2_STORAGE_IP}"; do
+      IFS=: read -r hostname ip <<< "$spec"
+      logn "Adding ${hostname}.${STORAGE_ZONE} → ${ip}"
+      dc "ipa dnsrecord-add ${STORAGE_ZONE} ${hostname} --a-rec=${ip} --a-create-reverse" 2>/dev/null || \
+        logn "  (record already exists or reverse zone missing — continuing)"
+    done
+
+    # swarm.home A records.
+    for spec in "${NODE1_HOST}:${NODE1_SWARM_IP}" "${NODE2_HOST}:${NODE2_SWARM_IP}"; do
+      IFS=: read -r hostname ip <<< "$spec"
+      logn "Adding ${hostname}.${SWARM_ZONE} → ${ip}"
+      dc "ipa dnsrecord-add ${SWARM_ZONE} ${hostname} --a-rec=${ip} --a-create-reverse" 2>/dev/null || \
+        logn "  (record already exists — continuing)"
+    done
+  fi
+fi
+
+# ── Phase 10: Verify ──────────────────────────────────────────────────────────
+
+if ! $SKIP_VERIFY; then
+  log "Phase 10: Verifying swarm health"
+
+  if $DRY_RUN; then
+    logn "[dry-run] Would verify swarm node list and NFS mounts"
+  else
+    logn "Swarm node list:"
+    n1 "docker node ls" || err "docker node ls failed on ${NODE1_HOST}"
+
+    logn "Checking swarm state on both nodes..."
+    for spec in "${NODE1_LAN_IP}:${NODE1_HOST}" "${NODE2_LAN_IP}:${NODE2_HOST}"; do
+      IFS=: read -r ip hostname <<< "$spec"
+      STATE=$(ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \
+        "${SWARM_USER}@${ip}" "docker info --format '{{.Swarm.LocalNodeState}}'" 2>/dev/null)
+      if [[ "$STATE" != "active" ]]; then
+        err "${hostname} swarm state is '${STATE}', expected 'active'"
+      fi
+      logn "  ${hostname}: swarm=${STATE} ✓"
+    done
+
+    logn "Checking NFS mounts on both nodes..."
+    for spec in "${NODE1_LAN_IP}:${NODE1_HOST}" "${NODE2_LAN_IP}:${NODE2_HOST}"; do
+      IFS=: read -r ip hostname <<< "$spec"
+      NFS_OK=$(ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \
+        "${SWARM_USER}@${ip}" "df -h /mnt/docker/config 2>/dev/null | grep -c nfs || echo 0" 2>/dev/null)
+      if [[ "$NFS_OK" -ge 1 ]]; then
+        logn "  ${hostname}: /mnt/docker/config NFS mount ✓"
+      else
+        logn "  WARNING: ${hostname}: /mnt/docker/config does not appear to be NFS-mounted"
+        logn "  (automount may still be pending — try: ssh nixos@${ip} 'ls /mnt/docker/config')"
+      fi
+    done
+
+    logn "Checking overlay network..."
+    NETWORKS=$(n1 "docker network ls --filter driver=overlay --format '{{.Name}}'")
+    if echo "$NETWORKS" | grep -q "ingress"; then
+      logn "  ingress overlay network present ✓"
+    else
+      logn "  WARNING: ingress overlay network not found — swarm may not be fully initialised"
+    fi
+  fi
+fi
+
+log "Deploy complete. Both nodes are ready for 'docker stack deploy'."
+log "Connect to either manager:"
+log "  ssh nixos@${NODE1_LAN_IP}   (${NODE1_HOST})"
+log "  ssh nixos@${NODE2_LAN_IP}   (${NODE2_HOST})"

scripts/env.sh

@@ -88,6 +88,17 @@ export NIX_CACHE_HOST
 : "${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

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 ]]

scripts/ha/acceptance-tests.sh

@@ -0,0 +1,231 @@
+#!/usr/bin/env bash
+# acceptance-tests.sh — HA cluster acceptance tests (T1–T7)
+#
+# Run from a host with SSH access to both HA nodes (or from node1 itself).
+# All 7 tests must pass before considering the cluster production-ready.
+# Test values below must match variables.nix haServer* values.
+set -euo pipefail
+
+# ── Configuration ─────────────────────────────────────────────────────────
+# All values override-able via environment variables; defaults match variables.nix.
+NODE1="${NODE1:-ha-server-1}"
+NODE2="${NODE2:-ha-server-2}"
+NODE1_IP="${NODE1_IP:-192.168.2.228}"   # vars.haServer1Ip
+NODE2_IP="${NODE2_IP:-192.168.2.227}"   # vars.haServer2Ip
+VIP="${VIP:-192.168.20.229}"            # vars.haServerVip
+XFS_MOUNT="${XFS_MOUNT:-/srv/ha-data}"  # vars.haStorageRoot
+ISCSI_IQN="${ISCSI_IQN:-iqn.2026-01.home.sweet:ha-storage}"  # vars.haIscsiIqn
+# ──────────────────────────────────────────────────────────────────────────
+
+PASS=0
+FAIL=0
+RESULTS=()
+
+# Use PASS=$((PASS+1)) instead of ((PASS++)) — the latter evaluates to 0 when
+# PASS=0, which triggers set -e and kills the script after the very first PASS.
+pass() { echo "  PASS: $1"; PASS=$((PASS+1)); RESULTS+=("PASS $1"); }
+fail() { echo "  FAIL: $1"; FAIL=$((FAIL+1)); RESULTS+=("FAIL $1"); }
+
+HA_USER="nixos"
+n1() { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE1_IP}" sudo "$@" 2>/dev/null; }
+n2() { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE2_IP}" sudo "$@" 2>/dev/null; }
+
+echo "════════════════════════════════════════════════════"
+echo " HA Cluster Acceptance Tests — $(date '+%Y-%m-%d %H:%M:%S')"
+echo "════════════════════════════════════════════════════"
+
+# ── Pre-flight: DRBD sync must be complete ────────────────────────────────
+# Tests that check disk state, XFS mount, and iSCSI will fail or give false
+# results while the initial full sync is in progress.  Block until done.
+echo ""
+echo "Pre-flight: verifying DRBD sync is complete..."
+DRBD_PREFLIGHT=$(n1 "drbdadm dstate ha-data 2>/dev/null" 2>/dev/null || echo "unknown")
+if ! echo "$DRBD_PREFLIGHT" | grep -q "^UpToDate/UpToDate$"; then
+  echo ""
+  echo "  ERROR: DRBD initial sync not complete."
+  echo "  Current dstate on $NODE1: $DRBD_PREFLIGHT"
+  echo ""
+  echo "  Monitor progress:"
+  echo "    ssh nixos@$NODE1_IP 'sudo watch -n3 cat /proc/drbd'"
+  echo ""
+  echo "  Re-run this script once dstate shows UpToDate/UpToDate."
+  exit 1
+fi
+echo "  dstate: $DRBD_PREFLIGHT — ready."
+
+# ── Detect Active/Standby nodes ────────────────────────────────────────────
+# Use crm_mon to detect which node holds the Promoted (Primary) DRBD resource.
+# Pacemaker is authoritative; DRBD role can briefly read as Secondary while
+# Pacemaker is mid-transition, giving a false Active/Standby swap.
+# Wait up to 90 s for Pacemaker to settle before giving up.
+echo ""
+echo "Detecting Active/Standby nodes (waiting for Pacemaker to settle)..."
+ACTIVE_NODE=""
+for i in $(seq 1 30); do
+  # crm_mon -1 output contains "Promoted: [ <node> ]" for the DRBD master.
+  CRM_OUT=$(n1 "crm_mon -1" 2>/dev/null || n2 "crm_mon -1" 2>/dev/null || true)
+  # crm_mon 2.x formats Promoted lines as "    * Promoted: [ node ]" — the * bullet
+  # means ^\s*(Promoted|Masters): never matches; filter Unpromoted first instead.
+  ACTIVE_NODE=$(echo "$CRM_OUT" | grep -v 'Unpromoted\|Unmanaged' | grep -E '(Promoted|Masters):' | grep -oE '\b(ha-server-[0-9]+)\b' | head -1 || true)
+  [[ -n "$ACTIVE_NODE" ]] && break
+  sleep 3
+done
+
+if [[ -z "$ACTIVE_NODE" ]]; then
+  echo "  WARNING: could not determine Active node from crm_mon after 90 s — defaulting to $NODE1"
+  ACTIVE_NODE="$NODE1"
+fi
+
+if [[ "$ACTIVE_NODE" == "$NODE1" ]]; then
+  ACTIVE_IP="$NODE1_IP"
+  STANDBY_NODE="$NODE2"; STANDBY_IP="$NODE2_IP"
+  na() { n1 "$@"; }
+  ns() { n2 "$@"; }
+else
+  ACTIVE_IP="$NODE2_IP"
+  STANDBY_NODE="$NODE1"; STANDBY_IP="$NODE1_IP"
+  na() { n2 "$@"; }
+  ns() { n1 "$@"; }
+fi
+echo "  Active:  $ACTIVE_NODE ($ACTIVE_IP)"
+echo "  Standby: $STANDBY_NODE ($STANDBY_IP)"
+
+# ── T1: Corosync quorum established ──────────────────────────────────────
+echo ""
+echo "[T1] Corosync quorum"
+if na "corosync-quorumtool -s" 2>/dev/null | grep -q "Quorate:.*Yes"; then
+  pass "cluster has quorum"
+else
+  fail "cluster does not have quorum — check corosync on both nodes"
+fi
+
+# ── T2: DRBD Primary on Active node, Secondary on Standby ────────────────
+echo ""
+echo "[T2] DRBD roles"
+DRBD_ROLE=$(na "drbdadm role ha-data" 2>/dev/null || echo "unknown")
+if [[ "$DRBD_ROLE" == "Primary/Secondary" || "$DRBD_ROLE" == "Primary" ]]; then
+  pass "DRBD Primary on $ACTIVE_NODE ($DRBD_ROLE)"
+else
+  fail "unexpected DRBD role on $ACTIVE_NODE: $DRBD_ROLE (expected Primary/Secondary)"
+fi
+
+DRBD_DSTATE=$(na "drbdadm dstate ha-data" 2>/dev/null || echo "unknown")
+if echo "$DRBD_DSTATE" | grep -q "UpToDate"; then
+  pass "DRBD disk state UpToDate ($DRBD_DSTATE)"
+else
+  fail "DRBD disk not UpToDate: $DRBD_DSTATE"
+fi
+
+# ── T3: XFS mounted at haStorageRoot on the Active node ──────────────────
+echo ""
+echo "[T3] XFS mount"
+if na "mountpoint -q '${XFS_MOUNT}'" 2>/dev/null; then
+  pass "XFS mounted at ${XFS_MOUNT} on $ACTIVE_NODE"
+else
+  fail "XFS not mounted at ${XFS_MOUNT} on $ACTIVE_NODE"
+fi
+
+if ns "mountpoint -q '${XFS_MOUNT}'" 2>/dev/null; then
+  fail "XFS unexpectedly mounted on $STANDBY_NODE (should only be on Active node)"
+else
+  pass "XFS not mounted on $STANDBY_NODE (correct — Standby)"
+fi
+
+# ── T4: iSCSI target visible on Active node ───────────────────────────────
+echo ""
+echo "[T4] iSCSI target"
+IQN_COUNT=$(na "bash -c 'ls /sys/kernel/config/target/iscsi/ 2>/dev/null | grep -c iqn || true'" 2>/dev/null || echo "0")
+if [[ "$IQN_COUNT" -ge 1 ]]; then
+  pass "iSCSI IQN active on $ACTIVE_NODE ($IQN_COUNT target(s))"
+else
+  fail "no iSCSI IQN active on $ACTIVE_NODE"
+fi
+
+# iSCSI port reachable from Standby node via VIP.
+# Use bash TCP probe (no iscsiadm needed — just checks port 3260 is open).
+if ns "bash -c 'echo >/dev/tcp/${VIP}/3260' 2>/dev/null"; then
+  pass "iSCSI port 3260 reachable from $STANDBY_NODE via VIP ${VIP}"
+else
+  fail "iSCSI port 3260 not reachable from $STANDBY_NODE via ${VIP}"
+fi
+
+# ── T5: Failover — standby Active node, verify resources move to Standby ──
+echo ""
+echo "[T5] Failover (standby $ACTIVE_NODE)"
+ACTIVE_CRMD_NAME=$(na "crm_node -n" 2>/dev/null || echo "")
+na "crm_standby -N '${ACTIVE_CRMD_NAME}' -v on" 2>/dev/null || true
+echo "  Waiting up to 120 s for resources to move to $STANDBY_NODE..."
+MOVED=false
+for i in $(seq 1 120); do
+  if ns "mountpoint -q '${XFS_MOUNT}'" 2>/dev/null; then
+    MOVED=true
+    echo "  Resources moved in ${i}s"
+    break
+  fi
+  sleep 1
+done
+
+if $MOVED; then
+  pass "XFS mounted on $STANDBY_NODE after failover"
+  IQN_ON_STANDBY=$(ns "bash -c 'ls /sys/kernel/config/target/iscsi/ 2>/dev/null | grep -c iqn || true'" 2>/dev/null || echo "0")
+  [[ "$IQN_ON_STANDBY" -ge 1 ]] \
+    && pass "iSCSI target active on $STANDBY_NODE after failover" \
+    || fail "iSCSI target NOT active on $STANDBY_NODE after failover"
+else
+  fail "XFS did not mount on $STANDBY_NODE within 120 s — failover incomplete"
+fi
+
+# ── T6: Data integrity — file written post-failover readable ─────────────
+echo ""
+echo "[T6] Data integrity"
+# Write a test file on the new Active (former Standby) and verify it.
+# Use `echo | sudo tee` for the write: "echo ... > file" via bash -c has the
+# redirect interpreted by the remote nixos shell (not sudo), so the file open
+# runs as nixos and fails with EACCES on the root-owned XFS mount.  Piping
+# through sudo tee lets tee (running as root) open the file instead.
+TEST_FILE="${XFS_MOUNT}/.acceptance-test-$$"
+TEST_CONTENT="ha-acceptance-test-$(date +%s)"
+echo "${TEST_CONTENT}" | ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${STANDBY_IP}" sudo tee "${TEST_FILE}" > /dev/null 2>/dev/null || true
+READBACK=$(ns cat "${TEST_FILE}" 2>/dev/null || echo "")
+if [[ "$READBACK" == "$TEST_CONTENT" ]]; then
+  pass "test file written and read back correctly on $STANDBY_NODE"
+else
+  fail "data integrity check failed (wrote: '$TEST_CONTENT', read: '$READBACK')"
+fi
+ns rm -f "${TEST_FILE}" 2>/dev/null || true
+
+# ── T7: Node rejoin — un-standby original Active, verify cluster is healthy ─
+echo ""
+echo "[T7] Node rejoin"
+na "crm_standby -N '${ACTIVE_CRMD_NAME}' -v off" 2>/dev/null || true
+na "crm_resource --cleanup" 2>/dev/null || true
+sleep 5
+
+if na "corosync-quorumtool -s 2>/dev/null | grep -q 'Quorate:.*Yes'"; then
+  pass "$ACTIVE_NODE rejoined — cluster has quorum"
+else
+  fail "$ACTIVE_NODE did not rejoin with quorum"
+fi
+
+DRBD_ROLE_AFTER=$(na "drbdadm role ha-data" 2>/dev/null || echo "unknown")
+if echo "$DRBD_ROLE_AFTER" | grep -q "Secondary"; then
+  pass "$ACTIVE_NODE is DRBD Secondary after rejoin ($DRBD_ROLE_AFTER)"
+else
+  fail "unexpected DRBD role on $ACTIVE_NODE after rejoin: $DRBD_ROLE_AFTER"
+fi
+
+# ── Summary ───────────────────────────────────────────────────────────────
+echo ""
+echo "════════════════════════════════════════════════════"
+echo " Results: ${PASS} PASS, ${FAIL} FAIL"
+echo "════════════════════════════════════════════════════"
+for r in "${RESULTS[@]}"; do echo "  $r"; done
+echo ""
+
+if [[ "$FAIL" -eq 0 ]]; then
+  echo "ALL PASS — cluster is production-ready."
+  exit 0
+else
+  echo "SOME TESTS FAILED — investigate before deploying."
+  exit 1
+fi

scripts/ha/cluster-enable-stonith.sh

@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+# cluster-enable-stonith.sh — enable STONITH fence agent after the fence SSH
+# key is deployed to both nodes and authorised on the Proxmox host.
+#
+# Run from ha-server-1 as root AFTER:
+#   - /etc/pacemaker/fence_pve_ssh exists on both nodes (chmod +x)
+#     (copy from scripts/ha/fence-pve-ssh.py)
+#   - /etc/fence-pve-ssh-key (SSH private key) exists on both nodes
+#   - The corresponding public key is in authorized_keys on PVE_HOST
+#   - VMID_NODE1 / VMID_NODE2 filled in below
+set -euo pipefail
+
+# ── Configuration ─────────────────────────────────────────────────────────
+NODE1="ha-server-1"
+NODE2="ha-server-2"
+VMID_NODE1=""          # FILL IN: Proxmox VMID for ha-server-1
+VMID_NODE2=""          # FILL IN: Proxmox VMID for ha-server-2
+PVE_HOST="pve1.sweet.home"
+PVE_USER="wayne"
+FENCE_KEY="/etc/fence-pve-ssh-key"
+FENCE_SCRIPT="/etc/pacemaker/fence_pve_ssh"
+# ──────────────────────────────────────────────────────────────────────────
+
+log() { echo "[stonith-setup] $*"; }
+die() { echo "[stonith-setup] ERROR: $*" >&2; exit 1; }
+
+[[ $(id -u) -eq 0 ]] || die "must run as root"
+[[ -n "$VMID_NODE1" ]] || die "VMID_NODE1 not set — edit this script"
+[[ -n "$VMID_NODE2" ]] || die "VMID_NODE2 not set — edit this script"
+[[ -f "$FENCE_KEY" ]] || die "fence key not found at $FENCE_KEY"
+[[ -f "$FENCE_SCRIPT" ]] || die "fence script not found at $FENCE_SCRIPT"
+
+log "Verifying fence agent can reach ${PVE_HOST}..."
+ssh -i "$FENCE_KEY" -o BatchMode=yes -o ConnectTimeout=10 \
+    -o StrictHostKeyChecking=no "${PVE_USER}@${PVE_HOST}" \
+    "sudo /usr/sbin/qm list" &>/dev/null \
+  || die "Cannot SSH to ${PVE_USER}@${PVE_HOST} — check authorized_keys and sudo"
+log "Fence agent SSH connectivity confirmed"
+
+log "Creating Pacemaker STONITH resources..."
+cibadmin --create --scope resources --xml-text "
+<primitive id=\"stonith-${NODE1}\" class=\"stonith\" type=\"external/fence_pve_ssh\">
+  <instance_attributes id=\"stonith-${NODE1}-attrs\">
+    <nvpair id=\"stonith-${NODE1}-plug\" name=\"plug\" value=\"${NODE1}\"/>
+    <nvpair id=\"stonith-${NODE1}-pve-host\" name=\"pve_host\" value=\"${PVE_HOST}\"/>
+    <nvpair id=\"stonith-${NODE1}-pve-user\" name=\"pve_user\" value=\"${PVE_USER}\"/>
+    <nvpair id=\"stonith-${NODE1}-key-file\" name=\"key_file\" value=\"${FENCE_KEY}\"/>
+    <nvpair id=\"stonith-${NODE1}-vmid1\" name=\"vmid_node1\" value=\"${VMID_NODE1}\"/>
+    <nvpair id=\"stonith-${NODE1}-vmid2\" name=\"vmid_node2\" value=\"${VMID_NODE2}\"/>
+    <nvpair id=\"stonith-${NODE1}-host-list\" name=\"pcmk_host_list\" value=\"${NODE1}\"/>
+  </instance_attributes>
+  <operations>
+    <op id=\"stonith-${NODE1}-monitor\" name=\"monitor\" interval=\"30s\" timeout=\"30s\"/>
+  </operations>
+</primitive>
+" 2>/dev/null || true
+
+cibadmin --create --scope resources --xml-text "
+<primitive id=\"stonith-${NODE2}\" class=\"stonith\" type=\"external/fence_pve_ssh\">
+  <instance_attributes id=\"stonith-${NODE2}-attrs\">
+    <nvpair id=\"stonith-${NODE2}-plug\" name=\"plug\" value=\"${NODE2}\"/>
+    <nvpair id=\"stonith-${NODE2}-pve-host\" name=\"pve_host\" value=\"${PVE_HOST}\"/>
+    <nvpair id=\"stonith-${NODE2}-pve-user\" name=\"pve_user\" value=\"${PVE_USER}\"/>
+    <nvpair id=\"stonith-${NODE2}-key-file\" name=\"key_file\" value=\"${FENCE_KEY}\"/>
+    <nvpair id=\"stonith-${NODE2}-vmid1\" name=\"vmid_node1\" value=\"${VMID_NODE1}\"/>
+    <nvpair id=\"stonith-${NODE2}-vmid2\" name=\"vmid_node2\" value=\"${VMID_NODE2}\"/>
+    <nvpair id=\"stonith-${NODE2}-host-list\" name=\"pcmk_host_list\" value=\"${NODE2}\"/>
+  </instance_attributes>
+  <operations>
+    <op id=\"stonith-${NODE2}-monitor\" name=\"monitor\" interval=\"30s\" timeout=\"30s\"/>
+  </operations>
+</primitive>
+" 2>/dev/null || true
+
+log "Enabling STONITH and restoring quorum policy..."
+crm_attribute -t crm_config -n stonith-enabled -v true
+crm_attribute -t crm_config -n no-quorum-policy -v stop
+
+log "DRBD fencing mode must also be updated to resource-only (already the"
+log "default in cluster-config.nix; confirm with: cat /etc/drbd.d/ha-data.conf)"
+
+log "Testing fence agent..."
+stonith_admin --list-devices && log "Fence devices listed successfully." \
+  || warn "stonith_admin --list-devices failed — check config"
+
+log "STONITH enabled. Cluster is now fully HA."

scripts/ha/cluster-init.sh

@@ -0,0 +1,483 @@
+#!/usr/bin/env bash
+# cluster-init.sh — one-time HA cluster initialisation script
+#
+# Run ONCE from ha-server-1 as root AFTER both VMs are booted and have SSH
+# access.  It:
+#   1. Generates and distributes the corosync authkey
+#   2. Waits for corosync quorum and pacemaker
+#   3. Initialises DRBD metadata, promotes node1 to primary
+#   4. Creates XFS on /dev/drbd0 and mounts it
+#   5. Creates the directory tree and iSCSI LUN backing file
+#   6. Configures LIO iSCSI target (file-backed LUN)
+#   7. Configures Pacemaker resources: DRBD → XFS → iSCSI → NFS → VIP
+#
+# Prerequisites:
+#   - Both VMs booted with the ha-server config (nixos-rebuild done)
+#   - SSH key access from node1 to root@NODE2_IP
+#   - VMID_NODE1 / VMID_NODE2 filled in below (needed for STONITH setup;
+#     cluster starts without STONITH, which you enable separately via
+#     scripts/ha/cluster-enable-stonith.sh)
+#   - Run as root on ha-server-1
+set -euo pipefail
+
+# ── Configuration ─────────────────────────────────────────────────────────
+# All values override-able via environment variables; defaults match variables.nix.
+NODE1="${NODE1:-ha-server-1}"
+NODE2="${NODE2:-ha-server-2}"
+NODE1_IP="${NODE1_IP:-192.168.2.228}"   # vars.haServer1Ip
+NODE2_IP="${NODE2_IP:-192.168.2.227}"   # vars.haServer2Ip
+VIP="${VIP:-192.168.20.229}"            # vars.haServerVip (storage-client, vmbr2, VLAN 20)
+VIP_LAN="${VIP_LAN:-192.168.2.229}"    # vars.haServerLanVip (LAN, vmbr0)
+XFS_MOUNT="${XFS_MOUNT:-/srv/ha-data}"  # vars.haStorageRoot
+ISCSI_IQN="${ISCSI_IQN:-iqn.2026-01.home.sweet:ha-storage}"  # vars.haIscsiIqn
+ISCSI_LUN_FILE="${XFS_MOUNT}/iscsi-lun.img"
+ISCSI_LUN_SIZE="10G"
+DRBD_DEVICE="/dev/drbd0"
+# DRBD backing disk — by-id path that resolves correctly on both nodes
+# regardless of whether the OS-level name is sda or sdb (Proxmox VM disk
+# ordering is not guaranteed). Matches haServerDrbdDisk in variables.nix.
+# Override DRBD_DISK if your hardware uses a different controller/slot path.
+DRBD_DISK="${DRBD_DISK:-/dev/disk/by-id/scsi-0QEMU_QEMU_HARDDISK_drive-scsi1}"
+VMID_NODE1="${VMID_NODE1:-}"            # set by deploy.sh; needed for STONITH
+VMID_NODE2="${VMID_NODE2:-}"
+PVE_HOST="${PVE_HOST:-pve1.sweet.home}"
+PVE_USER="${PVE_USER:-wayne}"
+# Inter-node SSH: HA_USER is the user to SSH as on NODE2; HA_KEY is the private
+# key to use.  Default is root-to-root (no key arg).  deploy.sh sets HA_USER=nixos
+# and HA_KEY=/tmp/cluster-init-key so the script works even when root-to-root SSH
+# is not available.
+HA_USER="${HA_USER:-root}"
+HA_KEY="${HA_KEY:-}"
+
+# NFS dataset subdirectories to create under XFS_MOUNT.
+# Must mirror vars.nfsShares subpath values in variables.nix.
+NFS_SUBDIRS=(
+  "docker/config"
+  "docker/volumes"
+  "docker/databases"
+  "docker/nextcloud-data"
+  "raspi/volumes"
+  "proxmox/iso"
+  "proxmox/lxc"
+  "pxe-boot/images"
+)
+# ──────────────────────────────────────────────────────────────────────────
+
+log()  { echo "[cluster-init] $*"; }
+die()  { echo "[cluster-init] ERROR: $*" >&2; exit 1; }
+warn() { echo "[cluster-init] WARNING: $*" >&2; }
+
+[[ $(id -u) -eq 0 ]] || die "must run as root"
+[[ "$(hostname)" == "$NODE1" ]] || die "must run on $NODE1"
+
+# NixOS may not include xfsprogs in root's PATH even when it's in the store.
+# If mkfs.xfs is missing, search the Nix store for it.
+if ! command -v mkfs.xfs &>/dev/null; then
+  _xfs_bin=$(find /nix/store -maxdepth 3 -name mkfs.xfs 2>/dev/null | head -1 | xargs dirname 2>/dev/null || true)
+  [[ -n "$_xfs_bin" ]] && export PATH="$_xfs_bin:$PATH" \
+    || die "mkfs.xfs not found — add xfsprogs to ha-server.nix environment.systemPackages and rebuild"
+fi
+
+# drbdmeta lives alongside drbdadm but may not be in PATH when run via sudo.
+if ! command -v drbdmeta &>/dev/null; then
+  _drbd_bin=$(dirname "$(command -v drbdadm)" 2>/dev/null || true)
+  [[ -n "$_drbd_bin" ]] && export PATH="$_drbd_bin:$PATH" \
+    || die "drbdmeta not found — is drbd-utils in ha-server environment.systemPackages?"
+fi
+
+# Portable 16-hex-char UUID generator (no openssl required).
+_rand_uuid() {
+  cat /proc/sys/kernel/random/uuid 2>/dev/null | tr -d '-' | cut -c1-16 | tr '[:lower:]' '[:upper:]'
+}
+
+# Inter-node SSH/SCP helpers — abstract over root-to-root vs nixos+sudo.
+_SSH_OPTS="-o StrictHostKeyChecking=no -o ConnectTimeout=10"
+[[ -n "$HA_KEY" ]] && _SSH_OPTS="-i $HA_KEY $_SSH_OPTS"
+if [[ "$HA_USER" == "root" ]]; then
+  n2_ssh() { ssh $_SSH_OPTS "root@${NODE2_IP}" "$@"; }
+  n2_scp() { scp $_SSH_OPTS "$1" "root@${NODE2_IP}:$2"; }
+else
+  # Non-root user with passwordless sudo; wrap each command with sudo.
+  n2_ssh() { ssh $_SSH_OPTS "${HA_USER}@${NODE2_IP}" sudo "$@"; }
+  n2_scp() {
+    # SCP to a tmp path, then sudo-move to the real destination as the remote user.
+    local src="$1" dst="$2"
+    local tmp="/tmp/_cluster_init_scp_$$"
+    scp $_SSH_OPTS "$src" "${HA_USER}@${NODE2_IP}:${tmp}"
+    ssh $_SSH_OPTS "${HA_USER}@${NODE2_IP}" sudo mv "${tmp}" "${dst}"
+  }
+fi
+
+# ── 0. Corosync authkey ───────────────────────────────────────────────────
+AUTHKEY="/etc/corosync/authkey"
+mkdir -p /etc/corosync
+if [[ ! -f "$AUTHKEY" ]]; then
+  log "Generating corosync authkey..."
+  corosync-keygen -k "$AUTHKEY"
+  chmod 0400 "$AUTHKEY"
+fi
+log "Distributing authkey to $NODE2..."
+n2_ssh "mkdir -p /etc/corosync"
+n2_scp "$AUTHKEY" "$AUTHKEY"
+n2_ssh "chmod 0400 '${AUTHKEY}'"
+
+log "Restarting corosync and pacemaker on both nodes..."
+systemctl restart corosync
+n2_ssh "systemctl restart corosync"
+sleep 3
+
+log "Starting pacemaker on both nodes (may have failed at boot before authkey was placed)..."
+systemctl start pacemaker 2>/dev/null || systemctl restart pacemaker 2>/dev/null || true
+n2_ssh "systemctl start pacemaker 2>/dev/null || systemctl restart pacemaker 2>/dev/null || true"
+sleep 2
+
+# ── 1. Corosync quorum ────────────────────────────────────────────────────
+log "Waiting for corosync quorum..."
+for i in $(seq 1 30); do
+  if corosync-quorumtool -s 2>/dev/null | grep -q 'Quorate:.*Yes'; then
+    log "Quorum established"
+    break
+  fi
+  [[ $i -eq 30 ]] && die "corosync quorum not established after 60 s"
+  sleep 2
+done
+
+log "Waiting for pacemaker..."
+for i in $(seq 1 30); do
+  if crm_mon -1 &>/dev/null; then
+    log "Pacemaker running"
+    break
+  fi
+  [[ $i -eq 30 ]] && die "pacemaker not running after 60 s"
+  sleep 2
+done
+
+# ── 2. DRBD initialisation ────────────────────────────────────────────────
+# Put both nodes in Pacemaker standby first so it stops managed resources
+# cleanly, then enable maintenance-mode so Pacemaker's monitor operations are
+# suspended.  Without maintenance-mode, Pacemaker keeps monitoring: when it
+# sees DRBD Primary on a standby node (that it didn't start), it triggers a
+# stop action — killing the initial sync after ~10 s.  Maintenance-mode
+# disables all start/stop/monitor actions for the duration of the sync; it is
+# cleared after UpToDate/UpToDate is confirmed.
+log "Setting both nodes to Pacemaker standby for DRBD metadata init..."
+crm_standby -N "$NODE1" -v on 2>/dev/null || true
+crm_standby -N "$NODE2" -v on 2>/dev/null || true
+
+# Wait for Pacemaker to actually stop DRBD (if it was managing it).
+log "Waiting for DRBD to stop under Pacemaker control..."
+for i in $(seq 1 30); do
+  n1_role=$(drbdadm role ha-data 2>/dev/null || echo "Unconfigured")
+  n2_role=$(n2_ssh "drbdadm role ha-data 2>/dev/null" 2>/dev/null || echo "Unconfigured")
+  if [[ "$n1_role" == "Unconfigured" ]] && [[ "$n2_role" == "Unconfigured" ]]; then
+    log "DRBD stopped on both nodes"
+    break
+  fi
+  [[ $i -eq 30 ]] && warn "DRBD still active after 60s standby — forcing down anyway"
+  sleep 2
+done
+
+log "Enabling Pacemaker maintenance-mode (suspends monitor/start/stop during sync)..."
+crm_attribute -t crm_config -n maintenance-mode -v true 2>/dev/null || true
+
+log "Detaching DRBD on $NODE1 (belt-and-suspenders after standby)..."
+drbdadm down ha-data 2>/dev/null || true
+log "Detaching DRBD on $NODE2..."
+n2_ssh "drbdadm down ha-data 2>/dev/null || true"
+sleep 2
+
+# Ensure /etc/drbd.conf on both nodes points to DRBD_DISK (the stable by-id
+# path).  VMs built before this fix may have /dev/sda or /dev/sdb hardcoded.
+# NixOS makes /etc/drbd.conf a symlink into the read-only Nix store, so
+# sed -i on the symlink target would fail — we break the symlink first with
+# cp --remove-destination, creating a regular writable copy.
+# Rebuild+redeploy (--force-rebuild) to make this permanent.
+_PATCH_DRBD=$(mktemp)
+cat > "$_PATCH_DRBD" << 'PATCHEOF'
+#!/bin/bash
+WANT="$1"
+conf=/etc/drbd.conf
+if [[ -L "$conf" ]]; then
+  cp --remove-destination "$(readlink -f "$conf")" "$conf"
+fi
+cur=$(drbdadm sh-ll-dev ha-data 2>/dev/null | head -1 || true)
+if [[ -n "$cur" && "$cur" != "$WANT" ]]; then
+  echo "[cluster-init] WARNING: patching $conf: $cur → $WANT (rebuild to make permanent)"
+  sed -i "s,${cur},${WANT},g" "$conf"
+fi
+PATCHEOF
+chmod +x "$_PATCH_DRBD"
+bash "$_PATCH_DRBD" "$DRBD_DISK"
+n2_scp "$_PATCH_DRBD" "/tmp/patch-drbd-disk.sh"
+n2_ssh "bash /tmp/patch-drbd-disk.sh ${DRBD_DISK}"
+n2_ssh "rm -f /tmp/patch-drbd-disk.sh"
+rm -f "$_PATCH_DRBD"
+
+log "Initialising DRBD metadata on $NODE1..."
+# Use drbdmeta --force directly for BOTH create-md and write-dev-uuid.
+# drbdadm create-md --force passes --force to drbdmeta create-md but NOT to
+# the write-dev-uuid sub-call it makes internally, so write-dev-uuid fails when
+# the backing disk is still busy and stdin is not a TTY:
+# "stdin not a TTY, not waiting for confirmation" → exit 20.
+# Calling drbdmeta --force directly bypasses the exclusive-open confirmation on
+# both steps without needing a TTY, regardless of whether the device is busy.
+# Skip metadata creation only if DRBD is UP and fully synced (UpToDate/UpToDate).
+# When the resource is down, drbdadm dstate reads metadata and returns just
+# "UpToDate" (no slash) — that must not be treated as "already synced".
+# Mismatched UUIDs from an interrupted sync cause instant WFConnection→StandAlone,
+# so we always recreate metadata unless the sync is genuinely complete.
+if [[ "$(drbdadm dstate ha-data 2>/dev/null)" != "UpToDate/UpToDate" ]]; then
+  UUID1=$(_rand_uuid)
+  drbdmeta --force 0 v08 "${DRBD_DISK}" internal create-md
+  drbdmeta --force 0 v08 "${DRBD_DISK}" internal write-dev-uuid "$UUID1"
+fi
+
+log "Initialising DRBD metadata on $NODE2..."
+if [[ "$(n2_ssh "drbdadm dstate ha-data 2>/dev/null" 2>/dev/null)" != "UpToDate/UpToDate" ]]; then
+  UUID2=$(n2_ssh "cat /proc/sys/kernel/random/uuid 2>/dev/null | tr -d '-' | cut -c1-16 | tr '[:lower:]' '[:upper:]'")
+  n2_ssh "drbdmeta --force 0 v08 ${DRBD_DISK} internal create-md"
+  n2_ssh "drbdmeta --force 0 v08 ${DRBD_DISK} internal write-dev-uuid ${UUID2}"
+fi
+
+log "Bringing up DRBD on both nodes..."
+drbdadm up ha-data 2>/dev/null || true
+n2_ssh "drbdadm up ha-data" 2>/dev/null || true
+
+log "Forcing $NODE1 to DRBD Primary for initial sync..."
+drbdadm primary ha-data --force
+# NOTE: Pacemaker standby is intentionally kept ON until after the sync
+# completes.  Clearing it here races with the OCF DRBD agent: Pacemaker
+# sees DRBD in WFConnection/SyncSource and may call drbdadm-down thinking
+# something went wrong, killing the sync.  Standby is cleared below, after
+# UpToDate/UpToDate is confirmed.
+
+log "Waiting for DRBD initial sync to complete (32 GB may take 10–20 min)..."
+log "  (monitor with: watch -n3 cat /proc/drbd)"
+_sync_chars=('|' '/' '-' $'\\')
+_sync_iter=0
+while true; do
+  _dstate=$(drbdadm dstate ha-data 2>/dev/null || echo "unknown")
+  if echo "$_dstate" | grep -q "UpToDate/UpToDate"; then
+    printf "\r%-80s\r" ""
+    log "DRBD initial sync complete (dstate: $_dstate)"
+    break
+  fi
+  # Parse connection state from /proc/drbd (cs:SyncSource, cs:Connected, cs:StandAlone …)
+  _cs=$(grep -oE 'cs:[A-Za-z]+' /proc/drbd 2>/dev/null | head -1 | sed 's/cs://' || echo "unknown")
+  # /proc/drbd uses variable whitespace: "sync'ed:  5.2%" (two spaces).
+  _pct=$(grep -oE "sync'ed:[[:space:]]+[0-9.]+" /proc/drbd 2>/dev/null | grep -oE "[0-9.]+" | head -1 || echo "")
+  _eta=$(grep -oE "finish:[[:space:]]+[0-9:]+" /proc/drbd 2>/dev/null | grep -oE "[0-9:]+$" | head -1 || echo "")
+  _spd=$(grep -oE "speed:[[:space:]]+[0-9,]+" /proc/drbd 2>/dev/null | grep -oE "[0-9,]+$" | head -1 || echo "")
+  _sync_iter=$(( _sync_iter + 1 ))
+  _sc="${_sync_chars[$_sync_iter % 4]}"
+  if [[ "$_cs" == "StandAlone" && $_sync_iter -gt 5 ]]; then
+    printf "\r%-80s\r" ""
+    die "DRBD is StandAlone after 15 s — peer connection lost (dstate: $_dstate). " \
+        "Check corosync/network and re-run cluster-init."
+  elif [[ -n "$_pct" ]]; then
+    printf "\r  [%s] syncing: %s%% done — ETA %s @ %s K/s     " \
+      "$_sc" "$_pct" "${_eta:-??:??:??}" "${_spd:-?}"
+  else
+    printf "\r  [%s] cs:%s dstate:%s — waiting for sync to start     " "$_sc" "$_cs" "$_dstate"
+  fi
+  sleep 3
+done
+
+log "Disabling Pacemaker maintenance-mode and clearing standby — handing DRBD back to Pacemaker..."
+crm_attribute -t crm_config -n maintenance-mode -v false 2>/dev/null || true
+crm_standby -N "$NODE1" -v off 2>/dev/null || true
+crm_standby -N "$NODE2" -v off 2>/dev/null || true
+
+# ── 3. XFS filesystem ─────────────────────────────────────────────────────
+log "Creating XFS on ${DRBD_DEVICE}..."
+if ! xfs_info "${DRBD_DEVICE}" &>/dev/null; then
+  mkfs.xfs -f "${DRBD_DEVICE}"
+fi
+
+log "Mounting ${DRBD_DEVICE} at ${XFS_MOUNT}..."
+mkdir -p "${XFS_MOUNT}"
+mountpoint -q "${XFS_MOUNT}" || mount "${DRBD_DEVICE}" "${XFS_MOUNT}"
+
+# ── 4. NFS dataset directories ────────────────────────────────────────────
+log "Creating NFS dataset directories..."
+for subdir in "${NFS_SUBDIRS[@]}"; do
+  mkdir -p "${XFS_MOUNT}/${subdir}"
+done
+
+# ── 5. iSCSI LUN backing file ─────────────────────────────────────────────
+log "Creating iSCSI LUN backing file ${ISCSI_LUN_FILE} (${ISCSI_LUN_SIZE})..."
+if [[ ! -f "${ISCSI_LUN_FILE}" ]]; then
+  fallocate -l "${ISCSI_LUN_SIZE}" "${ISCSI_LUN_FILE}"
+fi
+
+# ── 6. LIO iSCSI target ───────────────────────────────────────────────────
+log "Configuring LIO iSCSI target via targetcli..."
+# Note: do NOT bind portal to ${VIP} here — the VIP isn't assigned yet (Pacemaker
+# creates it).  The default portal (all IPs, port 3260) is correct; Pacemaker's
+# VIP resource will make the target reachable at the VIP address.
+#
+# Clear any existing LIO state first (idempotent: re-run after a partial failure).
+# Use specific delete commands — clearconfig does not reliably clear kernel state.
+if ls /sys/kernel/config/target/iscsi/ 2>/dev/null | grep -q "${ISCSI_IQN}"; then
+  log "Clearing existing LIO target ${ISCSI_IQN} before reconfiguration..."
+  targetcli "/iscsi delete ${ISCSI_IQN}" 2>/dev/null || true
+fi
+if ls /sys/kernel/config/target/core/ 2>/dev/null | grep -q "fileio"; then
+  log "Clearing existing LIO backstore ha-lun0 before reconfiguration..."
+  targetcli "/backstores/fileio delete ha-lun0" 2>/dev/null || true
+fi
+targetcli <<EOF
+/backstores/fileio create name=ha-lun0 file_or_dev=${ISCSI_LUN_FILE} size=0 write_back=false
+/iscsi create ${ISCSI_IQN}
+/iscsi/${ISCSI_IQN}/tpg1/luns create /backstores/fileio/ha-lun0
+/iscsi/${ISCSI_IQN}/tpg1 set attribute authentication=0
+/iscsi/${ISCSI_IQN}/tpg1 set attribute demo_mode_write_protect=0
+saveconfig /etc/target/saveconfig.json
+EOF
+
+log "Tearing down LIO kernel objects — Pacemaker will restore via targetctl on the Active node..."
+# LIO holds the backing file open; clear kernel state now so the XFS unmount succeeds.
+# Use specific delete commands (clearconfig does not reliably clear kernel configfs state).
+targetcli "/iscsi delete ${ISCSI_IQN}" 2>/dev/null || warn "LIO iscsi delete failed — umount may fail"
+targetcli "/backstores/fileio delete ha-lun0" 2>/dev/null || warn "LIO backstore delete failed"
+
+log "Distributing iSCSI saveconfig to $NODE2..."
+n2_scp /etc/target/saveconfig.json /etc/target/saveconfig.json
+
+
+log "Unmounting ${XFS_MOUNT} — Pacemaker manages it..."
+umount "${XFS_MOUNT}" || { sync; umount -l "${XFS_MOUNT}"; }
+
+log "Demoting DRBD to Secondary — Pacemaker manages primary role..."
+drbdadm role ha-data 2>/dev/null | grep -q "^Primary" && drbdadm secondary ha-data || true
+
+# ── 7. Pacemaker resources ────────────────────────────────────────────────
+log "Configuring Pacemaker cluster properties..."
+crm_attribute -t crm_config -n stonith-enabled -v false
+crm_attribute -t crm_config -n no-quorum-policy -v ignore
+
+log "Creating Pacemaker resources via cibadmin..."
+# Use cibadmin --replace with pacemaker-4.0-compatible XML.
+# Key schema rules for pacemaker-4.0:
+#   - globally-unique must be in <meta_attributes>, not a direct <clone> attribute
+#   - promoted-max / promoted-node-max (not master-max / master-node-max)
+#   - constraint with-rsc-role="Promoted" (not "Master")
+cibadmin --replace --scope resources --xml-text '<resources>
+  <clone id="ms-drbd0">
+    <meta_attributes id="ms-drbd0-meta">
+      <nvpair id="ms-drbd0-globally-unique" name="globally-unique" value="false"/>
+      <nvpair id="ms-drbd0-promotable" name="promotable" value="true"/>
+      <nvpair id="ms-drbd0-promoted-max" name="promoted-max" value="1"/>
+      <nvpair id="ms-drbd0-promoted-node-max" name="promoted-node-max" value="1"/>
+      <nvpair id="ms-drbd0-clone-max" name="clone-max" value="2"/>
+      <nvpair id="ms-drbd0-clone-node-max" name="clone-node-max" value="1"/>
+      <nvpair id="ms-drbd0-notify" name="notify" value="true"/>
+      <nvpair id="ms-drbd0-interleave" name="interleave" value="true"/>
+    </meta_attributes>
+    <primitive id="drbd0" class="ocf" type="drbd" provider="linbit">
+      <instance_attributes id="drbd0-attrs">
+        <nvpair id="drbd0-resource" name="drbd_resource" value="ha-data"/>
+      </instance_attributes>
+      <operations>
+        <op id="drbd0-start" name="start" interval="0" timeout="240s"/>
+        <op id="drbd0-stop" name="stop" interval="0" timeout="120s"/>
+        <op id="drbd0-promote" name="promote" interval="0" timeout="240s"/>
+        <op id="drbd0-demote" name="demote" interval="0" timeout="90s"/>
+        <op id="drbd0-monitor-promoted" name="monitor" interval="20s" timeout="20s" role="Promoted"/>
+        <op id="drbd0-monitor-unpromoted" name="monitor" interval="30s" timeout="20s" role="Unpromoted"/>
+      </operations>
+    </primitive>
+  </clone>
+  <group id="ha-group">
+    <primitive id="xfs-data" class="ocf" type="Filesystem" provider="heartbeat">
+      <instance_attributes id="xfs-data-attrs">
+        <nvpair id="xfs-data-device" name="device" value="/dev/drbd0"/>
+        <nvpair id="xfs-data-directory" name="directory" value="/srv/ha-data"/>
+        <nvpair id="xfs-data-fstype" name="fstype" value="xfs"/>
+        <nvpair id="xfs-data-options" name="options" value="defaults"/>
+        <nvpair id="xfs-data-force_unmount" name="force_unmount" value="true"/>
+      </instance_attributes>
+      <operations>
+        <op id="xfs-data-start" name="start" interval="0" timeout="60s"/>
+        <op id="xfs-data-stop" name="stop" interval="0" timeout="60s"/>
+        <op id="xfs-data-monitor" name="monitor" interval="20s" timeout="40s"/>
+      </operations>
+    </primitive>
+    <primitive id="iscsi-target" class="systemd" type="targetctl">
+      <operations>
+        <op id="iscsi-start" name="start" interval="0" timeout="60s"/>
+        <op id="iscsi-stop" name="stop" interval="0" timeout="60s"/>
+        <op id="iscsi-monitor" name="monitor" interval="20s" timeout="40s"/>
+      </operations>
+    </primitive>
+    <primitive id="nfs-server" class="systemd" type="nfs-server">
+      <operations>
+        <op id="nfs-start" name="start" interval="0" timeout="60s"/>
+        <op id="nfs-stop" name="stop" interval="0" timeout="60s"/>
+        <op id="nfs-monitor" name="monitor" interval="30s" timeout="40s"/>
+      </operations>
+    </primitive>
+    <primitive id="vip-storage" class="ocf" type="IPaddr2" provider="heartbeat">
+      <instance_attributes id="vip-storage-attrs">
+        <nvpair id="vip-storage-ip" name="ip" value="192.168.20.229"/>
+        <nvpair id="vip-storage-cidr" name="cidr_netmask" value="24"/>
+        <nvpair id="vip-storage-nic" name="nic" value="ens20"/>
+      </instance_attributes>
+      <operations>
+        <op id="vip-storage-start" name="start" interval="0" timeout="20s"/>
+        <op id="vip-storage-stop" name="stop" interval="0" timeout="20s"/>
+        <op id="vip-storage-monitor" name="monitor" interval="10s" timeout="20s"/>
+      </operations>
+    </primitive>
+    <primitive id="vip-lan" class="ocf" type="IPaddr2" provider="heartbeat">
+      <instance_attributes id="vip-lan-attrs">
+        <nvpair id="vip-lan-ip" name="ip" value="192.168.2.229"/>
+        <nvpair id="vip-lan-cidr" name="cidr_netmask" value="24"/>
+        <nvpair id="vip-lan-nic" name="nic" value="ens18"/>
+      </instance_attributes>
+      <operations>
+        <op id="vip-lan-start" name="start" interval="0" timeout="20s"/>
+        <op id="vip-lan-stop" name="stop" interval="0" timeout="20s"/>
+        <op id="vip-lan-monitor" name="monitor" interval="10s" timeout="20s"/>
+      </operations>
+    </primitive>
+  </group>
+</resources>'
+
+log "Adding Pacemaker ordering and colocation constraints..."
+cibadmin --replace --scope constraints --xml-text '<constraints>
+  <rsc_order id="order-drbd-group" first="ms-drbd0" first-action="promote" then="ha-group" then-action="start" kind="Mandatory"/>
+  <rsc_colocation id="coloc-group-with-drbd" score="INFINITY" rsc="ha-group" with-rsc="ms-drbd0" with-rsc-role="Promoted"/>
+</constraints>'
+
+log "Clearing stale Pacemaker failure history..."
+crm_resource --cleanup 2>/dev/null || true
+
+log "Waiting for resources to start..."
+for i in $(seq 1 60); do
+  if crm_resource -r vip-storage --locate 2>/dev/null | grep -q "running on"; then
+    log "VIPs are up: $(crm_resource -r vip-storage --locate)"
+    break
+  fi
+  [[ $i -eq 60 ]] && { warn "VIPs not up after 120 s — check: crm_mon -1"; break; }
+  sleep 2
+done
+
+log ""
+log "═══════════════════════════════════════════════════════════════"
+log " HA cluster initialised."
+log ""
+log "  crm_mon -1                               — cluster status"
+log "  iscsiadm -m discovery -t st -p ${VIP}       — verify iSCSI (storage net)"
+log "  iscsiadm -m discovery -t st -p ${VIP_LAN}   — verify iSCSI (LAN)"
+log "  showmount -e ${VIP}                          — verify NFS exports (storage net)"
+log "  showmount -e ${VIP_LAN}                      — verify NFS exports (LAN)"
+log ""
+log "  To enable STONITH (after deploying fence SSH key):"
+log "    1. Fill in VMID_NODE1 / VMID_NODE2 in cluster-enable-stonith.sh"
+log "    2. Copy scripts/ha/fence-pve-ssh.py to /etc/pacemaker/fence_pve_ssh"
+log "       on both nodes (chmod +x)"
+log "    3. Generate and distribute the fence SSH key"
+log "       (see docs or cluster-enable-stonith.sh header)"
+log "    4. bash scripts/ha/cluster-enable-stonith.sh"
+log "═══════════════════════════════════════════════════════════════"

