Export ZFS root pool before rebooting from the auto-installer

disko's --mode ...,mount leaves the pool imported (needed for
nixos-install to write into /mnt), and the script rebooted straight
into the newly-installed system without exporting it. That pool is
still stamped with the live installer's own hostid, which never
matches the target host's declared networking.hostId, and since
boot.zfs.forceImportRoot is false (the recommended setting, not a bug),
the first real boot refuses to force-import an unexported pool from a
different hostid -- which is exactly the ZFS-import stall baremetal-gui
was hitting after install. Exporting all pools right before reboot (a
no-op for non-ZFS hosts) clears the in-use state so import succeeds
regardless of hostid.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.gitea/workflows/check-nixos.yml

@@ -13,9 +13,17 @@ jobs:
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Install Nix
         uses: DeterminateSystems/nix-installer-action@v19
 
-      - name: Run maintenance checks (secrets, fmt, lint, eval)
+      # Scoped to files changed since the PR base / previous push -- see
+      # scripts/codex-maintenance.sh. CI never passes --full-check: that
+      # full sweep is for local/manual use, since it's slow enough to time
+      # out this runner.
+      - name: Run maintenance checks (secrets, fmt, lint, eval -- changed files only)
+        env:
+          MAINT_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
         run: bash scripts/codex-maintenance.sh

.github/workflows/check-nixos.yml

@@ -13,9 +13,17 @@ jobs:
     steps:
       - name: Check out repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Install Nix
         uses: DeterminateSystems/nix-installer-action@v19
 
-      - name: Run maintenance checks (secrets, fmt, lint, eval)
+      # Scoped to files changed since the PR base / previous push -- see
+      # scripts/codex-maintenance.sh. CI never passes --full-check: that
+      # full sweep is for local/manual use, since it's slow enough to time
+      # out this runner.
+      - name: Run maintenance checks (secrets, fmt, lint, eval -- changed files only)
+        env:
+          MAINT_BASE_SHA: ${{ github.event.pull_request.base.sha || github.event.before }}
         run: bash scripts/codex-maintenance.sh

.sops.yaml

@@ -1,12 +1,18 @@
 keys:
-  - &admin age10nd382a9klsn2mrs60emdtsxe43pht3a0m9p29phfrhy0wfyt3vsq9r667
+  - &admin age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
   - &docker age19gfn2yedg76dmztm4hncr7vf3r3c9j0qpt4rap7y7gersjk4m3ks2lhd0e
   - &server age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
   - &nix-cache age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
-  - &lxc-minimal age1qz9d4ka4xgexujyd247s7lp737sulp5fhxl5d65fj2ykvc4j4edqrsdks8
   - &nix-minimal age120whqj96g26lsgy4udvgsn8dc9lumh8jeu3a564fx79rjr5lxffqmrljuu
-  - &lxc-nix-cache age164px2a8e48ptsf9ngtan38aa6jls4jdl26mzrgzf6sn3vcvt49hqjrgr8w
   - &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
 
 creation_rules:
   # Shared across every currently-deployed host: root/nixos password hash,
@@ -24,6 +30,12 @@ creation_rules:
           - *nix-minimal
           - *lxc-nix-cache
           - *proxmox-minimal
+          - *lxc-docker
+          - *lxc-pxe-boot
+          - *lxc-gui
+          - *proxmox-server
+          - *vm-server
+          - *baremetal-gui
 
   - path_regex: secrets/nix-cache\.yaml$
     key_groups:
@@ -37,9 +49,24 @@ creation_rules:
       - age:
           - *admin
           - *server
+          - *proxmox-server
+          - *vm-server
 
   - path_regex: secrets/docker\.yaml$
     key_groups:
       - age:
           - *admin
           - *docker
+
+  # gui-host-specific secrets (currently: wifi-password, see
+  # modules/networking/wifi.nix). Only *lxc-gui has a registered key today
+  # -- proxmox-gui/linode-gui/baremetal-gui haven't been provisioned via
+  # scripts/secrets/sync-host-keys.sh yet, so whichever variant is actually
+  # deployed next needs its recipient added here (and `sops updatekeys` rerun)
+  # before it can decrypt this.
+  - path_regex: secrets/gui\.yaml$
+    key_groups:
+      - age:
+          - *admin
+          - *lxc-gui
+          - *baremetal-gui

AGENTS.md

@@ -7,7 +7,7 @@ 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`), generated from `modules/platforms/*`
+`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
@@ -35,9 +35,14 @@ Use these commands when validating changes:
 ```bash
 bash scripts/codex-setup.sh
 bash scripts/codex-maintenance.sh
-bash scripts/codex-maintenance.sh dry-run
 ```
 
+With no flags, `codex-maintenance.sh` scopes fmt-check/statix/eval to files
+changed against a base ref — this is what CI runs on every push/PR. For the
+full sweep (every host, every package — slow; CI never runs this), use
+`bash scripts/codex-maintenance.sh --full-check` (add `--dry-run` for build
+planning on top of whichever scope is active).
+
 Host evaluation is safe when limited to drvPath checks:
 
 ```bash

AUDIT_REPORT.md

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

CLAUDE.md

@@ -31,17 +31,96 @@ machines when deployed.
   the auto-installer (see `docs/auto-installer.md`). Never commit its
   contents; if `git status` ever shows it as trackable, something is wrong.
 
+### Two Proxmox nodes: `pve1.sweet.home` (production) and `pve-test.sweet.home` (sandbox)
+
+There are two SSH-reachable Proxmox nodes on the LAN, both defined in
+`scripts/env.sh` (`PVE1_HOST` / `PVE_TEST_HOST`), individually targetable
+via `scripts/proxmox/create-proxmox-resource.sh --node <host>` or by
+overriding `PROXMOX_HOST`. `PROXMOX_HOST` itself still defaults to
+`PVE1_HOST` (production) — that default, and every other script behavior,
+is unchanged from before `pve-test` existed; the only thing new is that
+`pve-test` can now be reached at all. They are **not interchangeable** —
+one is real production infrastructure, the other exists specifically so
+there's somewhere safe to test. The restriction below is a policy for
+Claude specifically, not a change to the tooling's own default or
+anything the operator needs to opt into.
+
+#### `pve1.sweet.home` (production — off-limits to Claude)
+
+A real, live Proxmox node hosting production VMs/containers — not a
+sandbox, and not Claude's to touch by default.
+
+- **Off-limits at all times unless the operator has given explicit,
+  same-session instructions to act on this specific host.** That
+  authorization is scoped to the task it was given for — don't carry it
+  forward to unrelated later work in the same conversation, and never
+  assume it from a previous session.
+- **Read-only for existing state is always fine, authorization or not.**
+  You may SSH in (or use `pvesm`, `qm list`, `pct list`, `qm config`, `pct
+  config`, the Proxmox API, etc.) to inspect the node's config, storage,
+  and any existing VM/container — including ones this repo didn't create.
+- **Never** modify, stop, restart, delete, reconfigure, or create anything
+  on this node (`qm set`, `pct set`, `qm destroy`, `pct destroy`, `qm
+  stop`, `pct stop`, `qm create`, `pct create`, snapshot operations,
+  storage changes, etc.) — including scratch/test resources — without
+  that explicit go-ahead. Use `pve-test.sweet.home` for anything
+  exploratory instead; it exists precisely so `pve1` never has to be the
+  answer to "where do I test this."
+- **This is a Claude-specific policy, not something the scripts enforce.**
+  `scripts/env.sh`/`create-proxmox-resource.sh` default to `pve1` exactly
+  as they did before `pve-test` existed, with no extra flag or prompt
+  required — that's deliberate, so the operator's own existing workflows
+  don't change. Claude, however, must never rely on that default: every
+  Proxmox action Claude takes on its own initiative — not explicitly
+  pointed at `pve1` by the operator this session — targets `pve-test`
+  instead (e.g. `--node "$PVE_TEST_HOST"`, or `PROXMOX_HOST=$PVE_TEST_HOST`).
+  Claude's own default is `pve-test`, full stop, regardless of what the
+  tooling's own unqualified default happens to be.
+
+#### `pve-test.sweet.home` (sandbox — Claude's default target)
+
+A separate Proxmox node set aside for testing. The *tooling's* default is
+still production (`PROXMOX_HOST` → `PVE1_HOST`, see above) — but
+**Claude's own default is this node**: absent an explicit, same-session
+instruction to use `pve1`, every Proxmox action Claude initiates targets
+`pve-test`. Once targeted, it's safe to create, interrogate, and destroy
+resources on without asking first.
+
+- **Test VMs/containers are allowed, but must be torn down.** Create a
+  scratch VM or container here (e.g. via
+  `scripts/proxmox/create-proxmox-resource.sh` or raw `qm`/`pct create`)
+  to validate something. Anything created this way must be destroyed
+  again in the same session, before ending the task — never leave a test
+  resource running. Use a VMID/name that's obviously scratch (and doesn't
+  collide with a real flake target) so it's unambiguous what's safe to
+  remove.
+- **Node-level config is still not yours to change.** Creating/destroying
+  your own scratch guests is fine; Proxmox host config, storage pools, and
+  networking on `pve-test` itself are still the operator's call to make
+  manually, same as on `pve1`.
+
 ## Commands
 
 ```bash
 # One-time environment bootstrap (installs Nix if missing, prints hosts)
 bash scripts/codex-setup.sh
 
-# Full validation: secret grep, nixpkgs-fmt --check, statix lint, eval all hosts
+# Changed-files-only validation: secret grep (whole repo), nixpkgs-fmt --check
+# and statix on changed *.nix files, eval of the hosts/packages those changes
+# can affect. This is what CI runs on every push/PR.
 bash scripts/codex-maintenance.sh
 
-# Same, plus a dry-run build (no result symlink) of every host's toplevel
+# Full sweep: nixpkgs-fmt --check/statix over the whole tree, eval every host
-bash scripts/codex-maintenance.sh dry-run
+# and package. Slow (minutes) -- CI never runs this; use it locally before a
+# release or after touching modules/common/*, flake.nix, or variables.nix for
+# extra confidence beyond the automatic full-fallback those paths already
+# trigger in the default mode (see below).
+bash scripts/codex-maintenance.sh --full-check
+
+# Either mode, plus a dry-run build (no result symlink) of every host/package
+# in whichever scope is active
+bash scripts/codex-maintenance.sh --dry-run
+bash scripts/codex-maintenance.sh --full-check --dry-run
 
 # List the hosts the flake currently exposes
 nix eval --json .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]'
@@ -58,35 +137,122 @@ maintenance script pulls them via `nix run github:NixOS/nixpkgs/nixos-25.11#<too
 There is no test suite — "correctness" here means the flake evaluates and
 `nixpkgs-fmt`/`statix` are clean.
 
-**In an interactive agent session**, prefer targeted checks over full-repo
+With no flags, `codex-maintenance.sh` diffs against a base ref (env
-sweeps: after editing one or two hosts/modules, evaluate just the
+`MAINT_BASE_SHA`, else the PR base SHA in CI, else `HEAD^` locally) and scopes
-`nixosConfigurations.<host>` you touched (plus any `config.system.build.tarball`
+fmt-check/statix to the changed `*.nix` files and eval to the hosts/packages
-/`diskoImagesScript`/package output affected) rather than looping over every
+those changes can affect — a `hosts/<name>/host.nix` edit only evals that
-host — `codex-maintenance.sh` evaluates 18 hosts plus every package/tarball/
+host's targets, a `modules/platforms/<platform>.nix` edit only evals that
-image variant now and is slow to run after each small change. Reserve a full
+platform's hosts, and so on. A change to `flake.nix`, `flake.lock`,
-`codex-maintenance.sh` run for changes that plausibly affect every host
+`variables.nix`, `modules/common/*`, or any other `modules/*.nix` file outside
-(`modules/common/*`, `flake.nix`, `variables.nix`) or as a final check before
+`platforms/`/`build-types/` (whose blast radius isn't safely inferable from
-committing. This is a session-workflow preference only — it does not apply to
+the path alone) falls back to evaluating every host and package, same as
-CI, which should keep running the full script on every push/PR regardless of
+`--full-check` would, just without the whole-tree fmt/statix sweep. This
-diff size; that's the point of it.
+exists because the whole-tree sweep is what was timing out CI; **CI always
+runs the plain, no-flag form and never passes `--full-check`.**
+
+The default mode's diff is against the working tree (uncommitted and staged
+edits included, not just committed ones), so it's already the right tool for
+an interactive session too: after editing one or two hosts/modules, plain
+`bash scripts/codex-maintenance.sh` naturally scopes to just what you
+touched. Reserve `--full-check` for changes that plausibly affect every host
+(`modules/common/*`, `flake.nix`, `variables.nix` — though the default mode
+already falls back to evaluating everything for those paths, `--full-check`
+additionally re-checks fmt/statix over the whole tree) or as a final check
+before committing.
 
 ## Scripts
 
-Beyond `codex-setup.sh`/`codex-maintenance.sh` above, `scripts/` also has:
+Beyond `codex-setup.sh`/`codex-maintenance.sh` above, `scripts/` is
+organized by purpose: `scripts/secrets/` (sops/age + SSH host-key
+management), `scripts/proxmox/` (Proxmox deployment), `scripts/installer/`
+(the auto-installer's own shell script, templated into the image — see
+below), `scripts/lib/` (shared helpers, sourced by the scripts below — not
+run directly), and a handful of repo-wide scripts left at the top level
+(`env.sh`, `bump-nixpkgs-release.sh`, plus `codex-setup.sh`/
+`codex-maintenance.sh` above). When adding a new script, put it in the
+matching subfolder rather than the top level, and if it duplicates logic
+another script already has, lift the shared part into `scripts/lib/`
+instead of copying it.
 
-- `scripts/sync-host-keys.sh` — generates/registers SSH host keys and their
+### `scripts/installer/`
-  `.sops.yaml`/`secrets/*.yaml` recipients for flake targets, idempotently
+
-  (`--all`, `<target>`, `--remove`, `--regenerate-all-keys`, all with
+- `scripts/installer/auto-install.sh` — the interactive install script
-  `--dry-run`). The primary tool for provisioning a new host's secrets
+  baked into the auto-installer image (see `docs/auto-installer.md`), kept
-  access — see "Creating a new machine" in `docs/auto-installer.md`.
+  as a real, version-controlled shell file rather than inline in
-- `scripts/prepare-host-key.sh` — narrower predecessor: generates a key by
+  `modules/installer/common.nix`'s Nix. It sources `scripts/env.sh` itself
-  an arbitrary name without touching `.sops.yaml`. Still useful to
+  for `LAN_DOMAIN` (`export LAN_DOMAIN`/`: "${LAN_DOMAIN:=...}"`, matching
+  `variables.nix`'s `lanDomain` — manually kept in sync, same pattern as
+  `NIX_CACHE_HOST` mirroring `nixCacheHost`), rather than Nix-level string
+  substitution — that's what makes it work identically whether run
+  straight from a git checkout or from inside the built installer image.
+  `common.nix` bakes `scripts/env.sh` in alongside it at a matching
+  relative path (`/etc/nixos-installer/env.sh` next to
+  `/etc/nixos-installer/installer/auto-install.sh`) so the script's own
+  `source "$(dirname ...)/../env.sh"` line resolves the same way in both
+  contexts — this is also why it's invoked from
+  `/etc/nixos-installer/installer/auto-install.sh` rather than a flat
+  `/etc/auto-install.sh`. `#!/usr/bin/env bash`, not
+  `#!/run/current-system/sw/bin/bash`: the latter only resolves on an
+  already-activated NixOS system, breaking the checked-out-file case
+  entirely (confirmed live: "cannot execute: required file not found" on
+  a non-NixOS box); `/usr/bin/env` is reliably present on both NixOS
+  (`environment.usrbinenv`'s own default) and any normal Linux distro.
+
+### `scripts/secrets/`
+
+- `scripts/secrets/sync-host-keys.sh` — generates/registers SSH host keys
+  and their `.sops.yaml`/`secrets/*.yaml` recipients for flake targets,
+  idempotently (`--all`, `<target>`, `--remove`, `--regenerate-all-keys`,
+  all with `--dry-run`). The primary tool for provisioning a new host's
+  secrets access — see "Creating a new machine" in `docs/auto-installer.md`.
+- `scripts/secrets/prepare-host-key.sh` — narrower predecessor: generates a
+  key by an arbitrary name without touching `.sops.yaml`. Still useful to
   pre-generate a key before its flake target exists yet, since
   `sync-host-keys.sh` can only act on targets `nixosConfigurations` already
   has.
-- `scripts/create-proxmox-resource.sh` — builds a `lxc-*`/`proxmox-*`
+- `scripts/secrets/rotate-admin-key.sh <backup-admin-key> [--new-key-file
-  target's tarball/disk image and creates it on a real Proxmox node
+  <path>] [--dry-run]` — rotates `.sops.yaml`'s `&admin` age key: decrypts
-  (`pct create` against the tarball as a CT template / `qm create`+
+  with a backed-up copy of the key currently trusted as `&admin` (verified
+  by deriving its public key and comparing, not taken on faith), replaces
+  the `&admin` line with a new key already present in the environment
+  (defaults to wherever sops/age itself would look), and runs
+  `sops updatekeys` on every `secrets/*.yaml`. One-way: the old key can no
+  longer decrypt anything re-encrypted this way. This is the automation
+  for the manual steps `sync-host-keys.sh`/`create-proxmox-resource.sh`
+  print when they bootstrap a brand-new, not-yet-trusted key on a machine
+  with no prior admin access.
+- `scripts/secrets/backup-admin-key.sh <dest-path> [--key-file <path>]
+  [--force] [--dry-run]` — copies the local sops age key (source
+  resolution matches sops/age itself: `$SOPS_AGE_KEY` inline, then
+  `--key-file`, then `$SOPS_AGE_KEY_FILE`, then the XDG default) to an
+  arbitrary destination path with `0600` permissions, validating it's a
+  real age identity and round-tripping the public key before and after the
+  write. Refuses to overwrite an existing `<dest-path>` without `--force`.
+  Purely a local filesystem copy — never touches `.sops.yaml`/
+  `secrets/*.yaml` or the repo at all. The resulting file is exactly what
+  `rotate-admin-key.sh` expects as its backup-key argument.
+- `scripts/secrets/sync-nix-cache-host-key.sh [--check] [--dry-run]
+  [--host <name>]` — detects drift between the ed25519 SSH host key
+  nix-cache is actually serving right now (via `ssh-keyscan`) and
+  `vars.nixCacheHostKey` (`variables.nix`), the value
+  `modules/nix-cache/remote-builder-client.nix` bakes into every real
+  client's declarative `programs.ssh.knownHosts` and
+  `configure-nix-cache-client.sh` hardcodes as its own default for
+  non-NixOS clients. That value has no automatic source of truth — it's
+  set once from whatever nix-cache's host key happened to be at the time,
+  and silently goes stale if the host is ever rebuilt/recreated with a new
+  key, breaking every client's distributed-build SSH trust with no error
+  that points back here. `--check` (used by `codex-maintenance.sh`, which
+  treats an unreachable nix-cache — e.g. from a non-LAN CI runner — as a
+  silent skip rather than a failure) only reports drift; the no-flags form
+  updates both files in place. Declarative clients still need a rebuild to
+  pick up the fix.
+
+### `scripts/proxmox/`
+
+- `scripts/proxmox/create-proxmox-resource.sh` — builds a `lxc-*`/
+  `proxmox-*` target's tarball/disk image and creates it on a real Proxmox
+  node (`pct create` against the tarball as a CT template / `qm create`+
   `importdisk`), or reconfigures an existing resource's cores/memory/disk
   size (`--modify`, always requires typing the VMID back to confirm).
   Checks for an already-uploaded image on the node before building
@@ -96,22 +262,71 @@ Beyond `codex-setup.sh`/`codex-maintenance.sh` above, `scripts/` also has:
   Refuses to create a target whose host identity already exists live on
   the node (checked directly via `qm`/`pct`, not any file in this repo)
   unless `--allow-duplicate-host` is passed. `--dry-run` throughout both
-  modes.
+  modes. The first time it has to bootstrap build tooling on a node (i.e.
+  `nix` wasn't already on its `PATH`), it also runs
+  `scripts/proxmox/configure-nix-cache-client.sh` there (non-fatally — a
+  failure just falls back to building from source / `cache.nixos.org`) so
+  the node substitutes from and can offload builds to nix-cache on every
+  subsequent run, not just this one.
+- `scripts/proxmox/configure-nix-cache-client.sh [--dry-run]
+  [--no-remote-builder] [--no-restart]` — the non-NixOS equivalent of
+  `modules/nix-cache/client.nix`/`remote-builder-client.nix`, for a plain
+  Debian machine with the Nix package manager (not NixOS) already
+  installed: run as root *on that machine* to add nix-cache as a
+  substituter in `/etc/nix/nix.conf` (`https://cache.nixos.org/` kept as
+  fallback) via `extra-substituters`/`extra-trusted-public-keys` so it
+  layers on top of whatever's already there instead of clobbering it, and,
+  if `/root/.ssh/nixremote` is already present (see docs/nix-cache.md
+  "Remote builder SSH keys"), configures it as a distributed-build
+  machine too and trusts nix-cache's SSH host key in
+  `/etc/ssh/ssh_known_hosts`. Idempotent (re-running replaces its own
+  marked block rather than duplicating it); restarts `nix-daemon` by
+  default so the change takes effect immediately.
+
+### `scripts/lib/`
+
+Sourced by the scripts above, never run directly:
+
+- `nix-bootstrap.sh` — `NIX_CONFIG`/`ensure_nix_profile`, shared by
+  `codex-setup.sh`/`codex-maintenance.sh` and the remote build commands
+  `create-proxmox-resource.sh` runs over SSH.
+- `nix-eval.sh` — `NIX_EVAL_FLAGS` plus `list_flake_targets`/
+  `flake_target_hostname` flake-introspection helpers.
+- `ssh-host-keys.sh` — `generate_host_ed25519_key`/`ssh_pubkey_to_age`,
+  shared by `sync-host-keys.sh` and `prepare-host-key.sh`.
+- `sops-age.sh` — `age_pubkey_from_identity_file`/`sops_yaml_admin_pubkey`/
+  `sops_updatekeys` plus the shared sops/age default key-file resolution,
+  shared by `backup-admin-key.sh`, `rotate-admin-key.sh`, and
+  `sync-host-keys.sh`.
+- `confirm.sh` — `confirm_typed`, the "type X back to confirm" destructive-
+  action prompt shared by `create-proxmox-resource.sh` and
+  `sync-host-keys.sh`.
+- `sync-host-keys-edit-sops.py` — the `.sops.yaml` anchor/key_groups editor
+  `sync-host-keys.sh` shells out to (see that script for why: precise,
+  idempotent YAML edits are impractical in bash).
+
+### Top level
+
 - `scripts/env.sh` — shared config (`PROXMOX_HOST`, storage pool, bridge,
-  default cores/memory) sourced by `create-proxmox-resource.sh`. Add new
+  default cores/memory, `NIX_CACHE_HOST`, `LAN_DOMAIN`) sourced by
-  cross-script config here instead of duplicating it per-script.
+  `create-proxmox-resource.sh` and `scripts/installer/auto-install.sh`. Add
+  new cross-script config here instead of duplicating it per-script.
 - `scripts/bump-nixpkgs-release.sh` — bumps `flake.nix`'s `nixpkgs.url`/
   `home-manager.url` in place. Exists because flake input URLs can't
   reference `variables.nix` (confirmed empirically — `nix flake metadata`
   errors on it), so this is the closest equivalent to a single source of
   truth for the tracked release.
 