scripts/ha/deploy.sh

@@ -0,0 +1,499 @@
+#!/usr/bin/env bash
+# deploy.sh — Full lifecycle management for the HA file-server cluster.
+#
+# Handles everything from zero (no VMs, no secrets) through a running,
+# tested cluster, and optionally tears it back down.
+#
+# Usage:
+#   scripts/ha/deploy.sh [options]
+#   scripts/ha/deploy.sh --destroy [options]
+#
+# Phases (all run by default; skip any with --skip-*):
+#   1. ensure-bridge   Create storage bridge (vmbr1) on the Proxmox node if absent.
+#   2. sync-keys       Generate SSH host keys and register age keys for both nodes.
+#   3. create-vms      Build disk images and create both VMs via create-proxmox-resource.sh.
+#   4. add-hardware    Attach storage NIC (vmbr1) and DRBD data disk to each VM.
+#   5. boot-wait       Start VMs, wait for SSH on both nodes.
+#   6. cluster-init    Form the cluster: DRBD, corosync, Pacemaker, NFS, VIP.
+#                      Also encrypts the generated corosync authkey into the repo.
+#   7. run-tests       Run acceptance tests (T1–T7).
+#
+# Options:
+#   --node <host>            Proxmox host to deploy on (default: pve1.sweet.home)
+#   --vmid1 <n>              VMID for ha-server-1 (default: 200)
+#   --vmid2 <n>              VMID for ha-server-2 (default: 201)
+#   --storage <pool>         Proxmox storage pool (default: local-zfs)
+#   --storage-bridge <br>    Bridge for HA storage network (default: vmbr1)
+#   --drbd-disk-gb <n>       DRBD data disk size in GB (default: 32)
+#   --memory <MB>            RAM per node (default: 4096)
+#   --cores <n>              vCPUs per node (default: 4)
+#   --skip-ensure-bridge     Skip storage bridge creation/check
+#   --skip-sync-keys         Skip sync-host-keys.sh (clan vars already exist)
+#   --skip-create-vms        Skip VM creation (VMs already exist)
+#   --skip-add-hardware      Skip net1/scsi1 attachment (already attached)
+#   --skip-boot-wait         Skip boot/SSH wait (VMs already running)
+#   --skip-refresh-sops-keys Skip scanning running VMs for fresh SSH host keys
+#   --skip-cluster-init      Skip cluster formation (cluster already configured)
+#   --skip-tests             Skip acceptance tests
+#   --force-rebuild          Pass --force-rebuild to create-proxmox-resource.sh
+#   --destroy                Stop and delete both VMs (skip all other phases)
+#   --dry-run                Print what would run without executing
+#   -h|--help                Show this message
+#
+# Prerequisites:
+#   - SSH access to the Proxmox node as $PROXMOX_SSH_USER (wayne).
+#   - sops age key in the standard location (used by sync-host-keys.sh).
+#   - For --skip-sync-keys: clan vars already in vars/per-machine/proxmox-ha-server-{1,2}/.
+#   - For full tests: secrets/common.yaml decryptable on both nodes (run
+#     `sops updatekeys secrets/common.yaml` after sync-keys).
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+# shellcheck source=../env.sh
+source "${REPO_ROOT}/scripts/env.sh"
+
+# ── Defaults ──────────────────────────────────────────────────────────────────
+
+NODE="${PROXMOX_HOST:-$PVE1_HOST}"
+VMID1=200
+VMID2=201
+STORAGE="${PROXMOX_STORAGE:-local-zfs}"
+STORAGE_BRIDGE="vmbr1"
+DRBD_DISK_GB=32
+MEMORY_MB=4096
+CORES=4
+
+SKIP_ENSURE_BRIDGE=false
+SKIP_SYNC_KEYS=false
+SKIP_CREATE_VMS=false
+SKIP_ADD_HARDWARE=false
+SKIP_BOOT_WAIT=false
+SKIP_REFRESH_SOPS_KEYS=false
+SKIP_CLUSTER_INIT=false
+SKIP_TESTS=false
+FORCE_REBUILD=false
+DESTROY=false
+DRY_RUN=false
+
+# ── Variables from repo ───────────────────────────────────────────────────────
+
+NODE1_HOST="ha-server-1"
+NODE2_HOST="ha-server-2"
+NODE1_IP="192.168.2.228"
+NODE2_IP="192.168.2.227"
+STORAGE_IP1="192.168.10.228"
+STORAGE_IP2="192.168.10.227"
+STORAGE_CIDR="192.168.10.224/29"
+SSH_USER="${PROXMOX_SSH_USER:-wayne}"
+
+# ── Argument parsing ──────────────────────────────────────────────────────────
+
+usage() {
+  sed -n '/^# Usage:/,/^[^#]/{ /^#/{ s/^# \?//; p } }' "$0"
+  exit "${1:-0}"
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --node)               NODE="$2";           shift 2 ;;
+    --vmid1)              VMID1="$2";          shift 2 ;;
+    --vmid2)              VMID2="$2";          shift 2 ;;
+    --storage)            STORAGE="$2";        shift 2 ;;
+    --storage-bridge)     STORAGE_BRIDGE="$2"; shift 2 ;;
+    --drbd-disk-gb)       DRBD_DISK_GB="$2";   shift 2 ;;
+    --memory)             MEMORY_MB="$2";      shift 2 ;;
+    --cores)              CORES="$2";          shift 2 ;;
+    --skip-ensure-bridge) SKIP_ENSURE_BRIDGE=true; shift ;;
+    --skip-sync-keys)     SKIP_SYNC_KEYS=true; shift ;;
+    --skip-create-vms)    SKIP_CREATE_VMS=true; shift ;;
+    --skip-add-hardware)  SKIP_ADD_HARDWARE=true; shift ;;
+    --skip-boot-wait)         SKIP_BOOT_WAIT=true; shift ;;
+    --skip-refresh-sops-keys) SKIP_REFRESH_SOPS_KEYS=true; shift ;;
+    --skip-cluster-init)      SKIP_CLUSTER_INIT=true; shift ;;
+    --skip-tests)         SKIP_TESTS=true;     shift ;;
+    --force-rebuild)      FORCE_REBUILD=true;  shift ;;
+    --destroy)            DESTROY=true;        shift ;;
+    --dry-run)            DRY_RUN=true;        shift ;;
+    -h|--help)            usage 0 ;;
+    *) echo "Unknown option: $1" >&2; usage 1 ;;
+  esac
+done
+
+# ── Helpers ───────────────────────────────────────────────────────────────────
+
+log()  { echo "==> $*"; }
+logn() { echo "    $*"; }
+err()  { echo "ERROR: $*" >&2; exit 1; }
+
+run() {
+  if $DRY_RUN; then
+    echo "[dry-run] $*"
+  else
+    "$@"
+  fi
+}
+
+pve() {
+  # Run a command on the Proxmox node via SSH.
+  if $DRY_RUN; then
+    echo "[dry-run] ssh ${SSH_USER}@${NODE} sudo $*"
+  else
+    ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "sudo $*"
+  fi
+}
+
+pve_check() {
+  # Run a read-only probe on the Proxmox node — always executes even in dry-run.
+  ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "sudo $*"
+}
+
+HA_USER="nixos"
+
+n1() {
+  # Run a command on ha-server-1 via SSH as nixos with sudo.
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE1_IP}" sudo "$@" 2>/dev/null
+}
+
+n2() {
+  # Run a command on ha-server-2 via SSH as nixos with sudo.
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE2_IP}" sudo "$@" 2>/dev/null
+}
+
+wait_for_ssh() {
+  local ip="$1" label="$2"
+  if $DRY_RUN; then
+    logn "[dry-run] Skipping SSH wait for ${label} (${ip})"
+    return 0
+  fi
+  local deadline=$(( $(date +%s) + 300 ))
+  log "Waiting for SSH on ${label} (${ip}) — up to 5 min..."
+  while [[ $(date +%s) -lt $deadline ]]; do
+    if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=3 \
+        -o BatchMode=yes "${HA_USER}@${ip}" true 2>/dev/null; then
+      logn "${label} is up."
+      return 0
+    fi
+    sleep 5
+  done
+  err "Timed out waiting for SSH on ${label} (${ip})"
+}
+
+# ── Destroy mode ─────────────────────────────────────────────────────────────
+
+if $DESTROY; then
+  log "Destroying HA cluster VMs (${VMID1}=${NODE1_HOST}, ${VMID2}=${NODE2_HOST}) on ${NODE}"
+  for vmid in "$VMID1" "$VMID2"; do
+    STATUS=$(pve "qm status ${vmid} 2>/dev/null" 2>/dev/null || true)
+    if echo "$STATUS" | grep -q "running"; then
+      log "Stopping VMID ${vmid}..."
+      pve "qm stop ${vmid} --skiplock 1"
+      sleep 5
+    fi
+    if $DRY_RUN || pve "qm config ${vmid} >/dev/null 2>&1"; then
+      log "Deleting VMID ${vmid}..."
+      run pve "qm destroy ${vmid} --purge 1"
+    else
+      logn "VMID ${vmid} not found — already gone."
+    fi
+  done
+  log "Done — cluster VMs destroyed."
+  exit 0
+fi
+
+# ── Phase 1: Storage bridge ───────────────────────────────────────────────────
+
+if ! $SKIP_ENSURE_BRIDGE; then
+  log "Phase 1: Ensuring storage bridge ${STORAGE_BRIDGE} on ${NODE}"
+  if pve_check "test -d /sys/class/net/${STORAGE_BRIDGE}" &>/dev/null; then
+    logn "${STORAGE_BRIDGE} already exists — skipping."
+  else
+    logn "Creating isolated internal bridge ${STORAGE_BRIDGE} (no upstream port, ${STORAGE_CIDR})"
+    BRIDGE_CONF="auto ${STORAGE_BRIDGE}
+iface ${STORAGE_BRIDGE} inet manual
+    bridge-ports none
+    bridge-stp off
+    bridge-fd 0"
+    if $DRY_RUN; then
+      echo "[dry-run] Would write /etc/network/interfaces.d/${STORAGE_BRIDGE}.conf and ifup it"
+    else
+      ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+        "echo '${BRIDGE_CONF}' | sudo tee /etc/network/interfaces.d/${STORAGE_BRIDGE}.conf > /dev/null && sudo ifup ${STORAGE_BRIDGE}"
+      logn "${STORAGE_BRIDGE} created and brought up."
+    fi
+  fi
+fi
+
+# ── Phase 2: Sync host keys ───────────────────────────────────────────────────
+
+if ! $SKIP_SYNC_KEYS; then
+  log "Phase 2: Syncing SSH host keys for both HA targets"
+  for target in proxmox-ha-server-1 proxmox-ha-server-2; do
+    CLAN_DIR="${REPO_ROOT}/vars/per-machine/${target}/openssh"
+    if [[ -d "$CLAN_DIR" ]]; then
+      logn "Clan vars for ${target} already exist — skipping."
+    else
+      logn "Generating host keys for ${target}..."
+      run bash "${REPO_ROOT}/scripts/secrets/sync-host-keys.sh" "$target"
+    fi
+  done
+fi
+
+# ── Phase 2.5: Prepare Proxmox node for building ─────────────────────────────
+if ! $SKIP_CREATE_VMS && ! $DRY_RUN; then
+  CURRENT_BRANCH="$(git -C "$REPO_ROOT" rev-parse --abbrev-ref HEAD)"
+
+  # Fix /nix ownership if it exists but belongs to a different UID.
+  # pve1's IPA-enrolled wayne (UID 50002) can't write to a store created by
+  # another UID — passwordless sudo corrects it once.
+  # Use direct SSH (no sudo) for the writability check so we test wayne's own
+  # access, not root's.
+  local_ssh() { ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" "$*"; }
+  if local_ssh "test -d /nix" &>/dev/null && ! local_ssh "test -w /nix" &>/dev/null; then
+    logn "/nix exists but not writable by ${SSH_USER} — fixing ownership with sudo (one-time)..."
+    local_ssh "sudo chown -R ${SSH_USER} /nix"
+    logn "Done."
+  fi
+  unset -f local_ssh
+
+  # Ensure the remote clone is on the correct branch so create-proxmox-resource.sh
+  # builds from the same commits we're deploying.
+  REMOTE_REPO="/home/${SSH_USER}/nixos"
+  if pve_check "test -d ${REMOTE_REPO}/.git" &>/dev/null; then
+    REMOTE_BRANCH=$(ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+      "cd ${REMOTE_REPO} && git rev-parse --abbrev-ref HEAD 2>/dev/null")
+    if [[ "$REMOTE_BRANCH" != "$CURRENT_BRANCH" ]]; then
+      logn "Remote clone is on '${REMOTE_BRANCH}', switching to '${CURRENT_BRANCH}'..."
+      ssh -i ~/.ssh/id_ed25519 "${SSH_USER}@${NODE}" \
+        "cd ${REMOTE_REPO} && git fetch origin && git checkout '${CURRENT_BRANCH}' && git pull --ff-only"
+      logn "Done."
+    fi
+  fi
+fi
+
+# ── Phase 3: Create VMs ───────────────────────────────────────────────────────
+
+if ! $SKIP_CREATE_VMS; then
+  log "Phase 3: Building and creating VMs on ${NODE}"
+
+  CREATE="${REPO_ROOT}/scripts/proxmox/create-proxmox-resource.sh"
+
+  for spec in "${VMID1}:ha-server-1:proxmox-ha-server-1" "${VMID2}:ha-server-2:proxmox-ha-server-2"; do
+    IFS=: read -r vmid host_name flake_target <<< "$spec"
+    log "Creating ${flake_target} (VMID ${vmid}) on ${NODE}..."
+    # Always --force-rebuild: create-proxmox-resource.sh only calls
+    # sync_remote_host_keys (which populates host-keys/ for proxmox.nix to
+    # bake the clan-var SSH key into the disko image) when it actually builds.
+    # Reusing a cached image skips that step, so destroy+recreate would reuse
+    # an image with a stale/random key baked in → sops fails on first boot.
+    run bash "$CREATE" \
+      --type vm \
+      --host "$host_name" \
+      --vmid "$vmid" \
+      --node "$NODE" \
+      --storage "$STORAGE" \
+      --memory "$MEMORY_MB" \
+      --cores "$CORES" \
+      --force-rebuild
+  done
+fi
+
+# ── Phase 4: Add storage NIC and DRBD disk ────────────────────────────────────
+
+if ! $SKIP_ADD_HARDWARE; then
+  log "Phase 4: Attaching storage NIC (${STORAGE_BRIDGE}) and DRBD disk (${DRBD_DISK_GB}G) to each VM"
+  for vmid in "$VMID1" "$VMID2"; do
+    log "  VMID ${vmid}: stopping to add hardware..."
+    pve "qm stop ${vmid} --skiplock 1 2>/dev/null; sleep 3" || true
+
+    logn "Adding net1 (${STORAGE_BRIDGE})..."
+    pve "qm set ${vmid} --net1 virtio,bridge=${STORAGE_BRIDGE},firewall=0"
+
+    logn "Adding scsi1 (${STORAGE}:${DRBD_DISK_GB}G for DRBD)..."
+    pve "qm set ${vmid} --scsi1 ${STORAGE}:${DRBD_DISK_GB},format=raw"
+
+    logn "Starting VMID ${vmid}..."
+    pve "qm start ${vmid}"
+  done
+fi
+
+# ── Phase 5: Wait for SSH ─────────────────────────────────────────────────────
+
+if ! $SKIP_BOOT_WAIT; then
+  log "Phase 5: Waiting for both nodes to come up"
+  wait_for_ssh "$NODE1_IP" "$NODE1_HOST"
+  wait_for_ssh "$NODE2_IP" "$NODE2_HOST"
+  logn "Both nodes are SSHable."
+  # Give systemd a few seconds to settle after activation
+  sleep 10
+fi
+
+# ── Phase 5.5: Refresh sops host-key registrations ───────────────────────────
+#
+# Disko builds raw disk images; each new VM boots with a freshly-generated SSH
+# host key rather than the one pre-seeded in clan vars.  This phase scans the
+# actual running VMs, and if their ed25519 host keys differ from what clan vars
+# record: updates the clan var pub-key files, rewrites the .sops.yaml age-key
+# anchors, and re-encrypts all affected sops files so the nodes can decrypt
+# secrets on the next nixos-rebuild.  Safe no-op when keys haven't changed.
+
+if ! $SKIP_REFRESH_SOPS_KEYS; then
+  if $DRY_RUN; then
+    logn "[dry-run] Would scan VM host keys and refresh .sops.yaml / secrets if needed"
+  else
+    log "Phase 5.5: Refreshing sops host-key registrations (disko key drift fix)"
+    SOPS_UPDATED=false
+
+    for spec in \
+      "${NODE1_IP}:proxmox-ha-server-1:${NODE1_HOST}" \
+      "${NODE2_IP}:proxmox-ha-server-2:${NODE2_HOST}"; do
+      IFS=: read -r node_ip flake_target host_name <<< "$spec"
+      CLAN_PUB="${REPO_ROOT}/vars/per-machine/${flake_target}/openssh/ssh_host_ed25519_key.pub/value"
+
+      logn "Scanning ed25519 host key from ${host_name} (${node_ip})..."
+      RAW=$(ssh-keyscan -t ed25519 "${node_ip}" 2>/dev/null | grep -v "^#") || true
+      if [[ -z "$RAW" ]]; then
+        logn "WARNING: no ed25519 key returned by ssh-keyscan for ${node_ip} — skipping"
+        continue
+      fi
+      # ssh-keyscan returns:  <ip>  ssh-ed25519  <b64key>
+      SCANNED_TYPE=$(awk '{print $2}' <<< "$RAW")
+      SCANNED_KEY=$(awk  '{print $3}' <<< "$RAW")
+      SCANNED_PUBKEY="${SCANNED_TYPE} ${SCANNED_KEY} ${host_name}"
+
+      CURRENT=$(tr -d '\n' < "$CLAN_PUB" 2>/dev/null || true)
+      if [[ "$SCANNED_PUBKEY" == "$CURRENT" ]]; then
+        logn "${host_name}: clan var matches running key — no update needed"
+        continue
+      fi
+
+      logn "${host_name}: key drift detected — updating clan var"
+      logn "  old: ${CURRENT}"
+      logn "  new: ${SCANNED_PUBKEY}"
+      echo "$SCANNED_PUBKEY" > "$CLAN_PUB"
+      SOPS_UPDATED=true
+
+      # Rewrite the .sops.yaml anchor for this host with the new age key.
+      ANCHOR="${flake_target}"   # e.g. proxmox-ha-server-1
+      NEW_AGE=$(echo "$SCANNED_PUBKEY" | \
+        nix run --quiet --no-warn-dirty nixpkgs#ssh-to-age 2>/dev/null)
+      if [[ -z "$NEW_AGE" ]]; then
+        err "ssh-to-age produced no output for ${host_name} — check nixpkgs#ssh-to-age"
+      fi
+      logn "  new age key: ${NEW_AGE}"
+      sed -i "/&${ANCHOR} /s| age[a-z0-9]*$| ${NEW_AGE}|" "${REPO_ROOT}/.sops.yaml"
+    done
+
+    if $SOPS_UPDATED; then
+      logn "Running sops updatekeys on affected secrets..."
+      SOPS="nix run --quiet --no-warn-dirty nixpkgs#sops --"
+      (cd "${REPO_ROOT}" && \
+        $SOPS updatekeys -y secrets/common.yaml && \
+        $SOPS updatekeys -y secrets/ha-server-1.yaml && \
+        $SOPS updatekeys -y secrets/ha-server-2.yaml && \
+        $SOPS updatekeys -y secrets/ha-server-1.keytab && \
+        $SOPS updatekeys -y secrets/ha-server-2.keytab)
+      # Note: ha-corosync-authkey is re-generated and re-encrypted by cluster-init below.
+
+      logn "Committing refreshed host keys and re-encrypted secrets..."
+      (cd "${REPO_ROOT}" && \
+        git add \
+          vars/per-machine/proxmox-ha-server-1/openssh/ssh_host_ed25519_key.pub/value \
+          vars/per-machine/proxmox-ha-server-2/openssh/ssh_host_ed25519_key.pub/value \
+          .sops.yaml \
+          secrets/common.yaml \
+          secrets/ha-server-1.yaml \
+          secrets/ha-server-2.yaml \
+          secrets/ha-server-1.keytab \
+          secrets/ha-server-2.keytab && \
+        git commit -m "secrets(ha): refresh sops host-key registrations for new VM instances" || true)
+      logn "Sops keys refreshed and committed."
+    fi
+  fi
+fi
+
+# ── Phase 6: Cluster init ─────────────────────────────────────────────────────
+
+if ! $SKIP_CLUSTER_INIT; then
+  log "Phase 6: Initialising HA cluster"
+
+  CLUSTER_INIT="${REPO_ROOT}/scripts/ha/cluster-init.sh"
+  [[ -x "$CLUSTER_INIT" ]] || chmod +x "$CLUSTER_INIT"
+
+  if $DRY_RUN; then
+    logn "[dry-run] Would generate temp key, authorise on ${NODE2_HOST}, scp cluster-init.sh to ${NODE1_HOST}, and run it as root via sudo"
+  else
+    # Generate a temp keypair so cluster-init.sh can SSH node1→node2 as ${HA_USER}.
+    # Root on node1 has no keys; a temp key bridging node1→node2 nixos solves this.
+    TEMP_KEY="${REPO_ROOT}/.tmp-cluster-init-key"
+    TEMP_KEY_PUB="${TEMP_KEY}.pub"
+    rm -f "$TEMP_KEY" "$TEMP_KEY_PUB"
+    ssh-keygen -t ed25519 -f "$TEMP_KEY" -N "" -C "cluster-init-temp-$(date +%s)" -q
+    TEMP_PUBKEY=$(cat "$TEMP_KEY_PUB")
+
+    logn "Authorising temp key on ${NODE2_HOST} for ${HA_USER}..."
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE2_IP}" \
+      "mkdir -p ~/.ssh && chmod 700 ~/.ssh && echo '${TEMP_PUBKEY}' >> ~/.ssh/authorized_keys"
+
+    logn "Placing temp key on ${NODE1_HOST} for root..."
+    scp -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \
+      "$TEMP_KEY" "${HA_USER}@${NODE1_IP}:/tmp/cluster-init-key"
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE1_IP}" \
+      "sudo mkdir -p /root/.ssh && sudo cp /tmp/cluster-init-key /root/.ssh/cluster-init-key && \
+       sudo chmod 600 /root/.ssh/cluster-init-key && rm -f /tmp/cluster-init-key"
+
+    logn "Uploading cluster-init.sh to ${NODE1_HOST}..."
+    scp -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \
+      "$CLUSTER_INIT" "${HA_USER}@${NODE1_IP}:/tmp/cluster-init.sh"
+
+    logn "Running cluster-init.sh on ${NODE1_HOST}..."
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE1_IP}" \
+      "sudo env NODE1=${NODE1_HOST} NODE2=${NODE2_HOST} \
+       NODE1_IP=${NODE1_IP} NODE2_IP=${NODE2_IP} \
+       VIP=192.168.20.229 XFS_MOUNT=/srv/ha-data \
+       ISCSI_IQN=iqn.2026-01.home.sweet:ha-storage \
+       VMID_NODE1=${VMID1} VMID_NODE2=${VMID2} \
+       HA_USER=${HA_USER} HA_KEY=/root/.ssh/cluster-init-key \
+       bash /tmp/cluster-init.sh"
+
+    logn "Cleaning up temp key from both nodes..."
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE2_IP}" \
+      "sed -i '/cluster-init-temp/d' ~/.ssh/authorized_keys" 2>/dev/null || true
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE1_IP}" \
+      "sudo rm -f /root/.ssh/cluster-init-key" 2>/dev/null || true
+    rm -f "$TEMP_KEY" "$TEMP_KEY_PUB"
+
+    # Encrypt the corosync authkey generated by cluster-init and commit it.
+    log "  Encrypting corosync authkey into secrets/ha-corosync-authkey..."
+    AUTHKEY_TMP="${REPO_ROOT}/secrets/ha-corosync-authkey.tmp"
+    ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${NODE1_IP}" \
+      "sudo cat /etc/corosync/authkey" > "$AUTHKEY_TMP"
+    if [[ ! -s "$AUTHKEY_TMP" ]]; then
+      err "corosync authkey on node1 is empty — cluster-init may have failed."
+    fi
+    mv "$AUTHKEY_TMP" "${REPO_ROOT}/secrets/ha-corosync-authkey"
+    (cd "${REPO_ROOT}" && nix run nixpkgs#sops -- -e --input-type binary -i secrets/ha-corosync-authkey)
+    logn "Authkey encrypted. Committing..."
+    (cd "${REPO_ROOT}" && git add secrets/ha-corosync-authkey && \
+      git commit -m "secrets(ha): encrypt corosync authkey generated by cluster-init")
+    logn "Committed."
+  fi
+fi
+
+# ── Phase 7: Acceptance tests ─────────────────────────────────────────────────
+
+if ! $SKIP_TESTS; then
+  log "Phase 7: Running acceptance tests (T1–T7)"
+  if $DRY_RUN; then
+    logn "[dry-run] Would run acceptance-tests.sh against ${NODE1_HOST}/${NODE2_HOST}"
+  else
+    NODE1="$NODE1_HOST" NODE2="$NODE2_HOST" \
+    NODE1_IP="$NODE1_IP" NODE2_IP="$NODE2_IP" \
+    VIP="192.168.20.229" \
+    bash "${REPO_ROOT}/scripts/ha/acceptance-tests.sh"
+  fi
+fi
+
+log "Deploy complete."

scripts/ha/failover.sh

@@ -0,0 +1,256 @@
+#!/usr/bin/env bash
+# failover.sh — graceful HA cluster failover
+#
+# Detects which node is active and moves all resources to the other node by
+# putting the active node into Pacemaker standby.  Waits for the XFS mount to
+# appear on the target before returning.
+#
+# Usage:
+#   scripts/ha/failover.sh [--to node1|node2] [--force] [--timeout <s>] [--dry-run]
+#
+#   --to node1|node2  target node (default: the node that is NOT currently active)
+#   --force           skip the interactive confirmation prompt
+#   --timeout <s>     seconds to wait for resources to move (default: 120)
+#   --dry-run         show what would be done without changing anything
+set -euo pipefail
+
+# ── Configuration ─────────────────────────────────────────────────────────
+NODE1="${NODE1:-ha-server-1}"
+NODE2="${NODE2:-ha-server-2}"
+NODE1_IP="${NODE1_IP:-192.168.2.228}"
+NODE2_IP="${NODE2_IP:-192.168.2.227}"
+VIP="${VIP:-192.168.20.229}"
+XFS_MOUNT="${XFS_MOUNT:-/srv/ha-data}"
+HA_USER="${HA_USER:-nixos}"
+# ──────────────────────────────────────────────────────────────────────────
+
+n1() { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE1_IP}" sudo "$@" 2>/dev/null; }
+n2() { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE2_IP}" sudo "$@" 2>/dev/null; }
+
+# ── Argument parsing ───────────────────────────────────────────────────────
+TARGET_NODE=""
+FORCE=false
+DRY_RUN=false
+TIMEOUT=120
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --to)
+      shift
+      case "${1:-}" in
+        node1|ha-server-1) TARGET_NODE="$NODE1" ;;
+        node2|ha-server-2) TARGET_NODE="$NODE2" ;;
+        *) echo "ERROR: --to must be node1, node2, ha-server-1, or ha-server-2"; exit 1 ;;
+      esac
+      ;;
+    --force)   FORCE=true ;;
+    --dry-run) DRY_RUN=true ;;
+    --timeout) shift; TIMEOUT="${1:?--timeout requires a value}" ;;
+    *) echo "Unknown argument: $1"; echo "Usage: $0 [--to node1|node2] [--force] [--timeout <s>] [--dry-run]"; exit 1 ;;
+  esac
+  shift
+done
+
+DRY_PREFIX=""
+$DRY_RUN && DRY_PREFIX="[dry-run] "
+
+echo "════════════════════════════════════════════════════"
+echo " HA Cluster Failover — $(date '+%Y-%m-%d %H:%M:%S')"
+$DRY_RUN && echo " MODE: dry-run — no changes will be made"
+echo "════════════════════════════════════════════════════"
+
+# ── Detect active node ─────────────────────────────────────────────────────
+echo ""
+echo "Detecting active node..."
+
+CRM_OUT=""
+if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE1_IP}" true 2>/dev/null; then
+  CRM_OUT=$(n1 "crm_mon -1" 2>/dev/null || true)
+fi
+if [[ -z "$CRM_OUT" ]]; then
+  if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE2_IP}" true 2>/dev/null; then
+    CRM_OUT=$(n2 "crm_mon -1" 2>/dev/null || true)
+  fi
+fi
+
+# crm_mon 2.x formats Promoted lines as "    * Promoted: [ node ]" — the * bullet
+# means ^\s*(Promoted|Masters): never matches; filter Unpromoted first instead.
+ACTIVE_NODE=$(echo "$CRM_OUT" | grep -v 'Unpromoted\|Unmanaged' | \
+  grep -E '(Promoted|Masters):' | \
+  grep -oE '\b(ha-server-[0-9]+)\b' | head -1 || true)
+
+if [[ -z "$ACTIVE_NODE" ]]; then
+  echo ""
+  echo "ERROR: could not determine active node from crm_mon."
+  echo "  Is Pacemaker still settling?  Try running scripts/ha/health.sh first."
+  echo "  If Pacemaker is down on both nodes, manual recovery is required."
+  exit 1
+fi
+
+if [[ "$ACTIVE_NODE" == "$NODE1" ]]; then
+  ACTIVE_IP="$NODE1_IP"
+  STANDBY_NODE="$NODE2"
+  STANDBY_IP="$NODE2_IP"
+  na() { n1 "$@"; }
+  ns() { n2 "$@"; }
+else
+  ACTIVE_IP="$NODE2_IP"
+  STANDBY_NODE="$NODE1"
+  STANDBY_IP="$NODE1_IP"
+  na() { n2 "$@"; }
+  ns() { n1 "$@"; }
+fi
+
+echo "  Active:  $ACTIVE_NODE ($ACTIVE_IP)"
+echo "  Standby: $STANDBY_NODE ($STANDBY_IP)"
+
+# ── Validate target ────────────────────────────────────────────────────────
+if [[ -n "$TARGET_NODE" ]]; then
+  if [[ "$TARGET_NODE" == "$ACTIVE_NODE" ]]; then
+    echo ""
+    echo "ERROR: $TARGET_NODE is already the active node — nothing to do."
+    exit 1
+  fi
+  echo "  Target:  $TARGET_NODE (as requested)"
+else
+  echo "  Target:  $STANDBY_NODE (auto — the other node)"
+fi
+
+# ── Pre-checks ─────────────────────────────────────────────────────────────
+echo ""
+echo "Pre-checks..."
+
+DRBD_DSTATE=$(na "drbdadm dstate ha-data 2>/dev/null" 2>/dev/null || echo "unknown")
+if ! echo "$DRBD_DSTATE" | grep -q "UpToDate/UpToDate"; then
+  echo ""
+  echo "  WARNING: DRBD dstate is '$DRBD_DSTATE' (not UpToDate/UpToDate)."
+  echo "  Failing over with a partially-synced disk risks split-brain."
+  if ! $FORCE; then
+    echo "  Use --force to proceed anyway (not recommended)."
+    exit 1
+  fi
+  echo "  --force specified — proceeding despite non-ideal DRBD state."
+else
+  echo "  DRBD dstate: $DRBD_DSTATE — OK"
+fi
+
+QUORUM_OK=$(na "corosync-quorumtool -s 2>/dev/null | grep -c 'Quorate:.*Yes'" 2>/dev/null || echo "0")
+if [[ "$QUORUM_OK" -lt 1 ]]; then
+  echo "  ERROR: cluster does not have quorum — failover would be unsafe."
+  exit 1
+fi
+echo "  Quorum: OK"
+
+# ── Confirm ────────────────────────────────────────────────────────────────
+if ! $FORCE && ! $DRY_RUN; then
+  echo ""
+  echo "  This will move all resources from $ACTIVE_NODE → $STANDBY_NODE."
+  echo "  VIP and services will be unreachable for ~10–30 seconds."
+  printf "  Proceed? [y/N] "
+  read -r ANSWER
+  [[ "${ANSWER,,}" == "y" || "${ANSWER,,}" == "yes" ]] || { echo "Aborted."; exit 0; }
+fi
+
+# ── Capture active node's crm_node name ───────────────────────────────────
+# crm_node -n returns the node name as registered in Pacemaker (may differ
+# from hostname if Pacemaker was configured with explicit node names).
+ACTIVE_CRMD_NAME=$(na "crm_node -n 2>/dev/null" 2>/dev/null || echo "$ACTIVE_NODE")
+
+# ── Perform failover ───────────────────────────────────────────────────────
+echo ""
+echo "${DRY_PREFIX}Putting $ACTIVE_NODE into standby (resources will migrate to $STANDBY_NODE)..."
+if ! $DRY_RUN; then
+  na "crm_standby -N '${ACTIVE_CRMD_NAME}' -v on" 2>/dev/null || true
+fi
+
+# ── Wait for resources to move ─────────────────────────────────────────────
+echo "${DRY_PREFIX}Waiting up to ${TIMEOUT}s for XFS to mount on $STANDBY_NODE..."
+MOVED=false
+SPIN_CHARS=('|' '/' '-' '\')
+SPIN_I=0
+
+if $DRY_RUN; then
+  echo "  [dry-run] would wait for mountpoint $XFS_MOUNT on $STANDBY_NODE"
+  MOVED=true
+else
+  for i in $(seq 1 "$TIMEOUT"); do
+    if ns "mountpoint -q '${XFS_MOUNT}' 2>/dev/null" 2>/dev/null; then
+      printf "\r%-80s\r" ""
+      echo "  Resources moved in ${i}s"
+      MOVED=true
+      break
+    fi
+    SPIN_I=$(( SPIN_I + 1 ))
+    SC="${SPIN_CHARS[$((SPIN_I % 4))]}"
+    printf "\r  [%s] waiting... (%ds)     " "$SC" "$i"
+    sleep 1
+  done
+fi
+
+if ! $MOVED; then
+  echo ""
+  echo "ERROR: XFS did not mount on $STANDBY_NODE within ${TIMEOUT}s."
+  echo ""
+  echo "  Current resource state:"
+  na "crm_mon -1 2>/dev/null" 2>/dev/null | grep -E 'Started|Stopped|Promoted|Unpromoted|FAILED' | sed 's/^/  /' || true
+  echo ""
+  echo "  Clearing standby to restore $ACTIVE_NODE (undo the failover attempt)..."
+  na "crm_standby -N '${ACTIVE_CRMD_NAME}' -v off" 2>/dev/null || true
+  na "crm_resource --cleanup" 2>/dev/null || true
+  exit 1
+fi
+
+# ── Clear failure history ──────────────────────────────────────────────────
+echo "${DRY_PREFIX}Clearing Pacemaker failure history..."
+if ! $DRY_RUN; then
+  ns "crm_resource --cleanup 2>/dev/null" 2>/dev/null || true
+fi
+
+# ── Re-enable original active node as standby ─────────────────────────────
+echo "${DRY_PREFIX}Re-enabling $ACTIVE_NODE (now standby — will not claim resources)..."
+if ! $DRY_RUN; then
+  na "crm_standby -N '${ACTIVE_CRMD_NAME}' -v off" 2>/dev/null || true
+fi
+
+# ── Wait briefly for DRBD resync to begin ─────────────────────────────────
+if ! $DRY_RUN; then
+  sleep 5
+fi
+
+# ── Final state ────────────────────────────────────────────────────────────
+echo ""
+echo "Failover complete.  Final state:"
+echo ""
+
+CRM_OUT_AFTER=""
+if ! $DRY_RUN; then
+  CRM_OUT_AFTER=$(ns "crm_mon -1" 2>/dev/null || na "crm_mon -1" 2>/dev/null || true)
+else
+  CRM_OUT_AFTER="$CRM_OUT"
+fi
+
+NEW_ACTIVE=$(echo "$CRM_OUT_AFTER" | grep -v 'Unpromoted\|Unmanaged' | \
+  grep -E '(Promoted|Masters):' | \
+  grep -oE '\b(ha-server-[0-9]+)\b' | head -1 || true)
+
+if [[ -n "$NEW_ACTIVE" ]]; then
+  if [[ "$NEW_ACTIVE" == "$ACTIVE_NODE" ]]; then
+    echo "  WARNING: $ACTIVE_NODE is still showing as active in crm_mon."
+    echo "  Pacemaker may still be settling — check again in a few seconds."
+  else
+    echo "  Active:  $NEW_ACTIVE"
+    echo "  Standby: $ACTIVE_NODE"
+  fi
+fi
+
+echo ""
+RESOURCES_AFTER=$(echo "$CRM_OUT_AFTER" | awk '/Full List of Resources/,0' | tail -n +2 || true)
+[[ -z "$RESOURCES_AFTER" ]] && RESOURCES_AFTER=$(echo "$CRM_OUT_AFTER" | \
+  grep -E 'Started|Stopped|Promoted|Unpromoted|FAILED|Master|Slave' || true)
+[[ -n "$RESOURCES_AFTER" ]] && echo "$RESOURCES_AFTER" | sed 's/^/  /'
+
+echo ""
+echo "  (DRBD resync of $ACTIVE_NODE may take a moment; monitor with:"
+echo "   ssh nixos@${ACTIVE_IP} 'sudo watch -n3 cat /proc/drbd')"
+echo ""
+echo "════════════════════════════════════════════════════"

scripts/ha/fence-pve-ssh.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+"""
+fence_pve_ssh - Proxmox VE SSH fence agent for Pacemaker.
+
+Uses SSH to reach the Proxmox host and run 'qm stop/start <vmid>'.
+Deploy to /etc/pacemaker/fence_pve_ssh on both HA nodes (chmod +x).
+
+Configuration (as pacemaker stonith resource attributes):
+  pve_host     Proxmox host to SSH to (default: pve1.sweet.home)
+  pve_user     SSH user (default: wayne)
+  key_file     SSH private key path (default: /etc/fence-pve-ssh-key)
+  vmid_node1   VMID for ha-server-1
+  vmid_node2   VMID for ha-server-2
+  plug         Node name to act on (set by pacemaker: ha-server-1 or ha-server-2)
+  action       Action: off|on|reboot|status|list|metadata
+"""
+
+import argparse
+import subprocess
+import sys
+import os
+
+
+METADATA = """<?xml version="1.0" ?>
+<resource-agent name="fence_pve_ssh" shortdesc="Proxmox VE SSH fence agent (test lab)">
+  <longdesc>Fences a VM on a Proxmox VE host by SSHing to the PVE host and
+  running qm stop/start.  For test use only.</longdesc>
+  <vendor-url>https://proxmox.com</vendor-url>
+  <parameters>
+    <parameter name="action" required="1" unique="0">
+      <getopt mixed="-a, --action=[action]"/>
+      <content type="string" default="reboot"/>
+      <shortdesc lang="en">Fencing action: off|on|reboot|status|list</shortdesc>
+    </parameter>
+    <parameter name="plug" required="0" unique="0">
+      <getopt mixed="-n, --plug=[nodename]"/>
+      <content type="string"/>
+      <shortdesc lang="en">Cluster node name to fence</shortdesc>
+    </parameter>
+    <parameter name="pve_host" required="0" unique="0">
+      <getopt mixed="--pve-host=[host]"/>
+      <content type="string" default="pve1.sweet.home"/>
+      <shortdesc lang="en">Proxmox VE host to SSH to</shortdesc>
+    </parameter>
+    <parameter name="pve_user" required="0" unique="0">
+      <getopt mixed="--pve-user=[user]"/>
+      <content type="string" default="wayne"/>
+      <shortdesc lang="en">SSH user on the Proxmox host</shortdesc>
+    </parameter>
+    <parameter name="key_file" required="0" unique="0">
+      <getopt mixed="--key-file=[path]"/>
+      <content type="string" default="/etc/fence-pve-ssh-key"/>
+      <shortdesc lang="en">SSH private key file path</shortdesc>
+    </parameter>
+    <parameter name="vmid_node1" required="1" unique="0">
+      <getopt mixed="--vmid-node1=[vmid]"/>
+      <content type="string"/>
+      <shortdesc lang="en">VMID for ha-test-node1</shortdesc>
+    </parameter>
+    <parameter name="vmid_node2" required="1" unique="0">
+      <getopt mixed="--vmid-node2=[vmid]"/>
+      <content type="string"/>
+      <shortdesc lang="en">VMID for ha-test-node2</shortdesc>
+    </parameter>
+  </parameters>
+  <actions>
+    <action name="off" timeout="60s"/>
+    <action name="on" timeout="60s"/>
+    <action name="reboot" timeout="60s"/>
+    <action name="status" timeout="30s"/>
+    <action name="list" timeout="10s"/>
+    <action name="metadata" timeout="5s"/>
+  </actions>
+</resource-agent>
+"""
+
+
+def parse_args():
+    p = argparse.ArgumentParser(add_help=False)
+    p.add_argument("-a", "--action", default="reboot")
+    p.add_argument("-n", "--plug")
+    p.add_argument("--pve-host", default="pve1.sweet.home")
+    p.add_argument("--pve-user", default="wayne")
+    p.add_argument("--key-file", default="/etc/fence-pve-ssh-key")
+    p.add_argument("--vmid-node1")
+    p.add_argument("--vmid-node2")
+    # Allow remaining unknown args (pacemaker may pass extra ones)
+    return p.parse_known_args()[0]
+
+
+def ssh(pve_host, pve_user, key_file, cmd):
+    result = subprocess.run(
+        [
+            "ssh",
+            "-i", key_file,
+            "-o", "StrictHostKeyChecking=no",
+            "-o", "BatchMode=yes",
+            "-o", "ConnectTimeout=10",
+            f"{pve_user}@{pve_host}",
+            cmd,
+        ],
+        capture_output=True,
+        text=True,
+        timeout=30,
+    )
+    return result
+
+
+def get_vmid(args):
+    node = args.plug
+    if not node:
+        print("ERROR: --plug not specified", file=sys.stderr)
+        sys.exit(1)
+    mapping = {
+        "ha-server-1": args.vmid_node1,
+        "ha-server-2": args.vmid_node2,
+    }
+    vmid = mapping.get(node)
+    if not vmid:
+        print(f"ERROR: unknown node '{node}'", file=sys.stderr)
+        sys.exit(1)
+    return vmid
+
+
+def main():
+    args = parse_args()
+    action = args.action.lower()
+
+    if action == "metadata":
+        print(METADATA)
+        sys.exit(0)
+
+    if action == "list":
+        if args.vmid_node1:
+            print("ha-server-1")
+        if args.vmid_node2:
+            print("ha-server-2")
+        sys.exit(0)
+
+    vmid = get_vmid(args)
+
+    if not os.path.exists(args.key_file):
+        print(f"ERROR: SSH key not found at {args.key_file}", file=sys.stderr)
+        sys.exit(1)
+
+    if action in ("off", "reboot"):
+        print(f"Stopping VM {vmid} ({args.plug}) on {args.pve_host}...")
+        r = ssh(args.pve_host, args.pve_user, args.key_file,
+                f"sudo /usr/sbin/qm stop {vmid}")
+        if r.returncode != 0:
+            print(f"ERROR stopping VM: {r.stderr}", file=sys.stderr)
+            sys.exit(1)
+        print(f"VM {vmid} stopped")
+
+    if action in ("on", "reboot"):
+        print(f"Starting VM {vmid} ({args.plug}) on {args.pve_host}...")
+        r = ssh(args.pve_host, args.pve_user, args.key_file,
+                f"sudo /usr/sbin/qm start {vmid}")
+        if r.returncode != 0:
+            print(f"ERROR starting VM: {r.stderr}", file=sys.stderr)
+            sys.exit(1)
+        print(f"VM {vmid} started")
+
+    if action == "status":
+        r = ssh(args.pve_host, args.pve_user, args.key_file,
+                f"sudo /usr/sbin/qm status {vmid}")
+        if r.returncode != 0:
+            print(f"ERROR querying VM status: {r.stderr}", file=sys.stderr)
+            sys.exit(1)
+        # qm status returns "status: running" or "status: stopped"
+        status_line = r.stdout.strip()
+        print(status_line)
+        if "stopped" in status_line:
+            sys.exit(2)   # pacemaker interprets exit 2 as "off"
+        sys.exit(0)       # running = exit 0
+
+
+if __name__ == "__main__":
+    main()

scripts/ha/health.sh

@@ -0,0 +1,206 @@
+#!/usr/bin/env bash
+# health.sh — HA cluster health snapshot (read-only, non-destructive)
+#
+# Prints a compact status panel across both nodes: SSH reachability, quorum,
+# DRBD state, Pacemaker resources, and service ports via the VIP.
+# Run from any host with SSH access to the HA nodes.
+set -euo pipefail
+
+# ── Configuration ─────────────────────────────────────────────────────────
+NODE1="${NODE1:-ha-server-1}"
+NODE2="${NODE2:-ha-server-2}"
+NODE1_IP="${NODE1_IP:-192.168.2.228}"   # vars.haServer1Ip
+NODE2_IP="${NODE2_IP:-192.168.2.227}"   # vars.haServer2Ip
+VIP="${VIP:-192.168.20.229}"            # vars.haServerVip (storage-client, VLAN 20 — internal only)
+VIP_LAN="${VIP_LAN:-192.168.2.229}"    # vars.haServerLanVip (LAN, VLAN 2 — reachable from workstation)
+XFS_MOUNT="${XFS_MOUNT:-/srv/ha-data}"  # vars.haStorageRoot
+HA_USER="${HA_USER:-nixos}"
+# ──────────────────────────────────────────────────────────────────────────
+
+REACHABLE_1=false
+REACHABLE_2=false
+
+n1()  { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE1_IP}" sudo "$@" 2>/dev/null; }
+n2()  { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${NODE2_IP}" sudo "$@" 2>/dev/null; }
+
+probe_node() {
+  local ip=$1
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 "${HA_USER}@${ip}" true 2>/dev/null && echo "ONLINE" || echo "OFFLINE"
+}
+
+section() { echo ""; echo "── $* ──"; }
+
+echo "════════════════════════════════════════════════════"
+echo " HA Cluster Health — $(date '+%Y-%m-%d %H:%M:%S')"
+echo "════════════════════════════════════════════════════"
+
+# ── Node reachability ──────────────────────────────────────────────────────
+section "Nodes"
+N1_STATUS=$(probe_node "$NODE1_IP")
+N2_STATUS=$(probe_node "$NODE2_IP")
+[[ "$N1_STATUS" == "ONLINE" ]] && REACHABLE_1=true
+[[ "$N2_STATUS" == "ONLINE" ]] && REACHABLE_2=true
+
+if ! $REACHABLE_1 && ! $REACHABLE_2; then
+  echo "  ERROR: both nodes unreachable — cannot continue."
+  exit 1
+fi
+
+# ── Detect active node ─────────────────────────────────────────────────────
+# crm_mon 2.x formats the Promoted line as "    * Promoted: [ node ]" — the
+# bullet * means ^\s*(Promoted|Masters): never matches.  Filter out Unpromoted
+# first, then match anywhere on the line.
+ACTIVE_NODE=""
+CRM_OUT=""
+if $REACHABLE_1; then
+  CRM_OUT=$(n1 "crm_mon -1" 2>/dev/null || true)
+elif $REACHABLE_2; then
+  CRM_OUT=$(n2 "crm_mon -1" 2>/dev/null || true)
+fi
+ACTIVE_NODE=$(echo "${CRM_OUT:-}" | grep -v 'Unpromoted\|Unmanaged' | \
+  grep -E '(Promoted|Masters):' | \
+  grep -oE '\b(ha-server-[0-9]+)\b' | head -1 || true)
+
+STANDBY_NODE=""
+if [[ "$ACTIVE_NODE" == "$NODE1" ]]; then
+  STANDBY_NODE="$NODE2"
+elif [[ "$ACTIVE_NODE" == "$NODE2" ]]; then
+  STANDBY_NODE="$NODE1"
+fi
+
+n1_tag=""; n2_tag=""
+[[ "$ACTIVE_NODE" == "$NODE1" ]] && n1_tag=" [ACTIVE]"  || n1_tag=" [STANDBY]"
+[[ "$ACTIVE_NODE" == "$NODE2" ]] && n2_tag=" [ACTIVE]"  || n2_tag=" [STANDBY]"
+[[ -z "$ACTIVE_NODE" ]] && { n1_tag=""; n2_tag=""; }
+
+printf "  %-14s  [%s]%s\n" "$NODE1" "$N1_STATUS" "$n1_tag"
+printf "  %-14s  [%s]%s\n" "$NODE2" "$N2_STATUS" "$n2_tag"
+
+if [[ -z "$ACTIVE_NODE" ]]; then
+  echo ""
+  echo "  WARNING: could not determine active node from crm_mon."
+  echo "  Pacemaker may still be settling, or both nodes may be in standby."
+fi
+
+# ── Quorum ─────────────────────────────────────────────────────────────────
+section "Quorum"
+if $REACHABLE_1; then
+  QUORUM=$(n1 "corosync-quorumtool -s 2>/dev/null" 2>/dev/null || echo "")
+elif $REACHABLE_2; then
+  QUORUM=$(n2 "corosync-quorumtool -s 2>/dev/null" 2>/dev/null || echo "")
+fi
+
+if [[ -z "${QUORUM:-}" ]]; then
+  echo "  corosync-quorumtool: unavailable"
+else
+  QUORATE=$(echo "$QUORUM" | grep "Quorate:" | awk '{print $2}' || echo "?")
+  VOTES=$(echo "$QUORUM" | grep "Total votes:" | awk '{print $3}' || echo "?")
+  NEEDED=$(echo "$QUORUM" | grep "Quorum votes:" | awk '{print $3}' || echo "?")
+  echo "  Quorate: $QUORATE   Votes: $VOTES / Expected: $NEEDED"
+fi
+
+# ── DRBD ───────────────────────────────────────────────────────────────────
+section "DRBD (ha-data)"
+
+drbd_info_from() {
+  local node=$1 run=$2
+  local role dstate cs pct
+  role=$($run "drbdadm role ha-data 2>/dev/null" 2>/dev/null || echo "unknown")
+  dstate=$($run "drbdadm dstate ha-data 2>/dev/null" 2>/dev/null || echo "unknown")
+  cs=$($run "grep -oE 'cs:[A-Za-z]+' /proc/drbd 2>/dev/null | head -1 | sed 's/cs://'" 2>/dev/null || echo "unknown")
+  pct=$($run "grep -oE \"sync'ed:[[:space:]]+[0-9.]+\" /proc/drbd 2>/dev/null | grep -oE '[0-9.]+$' | head -1" 2>/dev/null || echo "")
+  printf "  %-14s  role: %-22s  dstate: %-25s  cs: %s" \
+    "$node" "${role:-unknown}" "${dstate:-unknown}" "${cs:-unknown}"
+  [[ -n "$pct" ]] && printf "  syncing: %s%%" "$pct"
+  echo ""
+}
+
+$REACHABLE_1 && drbd_info_from "$NODE1" n1 || echo "  $NODE1  [OFFLINE]"
+$REACHABLE_2 && drbd_info_from "$NODE2" n2 || echo "  $NODE2  [OFFLINE]"
+
+# ── Pacemaker (full crm_mon output) ───────────────────────────────────────
+section "Pacemaker"
+if [[ -n "${CRM_OUT:-}" ]]; then
+  echo "$CRM_OUT" | sed 's/^/  /'
+else
+  echo "  crm_mon returned no output — trying again without suppression:"
+  if $REACHABLE_1; then
+    n1 "crm_mon -1" || true
+  elif $REACHABLE_2; then
+    n2 "crm_mon -1" || true
+  fi
+fi
+
+# ── XFS mount ─────────────────────────────────────────────────────────────
+section "XFS Mount ($XFS_MOUNT)"
+check_mount() {
+  local node=$1 run=$2
+  local status
+  if $run "mountpoint -q '$XFS_MOUNT' 2>/dev/null" 2>/dev/null; then
+    local usage
+    usage=$($run "df -h '$XFS_MOUNT' 2>/dev/null | tail -1 | awk '{print \$3\"/\"\$2\" used (\"\$5\")\";}'" 2>/dev/null || echo "")
+    status="mounted"
+    [[ -n "$usage" ]] && status="mounted  $usage"
+  else
+    status="not mounted"
+  fi
+  printf "  %-14s  %s\n" "$node" "$status"
+}
+
+$REACHABLE_1 && check_mount "$NODE1" n1 || echo "  $NODE1  [OFFLINE]"
+$REACHABLE_2 && check_mount "$NODE2" n2 || echo "  $NODE2  [OFFLINE]"
+
+# ── LAN VIP (NFS) — reachable from workstation ────────────────────────────────
+section "LAN VIP ($VIP_LAN) — NFS"
+if ping -c1 -W2 "$VIP_LAN" >/dev/null 2>&1; then
+  echo "  Ping       OK"
+else
+  echo "  Ping       UNREACHABLE"
+fi
+if bash -c "echo >/dev/tcp/${VIP_LAN}/2049" 2>/dev/null; then
+  printf "  %-10s  port %-5s  OK\n" "NFS" "2049"
+else
+  printf "  %-10s  port %-5s  UNREACHABLE\n" "NFS" "2049"
+fi
+
+# ── Storage VIP (NFS + iSCSI) — VLAN 20 internal bridge, tested via active node ─
+section "Storage VIP ($VIP) — NFS + iSCSI (via ${ACTIVE_NODE:-unknown})"
+
+run_active_raw() {
+  local active_ip=""
+  [[ "$ACTIVE_NODE" == "$NODE1" ]] && active_ip="$NODE1_IP"
+  [[ "$ACTIVE_NODE" == "$NODE2" ]] && active_ip="$NODE2_IP"
+  [[ -z "$active_ip" ]] && return 1
+  ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+    "${HA_USER}@${active_ip}" "$@" 2>/dev/null
+}
+
+if [[ -z "$ACTIVE_NODE" ]]; then
+  echo "  Cannot determine active node — skipping"
+else
+  if run_active_raw "ping -c1 -W2 '$VIP' >/dev/null 2>&1"; then
+    echo "  Ping       OK"
+  else
+    echo "  Ping       UNREACHABLE"
+  fi
+  if run_active_raw "bash -c 'echo >/dev/tcp/${VIP}/2049' 2>/dev/null"; then
+    printf "  %-10s  port %-5s  OK\n" "NFS" "2049"
+  else
+    printf "  %-10s  port %-5s  UNREACHABLE\n" "NFS" "2049"
+  fi
+  if run_active_raw "bash -c 'echo >/dev/tcp/${VIP}/3260' 2>/dev/null"; then
+    printf "  %-10s  port %-5s  OK\n" "iSCSI" "3260"
+  else
+    printf "  %-10s  port %-5s  UNREACHABLE\n" "iSCSI" "3260"
+  fi
+fi
+
+echo ""
+echo "════════════════════════════════════════════════════"
+if [[ -n "$ACTIVE_NODE" ]]; then
+  echo " Active: $ACTIVE_NODE   Standby: $STANDBY_NODE"
+else
+  echo " Active: unknown (Pacemaker not settled)"
+fi
+echo "════════════════════════════════════════════════════"
+echo ""

scripts/ha/resize-data-disk.sh

@@ -0,0 +1,274 @@
+#!/usr/bin/env bash
+# resize-data-disk.sh — online resize of the HA cluster data disk
+#
+# Three-phase process (all online-safe, no downtime required):
+#   1. Proxmox: grow scsi1 on both HA VMs   (qm resize)
+#   2. Guest:   rescan block device on both nodes so the kernel sees the new size
+#   3. DRBD + XFS: drbdadm resize, then xfs_growfs — active node only
+#
+# Usage:
+#   scripts/ha/resize-data-disk.sh --size +20G [--force] [--dry-run]
+#
+#   --size +NNg    amount to grow scsi1 by, e.g. +20G, +50G (required)
+#                  XFS and DRBD cannot shrink; only positive deltas accepted
+#   --force        skip the interactive confirmation prompt
+#   --dry-run      show what would be done without changing anything
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# shellcheck source=../env.sh
+source "${SCRIPT_DIR}/../env.sh"
+
+# ── Configuration ─────────────────────────────────────────────────────────
+NODE1="${NODE1:-ha-server-1}"
+NODE2="${NODE2:-ha-server-2}"
+NODE1_IP="${NODE1_IP:-192.168.2.228}"
+NODE2_IP="${NODE2_IP:-192.168.2.227}"
+XFS_MOUNT="${XFS_MOUNT:-/srv/ha-data}"
+DRBD_RESOURCE="${DRBD_RESOURCE:-ha-data}"
+DATA_DISK_SLOT="${DATA_DISK_SLOT:-scsi1}"   # Proxmox disk name (scsi1 = data disk)
+HA_USER="${HA_USER:-nixos}"
+PVE_HOST="${PVE_HOST:-${PVE1_HOST}}"
+PVE_SSH_USER="${PVE_SSH_USER:-${PROXMOX_SSH_USER}}"
+PVE_SUDO=""
+[[ "$PVE_SSH_USER" != "root" ]] && PVE_SUDO="sudo"
+# By-id symlink for the data disk; basename resolves to the raw block device.
+# matches variables.nix's haServerDrbdDisk.
+DATA_DISK_BYID="${DATA_DISK_BYID:-scsi-0QEMU_QEMU_HARDDISK_drive-${DATA_DISK_SLOT}}"
+# ──────────────────────────────────────────────────────────────────────────
+
+pve() { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=10 \
+          "${PVE_SSH_USER}@${PVE_HOST}" "$@"; }
+n1()  { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+          "${HA_USER}@${NODE1_IP}" sudo "$@" 2>/dev/null; }
+n2()  { ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+          "${HA_USER}@${NODE2_IP}" sudo "$@" 2>/dev/null; }
+
+# ── Argument parsing ───────────────────────────────────────────────────────
+SIZE=""
+FORCE=false
+DRY_RUN=false
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --size)    shift; SIZE="${1:?--size requires a value (e.g. +20G)}" ;;
+    --force)   FORCE=true ;;
+    --dry-run) DRY_RUN=true ;;
+    *) echo "Unknown argument: $1"
+       echo "Usage: $0 --size +NNg [--force] [--dry-run]"
+       exit 1 ;;
+  esac
+  shift
+done
+
+if [[ -z "$SIZE" ]]; then
+  echo "ERROR: --size is required (e.g. --size +20G)"
+  echo "Usage: $0 --size +NNg [--force] [--dry-run]"
+  exit 1
+fi
+
+# Only positive deltas — qm resize, DRBD, and XFS all refuse to shrink.
+if [[ ! "$SIZE" =~ ^\+[0-9]+(G|M|T)$ ]]; then
+  echo "ERROR: --size must be a positive delta like +20G, +50G, +500M, +2T"
+  echo "       (qm resize, drbdadm resize, and xfs_growfs can only grow, not shrink)"
+  exit 1
+fi
+
+DRY_PREFIX=""
+$DRY_RUN && DRY_PREFIX="[dry-run] "
+
+echo "════════════════════════════════════════════════════"
+echo " HA Data Disk Resize — $(date '+%Y-%m-%d %H:%M:%S')"
+echo " Size delta: $SIZE  •  Proxmox: $PVE_HOST"
+$DRY_RUN && echo " MODE: dry-run — no changes will be made"
+echo "════════════════════════════════════════════════════"
+
+# ── Detect active node ─────────────────────────────────────────────────────
+echo ""
+echo "Detecting active node..."
+
+CRM_OUT=""
+if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+     "${HA_USER}@${NODE1_IP}" true 2>/dev/null; then
+  CRM_OUT=$(n1 "crm_mon -1" 2>/dev/null || true)
+fi
+if [[ -z "$CRM_OUT" ]]; then
+  if ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no -o ConnectTimeout=5 \
+       "${HA_USER}@${NODE2_IP}" true 2>/dev/null; then
+    CRM_OUT=$(n2 "crm_mon -1" 2>/dev/null || true)
+  fi
+fi
+
+# crm_mon 2.x formats Promoted lines as "    * Promoted: [ node ]" (bullet *),
+# so ^\s*(Promoted|Masters): never matches; filter Unpromoted first instead.
+ACTIVE_NODE=$(echo "$CRM_OUT" | grep -v 'Unpromoted\|Unmanaged' | \
+  grep -E '(Promoted|Masters):' | \
+  grep -oE '\b(ha-server-[0-9]+)\b' | head -1 || true)
+
+if [[ -z "$ACTIVE_NODE" ]]; then
+  echo "ERROR: could not determine active node from crm_mon."
+  echo "  Is Pacemaker still settling?  Try running scripts/ha/health.sh first."
+  exit 1
+fi
+
+if [[ "$ACTIVE_NODE" == "$NODE1" ]]; then
+  ACTIVE_IP="$NODE1_IP"
+  na() { n1 "$@"; }
+else
+  ACTIVE_IP="$NODE2_IP"
+  na() { n2 "$@"; }
+fi
+
+echo "  Active node: $ACTIVE_NODE ($ACTIVE_IP)"
+
+# ── Pre-check DRBD state ───────────────────────────────────────────────────
+echo ""
+echo "Pre-checks..."
+
+DRBD_DSTATE=$(na "drbdadm dstate ${DRBD_RESOURCE} 2>/dev/null" 2>/dev/null || echo "unknown")
+if ! echo "$DRBD_DSTATE" | grep -q "UpToDate/UpToDate"; then
+  echo "  WARNING: DRBD dstate is '$DRBD_DSTATE' (expected UpToDate/UpToDate)."
+  echo "  Resizing with a partially-synced disk may cause issues."
+  if ! $FORCE; then
+    echo "  Use --force to proceed anyway."
+    exit 1
+  fi
+  echo "  --force specified — proceeding despite non-ideal DRBD state."
+else
+  echo "  DRBD dstate: $DRBD_DSTATE — OK"
+fi
+
+# ── Find VMIDs on Proxmox ─────────────────────────────────────────────────
+echo ""
+echo "Looking up VM IDs on ${PVE_HOST}..."
+
+QM_LIST=$(pve "$PVE_SUDO qm list 2>/dev/null" || true)
+VMID1=$(echo "$QM_LIST" | awk -v name="$NODE1" '$0 ~ name {print $1}' | head -1)
+VMID2=$(echo "$QM_LIST" | awk -v name="$NODE2" '$0 ~ name {print $1}' | head -1)
+
+if [[ -z "$VMID1" ]]; then
+  echo "  ERROR: could not find VMID for $NODE1 on $PVE_HOST"
+  echo "  qm list output:"
+  echo "$QM_LIST" | sed 's/^/    /'
+  exit 1
+fi
+if [[ -z "$VMID2" ]]; then
+  echo "  ERROR: could not find VMID for $NODE2 on $PVE_HOST"
+  echo "  qm list output:"
+  echo "$QM_LIST" | sed 's/^/    /'
+  exit 1
+fi
+
+echo "  $NODE1: VMID $VMID1"
+echo "  $NODE2: VMID $VMID2"
+
+# ── Confirm ────────────────────────────────────────────────────────────────
+if ! $FORCE && ! $DRY_RUN; then
+  echo ""
+  echo "  Plan:"
+  echo "    Phase 1 — qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}  (on $PVE_HOST)"
+  echo "              qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}  (on $PVE_HOST)"
+  echo "    Phase 2 — block device rescan on $NODE1 and $NODE2"
+  echo "    Phase 3 — drbdadm resize + xfs_growfs on $ACTIVE_NODE"
+  echo "  No downtime required (all operations are online-safe)."
+  printf "  Proceed? [y/N] "
+  read -r ANSWER
+  [[ "${ANSWER,,}" == "y" || "${ANSWER,,}" == "yes" ]] || { echo "Aborted."; exit 0; }
+fi
+
+# ═══════════════════════════════════════════════════════════════
+# Phase 1 — Resize both VM data disks in Proxmox
+# ═══════════════════════════════════════════════════════════════
+echo ""
+echo "── Phase 1 — Proxmox disk resize (${DATA_DISK_SLOT} ${SIZE} on both VMs) ──"
+
+echo "  ${DRY_PREFIX}qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}  ($NODE1 on ${PVE_HOST})"
+if ! $DRY_RUN; then
+  pve "$PVE_SUDO qm resize $VMID1 ${DATA_DISK_SLOT} ${SIZE}"
+fi
+
+echo "  ${DRY_PREFIX}qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}  ($NODE2 on ${PVE_HOST})"
+if ! $DRY_RUN; then
+  pve "$PVE_SUDO qm resize $VMID2 ${DATA_DISK_SLOT} ${SIZE}"
+fi
+
+echo "  Phase 1 done."
+
+# ═══════════════════════════════════════════════════════════════
+# Phase 2 — Rescan block device on both guest nodes
+# ═══════════════════════════════════════════════════════════════
+echo ""
+echo "── Phase 2 — Block device rescan (both nodes) ──"
+
+rescan_node() {
+  local node_name=$1 run_fn=$2
+
+  # Resolve block device name from the stable by-id symlink on the guest.
+  # Read-only lookup — safe to run even in dry-run so we show the real device.
+  local blk_dev=""
+  blk_dev=$($run_fn "bash -c 'basename \$(readlink -f /dev/disk/by-id/${DATA_DISK_BYID})'" 2>/dev/null || true)
+  if [[ -z "$blk_dev" ]]; then
+    echo "  ERROR: /dev/disk/by-id/${DATA_DISK_BYID} not found on $node_name" >&2
+    echo "         Check DATA_DISK_BYID or DATA_DISK_SLOT configuration." >&2
+    exit 1
+  fi
+
+  echo "  ${DRY_PREFIX}Rescanning /dev/${blk_dev} on ${node_name}..."
+  if ! $DRY_RUN; then
+    $run_fn "bash -c 'echo 1 > /sys/block/${blk_dev}/device/rescan'" 2>/dev/null
+    local new_size
+    new_size=$($run_fn "lsblk -nd -o SIZE /dev/${blk_dev} 2>/dev/null" 2>/dev/null || echo "unknown")
+    echo "    /dev/${blk_dev} on $node_name now reports: $new_size"
+  fi
+}
+
+rescan_node "$NODE1" n1
+rescan_node "$NODE2" n2
+
+echo "  Phase 2 done."
+
+# ═══════════════════════════════════════════════════════════════
+# Phase 3 — Grow DRBD metadata, then XFS (active node only)
+# ═══════════════════════════════════════════════════════════════
+echo ""
+echo "── Phase 3 — DRBD resize + XFS grow (on active node: $ACTIVE_NODE) ──"
+
+echo "  ${DRY_PREFIX}drbdadm resize ${DRBD_RESOURCE}"
+if ! $DRY_RUN; then
+  na "drbdadm resize ${DRBD_RESOURCE}"
+fi
+
+echo "  ${DRY_PREFIX}xfs_growfs ${XFS_MOUNT}"
+if ! $DRY_RUN; then
+  na "xfs_growfs ${XFS_MOUNT}"
+fi
+
+echo "  Phase 3 done."
+
+# ── Verify ────────────────────────────────────────────────────────────────
+echo ""
+echo "── Verify ──"
+
+if ! $DRY_RUN; then
+  DF_OUT=$(na "df -h '${XFS_MOUNT}' 2>/dev/null" 2>/dev/null || echo "")
+  if [[ -n "$DF_OUT" ]]; then
+    echo "  ${XFS_MOUNT}:"
+    echo "$DF_OUT" | sed 's/^/    /'
+  fi
+
+  DRBD_DSTATE_AFTER=$(na "drbdadm dstate ${DRBD_RESOURCE} 2>/dev/null" 2>/dev/null || echo "unknown")
+  echo "  DRBD dstate: $DRBD_DSTATE_AFTER"
+  if ! echo "$DRBD_DSTATE_AFTER" | grep -q "UpToDate/UpToDate"; then
+    echo "  NOTE: DRBD is resyncing — normal immediately after resize."
+    echo "        Monitor: ssh nixos@${ACTIVE_IP} 'sudo watch -n3 cat /proc/drbd'"
+  fi
+else
+  echo "  [dry-run] would verify df -h ${XFS_MOUNT} and drbdadm dstate on $ACTIVE_NODE"
+fi
+
+echo ""
+echo "════════════════════════════════════════════════════"
+echo " Resize complete."
+echo " Active node: $ACTIVE_NODE"
+echo "════════════════════════════════════════════════════"
+echo ""