-`sync-host-keys.sh` and `create-proxmox-resource.sh` genuinely mutate real
+`sync-host-keys.sh`, `create-proxmox-resource.sh`, and
-state when run for real (not `--dry-run`): real `secrets/*.yaml`
+`rotate-admin-key.sh` genuinely mutate real state when run for real (not
-recipients, real Proxmox VMs/containers. They require the operator's own
+`--dry-run`): real `secrets/*.yaml` recipients, real Proxmox VMs/
-SSH/sops access, which an agent session doesn't have — but don't suggest
+containers, real revocation of decrypt access. They require the
-running either non-dry-run without the operator's explicit go-ahead even
+operator's own SSH/sops access, which an agent session doesn't have — but
-if it becomes technically reachable.
+don't suggest running any of them non-dry-run without the operator's
+explicit go-ahead even if it becomes technically reachable.
+`backup-admin-key.sh` only writes a key copy to a path the operator gives
+it — lower-stakes than the others, but it still handles a real private
+key, so treat its destination path choice as the operator's call too.
 
 ## Architecture
 
@@ -133,10 +348,14 @@ nixosSystem {
 }
 ```
 
-Platforms: `linode`, `proxmox`, `lxc`. Build types: `minimal`, `nix-cache`,
+Platforms: `linode`, `proxmox`, `lxc`, `baremetal`. Build types: `minimal`,
-`server`, `docker`, `gui`, `pxe-boot`, `tailscale-exit-node`. Not every
+`nix-cache`, `server`, `docker`, `gui`, `pxe-boot`, `tailscale-exit-node`,
-combination is built — e.g. `pxe-boot` has no `linode` variant (PXE/DHCP/TFTP
+`tor-relay`. Not every combination is built — e.g. `pxe-boot` has no `linode`
-need LAN L2 adjacency a Linode VPS doesn't have). Treat `flake.nix`'s
+variant (PXE/DHCP/TFTP need LAN L2 adjacency a Linode VPS doesn't have),
+`tor-relay` currently only exists as `lxc-tor-relay`, and `baremetal`
+currently only exists as `baremetal-gui` (the real gui-host hardware —
+see `hosts/nixos/host.nix` and `modules/platforms/baremetal.nix`). Treat
+`flake.nix`'s
 `generatedTargets` as the source
 of truth for which hosts exist — `README.md`, `AGENTS.md`,
 `docs/flake-lock-automation.md`, and the CI eval workflows
@@ -152,19 +371,23 @@ removing a host.
   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.
-- `modules/platforms/{linode,proxmox,lxc}.nix` — platform-specific config:
+- `modules/platforms/{linode,proxmox,lxc,baremetal}.nix` — platform-specific
-  boot method, guest tooling, and (for linode/proxmox) the hypervisor-specific
+  config: boot method, guest tooling, and the hardware config, imported
-  hardware config, imported directly by the platform module itself
+  directly by the platform module itself — **not** wired in from
-  (`../hardware-configuration/vm/{proxmox,linode}.nix`) — **not** wired in
+  `flake.nix`. VM platforms use `../hardware-configuration/vm/{proxmox,linode}.nix`;
-  from `flake.nix`. `lxc.nix` has no hardware-configuration counterpart since
+  `baremetal.nix` uses `../hardware-configuration/baremetal.nix` (adapted
-  containers share the host kernel; instead it imports nixpkgs' own
+  from a real `nixos-generate-config` run on the actual hardware, not a
+  vm/ file, since it isn't a VM) plus `hardware.enableRedistributableFirmware
+  = true` for real wifi/GPU/microcode firmware that VMs never needed.
+  `lxc.nix` has no hardware-configuration counterpart since containers
+  share the host kernel; instead it imports nixpkgs' own
   `virtualisation/proxmox-lxc.nix`, which gives every `lxc-*` host a
   `config.system.build.tarball` output — a plain rootfs tarball, used as a
   `pct create ... vztmpl` CT template (**not** `pct restore`, which expects
   `vzdump` backup-archive metadata this doesn't have), no install step —
   see `docs/auto-installer.md`.
 - `modules/build-types/*.nix` — what a system is for:
-  minimal/server/docker/gui/pxe-boot/nix-cache.
+  minimal/server/docker/gui/pxe-boot/nix-cache/tailscale-exit-node/tor-relay.
 - `modules/common/configuration.nix` — base NixOS config imported by every
   host: locale, users, nix settings, git.
 - `modules/common/home.nix` / `hosts/nixos/home.nix` — Home Manager config for
@@ -181,6 +404,16 @@ removing a host.
   boots, so this declares them with `destroy = false` (disko never wipes
   them) and a bare `filesystem`/`swap` content type instead of a partition
   table — idempotent against an already-provisioned disk, never destructive.
+- `modules/disko/baremetal.nix` — `baremetal-gui`'s disko config: a ZFS
+  RAID0 (striped, no redundancy — disko's zpool `mode` defaults to `""`,
+  which is a plain stripe rather than `"mirror"`/`"raidz"`) root pool
+  across two disks, ESP + systemd-boot on the first. Device paths
+  (`vars.guiRootDisk1`/`guiRootDisk2`) are placeholders — fill in stable
+  `/dev/disk/by-id/...` paths before running disko for real.
+  `modules/platforms/baremetal.nix` also imports
+  `modules/services/zfs/enable-service.nix` for this (the `zfs_unstable`
+  package, autoScrub/autoSnapshot/trim) — the only other importer today is
+  `server`'s NFS data pool, an unrelated non-root ZFS use.
 - `modules/boot/efi.nix` — systemd-boot + EFI vars, paired with the disko module.
 - `modules/installer/` — the auto-installer environment (ISO, also served as
   PXE netboot): `common.nix` (shared config + the generated
@@ -199,7 +432,8 @@ removing a host.
   and `environmentFile`; used by `hosts/server/host.nix` and
   `hosts/nix-cache/host.nix` to avoid duplicating that boilerplate.
 - `modules/tailscale/`, `modules/docker/`, `modules/networking/`,
-  `modules/traefik/`, `modules/services/*` — single-purpose, single-host
+  `modules/traefik/`, `modules/tor/`, `modules/services/*` — single-purpose,
+  single-host
   feature modules (e.g. `docker/enable-service.nix`,
   `services/zfs/enable-service.nix`). Grep `modules/build-types/*.nix` for
   each build type's `imports` list to see which modules apply where.

README.md

@@ -8,13 +8,15 @@ workstation.
 Targets are named `<platform>-<buildtype>`, generated from two orthogonal
 pieces composed in `flake.nix`:
 
-- **Platforms** (what it runs on): `linode`, `proxmox`, `lxc`
+- **Platforms** (what it runs on): `linode`, `proxmox`, `lxc`, `baremetal`
 - **Build types** (what it's for): `minimal`, `nix-cache`, `server`, `docker`,
-  `gui`, `pxe-boot`, `tailscale-exit-node`
+  `gui`, `pxe-boot`, `tailscale-exit-node`, `tor-relay`
 
 Not every combination exists — `pxe-boot` has no `linode` variant, since
-PXE/DHCP/TFTP need LAN L2 adjacency that a Linode VPS doesn't have. The full
+PXE/DHCP/TFTP need LAN L2 adjacency that a Linode VPS doesn't have,
-list:
+`tor-relay` currently only exists as `lxc-tor-relay`, and `baremetal`
+currently only exists as `baremetal-gui` (the real gui-host hardware). The
+full list:
 
 | Target | Purpose |
 | --- | --- |
@@ -25,16 +27,23 @@ list:
 | `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 |
+| `lxc-tor-relay` | Tor middle relay |
 
 Which variant of a given buildtype is actually deployed isn't tracked
 anywhere in this repo — that's live infrastructure state, not something a
 committed file can keep accurate, and it changes independently of the code.
 Check the Proxmox node itself, or `/etc/flake-target` on a running host (see
 below), if you need to know what's really out there right now.
-`scripts/create-proxmox-resource.sh`'s duplicate-host guard works the same
+`scripts/proxmox/create-proxmox-resource.sh`'s duplicate-host guard works the same
 way: it checks the Proxmox node directly rather than any file here.
+Real, production deployments live on `pve1.sweet.home`; there's a second
+node, `pve-test.sweet.home`, set aside purely for scratch/test resources —
+see `scripts/env.sh` (`PVE1_HOST` / `PVE_TEST_HOST`, and the
+`--node`/`PROXMOX_HOST` targeting they feed into) and CLAUDE.md's Proxmox
+section for which is which.
 
 Each buildtype's `hosts/<name>/host.nix` carries the per-machine identity
 (hostname, hostId, per-machine secrets, `system.stateVersion`) that must stay
@@ -58,7 +67,7 @@ nix eval --json .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]'
 | `variables.nix` | Single source of truth for shared values (LAN domain/CIDR, hostnames, timezone, primary username, storage root, NFS share subpaths/mountpoints, service ports, ...) — passed to every module and Home Manager config as the `vars` argument via `specialArgs`/`extraSpecialArgs` |
 | `hosts/<name>/host.nix` | Per-machine identity: hostname, hostId, per-machine secrets, `system.stateVersion` |
 | `hosts/nixos/home.nix` | Workstation-specific Home Manager config (used by the `gui` build type) |
-| `modules/platforms/` | Platform-specific config: virtualisation guest tools, boot method, hardware config (`linode.nix`, `proxmox.nix`, `lxc.nix`) |
+| `modules/platforms/` | Platform-specific config: virtualisation guest tools, boot method, hardware config (`linode.nix`, `proxmox.nix`, `lxc.nix`, `baremetal.nix`) |
 | `modules/build-types/` | Build-type-specific config: what makes a system minimal/server/docker/gui/pxe-boot/nix-cache |
 | `modules/common/` | Shared NixOS config, Home Manager, aliases imported by every host |
 | `modules/nix-cache/` | Binary cache and remote builder client/server modules |
@@ -73,10 +82,19 @@ Safe validation commands for Codex and local review:
 
 ```bash
 bash scripts/codex-setup.sh
-bash scripts/codex-maintenance.sh dry-run
 bash scripts/codex-maintenance.sh
 ```
 
+`codex-maintenance.sh` with no flags (what CI runs on every push/PR) scopes
+fmt-check/statix/eval to files changed against a base ref — fast, but only
+as thorough as the diff. For the full sweep (every host, every package,
+fmt-check and statix over the whole tree — slow, CI never runs this):
+
+```bash
+bash scripts/codex-maintenance.sh --full-check
+bash scripts/codex-maintenance.sh --full-check --dry-run
+```
+
 For individual host evaluation:
 
 ```bash
@@ -113,10 +131,11 @@ Three different paths depending on target, none of them involving a manual
   disk image and attached to a new VM with no install step — see
   `docs/proxmox-images.md`.
 
-`scripts/create-proxmox-resource.sh --type lxc|vm --host <name>` automates
+`scripts/proxmox/create-proxmox-resource.sh --type lxc|vm --host <name>` automates
-either of the last two end to end (build, host-key registration, upload,
+either of the last two end to end (host-key registration, building the
-`pct create`/`qm create`), with `--dry-run` and a guard against duplicating
+image directly on the Proxmox node itself, `pct create`/`qm create`), with
-an already-deployed host's identity. See its `--help`.
+`--dry-run` and a guard against duplicating an already-deployed host's
+identity. See its `--help`.
 
 ## Security Notes
 

docs/auto-installer.md

@@ -8,10 +8,13 @@ lives here.
 The installer provides a small NixOS install environment (ISO, or the same
 image netbooted via PXE) with SSH access, Git support, and an interactive
 installation script.
-Logging in as any user (root or `nixos`) runs `/etc/auto-install.sh`,
+Logging in as any user (root or `nixos`) runs
-discovers available hosts from this same flake, lets the operator choose a
+`/etc/nixos-installer/installer/auto-install.sh` (the same file as
-target, applies that host's Disko storage configuration, installs NixOS, and
+`scripts/installer/auto-install.sh` in this repo — see "Installer process"
-reboots.
+below for why it's baked in at that path rather than a flat
+`/etc/auto-install.sh`), discovers available hosts from this same flake,
+lets the operator choose a target, applies that host's Disko storage
+configuration, installs NixOS, and reboots.
 
 **This applies to every `nixosConfigurations` target except `lxc-*` hosts —
 see "LXC hosts" immediately below for why those are different.**
@@ -19,7 +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`) are **not** installed via `auto-install.sh` — the
+`lxc-gui`, `lxc-pxe-boot`, `lxc-tailscale-exit-node`, `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
@@ -73,9 +76,9 @@ booting one:
 
 First boot runs `boot.postBootCommands` (registers the Nix store DB and
 system profile) — there's no separate activation step to run yourself.
-`scripts/create-proxmox-resource.sh --type lxc --host <name>` automates all
+`scripts/proxmox/create-proxmox-resource.sh --type lxc --host <name>` automates all
-of this (build, host-key handling, upload, `pct create` with the flags
+of this (host-key handling, building the tarball directly on the Proxmox
-above) — see its `--help`.
+node itself, `pct create` with the flags above) — see its `--help`.
 
 Host keys still need pre-seeding the same way as any other host — the
 sops-nix activation-vs-first-boot race is identical regardless of how the
@@ -102,7 +105,7 @@ groups required, got 0`, and *every* secret (including this host's own
 login) permanently fails to decrypt, silently — no error in the boot log
 at all, since the activation step that would install secrets only runs on
 a from-scratch first activation and skips silently once `/run/current-system`
-already exists. `scripts/create-proxmox-resource.sh` always builds with
+already exists. `scripts/proxmox/create-proxmox-resource.sh` always builds with
 `NIXOS_HOST_KEYS_DIR` set for this reason.
 
 ## Layout
@@ -116,10 +119,10 @@ already exists. `scripts/create-proxmox-resource.sh` always builds with
   `docs/pxe-boot.md`).
 - `modules/installer/host-keys.nix` — optionally bakes pre-generated SSH
   host keys into the image; see "Host keys" below.
-- `scripts/sync-host-keys.sh` — admin-workstation tool that generates,
+- `scripts/secrets/sync-host-keys.sh` — admin-workstation tool that generates,
   registers, and (via `--remove`/`--regenerate-all-keys`) retires host
   keys; see "Creating a New Machine" below.
-- `scripts/prepare-host-key.sh` — narrower predecessor: generates a single
+- `scripts/secrets/prepare-host-key.sh` — narrower predecessor: generates a single
   key by an arbitrary name without touching `.sops.yaml`. Still useful for
   pre-generating a key *before* its flake target exists (`sync-host-keys.sh`
   can only act on targets `nixosConfigurations` already has); otherwise
@@ -150,7 +153,11 @@ use case.
 
 The `pxe` variant is also built automatically as part of the `pxe-boot` host
 itself (`modules/pxe-boot/stage-installer-artifacts.nix`) and served over
-iPXE — see `docs/pxe-boot.md`.
+iPXE as the menu's "NixOS Auto-Installer" entry — see `docs/pxe-boot.md`.
+That same host also builds and serves `packages.x86_64-linux.pxe-minimal`,
+a vanilla NixOS minimal netboot image with none of this auto-installer's
+wiring, as a separate "NixOS Minimal" menu entry — also documented in
+`docs/pxe-boot.md`, not covered further here since it's not this installer.
 
 ## Host keys
 
@@ -188,6 +195,10 @@ default.
 `auto-install.sh` still supports the older manual path as a fallback: if a
 host's key isn't baked in (`/etc/host-keys`), it checks `/root/host-keys`
 next, where you can `scp` a key in after boot, same as before this migration.
+If neither has it and the script is running interactively (an actual
+operator at the other end of stdin, not an unattended run), it prompts for
+an arbitrary directory to check (a mounted USB stick, another filesystem,
+etc.) and copies the key pair into `/root/host-keys` from there if found.
 
 ## Storage
 
@@ -213,7 +224,21 @@ entirely (see "LXC hosts" above), so it never reaches this code path.
 
 ## Installer process
 
-`/etc/auto-install.sh`:
+`scripts/installer/auto-install.sh` is a real, version-controlled shell
+script — not an inline Nix string. It sources `scripts/env.sh` for
+`LAN_DOMAIN` itself (same as every other script in `scripts/`), so it
+behaves identically whether it's run straight from a git checkout (e.g.
+manually, from a stock NixOS ISO that isn't this repo's own installer
+image) or from inside the built installer image. That's also why it's
+baked in at `/etc/nixos-installer/installer/auto-install.sh` rather than a
+flat `/etc/auto-install.sh` — `modules/installer/common.nix` bakes
+`scripts/env.sh` in alongside it at `/etc/nixos-installer/env.sh`,
+preserving the same relative layout (`installer/auto-install.sh` ->
+`../env.sh`) the checked-out repo has, so the script's own
+`source ".../env.sh"` line resolves correctly in both places without any
+Nix-level templating.
+
+Once running, it:
 
 1. Queries `nixosConfigurations` from this flake over the network (`git+https://<lanDomain>/beatzaplenty/nixos.git`) — this happens at *install* time, not build time, so a generic installer image always sees whatever hosts are currently committed, without needing a rebuild.
 2. Presents them as a menu; confirms the choice.
@@ -238,7 +263,7 @@ GitHub token behind sops-nix for all of them).
 2. **On your admin workstation, generate and register its host key:**
 
    ```sh
-   ./scripts/sync-host-keys.sh <flake-target>
+   ./scripts/secrets/sync-host-keys.sh <flake-target>
    ```
 
    This generates `host-keys/<flake-target>_ssh_host_ed25519_key(.pub)`,
@@ -250,7 +275,7 @@ GitHub token behind sops-nix for all of them).
 
    Doing this for every host that needs one at once — after adding several
    new targets, or just to catch up any that were missed — is
-   `./scripts/sync-host-keys.sh --all`. See `scripts/sync-host-keys.sh --help`
+   `./scripts/secrets/sync-host-keys.sh --all`. See `scripts/secrets/sync-host-keys.sh --help`
    for its other modes (`--remove`, `--regenerate-all-keys`).
 
 3. **Commit and push.** The flake build the installer uses has to see the

docs/flake-lock-automation.md

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

docs/nix-cache.md

@@ -46,18 +46,26 @@ the new key up automatically on next activation — no more manual
 
 ## Remote builder SSH keys
 
-On each client, install the private key used to authenticate as `nixremote`:
+Each client authenticates as `nixremote` using its **own default root SSH
+identity** (`/root/.ssh/id_ed25519`) — not a separately-named or shared
+keypair. If a client doesn't have one yet:
 
 ```bash
-sudo install -d -m 0700 /root/.ssh
+sudo ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519
-sudo install -m 0600 ./nixremote /root/.ssh/nixremote
-sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
 ```
 
-On `nix-cache`, install the matching public key used by `nixremote` authorized keys.
+Then add its `.pub` contents as a new entry in `vars.remoteBuilderAuthorizedKeys`
+(`variables.nix`) and rebuild `nix-cache` to pick it up (that list is
+declarative — an imperative `ssh-copy-id nixremote@nix-cache` won't stick;
+it gets overwritten on every rebuild). Verify with:
 
-The committed `nixremote` authorized keys are public SSH keys only. Keep the
+```bash
-matching private keys on client hosts and out of the repository.
+sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache nix-store --version
+```
+
+The committed `remoteBuilderAuthorizedKeys` entries are public SSH keys
+only. Keep the matching private keys on client hosts and out of the
+repository.
 
 nix-cache's own SSH *host* key is trusted declaratively via
 `programs.ssh.knownHosts` in `modules/nix-cache/remote-builder-client.nix`,
@@ -76,8 +84,8 @@ After deployment:
 curl http://nix-cache/nix-cache-info
 nix store ping --store http://nix-cache
 nix show-config | grep -E 'substituters|trusted-public-keys|builders-use-substitutes'
-sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
+sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache nix-store --version
-nix build nixpkgs#hello --builders 'ssh://nixremote@nix-cache x86_64-linux /root/.ssh/nixremote 4 2 big-parallel,kvm,nixos-test,benchmark' -L
+nix build nixpkgs#hello --builders 'ssh://nixremote@nix-cache x86_64-linux /root/.ssh/id_ed25519 4 2 big-parallel,kvm,nixos-test,benchmark' -L
 nix path-info -r nixpkgs#hello
 curl -I "http://nix-cache/$(basename "$(nix path-info nixpkgs#hello)").narinfo"
 ```

docs/proxmox-images.md

@@ -7,11 +7,13 @@ config (`modules/disko/proxmox.nix`) already used to format a real disk on
 install, so there's nothing host-specific to write; it's available for every
 `proxmox-*` target automatically.
 
-`scripts/create-proxmox-resource.sh --type vm --host <name>` automates the
+`scripts/proxmox/create-proxmox-resource.sh --type vm --host <name>` automates the
 whole walkthrough below (and the equivalent LXC one) end to end, including
-host-key handling and upload — see its `--help`. The steps here are what it
+host-key handling and building the image directly on the Proxmox node
-runs under the hood, useful for doing any of it by hand or understanding
+itself (no local build, no image transfer) — see its `--help`. The steps
-what it does before you trust it against real infrastructure.
+here are what it runs under the hood, useful for doing any of it by hand
+or understanding what it does before you trust it against real
+infrastructure.
 
 ## Building
 
@@ -49,7 +51,7 @@ sudo ./result \
   --build-memory 2048
 ```
 
-Generate the key first with `scripts/sync-host-keys.sh <hostname>`, same
+Generate the key first with `scripts/secrets/sync-host-keys.sh <hostname>`, same
 as any other host — see `docs/auto-installer.md` for the full walkthrough
 (it registers the new key in `.sops.yaml` and re-encrypts the affected
 `secrets/*.yaml` files too, no manual editing needed).

docs/pxe-boot.md

@@ -1,9 +1,10 @@
 # pxe-boot
 
-The `pxe-boot` host serves HTTP boot assets for iPXE clients — including a
+The `pxe-boot` host serves HTTP boot assets for iPXE clients — including
-self-staged copy of this flake's own auto-installer netboot image, see
+self-staged copies of both this flake's own auto-installer netboot image
-`docs/auto-installer.md` for what that image actually is and does once
+(see `docs/auto-installer.md` for what that image actually is and does once
-booted.
+booted) and a vanilla, unmodified NixOS minimal netboot image for plain
+rescue/inspection use.
 
 ## Host Role
 
@@ -28,7 +29,8 @@ The host creates these directories with systemd tmpfiles:
 /srv/pxe
 /srv/pxe/http
 /srv/pxe/http/images
-/srv/pxe/http/nixos
+/srv/pxe/http/auto-installer
+/srv/pxe/http/nixos-minimal
 /srv/pxe/http/systemrescue
 /srv/pxe/http/ubuntu
 /srv/pxe/http/rescue
@@ -37,7 +39,7 @@ The host creates these directories with systemd tmpfiles:
 
 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/nixos`.
+directory such as `/srv/pxe/http/auto-installer`.
 