scripts/ipa/create-nixos-ipa-host-account.sh

@@ -0,0 +1,303 @@
+#!/usr/bin/env bash
+# Add a NixOS host to the FreeIPA domain and produce a sops-encrypted keytab
+# at secrets/<hostname>.keytab, ready for modules/ipa/client.nix.
+#
+# One command replaces three error-prone manual steps:
+#   1. ipa host-add on the domain controller
+#   2. ipa-getkeytab on the domain controller + SCP back
+#   3. sops encrypt in-place (must be at secrets/<hostname>.keytab for
+#      the creation rule to match -- the common mistake that breaks sops)
+#
+# Usage:
+#   scripts/ipa/create-nixos-ipa-host-account.sh [options] <hostname>
+#
+# Arguments:
+#   <hostname>       Short hostname, e.g. "tailscale-router". The FQDN is
+#                    derived as <hostname>.<HOME_DOMAIN>.
+#
+# Options:
+#   --ip <addr>      Register this IP with the IPA host record (optional).
+#   --dc <host>      SSH to this host to run IPA commands.
+#                    Default: $IPA_SERVER (from env.sh / environment).
+#   --dc-user <u>    SSH user on the domain controller. Default: wayne.
+#   --dry-run        Print what would be done without making any changes.
+#   -h, --help       Show this message.
+#
+# Prereqs:
+#   1. Run from the repo root (so .sops.yaml and secrets/ are found).
+#   2. SSH access to the domain controller as --dc-user (default: wayne)
+#      with passwordless sudo (or sudo cached). IPA commands and kinit run
+#      as root via sudo so the Kerberos ticket is in root's cache where all
+#      ipa tools expect it. If there's no valid ticket, the script runs
+#      `sudo kinit admin` interactively — you'll be prompted for the IPA
+#      admin password once. The password never touches this script.
+#   3. The host's age key(s) must already be in .sops.yaml. Run
+#      scripts/secrets/sync-host-keys.sh <flake-target> first so the host
+#      can decrypt its own keytab on boot. This script adds the .sops.yaml
+#      creation rule for secrets/<hostname>.keytab automatically, but the
+#      host age key anchor (&lxc-<hostname> etc.) must already exist —
+#      otherwise only the admin key can decrypt the keytab and the deployed
+#      host will fail to read it.
+#   4. sops in PATH, or Nix available to run it via `nix run`.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+
+# shellcheck source=../env.sh
+source "${SCRIPT_DIR}/../env.sh"
+
+# --- Argument parsing ---
+
+DC_HOST="${IPA_SERVER}"
+DC_USER="wayne"
+IP_ADDR=""
+DRY_RUN=false
+TARGET=""
+
+usage() {
+  sed -n '/^# Usage:/,/^[^#]/{ /^#/{ s/^# \?//; p } }' "$0"
+  exit "${1:-0}"
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --ip)      IP_ADDR="$2";  shift 2 ;;
+    --dc)      DC_HOST="$2";  shift 2 ;;
+    --dc-user) DC_USER="$2";  shift 2 ;;
+    --dry-run) DRY_RUN=true;  shift ;;
+    -h|--help) usage 0 ;;
+    -*)  echo "Unknown flag: $1" >&2; usage 1 ;;
+    *)
+      if [[ -n "${TARGET}" ]]; then echo "Unexpected argument: $1" >&2; usage 1; fi
+      TARGET="$1"; shift
+      ;;
+  esac
+done
+
+if [[ -z "${TARGET}" ]]; then
+  echo "Error: hostname required." >&2
+  usage 1
+fi
+
+# Reject FQDNs passed by mistake — the script appends HOME_DOMAIN itself.
+# "nixos.sweet.home" → FQDN would become "nixos.sweet.home.sweet.home".
+if [[ "${TARGET}" == *"."* ]]; then
+  echo "Error: <hostname> must be the short name (e.g. 'nixos'), not a FQDN." >&2
+  echo "       The FQDN is derived automatically as ${TARGET}.${HOME_DOMAIN}." >&2
+  exit 1
+fi
+
+FQDN="${TARGET}.${HOME_DOMAIN}"
+KEYTAB_SECRET="${REPO_ROOT}/secrets/${TARGET}.keytab"
+# Temp path on the domain controller — use a name that won't collide.
+DC_TMP="/tmp/nixos-keytab-${TARGET}-$$.keytab"
+
+# --- Helpers ---
+
+log()  { echo "==> $*"; }
+logn() { echo "    $*"; }
+
+run() {
+  if $DRY_RUN; then
+    echo "[dry-run] $*"
+  else
+    "$@"
+  fi
+}
+
+dc_run() {
+  # Run a command string on the domain controller via SSH.
+  if $DRY_RUN; then
+    echo "[dry-run] ssh ${DC_USER}@${DC_HOST} $*"
+  else
+    ssh "${DC_USER}@${DC_HOST}" "$@"
+  fi
+}
+
+# --- Locate sops ---
+
+if command -v sops &>/dev/null; then
+  SOPS_CMD=(sops)
+else
+  log "sops not in PATH — will use 'nix run nixpkgs#sops'"
+  SOPS_CMD=(nix run "nixpkgs#sops" --)
+fi
+
+# --- Preflight checks ---
+
+cd "${REPO_ROOT}"
+
+[[ -f .sops.yaml ]] || { echo "Error: .sops.yaml not found — run from repo root." >&2; exit 1; }
+[[ -d secrets  ]]   || { echo "Error: secrets/ not found — run from repo root."   >&2; exit 1; }
+
+# --- Step 1: Ensure .sops.yaml has a creation rule for this keytab ---
+#
+# sops matches creation rules against the PATH of the file being encrypted,
+# not the output path. To match secrets/<hostname>.keytab, the file must
+# already be at that path when sops -e -i is called. The creation rule must
+# also exist at that point or sops will refuse with "no matching creation
+# rules found."
+
+log "Checking .sops.yaml for creation rule: secrets/${TARGET}.keytab"
+
+RULE_EXISTS=false
+# Match "path_regex: secrets/<hostname>...keytab" — using .*keytab rather
+# than \.keytab because the file stores the regex verbatim (\.keytab = two
+# chars: backslash + dot), which a BRE \.  (= escaped literal dot) won't span.
+if grep -q "path_regex: secrets/${TARGET}.*keytab" .sops.yaml 2>/dev/null; then
+  RULE_EXISTS=true
+  logn "Rule already exists — skipping addition."
+fi
+
+if ! $RULE_EXISTS; then
+  # Collect which platform-variant age anchors exist in .sops.yaml for this
+  # hostname. The keytab is platform-agnostic (same FQDN regardless of
+  # whether lxc/proxmox/linode variant is deployed), so all platform anchors
+  # that have been registered get added as recipients.
+  RECIPIENTS=("*admin")
+  for platform in lxc proxmox linode; do
+    anchor="${platform}-${TARGET}"
+    if grep -q "^  - &${anchor} " .sops.yaml; then
+      RECIPIENTS+=("*${anchor}")
+    fi
+  done
+
+  if [[ ${#RECIPIENTS[@]} -eq 1 ]]; then
+    echo "Warning: no platform age keys found for '${TARGET}' in .sops.yaml." >&2
+    echo "         Run scripts/secrets/sync-host-keys.sh <flake-target> first," >&2
+    echo "         otherwise only the admin key can decrypt the keytab and the" >&2
+    echo "         deployed host won't be able to read it at boot." >&2
+    echo "         Continuing with admin-only encryption..." >&2
+  fi
+
+  # Build the indented recipient list for the YAML block.
+  RECIPIENT_YAML=""
+  for r in "${RECIPIENTS[@]}"; do
+    RECIPIENT_YAML+="          - ${r}"$'\n'
+  done
+  RECIPIENT_YAML="${RECIPIENT_YAML%$'\n'}"  # strip trailing newline
+
+  NEW_RULE="
+  # Host keytab for ${TARGET} FreeIPA enrollment (binary sops file).
+  # Generated by scripts/ipa/create-nixos-ipa-host-account.sh.
+  - path_regex: secrets/${TARGET}\\.keytab\$
+    key_groups:
+      - age:
+${RECIPIENT_YAML}"
+
+  if $DRY_RUN; then
+    echo "[dry-run] Would append to .sops.yaml:"
+    echo "${NEW_RULE}"
+  else
+    logn "Adding creation rule (recipients: ${RECIPIENTS[*]})"
+    printf '%s\n' "${NEW_RULE}" >> .sops.yaml
+    logn "Added."
+  fi
+fi
+
+# --- Step 2: Add IPA host account (idempotent) ---
+
+log "Adding FreeIPA host account: ${FQDN}"
+
+# Ensure there's a valid admin Kerberos ticket on the DC.
+# ipa host-add and ipa-getkeytab both need one. All IPA commands run via
+# sudo so the ticket must be in root's cache — check and refresh as root.
+# ssh -t allocates a PTY so kinit (and sudo if needed) can prompt normally;
+# no password ever touches this script or the shell history.
+if ! $DRY_RUN; then
+  if ! ssh "${DC_USER}@${DC_HOST}" "sudo klist -s" &>/dev/null; then
+    log "No valid Kerberos ticket on ${DC_HOST} — running sudo kinit admin"
+    ssh -t "${DC_USER}@${DC_HOST}" "sudo kinit admin"
+    if ! ssh "${DC_USER}@${DC_HOST}" "sudo klist -s" &>/dev/null; then
+      echo "Error: kinit admin failed or produced no valid ticket." >&2
+      exit 1
+    fi
+  else
+    logn "Kerberos ticket on ${DC_HOST} is valid."
+  fi
+fi
+
+IP_FLAG=""
+[[ -n "${IP_ADDR}" ]] && IP_FLAG="--ip-address=${IP_ADDR}"
+
+# --force: create the host record even if DNS doesn't resolve it yet.
+if $DRY_RUN; then
+  echo "[dry-run] ssh ${DC_USER}@${DC_HOST} sudo ipa host-add '${FQDN}' ${IP_FLAG} --force"
+else
+  HOST_ADD_OUT=$(ssh "${DC_USER}@${DC_HOST}" "sudo ipa host-add '${FQDN}' ${IP_FLAG} --force 2>&1") \
+    && HOST_ADD_RC=0 || HOST_ADD_RC=$?
+  if [[ $HOST_ADD_RC -eq 0 ]]; then
+    echo "${HOST_ADD_OUT}"
+  elif echo "${HOST_ADD_OUT}" | grep -q "already exists"; then
+    logn "(host already registered)"
+  else
+    echo "Error: ipa host-add failed (exit ${HOST_ADD_RC}):" >&2
+    echo "${HOST_ADD_OUT}" >&2
+    exit 1
+  fi
+fi
+
+# --- Step 3: Fetch the keytab from the domain controller ---
+
+log "Fetching keytab for host/${FQDN}"
+
+# Remove the plaintext keytab if the script aborts before encryption completes.
+# The trap is cleared at the end of step 4 once sops has encrypted it in-place.
+trap 'rm -f "${KEYTAB_SECRET}"' EXIT
+
+dc_run "sudo ipa-getkeytab -s '${IPA_SERVER}' -p 'host/${FQDN}' -k '${DC_TMP}'"
+
+if $DRY_RUN; then
+  echo "[dry-run] Would stream ${DC_USER}@${DC_HOST}:${DC_TMP} → secrets/${TARGET}.keytab"
+else
+  logn "Streaming keytab from ${DC_HOST}:${DC_TMP} → secrets/${TARGET}.keytab"
+  # scp can't read a root-owned temp file as ${DC_USER}; pipe through sudo cat instead.
+  ssh "${DC_USER}@${DC_HOST}" "sudo cat '${DC_TMP}'" > "${KEYTAB_SECRET}"
+
+  logn "Removing temp file on ${DC_HOST}"
+  dc_run "sudo rm -f '${DC_TMP}'"
+fi
+
+# --- Step 4: Encrypt in-place ---
+#
+# The file must already be at secrets/<hostname>.keytab (done above) so
+# sops matches the creation rule by path. Using -i (in-place) rather than
+# stdout redirect keeps the path intact through the encrypt call.
+
+log "Encrypting secrets/${TARGET}.keytab in-place with sops"
+run "${SOPS_CMD[@]}" -e --input-type binary -i "${KEYTAB_SECRET}"
+
+# Encryption succeeded — the file is now sops-encrypted; cancel the cleanup trap.
+trap - EXIT
+
+# --- Done ---
+
+if ! $DRY_RUN; then
+  echo ""
+  echo "Done. secrets/${TARGET}.keytab is sops-encrypted and ready."
+  echo ""
+  echo "Next steps:"
+  echo "  1. Verify: grep '\"data\": \"ENC' secrets/${TARGET}.keytab"
+  echo "  2. Stage and commit:"
+  echo "       git add secrets/${TARGET}.keytab .sops.yaml"
+  echo "       git commit -m 'secrets: add IPA keytab for ${TARGET}'"
+  echo "  3. Add to hosts/${TARGET}/host.nix (networking block and imports):"
+  echo ""
+  echo "       networking = {"
+  echo "         hostName = \"${TARGET}\";"
+  echo "         domain   = vars.homeDomain;          # required for Kerberos FQDN"
+  echo "         nameservers = [ vars.domainControllerIp ];  # IPA DNS"
+  echo "         ..."
+  echo "       };"
+  echo ""
+  echo "       imports = ["
+  echo "         (import ../../modules/ipa/client.nix {"
+  echo "           keytabSopsFile = ../../secrets/${TARGET}.keytab;"
+  echo "           caCertFile     = ../../certs/ipa-ca.crt;"
+  echo "         })"
+  echo "       ];"
+  echo ""
+  echo "  4. Deploy: nixos-rebuild switch (or create-proxmox-resource.sh)"
+fi

scripts/lib/clan-vars.sh

@@ -0,0 +1,106 @@
+#!/usr/bin/env bash
+# Clan vars helpers: manage SSH host keys stored as clan vars (sops-encrypted
+# binary files under vars/per-machine/<target>/openssh/) instead of the
+# gitignored host-keys/ directory.
+#
+# Layout (per clan's convention):
+#   vars/per-machine/<target>/openssh/ssh_host_ed25519_key/secret  -- sops binary (admin-encrypted)
+#   vars/per-machine/<target>/openssh/ssh_host_ed25519_key.pub/value  -- plaintext SSH pubkey
+#
+# Sourced by create-proxmox-resource.sh and sync-host-keys.sh.
+# Depends on sops-age.sh and ssh-host-keys.sh being sourced first (for
+# sops_yaml_admin_pubkey, ssh_pubkey_to_age, and NIX_OPTS).
+
+if ! declare -p NIX_OPTS >/dev/null 2>&1; then
+  declare -a NIX_OPTS=()
+fi
+
+# clan_ssh_key_exists <target> <repo_root>
+# Returns 0 if clan vars hold a SSH host key for <target>, 1 otherwise.
+clan_ssh_key_exists() {
+  local target="$1" repo_root="$2"
+  [[ -f "${repo_root}/vars/per-machine/${target}/openssh/ssh_host_ed25519_key/secret" ]]
+}
+
+# clan_ssh_pubkey_path <target> <repo_root>
+# Prints the path to the plaintext SSH public key value file.
+clan_ssh_pubkey_path() {
+  local target="$1" repo_root="$2"
+  echo "${repo_root}/vars/per-machine/${target}/openssh/ssh_host_ed25519_key.pub/value"
+}
+
+# clan_decrypt_ssh_key <target> <repo_root> <dest_dir>
+# Decrypts the sops-encrypted SSH host private key for <target> into <dest_dir>,
+# naming it <target>_ssh_host_ed25519_key (to match NIXOS_HOST_KEYS_DIR
+# conventions that lxc.nix and the disko build already expect). Also copies
+# the plaintext public key. The caller is responsible for protecting and
+# cleaning up <dest_dir>.
+clan_decrypt_ssh_key() {
+  local target="$1" repo_root="$2" dest_dir="$3"
+  local secret="${repo_root}/vars/per-machine/${target}/openssh/ssh_host_ed25519_key/secret"
+  local pubval="${repo_root}/vars/per-machine/${target}/openssh/ssh_host_ed25519_key.pub/value"
+  local dest_priv="${dest_dir}/${target}_ssh_host_ed25519_key"
+  local dest_pub="${dest_dir}/${target}_ssh_host_ed25519_key.pub"
+
+  nix-shell "${NIX_OPTS[@]}" -p sops --run \
+    "sops -d --output-type binary '${secret}'" > "$dest_priv"
+  chmod 0600 "$dest_priv"
+  cp "$pubval" "$dest_pub"
+}
+
+# clan_generate_ssh_key <target> <repo_root>
+# Generates a new SSH host key pair and stores it in clan vars format:
+#   - private key: sops binary-encrypted for the admin age key
+#   - public key: plaintext value file
+# Idempotent: if the secret already exists, prints a note and returns 0.
+# Requires sops_yaml_admin_pubkey (from sops-age.sh) to be available.
+clan_generate_ssh_key() {
+  local target="$1" repo_root="$2"
+  local var_base="${repo_root}/vars/per-machine/${target}/openssh"
+  local secret_dir="${var_base}/ssh_host_ed25519_key"
+  local pubval_dir="${var_base}/ssh_host_ed25519_key.pub"
+
+  if [[ -f "${secret_dir}/secret" ]]; then
+    echo "Clan SSH host key for ${target} already exists -- skipping generation."
+    return 0
+  fi
+
+  # Resolve admin age public key from .sops.yaml
+  local admin_pubkey
+  admin_pubkey="$(sops_yaml_admin_pubkey "${repo_root}/.sops.yaml")"
+  if [[ -z "$admin_pubkey" ]]; then
+    echo "ERROR: Could not find &admin age key in ${repo_root}/.sops.yaml" >&2
+    return 1
+  fi
+
+  # Generate the SSH key pair in a secure temp directory
+  local tmpdir
+  tmpdir="$(mktemp -d)"
+  local priv_tmp="${tmpdir}/ssh_host_ed25519_key"
+
+  # shellcheck disable=SC2064
+  trap "rm -rf '${tmpdir}'" RETURN
+
+  nix-shell "${NIX_OPTS[@]}" -p openssh --run \
+    "ssh-keygen -t ed25519 -N '' -C '${target}' -f '${priv_tmp}'" >/dev/null
+
+  # Create a minimal sops config that uses only the admin age key -- this
+  # prevents sops from merging in ALL recipients from .sops.yaml (which
+  # would unnecessarily encrypt for every host's key, not just admin).
+  local sops_cfg="${tmpdir}/sops-config.json"
+  printf '{"creation_rules":[{"key_groups":[{"age":["%s"]}]}]}\n' \
+    "$admin_pubkey" > "$sops_cfg"
+
+  # Encrypt the private key in sops binary format (admin-only recipient)
+  mkdir -p "$secret_dir" "$pubval_dir"
+  nix-shell "${NIX_OPTS[@]}" -p sops --run \
+    "sops -e --config '${sops_cfg}' --input-type binary '${priv_tmp}'" \
+    > "${secret_dir}/secret"
+
+  # Store the public key as a plaintext value file
+  cp "${priv_tmp}.pub" "${pubval_dir}/value"
+
+  echo "Generated and stored clan SSH host key for ${target}."
+  echo "  Private key: ${secret_dir}/secret (sops binary, admin-key encrypted)"
+  echo "  Public key:  ${pubval_dir}/value"
+}

scripts/proxmox/configure-nix-cache-client.sh

@@ -38,7 +38,7 @@
 set -euo pipefail
 
 : "${NIX_CACHE_HOST:=nix-cache}"
-: "${NIX_CACHE_HOST_KEY:=ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPeWgMsdaiz4axT/deFc1+0B5bN+GX/NOeW9bbQ0c/IT lxc-nix-cache}"
+: "${NIX_CACHE_HOST_KEY:=ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICuHUxGNH6ei3BZD+EfZs3l4X8uJNcjQiOsM/G4yo4O/ lxc-nix-cache}"
 : "${REMOTE_BUILDER_USER:=nixremote}"
 
 CACHE_PUB_KEY="cache.local-1:usoWYanY3Kpq2+kDIS2nhWoLZiRxanmdysdzqCFBHW4="

scripts/proxmox/create-proxmox-resource.sh

@@ -8,9 +8,12 @@
 # script -- there's no multi-gigabyte image to transfer afterward. The first
 # time a node doesn't have that repo path yet, it's bootstrapped: cloned from
 # this checkout's own `origin` remote, then scripts/codex-setup.sh installs
-# the build tooling (Nix, etc.). Every run after that just `git pull`s it and
-# copies over the locally-managed host-keys/ (gitignored, so a git pull
-# alone wouldn't carry it) before building.
+# the build tooling (Nix, etc.). Every run after that just `git pull`s it.
+# SSH host keys are stored as clan vars (vars/per-machine/<target>/openssh/,
+# committed and sops-encrypted) -- the script decrypts them locally and
+# copies only the two files for this target to the node's host-keys/ before
+# building. A target with no clan var is an error (generate one first with
+# scripts/secrets/sync-host-keys.sh <target>).
 #
 # --node (default: $PROXMOX_HOST, see scripts/env.sh) picks which of the two
 # LAN Proxmox nodes this runs against: production, pve1.sweet.home
@@ -59,6 +62,10 @@ source "${repo_root}/scripts/env.sh"
 source "${repo_root}/scripts/lib/nix-eval.sh"
 # shellcheck source=../lib/confirm.sh
 source "${repo_root}/scripts/lib/confirm.sh"
+# shellcheck source=../lib/sops-age.sh
+source "${repo_root}/scripts/lib/sops-age.sh"
+# shellcheck source=../lib/clan-vars.sh
+source "${repo_root}/scripts/lib/clan-vars.sh"
 
 sync_keys="${repo_root}/scripts/secrets/sync-host-keys.sh"
 
@@ -295,6 +302,12 @@ platform_prefix="lxc"
 [[ -z "$cores" ]] && cores="$PROXMOX_DEFAULT_CORES"
 [[ -z "$memory" ]] && memory="$PROXMOX_DEFAULT_MEMORY_MB"
 
+if [[ "$type" == "vm" && -n "$disk_size" ]]; then
+  echo "WARNING: --disk-size is LXC-only for create mode and is ignored for VMs." >&2
+  echo "  VM disk size comes from proxmoxImageSize in variables.nix (currently ${disk_size}G was requested)." >&2
+  echo "  To expand after creation, use: --modify --vmid <n> --grow-disk <GB>" >&2
+fi
+
 # --- discover / resolve the flake target from --host --------------------
 # Emits "<target>\t<hostName>" pairs for every ${platform_prefix}-* flake
 # target -- the one source both --list and the --host lookup below read
@@ -347,6 +360,14 @@ fi
 # feeds straight into the guest's real hostname) disagree with host.nix.
 [[ -z "$name" ]] && name="$host"
 
+# For VM builds: the diskoImagesScript (run via QEMU on the node) writes the
+# raw disk image as <hostname>.raw into the CWD it was called from (the remote
+# repo dir), not to /var/lib/vz/import/ or anywhere else.  Import directly from
+# there -- no intermediate mv that can fail crossing filesystem boundaries or
+# leave a stale file on error.
+vm_built_raw=""
+[[ "$type" == "vm" ]] && vm_built_raw="${remote_repo_dir}/${host}.raw"
+
 # --- refuse to duplicate a host that's already live on the node ---------
 # Queries the node itself (qm/pct's own name/hostname config), not any
 # static list in this repo -- a file can't track whether a resource still
@@ -485,12 +506,37 @@ echo "Target: ${flake_target} (host=${host}, type=${type}) -> Proxmox resource '
 nix_extra_opts
 
 # --- make sure this target has a registered host key --------------------
+# sync-host-keys.sh is idempotent and generates the key (via clan vars) if
+# no key exists yet -- the old inline prepare-host-key.sh call is gone.
 echo
 echo "==> Ensuring host key exists and is registered..."
 sync_args=("$flake_target")
 [[ "$dry_run" -eq 1 ]] && sync_args+=(--dry-run)
 bash "$sync_keys" "${sync_args[@]}"
 
+# If sync-host-keys.sh changed .sops.yaml, secrets/, or vars/per-machine/,
+# those changes must be committed and pushed before the remote `git pull`
+# below picks them up -- the PVE node builds from whatever HEAD is checked
+# out there, not the local working tree. Uncommitted clan vars or sops
+# recipients mean the image builds fine but the host cannot decrypt its
+# secrets on first boot. Block until the operator confirms they've pushed.
+if [[ "$dry_run" -eq 0 ]]; then
+  _dirty="$(git -C "$repo_root" status --porcelain -- .sops.yaml secrets/ vars/per-machine/ 2>/dev/null || true)"
+  if [[ -n "$_dirty" ]]; then
+    echo
+    echo "==> COMMIT + PUSH REQUIRED before the remote build can succeed:"
+    echo "    Uncommitted changes in .sops.yaml, secrets/, or vars/per-machine/."
+    echo "    The PVE node builds from the git-tracked flake, so these changes"
+    echo "    must be committed and pushed first -- otherwise the image build will"
+    echo "    succeed but the host cannot decrypt its secrets on first boot."
+    echo
+    git -C "$repo_root" status --short -- .sops.yaml secrets/ vars/per-machine/ || true
+    echo
+    read -rp "    Commit and push those changes, then press Enter to continue (Ctrl-C to abort): "
+  fi
+  unset _dirty
+fi
+
 # --- VMID: pick one, and refuse to touch anything that already exists ---
 echo
 if [[ -z "$vmid" ]]; then
@@ -613,21 +659,35 @@ ensure_remote_repo() {
   fi
 }
 
-# --- sync locally-managed host-keys/ to the node ---------------------------
-# Gitignored (see .gitignore), so `git pull` above never carries it -- both
-# build paths need it present as NIXOS_HOST_KEYS_DIR / --pre-format-files
-# input on the node itself now that the build runs there. scp (not rsync,
-# not already a dependency anywhere else in this repo) mirrors how this
-# script already transfers the --image case below.
+# --- sync host key to the node ---------------------------------------------
+# SSH host keys are stored as clan vars (vars/per-machine/<target>/openssh/).
+# Decrypt locally and scp just the two files for this target to the node's
+# host-keys/ directory, where the remote build script picks them up via
+# NIXOS_HOST_KEYS_DIR (LXC) or --pre-format-files (VM). A target with no
+# clan var is an error -- generate one first with sync-host-keys.sh.
 sync_remote_host_keys() {
   echo
-  echo "==> Syncing host-keys/ to ${node}..."
+  echo "==> Syncing host key for ${flake_target} to ${node}..."
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would copy ${repo_root}/host-keys/ to ${ssh_target}:${remote_repo_dir}/host-keys/"
+    echo "[dry-run] would decrypt clan SSH key for ${flake_target} and copy to ${ssh_target}:${remote_repo_dir}/host-keys/"
     return
   fi
+  if ! clan_ssh_key_exists "$flake_target" "$repo_root"; then
+    echo "ERROR: no clan SSH key found for ${flake_target}" >&2
+    echo "  (expected: ${repo_root}/vars/per-machine/${flake_target}/openssh/ssh_host_ed25519_key/secret)" >&2
+    echo "  Generate one first: bash scripts/secrets/sync-host-keys.sh ${flake_target}" >&2
+    exit 1
+  fi
+  local tmpdir
+  tmpdir="$(mktemp -d)"
+  # shellcheck disable=SC2064
+  trap "rm -rf '${tmpdir}'" RETURN
+  echo "  Decrypting clan SSH key for ${flake_target}..."
+  clan_decrypt_ssh_key "$flake_target" "$repo_root" "$tmpdir"
   ssh "$ssh_target" "mkdir -p '${remote_repo_dir}/host-keys'"
-  scp -pr "${repo_root}/host-keys/." "${ssh_target}:${remote_repo_dir}/host-keys/"
+  scp -p "${tmpdir}/${flake_target}_ssh_host_ed25519_key" \
+         "${tmpdir}/${flake_target}_ssh_host_ed25519_key.pub" \
+         "${ssh_target}:${remote_repo_dir}/host-keys/"
 }
 
 # --- build (or reuse an image already on the node) ------------------------
@@ -642,10 +702,14 @@ if [[ -n "$image" ]]; then
 elif [[ "$force_rebuild" -eq 1 ]]; then
   echo "--force-rebuild: skipping the existing-image check on ${node}."
 else
-  echo "==> Checking whether ${node} already has ${remote_path}..."
+  # VMs: check for the raw image in the remote repo dir (where disko writes it).
+  # LXC: check for the tarball in iso_storage (where the LXC build stages it).
+  _check_path="$remote_path"
+  [[ "$type" == "vm" ]] && _check_path="$vm_built_raw"
+  echo "==> Checking whether ${node} already has ${_check_path}..."
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would check: ssh ${ssh_target} -- test -f ${remote_path}"
-  elif ssh "$ssh_target" "test -f '${remote_path}'" 2>/dev/null; then
+    echo "[dry-run] would check: ssh ${ssh_target} -- test -f ${_check_path}"
+  elif ssh "$ssh_target" "test -f '${_check_path}'" 2>/dev/null; then
     echo "Found it -- reusing, skipping build (use --force-rebuild to override)."
     image_already_remote=1
   else
@@ -696,6 +760,12 @@ cd "$repo_dir"
 # right after a successful install.
 . scripts/lib/nix-bootstrap.sh
 ensure_nix_profile
+if [[ ! -f "host-keys/${target}_ssh_host_ed25519_key" ]]; then
+  echo "ERROR: host-keys/${target}_ssh_host_ed25519_key not found in ${repo_dir}." >&2
+  echo "Generate the key locally (scripts/secrets/sync-host-keys.sh ${target})" >&2
+  echo "and ensure it was synced here before starting the build." >&2
+  exit 1
+fi
 NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
   --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
   ".#nixosConfigurations.${target}.config.system.build.tarball" \
@@ -714,46 +784,60 @@ REMOTE_SCRIPT
     fi
   else
     if [[ "$dry_run" -eq 1 ]]; then
-      echo "[dry-run] would build on ${node}: nix build --no-use-registries --no-accept-flake-config${nix_opts_display} \\"
+      echo "[dry-run] would build on ${node}: NIXOS_HOST_KEYS_DIR=\$(pwd)/host-keys nix build --impure --no-use-registries --no-accept-flake-config${nix_opts_display} \\"
       echo "[dry-run]   .#nixosConfigurations.${flake_target}.config.system.build.diskoImagesScript"
-      echo "[dry-run] would run:   ${sudo_display}./result-${flake_target} \\"
-      echo "[dry-run]                --pre-format-files host-keys/${flake_target}_ssh_host_ed25519_key /etc/ssh/ssh_host_ed25519_key \\"
-      echo "[dry-run]                --pre-format-files host-keys/${flake_target}_ssh_host_ed25519_key.pub /etc/ssh/ssh_host_ed25519_key.pub \\"
-      echo "[dry-run]                --build-memory 2048"
-      echo "[dry-run] would stage the result at ${remote_path}"
+      echo "[dry-run] would run:   ${sudo_display}./result-${flake_target} --build-memory 2048"
+      echo "[dry-run] image will be at ${vm_built_raw} (imported from there; no mv to /var/lib/vz/import/)"
       local_image="<built-image>.raw"
     else
       echo "==> Building Disko image for ${flake_target} on ${node}..."
       # See the LXC branch above for why this is one %q-quoted command
       # string rather than separate ssh argv elements.
-      printf -v remote_cmd 'bash -s -- %q %q %q %q %q %q' \
-        "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS" "$sudo_prefix"
+      # $7 = image_name (hostname, the diskoImagesScript's own output filename).
+      #
+      # NIXOS_HOST_KEYS_DIR + --impure: modules/platforms/proxmox.nix reads
+      # this env var at eval time (like lxc.nix) to embed the clan SSH host
+      # key in environment.etc. nixos-install's own activation then places the
+      # key on the target disk, so sshd-keygen finds it already present and
+      # skips generation. --pre-format-files put the key on the QEMU builder
+      # VM's rootfs (not the target disk), so sshd-keygen regenerated a fresh
+      # key -- one not registered in .sops.yaml -- and sops could never decrypt.
+      printf -v remote_cmd 'bash -s -- %q %q %q %q %q %q %q' \
+        "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS" "$sudo_prefix" "$host"
       ssh "$ssh_target" "$remote_cmd" <<'REMOTE_SCRIPT'
 set -euo pipefail
-repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"; sudo_pfx="$6"
+repo_dir="$1"; target="$2"; dest_dir="$3"; dest_name="$4"; nix_extra_opts_str="$5"; sudo_pfx="$6"; image_name="$7"
 declare -a NIX_OPTS=()
 [[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
 cd "$repo_dir"
 . scripts/lib/nix-bootstrap.sh
 ensure_nix_profile
-nix build --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
-  ".#nixosConfigurations.${target}.config.system.build.diskoImagesScript" \
-  --out-link "result-${target}"
-$sudo_pfx "./result-${target}" \
-  --pre-format-files "host-keys/${target}_ssh_host_ed25519_key" /etc/ssh/ssh_host_ed25519_key \
-  --pre-format-files "host-keys/${target}_ssh_host_ed25519_key.pub" /etc/ssh/ssh_host_ed25519_key.pub \
-  --build-memory 2048
-built="$(find . -maxdepth 1 -name '*.raw' -newer "result-${target}" | head -1)"
-if [[ -z "$built" ]]; then
-  echo "ERROR: no .raw image found in ${repo_dir} after build." >&2
+if [[ ! -f "host-keys/${target}_ssh_host_ed25519_key" ]]; then
+  echo "ERROR: host-keys/${target}_ssh_host_ed25519_key not found in ${repo_dir}." >&2
+  echo "Generate the key locally (scripts/secrets/sync-host-keys.sh ${target})" >&2
+  echo "and ensure it was synced here before starting the build." >&2
   exit 1
 fi
-$sudo_pfx mkdir -p "$dest_dir"
-$sudo_pfx mv "$built" "${dest_dir}/${dest_name}"
-echo "Built and staged: ${dest_dir}/${dest_name}"
+# Build diskoImagesScript with NIXOS_HOST_KEYS_DIR so proxmox.nix embeds the
+# clan SSH key in environment.etc (same as lxc.nix). This causes nixos-install
+# to place the key on the target disk, so sshd-keygen finds it and skips
+# generation -- the disk image boots with the registered key, sops decrypts.
+NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
+  --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
+  ".#nixosConfigurations.${target}.config.system.build.diskoImagesScript" \
+  --out-link "result-${target}"
+# Remove any stale .raw from a previous failed build so the post-build check
+# below is unambiguous (diskoImagesScript writes to CWD as ${image_name}.raw).
+$sudo_pfx rm -f "${image_name}.raw" 2>/dev/null || true
+$sudo_pfx "./result-${target}" --build-memory 2048
+if [[ ! -f "${image_name}.raw" ]]; then
+  echo "ERROR: ${image_name}.raw not found in ${repo_dir} after build -- disko/QEMU may have failed." >&2
+  exit 1
+fi
+echo "Built image: ${repo_dir}/${image_name}.raw"
 REMOTE_SCRIPT
-      local_image="$remote_path"
-      echo "Built on ${node}: ${remote_path}"
+      local_image="$vm_built_raw"
+      echo "Built on ${node}: ${vm_built_raw}"
     fi
   fi
 fi
@@ -783,17 +867,17 @@ if [[ "$type" == "lxc" ]]; then
   local_swap="${swap:-$memory}"
   # --unprivileged: read back from modules/platforms/lxc.nix's own
   # proxmoxLXC.privileged (via flake_target_lxc_privileged) rather than
-  # hardcoded, since that's no longer the same for every lxc-* target --
-  # lxc-docker sets it true so the container's NFS mounts work at all (the
-  # kernel's NFS client can't mount from inside any unprivileged
-  # container's user namespace, no matter what AppArmor allows -- see that
-  # option's own comment). The NixOS config inside the image bakes in
-  # cgroup/capability/mount expectations matching whichever value it was
-  # built with, so this must stay in sync with it -- `pct create`'s own
-  # CLI default for this flag is privileged (unlike the web UI, which
-  # defaults its checkbox the other way), so leaving it unset would create
-  # a privileged container running a NixOS config that assumes
-  # unprivileged for every target except lxc-docker, a real mismatch.
+  # hardcoded. lxc.nix derives this automatically: any lxc-* host whose
+  # config.fileSystems has an NFS entry gets privileged=true, because the
+  # kernel's NFS client (FS_USERNS_MOUNT not set) rejects NFS mounts from
+  # inside any non-init user namespace -- exactly what an unprivileged
+  # container's UID-mapped root lives in -- with EPERM at the VFS layer,
+  # regardless of AppArmor (see lxc.nix's own comment). The NixOS config
+  # bakes in cgroup/capability/mount expectations matching whichever value
+  # it was built with, so this must stay in sync -- `pct create`'s CLI
+  # default is privileged (unlike the web UI, which defaults the other
+  # way), so leaving it unset would create a privileged container running
+  # a NixOS config that assumes unprivileged, a real mismatch.
   privileged_eval="$(flake_target_lxc_privileged "$repo_root" "$flake_target")"
   unprivileged_flag=1
   [[ "$privileged_eval" == "true" ]] && unprivileged_flag=0
@@ -831,14 +915,35 @@ else
 --net0 virtio,bridge=${bridge} --bios ovmf --machine q35 --scsihw virtio-scsi-pci \
 --efidisk0 ${storage}:1,efitype=4m,pre-enrolled-keys=0 --agent enabled=1"
 
+  # VMs built on the node: import from the repo dir (where disko/QEMU wrote it).
+  # VMs from --image: import from remote_path (where scp uploaded it).
+  _import_path="${remote_path}"
+  [[ -z "$image" ]] && _import_path="${vm_built_raw}"
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] ssh ${ssh_target} -- ${sudo_display}qm importdisk ${vmid} ${remote_path} ${storage}"
+    echo "[dry-run] ssh ${ssh_target} -- ${sudo_display}qm importdisk ${vmid} ${_import_path} ${storage}"
     echo "[dry-run] (would parse the resulting disk identifier from that output)"
     echo "[dry-run] ssh ${ssh_target} -- ${sudo_display}qm set ${vmid} --scsi0 ${storage}:<parsed-disk-id>"
   else
-    importdisk_output="$(ssh "$ssh_target" "${sudo_prefix} qm importdisk ${vmid} ${remote_path} ${storage}")"
+    if ! importdisk_output="$(ssh "$ssh_target" "${sudo_prefix} qm importdisk ${vmid} ${_import_path} ${storage}" 2>&1)"; then
+      echo "ERROR: qm importdisk failed:" >&2
+      echo "${importdisk_output}" >&2
+      exit 1
+    fi
     echo "$importdisk_output"
-    disk_id="$(echo "$importdisk_output" | grep -oP "(?<=Successfully imported disk as ')[^']+" | sed 's/^unused[0-9]*://')"
+    # PVE output format: "unusedN: successfully imported disk '<storage>:<vol>'"
+    # (lowercase "successfully", no "as"; the primary regex targets this form; the
+    # || true inside the substitution prevents set -e from aborting when grep finds
+    # no match -- without it the script would silently exit before reaching the
+    # fallback whenever the PVE format doesn't match).
+    disk_id="$(echo "$importdisk_output" | grep -oP "successfully imported disk '\\K[^']+" || true)"
+    if [[ -z "$disk_id" ]]; then
+      # Fallback for other PVE output variants: read qm config directly.
+      unused_line="$(ssh "$ssh_target" "${sudo_prefix} qm config ${vmid}" | grep '^unused[0-9]*:' | head -1 || true)"
+      if [[ -n "$unused_line" ]]; then
+        disk_id="${unused_line#*: }"
+        echo "Note: disk ID resolved from qm config: ${disk_id}"
+      fi
+    fi
     if [[ -z "$disk_id" ]]; then
       echo "ERROR: couldn't parse the imported disk identifier from qm importdisk's output above." >&2
       echo "The VM shell (${vmid}) and imported disk both exist -- finish attaching it by hand:" >&2
@@ -847,6 +952,12 @@ else
       exit 1
     fi
     remote "${sudo_prefix} qm set ${vmid} --scsi0 ${disk_id}"
+    # The disk data is now in ZFS; remove the source raw file (only for images
+    # we built on the node -- --image uploads are the operator's to manage).
+    if [[ -z "$image" ]]; then
+      ssh "$ssh_target" "${sudo_prefix} rm -f '${_import_path}'" 2>/dev/null || \
+        echo "Warning: couldn't remove ${_import_path} from ${node} -- you can delete it manually" >&2
+    fi
   fi
   remote "${sudo_prefix} qm set ${vmid} --boot order=scsi0"
   remote "${sudo_prefix} qm start ${vmid}"

scripts/recover-hosts.sh

@@ -0,0 +1,253 @@
+#!/usr/bin/env bash
+# recover-hosts.sh — Fix sops/SSH-key/GitHub-token issues on deployed NixOS hosts
+# and trigger a Switch-nix rebuild on each.
+#
+# Run from the repo root on the workstation (nixos@nixos):
+#   bash scripts/recover-hosts.sh [<hostname> ...]
+#
+# With no args it discovers and checks every known hostname.
+# With args it checks only those hostnames:
+#   bash scripts/recover-hosts.sh tor-relay
+#
+# Fixes applied automatically (then prompts before rebuilding):
+#   1. SSH host key drift — live key no longer matches host-keys/<target>_ssh_host_ed25519_key
+#      Fix: scp the registered key back and restore it (needs sudo once per host).
+#      To push new keys proactively (before drift, e.g. right after
+#      sync-host-keys.sh --regenerate-all-keys), use instead:
+#        scripts/secrets/push-host-keys.sh --all
+#   2. Stale/invalid GitHub access token — the rendered nix-github-token.conf has
+#      a token GitHub rejects (401), blocking any rebuild that fetches disko or
+#      other public GitHub flake inputs.
+#      Fix: empty the rendered file so nix makes unauthenticated requests instead.
+#      Public repos (disko, nixpkgs, etc.) work fine without auth. sops-nix
+#      re-renders the correct new token automatically after the first successful
+#      rebuild.
+#
+# Both fixes need one interactive sudo session per host. The script opens a
+# single ssh -t per broken host so you enter the password once and all steps
+# run in sequence.
+
+set -euo pipefail
+cd "$(dirname "$0")/.."
+source scripts/env.sh 2>/dev/null || true
+
+SSH_OPTS=(-o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=5)
+SSH_USER=nixos
+
+# Known flake-target → ssh hostname map for all currently-defined hosts.
+# Add new hosts here as they are deployed.
+declare -A TARGET_HOST=(
+  [lxc-docker]=docker
+  [lxc-nix-cache]=nix-cache
+  [lxc-pxe-boot]=pxe-boot
+  [lxc-tor-relay]=tor-relay
+  [lxc-minimal]=nix-minimal
+  [proxmox-server]=server
+  [baremetal-gui]=nixos
+)
+
+# ── helpers ───────────────────────────────────────────────────────────────────
+
+info() { echo "  [✓] $*"; }
+warn() { echo "  [!] $*"; }
+step() { echo "==> $*"; }
+
+ssh_host_age() {
+  ssh-keyscan -t ed25519 "$1" 2>/dev/null \
+    | nix shell nixpkgs#ssh-to-age --command ssh-to-age 2>/dev/null \
+    | head -1 || true
+}
+
+registered_age() {
+  local keyfile="host-keys/${1}_ssh_host_ed25519_key.pub"
+  [ -f "$keyfile" ] || return 0
+  nix shell nixpkgs#ssh-to-age --command ssh-to-age < "$keyfile" 2>/dev/null \
+    | head -1 || true
+}
+
+github_token_valid() {
+  local host=$1
+  local raw token code
+  raw=$(ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" \
+    "cat /run/secrets/rendered/nix-github-token.conf 2>/dev/null || true")
+  token=$(echo "$raw" | grep -oP '(?<=github\.com=)\S+' || true)
+  if [ -z "$token" ]; then
+    return 0  # no token = unauthenticated, works for public repos
+  fi
+  code=$(curl -s -o /dev/null -w "%{http_code}" \
+    -H "Authorization: token $token" \
+    "https://api.github.com/repos/nix-community/disko" 2>/dev/null || echo 000)
+  [ "$code" = "200" ]
+}
+
+# ── discover hosts ────────────────────────────────────────────────────────────
+
+if [ $# -gt 0 ]; then
+  HOSTNAMES=("$@")
+else
+  HOSTNAMES=()
+  seen=()
+  for target in "${!TARGET_HOST[@]}"; do
+    h="${TARGET_HOST[$target]}"
+    # deduplicate (e.g. proxmox-server and lxc-server both map to "server")
+    if [[ ! " ${seen[*]:-} " =~ " $h " ]]; then
+      seen+=("$h")
+      if ssh "${SSH_OPTS[@]}" "$SSH_USER@$h" "true" 2>/dev/null; then
+        HOSTNAMES+=("$h")
+      fi
+    fi
+  done
+fi
+
+if [ ${#HOSTNAMES[@]} -eq 0 ]; then
+  echo "No reachable hosts found. Pass hostnames explicitly or check SSH."
+  exit 1
+fi
+
+echo ""
+echo "Hosts to check: ${HOSTNAMES[*]}"
+echo ""
+
+# ── check phase ───────────────────────────────────────────────────────────────
+
+NEEDS_FIX=()
+
+for host in "${HOSTNAMES[@]}"; do
+  step "$host"
+
+  if ! ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" "true" 2>/dev/null; then
+    warn "SSH unreachable — clearing stale known_hosts entry"
+    ssh-keygen -R "$host" 2>/dev/null || true
+    continue
+  fi
+
+  flake_target=$(ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" \
+    "cat /etc/flake-target 2>/dev/null || true")
+  echo "  flake-target: ${flake_target:-unknown}"
+
+  host_broken=false
+
+  # SSH host key
+  if [ -n "$flake_target" ] && [ -f "host-keys/${flake_target}_ssh_host_ed25519_key.pub" ]; then
+    live=$(ssh_host_age "$host")
+    want=$(registered_age "$flake_target")
+    if [ "$live" = "$want" ]; then
+      info "SSH host key OK"
+    else
+      warn "SSH host key MISMATCH (live ≠ host-keys/) -- use push-host-keys.sh proactively next time"
+      echo "       live:       $live"
+      echo "       registered: $want"
+      host_broken=true
+    fi
+  else
+    echo "  [~] No host-keys/ entry for ${flake_target:-unknown} — skipping key check"
+  fi
+
+  # GitHub token
+  if github_token_valid "$host"; then
+    info "GitHub token OK"
+  else
+    warn "GitHub token invalid (rebuild will fail with 401)"
+    host_broken=true
+  fi
+
+  # sops-nix result
+  sops_result=$(ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" \
+    "systemctl show sops-nix --property=Result --value 2>/dev/null || echo unknown")
+  if [ "$sops_result" = "success" ]; then
+    info "sops-nix: success"
+  else
+    warn "sops-nix: $sops_result"
+  fi
+
+  $host_broken && NEEDS_FIX+=("$host")
+  echo ""
+done
+
+# ── fix phase ─────────────────────────────────────────────────────────────────
+
+if [ ${#NEEDS_FIX[@]} -eq 0 ]; then
+  echo "All hosts healthy — nothing to fix."
+  exit 0
+fi
+
+echo "Hosts needing fixes: ${NEEDS_FIX[*]}"
+echo ""
+echo "Each fix requires one sudo session per host. You will be prompted for"
+echo "the nixos sudo password once per host; all steps run in that session."
+echo ""
+read -r -p "Proceed with fixes + Switch-nix on each broken host? [y/N] " confirm
+[[ "$confirm" =~ ^[Yy]$ ]] || { echo "Aborted."; exit 0; }
+echo ""
+
+for host in "${NEEDS_FIX[@]}"; do
+  step "Fixing $host"
+  flake_target=$(ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" \
+    "cat /etc/flake-target 2>/dev/null || true")
+
+  fix_script=""
+
+  # Fix 1: restore SSH host key
+  live=$(ssh_host_age "$host")
+  want=$(registered_age "${flake_target:-}")
+  if [ -n "$want" ] && [ "$live" != "$want" ]; then
+    echo "  Uploading registered SSH host key (private + public)..."
+    scp -o StrictHostKeyChecking=no \
+      "host-keys/${flake_target}_ssh_host_ed25519_key" \
+      "$SSH_USER@$host:/tmp/recover_ed25519_key"
+    scp -o StrictHostKeyChecking=no \
+      "host-keys/${flake_target}_ssh_host_ed25519_key.pub" \
+      "$SSH_USER@$host:/tmp/recover_ed25519_key.pub"
+    fix_script+='
+echo "[fix] Restoring SSH host key..."
+install -m 0600 /tmp/recover_ed25519_key /etc/ssh/ssh_host_ed25519_key
+install -m 0644 /tmp/recover_ed25519_key.pub /etc/ssh/ssh_host_ed25519_key.pub
+rm -f /tmp/recover_ed25519_key /tmp/recover_ed25519_key.pub
+echo "      Done."
+'
+    ssh-keygen -R "$host" 2>/dev/null || true
+  fi
+
+  # Fix 2: clear invalid GitHub token
+  if ! github_token_valid "$host"; then
+    fix_script+='
+echo "[fix] Clearing stale GitHub token (nix will use unauthenticated access)..."
+echo "" > /run/secrets/rendered/nix-github-token.conf
+systemctl restart nix-daemon 2>/dev/null || true
+echo "      Done."
+'
+  fi
+
+  # Fix 3: rebuild
+  fix_script+='
+echo "[fix] Running nixos-rebuild switch..."
+nixos-rebuild switch \
+  --no-write-lock-file \
+  --refresh \
+  --flake "git+https://gitea.lan.ddnsgeek.com/beatzaplenty/nixos.git#$(cat /etc/flake-target)"
+echo "[fix] Rebuild complete."
+'
+
+  echo "  Opening SSH session (enter sudo password when prompted)..."
+  if ssh -t -o StrictHostKeyChecking=no "$SSH_USER@$host" \
+    "sudo bash -s" <<< "$fix_script"; then
+    echo ""
+    info "$host fixed and rebuilt"
+  else
+    rc=$?
+    echo ""
+    warn "$host: rebuild exited with code $rc (may still have succeeded — check sops-nix below)"
+  fi
+
+  # Verify: re-check sops-nix result post-rebuild
+  sops_result_after=$(ssh "${SSH_OPTS[@]}" "$SSH_USER@$host" \
+    "systemctl show sops-nix --property=Result --value 2>/dev/null || echo unknown" 2>/dev/null || echo "ssh-failed")
+  if [ "$sops_result_after" = "success" ]; then
+    info "$host sops-nix: success post-rebuild"
+  else
+    warn "$host sops-nix: $sops_result_after post-rebuild (may need another pass)"
+  fi
+  echo ""
+done
+
+echo "Recovery complete."