 The HTTP iPXE chain is:
 
@@ -50,20 +52,37 @@ undionly.kpxe or ipxe.efi
 
 The generated menu currently exposes entries for:
 
-- NixOS installer
+- NixOS Auto-Installer
+- NixOS Minimal
 - SystemRescue environment
 - iPXE shell
 - Reboot
 
-The NixOS installer entry chain-loads `/srv/pxe/http/nixos/netboot.ipxe`,
+Both NixOS entries chain-load a `netboot.ipxe` staged into their own
-which is nixpkgs' own generated netboot iPXE script (correct `init=`/`initrd=`
+directory (`/srv/pxe/http/auto-installer/netboot.ipxe` and
-kernel parameters included) rather than a hand-rolled boot line — that script
+`/srv/pxe/http/nixos-minimal/netboot.ipxe`), each nixpkgs' own generated
-in turn expects its kernel/initrd siblings in the same directory. All three
+netboot iPXE script (correct `init=`/`initrd=` kernel parameters included)
-files (`bzImage`, `initrd`, `netboot.ipxe`) are built from this flake's own
+rather than a hand-rolled boot line — that script in turn expects its
-`modules/installer/iso.nix` netboot image (the same one `nix build .#pxe`
+kernel/initrd siblings in the same directory. Each directory's three files
-produces) and staged automatically by
+(`bzImage`, `initrd`, `netboot.ipxe`) are built from source and staged
-`modules/pxe-boot/stage-installer-artifacts.nix` via `systemd.tmpfiles.rules`
+automatically by `modules/pxe-boot/stage-installer-artifacts.nix` via
-— no manual operator step required.
+`systemd.tmpfiles.rules` — no manual operator step required:
+
+- `auto-installer` is this flake's own `netbootSystem` (`flake.nix`) — the
+  same auto-installer image `nix build .#pxe` produces. See
+  `docs/auto-installer.md`.
+- `nixos-minimal` is `netbootMinimalSystem` (`flake.nix`) — nixpkgs'
+  `netboot-minimal.nix` composed on its own, with none of this flake's
+  auto-installer wiring (no `common.nix`, no `auto-install.sh`, no baked
+  host keys or custom users). Same `nix build .#pxe-minimal` mechanism as
+  the auto-installer image, just a different module composition. Useful
+  as a plain rescue/inspection shell that doesn't assume anything about
+  this flake.
+
+Both images set `networking.hostName` to match their menu entry/staged
+directory name (`auto-installer` / `nixos-minimal`), so each one's
+generated system name (`nixos-system-<name>-*`) is self-describing rather
+than the nixpkgs default of `nixos-system-nixos-*` for both.
 
 The SystemRescue entry expects the source ISO at:
 

flake-target-refactor-spec.md

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

flake.lock

@@ -95,11 +95,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1783740085,
+        "lastModified": 1784350909,
-        "narHash": "sha256-qajyHfZY29G2oEQk+uHxmsJcRoBUBXP9maTpFlwP/dI=",
+        "narHash": "sha256-ZWyzLbS1yKUTeFJLmdVuWNnHttL333/ldJbEE+KzCrM=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "3cd22efe6471dc7365c822bd9ad73a21e55f38fb",
+        "rev": "4ce190229c73d44536caa7072f6308fb2d8feeb3",
         "type": "github"
       },
       "original": {
@@ -147,11 +147,11 @@
     },
     "nixpkgs_2": {
       "locked": {
-        "lastModified": 1784011430,
+        "lastModified": 1784432872,
-        "narHash": "sha256-lDebytrYdd47IBLwvNOD+6AGeoqZ78CIKlp70hzW280=",
+        "narHash": "sha256-n3gKTBIV4ZA5VQpUakffBe3KGu4+mhPoA34rrqS0GkA=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "8eeec934ae0dbeca3d7868c059568a65c08b2fc3",
+        "rev": "fd1462031fdee08f65fd0b4c6b64e22239a77870",
         "type": "github"
       },
       "original": {

flake.nix

@@ -65,7 +65,7 @@
           # file without a same-option circular dependency (a module
           # contributing to environment.etc can't read the merged
           # environment.etc it's itself contributing to).
-          specialArgs = { inherit inputs vars netbootSystem flakeTarget; };
+          specialArgs = { inherit inputs vars netbootSystem netbootMinimalSystem flakeTarget; };
         };
 
       # Generated platform x build-type matrix. pxe-boot has no linode
@@ -91,6 +91,7 @@
         linode-gui = mkTarget { platform = "linode"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
         proxmox-gui = mkTarget { platform = "proxmox"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
         lxc-gui = mkTarget { platform = "lxc"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
+        baremetal-gui = mkTarget { platform = "baremetal"; buildType = "gui"; hostPath = ./hosts/nixos/host.nix; homeFile = ./hosts/nixos/home.nix; };
 
         proxmox-pxe-boot = mkTarget { platform = "proxmox"; buildType = "pxe-boot"; hostPath = ./hosts/pxe-boot/host.nix; };
         lxc-pxe-boot = mkTarget { platform = "lxc"; buildType = "pxe-boot"; hostPath = ./hosts/pxe-boot/host.nix; };
@@ -98,6 +99,8 @@
         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; };
+
+        lxc-tor-relay = mkTarget { platform = "lxc"; buildType = "tor-relay"; hostPath = ./hosts/tor-relay/host.nix; };
       };
 
       # Auto-install environments (migrated from the former nix-auto-installer
@@ -117,19 +120,61 @@
 
       # Same installer environment, built as netboot (kernel + initrd +
       # iPXE script) instead of an ISO — this is what packages.pxe bundles.
+      #
+      # Deliberately imports common.nix directly, NOT ./modules/installer/iso.nix
+      # (which pulls in nixpkgs' installation-cd-minimal.nix) -- confirmed live
+      # that composing the ISO module together with netboot-minimal.nix hangs
+      # every boot waiting for a device that can never exist on a netboot
+      # client ("A start job is running for /dev/disk/by-label/nixos-minimal-...").
+      # Both installation-cd-base.nix and netboot.nix set fileSystems."/" via
+      # the identical lib.mkImageMediaOverride (mkOverride 60) priority --
+      # genuinely conflicting root-filesystem strategies (ISO-by-label vs.
+      # netboot-tmpfs) at the same priority, and the ISO one was winning.
+      # netboot-minimal.nix's own chain (netboot-base.nix) already imports
+      # profiles/installation-device.nix independently, so common.nix's
+      # initialHashedPassword override (which assumes that profile is
+      # present) still applies correctly without iso.nix in the mix.
+      #
+      # networking.hostName is set explicitly (rather than left at nixpkgs'
+      # own "nixos" default) so this image's generated system name
+      # (nixos-system-auto-installer-*) matches its iPXE menu entry —
+      # see modules/build-types/pxe-boot.nix's :auto-installer item — and
+      # its staged directory, /srv/pxe/http/auto-installer.
       netbootSystem = nixpkgs.lib.nixosSystem {
         inherit system;
         modules = [
-          ./modules/installer/iso.nix
+          ./modules/installer/common.nix
           ({ modulesPath, ... }: {
             imports = [
               (modulesPath + "/installer/netboot/netboot-minimal.nix")
             ];
           })
+          { networking.hostName = "auto-installer"; }
         ];
         specialArgs = { inherit vars; };
       };
 
+      # A genuinely vanilla NixOS minimal netboot image: nixpkgs'
+      # netboot-minimal.nix on its own, with none of this flake's
+      # auto-installer wiring (no common.nix — no auto-install.sh, no
+      # baked host keys, no custom users/passwords). Built from source via
+      # the same nixosSystem + netboot-minimal.nix path as netbootSystem
+      # above, so both go through an identical build mechanism; the only
+      # difference is what's composed in. hostName again matches this
+      # image's iPXE menu entry (:nixos-minimal) and staged directory
+      # (/srv/pxe/http/nixos-minimal).
+      netbootMinimalSystem = nixpkgs.lib.nixosSystem {
+        inherit system;
+        modules = [
+          ({ modulesPath, ... }: {
+            imports = [
+              (modulesPath + "/installer/netboot/netboot-minimal.nix")
+            ];
+          })
+          { networking.hostName = "nixos-minimal"; }
+        ];
+      };
+
     in
     {
 
@@ -151,6 +196,15 @@
           { name = "initrd"; path = netbootSystem.config.system.build.netbootRamdisk; }
           { name = "kernel"; path = netbootSystem.config.system.build.kernel; }
         ];
+
+        # Vanilla NixOS minimal netboot bundle — see netbootMinimalSystem
+        # above. Staged onto the pxe-boot host alongside packages.pxe by
+        # modules/pxe-boot/stage-installer-artifacts.nix.
+        pxe-minimal = pkgs.linkFarm "pxe-minimal" [
+          { name = "netboot.ipxe"; path = netbootMinimalSystem.config.system.build.netbootIpxeScript; }
+          { name = "initrd"; path = netbootMinimalSystem.config.system.build.netbootRamdisk; }
+          { name = "kernel"; path = netbootMinimalSystem.config.system.build.kernel; }
+        ];
       };
     };
 }

hosts/nixos/host.nix

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

hosts/tor-relay/host.nix

@@ -0,0 +1,12 @@
+_:
+
+{
+  networking.hostName = "tor-relay";
+
+  # 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";
+}

modules/build-types/pxe-boot.nix

@@ -68,15 +68,19 @@ let
     set base ${pxeBaseUrl}
 
     menu PXE Boot Menu
-    item nixos NixOS Installer
+    item auto-installer NixOS Auto-Installer
+    item nixos-minimal NixOS Minimal
     item rescue Rescue Environment
     item shell iPXE Shell
     item reboot Reboot
 
     choose target && goto ''${target}
 
-    :nixos
+    :auto-installer
-    chain ''${base}/nixos/netboot.ipxe
+    chain ''${base}/auto-installer/netboot.ipxe
+
+    :nixos-minimal
+    chain ''${base}/nixos-minimal/netboot.ipxe
 
     :rescue
     chain ''${base}/systemrescue.ipxe
@@ -129,7 +133,8 @@ in
     "d ${pxeRoot} 0755 root root -"
     "d ${httpRoot} 0755 root root -"
     "d ${httpRoot}/images 0755 root root -"
-    "d ${httpRoot}/nixos 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 -"

modules/build-types/tor-relay.nix

@@ -0,0 +1,7 @@
+{ ... }:
+
+{
+  imports = [
+    ../tor/enable-relay.nix
+  ];
+}

modules/disko/baremetal.nix

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

modules/docker/mount-data.nix

@@ -1,65 +1,84 @@
 { config, lib, pkgs, vars, ... }:
 
+let
+  # `x-systemd.automount` never works inside a Linux container (LXC
+  # included, regardless of privilege) -- confirmed live on lxc-docker:
+  # systemd logs "Starting of <unit>.automount unsupported" for every
+  # share and never mounts them. Mount eagerly there instead, with
+  # `nofail` so a boot with the NFS server unreachable doesn't hang
+  # (the VM platforms rely on automount itself to get that same
+  # non-blocking behavior, so they don't need `nofail` too).
+  automountOpts = if config.boot.isContainer then [ "nofail" ] else [ "x-systemd.automount" ];
+
+  # 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}";
+in
 {
   fileSystems = {
     ${vars.nfsShares.dockerConfig.mountpoint} = {
-      device = "${vars.nfsServerHost}:${vars.storageRoot}/${vars.nfsShares.dockerConfig.subpath}";
+      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerConfig.subpath}";
       fsType = "nfs";
 
       options = [
         "nfsvers=4.2"
         "_netdev"
-        "x-systemd.automount"
         "noatime"
-      ];
+      ] ++ automountOpts;
     };
 
     ${vars.nfsShares.dockerDatabases.mountpoint} = {
-      device = "${vars.nfsServerHost}:${vars.storageRoot}/${vars.nfsShares.dockerDatabases.subpath}";
+      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerDatabases.subpath}";
       fsType = "nfs";
 
       options = [
         "nfsvers=4.2"
         "_netdev"
-        "x-systemd.automount"
         "noatime"
-      ];
+      ] ++ automountOpts;
     };
 
     ${vars.nfsShares.dockerVolumes.mountpoint} = {
-      device = "${vars.nfsServerHost}:${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
+      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.dockerVolumes.subpath}";
       fsType = "nfs";
 
       options = [
         "nfsvers=4.2"
         "_netdev"
-        "x-systemd.automount"
         "noatime"
-      ];
+      ] ++ automountOpts;
     };
 
     ${vars.nfsShares.nextcloudData.mountpoint} = {
-      device = "${vars.nfsServerHost}:${vars.storageRoot}/${vars.nfsShares.nextcloudData.subpath}";
+      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.nextcloudData.subpath}";
       fsType = "nfs";
 
       options = [
         "nfsvers=4.2"
         "_netdev"
-        "x-systemd.automount"
         "noatime"
-      ];
+      ] ++ automountOpts;
     };
 
     ${vars.nfsShares.raspiVolumes.mountpoint} = {
-      device = "${vars.nfsServerHost}:${vars.storageRoot}/${vars.nfsShares.raspiVolumes.subpath}";
+      device = "${nfsServer}:${vars.storageRoot}/${vars.nfsShares.raspiVolumes.subpath}";
       fsType = "nfs";
 
       options = [
         "nfsvers=4.2"
         "_netdev"
-        "x-systemd.automount"
         "noatime"
-      ];
+      ] ++ automountOpts;
     };
   };
 }

modules/hardware-configuration/baremetal.nix

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

modules/installer/common.nix

@@ -45,140 +45,21 @@
       disko
     ];
 
-    # Write auto-install script to /root
+    # Auto-install script, kept as a real, version-controlled shell file at
-    etc."auto-install.sh" = {
+    # scripts/installer/auto-install.sh rather than an inline Nix string.
-      text = ''
+    # It sources scripts/env.sh itself (for LAN_DOMAIN, same as every other
-            #!/run/current-system/sw/bin/bash
+    # script in this repo) rather than relying on Nix-level templating, so
-            set -eux
+    # it behaves identically whether it's run straight from a git checkout
+    # or from here -- baking scripts/env.sh in alongside it at a matching
+    # relative path (installer/auto-install.sh -> ../env.sh) is what makes
+    # that resolve correctly in both places.
+    etc = {
+      "nixos-installer/env.sh".source = ../../scripts/env.sh;
 
-            set -euo pipefail
+      "nixos-installer/installer/auto-install.sh" = {
-
+        source = ../../scripts/installer/auto-install.sh;
-        export FLAKE_BASE_URL="git+https://${vars.lanDomain}/beatzaplenty/nixos.git"
+        mode = "0755";
-
+      };
-        echo "Fetching available NixOS hosts from flake..."
-        # Two categories deliberately excluded from the menu:
-        #   lxc-*     — these build a config.system.build.tarball meant for
-        #               `pct restore` on Proxmox directly, not an install.
-        #               Running nixos-install against one here would
-        #               bind-mount / onto /mnt and then refuse to touch the
-        #               filesystem it's currently running on — see
-        #               docs/auto-installer.md.
-        #   installer — this *is* the installer image's own flake target,
-        #               not a deployable host; "installing" it means
-        #               nixos-install-ing a copy of the installer into
-        #               itself.
-        mapfile -t options < <(
-          nix eval --json --no-use-registries --no-accept-flake-config --extra-experimental-features "flakes nix-command" \
-            "''${FLAKE_BASE_URL}#nixosConfigurations" \
-            --apply builtins.attrNames \
-          | jq -r '.[]
-              | select(startswith("lxc-") | not)
-              | select(. != "installer")'
-        )
-
-        if [[ ''${#options[@]} -eq 0 ]]; then
-          echo "ERROR: No NixOS hosts found in ''${FLAKE_BASE_URL}#nixosConfigurations" >&2
-          exit 1
-        fi
-
-        echo "Note: lxc-* targets aren't installed this way — build them with"
-        echo "  nix build .#nixosConfigurations.<name>.config.system.build.tarball"
-        echo "and 'pct restore' the result on Proxmox directly. See docs/auto-installer.md."
-
-        echo "Choose the flake profile to install:"
-        select choice in "''${options[@]}"; do
-          if [[ -n "$choice" ]]; then
-            echo "You selected: $choice"
-            break
-          else
-            echo "Invalid selection. Try again."
-          fi
-        done
-
-        echo "Starting install with flake: ''${FLAKE_BASE_URL}#''${choice}"
-
-        # Optional: confirm before proceeding
-        read -rp "Proceed with installation? (y/N): " confirm
-        if [[ ! "$confirm" =~ ^[Yy]$ ]]; then
-          echo "Aborted."
-          exit 1
-        fi
-
-        # A nix-cache host is *the* substituter/remote-builder for every other
-        # host once installed (its own config explicitly excludes itself from
-        # using either — see buildType != "nix-cache" in the nixos flake.nix).
-        # Installing one shouldn't depend on a nix-cache substituter either,
-        # for the same reason — plus in practice "nix-cache" only resolves over
-        # Tailscale, which a fresh installer environment was never connected to
-        # anyway, so it's dead weight even for non-nix-cache installs until
-        # that's sorted out. Override it away here specifically for nix-cache
-        # targets to keep install-time behaviour consistent with run-time.
-        nix_extra_opts=()
-        if [[ "''${choice}" == *-nix-cache ]]; then
-            echo "Installing a nix-cache host — skipping the nix-cache substituter."
-            nix_extra_opts+=(--option substituters "https://cache.nixos.org/")
-        fi
-
-        # Every host reachable through this menu has a Disko config (lxc-*
-        # is filtered out above, and is the only category that doesn't —
-        # see docs/auto-installer.md), so this can run unconditionally: no
-        # need to probe the flake first and branch on whether Disko applies.
-        disko --mode destroy,format,mount \
-            --flake "''${FLAKE_BASE_URL}#''${choice}" "''${nix_extra_opts[@]}" --yes-wipe-all-disks
-
-        # sops-nix derives this host's decryption key from its own SSH host key
-        # at *activation* time, which runs before systemd would otherwise
-        # generate one on first boot. Without pre-seeding it here, secrets
-        # (including the login password) fail to decrypt on first boot.
-        # Generate the key with scripts/prepare-host-key.sh first.
-        #
-        # Two places a key can come from, checked in order:
-        #   /etc/host-keys  — baked into this image at build time (see
-        #                      modules/installer/host-keys.nix; only present
-        #                      if built with NIXOS_HOST_KEYS_DIR set)
-        #   /root/host-keys — scp'd in manually after boot (older fallback,
-        #                      still supported for images built without keys)
-        mkdir -p /root/host-keys
-        if [[ -f "/etc/host-keys/''${choice}_ssh_host_ed25519_key" ]]; then
-            echo "Found baked-in SSH host key for ''${choice}, installing to target..."
-            install -D -m 0600 "/etc/host-keys/''${choice}_ssh_host_ed25519_key" /mnt/etc/ssh/ssh_host_ed25519_key
-            install -D -m 0644 "/etc/host-keys/''${choice}_ssh_host_ed25519_key.pub" /mnt/etc/ssh/ssh_host_ed25519_key.pub
-        elif [[ -f "/root/host-keys/''${choice}_ssh_host_ed25519_key" ]]; then
-            echo "Found pre-seeded SSH host key for ''${choice}, installing to target..."
-            install -D -m 0600 "/root/host-keys/''${choice}_ssh_host_ed25519_key" /mnt/etc/ssh/ssh_host_ed25519_key
-            install -D -m 0644 "/root/host-keys/''${choice}_ssh_host_ed25519_key.pub" /mnt/etc/ssh/ssh_host_ed25519_key.pub
-        else
-            echo "WARNING: no SSH host key found for ''${choice} (checked /etc/host-keys and /root/host-keys)"
-            echo "sops-nix secrets (including the login password) will NOT decrypt on first boot."
-            echo "Run scripts/prepare-host-key.sh for host ''${choice} on your admin workstation first,"
-            echo "then either rebuild this image with NIXOS_HOST_KEYS_DIR set, or scp the result to"
-            echo "/root/host-keys/ on this machine."
-            read -rp "Continue without a pre-seeded key anyway? (y/N): " skip_key
-            if [[ ! "$skip_key" =~ ^[Yy]$ ]]; then
-                echo "Aborted."
-                exit 1
-            fi
-        fi
-
-        mkdir -p /mnt/install-tmp
-        export TMPDIR=/mnt/install-tmp
-
-        nixos-install \
-            --flake "''${FLAKE_BASE_URL}#''${choice}" \
-            "''${nix_extra_opts[@]}" \
-            --no-root-password
-
-
-            rm -rf /mnt/install-tmp
-            # Redundant copy of the host's private key — the real one is now at
-            # /etc/ssh/ssh_host_ed25519_key. Nothing NixOS-managed ever cleans this
-            # up on its own since it was written imperatively, not declaratively.
-            rm -rf /root/host-keys
-            sleep 10
-            reboot
-      '';
-
-      mode = "0755";
     };
   };
 
@@ -192,7 +73,7 @@
   # file-copying/chown.
   programs.bash.loginShellInit = ''
     if [ -n "$PS1" ] && [ ! -e "$HOME/.auto_install_ran" ]; then
-      sudo /etc/auto-install.sh
+      sudo /etc/nixos-installer/installer/auto-install.sh
       touch "$HOME/.auto_install_ran"
     fi
   '';

modules/networking/wifi.nix

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

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

@@ -1,10 +1,14 @@
 { pkgs, vars, ... }:
 
 {
-  # Install the remote builder key on each client host (do not commit private keys):
+  # Authenticate as nixremote using the client host's own default root SSH
-  #   sudo install -d -m 0700 /root/.ssh
+  # identity (/root/.ssh/id_ed25519) rather than a separately-named key --
-  #   sudo install -m 0600 ./nixremote /root/.ssh/nixremote
+  # matches vars.remoteBuilderAuthorizedKeys, which already authorizes
-  #   sudo ssh -i /root/.ssh/nixremote nixremote@nix-cache nix-store --version
+  # each host's own default key (one entry per host, not a shared
+  # dedicated keypair). If this host doesn't have one yet:
+  #   sudo -u root ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519
+  #   # then add its .pub to vars.remoteBuilderAuthorizedKeys and rebuild nix-cache
+  #   sudo ssh -i /root/.ssh/id_ed25519 nixremote@nix-cache 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.
@@ -20,7 +24,7 @@
       {
         hostName = vars.nixCacheHost;
         sshUser = vars.remoteBuilderUser;
-        sshKey = "/root/.ssh/${vars.remoteBuilderUser}";
+        sshKey = "/root/.ssh/id_ed25519";
         inherit (pkgs.stdenv.hostPlatform) system;
         maxJobs = 4;
         speedFactor = 2;

modules/platforms/baremetal.nix

@@ -0,0 +1,28 @@
+{ ... }:
+
+{
+  imports = [
+    ../hardware-configuration/baremetal.nix
+    ../boot/efi.nix
+    ../disko/baremetal.nix
+    ../services/zfs/enable-service.nix
+  ];
+
+  # Needed for real wifi/bluetooth/GPU firmware blobs and CPU microcode
+  # updates (hardware-configuration/baremetal.nix's amd.updateMicrocode
+  # keys off this) -- irrelevant on the linode/proxmox/lxc platforms,
+  # which are all VMs with no real hardware to load firmware for.
+  hardware.enableRedistributableFirmware = true;
+
+  # AMD GPU: the amdgpu kernel driver autoloads from the PCI ID with no
+  # extra boot.kernelModules entry needed; this is the userspace half --
+  # the dedicated Xorg driver (not just the generic modesetting fallback)
+  # plus Mesa OpenGL/Vulkan (amdgpu/RADV), same firmware blobs as above.
+  # 32-bit support is for compatibility with 32-bit apps/games.
+  services.xserver.videoDrivers = [ "amdgpu" ];
+
+  hardware.graphics = {
+    enable = true;
+    enable32Bit = true;
+  };
+}

modules/platforms/lxc.nix

@@ -1,4 +1,4 @@
-{ lib, modulesPath, flakeTarget, ... }:
+{ config, lib, modulesPath, flakeTarget, ... }:
 
 let
   # Bakes this exact flake target's pre-generated SSH host key straight
@@ -14,7 +14,7 @@ let
   # Without this, config.system.build.tarball's built-in system just
   # generates a fresh host key at first boot like any other host would --
   # but sops-nix derives its decryption key from *this* file, and
-  # .sops.yaml only trusts whatever key scripts/sync-host-keys.sh already
+  # .sops.yaml only trusts whatever key scripts/secrets/sync-host-keys.sh already
   # registered for this exact target name. A freshly-generated key can
   # never match that, so every secret (including this host's own login)
   # permanently fails to decrypt. Confirmed live: sops-install-secrets
@@ -26,7 +26,7 @@ let
   hostKeysDir = /. + hostKeysDirStr;
 
   # flakeTarget ("${platform}-${buildType}") comes in via specialArgs from
-  # flake.nix's mkTarget -- exactly the name scripts/sync-host-keys.sh
+  # flake.nix's mkTarget -- exactly the name scripts/secrets/sync-host-keys.sh
   # registers keys under. Deliberately not read back from
   # config.environment.etc."flake-target" (which is set to the same value)
   # -- this module also *contributes* to environment.etc below, and a
@@ -58,8 +58,28 @@ in
     # host.nix declares each host's real hostname (networking.hostName);
     # keep that instead of letting Proxmox's ambient container config win.
     manageHostName = true;
-    # Unprivileged matches how these containers are actually created.
+    # Unprivileged by default -- matches how these containers are actually
-    privileged = false;
+    # created (scripts/proxmox/create-proxmox-resource.sh reads this value
+    # 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";
   };
 
   boot.loader = {

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

@@ -1,23 +1,32 @@
-{ netbootSystem, ... }:
+{ netbootSystem, netbootMinimalSystem, ... }:
 
 let
   # config.system.build.kernel and .netbootRamdisk are directories, not the
   # files themselves — nixpkgs' own system.build.kexecTree does the same
   # ${...}/<file> dereference for the same reason.
-  inherit (netbootSystem.config.system.boot.loader) kernelFile;
+  mkStageRules = { dirName, system }:
+    let
+      inherit (system.config.system.boot.loader) kernelFile;
+      dir = "/srv/pxe/http/${dirName}";
+    in
+    [
+      # Declared here too (not just in build-types/pxe-boot.nix) so this
+      # module's C+ rules don't depend on cross-module list-merge ordering —
+      # tmpfiles' C type needs the target directory to already exist.
+      "d ${dir} 0755 root root -"
+      "C+ ${dir}/${kernelFile} 0644 root root - ${system.config.system.build.kernel}/${kernelFile}"
+      "C+ ${dir}/initrd 0644 root root - ${system.config.system.build.netbootRamdisk}/initrd"
+      "C+ ${dir}/netboot.ipxe 0644 root root - ${system.config.system.build.netbootIpxeScript}/netboot.ipxe"
+    ];
 in
 {
   # Builds this flake's own installer netboot image (the same one
-  # `nix build .#pxe` produces) and stages it where menu.ipxe's :nixos
+  # `nix build .#pxe` produces) plus the vanilla NixOS minimal netboot image
-  # entry expects it, so the pxe-boot host is self-contained — no manual
+  # (`nix build .#pxe-minimal`), and stages both where menu.ipxe's
-  # operator step to populate /srv/pxe/http/nixos after deploy.
+  # :auto-installer / :nixos-minimal entries expect them, so the pxe-boot
-  systemd.tmpfiles.rules = [
+  # host is self-contained — no manual operator step to populate
-    # Declared here too (not just in build-types/pxe-boot.nix) so this
+  # /srv/pxe/http after deploy.
-    # module's C+ rules don't depend on cross-module list-merge ordering —
+  systemd.tmpfiles.rules =
-    # tmpfiles' C type needs the target directory to already exist.
+    mkStageRules { dirName = "auto-installer"; system = netbootSystem; }
-    "d /srv/pxe/http/nixos 0755 root root -"
+    ++ mkStageRules { dirName = "nixos-minimal"; system = netbootMinimalSystem; };
-    "C+ /srv/pxe/http/nixos/${kernelFile} 0644 root root - ${netbootSystem.config.system.build.kernel}/${kernelFile}"
-    "C+ /srv/pxe/http/nixos/initrd 0644 root root - ${netbootSystem.config.system.build.netbootRamdisk}/initrd"
-    "C+ /srv/pxe/http/nixos/netboot.ipxe 0644 root root - ${netbootSystem.config.system.build.netbootIpxeScript}/netboot.ipxe"
-  ];
 }

modules/raspi/mount-data.nix

@@ -1,4 +1,4 @@
-{ vars, ... }:
+{ config, lib, vars, ... }:
 
 {
   fileSystems.${vars.raspiMountpoint} = {
@@ -9,6 +9,15 @@
       "_netdev"
       "noatime"
 
+      # Explicitly use NFSv4.2 if supported
+      "nfsvers=4.2"
+    ] ++ lib.optionals (!config.boot.isContainer) [
+      # `x-systemd.automount` never works inside a Linux container (LXC
+      # included) -- confirmed live on lxc-docker: systemd logs "Starting
+      # of <unit>.automount unsupported" and never mounts it. `nofail`
+      # above already keeps boot non-blocking there, so plain eager
+      # mounting is fine.
+
       # Don't mount until first access
       "x-systemd.automount"
 
@@ -17,9 +26,6 @@
 
       # Give the Pi/Tailscale a little time to appear
       "x-systemd.device-timeout=10s"
-
-      # Explicitly use NFSv4.2 if supported
-      "nfsvers=4.2"
     ];
   };
 

modules/tailscale/exit-node.nix

@@ -1,8 +1,16 @@
 _:
 
 {
+  imports = [ ./enable-service.nix ];
+
   services.tailscale = {
-    enable = true;
+    # 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

modules/tor/enable-relay.nix

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

remove-sensetive-info-refactor.md

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

scripts/bump-nixpkgs-release.sh

@@ -129,5 +129,6 @@ echo "flake.lock still points at the old input revisions until refreshed. Either
 echo "  nix flake update nixpkgs home-manager   # just these two inputs"
 echo "  nix flake update                        # everything — see docs/flake-lock-automation.md"
 echo
-echo "Then run 'bash scripts/codex-maintenance.sh dry-run' before committing —"
+echo "Then run 'bash scripts/codex-maintenance.sh --full-check --dry-run' before"
-echo "a channel bump can shift option defaults across every host."
+echo "committing — a channel bump can shift option defaults across every host,"
+echo "and only --dry-run actually builds anything to catch that."

scripts/codex-maintenance.sh

@@ -1,22 +1,73 @@
 #!/usr/bin/env bash
+# Validation entry point for CI and local/agent review.
+#
+# Default mode (what CI runs on every push/PR): fmt-check, statix, and eval
+# are scoped to files that actually changed against a base ref, plus
+# whichever hosts/packages those changes can affect. This exists because
+# the unscoped sweep below is slow enough to time out CI runners -- see
+# --full-check.
+#
+# --full-check: the historical full sweep (every host, every package,
+# fmt --check ./statix check . over the whole tree). Slow -- minutes, not
+# seconds. CI never passes this; run it locally before a release or after
+# touching modules/common/*, flake.nix, or variables.nix if you want extra
+# confidence beyond what the changed-files scope already covers for those
+# paths (see below).
+#
+# --dry-run: adds `nix build --dry-run --no-link` for whatever scope is
+# active (changed-files scope by default, full scope under --full-check).
+#
+# Per-host/per-package eval and dry-run build calls run concurrently (see
+# scripts/lib/nix-parallel.sh) since they're independent of each other.
+# Concurrency defaults to core count capped by available memory (~1GB/job)
+# rather than plain core count, since each concurrent `nix eval` evaluates a
+# whole NixOS system closure and can OOM a small/memory-constrained CI
+# runner otherwise; override via NIX_PARALLEL_JOBS if a runner has more (or
+# less) room than that estimate assumes.
 set -euo pipefail
 
-export NIX_CONFIG="${NIX_CONFIG:-}
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-experimental-features = nix-command flakes
+# shellcheck source=lib/nix-bootstrap.sh
-accept-flake-config = false
+source "${script_dir}/lib/nix-bootstrap.sh"
-warn-dirty = false
+# shellcheck source=lib/nix-eval.sh
-"
+source "${script_dir}/lib/nix-eval.sh"
+# shellcheck source=lib/nix-parallel.sh
+source "${script_dir}/lib/nix-parallel.sh"
 
-MODE="${1:-validate}"
+repo_root="$(cd "${script_dir}/.." && pwd)"
+cd "$repo_root"
 
-ensure_nix_profile() {
+full_check=false
-  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+dry_run=false
-    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+
-  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+usage() {
-    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
+  cat <<'EOF'
-  fi
+Usage: scripts/codex-maintenance.sh [--full-check] [--dry-run]
+
+  --full-check  Run the full sweep: fmt-check and statix over the whole
+                repo, eval every host and package. Slow. Never run by CI.
+  --dry-run     Additionally run `nix build --dry-run --no-link` for
+                whatever scope is active.
+
+With neither flag (the CI default), fmt-check/statix/eval are scoped to
+files changed against a base ref (env MAINT_BASE_SHA, else the PR base,
+else HEAD^), plus the hosts/packages those changes can affect.
+EOF
 }
 
+for arg in "$@"; do
+  case "$arg" in
+    --full-check) full_check=true ;;
+    --dry-run) dry_run=true ;;
+    -h|--help) usage; exit 0 ;;
+    *)
+      echo "Unknown argument: $arg" >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+done
+
 ensure_nix_profile
 
 if ! command -v nix >/dev/null 2>&1; then
@@ -24,13 +75,6 @@ if ! command -v nix >/dev/null 2>&1; then
   exit 127
 fi
 
-hosts_json="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames)"
-hosts="$(echo "$hosts_json" | jq -r '.[]')"
-
-echo "Hosts:"
-echo "$hosts"
-
-echo
 echo "Checking for obvious committed secrets..."
 if grep -RInE 'github_pat_|ghp_|access-tokens|hashedPassword[[:space:]]*=' \
   --exclude-dir=.git \
@@ -42,71 +86,235 @@ else
   echo "No obvious token patterns found."
 fi
 
+mapfile -t all_hosts < <(list_flake_targets .)
+mapfile -t all_packages < <(nix eval --json "${NIX_EVAL_FLAGS[@]}" .#packages.x86_64-linux --apply builtins.attrNames | jq -r '.[]')
+
+# host_targets_for_dir <hosts-subdir-name>
+# Prints the nixosConfigurations target names whose hostPath is
+# ./hosts/<dir>/host.nix, derived straight from flake.nix's generatedTargets
+# (one mkTarget { ... } call per line) rather than a hand-maintained table,
+# so it can't drift the way a copied mapping would.
+host_targets_for_dir() {
+  local dir="$1"
+  grep -oE '^[[:space:]]*[A-Za-z0-9_-]+ = mkTarget \{[^}]*hostPath = \./hosts/'"${dir}"'/host\.nix;[^}]*\};' flake.nix \
+    | sed -E 's/^[[:space:]]*([A-Za-z0-9_-]+) = mkTarget.*/\1/' \
+    || true
+}
+
+declare -a changed_files=()
+scope_desc="full repo"
+
+if ! $full_check; then
+  resolve_base_ref() {
+    if [[ -n "${MAINT_BASE_SHA:-}" ]] && git cat-file -e "${MAINT_BASE_SHA}^{commit}" 2>/dev/null; then
+      echo "$MAINT_BASE_SHA"
+      return
+    fi
+    if git rev-parse --verify -q HEAD^ >/dev/null 2>&1; then
+      echo "HEAD^"
+      return
+    fi
+    git hash-object -t tree /dev/null
+  }
+
+  base_ref="$(resolve_base_ref)"
+  echo
+  echo "Changed-files scope: diffing against ${base_ref}"
+  mapfile -t changed_files < <(git diff --name-only --diff-filter=ACMR "$base_ref" -- . | sort -u)
+
+  if [[ ${#changed_files[@]} -eq 0 ]]; then
+    echo "No changed files detected."
+  else
+    printf '  %s\n' "${changed_files[@]}"
+  fi
+  scope_desc="changed files only (base: ${base_ref})"
+fi
+
+# Whole-tree fmt/lint always run under --full-check; otherwise scoped below.
+declare -a changed_nix_files=()
+for f in "${changed_files[@]:-}"; do
+  [[ "$f" == *.nix && -f "$f" ]] && changed_nix_files+=("$f")
+done
+
 echo
 echo "Checking Nix formatting with nixpkgs-fmt..."
-nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .
+if $full_check; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check .
+elif [[ ${#changed_nix_files[@]} -gt 0 ]]; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#nixpkgs-fmt -- --check "${changed_nix_files[@]}"
+else
+  echo "No changed .nix files; skipping."
+fi
 
 echo
 echo "Running statix lint..."
-nix run --no-use-registries --no-accept-flake-config github:NixOS/nixpkgs/nixos-25.11#statix -- check .
+if $full_check; then
+  nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#statix -- check .
+elif [[ ${#changed_nix_files[@]} -gt 0 ]]; then
+  for f in "${changed_nix_files[@]}"; do
+    nix run "${NIX_EVAL_FLAGS[@]}" github:NixOS/nixpkgs/nixos-25.11#statix -- check "$f"
+  done
+else
+  echo "No changed .nix files; skipping."
+fi
+
+# Figure out which hosts/packages this run needs to eval (and, under
+# --dry-run, build). full_check always means "everything"; otherwise a
+# change to flake.nix/flake.lock/variables.nix/modules/common/* (repo-wide
+# inputs) or to any other modules/*.nix outside platforms//build-types
+# (whose blast radius isn't safely inferable from the path alone -- see
+# CLAUDE.md's "Grep modules/build-types/*.nix for each build type's imports
+# list") also falls back to everything, on the same reasoning CLAUDE.md
+# already gives interactive sessions for when to run the full sweep.
+# Anything more targeted -- a host.nix, a platform module, a build-type
+# module -- narrows to just the hosts it can affect.
+declare -A affected_hosts=()
+eval_packages=false
+
+if $full_check; then
+  for h in "${all_hosts[@]}"; do affected_hosts[$h]=1; done
+  eval_packages=true
+else
+  full_fallback=false
+  for f in "${changed_files[@]:-}"; do
+    case "$f" in
+      flake.nix|flake.lock|variables.nix|modules/common/*)
+        full_fallback=true
+        ;;
+    esac
+  done
+
+  if ! $full_fallback; then
+    for f in "${changed_files[@]:-}"; do
+      case "$f" in
+        hosts/*/*)
+          hostdir="${f#hosts/}"
+          hostdir="${hostdir%%/*}"
+          while IFS= read -r t; do
+            [[ -n "$t" ]] && affected_hosts[$t]=1
+          done < <(host_targets_for_dir "$hostdir")
+          ;;
+        modules/platforms/*.nix)
+          platform="$(basename "$f" .nix)"
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == "${platform}-"* ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/build-types/*.nix)
+          buildtype="$(basename "$f" .nix)"
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == *"-${buildtype}" ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/installer/*)
+          # iso.nix (imported by both the "installer" nixosConfigurations
+          # target and netbootSystem, which backs packages.pxe) pulls in
+          # common.nix, so a common.nix change reaches all three.
+          affected_hosts[installer]=1
+          eval_packages=true
+          ;;
+        modules/pxe-boot/*)
+          # stage-installer-artifacts.nix is imported by
+          # modules/build-types/pxe-boot.nix only -- same blast radius as a
+          # build-types/*.nix change, not a packages one.
+          for h in "${all_hosts[@]}"; do
+            [[ "$h" == *"-pxe-boot" ]] && affected_hosts[$h]=1
+          done
+          ;;
+        modules/*)
+          full_fallback=true
+          ;;
+      esac
+    done
+  fi
+
+  if $full_fallback; then
+    echo
+    echo "Changed files affect shared config; falling back to evaluating every host/package."
+    for h in "${all_hosts[@]}"; do affected_hosts[$h]=1; done
+    eval_packages=true
+  fi
+fi
+
+mapfile -t hosts < <(for h in "${!affected_hosts[@]}"; do echo "$h"; done | sort)
 
 echo
-echo "Evaluating host toplevel derivations..."
+echo "Checking nix-cache host key for drift..."
-for host in $hosts; do
+if bash "${script_dir}/secrets/sync-nix-cache-host-key.sh" --check; then
-  echo "==> $host"
+  :
-  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
+else
+  drift_status=$?
+  if [[ "$drift_status" -eq 2 ]]; then
+    echo "nix-cache unreachable from here -- skipping host-key drift check."
+  else
+    echo "WARNING: nix-cache's host key has drifted from variables.nix (see above)." >&2
+    echo "  Run 'bash scripts/secrets/sync-nix-cache-host-key.sh' to fix." >&2
+  fi
+fi
 
+echo
+if [[ ${#hosts[@]} -eq 0 ]]; then
+  echo "No hosts affected by changed files; skipping host eval."
+else
+  echo "Evaluating host toplevel derivations (${scope_desc}, up to ${NIX_PARALLEL_JOBS} at a time)..."
   # lxc-* hosts deploy via a directly pct-restore-able tarball instead of
   # nixos-install (see docs/auto-installer.md); proxmox-* hosts can
   # alternatively be built as a standalone disk image (see
   # docs/proxmox-images.md). Both are otherwise-unvalidated buildable
   # surface, easy to silently break without this.
-  case "$host" in
+  declare -a host_eval_jobs=()
-    lxc-*)
+  for host in "${hosts[@]}"; do
-      echo "==> $host (tarball)"
+    host_eval_jobs+=("${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel.drvPath")
-      nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.tarball.drvPath"
-      ;;
-    proxmox-*)
-      echo "==> $host (diskoImagesScript)"
-      nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath"
-      ;;
-  esac
-done
-
-echo
-echo "Evaluating buildable packages..."
-packages_json="$(nix eval --json --no-use-registries --no-accept-flake-config .#packages.x86_64-linux --apply builtins.attrNames)"
-packages="$(echo "$packages_json" | jq -r '.[]')"
-for pkg in $packages; do
-  echo "==> packages.x86_64-linux.${pkg}"
-  nix eval --raw --no-use-registries --no-accept-flake-config ".#packages.x86_64-linux.${pkg}"
-done
-
-if [[ "$MODE" == "dry-run" ]]; then
-  echo
-  echo "Running dry-run builds for all hosts. This will not create result symlinks."
-  for host in $hosts; do
-    echo "==> Dry-run build: $host"
-    nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel"
-
     case "$host" in
       lxc-*)
-        echo "==> Dry-run build: $host (tarball)"
+        host_eval_jobs+=("${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball.drvPath")
-        nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.tarball"
         ;;
       proxmox-*)
-        echo "==> Dry-run build: $host (diskoImagesScript)"
+        host_eval_jobs+=("${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript.drvPath")
-        nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.diskoImagesScript"
         ;;
     esac
   done
+  run_nix_parallel host_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+fi
 
-  echo
+echo
-  echo "Running dry-run builds for all packages."
+if ! $eval_packages; then
-  for pkg in $packages; do
+  echo "No packages affected by changed files; skipping package eval."
-    echo "==> Dry-run build: packages.x86_64-linux.${pkg}"
+else
-    nix build --dry-run --no-link --no-use-registries --no-accept-flake-config ".#packages.x86_64-linux.${pkg}"
+  echo "Evaluating buildable packages (up to ${NIX_PARALLEL_JOBS} at a time)..."
+  declare -a package_eval_jobs=()
+  for pkg in "${all_packages[@]}"; do
+    package_eval_jobs+=("packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
   done
+  run_nix_parallel package_eval_jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+fi
+
+if $dry_run; then
+  echo
+  echo "Running dry-run builds for the active scope (up to ${NIX_PARALLEL_JOBS} at a time). This will not create result symlinks."
+  declare -a host_build_jobs=()
+  for host in "${hosts[@]:-}"; do
+    host_build_jobs+=("Dry-run build: ${host}${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.toplevel")
+    case "$host" in
+      lxc-*)
+        host_build_jobs+=("Dry-run build: ${host} (tarball)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.tarball")
+        ;;
+      proxmox-*)
+        host_build_jobs+=("Dry-run build: ${host} (diskoImagesScript)${NIX_PARALLEL_SEP}.#nixosConfigurations.${host}.config.system.build.diskoImagesScript")
+        ;;
+    esac
+  done
+  run_nix_parallel host_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+
+  if $eval_packages; then
+    echo
+    echo "Running dry-run builds for packages."
+    declare -a package_build_jobs=()
+    for pkg in "${all_packages[@]}"; do
+      package_build_jobs+=("Dry-run build: packages.x86_64-linux.${pkg}${NIX_PARALLEL_SEP}.#packages.x86_64-linux.${pkg}")
+    done
+    run_nix_parallel package_build_jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+  fi
 fi
 
 echo

scripts/codex-setup.sh

@@ -1,19 +1,11 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-export NIX_CONFIG="${NIX_CONFIG:-}
+script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-experimental-features = nix-command flakes
+# shellcheck source=lib/nix-bootstrap.sh
-accept-flake-config = false
+source "${script_dir}/lib/nix-bootstrap.sh"
-warn-dirty = false
+# shellcheck source=lib/nix-eval.sh
-"
+source "${script_dir}/lib/nix-eval.sh"
-
-ensure_nix_profile() {
-  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
-    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
-  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
-    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
-  fi
-}
 
 install_nix_if_missing() {
   if command -v nix >/dev/null 2>&1; then
@@ -49,6 +41,17 @@ warn-dirty = false
 build-users-group = nixbld
 EOF
 
+    # The official installer's single-user root path still shells out to
+    # `sudo` to create /nix even though it already knows it's running as
+    # root -- confirmed live against a sudo-less minimal Debian/Proxmox
+    # node, where it fails with "sudo: not found" and prints this exact
+    # mkdir/chown as the manual fix. Pre-create it so that branch of the
+    # installer is skipped entirely.
+    if [ ! -d /nix ]; then
+      mkdir -m 0755 /nix
+      chown root /nix
+    fi
+
     sh <(curl -L https://nixos.org/nix/install) --no-daemon
   else
     sh <(curl -L https://nixos.org/nix/install) --no-daemon
@@ -79,13 +82,6 @@ if ! command -v jq >/dev/null 2>&1; then
 fi
 
 echo "Available NixOS hosts:"
-hosts="$(nix eval --json --no-use-registries --no-accept-flake-config .#nixosConfigurations --apply builtins.attrNames | jq -r '.[]')"
+list_flake_targets .
-echo "$hosts"
 
-echo "Evaluating all host toplevel derivations..."
+echo "Codex setup complete. Run bash scripts/codex-maintenance.sh to validate changes."
-for host in $hosts; do
-  echo "==> Evaluating $host"
-  nix eval --raw --no-use-registries --no-accept-flake-config ".#nixosConfigurations.${host}.config.system.build.toplevel.drvPath"
-done
-
-echo "Codex setup complete."