scripts/secrets/prepare-host-key.sh

@@ -41,8 +41,9 @@ mkdir -p "$keydir"
 keyfile="${keydir}/${hostname}_ssh_host_ed25519_key"
 
 if [[ -f "$keyfile" ]]; then
-  echo "ERROR: $keyfile already exists. Remove it first if you want to regenerate." >&2
-  exit 1
+  echo "Key already exists: ${keyfile}"
+  echo "Reusing the existing key. Remove it first if you want to regenerate."
+  exit 0
 fi
 
 nix_extra_opts

scripts/secrets/push-host-keys.sh

@@ -0,0 +1,318 @@
+#!/usr/bin/env bash
+# Pushes newly-generated SSH host keys from host-keys/ to already-running
+# NixOS hosts, so they can decrypt sops secrets after a nixos-rebuild
+# following scripts/secrets/sync-host-keys.sh --regenerate-all-keys.
+#
+# Before pushing any key, verifies that .sops.yaml and secrets/*.yaml are
+# committed and pushed to the remote -- hosts rebuild from the remote Gitea
+# flake, so recipient changes must land there before any rebuild, not just
+# before the key push.
+#
+#   push-host-keys.sh --all [--dry-run] [--skip-git-check]
+#   push-host-keys.sh <target> [--dry-run] [--skip-git-check]
+#
+#   --all              Push to every reachable managed host. Default when no
+#                      target is given.
+#   <target>           Push to one flake target only (e.g. lxc-server).
+#   --dry-run          Print what would be done; write nothing.
+#   --skip-git-check   Skip the commit/push check. Use only when the remote
+#                      already has the current .sops.yaml/secrets/*.yaml.
+#
+# SSH: connects as SSH_USER@<hostname> (default: nixos, the user with the
+# admin authorized key), then installs files via sudo -S (reads the sudo
+# password from stdin). The password is prompted once at startup and reused
+# for every host -- no PTY or terminal required on the remote side.
+# Hosts are reached at their bare hostname (relies on LAN DNS/mDNS).
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+keydir="${repo_root}/host-keys"
+
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/nix-eval.sh
+source "${repo_root}/scripts/lib/nix-eval.sh"
+
+: "${SSH_USER:=nixos}"
+SSH_OPTS=(-o StrictHostKeyChecking=no -o BatchMode=yes -o ConnectTimeout=5)
+
+dry_run=0
+skip_git_check=0
+sudo_password=""
+
+usage() {
+  cat <<EOF
+Usage: $0 [--all | <target>] [--dry-run] [--skip-git-check]
+
+  --all              Push to every reachable managed host. Default when no
+                     target is given.
+  <target>           Push to one flake target only (e.g. lxc-server).
+  --dry-run          Print what would be done; write nothing.
+  --skip-git-check   Skip the check that .sops.yaml/secrets/*.yaml are
+                     committed and pushed to the remote repo.
+
+Environment:
+  SSH_USER           SSH username (default: nixos).
+  SUDO_PASS          Sudo password (skips the interactive prompt; useful
+                     when calling from another script).
+EOF
+}
+
+# Prompt for the sudo password once; store it for all _do_push calls.
+# Accepts SUDO_PASS from the environment to allow non-interactive callers.
+prompt_sudo_password() {
+  [[ "$dry_run" -eq 1 ]] && return
+  if [[ -n "${SUDO_PASS:-}" ]]; then
+    sudo_password="$SUDO_PASS"
+    return
+  fi
+  # read exits non-zero when stdin is not a terminal (e.g. CI, background
+  # agents). Catch that and give a clear message rather than a silent exit.
+  if ! read -r -s -p "sudo password for ${SSH_USER} on remote hosts: " sudo_password; then
+    echo >&2
+    echo "ERROR: stdin is not a terminal -- cannot prompt for sudo password." >&2
+    echo "       Set SUDO_PASS=<password> in the environment and re-run." >&2
+    exit 1
+  fi
+  echo >&2
+}
+
+locally_managed_hosts() {
+  for f in "${keydir}"/*_ssh_host_ed25519_key.pub; do
+    [[ -e "$f" ]] || continue
+    basename "$f" _ssh_host_ed25519_key.pub
+  done
+}
+
+# --- git state check/fix --------------------------------------------------
+# Hosts rebuild from the remote Gitea flake:
+#   nixos-rebuild switch --flake "git+https://<gitea>/nixos.git#<target>"
+# so .sops.yaml (updated recipients) and secrets/*.yaml (re-encrypted DEKs)
+# must be committed and pushed before any rebuild can succeed. This check
+# catches the common case where --regenerate-all-keys was just run but the
+# resulting diff hasn't been committed/pushed yet.
+ensure_remote_current() {
+  [[ "$skip_git_check" -eq 1 ]] && return
+
+  cd "$repo_root"
+
+  local dirty_unstaged dirty_staged
+  dirty_unstaged="$(git diff --name-only -- .sops.yaml secrets/ 2>/dev/null || true)"
+  dirty_staged="$(git diff --cached --name-only -- .sops.yaml secrets/ 2>/dev/null || true)"
+
+  if [[ -n "$dirty_unstaged" || -n "$dirty_staged" ]]; then
+    echo "Uncommitted changes in sops-managed files:"
+    [[ -n "$dirty_unstaged" ]] && sed 's/^/  (unstaged) /' <<<"$dirty_unstaged"
+    [[ -n "$dirty_staged"   ]] && sed 's/^/  (staged)   /' <<<"$dirty_staged"
+    echo
+    if [[ "$dry_run" -eq 1 ]]; then
+      echo "[dry-run] would prompt to commit .sops.yaml/secrets/ before continuing."
+    else
+      read -rp "Commit .sops.yaml + secrets/ now? [y/N]: " ans
+      if [[ "$ans" =~ ^[Yy]$ ]]; then
+        git add -- .sops.yaml secrets/
+        git commit -m "secrets: update recipients and re-encrypt for host key changes"
+        echo "Committed."
+      else
+        echo "Continuing with uncommitted changes -- the remote won't have the"
+        echo "updated recipients until you commit and push."
+      fi
+    fi
+    echo
+  fi
+
+  # Check if we're ahead of the remote tracking branch
+  local ahead
+  ahead="$(git rev-list --count '@{upstream}..HEAD' 2>/dev/null || echo "")"
+  if [[ -z "$ahead" ]]; then
+    echo "NOTE: no remote tracking branch found -- skipping push check."
+    echo "      Ensure the remote has the current .sops.yaml/secrets/ before"
+    echo "      triggering nixos-rebuild on any host."
+    echo
+    return
+  fi
+
+  if [[ "$ahead" -gt 0 ]]; then
+    echo "Local branch is ${ahead} commit(s) ahead of remote."
+    if [[ "$dry_run" -eq 1 ]]; then
+      echo "[dry-run] would prompt to push before continuing."
+    else
+      read -rp "Push to remote now? [y/N]: " ans
+      if [[ "$ans" =~ ^[Yy]$ ]]; then
+        git push
+        echo "Pushed."
+      else
+        echo "Continuing without pushing -- remember to push before running"
+        echo "nixos-rebuild on any of these hosts."
+      fi
+    fi
+    echo
+  fi
+}
+
+# --- key installation (shared) -------------------------------------------
+_do_push() {
+  local hostname="$1" target="$2"
+  local keyfile="${keydir}/${target}_ssh_host_ed25519_key"
+  local pubfile="${keyfile}.pub"
+
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "  [dry-run] would scp host-keys/${target}_ssh_host_ed25519_key{,.pub} to /tmp/"
+    echo "  [dry-run] would: sudo -S install -m 0600/0644 to /etc/ssh/ and rm /tmp copies"
+    return
+  fi
+
+  # Upload to /tmp (writable as nixos, no privilege needed)
+  scp -o StrictHostKeyChecking=no \
+    "$keyfile" "${SSH_USER}@${hostname}:/tmp/push_ed25519_key"
+  scp -o StrictHostKeyChecking=no \
+    "$pubfile" "${SSH_USER}@${hostname}:/tmp/push_ed25519_key.pub"
+
+  # Install via sudo -S: the password is piped via herestring so no PTY is
+  # needed on either side. -p '' suppresses sudo's own prompt string.
+  ssh -o StrictHostKeyChecking=no "${SSH_USER}@${hostname}" \
+    "sudo -S -p '' bash -c '
+      install -m 0600 /tmp/push_ed25519_key     /etc/ssh/ssh_host_ed25519_key
+      install -m 0644 /tmp/push_ed25519_key.pub /etc/ssh/ssh_host_ed25519_key.pub
+      rm -f /tmp/push_ed25519_key /tmp/push_ed25519_key.pub
+      echo \"  [ok] host key installed\"
+    '" <<< "$sudo_password"
+
+  # Drop the stale known_hosts entry for this host (public key just changed)
+  ssh-keygen -R "$hostname" 2>/dev/null || true
+
+  echo "  Done. Run nixos-rebuild switch on ${hostname} to activate."
+}
+
+# --- single named target --------------------------------------------------
+push_target() {
+  local target="$1"
+  local keyfile="${keydir}/${target}_ssh_host_ed25519_key"
+
+  if [[ ! -f "$keyfile" ]]; then
+    echo "ERROR: host-keys/${target}_ssh_host_ed25519_key not found." >&2
+    echo "       This target may not be locally managed (e.g. &${target} was" >&2
+    echo "       registered from the host's real SSH key, not generated here)." >&2
+    exit 1
+  fi
+
+  local hostname
+  hostname="$(flake_target_hostname "$repo_root" "$target")"
+  if [[ -z "$hostname" ]]; then
+    echo "ERROR: cannot resolve hostname for '${target}' from the flake." >&2
+    exit 1
+  fi
+
+  echo "==> ${target} (→ ${hostname})"
+
+  if ! ssh "${SSH_OPTS[@]}" "${SSH_USER}@${hostname}" true 2>/dev/null; then
+    echo "  SKIP: ${SSH_USER}@${hostname} unreachable."
+    return
+  fi
+
+  # Sanity-check that /etc/flake-target on the host agrees
+  local live_target
+  live_target="$(ssh "${SSH_OPTS[@]}" "${SSH_USER}@${hostname}" \
+    "cat /etc/flake-target 2>/dev/null || true")"
+  if [[ -n "$live_target" && "$live_target" != "$target" ]]; then
+    echo "  WARN: host reports /etc/flake-target='${live_target}', not '${target}'."
+    echo "       Pushing the key you specified (${target}) anyway."
+  fi
+
+  _do_push "$hostname" "$target"
+}
+
+# --- all managed hosts ----------------------------------------------------
+# For each unique hostname derived from managed targets, SSHes in and reads
+# /etc/flake-target to determine which key to push -- handles the case where
+# multiple targets share a hostname (e.g. lxc-server and proxmox-server both
+# resolve to "server"; only one is actually running).
+push_all() {
+  mapfile -t managed < <(locally_managed_hosts)
+  if [[ "${#managed[@]}" -eq 0 ]]; then
+    echo "No managed keys in host-keys/ -- nothing to push."
+    return
+  fi
+
+  echo "Pushing to all reachable managed hosts..."
+  echo
+
+  declare -A seen_hostnames=()
+  local t hostname
+  for t in "${managed[@]}"; do
+    hostname="$(flake_target_hostname "$repo_root" "$t" 2>/dev/null || true)"
+    [[ -z "$hostname" ]] && continue
+    [[ -n "${seen_hostnames[$hostname]+x}" ]] && continue
+    seen_hostnames["$hostname"]=1
+
+    echo "==> checking ${hostname}"
+
+    if ! ssh "${SSH_OPTS[@]}" "${SSH_USER}@${hostname}" true 2>/dev/null; then
+      echo "  SKIP: ${SSH_USER}@${hostname} unreachable."
+      continue
+    fi
+
+    # Ask the host which flake target it actually is
+    local live_target
+    live_target="$(ssh "${SSH_OPTS[@]}" "${SSH_USER}@${hostname}" \
+      "cat /etc/flake-target 2>/dev/null || true")"
+
+    if [[ -z "$live_target" ]]; then
+      echo "  SKIP: no /etc/flake-target on host -- can't determine which key to push."
+      continue
+    fi
+
+    local live_keyfile="${keydir}/${live_target}_ssh_host_ed25519_key"
+    if [[ ! -f "$live_keyfile" ]]; then
+      echo "  SKIP: host is '${live_target}' but no host-keys/${live_target}_... (hand-registered key, not managed here)."
+      continue
+    fi
+
+    echo "  target: ${live_target}"
+    _do_push "$hostname" "$live_target"
+  done
+}
+
+# --- main -----------------------------------------------------------------
+mode="all"
+target_arg=""
+extra_args=()
+
+for arg in "$@"; do
+  case "$arg" in
+    --dry-run)        dry_run=1 ;;
+    --skip-git-check) skip_git_check=1 ;;
+    --all)            mode="all" ;;
+    -h|--help)        usage; exit 0 ;;
+    --*)              echo "Unknown option: $arg" >&2; usage >&2; exit 1 ;;
+    *)                extra_args+=("$arg") ;;
+  esac
+done
+
+if [[ "${#extra_args[@]}" -gt 1 ]]; then
+  echo "ERROR: specify at most one target (or --all)." >&2
+  usage >&2; exit 1
+elif [[ "${#extra_args[@]}" -eq 1 ]]; then
+  mode="single"
+  target_arg="${extra_args[0]}"
+fi
+
+[[ "$dry_run" -eq 1 ]] && { echo "[dry-run] no changes will be made"; echo; }
+
+nix_extra_opts
+ensure_remote_current
+prompt_sudo_password
+
+if [[ "$mode" == "single" ]]; then
+  push_target "$target_arg"
+else
+  push_all
+fi
+
+echo
+if [[ "$dry_run" -eq 1 ]]; then
+  echo "[dry-run] Nothing was changed. Re-run without --dry-run to apply."
+else
+  echo "Key push complete. For each updated host, run nixos-rebuild switch to"
+  echo "apply the config and let sops-nix decrypt secrets with the new key."
+fi

scripts/secrets/sync-host-keys.sh

@@ -11,17 +11,16 @@
 #   sync-host-keys.sh --regenerate-all-keys Remove and freshly regenerate
 #                                           every locally-managed key.
 #
-# "Generate/register" is idempotent and additive only: an existing
-# host-keys/ file is never touched, and .sops.yaml only ever gains an
-# anchor/alias it doesn't already have -- safe to re-run any time, e.g.
-# right after adding a new host to flake.nix.
+# "Generate/register" is idempotent and additive only: an existing clan
+# var is never overwritten, and .sops.yaml only ever gains an anchor/alias
+# it doesn't already have -- safe to re-run any time, e.g. right after
+# adding a new host to flake.nix.
 #
-# --remove and --regenerate-all-keys only ever operate on anchors that have
-# a corresponding host-keys/<name>_ssh_host_ed25519_key file. Anchors
-# without one (&admin, and any anchor for an already-deployed host whose
-# real /etc/ssh key was registered by hand, e.g. &docker/&server/&nix-cache
-# today) are never listed, removed, or regenerated -- this tooling only
-# ever touches keys it itself manages.
+# --remove and --regenerate-all-keys only ever operate on anchors that
+# have a corresponding clan var (vars/per-machine/<name>/openssh/) or
+# host-keys/ file. Anchors without either (&admin) are never listed,
+# removed, or regenerated -- this tooling only ever touches keys it itself
+# manages.
 set -euo pipefail
 
 repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
@@ -39,6 +38,8 @@ source "${repo_root}/scripts/lib/ssh-host-keys.sh"
 source "${repo_root}/scripts/lib/sops-age.sh"
 # shellcheck source=../lib/confirm.sh
 source "${repo_root}/scripts/lib/confirm.sh"
+# shellcheck source=../lib/clan-vars.sh
+source "${repo_root}/scripts/lib/clan-vars.sh"
 
 mkdir -p "$keydir"
 
@@ -54,13 +55,14 @@ Usage: $0 --all [--dry-run]
   <flake-target>            Same, for just one target (e.g. lxc-server).
                             Reports if it already has one.
   --remove                  Interactively pick one locally-managed key to
-                            remove from .sops.yaml and host-keys/.
+                            remove from .sops.yaml and vars/per-machine/
+                            (or host-keys/ for legacy keys).
   --regenerate-all-keys     Remove every locally-managed key and generate
-                            fresh replacements for every current flake
-                            target. Destructive -- requires typed
+                            fresh clan-var replacements for every current
+                            flake target. Destructive -- requires typed
                             confirmation.
   --dry-run                 Combine with any of the above: print what would
-                            change (host-keys/ files, .sops.yaml anchors and
+                            change (clan vars, .sops.yaml anchors and
                             key_groups, which secrets/*.yaml would be
                             re-encrypted) without touching anything. No keys
                             generated, no files written, no sops calls,
@@ -83,6 +85,10 @@ ensure_admin_decrypt_key() {
   fi
 
   local key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
+  # Expand a leading ~ that survived variable substitution without tilde
+  # expansion (happens when SOPS_AGE_KEY_FILE or XDG_CONFIG_HOME is set with
+  # a literal ~ in the caller's environment).
+  key_file="${key_file/#~\//$HOME/}"
 
   if [[ -s "$key_file" ]]; then
     echo "Found existing sops age key at ${key_file}."
@@ -91,36 +97,23 @@ ensure_admin_decrypt_key() {
 
   if [[ "$dry_run" -eq 1 ]]; then
     echo "[dry-run] No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file})."
-    echo "[dry-run] Would generate a new one here -- continuing the dry run without one; any"
-    echo "[dry-run] 'would re-encrypt' output below couldn't actually run for real yet."
+    echo "[dry-run] Continuing dry run without one -- any 'would re-encrypt' output below"
+    echo "[dry-run] couldn't actually run for real until a key is present."
     return
   fi
 
-  echo "No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file})."
-  echo "Generating a new one at ${key_file}..."
-  mkdir -p "$(dirname "$key_file")"
-  nix-shell "${NIX_OPTS[@]}" -p age --run "age-keygen -o '${key_file}'" 2>&1 | grep -v "^Public key:" || true
-  local new_pub
-  new_pub="$(age_pubkey_from_identity_file "$key_file")"
+  cat >&2 <<EOF
+No sops age decryption key found (checked \$SOPS_AGE_KEY, \$SOPS_AGE_KEY_FILE, ${key_file}).
 
-  cat <<EOF
+Place your admin age private key at ${key_file}, or set SOPS_AGE_KEY (inline
+key) or SOPS_AGE_KEY_FILE (path to a different key file) and re-run.
 
-A brand-new age key was just generated -- it cannot decrypt anything that
-already exists in secrets/*.yaml, since nothing was ever encrypted for it.
-That trust can't be bootstrapped automatically (nobody can decrypt a file
-for a recipient that didn't exist when it was last encrypted).
-
-To actually use this key:
-  1. Have someone who currently CAN decrypt replace the &admin entry in
-     .sops.yaml with this public key:
-       ${new_pub}
-  2. They re-encrypt every secrets/*.yaml:
-       sops updatekeys --yes secrets/common.yaml
-       sops updatekeys --yes secrets/nix-cache.yaml
-       sops updatekeys --yes secrets/server.yaml
-  3. Re-run this script.
-
-Exiting without making any other changes.
+If the key is truly missing (not just mislocated), this is a manual recovery
+situation -- generating a brand-new admin key won't help, since it cannot
+decrypt anything already encrypted for the old one.  Each secrets/*.yaml is
+also encrypted for its respective host key(s), so a running deployed host can
+still decrypt what it needs -- but the admin key is required for re-encryption
+(e.g. adding new recipients via sops updatekeys).
 EOF
   exit 1
 }
@@ -133,10 +126,17 @@ discover_targets() {
 }
 
 locally_managed_hosts() {
-  for f in "$keydir"/*_ssh_host_ed25519_key.pub; do
-    [[ -e "$f" ]] || continue
-    basename "$f" _ssh_host_ed25519_key.pub
-  done
+  {
+    for f in "$keydir"/*_ssh_host_ed25519_key.pub; do
+      [[ -e "$f" ]] || continue
+      basename "$f" _ssh_host_ed25519_key.pub
+    done
+    local d
+    for d in "${repo_root}/vars/per-machine"/*/openssh/ssh_host_ed25519_key/secret; do
+      [[ -f "$d" ]] || continue
+      basename "$(dirname "$(dirname "$(dirname "$d")")")"
+    done
+  } | sort -u
 }
 
 add_keys_json="[]"
@@ -146,13 +146,15 @@ dry_run=0
 queue_host_sync() {
   local host="$1"
   local keyfile="${keydir}/${host}_ssh_host_ed25519_key"
-  local has_local_key=0 has_anchor=0
+  local has_local_key=0 has_clan_key=0 has_anchor=0
   [[ -f "$keyfile" ]] && has_local_key=1
+  clan_ssh_key_exists "$host" "$repo_root" && has_clan_key=1
   grep -qE "^  - &${host} age1" "$sops_yaml" && has_anchor=1
 
-  if [[ "$has_local_key" -eq 0 && "$has_anchor" -eq 1 ]]; then
+  if [[ "$has_local_key" -eq 0 && "$has_clan_key" -eq 0 && "$has_anchor" -eq 1 ]]; then
     echo "SKIP ${host}: .sops.yaml already has an &${host} anchor, but"
-    echo "     host-keys/${host}_ssh_host_ed25519_key is missing locally."
+    echo "     neither host-keys/${host}_ssh_host_ed25519_key nor"
+    echo "     vars/per-machine/${host}/openssh/ exist locally."
     echo "     Not generating a replacement -- it wouldn't match whatever's"
     echo "     already registered (and possibly deployed). Remove the"
     echo "     &${host} line from .sops.yaml first if you really want a"
@@ -160,21 +162,26 @@ queue_host_sync() {
     return 1
   fi
 
-  if [[ "$has_local_key" -eq 0 ]]; then
+  if [[ "$has_local_key" -eq 0 && "$has_clan_key" -eq 0 ]]; then
     if [[ "$dry_run" -eq 1 ]]; then
-      echo "[dry-run] ${host}: would generate host key"
+      echo "[dry-run] ${host}: would generate host key via clan vars"
     else
-      echo "==> ${host}: generating host key"
-      generate_host_ed25519_key "$host" "$keyfile"
+      echo "==> ${host}: generating host key via clan vars"
+      clan_generate_ssh_key "$host" "$repo_root"
+      has_clan_key=1
     fi
+  elif [[ "$has_clan_key" -eq 1 ]]; then
+    echo "==> ${host}: clan-managed SSH host key already present"
   else
-    echo "==> ${host}: host key already present"
+    echo "==> ${host}: host key already present (host-keys/)"
   fi
 
   if [[ "$has_anchor" -eq 0 ]]; then
     local age_pub
     if [[ "$dry_run" -eq 1 ]]; then
       age_pub="dry-run-placeholder-not-a-real-key"
+    elif [[ "$has_clan_key" -eq 1 ]]; then
+      age_pub="$(ssh_pubkey_to_age "$(clan_ssh_pubkey_path "$host" "$repo_root")")"
     else
       age_pub="$(ssh_pubkey_to_age "${keyfile}.pub")"
     fi
@@ -299,7 +306,7 @@ cmd_remove() {
   local hosts
   mapfile -t hosts < <(locally_managed_hosts)
   if [[ "${#hosts[@]}" -eq 0 ]]; then
-    echo "No locally-managed keys in host-keys/ -- nothing to remove."
+    echo "No locally-managed keys found (checked host-keys/ and vars/per-machine/) -- nothing to remove."
     return
   fi
 
@@ -308,7 +315,9 @@ cmd_remove() {
   for host in "${hosts[@]}"; do
     local registered="not registered in .sops.yaml"
     grep -qE "^  - &${host} age1" "$sops_yaml" && registered="registered in .sops.yaml"
-    printf '  %d) %s (%s)\n' "$i" "$host" "$registered"
+    local where="host-keys/"
+    clan_ssh_key_exists "$host" "$repo_root" && where="clan-vars"
+    printf '  %d) %s [%s, %s]\n' "$i" "$host" "$where" "$registered"
     i=$((i + 1))
   done
 
@@ -325,7 +334,7 @@ cmd_remove() {
   local target="${hosts[$((choice - 1))]}"
 
   if [[ "$dry_run" -ne 1 ]]; then
-    read -rp "Really remove '${target}'? Its host-keys/ files will be deleted and it will lose access to every secrets file it can currently decrypt. (y/N): " confirm
+    read -rp "Really remove '${target}'? Its key files will be deleted and it will lose access to every secrets file it can currently decrypt. (y/N): " confirm
     if [[ ! "$confirm" =~ ^[Yy]$ ]]; then
       echo "Cancelled."
       return
@@ -338,11 +347,13 @@ cmd_remove() {
   apply_edit_plan "$plan"
 
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would delete host-keys/${target}_ssh_host_ed25519_key(.pub)."
+    echo "[dry-run] would delete host-keys/${target}_ssh_host_ed25519_key(.pub) if present."
+    echo "[dry-run] would delete vars/per-machine/${target}/openssh/ if present."
     echo "[dry-run] Nothing was changed. Re-run without --dry-run to apply this."
   else
     rm -f "${keydir}/${target}_ssh_host_ed25519_key" "${keydir}/${target}_ssh_host_ed25519_key.pub"
-    echo "Removed host-keys/${target}_ssh_host_ed25519_key(.pub)."
+    rm -rf "${repo_root}/vars/per-machine/${target}/openssh"
+    echo "Removed key for ${target} (host-keys/ and/or vars/per-machine/ as applicable)."
     echo
     echo "Review the diff, then commit and push."
   fi
@@ -352,15 +363,18 @@ cmd_regenerate_all() {
   local hosts
   mapfile -t hosts < <(locally_managed_hosts)
   if [[ "${#hosts[@]}" -eq 0 ]]; then
-    echo "No locally-managed keys in host-keys/ -- nothing to regenerate."
+    echo "No locally-managed keys found (checked host-keys/ and vars/per-machine/) -- nothing to regenerate."
     return
   fi
 
   echo "This will remove and freshly regenerate ALL locally-managed keys:"
   printf '  %s\n' "${hosts[@]}"
   echo
-  echo "Every host above will need its new key baked into a rebuilt install"
-  echo "image/tarball before it can decrypt secrets again."
+  echo "After regenerating, each host needs its new key before it can decrypt secrets:"
+  echo "  • Already running: push the key before rebuilding:"
+  echo "      scripts/secrets/push-host-keys.sh --all"
+  echo "  • Not yet deployed: rebuild the install image with the new keys baked in"
+  echo "      (see docs/auto-installer.md)."
 
   if [[ "$dry_run" -ne 1 ]]; then
     if ! confirm_typed "REGENERATE" "Type REGENERATE to confirm: "; then
@@ -378,8 +392,8 @@ cmd_regenerate_all() {
   apply_edit_plan "$plan"
 
   if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would delete ${#hosts[@]} host-keys/ file pair(s)."
-    echo "[dry-run] would then generate fresh replacements for the same hosts"
+    echo "[dry-run] would delete ${#hosts[@]} key pair(s) from host-keys/ and/or vars/per-machine/."
+    echo "[dry-run] would then generate fresh clan vars replacements for the same hosts"
     echo "[dry-run] (not simulated further here -- run without --dry-run, or"
     echo "[dry-run] preview a specific target with: $0 <target> --dry-run)."
     echo
@@ -391,12 +405,23 @@ cmd_regenerate_all() {
   local host
   for host in "${hosts[@]}"; do
     rm -f "${keydir}/${host}_ssh_host_ed25519_key" "${keydir}/${host}_ssh_host_ed25519_key.pub"
+    rm -rf "${repo_root}/vars/per-machine/${host}/openssh"
   done
-  echo "Removed ${#hosts[@]} host-keys/ file pair(s)."
+  echo "Removed ${#hosts[@]} key pair(s)."
 
   echo
   echo "Regenerating fresh keys for every current flake target..."
   cmd_all
+
+  echo
+  echo "Next steps:"
+  echo "  1. Commit and push .sops.yaml + secrets/ so the remote flake is current."
+  echo "  2. Push the new host key to each already-running managed host:"
+  echo "       scripts/secrets/push-host-keys.sh --all"
+  echo "     (this also prompts to commit/push if step 1 wasn't done yet)"
+  echo "  3. Run nixos-rebuild switch on each updated host."
+  echo "  4. For hosts not yet deployed, rebuild the install image (see"
+  echo "     docs/auto-installer.md)."
 }
 