scripts/create-proxmox-resource.sh

@@ -1,556 +0,0 @@
-#!/usr/bin/env bash
-# Creates new Proxmox VMs/LXC containers from this flake, and reconfigures
-# existing ones -- the manual workflows in docs/proxmox-images.md (VM) and
-# docs/auto-installer.md's "LXC hosts" section (container), automated.
-#
-# Usage:
-#   scripts/create-proxmox-resource.sh --type lxc|vm --host <name> [options]
-#   scripts/create-proxmox-resource.sh --type lxc|vm --list
-#   scripts/create-proxmox-resource.sh --modify --vmid <n> [--cores N] [--memory MB] [--grow-disk GB]
-#
-# SAFETY:
-#   - The default (create) mode only ever creates a NEW resource -- it
-#     refuses to run if the target VMID already exists on the node, or if
-#     a VM/CT identified as --host already exists under any other VMID
-#     (checked live against the node; --allow-duplicate-host overrides).
-#   - --modify only ever touches a resource you name explicitly via
-#     --vmid, shows exactly what will change first, and (outside
-#     --dry-run) always requires typing that VMID back to confirm before
-#     anything is sent to the node. There is no bulk/implicit modify.
-#   - Neither mode can start/stop/delete a resource. Not implemented on
-#     purpose -- ask before adding it.
-#
-# See --help for the full option list.
-set -euo pipefail
-
-repo_root="$(cd "$(dirname "$0")/.." && pwd)"
-# shellcheck source=env.sh
-source "${repo_root}/scripts/env.sh"
-
-sync_keys="${repo_root}/scripts/sync-host-keys.sh"
-
-usage() {
-  cat <<EOF
-Usage: $0 --type lxc|vm --host <name> [options]      (create)
-       $0 --type lxc|vm --list                        (list --host values)
-       $0 --modify --vmid <n> [options]                (reconfigure)
-
-Create mode (default):
-  --type lxc|vm        lxc = container, built as a CT template tarball.
-                        vm  = VM, built as a Disko .raw disk image (UEFI/OVMF).
-  --host <name>         Which host identity to deploy -- matches
-                        config.networking.hostName (server, docker,
-                        nix-cache, nixos, pxe-boot, nix-minimal). Use
-                        --list to see what's available for --type.
-  --name <name>          Proxmox display name/hostname (default: --host's
-                          value, e.g. nix-cache -- for lxc this becomes the
-                          guest's real networking.hostName too, since
-                          proxmoxLXC.manageHostName pulls it from Proxmox's
-                          own container config, so it must match host.nix
-                          regardless of build type)
-  --vmid <n>              Numeric VMID (default: next free, via
-                          \`pvesh get /cluster/nextid\` on the node).
-                          Refuses to run if this ID already exists.
-  --disk-size <GB>           lxc only: rootfs size for \`pct create\`
-                              (default: \$PROXMOX_DEFAULT_LXC_DISK_GB, ${PROXMOX_DEFAULT_LXC_DISK_GB}).
-  --image <path>              Use this local image/tarball instead of
-                              checking the node / building one from the flake.
-  --force-rebuild                Skip the "does the node already have this
-                                  image" check -- always build fresh and
-                                  overwrite what's there.
-  --allow-duplicate-host        Required if a VM/CT identified as --host
-                                already exists on the node (checked live via
-                                qm/pct, not any file in this repo) --
-                                otherwise refused, since it'd share that
-                                host's hostName/hostId.
-
-Modify mode (reconfigure an EXISTING resource -- requires --modify):
-  --modify                Switch to modify mode.
-  --vmid <n>                Required: which existing resource to change.
-                            Type/VM-vs-CT is auto-detected on the node.
-  --grow-disk <GB>            Grow the primary disk by this many GB
-                              (qm/pct resize; Proxmox only supports
-                              growing, never shrinking, an existing disk).
-  At least one of --cores / --memory / --grow-disk is required. Always
-  prints the current -> new values and requires typing the VMID back to
-  confirm, even outside --dry-run.
-
-Shared:
-  --cores <n>              create: default \$PROXMOX_DEFAULT_CORES (${PROXMOX_DEFAULT_CORES}).
-                            modify: omit to leave unchanged.
-  --memory <MB>              create: default \$PROXMOX_DEFAULT_MEMORY_MB (${PROXMOX_DEFAULT_MEMORY_MB}).
-                              modify: omit to leave unchanged.
-  --swap <MB>                 lxc only, create time: \`--memory\` doesn't
-                              touch swap -- it silently stays at Proxmox's
-                              own 512M default otherwise. (default: matches
-                              whatever --memory resolves to)
-  --storage <pool>              (default: \$PROXMOX_STORAGE, ${PROXMOX_STORAGE})
-  --iso-storage <pool>            (default: \$PROXMOX_ISO_STORAGE, ${PROXMOX_ISO_STORAGE})
-  --bridge <bridge>                (default: \$PROXMOX_BRIDGE, ${PROXMOX_BRIDGE})
-  --node <host>                     Proxmox node to SSH into (default:
-                                    \$PROXMOX_HOST, ${PROXMOX_HOST})
-  --dry-run                           Print the full plan; touch nothing
-                                      local or remote, no prompts.
-  -h, --help
-
-Config for --storage/--bridge/--node/etc. lives in scripts/env.sh -- edit
-that instead of passing the same flag every time.
-EOF
-}
-
-dry_run=0
-modify=0
-type=""
-host=""
-name=""
-vmid=""
-cores=""
-memory=""
-swap=""
-disk_size=""
-grow_disk=""
-image=""
-storage="$PROXMOX_STORAGE"
-iso_storage="$PROXMOX_ISO_STORAGE"
-bridge="$PROXMOX_BRIDGE"
-node="$PROXMOX_HOST"
-do_list=0
-allow_duplicate_host=0
-force_rebuild=0
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-  --type) type="$2"; shift 2 ;;
-  --host) host="$2"; shift 2 ;;
-  --name) name="$2"; shift 2 ;;
-  --vmid) vmid="$2"; shift 2 ;;
-  --cores) cores="$2"; shift 2 ;;
-  --memory) memory="$2"; shift 2 ;;
-  --swap) swap="$2"; shift 2 ;;
-  --disk-size) disk_size="$2"; shift 2 ;;
-  --grow-disk) grow_disk="$2"; shift 2 ;;
-  --image) image="$2"; shift 2 ;;
-  --storage) storage="$2"; shift 2 ;;
-  --iso-storage) iso_storage="$2"; shift 2 ;;
-  --bridge) bridge="$2"; shift 2 ;;
-  --node) node="$2"; shift 2 ;;
-  --list) do_list=1; shift ;;
-  --allow-duplicate-host) allow_duplicate_host=1; shift ;;
-  --force-rebuild) force_rebuild=1; shift ;;
-  --modify) modify=1; shift ;;
-  --dry-run) dry_run=1; shift ;;
-  -h | --help) usage; exit 0 ;;
-  *) echo "Unknown option: $1" >&2; usage >&2; exit 1 ;;
-  esac
-done
-
-ssh_target="${PROXMOX_SSH_USER}@${node}"
-
-remote() {
-  if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] ssh ${ssh_target} -- $*"
-  else
-    ssh "$ssh_target" "$@"
-  fi
-}
-
-# ============================================================ modify mode
-cmd_modify() {
-  if [[ -z "$vmid" ]]; then
-    echo "ERROR: --modify requires --vmid." >&2
-    exit 1
-  fi
-  if [[ -z "$cores" && -z "$memory" && -z "$grow_disk" ]]; then
-    echo "ERROR: --modify needs at least one of --cores / --memory / --grow-disk." >&2
-    exit 1
-  fi
-
-  echo "Looking up VMID ${vmid} on ${node}..."
-  local kind current_cores current_memory disk_key
-  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1; then
-    kind="vm"
-    disk_key="scsi0"
-  elif ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
-    kind="lxc"
-    disk_key="rootfs"
-  else
-    echo "ERROR: VMID ${vmid} doesn't exist on ${node} -- nothing to modify." >&2
-    exit 1
-  fi
-
-  local config_cmd="qm config ${vmid}"
-  [[ "$kind" == "lxc" ]] && config_cmd="pct config ${vmid}"
-  local current_config
-  current_config="$(ssh "$ssh_target" "$config_cmd")"
-  current_cores="$(echo "$current_config" | grep -oP '^cores:\s*\K\S+' || echo '?')"
-  current_memory="$(echo "$current_config" | grep -oP '^memory:\s*\K\S+' || echo '?')"
-
-  echo
-  echo "VMID ${vmid} is a ${kind} on ${node}. Planned changes:"
-  [[ -n "$cores" ]] && echo "  cores:  ${current_cores} -> ${cores}"
-  [[ -n "$memory" ]] && echo "  memory: ${current_memory} MB -> ${memory} MB"
-  [[ -n "$grow_disk" ]] && echo "  ${disk_key}: grow by +${grow_disk}G (Proxmox can only grow, not shrink, an existing disk)"
-
-  if [[ "$dry_run" -eq 1 ]]; then
-    echo
-    echo "[dry-run] Nothing was changed."
-    return
-  fi
-
-  echo
-  read -rp "Type the VMID (${vmid}) to confirm these changes: " confirm
-  if [[ "$confirm" != "$vmid" ]]; then
-    echo "Cancelled -- input didn't match ${vmid}."
-    exit 1
-  fi
-
-  local set_cmd="qm set"
-  local resize_cmd="qm resize"
-  [[ "$kind" == "lxc" ]] && set_cmd="pct set" && resize_cmd="pct resize"
-
-  if [[ -n "$cores" || -n "$memory" ]]; then
-    local args=""
-    [[ -n "$cores" ]] && args="${args} --cores ${cores}"
-    [[ -n "$memory" ]] && args="${args} --memory ${memory}"
-    remote "${set_cmd} ${vmid}${args}"
-  fi
-  if [[ -n "$grow_disk" ]]; then
-    remote "${resize_cmd} ${vmid} ${disk_key} +${grow_disk}G"
-  fi
-
-  echo
-  echo "Done. VMID ${vmid} updated."
-}
-
-if [[ "$modify" -eq 1 ]]; then
-  cmd_modify
-  exit 0
-fi
-
-# ============================================================= create mode
-if [[ "$type" != "lxc" && "$type" != "vm" ]]; then
-  echo "ERROR: --type must be 'lxc' or 'vm'." >&2
-  usage >&2
-  exit 1
-fi
-
-platform_prefix="lxc"
-[[ "$type" == "vm" ]] && platform_prefix="proxmox"
-[[ -z "$cores" ]] && cores="$PROXMOX_DEFAULT_CORES"
-[[ -z "$memory" ]] && memory="$PROXMOX_DEFAULT_MEMORY_MB"
-
-# --- discover / resolve the flake target from --host --------------------
-list_hosts() {
-  local target hostname
-  for target in $(nix eval --json --no-use-registries --no-accept-flake-config \
-    "${repo_root}#nixosConfigurations" --apply builtins.attrNames 2>/dev/null \
-    | jq -r --arg p "${platform_prefix}-" '.[] | select(startswith($p))'); do
-    hostname="$(nix eval --raw --no-use-registries --no-accept-flake-config \
-      "${repo_root}#nixosConfigurations.${target}.config.networking.hostName" 2>/dev/null)"
-    printf '  %-12s -> %s\n' "$hostname" "$target"
-  done
-}
-
-if [[ "$do_list" -eq 1 ]]; then
-  echo "Available --host values for --type ${type}:"
-  list_hosts
-  exit 0
-fi
-
-if [[ -z "$host" ]]; then
-  echo "ERROR: --host is required (or use --list to see options)." >&2
-  exit 1
-fi
-
-flake_target=""
-for target in $(nix eval --json --no-use-registries --no-accept-flake-config \
-  "${repo_root}#nixosConfigurations" --apply builtins.attrNames \
-  | jq -r --arg p "${platform_prefix}-" '.[] | select(startswith($p))'); do
-  hn="$(nix eval --raw --no-use-registries --no-accept-flake-config \
-    "${repo_root}#nixosConfigurations.${target}.config.networking.hostName")"
-  if [[ "$hn" == "$host" ]]; then
-    flake_target="$target"
-    break
-  fi
-done
-
-if [[ -z "$flake_target" ]]; then
-  echo "ERROR: no ${platform_prefix}-* target has hostName '${host}'." >&2
-  echo "Available:" >&2
-  list_hosts >&2
-  exit 1
-fi
-
-# The container/VM's real identity is --host (e.g. "nix-cache"), validated
-# above against config.networking.hostName -- not the flake target name
-# (e.g. "lxc-nix-cache"), which is build-type-specific and only exists to
-# pick which platform variant to build. Defaulting --name to the flake
-# target would make lxc's --hostname (which proxmoxLXC.manageHostName
-# feeds straight into the guest's real hostname) disagree with host.nix.
-[[ -z "$name" ]] && name="$host"
-
-# --- 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
-# actually exists, and this used to be checked against variables.nix's
-# deployedTargets, which drifted stale (it kept naming a VM as "the real
-# deployment" well after that VM had been destroyed, blocking its own
-# redeploy) until that list was dropped in favour of this live check. This
-# only catches guests identified with the default --name (== --host, what
-# this script itself always uses unless --name is overridden) -- a guest
-# manually renamed on the node afterwards wouldn't match, but nothing here
-# creates guests that way.
-if [[ "$allow_duplicate_host" -eq 1 ]]; then
-  echo
-  echo "--allow-duplicate-host: skipping the check for an existing '${host}' on ${node}."
-elif [[ "$dry_run" -eq 1 ]]; then
-  echo
-  echo "[dry-run] would check ${node} for an existing VM/CT identified as '${host}'"
-else
-  echo
-  echo "==> Checking ${node} for an existing VM/CT identified as '${host}'..."
-  ssh_check_status=0
-  existing="$(ssh "$ssh_target" bash -s -- "$host" <<'REMOTE_SCRIPT'
-target="$1"
-for id in $(qm list 2>/dev/null | awk 'NR>1{print $1}'); do
-  n="$(qm config "$id" 2>/dev/null | grep -oP '^name:\s*\K\S+' || true)"
-  [[ "$n" == "$target" ]] && echo "vm ${id} ${n}"
-done
-for id in $(pct list 2>/dev/null | awk 'NR>1{print $1}'); do
-  n="$(pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
-  [[ "$n" == "$target" ]] && echo "lxc ${id} ${n}"
-done
-REMOTE_SCRIPT
-  )" || ssh_check_status=$?
-  if [[ "$ssh_check_status" -ne 0 ]]; then
-    echo "ERROR: couldn't reach ${node} (ssh exited ${ssh_check_status}) to check for an" >&2
-    echo "existing '${host}' resource -- refusing to guess. Fix connectivity and retry," >&2
-    echo "or pass --allow-duplicate-host if you're sure none exists (this skips the" >&2
-    echo "check entirely)." >&2
-    exit 1
-  fi
-  if [[ -n "$existing" ]]; then
-    echo "ERROR: '${host}' already exists on ${node}:" >&2
-    echo "$existing" | while read -r kind id n; do
-      echo "  - ${kind} VMID ${id} (${n})" >&2
-    done
-    echo "Refusing to create a second resource sharing this identity. Pass" >&2
-    echo "--allow-duplicate-host to create one anyway (it gets its own distinct" >&2
-    echo "sops key and VMID -- the existing resource(s) above are left untouched)," >&2
-    echo "or use --modify to reconfigure the existing one instead." >&2
-    exit 1
-  fi
-fi
-
-echo "Target: ${flake_target} (host=${host}, type=${type}) -> Proxmox resource '${name}'"
-
-# Decide on nix-cache once, here -- this is the earliest point that needs
-# it (sync-host-keys.sh below needs nix-shell packages regardless of
-# whether an image ends up getting built later), and the decision is
-# exported so that subprocess -- and this script's own later build step,
-# if it gets there -- both reuse it instead of probing again.
-nix_extra_opts
-
-# --- make sure this target has a registered host key --------------------
-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[@]}"
-
-# --- VMID: pick one, and refuse to touch anything that already exists ---
-echo
-if [[ -z "$vmid" ]]; then
-  if [[ "$dry_run" -eq 1 ]]; then
-    vmid="<next-free-vmid>"
-    echo "[dry-run] would ask ${node} for the next free VMID (pvesh get /cluster/nextid)"
-  else
-    vmid="$(ssh "$ssh_target" "pvesh get /cluster/nextid" | tr -d '[:space:]')"
-    echo "Auto-assigned VMID: ${vmid}"
-  fi
-else
-  echo "Requested VMID: ${vmid}"
-fi
-
-if [[ "$dry_run" -eq 0 ]]; then
-  # qm/pct status exits non-zero (and prints "does not exist") for a free
-  # ID on that resource type -- but a VMID could exist as the OTHER
-  # resource type (e.g. requested a CT id that's actually a VM), so check
-  # both. Any success here means something is already using this ID --
-  # refuse to go anywhere near it. (Reconfiguring an existing resource is
-  # --modify's job, not this one's.)
-  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1 \
-    || ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
-    echo "ERROR: VMID ${vmid} already exists on ${node}. Refusing to touch an" >&2
-    echo "existing resource here -- use --modify to reconfigure it, pick a" >&2
-    echo "different --vmid, or omit it to auto-assign." >&2
-    exit 1
-  fi
-fi
-
-# --- resolve the remote path -- fixed naming (not the nix store's own
-# derivation-hash-based filename), so a later run can check for it by name.
-# lxc uploads as a CT *template* (Proxmox's "vztmpl" content type, under
-# iso_storage) -- config.system.build.tarball is a plain rootfs tarball,
-# not a vzdump backup archive, so it's created with `pct create ... vztmpl`,
-# not restored with `pct restore` (that expects backup-archive metadata
-# this tarball doesn't have, and fails with "archive contains no
-# configuration file").
-remote_dir="/var/lib/vz/import"
-remote_filename="${flake_target}.raw"
-if [[ "$type" == "lxc" ]]; then
-  remote_dir="/var/lib/vz/template/cache"
-  remote_filename="${flake_target}.tar.xz"
-fi
-remote_path="${remote_dir}/${remote_filename}"
-
-# --- build (or reuse an image already on the node) ------------------------
-echo
-local_image=""
-image_already_remote=0
-
-if [[ -n "$image" ]]; then
-  [[ -f "$image" ]] || { echo "ERROR: --image '${image}' not found." >&2; exit 1; }
-  local_image="$image"
-  echo "Using provided image: ${local_image}"
-elif [[ "$force_rebuild" -eq 1 ]]; then
-  echo "--force-rebuild: skipping the existing-image check on ${node}."
-else
-  echo "==> Checking whether ${node} already has ${remote_path}..."
-  if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] would check: ssh ${ssh_target} -- test -f ${remote_path}"
-  elif ssh "$ssh_target" "test -f '${remote_path}'" 2>/dev/null; then
-    echo "Found it -- reusing, skipping build and upload (use --force-rebuild to override)."
-    image_already_remote=1
-  else
-    echo "Not found -- will build."
-  fi
-fi
-
-if [[ "$image_already_remote" -eq 0 && -z "$local_image" ]]; then
-  # Mirrors the real build commands' "${NIX_OPTS[@]}" below -- nix_extra_opts
-  # (called earlier, once) has already decided whether nix-cache is in play,
-  # and the dry-run preview needs to reflect that decision instead of always
-  # printing the same command regardless of outcome.
-  nix_opts_display=""
-  if [[ ${#NIX_OPTS[@]} -gt 0 ]]; then
-    printf -v nix_opts_display '%q ' "${NIX_OPTS[@]}"
-    nix_opts_display=" ${nix_opts_display% }"
-  fi
-  if [[ "$type" == "lxc" ]]; then
-    if [[ "$dry_run" -eq 1 ]]; then
-      echo "[dry-run] would build: NIXOS_HOST_KEYS_DIR=${repo_root}/host-keys nix build --impure \\"
-      echo "[dry-run]   --no-use-registries --no-accept-flake-config${nix_opts_display} \\"
-      echo "[dry-run]   .#nixosConfigurations.${flake_target}.config.system.build.tarball"
-      local_image="<built-tarball>"
-    else
-      echo "==> Building LXC tarball for ${flake_target}..."
-      NIXOS_HOST_KEYS_DIR="${repo_root}/host-keys" nix build --impure \
-        --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
-        ".#nixosConfigurations.${flake_target}.config.system.build.tarball" \
-        --out-link "${repo_root}/result-${flake_target}"
-      local_image="$(find "${repo_root}/result-${flake_target}/tarball" -maxdepth 1 -type f | head -1)"
-      echo "Built: ${local_image}"
-    fi
-  else
-    if [[ "$dry_run" -eq 1 ]]; then
-      echo "[dry-run] would build: nix build --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 ./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"
-      local_image="<built-image>.raw"
-    else
-      echo "==> Building Disko image script for ${flake_target}..."
-      nix build --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
-        ".#nixosConfigurations.${flake_target}.config.system.build.diskoImagesScript" \
-        --out-link "${repo_root}/result-${flake_target}"
-      echo "==> Running it (builds the .raw image in a temporary QEMU VM, needs sudo)..."
-      ( cd "$repo_root" && sudo "./result-${flake_target}" \
-          --pre-format-files "host-keys/${flake_target}_ssh_host_ed25519_key" /etc/ssh/ssh_host_ed25519_key \
-          --pre-format-files "host-keys/${flake_target}_ssh_host_ed25519_key.pub" /etc/ssh/ssh_host_ed25519_key.pub \
-          --build-memory 2048 )
-      local_image="$(find "$repo_root" -maxdepth 1 -name "*.raw" -newer "${repo_root}/result-${flake_target}" | head -1)"
-      if [[ -z "$local_image" ]]; then
-        echo "ERROR: expected a .raw image after the build but didn't find one in ${repo_root}." >&2
-        exit 1
-      fi
-      echo "Built: ${local_image}"
-    fi
-  fi
-fi
-
-# --- upload (skip entirely if reusing an image already on the node) ------
-echo
-if [[ "$image_already_remote" -eq 1 ]]; then
-  : # nothing to upload
-elif [[ "$dry_run" -eq 1 ]]; then
-  echo "[dry-run] would upload: scp ${local_image} ${ssh_target}:${remote_path}"
-else
-  echo "==> Uploading to ${node}:${remote_path}..."
-  ssh "$ssh_target" "mkdir -p ${remote_dir}"
-  scp "$local_image" "${ssh_target}:${remote_path}"
-fi
-
-# --- create -----------------------------------------------------------------
-echo
-if [[ "$type" == "lxc" ]]; then
-  echo "==> Creating LXC container ${vmid} (${name})..."
-  local_disk_size="${disk_size:-$PROXMOX_DEFAULT_LXC_DISK_GB}"
-  # --memory doesn't touch swap -- it silently stays at Proxmox's own
-  # 512M default otherwise (confirmed live: --memory 2048 left swap at
-  # 512). Default to matching whatever --memory resolved to above.
-  local_swap="${swap:-$memory}"
-  # --unprivileged 1: modules/platforms/lxc.nix sets proxmoxLXC.privileged
-  # = false, so the NixOS config inside the image assumes it's running as
-  # an unprivileged container (cgroup/capability/mount expectations baked
-  # in at boot). `pct create`'s own CLI default for this flag is
-  # privileged (unlike the web UI, which defaults its checkbox the other
-  # way) -- leaving it unset creates a privileged container running a
-  # NixOS config that assumes unprivileged, a real mismatch.
-  #
-  # --features nesting=1,keyctl=1: required for a modern (v247+) systemd
-  # guest to actually boot unprivileged -- confirmed live: without this,
-  # AppArmor denies the nested user namespaces and credential mounts
-  # systemd routinely uses (even plain getty units), and every getty
-  # crash-loops on a denied mount every ~3s (visible as garbage on the
-  # console) while core services like nsncd fail the same way.
-  create_cmd="pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged 1 --features ${PROXMOX_DEFAULT_LXC_FEATURES} --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
-  remote "$create_cmd"
-  remote "pct start ${vmid}"
-else
-  echo "==> Creating VM ${vmid} (${name})..."
-  # pre-enrolled-keys=0 disables OVMF's Secure Boot key pre-enrollment --
-  # required, or systemd-boot (unsigned) can't be trusted by the firmware.
-  remote "qm create ${vmid} --name ${name} --memory ${memory} --cores ${cores} \
---net0 virtio,bridge=${bridge} --bios ovmf --machine q35 --scsihw virtio-scsi-pci \
---efidisk0 ${storage}:1,efitype=4m,pre-enrolled-keys=0"
-
-  if [[ "$dry_run" -eq 1 ]]; then
-    echo "[dry-run] ssh ${ssh_target} -- qm importdisk ${vmid} ${remote_path} ${storage}"
-    echo "[dry-run] (would parse the resulting disk identifier from that output)"
-    echo "[dry-run] ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<parsed-disk-id>"
-  else
-    importdisk_output="$(ssh "$ssh_target" "qm importdisk ${vmid} ${remote_path} ${storage}")"
-    echo "$importdisk_output"
-    disk_id="$(echo "$importdisk_output" | grep -oP "(?<=Successfully imported disk as ')[^']+" | sed 's/^unused[0-9]*://')"
-    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
-      echo "  ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<disk-id-from-output-above>" >&2
-      echo "  ssh ${ssh_target} -- qm set ${vmid} --boot order=scsi0" >&2
-      exit 1
-    fi
-    remote "qm set ${vmid} --scsi0 ${disk_id}"
-  fi
-  remote "qm set ${vmid} --boot order=scsi0"
-  remote "qm start ${vmid}"
-fi
-
-echo
-if [[ "$dry_run" -eq 1 ]]; then
-  echo "[dry-run] Nothing was built, uploaded, or created."
-else
-  echo "Done. ${name} (VMID ${vmid}) should be booting on ${node}."
-fi

scripts/env.sh

@@ -3,21 +3,39 @@
 # second copy of these values in every script:
 #   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/env.sh"
 # Every variable can still be overridden per-invocation via the
-# environment (e.g. PROXMOX_STORAGE=tank-nvme ./scripts/create-proxmox-resource.sh ...)
+# environment (e.g. PROXMOX_STORAGE=tank-nvme ./scripts/proxmox/create-proxmox-resource.sh ...)
 # since each one only sets a default if unset.
 
-# SSH-reachable Proxmox node that scripts/create-proxmox-resource.sh runs
+# Two SSH-reachable Proxmox nodes exist on the LAN:
-# pct/qm on. Matches the Proxmox web UI hostname already used in
+#   - pve1.sweet.home      -- production. Real, live VMs/containers.
-# hosts/nixos/home.nix's desktop shortcuts (pve.<homeDomain> from
+#   - pve-test.sweet.home  -- sandbox/test node, for scratch VMs/containers
-# variables.nix) -- change this if that's not actually reachable over SSH,
+#     that don't belong on production.
-# or if you're targeting a different node in a multi-node cluster.
+#
-: "${PROXMOX_HOST:=pve.sweet.home}"
+# PROXMOX_HOST is what scripts/proxmox/create-proxmox-resource.sh actually
+# targets by default -- overridable per-invocation with --node <hostname>,
+# or per-variable as usual (e.g. PROXMOX_HOST=$PVE_TEST_HOST). It defaults
+# to production, matching this repo's behavior before pve-test existed --
+# see CLAUDE.md's "Two Proxmox nodes" section for the policy on which
+# situations should target which node (in particular: Claude defaults to
+# pve-test, not this variable's own default, unless explicitly told
+# otherwise).
+: "${PVE1_HOST:=pve1.sweet.home}"
+: "${PVE_TEST_HOST:=pve-test.sweet.home}"
+: "${PROXMOX_HOST:=$PVE1_HOST}"
 : "${PROXMOX_SSH_USER:=root}"
 
+# Where this flake repo lives on the Proxmox node itself.
+# scripts/proxmox/create-proxmox-resource.sh builds images directly on the node
+# instead of transferring them over the network -- it clones the repo here
+# (from this checkout's own `origin` remote) the first time it doesn't
+# find it, installing build tooling via scripts/codex-setup.sh, then
+# `git pull`s it before every subsequent build.
+: "${PROXMOX_REMOTE_REPO_DIR:=/root/nixos}"
+
 # Storage pool names -- Proxmox's own stock-install defaults, but this
 # varies a lot by setup (ZFS pool name, custom LVM-thin volume, etc.).
 # Verify with `pvesm status` on the node and correct these if wrong.
-: "${PROXMOX_STORAGE:=local-lvm}"     # VM disks / CT rootfs
+: "${PROXMOX_STORAGE:=local-zfs}"     # VM disks / CT rootfs
 : "${PROXMOX_ISO_STORAGE:=local}"     # uploaded images/ISOs/CT templates
 
 : "${PROXMOX_BRIDGE:=vmbr0}"
@@ -45,16 +63,31 @@
 # crash-loops on a denied `/run/credentials/*` mount every ~3s (visible
 # as garbage on the console) and core services like nsncd fail the same
 # way on userns_create; system.build.tarball never finishes activating.
-: "${PROXMOX_DEFAULT_LXC_FEATURES:=nesting=1,keyctl=1}"
+#
+# mount=nfs;nfs4: without it, AppArmor blanket-denies the `nfs`/
+# `rpc_pipefs` mount syscalls any NFS client share needs -- confirmed
+# live on lxc-docker (which mounts several, see modules/docker/mount-data.nix
+# and modules/raspi/mount-data.nix): `mount: /var/lib/nfs/rpc_pipefs:
+# permission denied`. Harmless to grant on lxc targets that don't mount
+# NFS at all -- it only widens what the container is *allowed* to mount,
+# nothing here forces a mount to happen.
+: "${PROXMOX_DEFAULT_LXC_FEATURES:=nesting=1,keyctl=1,mount=nfs;nfs4}"
 
-export PROXMOX_HOST PROXMOX_SSH_USER PROXMOX_STORAGE PROXMOX_ISO_STORAGE \
+export PVE1_HOST PVE_TEST_HOST PROXMOX_HOST PROXMOX_SSH_USER PROXMOX_STORAGE \
-  PROXMOX_BRIDGE PROXMOX_DEFAULT_CORES PROXMOX_DEFAULT_MEMORY_MB \
+  PROXMOX_ISO_STORAGE PROXMOX_BRIDGE PROXMOX_DEFAULT_CORES \
-  PROXMOX_DEFAULT_LXC_DISK_GB PROXMOX_DEFAULT_LXC_FEATURES
+  PROXMOX_DEFAULT_MEMORY_MB PROXMOX_DEFAULT_LXC_DISK_GB \
+  PROXMOX_DEFAULT_LXC_FEATURES PROXMOX_REMOTE_REPO_DIR
 
 # Matches variables.nix's nixCacheHost -- update both if it ever changes.
 : "${NIX_CACHE_HOST:=nix-cache}"
 export NIX_CACHE_HOST
 
+# Matches variables.nix's lanDomain (the Gitea host this flake's own repo
+# is served from -- see scripts/installer/auto-install.sh's FLAKE_BASE_URL)
+# -- update both if it ever changes.
+: "${LAN_DOMAIN:=gitea.lan.ddnsgeek.com}"
+export LAN_DOMAIN
+
 # 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/installer/auto-install.sh

@@ -0,0 +1,188 @@
+#!/usr/bin/env nix-shell
+#!nix-shell -i bash -p jq disko nixos-install-tools zfs
+# shellcheck shell=bash
+# The only genuinely external tools this script calls directly: `jq`
+# (parsing the `nix eval` host list), `disko`/`nixos-install` (the
+# install itself), and `zpool` (exporting a ZFS root pool before reboot,
+# see the comment above that call below). Everything disko shells out to
+# internally (parted/sgdisk/mkfs.*/zfs/...) is self-contained -- disko's
+# own generated scripts hardcode absolute Nix store paths for those, they
+# don't rely on this script's PATH at all (confirmed by inspecting a
+# generated system.build.formatScript). The built installer image
+# (modules/installer/common.nix, plus the upstream
+# installation-cd-minimal.nix it imports via iso.nix) already has all
+# four in environment.systemPackages, so this nix-shell wrapper is a
+# fast no-op there; it's what makes the script also work standalone
+# (e.g. run directly from a checkout on a stock ISO), where they aren't
+# guaranteed.
+set -eux
+
+set -euo pipefail
+
+# shellcheck source=../env.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/env.sh"
+
+export FLAKE_BASE_URL="git+https://${LAN_DOMAIN}/beatzaplenty/nixos.git"
+
+echo "Fetching available NixOS hosts from flake..."
+# Two categories deliberately excluded from the menu:
+#   lxc-*     — these build a config.system.build.tarball meant for
+#               `pct restore` on Proxmox directly, not an install.
+#               Running nixos-install against one here would
+#               bind-mount / onto /mnt and then refuse to touch the
+#               filesystem it's currently running on — see
+#               docs/auto-installer.md.
+#   installer — this *is* the installer image's own flake target,
+#               not a deployable host; "installing" it means
+#               nixos-install-ing a copy of the installer into
+#               itself.
+mapfile -t options < <(
+  nix eval --json --no-use-registries --no-accept-flake-config --extra-experimental-features "flakes nix-command" \
+    "${FLAKE_BASE_URL}#nixosConfigurations" \
+    --apply builtins.attrNames \
+  | jq -r '.[]
+      | select(startswith("lxc-") | not)
+      | select(. != "installer")'
+)
+
+if [[ ${#options[@]} -eq 0 ]]; then
+  echo "ERROR: No NixOS hosts found in ${FLAKE_BASE_URL}#nixosConfigurations" >&2
+  exit 1
+fi
+
+echo "Note: lxc-* targets aren't installed this way — build them with"
+echo "  nix build .#nixosConfigurations.<name>.config.system.build.tarball"
+echo "and 'pct restore' the result on Proxmox directly. See docs/auto-installer.md."
+
+echo "Choose the flake profile to install:"
+select choice in "${options[@]}"; do
+  if [[ -n "$choice" ]]; then
+    echo "You selected: $choice"
+    break
+  else
+    echo "Invalid selection. Try again."
+  fi
+done
+
+echo "Starting install with flake: ${FLAKE_BASE_URL}#${choice}"
+
+# Optional: confirm before proceeding
+read -rp "Proceed with installation? (y/N): " confirm
+if [[ ! "$confirm" =~ ^[Yy]$ ]]; then
+  echo "Aborted."
+  exit 1
+fi
+
+# A nix-cache host is *the* substituter/remote-builder for every other
+# host once installed (its own config explicitly excludes itself from
+# using either — see buildType != "nix-cache" in the nixos flake.nix).
+# Installing one shouldn't depend on a nix-cache substituter either,
+# for the same reason — plus in practice "nix-cache" only resolves over
+# Tailscale, which a fresh installer environment was never connected to
+# anyway, so it's dead weight even for non-nix-cache installs until
+# that's sorted out. Override it away here specifically for nix-cache
+# targets to keep install-time behaviour consistent with run-time.
+nix_extra_opts=()
+if [[ "${choice}" == *-nix-cache ]]; then
+    echo "Installing a nix-cache host — skipping the nix-cache substituter."
+    nix_extra_opts+=(--option substituters "https://cache.nixos.org/")
+fi
+
+# Every host reachable through this menu has a Disko config (lxc-*
+# is filtered out above, and is the only category that doesn't —
+# see docs/auto-installer.md), so this can run unconditionally: no
+# need to probe the flake first and branch on whether Disko applies.
+disko --mode destroy,format,mount \
+    --flake "${FLAKE_BASE_URL}#${choice}" "${nix_extra_opts[@]}" --yes-wipe-all-disks
+
+# sops-nix derives this host's decryption key from its own SSH host key
+# at *activation* time, which runs before systemd would otherwise
+# generate one on first boot. Without pre-seeding it here, secrets
+# (including the login password) fail to decrypt on first boot.
+# Generate the key with scripts/secrets/prepare-host-key.sh first.
+#
+# Two places a key can come from, checked in order:
+#   /etc/host-keys  — baked into this image at build time (see
+#                      modules/installer/host-keys.nix; only present
+#                      if built with NIXOS_HOST_KEYS_DIR set)
+#   /root/host-keys — scp'd in manually after boot (older fallback,
+#                      still supported for images built without keys)
+mkdir -p /root/host-keys
+if [[ -f "/etc/host-keys/${choice}_ssh_host_ed25519_key" ]]; then
+    echo "Found baked-in SSH host key for ${choice}, installing to target..."
+    install -D -m 0600 "/etc/host-keys/${choice}_ssh_host_ed25519_key" /mnt/etc/ssh/ssh_host_ed25519_key
+    install -D -m 0644 "/etc/host-keys/${choice}_ssh_host_ed25519_key.pub" /mnt/etc/ssh/ssh_host_ed25519_key.pub
+elif [[ -f "/root/host-keys/${choice}_ssh_host_ed25519_key" ]]; then
+    echo "Found pre-seeded SSH host key for ${choice}, installing to target..."
+    install -D -m 0600 "/root/host-keys/${choice}_ssh_host_ed25519_key" /mnt/etc/ssh/ssh_host_ed25519_key
+    install -D -m 0644 "/root/host-keys/${choice}_ssh_host_ed25519_key.pub" /mnt/etc/ssh/ssh_host_ed25519_key.pub
+else
+    # Third place a key can come from: an arbitrary path the operator
+    # points at interactively (e.g. a USB stick, a mount from another
+    # machine) -- only offered when there's an actual human at the other
+    # end of stdin to ask, never in a non-interactive run.
+    key_copied=0
+    if [[ -t 0 ]]; then
+        echo "No SSH host key found for ${choice} (checked /etc/host-keys and /root/host-keys)."
+        read -rp "Path to a directory containing ${choice}_ssh_host_ed25519_key(.pub) (blank to skip): " key_src_dir
+        if [[ -n "$key_src_dir" && -f "${key_src_dir}/${choice}_ssh_host_ed25519_key" && -f "${key_src_dir}/${choice}_ssh_host_ed25519_key.pub" ]]; then
+            cp "${key_src_dir}/${choice}_ssh_host_ed25519_key" "${key_src_dir}/${choice}_ssh_host_ed25519_key.pub" /root/host-keys/
+            key_copied=1
+        elif [[ -n "$key_src_dir" ]]; then
+            echo "WARNING: ${choice}_ssh_host_ed25519_key(.pub) not found in ${key_src_dir}."
+        fi
+    fi
+
+    if [[ "$key_copied" -eq 1 ]]; then
+        echo "Copied SSH host key for ${choice} from ${key_src_dir}, installing to target..."
+        install -D -m 0600 "/root/host-keys/${choice}_ssh_host_ed25519_key" /mnt/etc/ssh/ssh_host_ed25519_key
+        install -D -m 0644 "/root/host-keys/${choice}_ssh_host_ed25519_key.pub" /mnt/etc/ssh/ssh_host_ed25519_key.pub
+    else
+        echo "WARNING: no SSH host key found for ${choice} (checked /etc/host-keys and /root/host-keys)"
+        echo "sops-nix secrets (including the login password) will NOT decrypt on first boot."
+        echo "Run scripts/secrets/prepare-host-key.sh for host ${choice} on your admin workstation first,"
+        echo "then either rebuild this image with NIXOS_HOST_KEYS_DIR set, scp the result to"
+        echo "/root/host-keys/ on this machine, or point at it when prompted above."
+        read -rp "Continue without a pre-seeded key anyway? (y/N): " skip_key
+        if [[ ! "$skip_key" =~ ^[Yy]$ ]]; then
+            echo "Aborted."
+            exit 1
+        fi
+    fi
+fi
+
+mkdir -p /mnt/install-tmp
+export TMPDIR=/mnt/install-tmp
+
+nixos-install \
+    --flake "${FLAKE_BASE_URL}#${choice}" \
+    "${nix_extra_opts[@]}" \
+    --no-root-password
+
+
+    rm -rf /mnt/install-tmp
+    # Redundant copy of the host's private key — the real one is now at
+    # /etc/ssh/ssh_host_ed25519_key. Nothing NixOS-managed ever cleans this
+    # up on its own since it was written imperatively, not declaratively.
+    rm -rf /root/host-keys
+
+    # disko's --mode ...,mount left any ZFS root pool imported (that's what
+    # let nixos-install write into /mnt). If we reboot with it still
+    # imported, it isn't just "not exported" -- it's stamped with *this*
+    # live installer environment's hostid, which almost never matches the
+    # target's own networking.hostId (see hosts/*/host.nix; the installer
+    # itself sets none). modules/services/zfs/enable-service.nix and
+    # modules/common/configuration.nix both set boot.zfs.forceImportRoot =
+    # false deliberately (the safe option per that setting's own docs), so
+    # the freshly-installed system's first real boot sees a pool "in use by
+    # another system" and refuses to import it without -f -- which is what
+    # makes boot stall waiting on the ZFS import. Exporting here (a no-op
+    # if the chosen host has no ZFS root, e.g. proxmox-*/linode-*) clears
+    # that in-use state so the next import, from any hostid, succeeds.
+    if [[ -n "$(zpool list -H -o name 2>/dev/null)" ]]; then
+        echo "Exporting ZFS pool(s) before reboot..."
+        zpool export -a
+    fi
+
+    sleep 10
+    reboot

scripts/lib/confirm.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+# Shared "type X to confirm" prompt for scripts/proxmox/create-proxmox-resource.sh
+# (--modify, and replacing an existing --allow-duplicate-host resource) and
+# scripts/secrets/sync-host-keys.sh (--regenerate-all-keys) -- three destructive
+# confirmations that all work the same way (echo the expected value back
+# exactly), kept in one place so the prompt/comparison logic can't drift.
+# Source alongside env.sh:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/confirm.sh"
+#
+# Deliberately does NOT print anything on mismatch or decide exit-vs-return
+# -- callers vary on both (a top-level script exits, a subcommand function
+# returns; wording differs too), so that stays at the call site.
+
+# confirm_typed <expected> <prompt>
+# Prints <prompt> via `read -rp`, then reports (via exit status) whether the
+# typed input matched <expected> exactly.
+confirm_typed() {
+  local expected="$1" prompt="$2" input
+  read -rp "$prompt" input
+  [[ "$input" == "$expected" ]]
+}

scripts/lib/nix-bootstrap.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# Shared Nix bootstrap for scripts/codex-setup.sh and
+# scripts/codex-maintenance.sh: the nix.conf settings both need in effect
+# before a single `nix` command runs (flakes enabled, never honor a flake
+# input's own nixConfig, no "dirty tree" warning spam), plus a helper to
+# pull an already-installed Nix's daemon/profile script onto PATH if it
+# isn't there yet. Source this instead of copying it -- see CLAUDE.md.
+export NIX_CONFIG="${NIX_CONFIG:-}
+experimental-features = nix-command flakes
+accept-flake-config = false
+warn-dirty = false
+"
+
+ensure_nix_profile() {
+  if [ -f /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh ]; then
+    . /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
+  elif [ -f "$HOME/.nix-profile/etc/profile.d/nix.sh" ]; then
+    . "$HOME/.nix-profile/etc/profile.d/nix.sh"
+  fi
+}

scripts/lib/nix-eval.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+# Shared flake-introspection helpers for scripts/*.sh. Source alongside
+# env.sh:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/nix-eval.sh"
+#
+# NIX_EVAL_FLAGS: --no-use-registries so a call here never resolves through
+# the user's global flake registry (every call targets this repo's own
+# flake, or an explicit github: ref, not a registry alias); --no-accept-flake-config
+# so a flake input's own nixConfig (e.g. a dependency's substituters) is
+# never honored -- matches accept-flake-config = false already set repo-wide
+# (see lib/nix-bootstrap.sh / CLAUDE.md). Reuse this array rather than
+# retyping the two flags at each call site.
+declare -a NIX_EVAL_FLAGS=(--no-use-registries --no-accept-flake-config)
+
+# list_flake_targets <flake_ref>
+# Prints the attribute names under <flake_ref>#nixosConfigurations, one per
+# line, e.g.:
+#   list_flake_targets .            # from inside the repo
+#   list_flake_targets "$repo_root" # from anywhere
+list_flake_targets() {
+  local flake_ref="$1"
+  nix eval --json "${NIX_EVAL_FLAGS[@]}" \
+    "${flake_ref}#nixosConfigurations" --apply builtins.attrNames \
+  | jq -r '.[]'
+}
+
+# flake_target_hostname <flake_ref> <target>
+# Prints one nixosConfigurations target's config.networking.hostName.
+# Empty (not an error under set -e) if the target doesn't exist or the
+# eval otherwise fails -- callers that need to distinguish "empty" from
+# "eval failed" should check $? themselves instead of relying on this.
+flake_target_hostname() {
+  local flake_ref="$1" target="$2"
+  nix eval --raw "${NIX_EVAL_FLAGS[@]}" \
+    "${flake_ref}#nixosConfigurations.${target}.config.networking.hostName" 2>/dev/null
+}
+
+# flake_target_lxc_privileged <flake_ref> <target>
+# Prints "true" or "false" for one lxc-* target's config.proxmoxLXC.privileged
+# (modules/platforms/lxc.nix is the single source of truth -- e.g.
+# lxc-docker sets this true so it can NFS-mount; every other lxc-* host
+# stays unprivileged). Only meaningful for lxc-* targets -- the option
+# doesn't exist for linode-*/proxmox-* (nixpkgs' proxmox-lxc.nix, which
+# declares it, is only ever imported by modules/platforms/lxc.nix). Empty
+# (not an error under set -e) if the eval fails.
+flake_target_lxc_privileged() {
+  local flake_ref="$1" target="$2"
+  # Not --raw: the option is a Nix boolean, and --raw can only coerce
+  # strings ("cannot coerce a Boolean to a string"). Plain `nix eval`
+  # prints a bare `true`/`false` for a boolean, which is exactly the
+  # string this needs.
+  nix eval "${NIX_EVAL_FLAGS[@]}" \
+    "${flake_ref}#nixosConfigurations.${target}.config.proxmoxLXC.privileged" 2>/dev/null
+}

scripts/lib/nix-parallel.sh

@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# Shared parallel-nix-invocation helper for scripts/codex-maintenance.sh.
+# Source alongside nix-eval.sh:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/nix-parallel.sh"
+#
+# The per-host/per-package `nix eval`/`nix build --dry-run` calls in
+# codex-maintenance.sh are independent of each other, so running them one at
+# a time leaves most cores idle for most of the sweep -- run_nix_parallel
+# fans a batch of them out across up to NIX_PARALLEL_JOBS processes instead.
+
+# NIX_PARALLEL_JOBS: how many `nix` invocations run_nix_parallel runs at
+# once. Defaults to core count capped by available memory (~1GB/job,
+# floor 1) rather than plain `nproc` -- each concurrent `nix eval` here
+# evaluates a whole NixOS system closure from scratch, and on a small/
+# memory-constrained CI runner, `nproc` concurrent evals can OOM-kill each
+# other (confirmed empirically: on a 4GB/6-core box, 5-6 concurrent evals
+# started getting killed while 3-4 ran clean and were still ~2x faster than
+# serial). Override via env if a given machine/CI runner has room to spare
+# or needs a tighter cap.
+default_nix_parallel_jobs() {
+  local cores mem_avail_kb mem_cap
+  cores="$(nproc 2>/dev/null || echo 4)"
+  mem_avail_kb="$(awk '/^MemAvailable:/ {print $2}' /proc/meminfo 2>/dev/null)"
+  if [[ -z "$mem_avail_kb" ]]; then
+    echo "$cores"
+    return
+  fi
+  mem_cap=$((mem_avail_kb / 1024 / 1024))
+  ((mem_cap < 1)) && mem_cap=1
+  ((mem_cap < cores)) && echo "$mem_cap" || echo "$cores"
+}
+NIX_PARALLEL_JOBS="${NIX_PARALLEL_JOBS:-$(default_nix_parallel_jobs)}"
+
+# Separator between a job's label and its flake attr in the arrays
+# run_nix_parallel takes -- a control character so it can't collide with
+# anything a label or attr path would plausibly contain.
+NIX_PARALLEL_SEP=$'\x1f'
+
+# run_nix_parallel <jobs_array_name> <nix subcommand + flags...>
+#
+# jobs_array_name: name of an already-populated bash array whose entries are
+# "<label>${NIX_PARALLEL_SEP}<attr>" pairs, e.g.
+#   jobs=("proxmox-docker${NIX_PARALLEL_SEP}.#nixosConfigurations.proxmox-docker...drvPath")
+# Remaining args are passed to `nix` before the attr, e.g.:
+#   run_nix_parallel jobs eval --raw "${NIX_EVAL_FLAGS[@]}"
+#   run_nix_parallel jobs build --dry-run --no-link "${NIX_EVAL_FLAGS[@]}"
+#
+# Prints "==> <label>" followed by that job's stdout+stderr for every job,
+# in submission order (not completion order) so a run stays readable and
+# diffable across invocations even though the work itself doesn't finish in
+# that order. Returns non-zero if any job failed, only after every job has
+# finished and been printed -- same "surface everything, then fail" contract
+# a `set -e` caller gets, just parallelized instead of stopping at the first
+# failure.
+run_nix_parallel() {
+  local -n jobs_ref="$1"
+  shift
+  local -a nix_args=("$@")
+
+  local n=${#jobs_ref[@]}
+  [[ $n -eq 0 ]] && return 0
+
+  local tmp_dir
+  tmp_dir="$(mktemp -d)"
+
+  local i=0 running=0
+  for job in "${jobs_ref[@]}"; do
+    local attr="${job#*"${NIX_PARALLEL_SEP}"}"
+    printf '%s\n' "${job%%"${NIX_PARALLEL_SEP}"*}" >"${tmp_dir}/${i}.label"
+    (
+      if nix "${nix_args[@]}" "$attr" >"${tmp_dir}/${i}.out" 2>&1; then
+        echo 0 >"${tmp_dir}/${i}.status"
+      else
+        echo 1 >"${tmp_dir}/${i}.status"
+      fi
+    ) &
+    i=$((i + 1))
+    running=$((running + 1))
+    if ((running >= NIX_PARALLEL_JOBS)); then
+      wait -n
+      running=$((running - 1))
+    fi
+  done
+  wait
+
+  local failed=0 j
+  for ((j = 0; j < n; j++)); do
+    echo "==> $(cat "${tmp_dir}/${j}.label")"
+    cat "${tmp_dir}/${j}.out"
+    [[ "$(cat "${tmp_dir}/${j}.status")" -ne 0 ]] && failed=1
+  done
+
+  rm -rf "$tmp_dir"
+  return $failed
+}