 main() {

secrets/common.yaml

@@ -1,135 +1,227 @@
 root-hashedPassword: ENC[AES256_GCM,data:Kp0nOZI7vDoLhJHiOJBwJn0rQZ5yhnwapGnAcA+qh8vlDETtFs/iQdetF/2ZxmANf62SviTNd+Ag0q5JIF1996x7onZGXqxgSMCuVzZLBdUlsO5IR0BslWWz47khYGTe4WkUg4NB1itBfQ==,iv:5Sra5vJ79V8hxQT3g9qJ+dOj2W2sumIhqpitqnHjJdk=,tag:3Igu0+8GeUZHqS3fKUVwog==,type:str]
 nixos-hashedPassword: ENC[AES256_GCM,data:pT7tVRN6X4a+DNUgB7fIUUE3CbnetkjxmoSL1PxSU+ktsFU+fB0mEvJjA1uujsGH5Rcztg7YM815+M0Z67ILmHaXbza5DtFacrqhi4/b277xly0SHRX4yOvBwQh6mJG1jn/0O/wvUUIYdw==,iv:bp2nfhC8nFbk6o5iWDAugvbzu7J/a1xayFnBEtkhNpE=,tag:HqWgkIpSrSM/K9OK2WO+VQ==,type:str]
-nix-github-token: ENC[AES256_GCM,data:OfNRGJg16Ede6EilWUetCs9za+xk5/Lsa3SpVajsqz8PMdA1xQNeCWdX7ZAMdijHClpBhU6ETFGsXvt41O9aORS951uijeGSW7/NH35/bnPISrKdYeBx/+xEiqwH,iv:QGU3v7xOy89uzRTCb1U9ICyJ8XYIpXrUsDt12aL3g2Y=,tag:Bde2wcWNv8H4WLxSEUAodg==,type:str]
+nix-github-token: ENC[AES256_GCM,data:k1vYz7SqVhzpWa6jTL6NUD8lKOCpHCgTm+HT4IcnbzbSTUZP/bJUYw==,iv:UqAULZnr/4+VcioUDfTwvOSuwM8K9JgGhiApvYQPyoc=,tag:1LKHXhWAO/AHPDIZFBb04A==,type:str]
+beszel-token: ENC[AES256_GCM,data:OWmSRkZjb11y0Y8GdobqiE9GFwzdHOvvxCbYx69qUghGYARN,iv:i/JhGH0O7ThxPkL0SLAjfN0Fq8prm7tybI5kF2NRNpw=,tag:dBcqxOSHTnD4xngpOog55Q==,type:str]
+nix-gitea-token: ENC[AES256_GCM,data:HRQ8ymx/D8pLcL/pYIhcSTv3tlBCKOU5nhXPp/W6rNI+t+yxfOoRPQ==,iv:0Av3lrxQew2bDFf67nX/UM+cD0/8CtbQ2fZSaKWHAzM=,tag:0K+atsB/YmYd/qCN3hMdBw==,type:str]
 sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBIakJkWDQ2TjVIS1Q1UlRJ
-            elVLNmhEVUpMNjROWmN6VC8wTnZzeWhLb0hFCmxmTXp3ZVdQMUhDeGlscThSdFhP
-            eWNZSkFpeEg0cUUxbGFyQWIrTkJkc0EKLS0tIGRBTHdaZ2d5eHhxd3BtWVBLbFlo
-            OVJlYnQ0N09qWFp2TmtXb2E0Wkk2bzQKTxA4rfkF3qlGpDqaZF/J9tgTx1UZ7ZFt
-            W1KevMq/Klnkjb9XDuTEx7zgrjILoViVspe6eGI14myBNYtAP4nLSA==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAyR3lnUnZwUnlJTkFaeVdz
+            T3Q2eW52cWI2eTlhSFpHNDRHTEVNVGZJYm1NCldaMmlHaCt1K3lWRHhEZExHK3lo
+            azZFck1URVg5ejBaRVdCWjdFMTc4dGsKLS0tIG9mNkxsZXI1N1hCRWk1NTZKcUUr
+            SlJoWGdWbXhqZEJHM3IzZmZSQ25QbzAKPzBIA/IJiZr5NpOhB6IPkUSDGQzPwpTU
+            vgFLMze8OSEviaGXKLt/ZwTXHsr5As7V9yGvJKJHhS/hzuSLRjs8rQ==
             -----END AGE ENCRYPTED FILE-----
           recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBUWXYyUG5UdHdFa2NDZmtt
-            ZG1GSmxVbTg5Qnh4UGxJaitmTmFqK2J1cUV3CmdPSU5GTC9hWkROTkJzMk5Tcmpw
-            ODJzdlIvNkp0ZXdZNlRlUHBkOGVoR1kKLS0tIGsvUWxpU2hkanFNaExJWGozMTJL
-            bndPNkpQNktmQVNKNEhGOEtHSlRBRXMK9rr6NHf3H91GIqTmckjD1eV94FW1vk9G
-            h2KauyebWPyBe8hsCExiPd45ZGqKF0g8pEtWUzonMq9NU/MNVL8YVQ==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpYmZHNWVCL0ErNEF3OTlG
+            TTJDT1hZMXJNNUdLZ3ByUDNndVpLWVVGUm1RCkZSRmJmd3NyeHc0V0tpZEdYakF1
+            WXhyWUJ0V1hTYzhrSUo1ZUNzR2J3OVUKLS0tIEthYXVvNVRibDVSQ2N0NWt3TmNP
+            cTlteEtRYmxnUmdIUlBTREZzQXBBSVEKxQq10KDseuoVPe0cLBbk1+weuq0y6di+
+            wJjaMShqVQBUI+MFWiQokBhPt8gZS7cs33LkWf3BegNALLDd6HXoOg==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age19gfn2yedg76dmztm4hncr7vf3r3c9j0qpt4rap7y7gersjk4m3ks2lhd0e
+          recipient: age19m0m7vdfg86yqy8l5mmle5jdd0unrn3f55t232w8h5ey42cqw34sfpt32n
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBXdnpGR2ZnaFRSUUNlOUVy
-            ME9pWkFJRTl6ampuZTR0QlQ2TUVEVHV3dkRFCmxML1NSV2dwanRPK3AySDJiUU9P
-            a2VKZ09EaktYU2xvWWpESWtrU3oxalEKLS0tIEt1aWxuNmlaV3l1OGNqS2RtMmhm
-            Rk9SUEpBaXY0RG9uMk53ejdJdVZ4NDQKfn4paPsHrfU3Ki2AgPBB8aLBbmD2yh1O
-            9rDxv/6xSsDXNTquP11smPOKsRG7mDMDHVByn6GieZrpSxUf9vu3Iw==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArOE9oU210Vkk1Z1VKMS8x
+            YTJGbFlSYmx6eWgvMXExZ243SndXWkZ0ekY4ClJVUTFSVkRERjY1UVZMZjlFeE1P
+            Vm40WHY4UjMwZWxVa05lblBMUW9iNEEKLS0tIGVlbDVxakR4MlBEaFlrM0tNOWRX
+            elIvMnp5NmhnYVBYOFA0aUdtOE5DbEUKy+soKNLlRe0SC8kcnwrpKqvSrTGE114/
+            FaX2829gQWm0bYI0M4ixeTc5ME2O2Ct2tvYlzfZQPnAuub+jVx2k8g==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
+          recipient: age1rrxqea6q6pn39sw8y5te63h2py8jgjl9v0jyper86w3ggtn67upqg3ah39
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArNHZpMDV5a2JCN1NxY2hF
-            MWxtNUNVQXp6K3lWYndTRU85Wjh4YlN3UFFrCnNZbHA2Z2RUSmxITm4yeU9rYnV0
-            TTFkZUczcTZLU2pJRDQ3TVl5ZGErWDgKLS0tIDJGbzZZNjQ2RXUzRmUwKzdiUHlK
-            TEU5VERpZ1p3bU1KcnEvRDRCSVNqT2MKQPfu0lskXaEAYgecmN1a0kPHF+fGEm7R
-            wiY7TFNLeXM5aJqEnKARtOotJDetI+9VNssTT21X/Qaik6fqgM+b1A==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzR0R1VEc2eTRIOWNxaVpa
+            RXVaNkxjaDVDTmxMVWJEU0dWNkxDeE56c2swCjdkZGVQM3V0SnhGMXFxSEFEeEpP
+            OFNwTWQwYTY0S0trMy9FMjNjbWFxajAKLS0tIHhjUW1lZ1EycUh2Sm1yanhzS3dP
+            WFlMcndzOThUVVVDZlJJeGFBT2JLTEUKHsJ6cwSPcO0IB1CQe2RqKeid8Q92BTNF
+            RfURqE7Curj1yaFB45mzv2ThBgTKN5FE6y5BWgBnF6+szdMMXRw4uQ==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
+          recipient: age1adur9g330gua4l6ndk8cqjg35qc8yxwgme6wrl2hpylcc7vxm38q05ejuy
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBOUlp5MmcvSFRnaVdWZ1g0
-            NmwvS3pGa1JCd0RuQnFMeU5wZDZYK0NQR1FJClF0Z0VENThtTzZ1OUtmUjdDenV4
-            Mko0T2o4UzVubVRCdUlCMERyV2w5WmcKLS0tIGZUallPeUhXUGtVMmNIWWRkaFVT
-            TVNVTjhiQzJkdlVQN3p1bnR1aUYyQmcKVnqbCuaSYEA7stk1MyfCzRbqt7EL+E5/
-            jgxraiFmaZqjDI5mxG/e7eFdXfv53AtKzZm92TlzvV+4bfidj5SvYw==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlQkVPTHBYWkdMM3Jyd3NW
+            bkNGa3VtYXNBanZPc1puSGdwUEN5ejIwRkFJCjlNNXFlTEV1eEZNVTFxWnNJZG5O
+            UG5hci9XVmMyeXF1ZHF2Rm5DUVdPcFEKLS0tIDBEZUtZNXR2R093OVNNYzRnbXlj
+            S3R2UzFoTmhZT3Y0K1d4STFjU2RRamsKU9LcaOLLjmcarmdir9Hnt/qaNvlxvSsE
+            RdXIdOKuaQqJyJ1VEpuDCfuZgtIdkr7OG1360giXFUIEUDliM9OPiA==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1jy444f9d9stygj4p3w9kh54cqcfr654tvr75tdvee5cxsgtdtc9q3v60ep
+          recipient: age17e89ty6p0fw24daanen57wg8uald9s025t3wwxsw269svwpmgvrshfvfvt
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCWTdCWHhTamI1VHpvUzZ3
-            M2VnV3NFZTcrc2Jzazc0V3NsMDQ4RmtYZ0ZrCmVhV0pweTVLdzBLRnlJZURwNXVT
-            YzN1aHZyTmRqc0dtYjJWekRaODZoR3MKLS0tIHZPV2ppSTVwb2VHWStRY0pKSTZ5
-            MXVFSE1odzRMeW9LQjVQUytBTWhHUDAK+UUowhIQ3w5O4Y/m9Pq41X2l0DZQfzOT
-            itFkXJRnvUmkCxWYRDFJjQ6FpHHaNDqs0BlQZ5QZ+chzcKuUAG+uEg==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBWUFJETUk2TGZTdVJqUTcz
+            MUZvUWhmWGR4SGVxOW8xcy9Pd1A2ZnhPcXpzCnhvL1lPTmZJclJ3OHVqbGtGZFMw
+            VysxdnY5ZzgwUEFiVUxpYStUb3NsTEUKLS0tIHRpS0dpb1ZNMXBiRUhFVVZiSHQ2
+            UTRoTXFjNVFOeE84WXdsT25UQUprbE0K5U8S5xojEgUn8pAgY6X+Njllv/jqm/Qp
+            tqeTbMw+w/afAhRxY80x/mTJdCAxUh4guLTKO6eojHYcFvwT6eZA4w==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age120whqj96g26lsgy4udvgsn8dc9lumh8jeu3a564fx79rjr5lxffqmrljuu
+          recipient: age1hrx8qj02fj2ea6d4g9vqhyj9hl7fppkjqfdx2l37py3h6pdkr95s8n8rvs
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB2MEZxZTI3Y0xWSDdzanRC
-            RytNV2x0UkY0SnRzVnR0eFNvaDRJeUtpZjBjCko2T09qSTJsQm51aW9pR3JUbkRm
-            NWRXODg0L08xdGNLdCtORXA1VWRteTAKLS0tIC90bkZEd2pOYWFCeGg3UW54TWxH
-            Y1liQWVWS0t4WXBROENGNnpDVUpxRVUK57qCQ0l5Gw1ZqM50XSBNwVlXkue3QOT/
-            BPmPFkMNpVIcUDENj+mJAS5GHuEm1MkZcMi/wN9Hp2KE05ZywPR2Zg==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpY1FUZ3RKU080RVNPZFZ6
+            cDExYmhLdlU4K2xWU213MkZtUWY4elVxdlF3Ci9LK0cxV2hKbXZEMEd5dzVCWGVU
+            SjErTmpYbDhmcDlSSENhNnRrN1QrcTgKLS0tIFRlbVlKOW51R3ZiZ2pLd0JXdks0
+            b0FsZ3VETmREVEhqTGI4Vm5KQnZaWjAKXq+8u2Qk84Vt+eDUxzE6sDk4DDm78P7H
+            KVnrZfhAmwP3X7dSuBhW+dK8in8D3jaqRK50d/eHUUWX0NIqniUMKg==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1xjst4frdh0th6q8m7p7u9g5af7ty5jqeum0p6z8a52a9q7st7ewqw8yl9j
+          recipient: age1e7l8dusgmgfzd2cxrrzwepzjxt69hzqj4epee0cs27u6yg4kxcuqm34ncx
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCaGhvbE9EU1dMZitXYlZk
-            NVBEYWxHbzAwQ1FUU2JidjJPZDZLVDZLODI4CjYxaG9OSlVOeGQ5SmlGNWEzNG1n
-            WU9PRVpVRk9rd1BvWDNnMFcrZFNJZDAKLS0tIEUzV0E3OGE5cWM4MjBwTk9Mb3Np
-            cDJQZGNqNXlySjRLcWF4R0V0ZS9DVFEKS0CmXOfJ1qpUF24EJT6F5/6xzR7h593O
-            mLiMdOCeFYWlTtBwrD1dkweAzStiHlzTVEq3w9BFvAsr5x/NbQJUJA==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBZU2R4VVVkWTdqS1dxbDhv
+            K21KeWs2NVo4UTBvNEF6SDRYdE9WUldYUmpRClloR1lBRU9UYkpRSzYxY0NsR2c0
+            WHlXT0MycWJPdHhHaThWUHltdGZYQXcKLS0tIGJuaTEwSnpmMnFGVml4UUs1ZCtT
+            U1V3U2NNN0l4L2JPRHFDOWpWWE9HaVkK/i5m6YFiAR6xtms/pbcDNhKaZreqIpjT
+            8tvnqHz2HDSuCMAjAnZfluvuP1USHvjJQGZpBfreZ/XGhW0oqa7D7w==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age10at8862478urh0eeuwh8hzln6ck78jgwtztgxatwqlzwagg77y5snm4xzg
+          recipient: age1jcx3yajjhghn8qh8za3yeu8nxykzlg3p4nrv03vnfvzl0mzayg2qmg940e
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzOUxYa2xOYlVYd1lWclR1
-            bDJFTEg1SjBhNjhFT0IwY0ZxZFRFTzRUVlhZCmpwL1VBMElZNzV3UkFCV0FWb3Jr
-            SlN2dTNmOFRXeGJVTFgwdjA4SmdSQXMKLS0tIHZOdjFzalRkL2N5eU1iSDkzbHYw
-            NEU3VWxBNE9NZy9hVFJwM0VnQ2RIbjQKc62J04UtVjqiU7p7GueMicdCDRTvM9zY
-            IPOJSwTCatRMWeuBJIsRNkbyOLeSAesQdfAXL5GoAE8mBtBdhJKaLA==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBKNklENW8yZ3VlMytlVHJs
+            dUhDcDI0amdZWlhmN3UzbFJyR2x4RGVOdFNVCmovVzFlYnh6YWxYTnYxVzBNejVT
+            MGFhdjZzU2hnMW42d1RucENGeFdXa28KLS0tIGhIZy8rZ0pFM3o0cDBKTXQzaFNO
+            bG9XNzFGdVNyczRhWjRqQXlxNHFvL1UK8NMj76782tmIdJJ4qIzLicFytNhj6ZMk
+            HIIOJGCrBnqgCtcKTiCrTGRhGbqGzhkId1oJkZkhMFRoU7kdSvwD8Q==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1ezk9x53zt8kcnscdm80jcyf0xq97vndv7jsn3rl8cc0cwm2jmpmq372dzs
+          recipient: age1f7usptjx9rv4rxauasve200gxtdt9jkqhhdqstlf20wvlm7u75rsjfw50m
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB1NkppWjNXRDlsVXZ6b1ND
-            OExFRXVOcXVSWmZXemNoK09EcXBHZ0JMYnd3CjlsaEM4MjdJT1lBZGFCZTNISHZV
-            MjBRTUlTVkZBQitFc1I3ekRLN0RtYzQKLS0tIC9oelk1TTRzeFNpbWQzL0pObXJq
-            eWxHbkF3anVPRFgyQ0kvSlJqQTdLQW8KLfZ+UIzas43ROGO51KKOmy58R2tl3jwh
-            M+1WXB8vIXA7DLQ6vMbzMPMhBnJ4kbZgRtxELg7fzSLQStLvkY+O9A==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzbFU5YWREdFpsK3NScXNU
+            NUFMMml2VEVOQU5pWkIrUjkzM2tZOG9vcTNRCmR6Vzc5OWRQaGdvU1Naam51dXhD
+            ME1yNFJObktNNTA2eXFsNExTL3JNeHMKLS0tIE13L0xYMCt5TE5ac3FEbkxVWmVv
+            V3NCSk9LUCtPZFZCbVNmSjR5QkFKTmMK5qFJXtZCKLjOCg1r+sVQpMKl75GNcrbI
+            Dum/K/3HU03wv5reG51UDsQ1tMrsFDsaFh2fjR+LxLKSGlG7b3Rz4w==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1fxxzpnfse8nd9wz78ht3m0plrmraacf4cpga0pe8fm2tdnqcgy8q7qsyvp
+          recipient: age17jqc66x9yeshfgd9v78mj483r4zzarqdtuxtrkxe4x5mw679gphshd94th
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBWVm5uZU43cFFLcC8wVkZO
-            NmlOMmlocGpwbXFkUFlCMEl5Tkx1QWJIdVRjCnFBTzdWT3NaM0N2eGlCbDV2NUU3
-            Z3FnYktsZ3NHT3Y0b2hOd0xmRjlLMjgKLS0tIFBQVXVDeHkyeVNNek5CSldSMFlY
-            a0Q5bHVlRHUxMWduMCtLRjdnMUw5RG8KDJX8I21+bUpkJ5wnX+kGhsSa8mKqsR25
-            iNdOtVtb2WRxIAgyjR72yp1tLMrop9NkZN68MGvd/LsNM+6simyosQ==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBEWFdCNGpPYU5pSXkzd3lG
+            TGU1WkhuUEhmaDdybzFUbVVaVmVqU0FyQXhBCnRmRngrbXlsTVVMSDV6dkhBS1lD
+            MmNUd0NjTE5ybFEweFhkWXdGbDNwTmcKLS0tIGU5Sk5hM3Y2bUVsS3pTaDZiaTBi
+            S21vU1ZVbjZ1SHE0WStab1VHQUNLRUUKBDW9hwI90Yn+B2mB7LUNTVxFGbwEFSw3
+            LGGqgZdvnN5p6NMigBbJz+kSwOk1gQ/yo86HtRj8Ejllp7P7jRsfmw==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age190htw7prp4vln076dxjx3gxxaq06h0zl0te7cqgpx79vl3lhkaes8suy05
+          recipient: age1px0h5l9zp2dww0m8fncrc82kfdmzplsfv2ltat7sna28xpg09pqqcl3s2k
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBHcmIxZVc4aGRmNEhSY3Iv
-            YXhzLzduWFdzVVlKZTR6WExzcDNtSWQza0FjCmlsZDVJUWpqY0pRSktQeGk2SlAy
-            cjZXL0JCVFRtQXpHNkNIejhyTnVtWjgKLS0tIHBSZ1JyMFBJVWZ3VWFLOUt5OHd6
-            YUI4ODhHc1I2UHVRQ0diSnhsSUhDelEK3hBBX1+Uwe/MusLqmt4oAy7Z6jOU96Cd
-            7zTe8YyLc0/DUDsyuFZ7a68riO9/My+zrFllwtKe/JPmPHLY0+3Pnw==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBaMWdPVkV4WnNHNmU1dTZZ
+            ekVoVTJWY3laQ1ROM1NLUnlZY2FKTnJwNkFFCm8wVWtoNFpxMS91RkxzQWRhOWRs
+            V3k2STdvN1JRdjIrSHVFaFpSYmlmT00KLS0tIExnSmw2anNtdzVGMjRYdzdpcFRq
+            alFrUTJVckpTVEVIcUxTK3pPbWNpUzAKSe3Z9V5u8+om2s+HqUcx6qXIaTmQUgOT
+            zIrU8T0tLOHzdS1SAdh1Yb50yevN+P2+5TORdLjrtigpyzeYc2U/zQ==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1ukpqxzl44mnjpy5r96sfuc5sqzm47u4k8ujjh5qdgy6jvl9uqgpspymqfk
+          recipient: age1ufg390ydrmma849t9xfkxxl5xvdkk6mngnlzhmy7mvuaje8sgcmsmnq6l7
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBZSE53Yy9FOHNpeVFtTmF1
-            UUExbzJlZktxMGR3Ukora3RpbVN2THlyVjNJCnFpWVEyK2U1N1diOWZQWm5Bb1lD
-            djV0U3QxamRJY3BRN3hBTmZ4SVRiV0UKLS0tIFU2Q0o1UTRjaEFaSTRVTm5MVW5T
-            QXdEbVB0Y3YwM3R5dGp5d1oxeUxHNGcKRj5hNLlXtZoT3IwXHTxaReJLu8k133n/
-            ZoCtv470LPL1M/kTjdPc/nWMgYOHDKkO90gr3WILfHg8idkVuCLT2Q==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtWDI1Z2hVRG9ieHkyZnlP
+            SVQ3VHNsSlZxMjdIMUsxQWdIclNQQk5OUWhzCnZSMzFZUGkvYlNSRTJiT1ZMU0h3
+            L0RIWkt4R1F5bUlWNVlQQklKc0tGa3cKLS0tIEJpTXNzZkFUOWp1ZnFocjJEVExa
+            dGlqRDRLd1BDYzYwSWZXaG1ueXhrSzAKdJ8yA+igZKyetNuQdoN2Woi2bl2I3Xj7
+            dDBVAn8bvxx5ZG1eyDXXcHSh76xUp5ZPRlLOFCvRK9oOLWd8FntBmw==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age15kh7akxlx7zn00tey79rq2g8lgs4j5y77rcnyfxrxap8ckfu0a9sqvtdhh
+          recipient: age16j42pdc5dr6wnj7xayhkqdj2rny9u68fcqejs50hqq42scssh4gsnrrnlt
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBQazFqSWpaVGtkNFhPU3A5
-            cE1oVXEvSU5RNnY5NU9mbFhGOFQycVFuL1U4CnNwRnVkYmxCNFZzNVZvM2N5eVN0
-            clNjUWY4RHZxbVNsMFlFSnZKcmI3dm8KLS0tIFBDZTRuRlprdzdVT1ZHejNsNDBJ
-            OUVjclpPSjl0RGtLVlZRSkpFeG02KzAKt0rcJunZppojjijrjbXsztLwRD9pgWRb
-            jYsn7dCvWGFZGVgeyxqfL0jfYNz6dW0yecRE/gbP5hIooxbcPcxfag==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBkb3RrRDNqTGZGYlR1eTls
+            Y2FYQWxncmJBQ1ZiNWFpMTBMUmtlSnJzemhVCk5NTWZRcTJMWkIrTnVsbVAzcndB
+            MVp2NHJSazJjMVN5UXJHOWpnc0dLK1EKLS0tIGJlelUvbEZZZkFKd3BpdWx4VVNH
+            cHJSVmJ4ZWlVTlA3VXpWeE5DNkphcWsKTGpdWU/cE8vC/43lwmnwJDh4IPqHQoVV
+            yjnUdZnPDGyQHwwrydVgun2fdaAKH1zxAut8TZlH9pxD4ir0B69G+g==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1ehkswwz2pqaz4svzh7ela5tdnssl8kn6d4vwwxd6zwg8exfpd43syyrrjp
-    lastmodified: "2026-07-19T02:30:40Z"
-    mac: ENC[AES256_GCM,data:UiL3VMDF6rq4Nr87KspcDx434q3tfNXeb5pwH2O+4ssNQ6xzcYDdzXBnhAY3zLBsqPMKrvHBd4Ot/gEMcq3FMIVe7Q6p9yWKpep66KZ/yWEhAlwIVhD79Oj8VS+1CHKjf25zpRdhZorp04oeFQQd9VfjJB4EE/Q1aVbwTGlpIic=,iv:i/0conaFgFia+wzNTdUL6tlSTw35HTK3Ap1Sr5RGHf8=,tag:ULbz5FllShA/JjlSRdxA0g==,type:str]
+          recipient: age1k7d2du5mejsmv5rzavm4xwgpthqvcfsehduquv28nzs53zppa3kqngfxq2
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBaZ0tVT09Sd1hXVHZPd0tD
+            YmZKaStnUXg3cERMTjRmOVh2RmxFbG1FZ0hJCjNMWWJmaUFqTURoL2NvRnJIdzNW
+            OWFmSFAxWVRrdit6S2lpaFdERGNrOWcKLS0tIEJlVVFBSE5PK3k0dTRTRlZYMGZt
+            elcxVlltUnJVd256NHQ4TithUmFnSkkKkbFSRRktuO+tNxlfIEuJ27C7LWalHJMb
+            aCnjE9301XMceGB8SstPtGi5SJRSHD4WrJleeJbKXYMronfvWnYDSg==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age16kqfmvz4e23hmdlqresnyw69ej604s320mmd49h4hm3fhqchtgyqrws0k2
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBEa3E2ek9BcHZRRUR1cUpK
+            UEFERzc1ZEtrYjc4bEdEeDRnSDNkWHV6elhFCjljdnJLa2syR0UzYTRveGhPYVk1
+            cGNnWkNMNUVwbXFrOUZ1aE5UelFyMGsKLS0tIFNyQ29ieUpReW96OGhJaE4yU2Ni
+            Y3VWNUFYTU5LdHlmd0krK0NyQk9mMVEKfh7I/9+V9+0DLkzTf6n4sBKs+oZlMlTx
+            ar203b95cR/jjsUekF0NoZjj6MW1IZSV7BkaDoizVwrAxh7WS0vwqQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1arhf2q45zw6wf2uevju4savp575x3m2tfvved5zzq3ay92ynua9s3cm92c
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtSUcxeE5pM3NZVHlhcGNt
+            d1EwODM3Wm5BOGNybkNMdnM0SnJmTG5ScEhNCk5yZHhieVN4QnNPMkxzbUZ3SS9G
+            aG5WVENIbVBYRGI5ZzQ3QndUTG12NjgKLS0tIFF6ZFp5YWJ6UzlqMWRsb3pTS3l0
+            ODRZZG9pRkNxL1Mxa1dwUG9vdkJZZTgKYrjkSkjNQCU2wMIuZMvJnd/regVplzMi
+            3kPGRBMWzO1t4CSFtf2PMqv5AHw754I+vVNs5CpTXBuxVUcQDcGJCA==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age19mn8zrxl8zpps9yvrh4euquvygpp4fp8queg7xc6qhtnl4ng8c9qx02qwn
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBGNHY0Wm9oNk1BWFBiYTRm
+            OXBxNU9ETDNyTEhyMnBxZFRnZmFjVGVHN0RjCkdPNWpvRkVMTCtWdDhlR3Q0U3Nw
+            QUh6KzBVMU1ONXh2TTYrd0FaWlhCU28KLS0tIEhsaGxvcGFtaVF5T1NIc1NUOFBt
+            d2NGeW9YNVVxdUpYbFRoVnhUM2VTUGsK4adI9pgC2PipcAY4zXMRf9hPv5kilTvc
+            BsUNz0Qr4YdRfVfrPlPBzMCPOTDofTp6qBv+Gc8FE4hvwxtbjIcJ3A==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1jlltcv5jcnm40z5k0q6hv053k2rqpqvemtuecdwn527uw8uqz4es3x7m68
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBBT25YN3BtMVZrVnhDazhO
+            OXpzOEd0Wk5KUnZ4a2JjRGI3U0RsMExXN1FZClM3UFoyeUIzY3FVNnlkTU1NSCtn
+            dXhNb3c4ZFlMTU5VTFc3blBUV0c5MkkKLS0tIHUzUzliL1NEUSt3cWx2d0tjRHcv
+            a1Nmbm1MZEptQjJuZ2ROWGUzN01zbDQKy3dPKE5oYwsTwE2vnhUi3auqJ/KBOBPX
+            vSKOROUuS/uEfsdo8NoVxuZ2RaJHetrbHAYPHFHOMgpe/X72pCcQNQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1ug787sgt6st6k82fgkrug2lzltw4qsukrrqqs3w27ewwqj8rg4hsxcmylz
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA2Q24xSkJaVDVUZlBWcW11
+            cWFOdjhXZEtuNkJtaUhQTEN3QkVUQnRRRjBZCnY4V1lCOTBNM3Mrc09naWNTQndn
+            VXU2ZWt5Zi9CbjBFa3YrejFHM041VFEKLS0tIHd5L0hRN00wdmdsSUhkdFpTcUNS
+            YUNiUGhVR2M2clFrOUkxNW5idkR2cnMKXO02RJh4ew22tf5GWH4lNdLlhf4bWyef
+            +hW9R4TGCJOnIO1xSGpBX0wJsM3oiW4qy/1tgfQw2ejVih5qUr7JRg==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1zhfyuzlq40reuqlr34gf77852nhs3t6mqfzrqmas8z6sxk7tcfhsungrm0
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA1SnhhMEpwOS9vUWVuT0Iz
+            bWFCUzE4djFyUzN0alRvOG94bGJldUhlb1ZnCkxHd1pUU3B4b0ZhRklnczUyRzBR
+            djF1bS9scjBlQXJEbmtiUFgzTndKQVEKLS0tIDRpUnhWYTM2U3lLcWZyVFkwcVNL
+            NFpldXQraURraWZNdUNqZFNwVFY0WlEKhV8IZYbBXKGb0x+2E5pJkoMavH2ox4qp
+            dK/XRlBpEG0SCUkKZ5sDegzz/HyqbxRF26jC3IOL1uR8A5nsnwC2Cw==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1k73g8x47hs93wcv7qh92n3htz8pl295g49hyvlrf3570mts0hgys5g04d6
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBEWmIvVG1GWEZmbnpFU252
+            bFhOajA2dnJXNlFGMmF0TDRuR1YrYmZqc0hnCk85WGFUMGZXdElWU2tvdFV3eE1v
+            czEyTHBkZXFnSi9MVWFQVHJabEpUb1UKLS0tIC9TNGZiQ0xYR1dQWHl6NTAxbzlD
+            YmNhQkFVZTZidWFtbURqYnY2eGMxZ2sKaUPhe5mQ4QSyxuQMqLNI1jqfkCUBnBWc
+            HR5ck3H80/H0pMwzP5uaBnN/hD5L4CT2FcZBgUygbyNz4G3VgbjaMA==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1fefy6dk8zn5c3edwmrs9vwx79quftnt784m628t9e34q3ft3cehqz8u72r
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlU3BybGcyckNaT2dQR0ZO
+            dDVXa2NtNGFTS1RqZ0ViLzVJSk5PbWdYU3lVCkRZNTJ4MytYYVpON0JBQTh4SWRY
+            ay9xdkViektHNGRuSFNSeVoyMFdrNE0KLS0tIGJ1QW5RUjhWR2NlclR2dnh4SUQ5
+            SlJEWHhBTFI5Rm1rZVFjTGZlUWhZMGcKReNE3l+U35iutlQ07AZ+3fOFF4YdVbdx
+            bR/Sz3NqpqmZqBEmgjUjjjQI4h4Xturv4tT8/JUzEmVnEyDsqCbhHQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age16y0vfts5v2k20e2rj23qa5lc5gm96gm64uwsqsr0y688xl0ne46qcfr0sm
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBTMjhleFpqRGRBMGIrVmU0
+            aXcrclh1TmtIV1JZSlNWRXRRc2RCYThyUVMwCmZOdXptWnhvajYxeERlOEJFVTU4
+            WTY0R2NZSXplMDNNSzZ6eCtEeTN1NjgKLS0tIFIvYmY3VHM4T1RTZzljR2RnV0ND
+            Z0ZhY2JpL0psb0RJcEJNN3FHUHJVQlEKJdoXKdvm6fGA+C21lsxY4Zq+VVPt/6k4
+            vH0IirsPd9Cg33+tBzrySwkF+GVNtYLtekup2L61pFQ6/Y/necfQ2A==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1tm3zj5lp3elw2j832az4nj9xxmhqd66ag3cqcv3vskvmd7qdmqmsdpdcn0
+    lastmodified: "2026-07-30T07:49:07Z"
+    mac: ENC[AES256_GCM,data:D5Y+zyLvs3gz8BWS3+lrra/tc1TsDIk7FykxSPiz0Er1jUB5LOe4IKircytMpwGqdLcVhUKgXYdRA+C0KAXaI9KpQp5qKfRDvX2jX24jveVNFPgbvxA2LidYasVMzA7ayTU0I+oirPcEtj+5VH/ahSjDz9YtarTDeHMpXvBZMLU=,iv:KcIGEs+61yS8Ul734fqsrC95iA82wIinf72DE2bLk/A=,tag:RzL48FqVcMro2W6VAgIxzQ==,type:str]
     unencrypted_suffix: _unencrypted
-    version: 3.13.1
+    version: 3.13.3

secrets/docker.keytab

@@ -0,0 +1,26 @@
+{
+	"data": "ENC[AES256_GCM,data://9IEHIVCfHjyMNao5sCu2zNlZ/CaW+JyxVpGpD/vab2qvURunCUY7eMfSOyvOx/2WPXnWWlkoVJPCR1ec/yUg09EaSMfxrvqlu4UJI3Sxvu9xNuDszMwMMD/sCulJDiMWFNLp8qaYt7UGzexp4+GlGiqWDxk3ZEu/iLmSApzBrpciTF0lfehT4qblDovo9QXG2KDWFhCt2SwEKmHJ61Yl3pVAQnPLyTWaNhwWD/mYL76mIiDVKq7DJlvi9MBxzi3aYh/ttuHgRCvnCL0C9oUvOyT2cljwra0LXuOrum7FhPIXXboA7WTEbTHJm1LB5yLfxDrnWCrGxQzFQAwNixVHIcjuvjjvA/LifTvbj5FYM8x7an+DwXPfPhruFrDew1paAWsEGNNYXSmAlju2QLI/OwLHFFLuDyLnBKQ6RLtZbCEAOUKf2h4iZj7nH86eb/aGU=,iv:rj76+MJBCpiYyx2Ogut5UxJj3Gn+bygvu2mtuY5hFLA=,tag:yQmTvWVu8ZLug/7fo6RnwA==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqcURBS2tIMGl1aWxLMHFQ\nS3ZGVTE0cnYzTmpnQ0daL1F3QnlpemRCMmtjClJiZzIrc2syN29sRXVoaXlPRUNF\nakw4RndmbEduTFg5ZVRKUTVwRWpGRjgKLS0tIHZ5ZFlyODlGWTJoNGpXR3RhY0ZH\nOGpPdDZQVmt6UWZXbHkxQTBoeW1JencKbsfH1V1lUj8mmHyLNj36VaRDgaBojcDU\ndoQWmSEXxjticJqdadbVKb3UABpvzAZxASCy81sa3wH0gT+7zLaNyQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBrbFdaMmRjcHgyV3Y0eWZL\neG1uMEtpQVUxQmNTU0Z3aC95Zi9uQlgvMEhRCmJiVlRTR2NocGlnbVU1UmlLVVA2\neERiMXpiQlVPNVhRU09XVGxrY0Ixa2sKLS0tIFRuOHdoelJxOXNRRHBJNnlhSE9j\nUUZHZmQzOVFwRmhFV3pvdnpRMTMraGcKRHBuSUpbHaEzH2tuSBE5MsLJDCuH3vUx\nO0jnDldCWkCw7Wvr/tQAkaDI8axZcYVDUkCEk+xqAdxDozLCPhEO6g==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age17e89ty6p0fw24daanen57wg8uald9s025t3wwxsw269svwpmgvrshfvfvt"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBZMW5taXh2QkJkT0JjaVpq\nQlBjVFpFYUhXTHhOT3prbFcvUFB0YnRGUzMwCjhHT01lY3dPWDE2dDZWZnJza1hN\nS1AvZWIvdjZoYmRjWlliK1hiOEdrT00KLS0tIDljWWY0NlQveS9VR2hOSUNyTUtH\nK2gvbEVibmZSdktPemdEQ2p5U0Y4d2MKKitoTi2vbxJ41IoWMlj4vO91Ahpj0hHP\nrKCPyx7ws/IUMmKGyvDLpZ3pYqHD9jl5pLfB05Hh4Emhv4lA1qtwwQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age17jqc66x9yeshfgd9v78mj483r4zzarqdtuxtrkxe4x5mw679gphshd94th"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA3K2dVV1BHbDk2Z3FhNmdV\nZEN2Um94K0pma1k4b1V5ZUJxQ1hWU1grZjJNCi9iRVVqOVpEMmtBUi80NThlYldY\nTUtZOVErT2VSWk43NndpVzBlL1lQaTgKLS0tIEpCM3Q4NjM3N1lpUE56N04rTXN0\nZkZ6TkV1TU9OV3dpc25RNWRpVnprM00KItUzKBdShakOfX8Sr+k906nsvYPl8QLb\nge//1GA+ukGsaS9rcChOY89vFdm61JDmj1jXSJ0CN4wLMW9/eblZRw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1arhf2q45zw6wf2uevju4savp575x3m2tfvved5zzq3ay92ynua9s3cm92c"
+			}
+		],
+		"lastmodified": "2026-07-28T01:44:28Z",
+		"mac": "ENC[AES256_GCM,data:efFXIqbauOURR7lrVpK7kqRIPgYjgWfenBYoX7mUrQ/thFc+ApcAx58Fi1zg4biwIs7NarJAgDqAxZi+yKb2Sll8H/wlsEjWDU4iQlLJdIQw7wey9eDW8pgBLd+6E7FXrgn1Vh49dS5GXlC6clAYk1lCiB4NvfzPDy5Ktpl+Chs=,iv:+zCqj5I1MLJfRRiIrqgocYB49PZnlV45PUTH4gYlfrQ=,tag:WxY1sF4kFOTEzbSFcfJFbQ==,type:str]",
+		"version": "3.13.2"
+	}
+}

secrets/gui.yaml

@@ -3,31 +3,49 @@ sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBrWFpRSURBR0gvRzVIMElk
-            ZlJGZlJvc3lFOVJIZ29YbFp3akFCNG42TWkwCjhNM0J6cjIwRXBzc3VWNVpZSGdL
-            Q1M1bm90OE1tTG9GbUxvS1dvRkZ0UGsKLS0tIE43L1dnbWhQOUhhYjg5bEIvZkVD
-            Zkh1NDhvZjlDc2c0cUZUYVRLdEozS2sKU/r6JnEnUs2WPj/J724B+lgiV84iteZa
-            uMlhgnwYJFLkH7ZyydQqjYcHL7xEInr0taYJN+M0nZIsZTvzAEi7iw==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzTFFlZHdGUzk0b1Zva1U5
+            V1UwREEwS05icWxYNEdKTE8rQ3lJMjM5YXdzCkw4OE4xWVUzVWZMaXg5OFo1UG8z
+            WkNwK20yb09rV2VVSENwNWUvTmhJNk0KLS0tIGVPWUhFS2RDcTNjY2JLaWxvcTZt
+            Z2RscURQdDVCMUdiVng2YWRMSlEvVVEKmyd3re6AaKn4gBjoT0x3e/zJznvJFYKn
+            ugKu3EsUX+gbailPmY1ss9+MVtpJFGZa2FiM0x1wSMKm6UJH0aPhVA==
             -----END AGE ENCRYPTED FILE-----
           recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBXZmYrVTZxWW1QKzhLWThX
-            UFAwSEhId24yMitmVk1kT215OGdqbGp4akFjCjRzN2dkTURXS0wzbzhYL0YxRW41
-            TWJ3UExXaHNhSUxaYkVsMFNCekZHZDgKLS0tIGQrSWNzalhCbGJZdkxvT1N5ZWlo
-            a0l0Nk9DY1BKYU9ReWovaHJ0Z2NyWGcKFoIYS1M4EbR6H6QG3Wjv2ZdX3r2W8zKp
-            S9f578O5ZLh2OWaawcSb0oecZJykT9pgudVcuKRunzZN7NQvFxBRnQ==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtK2tud3pWSmd2aC95ZkV4
+            RkVvZXNrK09ZVmZsYWhqZ3JlaXBCd1NRWGhzCk5lelhSN2N6N2VhWEVXUjhLTjZH
+            V2VlMm5XdUtuK2d0MjIyRi9xeTh2ZXcKLS0tIDh5Rk1UT0dWblBkUXYzU3YzVGkw
+            OFk0bkJ5RXZpWE4rK05QUHlLQktYSmsK/HsVEIhBEIo3qqVWdUJEWnHZiKB3uHVH
+            R+nJGuXa2B/oUoxEwMP2YBHwwjLLiJCTYy+aQtiPdTrVq0YJ0HmC7w==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age190htw7prp4vln076dxjx3gxxaq06h0zl0te7cqgpx79vl3lhkaes8suy05
+          recipient: age1rrxqea6q6pn39sw8y5te63h2py8jgjl9v0jyper86w3ggtn67upqg3ah39
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlWnpPUk10YW82TVRzbk80
-            WHJqbXVVSUFrSTVjMEdqUTdSQWwvdG1TcW1nClQ5T0E0akFtSlFGdC9WaU1LbGkw
-            allOSjJ2SjQ0MkVMcVNtdzN3cW1hVzgKLS0tIERlQ2l3NitPQndERTYrNVA3ajF0
-            bCtnYzhHcnZkalRNK1BHbjdIS2JLNmcK5RwFzeaK1KafO4cAtdFh5Tnz1lpZbj1Q
-            aeMmTGMkxJYVGzXKS6SRspVT3MvY4Fvay8B0MezjG5Y5HKNIv22Vog==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpVVVxWE1nUDBLTVFUaGJJ
+            Vm9EUldwRGcvbXhuT3JPd3N0WXo2S0gwRnh3CktabkdaSndaZUNSeUJGRzFKcjlH
+            b0x0SFdEQ0VqNWdQcEkxb0drVVJNcVUKLS0tICtyVGRqUmFtRHV1SlpXSVd3N2VN
+            elQrVFdhWTJ1R2pJbjdYa2w4NmRmc2sKJHqLYdNQJcna71KNhGF80iS1hIYG1U1w
+            I2kihepJsrmYr76ld9k+u1ZfnuIuJ1ozYsZothE+dr4pV0k8s6wkpg==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1ehkswwz2pqaz4svzh7ela5tdnssl8kn6d4vwwxd6zwg8exfpd43syyrrjp
+          recipient: age1adur9g330gua4l6ndk8cqjg35qc8yxwgme6wrl2hpylcc7vxm38q05ejuy
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBSWXJxUEk5Mkp5eTZXamFR
+            SXZ4L1JTSGNaQjFiVXFGaEdvWkV2ZzBlVzJJCmd4NmUzZEdCbi9vdWdkVGZRL2Qv
+            cnVXa05xd2gzaXh1SnlMZmtueGpZMHMKLS0tIFowdnhFVGFheURQU1V2M0ZuM1Y0
+            NTJFWXBEYUxmOU9ROTkxWGhYUmlqMHMK3pexvc16BLKjh2meqtNm3M1zyLQ3eEsz
+            7C5WkdcSpCkW1lPDGtW7pEdAIL15StD4x7ut4MkSk0BjG1S+RpDbzA==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1hrx8qj02fj2ea6d4g9vqhyj9hl7fppkjqfdx2l37py3h6pdkr95s8n8rvs
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBkR0o0SFh1L2xjZ1RjSC9K
+            ZnFyb1lJbnlMbENYN0VjSVQyU1F6RDBrL2hjCnRwTUp6Y1hJWldVeFdQZSttZ1Vw
+            L0dCS0ZROFArb0ppVzB5WmV4bWI5alEKLS0tIDh4VDV2TFhhaUp4L09jYm52UCsr
+            NGh5a3VMY2ZMZVBQbmRHeWsrQnZVWDQKR1UeSZ/EzZEXMqyjB1I2SHELv8Ha/tmI
+            kJKs2WT1RtDhAiTrbty3f4oVrXWSYKZr40kNiP/RLbUcH1s65ys/tQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age19mn8zrxl8zpps9yvrh4euquvygpp4fp8queg7xc6qhtnl4ng8c9qx02qwn
     lastmodified: "2026-07-22T01:15:21Z"
     mac: ENC[AES256_GCM,data:dC/oIqMUHkOh3AocOwP7Gc6XGH3L+nTqJfhFNts1DNbRXsopNIxVBtIz2pEhwnWSQrqPisDLmPHFBwRpGVn01u8w8IU1FKbAKC0J2nJXF8ozpInbjzDOmehqPWZG7yaKoq8cwAnp5XOk+IVO4l6tPxLxkExU5fT2ALuMq+sgOko=,iv:jaVyArpf6zMCFa6J9X1aQMGrmFq+W2CPZdWO6vVW68c=,tag:S+qF8/FkgHc4uW0e4ICmSQ==,type:str]
     unencrypted_suffix: _unencrypted

secrets/ha-corosync-authkey

@@ -0,0 +1,22 @@
+{
+	"data": "ENC[AES256_GCM,data:JwjmYg0qzoer+8/jv7KOfK/BxmpObHOn04GNsUFQd6hSFBWbQlRbODfluL54hnWQ4gsS9MHgwWh8nrLciBhye05kRQCqADB7Crm0CZYubNb65WzM/devh14jmerc3MYIp1M3VmDisML3x5IqhJkFMSqKM/VaNAC3f0otcVR8TTgZw/fJyvPlfqpPTjikGmo5xg++Yk7Cy8A1Dj70kYk10+EQjQ78jf4k/agLoaS+YvMmKXFk4EljtHg8Fe5H6Rn9nfMSSKGTZeAH3Riix2e+fIH+nWEZiPHC0UlPjJrB3SeBqqGRSUUJshVKHFIdKI1Tq2Ea+GDWrAyIRI0qO8e7WQ==,iv:mr39NxbZuYUDHDw0e+fJDshbt9R1hLgVqkUxUVX/+l0=,tag:u31xZRPfvH5j3Sw5U8/nqg==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBtVW5ENXlkUW83elc3ZnhE\nOEZ4MWIvQWZ4aXhuUmZGYXZNQnhJemsvOWlVCjIwNmFjS3pJOWEwRnhBOGNRamlM\ncXZid1RNYVBXOFZpMlpnU3ZnVE1scnMKLS0tIGFhWFZFd2JPTFNrV1VHSDVKVHRK\nbmhoeFh6YlUySU1ZRVhHbjZnM1IxMFkKo7aHkz2pEeV64m+OEkBZ2V1e+PUzoChu\nUc/Mnh37dNXSSJtg2KnocHdyzDGi1yQbA72xKTxx6QjYJWrAC/jurg==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBReWRLb09reXUxS0YyMUVV\nQlR2bEdYY08rK0RoR2pIelpLVEtYL0pqNUVNCklRaDNoSjBWT20xbk1UdmNqWHNt\nR3JoSlVwODVMUVBzMERUNktHMVViZm8KLS0tIHc0SXRIS1IreDF1VCthb0FBR0Na\ncGFRWTROUHF3clFtTmY1azEwNUpPNzQKsgCND/BZcMTgBTAcnHunQcT6LG1jNrtO\n+W7Yx7bFtFBajWnRYiNpUZPibQJlv5SE9os47WDH1gs86xftgV+uyA==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1k73g8x47hs93wcv7qh92n3htz8pl295g49hyvlrf3570mts0hgys5g04d6"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBGbllNTlhxNVVkd01GSUNi\nR0lxQWZoRXI5NWxoTExRUnBSb2FPR1BONnpzCkxCN3pNOXVrTW5GR2J0WFhZUE9r\ncm1QTThINDVVVlZEalJiS1RXcHJRS28KLS0tIHV6aGh5QjB0M1VPWDVMT1k3cTBh\nNTNGY25NV0tWSUl3UHlJSExFQVdpVDQK3ARj8xhFRYU6oqYxNQ5+Ryza86ALNUwX\n7yK/8ATnquYC8/ZIYUbgTPxzsocmXX9lVT0+ktIALqjtG8PgNTlOow==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1fefy6dk8zn5c3edwmrs9vwx79quftnt784m628t9e34q3ft3cehqz8u72r"
+			}
+		],
+		"lastmodified": "2026-07-28T16:04:51Z",
+		"mac": "ENC[AES256_GCM,data:9X0dkAEGJiug16LDy/8//QOkHITTzt4zwTKiIU13tRgSRXRpt/7b27+3eDauscXDMamg5wbYo1YF0+VwLl21Ip4icnnwrZBHd6HWleP30HTgef8rmo21SstshnclZz6RH8SEGVDO/vjrMDChaZ3A2WD+nbcomw47DpK3cG3kBIk=,iv:G7CScSD5Z1Z9WMEMydyeGK/RD4W43xA0PlcpmTCxLOc=,tag:DZmby/xkxpinoJztZZRWwA==,type:str]",
+		"version": "3.13.3"
+	}
+}

secrets/ha-docker-1.keytab

@@ -0,0 +1,18 @@
+{
+	"data": "ENC[AES256_GCM,data:81JCCVaOeEYNyqTT3vXkFDDV1oSAlOrElGmvN+1Jy+U+dF6EaCSeFYT0U2i2BvUu9VAYEiY6NRAXwWUgZXeQXsI65eziB6d/8NKTr7UWb0eQxvhHbthgzxoCfdCvofZH49DdGuCEl8kU6hppSeM+wnDIIYvEgWljO4JQJr4/qnQRegMqJ33564+ZvhiYqrbfojcBYpTjVBzh+4aitqZEAYoFx4xhFAtdBfmAA1W6FwDvZLrX09bbdFT5jOqnSSkPunvTHiyWtyAfLgaNzG656F1U+3eRDv4eZQYOaLXXo9H4BaBMC5jyJFV1rDgl5s3diCuQggSyDbWUnwSS3Prcixj3dkrF8h8heNk/LDV5lGBtGEV3BQsEAlCPl01PIe3O5McfsRaR8IqwD7wQQ8ULyA56fHHAYJR1xe9bNGgdLryhqLDBFWi06Ztidi1MQXFLnNFJxoIhvANIAmt//TBWimkHnXidkg==,iv:WNChOcSG+QiZOMUi8jpb2gmOCLonM3zK7vcZCrXt4Yg=,tag:zq6Zvf3xu4kofaCechUpcg==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAxMzVHK0tOazNoazU0RWZF\nT1h2N01NNktHRjVMQ0pEOWR4RDIxNVlQTWlZCkV2a2pQS0o0VFZWN1lyaklLWllp\nZXJvZEt6Zng1Q09xQTFkNnVtTDNNVDQKLS0tIFhnNW1sY09ZcWpVcGdmM1hrK0o3\nZ3VscjBXMVFEa0xtbVlZM0lMN1dHS2sKcYtCKhw6D1ax3Isf5Vk93cDteUEjx79j\n1fheqgOjytY3W9t8U2NOEpUP1hT7zWYswnaq+agm8nfEjf1fbwR9MQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA4K3VSL1NrSm9rMm5WNTk1\nVEpudHhJUkJUeWxieEtKSUdCL2c1YkNHWVdNCk9EeGNoWHdLOVNUR2dRY2YrMVlJ\nblliN08yQW1xdXN5VTRjbm9vZUxZaDgKLS0tICtLaldjemJHSkZzY2R1MHlySEsy\ncXJ6UGdZMi9hTnNjRHRTVW5UMlNMQkkKWhLTte9gTpppGCmA0lf/FEYu5b/ZaGYT\njn9j9qj3Lets0gNj9qBVaHUkCoJ2TAGORdkhnLEdY/Tm/J1w3XfjNQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age16y0vfts5v2k20e2rj23qa5lc5gm96gm64uwsqsr0y688xl0ne46qcfr0sm"
+			}
+		],
+		"lastmodified": "2026-07-30T09:34:38Z",
+		"mac": "ENC[AES256_GCM,data:oC5OPZyZ4kEh0A8Mmwoi5oZ3+fBNvEDN3A+o3n099RdPREn6mcH5QC+XD9BXvWVxp9BzQEwRBmExlyZBEoRuwrB6DQy5Fn8TneEjQoCvZrudpbXIB66/EvORk1utpUsbAov3wn9A8tXUDAUJaRsY93/Pe1mTc8KzIOGv/QTMR9w=,iv:+p87aL7dKsbyAfCWxc0pecVB36yUUa+ltfzQZc4oovk=,tag:tNRRC056bqMToaHz1UrqQQ==,type:str]",
+		"version": "3.13.3"
+	}
+}

secrets/ha-docker-2.keytab

@@ -0,0 +1,18 @@
+{
+	"data": "ENC[AES256_GCM,data:6Is5g/gqFdQ9aTE6dpe80g7kSgDbhRr3yIwffv6tT5CLqsQLA6i+V5XPAqqhH0zbpXnT7k5Rc2tA2880MDa0eVoI+x7qDnhadfLKVgErWZNwQ4Nz9ukovf+lDfoKXn9AWNFxbiBckpCoxNOms3zMv6kqf1gbEwV7eRIoiq/i2xypke4nOJSmRH22dqFUldfQOOUL1D0H6RFQpNK+5O/Okb7URxIzdUgmq6/9zIsZTOlX5j1V7kzpx8U4P+YPyoPoRSLTOxpK/5gh+Gx1BQbXVTf8z5lm42tJxuQAt5kXqu0Tu8aXZzUUcMKf1oGVbo4TwRaQN+9tFgkhegVMSS/l2don3X3vWPimBcYHTfXfvvCh3krH3hoSmej8es2jCG8AesObDEmCyMNu9hdqhGGdCWspakrXVEuefCJ2Tq8fJfOn5XQhh4AX1wAf04Us0FJO4NjByNrgW8Bo1344wocAStxBxuD3rw==,iv:kkk5muigMC6iTIiTHKwXFreCuJGl7CWmwp1W7ILmq7U=,tag:W49PPiOISdFjk54wroD8ZQ==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBQN0NWRllWaEtPdTdlOHFz\nUXJBbG1IRXlPbnNzMEJhT0FuazJLYVZHWUdFCnJXdUtvV2RvUU05eDBaaVdxSlBw\nUVh1azM0T2dFZlpMMFhsU2tWbm4vSVUKLS0tIGNlUXMrbUlDYWpiRTQzV2svcXJH\nd1RIcmpGbkYvSlZwYkwxanBZajVTMUEKt4HCEEPjsSDKvp6XuSSrQjVXFQLQHwk0\n1Fi/HrkhhdkIO1f4DyTOOznvK5bc+Z4JKT5lrOkKQln92uAho2ECiw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBock0vOGVLMC9HZ0NYckxr\nZWRwK0NhbkVaV1FVVndDNmRoNWhGVXlUOEdjCk50NFVtdmdxbEFuZE92YU1IUDlN\nbVJ6QnN1TEk5c1VmWDQwNXJReFdCSXMKLS0tIEl6TW1iV1NvTk5OeUkyOTRtT0ZZ\nR3NsV1lwa00rdHdTRUkwbzdrc1VaVkkK2ioVnzacNrQD6cpNOomKz9WfRRq+B3oK\nnabokq5rEOoNsSFNip5TBeDjo/34kOTXZCKXpFYwmBSoHCrkdFHvYg==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1tm3zj5lp3elw2j832az4nj9xxmhqd66ag3cqcv3vskvmd7qdmqmsdpdcn0"
+			}
+		],
+		"lastmodified": "2026-07-30T09:34:40Z",
+		"mac": "ENC[AES256_GCM,data:QOvDbiPiQBPYBGg3BzJNZzLBv//UccDfOnoOVqnpdskOpPw88uQOcpK0mcF/unW8o+B0AJe4wzr8/XhlhtlLSRi6buES2uZr8pjgCqrgFMCUX8WP+4rxiSq9DkZtmLO1XBtBtjJy37PgFr8bwUw1p8fNdhnOEJBYR75MDC8JG38=,iv:YCCfUyncprAkIbvxWwMGGZZywNHLTrr5bYjBBdQp2OI=,tag:mHyHw11ok4jm79iYn6L74Q==,type:str]",
+		"version": "3.13.3"
+	}
+}

secrets/ha-server-1.keytab

@@ -0,0 +1,19 @@
+{
+	"data": "ENC[AES256_GCM,data:VpxnzrdX5FY2gfDcZpqg1f2wqL6mAawcrdE5A9A3fQOKr4BWXmCT/hjQEtt8qG+yVOTApdG+vF8SKDj1AKZ25KsZ253WS7W5C4j8oiT/xHo0CtvVani4fZqN60lB/9381h7aUZ+lcBMPaQcNn35zoQqYthuCGrC9PH1qQgD2VVHr0v8J6kceXKp0KTJldtDsQxky6ROC9Zyc44wwkrFPgPss4/yGaRWWqiojDvK5fK8238hmR8HyfD6Tf5KhgbqCsSGS2g6yt1muUhmegaZwtpi/KpoqBmf1XFaObuHGRPKvblq4Fa0x/sSjpPogBZyNuvRKIwRhla0FkKOH1bX4gC9bzOlgiUUfVcRJT6Nr9jocYuhIv9wvIT4TujGbgHyorYaDSQLFPJoJEUa3fgpGq+AC6p1DJJE3b/wqUSngNbdOtAPE/imaEuprOfnbS7cRx+Ti/Yu+ZYZuAlDtLkSVdXi1hQ4fLQ==,iv:rq/BzePXa/w/Gqewz8JfM/NdU+x4ShiH1OuQT7wRyCQ=,tag:IcO3ddoj4M57CkndHEmNkQ==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBRdWFEUlRJMlZId2Yvc29F\nNnkwREkwQkllY25vZnRjV3Nob3BvNE1Zd21NCm56UVg5YUFGbEc2ak5MakxDbCs2\nTFVsRFhjVlRwMXdUbGpMKzQ1N2hBUUEKLS0tIEhmdm9hZEJqUEhRN0dsSk80bDY2\nY1JpajNOVFpEejhibjdKZlNHVjE1bGcKycyDfEBZ1WYc4EfAK2y5x/nKRqq7mnb4\nDlpR1Som4bSt7+B+OCZa48mC0Zv05HbP8PnoZdCe83swGNljvRONcQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB0SGFVbXYycTE3amR3ZVhi\nVFJHVVhWNWVQQlJKZUJvZ2p4ditqdnYrWnd3ClZaaUVLUXFKaWlDdDQ4QW5SQUZY\nbG05c0RGNnZUenI1QTBlemVjT0szRncKLS0tIHBWTmNpd2FjWHc3MmR3cWt4SCtH\nWS8xZnVON1lGZVc4YzZFRmRBamdSVlUKdlQTlwiExTUVsiY05MXFG2/IQt1bZwKU\nlFDnuy6YCQzawBLQZuSUAp7WSGedupexlZKQKNUzPf+dis26XEYZoA==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1k73g8x47hs93wcv7qh92n3htz8pl295g49hyvlrf3570mts0hgys5g04d6"
+			}
+		],
+		"lastmodified": "2026-07-28T11:53:06Z",
+		"mac": "ENC[AES256_GCM,data:PMsPSffQkxRmqT6HwFezIoT4WKJ9WDlAcflWynsFLtzbqVTREN0YGOJgMwLd0yBR2sbGBWogG5xAuKjO16aiWUVpCFPRvP97um351679ZoXIlrOL+GlFn4NKwoLH9/eCp8BteB9mv5huhEEN631lqCr+jtYO6yS0ULk6QS4+7/c=,iv:oYWV4J1JUuGryvqntVXkj/HOzRDRr9E2C1RKNvr2bT4=,tag:e4p+I40y1LrgdlK9tLRicA==,type:str]",
+		"unencrypted_suffix": "_unencrypted",
+		"version": "3.13.3"
+	}
+}

secrets/ha-server-2.keytab

@@ -0,0 +1,19 @@
+{
+	"data": "ENC[AES256_GCM,data:Ea5AGwloFMyRgmQhJaDNTW19mpDvx0+dSc3ibENEXEniEIBV4Wv135mAwE6jQPbN8wF6f5ki3B5mDXHOMuhDQEqUXg6jcs4uEm2nwz7wAKYXEX4T8p0gUj7FPISiSQrw8O3jwzt4qF7AVcPsNhMtZLgrx9ssMtVmGct5do+E61Y7dFe0XbpJLynfzeiMKYvaBngTbHwQjv1mn9AMpX98apsp3tyzg8avLDR+WXRcMusds2mdov0jCoKuWPLG/srhMwjKOp1Z1Tu+aZCr9lHTT76mytpGIWGSbrP5l3UTp3oPLmy87Kwi/FJStZYdYikMnvmSo5qovePiYsLKVD74dS+d3oFGARyW4TILd9OQdXEjzdDRak5HcPv2/HhR638kvukVMdEdH0hpeJcqcV0h+BoLyIHe1e037iF1ZkCjuXE+A8LtlzRR0wqP202uzBIyg21ca4X5bRiHkkAOX4P3riaEcMgKfw==,iv:IXq4sHHsjnK6maVd3RRVZzhnxx1hOnxfsvYX8IKLn+4=,tag:jRZinAVLH8nGVf3gE4aSKA==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSByOTkrVVd0TXlBRzdkTktO\nalU3WlVOb2ltc1k5RG5sRE9EN2M2WUlnQVRnClFGZFYvSHdpVlhtNXExSXZMZnU3\ncnl6aHRzU3k2V3R3dU9RVDA3VWp3VkkKLS0tIHcwREM1dDREK0h0UFp0bU5JTW9Q\ncWdyanNMVjY0SnZUWUl3Y2R2SXNyc1UKI1FPIE66to19oQK2TwM5B4snGOVMLFfx\nl6JMEilDVSgy2RR/tSiovmo4NwOsv0hmmF1t34547rbZb+dB5KrMEQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBnbWp2UWphSnFibnA4N0ZV\nRHlNUnBNYUNzMzNZakFVc3JXT1d0R3Yyakg0CkowMFlOcEhPcHE5dXd4ZUd3cDAx\nbjQ2T1NqejNRMnFvbTdNRGFGdW1pM2sKLS0tIDhGb1JBQ0RFQ3NxbmpkdXg2WVF6\nS25uZW1hMVo4Q1JGdGNQWWRyWE84b0EK0FmFZB6sN7uZynhzYU932x461zSZIUWU\n8oyDEKNoUuPqpWK8RktgjWlKHtB0oLXC+SLAOJEhtnhWF+GSqloGfw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1fefy6dk8zn5c3edwmrs9vwx79quftnt784m628t9e34q3ft3cehqz8u72r"
+			}
+		],
+		"lastmodified": "2026-07-28T11:53:32Z",
+		"mac": "ENC[AES256_GCM,data:EhWEEIamG62xHI6SqO4tzdK6gcEXxUU/UGcF25m+X11kUVXzHd6yLcfiM2DvqcwGLmwmOOf3SpFLABlQUzTka4QRzTMFIAJi7x1rzQV4J0YIGITHk9rgvy0V50TI0loONBb2du+vDt8IlTBNvF9WMbNCki+fHPAjIemyoRBdubo=,iv:wfsx0H4fD3L7WeGzz57SzZtajBr/xTRDljSpz22DD7Y=,tag:naDyGH0WTKkqgd954Ya8jA==,type:str]",
+		"unencrypted_suffix": "_unencrypted",
+		"version": "3.13.3"
+	}
+}

secrets/nix-cache.keytab

@@ -0,0 +1,26 @@
+{
+	"data": "ENC[AES256_GCM,data:z2bazlADvtWkGcY4an7NgZgIDSDq8KmYpSq8tcBleW/33HlElMNhdmje8m8hd7WxgrVvCQDdlAfodBLj2mjbgSwBptlPX2zbwcmJdm0g0Ope+YyQZucIio7NnBaYa+OK8meWqmxO2WEeOk+hnNfNPbt8MkzF/FMMbP8xv9wSTKP9CDdmO7s8rdg8G1JxVfn9dyaSDUTuA2JGNtbh+osd4CtNCV/bc84MjXDZTgTfT0W/uv8VH3iPNT7BhQbU9FIY4dsFRYBf758VtJ+3mTBiQkR38IevJBvhFB7Wiqn118LSBgjdTKJnBwmGo6lMdo0LRYHEgUnb2ejhWMNie19x+LEAErDki0RBmjc2BbnOF908kUlW2fUPo5fz/hlfqlhDLS1uOxESKhfnKt7s5qzWiMX/nohpknVfyMbmu9j/M571z9sgFnJAylpW3NLp53lX8N9mINwRGXsyL/ijbNE=,iv:M/MNquAGN+lIIyVVvFRgKR6DKAhLclc/OY1HV5Xwoog=,tag:eEuURMErSqsoh+l9ZaHY9Q==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBqZlUxRG0zR3IzMlpDL3Vl\nNmRWQXUvc1NDek5wbWtKVEFTcTlxL3ZoWldNCmJVMkFtbDkxN1FGQ2VLTlhBUW5Q\nZ3VzL0UydUQ2YnlUMmtqa1Z0d0FSVFUKLS0tIGJFelc4Rm84T3ZHSGZDdnNUbUFM\nRXZHV3N3aVlSOXhUZk04UFRMWU5TbFUKhPU80PVYuDFUCxu1CA8+W8bqkr+Ne2fh\n+nBUPJbGxfN9TyD9tUC77AMbcL1R2L5x+SSAh0bEgSWE24/RjsuVKw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB3M1o3S2FibHV6N2tIOFEx\nRytJRDFIUU05azNDbWlpaDdFQXFRWlBUNnlFCnBwNVB0SEVwL3NWNS9aeG4xSUI1\nV3NOcUFxUUhaODYyWXdFMEhWeFpvancKLS0tIHY4NHFQRGJwUURQbWZ2cGlSdm9s\nOFJodGZkekk3UnBRRUwxb2YrQ1ZPcU0K0tCapb1hfVHFSNpmESXexYa5k9OE9Tha\n51QpU4mZHKGrnWPK/kyj7rHiz95TLsmwUdA8Q2hOiYNSxEaVBjYDQw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1jcx3yajjhghn8qh8za3yeu8nxykzlg3p4nrv03vnfvzl0mzayg2qmg940e"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBkTmNrbUFoVFVGcytzQkk1\nMUxDdmJGL0xDcUNZaDFRQnUwNXoyMU90SEVvCi9EaTlVOGlMeUZtQzRJS1J2TTJY\neWdkMGNFMWZzQXVKOU5KcXVvalk1ekkKLS0tIDN2MlRQcG5aQnN3bUMrSDdvc09X\nM29hQ0pJRzk1amRHaS9mRlhrb2FMZG8KEWkSSP+MqGRU75qo7ctOCL7qHhyCM3l4\nL+ga1XOKxRsQkKQPozCi5Bm+k28W9hIDaC34Rw9difxICM9Z1rAbOA==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1ufg390ydrmma849t9xfkxxl5xvdkk6mngnlzhmy7mvuaje8sgcmsmnq6l7"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA1TUtxVjJ2STFpU3RNdWpJ\nVjcwUHVORVN6L1pKVC9TeWt4cTNoR2pPWVRBCkR4QVJ1bHFUa2Z5aWw1bG0vQWVy\ncjNGRDl5REZzbzdZWTFMRkU1eHFTc1kKLS0tIHNLVDFiRkRKTHhrSEx2S0J1R3cx\nSkdEQWJya1ptTTRqUjJZT3FFaFhkd0kKgecHrnzW9+Eb+b7c0z1yR+Y0Czsr9Kjh\nx1UUOfleHntJUCs8oYcOogKknEnhBJJoJ5oe/gWruRSwle1fs3cBqQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1jlltcv5jcnm40z5k0q6hv053k2rqpqvemtuecdwn527uw8uqz4es3x7m68"
+			}
+		],
+		"lastmodified": "2026-07-27T21:22:58Z",
+		"mac": "ENC[AES256_GCM,data:VG2ygV4X6yMxGlJgq3sN4GAzgVqiD06noyMxB2yb/FCmiFVYZAH/9LqF//G7MTInfIjFrTDyoHAny+m/ztUrJkHXI1Fzg0U8R/zYyQ6wj/GguL0gyhA70uriQhvHsRHefHPa7Km61Blo9cME6CBJWejtRvh1IMw9itAioVrSIZE=,iv:zjxNG6IYxkcNqLk08NADoDiIbS6at86y136SBzadW1U=,tag:sj4ZRR7ixU8h7aOUJmTCYg==,type:str]",
+		"version": "3.13.2"
+	}
+}

secrets/nix-cache.yaml

@@ -1,35 +1,43 @@
-beszel-token: ENC[AES256_GCM,data:meuzUP/6wCssJDVTgbC0XwiLZPMGyDl55HEIiON9xOXCD9k6,iv:TDqWcp+8Mxd8wN09r5otQRQXq3XTeQphaTWxvvuLTAs=,tag:cRPZQGlwB/dTguBAheWPQg==,type:str]
 cache-priv-key: ENC[AES256_GCM,data:6vQKIf7eS0WNL2Eptoi4VWr18SRMZfN/H/aFUUtXdMYQY5LLyBp2EHRKqZcGFuh1nZhUdAxUztq/CVXx+QFxKW+ElHxCxUSp0QqI1fdSkBkKZb8hlit5SoX9JtLzZGg0HBNM3nJu,iv:0J+xmrPJhInHhFR/c41ACjuTfaIoMkQFSfbL2KkgFa8=,tag:f4s9Szs5oprVVRSyXaX48A==,type:str]
 sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBPWE1HTUhiSUp5ZEUwWEpI
-            bGpkZlBIMUo5ZlYrQ09SN3Q1a0ZkQ0ZnOEhVCnJPNEZQenVWWGZiODlzQzNEc1Zq
-            c3l4OWZJTElJc2Y2UE15OGtEUzhyY1EKLS0tIHNJUStyWnlQWjZBbEZjQ3UwdUpz
-            ZndoUDR6bisrNGJCUHk3TGI4bTZaMFUK87fFsm9ne9s+PK2pcwtrDjqyGBss2r2E
-            8lhqoeiKZ2j96z8kP/7ChzovwTCmqdcmAQuyNQD+ZAFijseipSvfbQ==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBwMklZTFJuR3NYbkFvV0l0
+            eUhMWU4vMHpnN1NKVThuVVdiOFpkZW9rTjBVCjJabWkvOFpOSm1hdEdlZTYxc3BP
+            WkRURDFEQzMvRFlka1VnaU9zRjhiSEkKLS0tIHZXRG9GaE5iVjg3M3I0SzhtN0JP
+            UlJVUzRzN3NEZWxXZHJ6RW1oYWwxS2MKonnhq7YDg4v93PZtoaLANDy8mdRCenjo
+            FjRUzozMLpgWBll4DwRWikejsrRofRBwlcsiIdrBr90f8Lr9pHdQ/Q==
             -----END AGE ENCRYPTED FILE-----
           recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBUYi9SRFFGV3Z6cFd2Znk5
-            b2FLbWtzTllJMDBUaGk0NTViOTNBa2hQclVZClZHKzNhbGVjQUJhWkFWdTFBMG5a
-            cUFJdUdyVG5HQXJRRnJId3hqRTN2cXMKLS0tIEFMRjh3WE1ON0U2TTNTZ3hxMTR4
-            ZGRlemlIbDZKeExmVHROc3Eyak5DdzQKaLwIVDi6BN4cxpVxJoqTYvJETPOp4thc
-            l9uVMvIGuEsEZgDsvShw1dYLljd+uGy/A+dXbcxIUCP/mmPkwmd1Pw==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBsWDJQYzM5Z1JRT3FlVkJy
+            TkVaSXdzanYwbnpOM1d2RFh0c2NaSUFmdW1ZCit4SVFxSS9HNXhVM2gveERGVS81
+            NVFQaUV2RGR5Q3kyUTQ5eEpDVXJVMWcKLS0tIHdHSy9WM0o3Q0o1THhXZW11K2Vp
+            NTNtSGM2UDFuWDBEdS9tbTY1ZWt6UlUK8z5qoi0kGn0ES3m9khummuU51rkR0Sb9
+            TWT92+BWvPdNrAsDFjv0fgpUKyTMzN72EzHZKAJCIM3crUG9I0tX2g==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
+          recipient: age1jcx3yajjhghn8qh8za3yeu8nxykzlg3p4nrv03vnfvzl0mzayg2qmg940e
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArOWovSW9DeFpxL0VDUDQ3
-            SHUwTzJVZUtPV01ZRkdCUXZGL2lTRCtCNFNnCjBSNExqRW5mTEN5SFVucHJHSzZt
-            cDlNc3BjY3M1c1k1Z2tkVEg4R1pacGsKLS0tIEFWbHNKZW0vbVh1Y2VhQW93OUwx
-            MWV0eW9sOXdQd0l2ZjlWOEVVc1dwcTgK2s4p9xoNkawH2OkGsl80bNIo3ad5vn4W
-            Z2w+jwppSoUmbQnD3WFbLmSSxmuobmU8HILwElv6SZu+KE3aspF6XA==
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpY3o4SEpwZEdFQmVnOTVV
+            d2NqL0VudHM4VjdDK1N4dWdlS0lGR1V6a0c0CmJUTHlsbEMwaEU0Kzdaa21lRFRm
+            RTRnTUlGUG9GQVB4U2pzTHdRY09udkEKLS0tIGlFQW9Wd0N5WFg2WUpCQzhWUm5v
+            aG1VVWV5ajBmc2o4ckgyQWpWaFVxVmcKisAw40bGQBRH+u6uNygfYpfb7iEgfEHj
+            E+g9n2WeVH8kUzD2O1o6VAu4m/SVuI4+IQ77j9GEWmlI/wgp8wKXgQ==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1xjst4frdh0th6q8m7p7u9g5af7ty5jqeum0p6z8a52a9q7st7ewqw8yl9j
-    lastmodified: "2026-07-19T23:30:21Z"
-    mac: ENC[AES256_GCM,data:kLGE2xawQT7mx+sfw68hmGk5nCEGiEjZrqTEl9B1dtQmTrMwmoVr/1RISi4LfJrwxy31mDgff4lcIL4wIJuM373uk3X8j4RNyYQNTfKEkORT6r8NHeepNs267O77pKGd7OmcM4MT/BqOnB8ELS7Wlf2ect7CAlvUUVyc8icxgZE=,iv:EYLDsHYHZ1XOQXafOTqHHWpk/OBNq/R6IJnOBYV33E4=,tag:thxrCPC5oGvDjhK7Dz87YA==,type:str]
+          recipient: age1ufg390ydrmma849t9xfkxxl5xvdkk6mngnlzhmy7mvuaje8sgcmsmnq6l7
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB1elpNZXVJbmJWSU85aUV6
+            NG9YTWVBeWxiRHUveStTQnl4NC8rT2VNdHpNCldxZVJYNVhUR2V3Vk41VnJxenVT
+            WS9rRWlKcGpVdVJPakkwUTY2a2xQTlkKLS0tIFhFVTRucFNuS0pMK0FNRk1ndnFO
+            SlVvakczaktUa2VLY3RLYUdVRzFyamcKIhctg0mbYL7OE08dRwj5wMu2x+O8/BMu
+            IqA477+noQ/Rjrszb2hEvxID7keogcDUWMWQzQvdMc22+3mvAr9qIg==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1jlltcv5jcnm40z5k0q6hv053k2rqpqvemtuecdwn527uw8uqz4es3x7m68
+    lastmodified: "2026-07-29T01:59:11Z"
+    mac: ENC[AES256_GCM,data:/nbcfause6G6F8IvMoyPZtkWS1XRLAivhwTFu6y5P0Mm0eCcO6M7/rgioN9dngKzPXrCUl3Dx/EvhrrWKe2/Saq9WEOFgvS2V05pTRbQgYjuugVzW2paPq1fgmoDYNjHz2yFYWAovbIFtjVxMR9tmcASMTe6r/FocvMXbFCJh7Y=,iv:n3KoaPPtDhWK8mxJNJRk7WPVUUNR59nZSA8JyysWNDc=,tag:tYhkNXsj2ohVjHkvxife2w==,type:str]
     unencrypted_suffix: _unencrypted
-    version: 3.13.1
+    version: 3.13.3

secrets/nixos.keytab

@@ -0,0 +1,30 @@
+{
+	"data": "ENC[AES256_GCM,data:apiijrtrqd77CTizITg0R35BfCi8PBnufpxIyC+hLYqwoBzP//3z/yjFyHPLG98m/c/qywoi3Kn+zsaTT7MjP++9OMhhX94YKlSHV1/cHB76OkwsNc+ClqWxl6vpaFX29Qvh3gFX9c/NR3xvYQutYwrIrQ9NR+t/M52IMC8hvtR1LQy0ak3VIuXJlSnG2r4kF2Ym1iP7phjuq39Gd245Axzw8OB7yGvOjNxSdTPxW/qL0fMlzNcMrjr9hw15WlqnZfWPOsB1+gZjHXpGfPD5BCbAAMoTRJd75vhKKXP/ERhIffewuuH2x/QHfSFvXVB3QyhBQMxd2b8QEEE5cjvcExOST3tkj6QARkzoUpRT7AE3jhl3XZ0uA2qu9SwyrSvbr0tBRKxCdK0g2E2/hqwcK/Tck5GB1eKb4aN+UkqxOblNDH+B1RfDoyNAuN+KEg==,iv:0p+ScrKpP4kQvO52gBAlwAis6oAzZ0EHFnU74hYPrn4=,tag:ON7qOjztF52xsJWAou7ogg==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlYXB3cVAzb2xEZ2pGa1RJ\nbS9ZVTc4Ums5eUZJUjEvd1g1aGVyNUNramowCnptZXFOZVB3MFRFcUtzSXBEZk1B\neEtKcDdLS0h0b1h3VjRjRXRvV3V5V3MKLS0tIHBDemkyUnV6ZXhTeE5VOVVOMlky\nWWMzVGVzZlAxMjZYUGpQUCs5QmxiYkkKcuBshCgWX4TwfVlQ5lHikzvwWdLEXWD1\n/uSiy0J6yMSiu8u6cg2SxeFrlKJ3j47dDlT6WHCxS0PfeEA0bJb3LA==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBGa2VTc2NWdkFRNUJxelVR\nWFk4RWxoelYzNHo1UFVhU2ZkLzEySlRWN2xNCmNmcmJod2crL3NMRlVsSmpmVkU2\nMjlXMktjc3piUVNhUXlTdnVGTWJkUTQKLS0tIGQrMUxrNDlNTkRCSUtFWkxRdXgw\nRlV4ZmtYSGhPQU84eWtiQXVqTmxUK3cKk5fn72UZPH68t5ZappfAhZJwzpLkfKmT\ny9TbUPIr4Pbrexau6YiH43QIbDQFdwYPfkBjGkd57zCg8AVo1+MBRw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1adur9g330gua4l6ndk8cqjg35qc8yxwgme6wrl2hpylcc7vxm38q05ejuy"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArNWkwQXFWT1RpaDNvbzYy\nQWc1aHhmNHFEUXVsQjZqb0EzM0wrV0dwN1hnCjFsUFJiT3REK05uSGRWTEw2SFE4\nY1FleE1XVjhBbndiMmZxTWNTYmhYeVEKLS0tIEJiZzJvS3BsYzB3cHIxa2k5N1Ro\nenFFZDVaODNnVGdBZTBOYWJwRjQzc1kKlXJgee8wTSN4Beq4P0t9cYbk0BWHCseQ\nyaWpiPT9aZBEGLFmuEd3zKABc8lrilX/ySTmOG49vRg6CPmr7cT0Wg==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1rrxqea6q6pn39sw8y5te63h2py8jgjl9v0jyper86w3ggtn67upqg3ah39"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBEa0JYenFMNmNzWnVmcXdz\ndG90ZUZ0WWlIU0FCZG9OaWpBM3ZDWnFhZFhNCjhuV1FTOTJ2WVJGa2RuNVV2MjR0\naVNXa3diaWxWUlJtdkNOQXZ2R2NsQkUKLS0tIDcyYXh3N3B2QmNiK3dzemFFMGV1\nNTZpTk5yNGV5YVo3cGswK0NLWFQxQlEKIe0N5OxooWXzt1cUViBmjihmGEe3G6/f\nkz2/IscnG78ZvNgYKjdoG1jlsyje/3zI4C8aWXLq2DnIyxUyAhPgsQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age19mn8zrxl8zpps9yvrh4euquvygpp4fp8queg7xc6qhtnl4ng8c9qx02qwn"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB2b0NVVm9QNm9waUUzcXBi\nWnZWU0JETjZRZmprZVRUL1h6ZHB4cXkrdm5rCm9GZ0VnTXB3S1BYSmlGWFJVcDhJ\naUl3RjR0ak9BRmQvVk1GRnQxNmtYM00KLS0tIFlTU1p2OHhWUGlOWngwbE56NEhF\nRW5QSkVVUWZpdDZXWEIxZ1BkbzVwclEK2P25nBgf8255vaKW/+T97aNTecRgNjLu\nedIUiPdXbFATCe3v/YRo6sqzFwIsvM6Bl9yHh/SXo6Ftc7eWZZd8zQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1hrx8qj02fj2ea6d4g9vqhyj9hl7fppkjqfdx2l37py3h6pdkr95s8n8rvs"
+			}
+		],
+		"lastmodified": "2026-07-28T01:44:24Z",
+		"mac": "ENC[AES256_GCM,data:J0D8bEs5mHLraLS6TvYuCgfiNU1xKM2Yfb5Y0f/q/4wM4LzXufNzv3+SWDHumTe328U8UnNXLqjNHEKL0bZi0coxpU5hVM+BvPcmqD72vscETzbQ2hnU05sfW+XjfZhcN8/ke0bpLt7nP0crD5hsZv3esV1E2UWvzjEiYtWzFHY=,iv:lcmXYG2H469UKBYDndWKMO+GP0mSGLztenm+kBaUdYI=,tag:ujiXbLM9CUsuoFwQQWI84Q==,type:str]",
+		"version": "3.13.2"
+	}
+}

secrets/pxe-boot.keytab

@@ -0,0 +1,22 @@
+{
+	"data": "ENC[AES256_GCM,data:Q++XWxg9tvY7ugT8+8FWCC5jgOfQ1+LYLsnqN0/WGxTf5XT2VmoXvszcE/ow2BUOBG3qBTXS3OHYFPwmj1GgaBHB8rpdXX6+LveSBE2gmx1VR+NUDTxy+0/DBq411MK9n/J9eIYcybdFIE11biFSAob9EgfxBF5roCDXIPDPyVCSe6LyhNvqYPnGQsfHCbejSewLTcRQEiguP9BX96CpMPIpmaB9fHN25t5RWCgMI7MtacrRxRsyKg44+2FZstXdZrp2Wv9u86BxqdAFqtZE8qpPeGdrdzluZx9jhnw0wZPzHdKg5wS7/UrLCb0UxIQiDxDMDuuBuLGkKXfAhb6SGZU41wWAWYk548iGRUaG+79BO4HhRZNObOFvfsjpMXEfcH/Vbv/wHVY4OpJUPe/ZWK4wpL9YrY4nT0t62HH7MirOy1uhwLE50h2+6dHKj6ur5G7thkSqgzVWXQ==,iv:zaRBwS+gfXLhH30havn6Q2+oPWuLV3qBfbOj00kewlQ=,tag:Vr5iEQ2u+9YNahryhgzwSw==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArTGJnaVhleUtsWnlITE1s\nNmRCaW1QWTFNSG5LRFdmb1lzRlV5NWl3YTBNCmF6eUN6RkJBZzc0MmJJa0dKTW01\ncVh4K1VLR2lURUpKQXpxNGpQNnpSUlUKLS0tIFJONnJFWkNCR3pqalRsUW9POVBj\nQ0pFQ3ltKzBETTVXTW5sV1ppWTFJc1kKzxUboNZO+Nwn2eTWy11VP9w1pRswCHaJ\nE2dYU0oUOClVzc0oSuIJxraG6TPj1N4WGC24gS+UmpkmSuCiOeZBsw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBDSmxNR1I3dUFKT0xUVG9h\nWkRIakNVeWRQOEN3blNRVjZlWHF4K2NRa0hBClRiOXlmTTJ4T2JTUEw2c1l0R2N2\nMnRwdDA5bEZlQWJRTm9vUmNKclBSU1EKLS0tIFcyeDFjbTZyVEVDUjN1VzU1VHly\nNWNDMW9rTXY2bHNWYVR0SmtMckovUzQKhTWr6yFVW9am3okCiIswwqR5+/p9OLmB\nWCgPtwoFaBt1RjUXPK4/eS4LlucR2K6V/mNMn4xVsnkIl193U9632g==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age16j42pdc5dr6wnj7xayhkqdj2rny9u68fcqejs50hqq42scssh4gsnrrnlt"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA2ME9CbmVGcENRWksyL0pW\nOEJyUGhpbGMwWlBhVXBSeXQ2MW1EWnFuR0E4CnMwU0pjdk1YMzF5ZEhTVFlBaHZq\nam94UWVGbjhZSEx6VHBmem9JRWgwYzAKLS0tIHFJZWRyRjRHNzhXdDJSYWN3bDlR\nYVp3eGJWWkh3Y09ZWElyclZQN1ZSVFkKjR32//EcFAdMjVlNgky5zvVkwXwEN68D\nrkTuHKjiO5aV7yAQGPkdNw0UM0oRGF0u4YF3oOUcZfSvnKgDeoi2Zw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1ug787sgt6st6k82fgkrug2lzltw4qsukrrqqs3w27ewwqj8rg4hsxcmylz"
+			}
+		],
+		"lastmodified": "2026-07-28T00:27:46Z",
+		"mac": "ENC[AES256_GCM,data:AbJIHYcFpeanQsJ3x7RPL9Yjlg5BJgkepKax0fL9L/PpA03Antab93iUNG95Mp6k/duovp8Jm445lbuppDZq1dh9ij/deBa8GbzJ50wwEe9zMc3EwRKScpqZEhRPF7KlJsIjsHJyd8NkcI5ji49XkHb4Ae1//8zG5HpVgy+3b04=,iv:uxQCbMwMIfP5S1dbsvIx3F79YWEguxwox8T0YZvUBdc=,tag:3utjmBGDmPc8q4JjaXvCkA==,type:str]",
+		"version": "3.13.2"
+	}
+}

secrets/server.yaml

@@ -1,43 +0,0 @@
-beszel-token: ENC[AES256_GCM,data:cbQOXhLzNk4g9d6hvm2DH7Q5ApTPCTzsW2txflDT2dD/UPIE,iv:V19MI1GEo5/0205Hrt7JImfkjduFiZ7f9aIkDVaI8mU=,tag:WCArgdrnIOudVe/Tw+oxRw==,type:str]
-sops:
-    age:
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBaYU9HR0lETDhkYXR5NWlj
-            L0diSE5JQU9KWjRoU3hrVjdqZ2tPNUtOdFZvCjdUVGNFbDVYa3pVSC9ZWVNORER4
-            QWozUlhoSEtjTk9IRlM3VkZoYlc1RTAKLS0tIDlHS01WVWlOMWFEQU5GTVRLZVhV
-            VTcwekhrRHB3SlVYT2MzOW5GbE52dkkKKCWehPhpdGapdyzpll20NJUcZwvW/7X8
-            KQ1EqAgI2fewnbwuIDYCleN0b0SLJNUeSV/tFKDDoTMnHWCdeD4ECg==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4YndybFBTQ2p4SGZ4SDJs
-            a2p0eFRQOVVWcGd2a25ESW9ESGx1RWw0Zno4CnhpVVh3cGI5UjY0YmFINFFPMTh4
-            b1B5SjJ3NTNvUE1QUmJjVFozY1dYS2MKLS0tIC9HZGNpOFZhZGNFZGt5blJuZXVV
-            SXpkRzV4d2ppV3ZQZSt1dmxYNGVFMUEKmSe9dkrmkND81Hw2/ATAmFvcmhk1tUC1
-            LxxBw54IVHUqwYKgRYUYRNu+pykDT5OnFDPiskd49Xso99LY87PyiA==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBLd1FSSHVTSGdHWm8wMVQz
-            d0dlOEsxeGwxdHU0eUlFSUxka0ZmcVpnOTM0CndYNUVjVy92QVhNY2orQmpSQjYy
-            VS9KM0NUTXhuM0lCSDBZMWtISEdtWTgKLS0tIExTL2wvS3FEdVViUmRYZEFsR3R0
-            YTJFM200RjF6MjNxOFA4eHRpWVhtRkUKOqBIT445HnPXrrH/qV6FIuAhAuJmSL6V
-            +PQopM/m3PAnK5m5Mu3cfjYfDiB8+GWTABhljfT+GbcoK7CqWLehrw==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age1ukpqxzl44mnjpy5r96sfuc5sqzm47u4k8ujjh5qdgy6jvl9uqgpspymqfk
-        - enc: |
-            -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAvVXF4a2NmaW15R2VXS3FP
-            SDVPUGpUWTlIWjl2N2N2SXR1UlRkdllWNVRJClZDbVo4dUhrZytqZkMrYWtpOEZx
-            c0dSZGViN04zQ1B1WEZEWm1QM1lsejQKLS0tIE0wa0k5Rm1xZmw3OHFESkVXc25j
-            NlFpYTJSckQ4MVlZQ01reDlkaWY3TkEKsmQlreRhRAjVZ/q5x52FNATDF2sLhbHo
-            djOZigZx2rs6shqQ6It/XRJ8CiPaXZBPOt529Gwmplu+hWlAU1+l2Q==
-            -----END AGE ENCRYPTED FILE-----
-          recipient: age15kh7akxlx7zn00tey79rq2g8lgs4j5y77rcnyfxrxap8ckfu0a9sqvtdhh
-    lastmodified: "2026-07-19T02:30:40Z"
-    mac: ENC[AES256_GCM,data:rKHZjU/MH08ASTlu32HZO9uWmsBYuMCEC6M8gwVhzuWvmablnP05tS2z13XfaWaCEUXk6kmGJKuU0zu5+IKVZgamCF6DAMtxQb6bVCaLsoAm/GSqWQ5VI9eHqgnSSdN/o3ul/33Rf8iBQo4aw8FFAmDVuNz8bfAn0QefFTj0ByI=,iv:JD2gtqRinOY77etg6PUmZNovkYl1Q3F6ZvRi4x7RznQ=,tag:/5IMpWKRVt+l1luCTQE0BA==,type:str]
-    unencrypted_suffix: _unencrypted
-    version: 3.13.1