scripts/lib/sops-age.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+# Shared sops/age helpers for scripts/secrets/backup-admin-key.sh,
+# scripts/secrets/rotate-admin-key.sh, and scripts/secrets/sync-host-keys.sh -- all three
+# derive an age public key from a private identity file the same way, two
+# of them resolve the same sops/age default key-file path, and two of them
+# run `sops updatekeys` the same way. Kept in one place so they can't drift
+# apart. Source alongside env.sh:
+#   source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/lib/sops-age.sh"
+#
+# Uses NIX_OPTS (an array of extra `nix-shell` options -- see env.sh's
+# nix_extra_opts) if the caller has already set it, same convention as
+# lib/ssh-host-keys.sh. Falls back to no extra options if the caller never
+# sourced env.sh.
+if ! declare -p NIX_OPTS >/dev/null 2>&1; then
+  declare -a NIX_OPTS=()
+fi
+
+# sops/age's own default identity-file resolution order, minus $SOPS_AGE_KEY
+# itself (an inline identity, not a path -- callers that accept it check it
+# separately, before falling back to this).
+: "${DEFAULT_SOPS_AGE_KEY_FILE:=${SOPS_AGE_KEY_FILE:-${XDG_CONFIG_HOME:-$HOME/.config}/sops/age/keys.txt}}"
+
+# age_pubkey_from_identity_file <identity-file>
+# Prints the age public key for a private identity file (age-keygen -y).
+age_pubkey_from_identity_file() {
+  local identity_file="$1"
+  nix-shell "${NIX_OPTS[@]}" -p age --run "age-keygen -y '${identity_file}'"
+}
+
+# sops_yaml_admin_pubkey <sops-yaml-path>
+# Prints .sops.yaml's current &admin age public key, or empty (not an error
+# under set -e) if no such anchor line exists -- callers that need to treat
+# "missing" as fatal check for an empty result themselves.
+sops_yaml_admin_pubkey() {
+  local sops_yaml="$1"
+  grep -E '^  - &admin age1' "$sops_yaml" 2>/dev/null | awk '{print $NF}' || true
+}
+
+# sops_updatekeys <secrets-file> [key-file]
+# Re-encrypts <secrets-file> for .sops.yaml's current recipient set. If
+# <key-file> is given, decrypts with that identity (SOPS_AGE_KEY_FILE)
+# instead of whatever's ambient -- needed when the ambient default key
+# doesn't match yet (e.g. mid-rotation, decrypting with the outgoing key).
+sops_updatekeys() {
+  local secrets_file="$1" key_file="${2:-}"
+  if [[ -n "$key_file" ]]; then
+    SOPS_AGE_KEY_FILE="$key_file" nix-shell "${NIX_OPTS[@]}" -p sops --run \
+      "sops updatekeys --yes '${secrets_file}'"
+  else
+    nix-shell "${NIX_OPTS[@]}" -p sops --run "sops updatekeys --yes '${secrets_file}'"
+  fi
+}

scripts/lib/ssh-host-keys.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# Shared SSH-host-key / age-conversion helpers for scripts/secrets/sync-host-keys.sh
+# and scripts/secrets/prepare-host-key.sh -- both generate the same kind of key
+# (ed25519, no passphrase, the sops-nix age-derivation input) and convert it
+# to an age recipient the same way; kept in one place so the two can't
+# drift apart.
+#
+# Uses NIX_OPTS (an array of extra `nix-shell` options -- see env.sh's
+# nix_extra_opts) if the caller has already set it, so a decision to avoid
+# an unreachable nix-cache is reused here instead of probed again. Falls
+# back to no extra options if the caller never sourced env.sh.
+if ! declare -p NIX_OPTS >/dev/null 2>&1; then
+  declare -a NIX_OPTS=()
+fi
+
+# generate_host_ed25519_key <hostname> <keyfile>
+# Writes <keyfile> and <keyfile>.pub. Caller is responsible for refusing to
+# overwrite an existing keyfile -- this always runs ssh-keygen fresh.
+generate_host_ed25519_key() {
+  local hostname="$1" keyfile="$2"
+  nix-shell "${NIX_OPTS[@]}" -p openssh --run \
+    "ssh-keygen -t ed25519 -N '' -C '${hostname}' -f '${keyfile}'" >/dev/null
+}
+
+# ssh_pubkey_to_age <pubkeyfile>
+# Prints the age public key derived from an ed25519 SSH public key file.
+ssh_pubkey_to_age() {
+  local pubkeyfile="$1"
+  nix-shell "${NIX_OPTS[@]}" -p ssh-to-age --run "ssh-to-age -i '${pubkeyfile}'"
+}

scripts/proxmox/clone-pve1-to-pve-test.sh

@@ -0,0 +1,221 @@
+#!/usr/bin/env bash
+# Ad hoc clone of a single VM/CT from pve1 (production) to pve-test
+# (sandbox), via vzdump + qmrestore/pct restore -- not a general-purpose
+# backup tool, just a quick "give me a disposable copy of this thing on
+# pve-test" for testing against real-ish data without touching prod.
+#
+# Flow:
+#   1. vzdump the resource on pve1 into its "local" storage (--mode
+#      snapshot by default, so the source keeps running throughout --
+#      see --mode below for when that's not possible).
+#   2. Stream the resulting archive straight from pve1 to pve-test
+#      (ssh pve1 cat ... | ssh pve-test cat > ...) -- this machine is
+#      just the relay, no separate on-disk staging copy here.
+#   3. qmrestore / pct restore it on pve-test under --new-vmid (default:
+#      same VMID as the source -- pve-test is a separate node/cluster, so
+#      no collision unless that VMID is already in use there too).
+#      Always restored with --unique 1 (fresh MAC addresses) since the
+#      source is typically still running on the same LAN -- restoring
+#      with the *same* MAC would put two live guests on the wire with
+#      identical hardware addresses.
+#   4. Delete the vzdump archive from pve1's local storage and the
+#      relayed copy on pve-test, so neither node accumulates ad hoc
+#      backup files from this script. Only the pve1 original is
+#      preserved on any failure after step 1, so a failed
+#      transfer/restore can be retried without re-running the backup.
+#
+# This script's own defaults are pve1 -> pve-test, unlike
+# create-proxmox-resource.sh's --node (which defaults to production) --
+# see CLAUDE.md's "Two Proxmox nodes" section. pve1 is only ever touched
+# here after typing the source VMID back to confirm; pve-test is treated
+# as disposable, matching this repo's usual policy for that node.
+#
+# See --help for the full option list.
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/confirm.sh
+source "${repo_root}/scripts/lib/confirm.sh"
+
+usage() {
+  cat <<EOF
+Usage: $0 --vmid <n> [options]
+
+  --vmid <n>              Required: VMID on the source node to clone.
+                           Kind (qemu VM vs LXC CT) is auto-detected.
+  --new-vmid <n>           VMID to restore as on the target node
+                           (default: same as --vmid).
+  --mode snapshot|suspend|stop
+                           vzdump backup mode (default: snapshot -- the
+                           source resource keeps running throughout;
+                           requires snapshot-capable storage, e.g.
+                           ZFS/LVM-thin/Ceph/qcow2). Fall back to
+                           "suspend" (brief pause) or "stop" (source
+                           goes down for the duration) if the source's
+                           storage doesn't support live snapshots --
+                           vzdump's own error will say so.
+  --source-node <host>      (default: \$PVE1_HOST, ${PVE1_HOST})
+  --target-node <host>       (default: \$PVE_TEST_HOST, ${PVE_TEST_HOST})
+  --source-storage <pool>      Where vzdump writes the backup on the
+                               source node (default: local).
+  --target-storage <pool>       Where the restored disk/rootfs lands on
+                               the target node (default: \$PROXMOX_STORAGE, ${PROXMOX_STORAGE}).
+  --keep-backup                  Don't delete the vzdump archive from
+                                 either node afterward (debugging aid).
+  --yes                            Skip the typed VMID confirmation
+                                   before touching the source node.
+  --dry-run                          Print the full plan and skip every
+                                     mutating step (vzdump, transfer,
+                                     restore, delete) and the confirm
+                                     prompt. Still makes read-only SSH
+                                     calls to look up the source kind
+                                     and check the target VMID is free
+                                     -- harmless on either node.
+  -h, --help
+EOF
+}
+
+vmid=""
+new_vmid=""
+mode="snapshot"
+source_node="$PVE1_HOST"
+target_node="$PVE_TEST_HOST"
+source_storage="local"
+target_storage="$PROXMOX_STORAGE"
+keep_backup=0
+skip_confirm=0
+dry_run=0
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+  --vmid) vmid="$2"; shift 2 ;;
+  --new-vmid) new_vmid="$2"; shift 2 ;;
+  --mode) mode="$2"; shift 2 ;;
+  --source-node) source_node="$2"; shift 2 ;;
+  --target-node) target_node="$2"; shift 2 ;;
+  --source-storage) source_storage="$2"; shift 2 ;;
+  --target-storage) target_storage="$2"; shift 2 ;;
+  --keep-backup) keep_backup=1; shift ;;
+  --yes) skip_confirm=1; shift ;;
+  --dry-run) dry_run=1; shift ;;
+  -h | --help) usage; exit 0 ;;
+  *) echo "Unknown option: $1" >&2; usage >&2; exit 1 ;;
+  esac
+done
+
+if [[ -z "$vmid" ]]; then
+  echo "ERROR: --vmid is required." >&2
+  usage >&2
+  exit 1
+fi
+if [[ "$mode" != "snapshot" && "$mode" != "suspend" && "$mode" != "stop" ]]; then
+  echo "ERROR: --mode must be snapshot, suspend, or stop." >&2
+  exit 1
+fi
+[[ -z "$new_vmid" ]] && new_vmid="$vmid"
+
+source_target="${PROXMOX_SSH_USER}@${source_node}"
+target_target="${PROXMOX_SSH_USER}@${target_node}"
+
+# No dry-run wrapper needed for the calls below: every mutating step
+# (vzdump, transfer, restore, delete) is reached only after the --dry-run
+# early-exit further down, so a plain `ssh` call is never in the dry-run
+# path.
+
+# --- identify the resource kind on the source node -----------------------
+echo "==> Looking up VMID ${vmid} on ${source_node}..."
+kind=""
+if ssh "$source_target" "qm status ${vmid}" >/dev/null 2>&1; then
+  kind="vm"
+elif ssh "$source_target" "pct status ${vmid}" >/dev/null 2>&1; then
+  kind="lxc"
+else
+  echo "ERROR: VMID ${vmid} doesn't exist on ${source_node} as either a VM or CT." >&2
+  exit 1
+fi
+echo "VMID ${vmid} on ${source_node} is a ${kind}."
+
+# --- refuse to clobber an existing resource on the target node -----------
+if ssh "$target_target" "qm status ${new_vmid}" >/dev/null 2>&1 \
+  || ssh "$target_target" "pct status ${new_vmid}" >/dev/null 2>&1; then
+  echo "ERROR: VMID ${new_vmid} already exists on ${target_node}. Pass --new-vmid" >&2
+  echo "with a free ID, or remove the existing resource there first." >&2
+  exit 1
+fi
+
+echo
+echo "Plan:"
+echo "  source: ${kind} VMID ${vmid} on ${source_node} (storage: ${source_storage}, mode: ${mode})"
+echo "  target: VMID ${new_vmid} on ${target_node} (storage: ${target_storage}, fresh MAC via --unique)"
+[[ "$keep_backup" -eq 1 ]] && echo "  backup archives are kept on both nodes afterward (--keep-backup)"
+
+if [[ "$dry_run" -eq 1 ]]; then
+  echo
+  echo "[dry-run] No backup, transfer, restore, or delete was performed."
+  exit 0
+fi
+
+if [[ "$skip_confirm" -ne 1 ]]; then
+  echo
+  if ! confirm_typed "$vmid" "Type the source VMID (${vmid}) to confirm backing it up from ${source_node}: "; then
+    echo "Cancelled -- input didn't match ${vmid}." >&2
+    exit 1
+  fi
+fi
+
+# --- vzdump on the source node --------------------------------------------
+echo
+echo "==> Backing up VMID ${vmid} on ${source_node} (mode=${mode}, storage=${source_storage})..."
+vzdump_log="$(ssh "$source_target" \
+  "vzdump ${vmid} --mode ${mode} --storage ${source_storage} --compress zstd" 2>&1)" \
+  || {
+    echo "$vzdump_log" >&2
+    echo "ERROR: vzdump failed on ${source_node}." >&2
+    exit 1
+  }
+echo "$vzdump_log"
+
+archive="$(echo "$vzdump_log" | grep -oP "creating vzdump archive '\K[^']+" | tail -n1)"
+if [[ -z "$archive" ]]; then
+  echo "ERROR: couldn't find the archive path in vzdump's output above." >&2
+  exit 1
+fi
+archive_basename="$(basename "$archive")"
+target_tmp_archive="/var/tmp/${archive_basename}"
+echo "Archive: ${archive}"
+
+# Always clean up the relayed copy on the target node, success or failure
+# -- it's only ever a working copy, restored or not.
+cleanup_target_tmp() {
+  if [[ "$keep_backup" -ne 1 ]]; then
+    ssh "$target_target" "rm -f '${target_tmp_archive}'" >/dev/null 2>&1 || true
+  fi
+}
+trap cleanup_target_tmp EXIT
+
+# --- relay the archive from source to target ------------------------------
+echo
+echo "==> Transferring archive to ${target_node}..."
+ssh "$source_target" "cat '${archive}'" | ssh "$target_target" "cat > '${target_tmp_archive}'"
+
+# --- restore on the target node --------------------------------------------
+echo
+echo "==> Restoring as VMID ${new_vmid} on ${target_node} (storage=${target_storage})..."
+if [[ "$kind" == "vm" ]]; then
+  ssh "$target_target" "qmrestore '${target_tmp_archive}' ${new_vmid} --storage ${target_storage} --unique 1"
+else
+  ssh "$target_target" "pct restore ${new_vmid} '${target_tmp_archive}' --storage ${target_storage} --unique 1"
+fi
+
+# --- clean up the source backup now that the restore succeeded -----------
+if [[ "$keep_backup" -ne 1 ]]; then
+  echo
+  echo "==> Deleting backup archive from ${source_node}'s ${source_storage} storage..."
+  ssh "$source_target" "rm -f '${archive}' '${archive}.notes' '${archive}.log'" >/dev/null 2>&1 || true
+fi
+
+echo
+echo "Done. VMID ${new_vmid} (${kind}) is now on ${target_node}, cloned from" \
+  "VMID ${vmid} on ${source_node}."

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

@@ -0,0 +1,182 @@
+#!/usr/bin/env bash
+# Points a non-NixOS Debian machine's Nix install at nix-cache: adds it as
+# a substituter (with cache.nixos.org kept as fallback) and, once the
+# remote-builder private key is installed, as a distributed-build machine
+# too.
+#
+# This is the non-NixOS equivalent of modules/nix-cache/client.nix +
+# modules/nix-cache/remote-builder-client.nix -- those two only apply to
+# hosts built from this flake. A plain Debian box with Nix installed
+# (single- or multi-user install, nix-daemon running) has no NixOS module
+# system to pick that config up, so this edits /etc/nix/nix.conf by hand
+# instead. Run this ON the target Debian machine, as root.
+#
+# The values below mirror variables.nix / modules/nix-cache/client.nix in
+# this repo -- update both if nix-cache is ever rebuilt with a new host
+# key or the cache signing key is rotated (see docs/nix-cache.md).
+#
+# REMOTE_BUILDER_KEY defaults to this machine's own default root SSH
+# identity (matches modules/nix-cache/remote-builder-client.nix's
+# convention for real NixOS clients: authenticate as nixremote with the
+# host's own default key, added individually to
+# vars.remoteBuilderAuthorizedKeys, rather than a separately-named or
+# shared keypair) -- generate one with
+# `ssh-keygen -t ed25519 -N '' -f /root/.ssh/id_ed25519` if this machine
+# doesn't have one yet, then add its .pub to vars.remoteBuilderAuthorizedKeys
+# and rebuild nix-cache.
+#
+# Usage:
+#   sudo ./configure-nix-cache-client.sh [--dry-run] [--no-remote-builder] [--no-restart]
+#
+# Env overrides (defaults match variables.nix):
+#   NIX_CACHE_HOST, NIX_CACHE_HOST_KEY, REMOTE_BUILDER_USER, REMOTE_BUILDER_KEY
+
+set -euo pipefail
+
+: "${NIX_CACHE_HOST:=nix-cache}"
+: "${NIX_CACHE_HOST_KEY:=ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPeWgMsdaiz4axT/deFc1+0B5bN+GX/NOeW9bbQ0c/IT lxc-nix-cache}"
+: "${REMOTE_BUILDER_USER:=nixremote}"
+: "${REMOTE_BUILDER_KEY:=/root/.ssh/id_ed25519}"
+
+CACHE_PUB_KEY="cache.local-1:usoWYanY3Kpq2+kDIS2nhWoLZiRxanmdysdzqCFBHW4="
+FALLBACK_URL="https://cache.nixos.org/"
+FALLBACK_PUB_KEY="cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
+
+NIX_CONF="/etc/nix/nix.conf"
+KNOWN_HOSTS="/etc/ssh/ssh_known_hosts"
+MARKER_BEGIN="# BEGIN nix-cache client config (configure-nix-cache-client.sh)"
+MARKER_END="# END nix-cache client config"
+
+dry_run=0
+with_remote_builder=1
+restart_daemon=1
+
+for arg in "$@"; do
+  case "$arg" in
+    --dry-run) dry_run=1 ;;
+    --no-remote-builder) with_remote_builder=0 ;;
+    --no-restart) restart_daemon=0 ;;
+    -h|--help)
+      sed -n '2,20p' "$0"
+      exit 0
+      ;;
+    *)
+      echo "ERROR: unknown argument: $arg" >&2
+      exit 1
+      ;;
+  esac
+done
+
+if [[ "$dry_run" -eq 0 && "$EUID" -ne 0 ]]; then
+  echo "ERROR: must run as root (writes $NIX_CONF and, unless --no-remote-builder, $KNOWN_HOSTS)." >&2
+  exit 1
+fi
+
+if ! command -v nix >/dev/null 2>&1; then
+  echo "ERROR: no 'nix' binary on PATH -- install the Nix package manager first." >&2
+  exit 1
+fi
+
+if [[ ! -f "$NIX_CONF" ]]; then
+  echo "ERROR: $NIX_CONF not found -- expected an existing multi-user Nix install." >&2
+  exit 1
+fi
+
+builder_line=""
+if [[ "$with_remote_builder" -eq 1 ]]; then
+  if [[ -f "$REMOTE_BUILDER_KEY" ]]; then
+    case "$(uname -m)" in
+      x86_64) nix_system="x86_64-linux" ;;
+      aarch64) nix_system="aarch64-linux" ;;
+      *)
+        echo "WARNING: unrecognized architecture '$(uname -m)' -- skipping remote builder, keeping substituter config." >&2
+        with_remote_builder=0
+        ;;
+    esac
+    if [[ "$with_remote_builder" -eq 1 ]]; then
+      builder_line="builders = ssh://${REMOTE_BUILDER_USER}@${NIX_CACHE_HOST} ${nix_system} ${REMOTE_BUILDER_KEY} 4 2 big-parallel,kvm,nixos-test,benchmark"
+    fi
+  else
+    echo "WARNING: $REMOTE_BUILDER_KEY not found -- skipping remote builder config (substituter still configured)." >&2
+    echo "  See docs/nix-cache.md 'Remote builder SSH keys' for how to install it, then re-run this script." >&2
+    with_remote_builder=0
+  fi
+fi
+
+block="$(cat <<EOF
+$MARKER_BEGIN
+extra-substituters = http://${NIX_CACHE_HOST} ${FALLBACK_URL}
+extra-trusted-public-keys = ${CACHE_PUB_KEY} ${FALLBACK_PUB_KEY}
+EOF
+)"
+if [[ "$with_remote_builder" -eq 1 ]]; then
+  block="${block}
+builders-use-substitutes = true
+${builder_line}"
+fi
+block="${block}
+$MARKER_END"
+
+echo "== nix.conf block to install =="
+echo "$block"
+echo "================================"
+
+if [[ "$dry_run" -eq 1 ]]; then
+  echo "(--dry-run: not writing $NIX_CONF)"
+else
+  tmp_conf="$(mktemp)"
+  trap 'rm -f "$tmp_conf"' EXIT
+
+  if grep -qF "$MARKER_BEGIN" "$NIX_CONF"; then
+    awk -v begin="$MARKER_BEGIN" -v end="$MARKER_END" -v block="$block" '
+      $0 == begin { print block; skip = 1; next }
+      $0 == end   { skip = 0; next }
+      skip        { next }
+      { print }
+    ' "$NIX_CONF" > "$tmp_conf"
+  else
+    cp "$NIX_CONF" "$tmp_conf"
+    printf '\n%s\n' "$block" >> "$tmp_conf"
+  fi
+
+  cp "$NIX_CONF" "${NIX_CONF}.bak.$(date +%Y%m%d%H%M%S)"
+  install -m 0644 "$tmp_conf" "$NIX_CONF"
+  echo "Updated $NIX_CONF (backup saved alongside it)."
+fi
+
+if [[ "$with_remote_builder" -eq 1 ]]; then
+  known_hosts_line="${NIX_CACHE_HOST} ${NIX_CACHE_HOST_KEY}"
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "(--dry-run: would ensure this line is present in $KNOWN_HOSTS)"
+    echo "  $known_hosts_line"
+  else
+    mkdir -p "$(dirname "$KNOWN_HOSTS")"
+    touch "$KNOWN_HOSTS"
+    if ! grep -qF "$known_hosts_line" "$KNOWN_HOSTS" 2>/dev/null; then
+      echo "$known_hosts_line" >> "$KNOWN_HOSTS"
+      echo "Added nix-cache's SSH host key to $KNOWN_HOSTS."
+    fi
+  fi
+fi
+
+if [[ "$dry_run" -eq 0 && "$restart_daemon" -eq 1 ]]; then
+  if command -v systemctl >/dev/null 2>&1 && systemctl is-active --quiet nix-daemon 2>/dev/null; then
+    systemctl restart nix-daemon
+    echo "Restarted nix-daemon to pick up the new config."
+  else
+    echo "nix-daemon not managed by systemd (or not running) -- restart it manually to pick up the new config."
+  fi
+fi
+
+cat <<EOF
+
+Done. Verify with:
+  curl http://${NIX_CACHE_HOST}/nix-cache-info
+  nix show-config | grep -E 'substituters|trusted-public-keys|builders'
+EOF
+if [[ "$with_remote_builder" -eq 1 ]]; then
+  cat <<EOF
+  ssh -i ${REMOTE_BUILDER_KEY} ${REMOTE_BUILDER_USER}@${NIX_CACHE_HOST} nix-store --version
+  nix build nixpkgs#hello -L
+EOF
+fi