secrets/tailscale-router.keytab

@@ -0,0 +1,26 @@
+{
+	"data": "ENC[AES256_GCM,data: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,iv:kUlVXF4Yl5HGvoLwu9loiuuDVtz0kARRiUU3K+BPL2A=,tag:pVaGzQAX9Etoqc5XMGmNeg==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB6OUVUdkoxM1M5THlYZ1ky\nYWJ5RjhtRGoxTldwRkI2T1p6dHR4Y3gwR1ZrCjRDS1hTM01lZ0FSalBYQ1B0bENs\nUytXNmlrUkV4TmJkMUM1QW1ZaExIcGMKLS0tIHdHKzdEcUxvM0ZYUEp0a2d6SHp5\nYXQydy9uNG15V2FhUUd4NEFTMTNNMEUKkIzKEoYzoVs+nhnpkHFgDkQqrWykatND\ntsNxcr1SXSKeEW1m/QpXZnn/aW3zSQR09PqOHf7PYU47/AdkwrUaAg==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSByZENrck42dWJjR2hYUVBl\ncERtRjR6dTdING5nWXlBc3o3eXFhaSs5NkFRCk43QXFUeTBJR0U5dG9YTDRmQ0Yx\naEo2blUvUXNZY3dpbEZRTUx1elNzdkkKLS0tIHJwNjRNM3V6WktWZ1BlUUtLRTNI\nMTVEbCtYbllIbTdxTGozWUluS3pIRXMKZCruDIkD/JofdAHWgPuaaKTDsz408ZkY\n77mhO8J+kd03qwt6qhFC5KF1lyjhwEnqrOE195+R/8Yl7hA/DsL2ZQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1k7d2du5mejsmv5rzavm4xwgpthqvcfsehduquv28nzs53zppa3kqngfxq2"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBxaC95RjYybzVlU2tYdHdU\naGJ4M2IvNkJwVlNIU0VCZEFUZk5VaksrVnpFCmJXS3luTG9WejR0Rk9DbHA3dngy\nRElFWjU1N2xuc3JaKzQ0L0U2Yktib1kKLS0tIFlrK3F0ZFh5Ync3ejVWMzRKTUx2\nZDhxdEMwa3B4TFZUcWdTdktDeGt1QUEKfgYnK2lW3cZuJGaw+bAKDipLuC4S5vK2\nxK2eJB5TP/xXrp0F3lx9sc2b1FOY9Vt9IQ7zVlBqJFkzJrcw8zYJJw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1zhfyuzlq40reuqlr34gf77852nhs3t6mqfzrqmas8z6sxk7tcfhsungrm0"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBwOGFkSXNxTUIzLzR1Skk5\nMGZveHFDN3YwVmpwT3VTYkppWEU1aGVpdkhRCjZtRC92bVphd0ZFbzFxVzRUcGk4\nMUd1aWdEbFRaM01FT25JSVRoMTRsNUUKLS0tIDAybmcrYjFVWkFYaGY5TFZjcjFO\nYlZoQjJjN2lFNzd4RlJuSHFlRlNCOFEKgUIPnL2/OJgz9oMYt86/llHa7adTkhs6\n8yGYGV1wtU9aYtUMIR907SfYyZ6M4z8jH2wwzpQLbwQQMLgkejl1jg==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1f7usptjx9rv4rxauasve200gxtdt9jkqhhdqstlf20wvlm7u75rsjfw50m"
+			}
+		],
+		"lastmodified": "2026-07-27T23:14:51Z",
+		"mac": "ENC[AES256_GCM,data:CYhzR0Y29GXvWUBbb13s16v9hDQ4k4Xmd4FUpcyNtHe0L/IrDGkx1WHzAohNGZjGMNB9W3BgiEH85OoOo8r1F82El4/8s2prEJi8AARvQU3+2cmRjjhNCCYQWmJkoF/cZNpw6nVyWzZdfUpPvHjbuf6utlI3rtR0qiCpSo/32S0=,iv:XLKTU2Ute4jMkfRAbXiVGxqP9+fjSs6HwRv1JfTTe7w=,tag:oIqS/1HWQZ7mLWaO7GwLFA==,type:str]",
+		"version": "3.13.2"
+	}
+}

secrets/tor-relay.keytab

@@ -0,0 +1,18 @@
+{
+	"data": "ENC[AES256_GCM,data:QvViw/s1N7eIN3CoD27llEjriuSrohOou4Cv310nigcW8xMnA2SDN2id3H3AoKii1JlJ+qWpKn+gUmt5HOM0UlbeNe3os2RVwiX38O7eN9xFH9F5kA3TFs6Umqq3EoI586PwIVmB2LyxDnTeEEXVd7v5PFkBcfu7u8YIcNF7lpcj+6rOyHMB8uxPhrGep3yiKawFd9c9wWD0hlSSatV5tMHA1qmdK8VmDbCU/iuGwIoMzN1eZwGAXzG6LkCA63bUfdxU6yGuTboD+kN2Wbo+GZB0EACmiZoofl2wqlXuiw6qwTvlXkyauc9O5EG//PUkIECzDwiXcX+qSOM9DIBlZNth4ebhtic/PskyF09etL/gICz5YvV4ph5lyrWHq41KxljSU7QXOkGhzagruuMrYzhZb35wFH4Tie1ee2DXbGhreJr8V3Zse/zTMaD+iM57V8bvNcarTzOFXyKfp7Y=,iv:XBPhj2wT0k/yRCRHU4d+BQA/k00ZHWSKOucnZ5+PGys=,tag:Nh5MOxZIUXAYVZY5SZh/JA==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA0aUtETXlBMmRlTC9vK3NF\nRW4zS1FrSmo1dDN0OGN4SmV5ODd5MTRVejFJCnpPQkM2MVJ5WFlYRW1NVjduV1hv\nUWUzY0hHV05LV1BROVZVUlM2NldsTlEKLS0tIHFsTzI2SVZzYUtJWTM0MmFiUlVQ\neHEvUXgzc1pxSU1OZFo0cXhSZDdGUVEKpLVfzQEnntluUGsblnkHZJ9Jezu8tFte\nxEoV96GVHxUca6TFWpTLMqdR7NtuQGCkx295W3i1tkp58DP1OzRTUA==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			},
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA4ZW5ybVBvTkxibWJMWGRL\nZ1lnWEkxZ3l6d0FWbmxMY2VsTVlzOHJJM3owClNYd3BlQi9pL1lIdzJmekJUVEVi\ncWhSK3ZkZEMyeTNoZlpTT0NMUXZFWVEKLS0tIHVkVlhmQXdRQktTK3J5dXZ4aTNt\ncUw3WCt5dXJhTkdUbVpmeWoxWkoxNnMKj4XtdwmgFVOiVsIJs2Du7QJ09A9tv/Lf\nkFOq8y4tlZe0nCwRjq43sVz7hdCTdQ0rsaWjBGY90LLkJbOA+f+Wrw==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age16kqfmvz4e23hmdlqresnyw69ej604s320mmd49h4hm3fhqchtgyqrws0k2"
+			}
+		],
+		"lastmodified": "2026-07-28T01:44:30Z",
+		"mac": "ENC[AES256_GCM,data:zR2WLWX7NaHA15gi4kX0jDvzUIe9jtz5bMCAggbPW+IXOEedPrddAHZ8OfPErVMfx8O1pJKkAKSzoPTAbEle54FisSLMHXp8fI0297MByJrF9pOsMFpVcDy/L4Q+pBzmB7aS9r7+u7KRVVTZT3QwG1rFWZaDs5dFTP80RhtCbWQ=,iv:ZzPoO+h7ebS+jsSH7tWMx6QK8umpa2/HFQmx9dnJN+Y=,tag:vG9+ifxw4HaBE6YsmOwXcg==,type:str]",
+		"version": "3.13.2"
+	}
+}

variables.nix

@@ -1,182 +1,343 @@
-{
-  # Network / domains
-  lanDomain = "gitea.lan.ddnsgeek.com"; # Gitea/DDNS domain
-  homeDomain = "sweet.home"; # base LAN domain for service subdomains (pve., docker.)
-  tailnetDomain = "tail13f623.ts.net"; # Tailscale MagicDNS suffix
-  lanCidr = "192.168.2.0/24"; # LAN subnet
-  pxeServerIp = "192.168.2.247"; # pxe-boot host's LAN IP
-  pbsIp = "192.168.2.108"; # Proxmox Backup Server LAN IP
+rec {
+  # ── Gitea / flake remote ──────────────────────────────────────────────────
+
+  # External Gitea/DDNS domain — used only for the remote flake URL in
+  # Switch-nix / Test-nix aliases (modules/common/configuration.nix).
+  giteaDomain = "gitea.lan.ddnsgeek.com";
+
+  # Org/repo path within Gitea, combined with giteaDomain to form the
+  # git+https:// URL used by Switch-nix / Test-nix.
+  giteaRepoPath = "beatzaplenty/infrastructure";
+
+  # internal repo path to flake
+  giteaRepoFlakePath = "nixos";
+
+  # ── Network ───────────────────────────────────────────────────────────────
+
+  # Base LAN domain for service subdomains (pve., docker., nix-cache., …)
+  homeDomain = "sweet.home";
+
+  # Tailscale MagicDNS suffix for this tailnet
+  tailnetDomain = "tail13f623.ts.net";
+
+  lanCidr = "192.168.2.0/24";
+  lanGateway = "192.168.2.254";
+  lanPrefixLength = 24;
+
+  # NIC names inside guests — determined by the hypervisor/platform, not the OS.
+  lxcLanInterface = "eth0"; # LAN NIC in LXC containers (Proxmox --net0 name=eth0)
+  lxcStorageInterface = "eth1"; # storage-client NIC in LXC containers (vmbr2, --net1)
+  vmLanInterface = "ens18"; # LAN NIC in Proxmox VMs (virtio, first NIC)
+  vmStorageInterface = "ens19"; # cluster-internal NIC in HA VMs (vmbr1 — DRBD + Corosync)
+  vmStorageClientInterface = "ens20"; # storage-client NIC in HA VMs (vmbr2 — iSCSI/NFS VIP)
+
+  # ── Host IPs ──────────────────────────────────────────────────────────────
+
+  pxeServerIp = "192.168.2.223"; # pxe-boot LXC container LAN IP
+  nixCacheIp = "192.168.2.224"; # nix-cache LXC container LAN IP
+  tailscaleRouterIp = "192.168.2.222"; # tailscale-router LXC container LAN IP
+  torRelayIp = "192.168.2.221"; # tor-relay LXC container LAN IP
+  dockerIp = "192.168.2.225"; # docker Proxmox VM LAN IP
+  pbsIp = "192.168.2.244"; # Proxmox Backup Server LAN IP (not NixOS-managed)
+  domainControllerIp = "192.168.2.253"; # FreeIPA — authoritative DNS for sweet.home (not NixOS-managed)
+
+  # FreeIPA server FQDN used by security.ipa and Kerberos. Must be a
+  # resolvable name (not an IP); resolves to domainControllerIp.
+  ipaServer = "domain-controller.${homeDomain}";
+
+  # ── Cross-host references ─────────────────────────────────────────────────
 
-  # Cross-host references (LAN hostnames/users other hosts reach over the network)
   nixCacheHost = "nix-cache"; # substituter/remote-builder hostname
-  nfsServerHost = "server"; # NFS export source hostname
   dockerHost = "docker"; # docker-compose stack host
 
-  # Raspberry Pi's own Tailscale hostname (not fronted by `server` — it
+  # Raspberry Pi's own Tailscale hostname (not fronted by any server — it
   # exports its own NFS share directly). Resolved as
   # "${raspberryPiHost}.${tailnetDomain}" in modules/raspi/mount-data.nix.
   raspberryPiHost = "raspberrypi";
 
-  remoteBuilderUser = "nixremote"; # remote builder SSH user
+  remoteBuilderUser = "nixremote";
 
-  # nix-cache's own SSH host public key (not a secret — the private half
-  # never leaves the host). Wired into every client's
-  # programs.ssh.knownHosts by modules/nix-cache/remote-builder-client.nix
-  # so distributed builds don't hit "Host key verification failed" on a
-  # fresh client that has never manually ssh'd to nix-cache before. Update
-  # this if nix-cache's host key is ever rotated or the host is rebuilt
-  # from scratch.
-  nixCacheHostKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPeWgMsdaiz4axT/deFc1+0B5bN+GX/NOeW9bbQ0c/IT lxc-nix-cache";
+  # Tailscale's internal "Quad100" DNS resolver, reachable from any Tailscale
+  # node via tailscale0. Used by modules/tailscale/ts-dns-forwarder.nix to
+  # forward *.tailnetDomain queries on behalf of FreeIPA's conditional
+  # forwarder zone.
+  tailscaleResolverIp = "100.100.100.100";
+
+  # ── SSH keys ──────────────────────────────────────────────────────────────
+
+  # nix-cache's SSH host public key (not a secret — private half never leaves
+  # the host). Wired into every client's programs.ssh.knownHosts by
+  # modules/nix-cache/remote-builder-client.nix so distributed builds don't
+  # hit "Host key verification failed" on a fresh client. Update if nix-cache
+  # is ever rebuilt with a new host key.
+  nixCacheHostKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICuHUxGNH6ei3BZD+EfZs3l4X8uJNcjQiOsM/G4yo4O/ lxc-nix-cache";
+
+  # Beszel hub's SSH public key — used by every agent to authenticate the
+  # hub's incoming connection. Update if the docker host is ever rebuilt and
+  # the hub generates a new keypair.
+  beszelHubKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFPR9kwtC4TAeTRu46A7+opZsYpxqkRJ+x/ZyB2GWCeG";
 
   # Public keys authorized to SSH in as remoteBuilderUser on the nix-cache
-  # host (modules/nix-cache/server.nix) — one per client host that's allowed
-  # to use it as a distributed builder.
+  # host (modules/nix-cache/server.nix) — one per client host allowed to use
+  # it as a distributed builder.
   remoteBuilderAuthorizedKeys = [
-    "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"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK+ioWPhHixlgCB9KIQ0QTHTz6A+Oo2F3uKiINLip5rO root@docker"
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
-    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIJEj26SL/emsVjW2YhRucJVp2kTz8WgcEQgjBEBLRikk root@claude"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAII/rLceRhnDobVXQYiPceuhDHHvVjFQ1pc9A6un/eUlA root@server"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHj11bLPpRzH2oslnwFzEvY9cSgfEFtSZbLQaDm4nZMK root@pxe-boot"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIH4/Sesm8NYpj73R0cbGhI0Ubvz73vIVWAnbEDTlBTdh root@tor-relay"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIBCFUUtePndW7pqtlawft1QCdHmBVs3O/c8EJO+RcXV root@tailscale-router"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIBZ9WKKAlP9Z7GQdgaZ1Xgw9C+vja2lqEZO5rJFpVqYN root@ha-server-1"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIEGNKlaaMckd8nLWNGz4B2QokXjnnIvM+rEUv+R6h0sp root@ha-server-2"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK+XeMco7OxUpjrjZm54HogMs9QB5xlcKmElASRvrmlW root@nixos"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIMseQwPpmaa6cgV5U8KhUsiVSYARG85zGa9rho0LJWks wayne@pve1"
   ];
 
-  # Admin SSH public key, authorized on the primary user of every host and
-  # the installer image's nixos/root users.
+  # Primary admin SSH public key, authorized on the primary user of every
+  # host and the installer image's nixos/root users.
   adminSshKey = "ssh-rsa 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 wayne@stream";
 
+  # Additional SSH keys granted access alongside adminSshKey on every host
+  # (modules/common/configuration.nix) and on HA cluster root
+  # (modules/ha/cluster-config.nix). Single definition here prevents the
+  # two modules from drifting out of sync.
+  extraAdminSshKeys = [
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGygkCljN6uKpdJbHTOQtn8ZnH+wKXDLAwrDFbLrE/65 nixos@nixos"
+  ];
+
+  # ── Wifi ──────────────────────────────────────────────────────────────────
+
   # Prestaged wifi SSID for the gui host's NetworkManager profile
-  # (modules/networking/wifi.nix). The password is not here -- it's
-  # sops-encrypted in secrets/gui.yaml (wifi-password) instead, since this
-  # file isn't a secret store.
+  # (modules/networking/wifi.nix). Password is sops-encrypted in
+  # secrets/gui.yaml (wifi-password) — not stored here.
   wifiSsid = "nbn-fttp-net-5G";
 
-  # Bare-metal gui host's two disks for a ZFS RAID0 (striped) root pool
-  # (modules/disko/baremetal.nix). Only used transiently at disko-format
-  # time (partitioning); the resulting fileSystems/zpool import reference
-  # by-partlabel/by-id paths afterward regardless, same as
-  # modules/disko/proxmox.nix's own plain "/dev/sda".
+  # ── Bare-metal GUI host ───────────────────────────────────────────────────
+
+  # Two disks for the ZFS RAID0 (striped) root pool on baremetal-gui
+  # (modules/disko/baremetal.nix). Only referenced at disko-format time;
+  # afterward the pool imports by-partlabel/by-id paths regardless.
   guiRootDisk1 = "/dev/sda";
   guiRootDisk2 = "/dev/sdb";
 
-  # System
+  # ── System / users ────────────────────────────────────────────────────────
+
   timeZone = "Australia/Brisbane";
 
-  # Main interactive user on every host. Every module that grants this user
-  # a group, a home directory, or tmpfiles ownership should reference
-  # vars.primaryUser rather than the literal "nixos", so renaming it is a
-  # one-line change.
+  # Main interactive user on every host. Modules that grant this user a
+  # group, home directory, or tmpfiles ownership reference this so a rename
+  # is a one-line change here.
   primaryUser = "nixos";
 
-  # Storage
-  storageRoot = "/tank"; # ZFS pool root on `server`
+  # Primary IPA/domain user. Home Manager is configured for this user on
+  # every IPA-enrolled host (modules/ipa/client.nix).
+  ipaUser = "wayne";
 
-  # NFS datasets exported from `storageRoot` on `nfsServerHost` and mounted
-  # by client hosts. `subpath` is relative to `storageRoot` — combined with
-  # it to build both the export line in modules/build-types/server.nix and
-  # the "<nfsServerHost>:<storageRoot>/<subpath>" device string each client
-  # mount uses in modules/docker/mount-data.nix. `mountpoint` is the
-  # absolute local path clients mount it at, referenced by that same file's
-  # fileSystems attribute name plus every other place that needs to know
-  # where the share lives locally (modules/build-types/docker.nix's
-  # tmpfiles rules, modules/traefik/rotate-logs.nix's log path). Renaming a
-  # dataset or moving where it's mounted only needs changing it here — the
-  # export and every client reference follow automatically.
+  # GID of the IPA "docker-access" group (GID 50010 on the IPA server). The
+  # local "docker" group is pinned to this GID on every Docker host so IPA
+  # group membership alone grants socket access — no per-host
+  # users.groups.docker.members entries needed.
+  dockerAccessGid = 50010;
+
+  # ── HA file-server cluster ────────────────────────────────────────────────
+  #
+  # Three network segments, all internal to pve1:
+  #   LAN            VLAN 2  / vmbr0 / 192.168.2.x    — management only
+  #   Cluster        VLAN 10 / vmbr1 / 192.168.10.x   — DRBD replication + Corosync ring0
+  #   Storage-client VLAN 20 / vmbr2 / 192.168.20.x   — iSCSI + NFS client access
+  #
+  # The host octet is consistent across subnets: node1 = .228, node2 = .227,
+  # VIP = .229 everywhere.
+  #
+  # Protocol separation (firewall-enforced on HA nodes):
+  #   NFS   — both subnets; LAN VIP for pxe-boot/LAN clients, storage VIP for docker
+  #   iSCSI — storage-client subnet only
+
+  haServer1Host = "ha-server-1";
+  haServer2Host = "ha-server-2";
+
+  haServer1Ip = "192.168.2.228"; # LAN IP, node 1 (vmbr0 / ens18)
+  haServer2Ip = "192.168.2.227"; # LAN IP, node 2 (vmbr0 / ens18)
+
+  haServer1StorageIp = "192.168.10.228"; # cluster-net IP, node 1 (vmbr1 / ens19, VLAN 10)
+  haServer2StorageIp = "192.168.10.227"; # cluster-net IP, node 2 (vmbr1 / ens19, VLAN 10)
+  haStorageCidr = "192.168.10.224/29"; # cluster subnet — VLAN 10, internal to pve1
+  haStoragePrefixLength = 29;
+
+  haServer1ClientIp = "192.168.20.228"; # storage-client IP, node 1 (vmbr2 / ens20, VLAN 20)
+  haServer2ClientIp = "192.168.20.227"; # storage-client IP, node 2 (vmbr2 / ens20, VLAN 20)
+  haServerVip = "192.168.20.229"; # storage-client floating VIP (Pacemaker vip-storage, VLAN 20)
+  haServerLanVip = "192.168.2.229"; # LAN floating VIP (Pacemaker vip-lan) — NFS for LAN clients
+  dockerStorageIp = "192.168.20.225"; # docker CT storage-client IP (vmbr2 / eth1, VLAN 20)
+  haClientCidr = "192.168.20.0/24"; # storage-client subnet — VLAN 20, internal to pve1
+  haClientPrefixLength = 24;
+
+  haStorageRoot = "/srv/ha-data"; # XFS-over-DRBD mount point on the Active node
+
+  # NFS VIP FQDNs — use these in fileSystems device strings so mounts
+  # survive a future VIP renumber via a DNS-only update, not a NixOS rebuild.
+  haStorageNfsFqdn = "nfs.storage.home"; # storage-client VIP (VLAN 20) — docker + future swarm
+  haLanNfsFqdn = "ha-vip-lan.${homeDomain}"; # LAN VIP (VLAN 2) — pxe-boot + other LAN clients
+
+  haIscsiIqn = "iqn.2026-01.home.sweet:ha-storage";
+
+  # DRBD backing disk — identified by SCSI controller path so it resolves to
+  # the correct block device regardless of OS-level naming (sda vs sdb can
+  # differ between VMs depending on disk-add order). drive-scsi1 is always
+  # the data disk; drive-scsi0 is the OS disk.
+  haServerDrbdDisk = "/dev/disk/by-id/scsi-0QEMU_QEMU_HARDDISK_drive-scsi1";
+
+  # ── Docker Swarm cluster ──────────────────────────────────────────────────
+  #
+  # Three network segments, all internal to pve1:
+  #   LAN            vmbr0  192.168.2.0/24    — management; SSH + external service traffic
+  #   Storage-client vmbr2  192.168.20.0/24   — NFS from HA cluster VIP (shared with HA nodes)
+  #   Swarm cluster  vmbr3  192.168.30.0/24   — Docker Swarm gossip + VXLAN overlay
+  #
+  # Host octet consistent across subnets: node1 = .230, node2 = .231.
+  # IPs from the .230–.239 expansion buffer documented in docs/ip-addressing.md.
+  #
+  # Docker Swarm uses --advertise-addr and --data-path-addr on the swarm NIC
+  # (ens20/vmbr3) so all inter-node cluster traffic stays on the isolated
+  # internal bridge and never crosses the LAN.
+  #
+  # When expanding to a second Proxmox node, vmbr3 (VLAN 30) and vmbr1
+  # (VLAN 10) share the same inter-node trunk NIC via VLAN tagging — same
+  # physical wire, different VLAN IDs.
+
+  haDocker1Host = "ha-docker-1";
+  haDocker2Host = "ha-docker-2";
+
+  haDocker1Ip = "192.168.2.230";          # LAN management NIC (ens18, vmbr0)
+  haDocker2Ip = "192.168.2.231";
+
+  haDocker1StorageIp = "192.168.20.230";  # storage-client NIC (ens19, vmbr2)
+  haDocker2StorageIp = "192.168.20.231";
+
+  haDocker1SwarmIp = "192.168.30.230";    # swarm cluster NIC (ens20, vmbr3)
+  haDocker2SwarmIp = "192.168.30.231";
+
+  haDockerSwarmCidr = "192.168.30.0/24";
+  haDockerSwarmPrefixLength = 24;
+
+  # NIC names for ha-docker VMs. ens19/ens20 occupy the same guest bus
+  # positions as vmStorageInterface/vmStorageClientInterface on ha-server VMs
+  # but are attached to different bridges — storage (vmbr2) and swarm (vmbr3)
+  # respectively. Kept as named variables to avoid bare literals in modules.
+  haDockerStorageInterface = "ens19";  # vmbr2 — NFS client
+  haDockerSwarmInterface   = "ens20";  # vmbr3 — Docker Swarm gossip + VXLAN
+
+  # ── Storage / NFS ─────────────────────────────────────────────────────────
+
+  # NFS share definitions — used by ha-server.nix (exports), docker/mount-data.nix,
+  # and pxe-boot/mount-pxe-images.nix (mounts). `subpath` is relative to
+  # haStorageRoot; `mountpoint` is the absolute local path on each client.
+  # Renaming a share only requires changing it here — exports and all client
+  # mounts follow automatically.
   nfsShares = {
-    dockerConfig = {
-      subpath = "docker/config";
-      mountpoint = "/mnt/docker/config";
-    };
-    dockerDatabases = {
-      subpath = "docker/databases";
-      mountpoint = "/mnt/docker/databases";
-    };
-    dockerVolumes = {
-      subpath = "docker/volumes";
-      mountpoint = "/mnt/docker/volumes";
-    };
-    nextcloudData = {
-      subpath = "docker/nextcloud-data";
-      mountpoint = "/mnt/nextcloud-data";
-    };
-    raspiVolumes = {
-      subpath = "raspi/volumes";
-      mountpoint = "/mnt/raspi-backup";
-    };
+    options = "(rw,sync,no_subtree_check,no_root_squash)";
+    dockerConfig = { subpath = "docker/config"; mountpoint = "/mnt/docker/config"; };
+    dockerDatabases = { subpath = "docker/databases"; mountpoint = "/mnt/docker/databases"; };
+    dockerVolumes = { subpath = "docker/volumes"; mountpoint = "/mnt/docker/volumes"; };
+    nextcloudData = { subpath = "docker/nextcloud-data"; mountpoint = "/mnt/nextcloud-data"; };
+    raspiVolumes = { subpath = "raspi/volumes"; mountpoint = "/mnt/raspi-backup"; };
+    proxmoxIsos = { subpath = "proxmox/iso"; mountpoint = "/mnt/iso"; };
+    proxmoxLxcImages = { subpath = "proxmox/lxc"; mountpoint = "/mnt/lxc"; };
+    pxebootImages = { subpath = "pxe-boot/images"; mountpoint = "/mnt/pxe-images"; };
   };
 
-  # The Raspberry Pi's own NFS export — not under storageRoot/nfsServerHost,
-  # served directly by the Pi itself over Tailscale (see raspberryPiHost
-  # above) and mounted at raspiMountpoint by modules/raspi/mount-data.nix.
+  # The Raspberry Pi's own NFS export — not under haStorageRoot, served
+  # directly by the Pi over Tailscale (see raspberryPiHost) and mounted by
+  # modules/raspi/mount-data.nix.
   raspiNfsPath = "/home/raspi/raspi";
   raspiMountpoint = "/mnt/raspi";
 
+  # ── Ports ─────────────────────────────────────────────────────────────────
+  #
   # Every literal port referenced from modules/ or hosts/, grouped by the
-  # service/host that opens or connects to it — kept as separate entries
-  # even where two happen to share a number today (e.g. nixCacheHttp and
-  # pxeBootHttp are both 80) so changing one service's port can never
-  # silently change an unrelated one.
+  # service that opens or connects to it. Kept as separate entries even where
+  # two share a number today (e.g. nixCacheHttp and pxeBootHttp are both 80)
+  # so changing one service's port never silently changes another.
+
   ports = {
     # nix-cache's nginx reverse proxy in front of nix-serve
-    # (modules/nix-cache/server.nix).
+    # (modules/nix-cache/server.nix)
     nixCacheHttp = 80;
 
-    # pxe-boot's nginx asset server, also used to build pxeBaseUrl
-    # (modules/build-types/pxe-boot.nix).
+    # pxe-boot's nginx asset server; also used to build pxeBaseUrl
+    # (modules/build-types/pxe-boot.nix)
     pxeBootHttp = 80;
 
-    # pxe-boot's atftpd TFTP server — UDP, not TCP
-    # (modules/build-types/pxe-boot.nix).
+    # pxe-boot's atftpd TFTP server — UDP (modules/build-types/pxe-boot.nix)
     pxeBootTftp = 69;
 
-    # `server`'s NFS exports need both the portmapper (rpcbind) and the
-    # NFS data port itself opened (modules/build-types/server.nix).
+    # DHCP proxy port opened by dnsmasq on the pxe-boot host
+    # (modules/build-types/pxe-boot.nix)
+    dhcp = 67;
+
+    # DNS port opened on tailscale-router for FreeIPA's conditional forwarder
+    # (modules/tailscale/ts-dns-forwarder.nix)
+    dns = 53;
+
+    # NFS stack: portmapper (rpcbind), NFS data, and mountd RPC service.
+    # Mountd is pinned to a fixed port so the firewall can whitelist it
+    # without opening rpcbind's full dynamic range. All three need TCP + UDP
+    # (modules/build-types/ha-server.nix).
     nfsRpcbind = 111;
     nfsd = 2049;
+    nfsMountd = 20048;
 
-    # Opened on the docker host's firewall for the Traefik-fronted
-    # container stack (docker-compose config lives in the separate
-    # /home/debian/docker repo, not here): 80/443 are Traefik's own
-    # HTTP/HTTPS listeners; 8080 is an additional exposed service whose
-    # exact backend isn't declared in this repo (modules/build-types/docker.nix).
+    # HA cluster ports (modules/ha/cluster-config.nix)
+    haServerDrbd = 7789; # DRBD replication (TCP)
+    haServerIscsi = 3260; # iSCSI target (TCP)
+    haServerCorosync1 = 5404; # Corosync totem ring (UDP)
+    haServerCorosync2 = 5405; # Corosync totem ring (UDP)
+    haServerCorosyncCrypto = 5407; # Corosync crypto sync (UDP)
+    haServerPacemakerRemoted = 3121; # pacemaker-remoted (TCP)
+    haServerPcsd = 2224; # pcsd cluster daemon (TCP)
+
+    # Docker host — Traefik HTTP/HTTPS listeners plus one additional exposed
+    # service (modules/build-types/docker.nix)
     dockerHttp = 80;
     dockerHttps = 443;
     dockerExtra = 8080;
 
-    # Beszel monitoring hub, reachable at
-    # http://<dockerHost>.<homeDomain>:<beszelHub> from every agent
-    # (modules/beszel/enable-agent.nix, hosts/nixos/home.nix).
+    # Docker Swarm inter-node ports (modules/build-types/ha-docker.nix).
+    # Firewalled to haDockerSwarmCidr only — vmbr3 is an isolated bridge
+    # with no physical uplink, so these ports are unreachable from LAN.
+    dockerSwarmMgmt  = 2377;  # TCP   — Raft consensus + cluster management
+    dockerSwarmDisc  = 7946;  # TCP+UDP — Serf gossip (container network discovery)
+    dockerSwarmVxlan = 4789;  # UDP   — VXLAN overlay data path
+
+    # Beszel monitoring hub on docker.sweet.home, reached by every agent
+    # (modules/beszel/enable-agent.nix, hosts/nixos/home.nix)
     beszelHub = 8090;
 
-    # Proxmox VE and Proxmox Backup Server web UIs, opened as desktop
-    # shortcuts on the gui build type (hosts/nixos/home.nix).
+    # Proxmox VE and PBS web UIs — desktop shortcuts on the gui build type
+    # (hosts/nixos/home.nix, modules/build-types/gui.nix)
     pveWeb = 8006;
     pbsWeb = 8007;
 
-    # Tor relay's ORPort — the port other Tor relays connect to for onion
-    # routing traffic (modules/tor/enable-relay.nix). Tor's own conventional
-    # default; opened via services.tor.openFirewall rather than
-    # networking.firewall.allowedTCPPorts directly, but kept here anyway so
-    # it's not a bare literal duplicated between the relay's settings and
-    # anything else that ever needs to reference it.
+    # Tor relay's ORPort (modules/tor/enable-relay.nix). Opened via
+    # services.tor.openFirewall rather than allowedTCPPorts directly, but
+    # kept here so it's not a bare literal if ever referenced elsewhere.
     torRelayOrPort = 9001;
   };
 
-  # .raw disk image size for every proxmox-* host's standalone Disko image
-  # build (modules/disko/proxmox.nix, config.system.build.diskoImagesScript
-  # — see docs/proxmox-images.md). Root fills whatever's left after the ESP
-  # and swap partitions within this total.
-  proxmoxImageSize = "20G";
+  # ── Build / image settings ────────────────────────────────────────────────
 
-  # nix-cache's Nix store garbage collection retention
-  # (modules/nix-cache/server.nix).
+  # .raw disk image size for every proxmox-* host's standalone Disko image
+  # build (modules/disko/proxmox.nix — see docs/proxmox-images.md).
+  proxmoxImageSize = "50G";
+
+  # nix-cache Nix store GC retention (modules/nix-cache/server.nix)
   nixCacheGcMaxAge = "30d";
 
   # Traefik access log rotation, watched on the docker host at
-  # nfsShares.dockerVolumes.mountpoint (modules/traefik/rotate-logs.nix).
+  # nfsShares.dockerVolumes.mountpoint (modules/traefik/rotate-logs.nix)
   traefikLogRotate = {
     maxSize = "100M"; # rotate once a log file exceeds this size
-    keep = 20; # number of rotated logs to retain before deleting the oldest
+    keep = 20; # number of rotated logs to retain
   };
-
 }

vars/per-machine/baremetal-gui/openssh/ssh_host_ed25519_key.pub/value

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPwUaVHP4MHZXicMAYGOe2ME1tp+CJShr8WocevlGWMh baremetal-gui

vars/per-machine/baremetal-gui/openssh/ssh_host_ed25519_key/secret

@@ -0,0 +1,14 @@
+{
+	"data": "ENC[AES256_GCM,data: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,iv:vpaX2prOsN/4Ke2HvoNHHp86DQpcPC6EtfgWvlgRGlQ=,tag:2Fv0oy99E88owAnB1fkvDw==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBsU2pBT3M1TGJUYVlWUjNp\nN3JudVdVamN0TnF6cjlXN3BJRW5HbDFIZTBZCmhyRlQyNkl4bjBjOEhMZVhmQWxK\nVEJvaEpnTDREOXlKV3VxYzdkcW5tUEkKLS0tIHROY2RZeXFKQXBUeTZLODEzTGxZ\nSHl4WFhmOWVVR2NEcUxQSCtObU8xWkUKa/qmGyWYuEjf+BCoag5H9cA4ovW+ro8V\nhGsi3GqPEFfrI+qx/e6JqxazYpwfwIEaMZljhfgoFzg0I1U7OsnpSQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			}
+		],
+		"lastmodified": "2026-07-25T11:45:21Z",
+		"mac": "ENC[AES256_GCM,data:7xbxAir+/3FbbJU4L4qRpZIYr/gqyoHjGxJvYYVLZ5yZLs8k/UiTG/qlu2zVkN2yfQaUzAu4/bQco5vOin6pwFodRH8BK4fbVIOheExzN1fk2uayejt/wWRiWj8w+qH+HaWLejlvrmbNced9HTiGViAHa+EZv3OUphlZKAdk/3Q=,iv:ZBuC8htjmKKc84kCBRHj7TdRdiPaEGeVMl+8ydOfIMc=,tag:uO4evh0xShWmG8kY/AkOWQ==,type:str]",
+		"version": "3.13.2"
+	}
+}

vars/per-machine/linode-docker/openssh/ssh_host_ed25519_key.pub/value

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIO+Ub4qK5Asqgi3A17zEy/+VOQ4ozL85ZBvlJnyhLZHD linode-docker

vars/per-machine/linode-docker/openssh/ssh_host_ed25519_key/secret

@@ -0,0 +1,14 @@
+{
+	"data": "ENC[AES256_GCM,data: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,iv:GfqfGPjKxpOhdLJvJWTduYe2FbIKrMlKevErvnxfOa0=,tag:khM375z1e04y/JebLz/VgA==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBSbS96Rmc4eDJkNGNUV2c3\nS3FCYnY1TCtOWXh1MzBPbnRnL09VbzNxblZBCkp5NkpxUXlJbUFjay9KbjVZeGc3\nTzgxRk0yKzU0SFBGelBDZnVHVzNaNlUKLS0tIFZRWXFUVW56a2owWk9TYXZPTE9r\nbmZHcG5ZN1dla3pXa3ZhOUdjR2dyTVkKaqAlfNkc2wzjB2//7DzW7JWg2BZd0Vqe\nO9YttWf4ikU6vfM+M/yiWGpWJ4U8p/3PBmT3ZLQBRGRtcyPby5DxZQ==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			}
+		],
+		"lastmodified": "2026-07-25T11:45:23Z",
+		"mac": "ENC[AES256_GCM,data:+arWx20i4iAlFhbzH8/R9jggzJEP2PlEzyBnbAiDYZhp+2vfbsn+28WBzmjhi4AXz8CbBrhhFS6IFmYQZSFyYFuT943qoo82d/8E6p1DoyEEBL856SmkuVKpCq6IpWEJmkj8j7z3yyrpXva0aagReP+8+agWI+wWdNmG9M2tBRQ=,iv:Edqregq0OXRM4AWJ9EOtR/dZCObRepHnP4s8SYYkKHo=,tag:bBSiY7EVtli41w9s6JbQVw==,type:str]",
+		"version": "3.13.2"
+	}
+}

vars/per-machine/linode-gui/openssh/ssh_host_ed25519_key.pub/value

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOFHRs2HkjhOL/Ilii8PiwxGkQNsstmGn/Bs2Vx/OWsI linode-gui

vars/per-machine/linode-gui/openssh/ssh_host_ed25519_key/secret

@@ -0,0 +1,14 @@
+{
+	"data": "ENC[AES256_GCM,data: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,iv:g87PWSi9TyN4GwZdYAxUbRpJvtoYSon6tIoz4SC5bWg=,tag:hDem9tgzD0/lg44g3Us0vg==,type:str]",
+	"sops": {
+		"age": [
+			{
+				"enc": "-----BEGIN AGE ENCRYPTED FILE-----\nYWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSByQWUxUHpyZkk5aFNFMTVY\nc09vcHdDUFIwUHA1TVhwblVPMWRiS0dTaHlBCmtHWk9YTVRTcGJndjQ3bmhIWEJL\nMkFVdzNmU3RRUGN6clhZNGRtVnRTQjgKLS0tIFoxWnBsa2Y2MTM2SjBjNjhrUDNx\nU1dyZkhpZHZkb2toeUFpS2tLN2Fic1EKUxQ1J57TJytHqIuLowiSyoS/nJPxSoZI\ni35CHWWE0+Y344m/DmdJPspvYZSI3rY1JbgaqjIKZrshDggZVTka2A==\n-----END AGE ENCRYPTED FILE-----\n",
+				"recipient": "age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad"
+			}
+		],
+		"lastmodified": "2026-07-25T11:45:25Z",
+		"mac": "ENC[AES256_GCM,data:ARpnwhj3Y88r6FsqPFBUK/Nth/R6Kfel5cVtlKqjkAdK1FB5BMmdxNbbOn2AH7+zlzdH7qRKvkH49CS6P+bfLaIJBkdLanzF0lSzxq8+88fgqFhJi+mroAZGH6OJaVcHVdTytaE2b8xAMeoz07e1Smp07F6Sp5mwHemAB9EHi38=,iv:JrYUaIGeJYLcgKj845irmKPH05tD9z6Rabv1B5tVmZw=,tag:gK5X/dBJvrWF8LTpdhytAg==,type:str]",
+		"version": "3.13.2"
+	}
+}

vars/per-machine/linode-minimal/openssh/ssh_host_ed25519_key.pub/value

@@ -0,0 +1 @@
+ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPp8ZFWz97BFJJxHE+3w0/RpIXpRV64XE0eNBYl3jpSz linode-minimal