scripts/proxmox/create-proxmox-resource.sh

@@ -0,0 +1,858 @@
+#!/usr/bin/env bash
+# Creates new Proxmox VMs/LXC containers from this flake, and reconfigures
+# existing ones -- the manual workflows in docs/proxmox-images.md (VM) and
+# docs/auto-installer.md's "LXC hosts" section (container), automated.
+#
+# Images are built directly on the Proxmox node (PROXMOX_REMOTE_REPO_DIR /
+# --remote-repo-dir in scripts/env.sh), not on whatever machine runs this
+# 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.
+#
+# --node (default: $PROXMOX_HOST, see scripts/env.sh) picks which of the two
+# LAN Proxmox nodes this runs against: production, pve1.sweet.home
+# ($PVE1_HOST, PROXMOX_HOST's own default), or the sandbox node,
+# pve-test.sweet.home ($PVE_TEST_HOST) -- pass --node "$PVE_TEST_HOST" (or
+# set PROXMOX_HOST=$PVE_TEST_HOST) to target the sandbox instead. See
+# CLAUDE.md's "Two Proxmox nodes" section: an agent session should default
+# to pve-test and only touch pve1 when the operator has explicitly said so
+# for the current task -- this script itself doesn't enforce that (its own
+# default is production, matching this repo's behavior before pve-test
+# existed), it's a policy for whoever/whatever is driving it.
+#
+# Usage:
+#   scripts/proxmox/create-proxmox-resource.sh --type lxc|vm --host <name> [options]
+#   scripts/proxmox/create-proxmox-resource.sh --type lxc|vm --list
+#   scripts/proxmox/create-proxmox-resource.sh --modify --vmid <n> [--cores N] [--memory MB] [--grow-disk GB]
+#
+# SAFETY:
+#   - The default (create) mode only ever creates a NEW resource -- it
+#     refuses to run if the target VMID already exists on the node, or if
+#     a VM/CT identified as --host already exists under any other VMID
+#     (checked live against the node; --allow-duplicate-host overrides).
+#   - --allow-duplicate-host distinguishes an exact match (same --type
+#     *and* --host, e.g. re-running --type lxc --host docker while an
+#     lxc-docker container already exists -- almost always a redeploy of
+#     the same target to pick up a rebuilt image) from a cross-type match
+#     (a different platform sharing the same host identity, e.g. a
+#     proxmox-docker VM coexisting with lxc-docker). Only the exact match
+#     is destroyed and replaced, after typing the hostname back to
+#     confirm (outside --dry-run) -- a cross-type match is always left
+#     untouched, matching-or-not.
+#   - --modify only ever touches a resource you name explicitly via
+#     --vmid, shows exactly what will change first, and (outside
+#     --dry-run) always requires typing that VMID back to confirm before
+#     anything is sent to the node. There is no bulk/implicit modify.
+#   - Outside of --allow-duplicate-host's exact-match replace above,
+#     neither mode can start/stop/delete a resource.
+#
+# See --help for the full option list.
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/nix-eval.sh
+source "${repo_root}/scripts/lib/nix-eval.sh"
+# shellcheck source=../lib/confirm.sh
+source "${repo_root}/scripts/lib/confirm.sh"
+
+sync_keys="${repo_root}/scripts/secrets/sync-host-keys.sh"
+
+usage() {
+  cat <<EOF
+Usage: $0 --type lxc|vm --host <name> [options]      (create)
+       $0 --type lxc|vm --list                        (list --host values)
+       $0 --modify --vmid <n> [options]                (reconfigure)
+
+Create mode (default):
+  --type lxc|vm        lxc = container, built as a CT template tarball.
+                        vm  = VM, built as a Disko .raw disk image (UEFI/OVMF).
+  --host <name>         Which host identity to deploy -- matches
+                        config.networking.hostName (server, docker,
+                        nix-cache, nixos, pxe-boot, nix-minimal). Use
+                        --list to see what's available for --type.
+  --name <name>          Proxmox display name/hostname (default: --host's
+                          value, e.g. nix-cache -- for lxc this becomes the
+                          guest's real networking.hostName too, since
+                          proxmoxLXC.manageHostName pulls it from Proxmox's
+                          own container config, so it must match host.nix
+                          regardless of build type)
+  --vmid <n>              Numeric VMID (default: next free, via
+                          \`pvesh get /cluster/nextid\` on the node).
+                          Refuses to run if this ID already exists.
+  --disk-size <GB>           lxc only: rootfs size for \`pct create\`
+                              (default: \$PROXMOX_DEFAULT_LXC_DISK_GB, ${PROXMOX_DEFAULT_LXC_DISK_GB}).
+  --image <path>              Use this local image/tarball (uploaded to the
+                              node via scp) instead of checking the node /
+                              building one there from the flake.
+  --force-rebuild                Skip the "does the node already have this
+                                  image" check -- always build fresh and
+                                  overwrite what's there.
+  --remote-repo-dir <path>       Where this flake repo lives (or gets
+                                  cloned) on the node, and is built from
+                                  (default: \$PROXMOX_REMOTE_REPO_DIR, ${PROXMOX_REMOTE_REPO_DIR}).
+  --allow-duplicate-host        Required if a VM/CT identified as --host
+                                already exists on the node (checked live via
+                                qm/pct, not any file in this repo) --
+                                otherwise refused, since it'd share that
+                                host's hostName/hostId. An existing resource
+                                of this *same* --type (e.g. re-running --type
+                                lxc --host docker over an existing lxc-docker)
+                                is destroyed and replaced, after confirming --
+                                a different --type sharing the same --host
+                                (e.g. a proxmox-docker VM) is always left
+                                untouched.
+
+Modify mode (reconfigure an EXISTING resource -- requires --modify):
+  --modify                Switch to modify mode.
+  --vmid <n>                Required: which existing resource to change.
+                            Type/VM-vs-CT is auto-detected on the node.
+  --grow-disk <GB>            Grow the primary disk by this many GB
+                              (qm/pct resize; Proxmox only supports
+                              growing, never shrinking, an existing disk).
+  At least one of --cores / --memory / --grow-disk is required. Always
+  prints the current -> new values and requires typing the VMID back to
+  confirm, even outside --dry-run.
+
+Shared:
+  --cores <n>              create: default \$PROXMOX_DEFAULT_CORES (${PROXMOX_DEFAULT_CORES}).
+                            modify: omit to leave unchanged.
+  --memory <MB>              create: default \$PROXMOX_DEFAULT_MEMORY_MB (${PROXMOX_DEFAULT_MEMORY_MB}).
+                              modify: omit to leave unchanged.
+  --swap <MB>                 lxc only, create time: \`--memory\` doesn't
+                              touch swap -- it silently stays at Proxmox's
+                              own 512M default otherwise. (default: matches
+                              whatever --memory resolves to)
+  --storage <pool>              (default: \$PROXMOX_STORAGE, ${PROXMOX_STORAGE})
+  --iso-storage <pool>            (default: \$PROXMOX_ISO_STORAGE, ${PROXMOX_ISO_STORAGE})
+  --bridge <bridge>                (default: \$PROXMOX_BRIDGE, ${PROXMOX_BRIDGE})
+  --node <host>                     Proxmox node to SSH into (default:
+                                    \$PROXMOX_HOST, ${PROXMOX_HOST} --
+                                    production; the sandbox node is
+                                    \$PVE_TEST_HOST, ${PVE_TEST_HOST}).
+  --dry-run                           Print the full plan; touch nothing
+                                      local or remote, no prompts.
+  -h, --help
+
+Config for --storage/--bridge/--node/etc. lives in scripts/env.sh -- edit
+that instead of passing the same flag every time.
+EOF
+}
+
+dry_run=0
+modify=0
+type=""
+host=""
+name=""
+vmid=""
+cores=""
+memory=""
+swap=""
+disk_size=""
+grow_disk=""
+image=""
+storage="$PROXMOX_STORAGE"
+iso_storage="$PROXMOX_ISO_STORAGE"
+bridge="$PROXMOX_BRIDGE"
+node="$PROXMOX_HOST"
+remote_repo_dir="$PROXMOX_REMOTE_REPO_DIR"
+do_list=0
+allow_duplicate_host=0
+force_rebuild=0
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+  --type) type="$2"; shift 2 ;;
+  --host) host="$2"; shift 2 ;;
+  --name) name="$2"; shift 2 ;;
+  --vmid) vmid="$2"; shift 2 ;;
+  --cores) cores="$2"; shift 2 ;;
+  --memory) memory="$2"; shift 2 ;;
+  --swap) swap="$2"; shift 2 ;;
+  --disk-size) disk_size="$2"; shift 2 ;;
+  --grow-disk) grow_disk="$2"; shift 2 ;;
+  --image) image="$2"; shift 2 ;;
+  --storage) storage="$2"; shift 2 ;;
+  --iso-storage) iso_storage="$2"; shift 2 ;;
+  --bridge) bridge="$2"; shift 2 ;;
+  --node) node="$2"; shift 2 ;;
+  --remote-repo-dir) remote_repo_dir="$2"; shift 2 ;;
+  --list) do_list=1; shift ;;
+  --allow-duplicate-host) allow_duplicate_host=1; shift ;;
+  --force-rebuild) force_rebuild=1; shift ;;
+  --modify) modify=1; shift ;;
+  --dry-run) dry_run=1; shift ;;
+  -h | --help) usage; exit 0 ;;
+  *) echo "Unknown option: $1" >&2; usage >&2; exit 1 ;;
+  esac
+done
+
+ssh_target="${PROXMOX_SSH_USER}@${node}"
+
+remote() {
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "[dry-run] ssh ${ssh_target} -- $*"
+  else
+    ssh "$ssh_target" "$@"
+  fi
+}
+
+# ============================================================ modify mode
+cmd_modify() {
+  if [[ -z "$vmid" ]]; then
+    echo "ERROR: --modify requires --vmid." >&2
+    exit 1
+  fi
+  if [[ -z "$cores" && -z "$memory" && -z "$grow_disk" ]]; then
+    echo "ERROR: --modify needs at least one of --cores / --memory / --grow-disk." >&2
+    exit 1
+  fi
+
+  echo "Looking up VMID ${vmid} on ${node}..."
+  local kind current_cores current_memory disk_key
+  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1; then
+    kind="vm"
+    disk_key="scsi0"
+  elif ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
+    kind="lxc"
+    disk_key="rootfs"
+  else
+    echo "ERROR: VMID ${vmid} doesn't exist on ${node} -- nothing to modify." >&2
+    exit 1
+  fi
+
+  local config_cmd="qm config ${vmid}"
+  [[ "$kind" == "lxc" ]] && config_cmd="pct config ${vmid}"
+  local current_config
+  current_config="$(ssh "$ssh_target" "$config_cmd")"
+  current_cores="$(echo "$current_config" | grep -oP '^cores:\s*\K\S+' || echo '?')"
+  current_memory="$(echo "$current_config" | grep -oP '^memory:\s*\K\S+' || echo '?')"
+
+  echo
+  echo "VMID ${vmid} is a ${kind} on ${node}. Planned changes:"
+  [[ -n "$cores" ]] && echo "  cores:  ${current_cores} -> ${cores}"
+  [[ -n "$memory" ]] && echo "  memory: ${current_memory} MB -> ${memory} MB"
+  [[ -n "$grow_disk" ]] && echo "  ${disk_key}: grow by +${grow_disk}G (Proxmox can only grow, not shrink, an existing disk)"
+
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo
+    echo "[dry-run] Nothing was changed."
+    return
+  fi
+
+  echo
+  if ! confirm_typed "$vmid" "Type the VMID (${vmid}) to confirm these changes: "; then
+    echo "Cancelled -- input didn't match ${vmid}."
+    exit 1
+  fi
+
+  local set_cmd="qm set"
+  local resize_cmd="qm resize"
+  [[ "$kind" == "lxc" ]] && set_cmd="pct set" && resize_cmd="pct resize"
+
+  if [[ -n "$cores" || -n "$memory" ]]; then
+    local args=""
+    [[ -n "$cores" ]] && args="${args} --cores ${cores}"
+    [[ -n "$memory" ]] && args="${args} --memory ${memory}"
+    remote "${set_cmd} ${vmid}${args}"
+  fi
+  if [[ -n "$grow_disk" ]]; then
+    remote "${resize_cmd} ${vmid} ${disk_key} +${grow_disk}G"
+  fi
+
+  echo
+  echo "Done. VMID ${vmid} updated."
+}
+
+if [[ "$modify" -eq 1 ]]; then
+  cmd_modify
+  exit 0
+fi
+
+# ============================================================= create mode
+if [[ "$type" != "lxc" && "$type" != "vm" ]]; then
+  echo "ERROR: --type must be 'lxc' or 'vm'." >&2
+  usage >&2
+  exit 1
+fi
+
+platform_prefix="lxc"
+[[ "$type" == "vm" ]] && platform_prefix="proxmox"
+[[ -z "$cores" ]] && cores="$PROXMOX_DEFAULT_CORES"
+[[ -z "$memory" ]] && memory="$PROXMOX_DEFAULT_MEMORY_MB"
+
+# --- 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
+# from, so they can never see a different set of targets from each other.
+targets_for_platform() {
+  local target
+  for target in $(list_flake_targets "$repo_root" 2>/dev/null | grep -- "^${platform_prefix}-"); do
+    printf '%s\t%s\n' "$target" "$(flake_target_hostname "$repo_root" "$target")"
+  done
+}
+
+list_hosts() {
+  local target hostname
+  while IFS=$'\t' read -r target hostname; do
+    printf '  %-12s -> %s\n' "$hostname" "$target"
+  done < <(targets_for_platform)
+}
+
+if [[ "$do_list" -eq 1 ]]; then
+  echo "Available --host values for --type ${type}:"
+  list_hosts
+  exit 0
+fi
+
+if [[ -z "$host" ]]; then
+  echo "ERROR: --host is required (or use --list to see options)." >&2
+  exit 1
+fi
+
+flake_target=""
+while IFS=$'\t' read -r target hostname; do
+  if [[ "$hostname" == "$host" ]]; then
+    flake_target="$target"
+    break
+  fi
+done < <(targets_for_platform)
+
+if [[ -z "$flake_target" ]]; then
+  echo "ERROR: no ${platform_prefix}-* target has hostName '${host}'." >&2
+  echo "Available:" >&2
+  list_hosts >&2
+  exit 1
+fi
+
+# The container/VM's real identity is --host (e.g. "nix-cache"), validated
+# above against config.networking.hostName -- not the flake target name
+# (e.g. "lxc-nix-cache"), which is build-type-specific and only exists to
+# pick which platform variant to build. Defaulting --name to the flake
+# target would make lxc's --hostname (which proxmoxLXC.manageHostName
+# feeds straight into the guest's real hostname) disagree with host.nix.
+[[ -z "$name" ]] && name="$host"
+
+# --- 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
+# actually exists, and this used to be checked against variables.nix's
+# deployedTargets, which drifted stale (it kept naming a VM as "the real
+# deployment" well after that VM had been destroyed, blocking its own
+# redeploy) until that list was dropped in favour of this live check. This
+# only catches guests identified with the default --name (== --host, what
+# this script itself always uses unless --name is overridden) -- a guest
+# manually renamed on the node afterwards wouldn't match, but nothing here
+# creates guests that way.
+if [[ "$dry_run" -eq 1 ]]; then
+  echo
+  echo "[dry-run] would check ${node} for an existing VM/CT identified as '${host}'"
+  if [[ "$allow_duplicate_host" -eq 1 ]]; then
+    echo "[dry-run] --allow-duplicate-host: an existing ${type} named '${host}' would be" \
+      "destroyed and replaced; a different-type match would be left untouched"
+  fi
+else
+  echo
+  echo "==> Checking ${node} for an existing VM/CT identified as '${host}'..."
+  ssh_check_status=0
+  existing="$(ssh "$ssh_target" bash -s -- "$host" <<'REMOTE_SCRIPT'
+target="$1"
+for id in $(qm list 2>/dev/null | awk 'NR>1{print $1}'); do
+  n="$(qm config "$id" 2>/dev/null | grep -oP '^name:\s*\K\S+' || true)"
+  [[ "$n" == "$target" ]] && echo "vm ${id} ${n}"
+done
+for id in $(pct list 2>/dev/null | awk 'NR>1{print $1}'); do
+  n="$(pct config "$id" 2>/dev/null | grep -oP '^hostname:\s*\K\S+' || true)"
+  [[ "$n" == "$target" ]] && echo "lxc ${id} ${n}"
+done
+exit 0
+REMOTE_SCRIPT
+  )" || ssh_check_status=$?
+  if [[ "$ssh_check_status" -ne 0 ]]; then
+    echo "ERROR: couldn't reach ${node} (ssh exited ${ssh_check_status}) to check for an" >&2
+    echo "existing '${host}' resource -- refusing to guess. Fix connectivity and retry," >&2
+    echo "or pass --allow-duplicate-host if you're sure none exists (this skips the" >&2
+    echo "check entirely)." >&2
+    exit 1
+  fi
+
+  # Split into "exact" (same resource kind as --type -- i.e. literally this
+  # same host+platform combo already exists, almost always a redeploy of
+  # the same target to test a rebuilt image) vs "cross-type" (a different
+  # platform sharing this host identity, e.g. a stopped proxmox-docker VM
+  # coexisting with an lxc-docker container -- a deliberate, valid setup
+  # this script has never managed and still won't). Read via a herestring
+  # (not a pipe) so the appends below survive outside the loop.
+  this_kind="$type"
+  exact_matches=""
+  cross_matches=""
+  if [[ -n "$existing" ]]; then
+    while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      if [[ "$kind" == "$this_kind" ]]; then
+        exact_matches+="${kind} ${id} ${n}"$'\n'
+      else
+        cross_matches+="${kind} ${id} ${n}"$'\n'
+      fi
+    done <<<"$existing"
+  fi
+
+  if [[ -n "$exact_matches" && "$allow_duplicate_host" -ne 1 ]]; then
+    echo "ERROR: '${host}' already exists on ${node} as this same resource type:" >&2
+    echo "$exact_matches" | while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      echo "  - ${kind} VMID ${id} (${n})" >&2
+    done
+    echo "Refusing to create a second ${this_kind} sharing this identity. Pass" >&2
+    echo "--allow-duplicate-host to destroy it and create a fresh one in its place" >&2
+    echo "(after confirming), or use --modify to reconfigure the existing one instead." >&2
+    exit 1
+  fi
+
+  if [[ -n "$cross_matches" && "$allow_duplicate_host" -ne 1 ]]; then
+    echo "ERROR: '${host}' already exists on ${node} as a different resource type:" >&2
+    echo "$cross_matches" | while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      echo "  - ${kind} VMID ${id} (${n})" >&2
+    done
+    echo "Refusing to create a second resource sharing this identity. Pass" >&2
+    echo "--allow-duplicate-host to create one anyway (it gets its own distinct" >&2
+    echo "sops key and VMID -- the existing resource above is left untouched)," >&2
+    echo "or use --modify to reconfigure the existing one instead." >&2
+    exit 1
+  fi
+
+  if [[ -n "$cross_matches" ]]; then
+    echo "--allow-duplicate-host: '${host}' also exists on ${node} as a different resource" \
+      "type -- leaving it untouched:"
+    echo "$cross_matches" | while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      echo "  - ${kind} VMID ${id} (${n})"
+    done
+  fi
+
+  if [[ -n "$exact_matches" ]]; then
+    echo "--allow-duplicate-host: '${host}' already exists on ${node} as this same resource" \
+      "type -- it will be destroyed and replaced:"
+    echo "$exact_matches" | while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      echo "  - ${kind} VMID ${id} (${n})"
+    done
+    echo
+    if ! confirm_typed "$host" "Type the hostname (${host}) to confirm destroying the above and replacing it: "; then
+      echo "Cancelled -- input didn't match ${host}." >&2
+      exit 1
+    fi
+    echo "$exact_matches" | while read -r kind id n; do
+      [[ -z "$kind" ]] && continue
+      echo "==> Destroying ${kind} VMID ${id} (${n})..."
+      if [[ "$kind" == "vm" ]]; then
+        # qm destroy has no --force to stop-then-destroy in one call (pct's
+        # does) -- stop explicitly first if it's running.
+        if ssh "$ssh_target" "qm status ${id}" 2>/dev/null | grep -q running; then
+          ssh "$ssh_target" "qm stop ${id}"
+        fi
+        ssh "$ssh_target" "qm destroy ${id} --purge 1"
+      else
+        ssh "$ssh_target" "pct destroy ${id} --force 1 --purge 1"
+      fi
+    done
+  fi
+fi
+
+echo "Target: ${flake_target} (host=${host}, type=${type}) -> Proxmox resource '${name}'"
+
+# Decide on nix-cache once, here -- this is the earliest point that needs
+# it (sync-host-keys.sh below needs nix-shell packages regardless of
+# whether an image ends up getting built later), and the decision is
+# exported so that subprocess -- and this script's own later build step,
+# if it gets there -- both reuse it instead of probing again.
+nix_extra_opts
+
+# --- make sure this target has a registered host key --------------------
+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[@]}"
+
+# --- VMID: pick one, and refuse to touch anything that already exists ---
+echo
+if [[ -z "$vmid" ]]; then
+  if [[ "$dry_run" -eq 1 ]]; then
+    vmid="<next-free-vmid>"
+    echo "[dry-run] would ask ${node} for the next free VMID (pvesh get /cluster/nextid)"
+  else
+    vmid="$(ssh "$ssh_target" "pvesh get /cluster/nextid" | tr -d '[:space:]')"
+    echo "Auto-assigned VMID: ${vmid}"
+  fi
+else
+  echo "Requested VMID: ${vmid}"
+fi
+
+if [[ "$dry_run" -eq 0 ]]; then
+  # qm/pct status exits non-zero (and prints "does not exist") for a free
+  # ID on that resource type -- but a VMID could exist as the OTHER
+  # resource type (e.g. requested a CT id that's actually a VM), so check
+  # both. Any success here means something is already using this ID --
+  # refuse to go anywhere near it. (Reconfiguring an existing resource is
+  # --modify's job, not this one's.)
+  if ssh "$ssh_target" "qm status ${vmid}" >/dev/null 2>&1 \
+    || ssh "$ssh_target" "pct status ${vmid}" >/dev/null 2>&1; then
+    echo "ERROR: VMID ${vmid} already exists on ${node}. Refusing to touch an" >&2
+    echo "existing resource here -- use --modify to reconfigure it, pick a" >&2
+    echo "different --vmid, or omit it to auto-assign." >&2
+    exit 1
+  fi
+fi
+
+# --- resolve the remote path -- fixed naming (not the nix store's own
+# derivation-hash-based filename), so a later run can check for it by name.
+# lxc uploads as a CT *template* (Proxmox's "vztmpl" content type, under
+# iso_storage) -- config.system.build.tarball is a plain rootfs tarball,
+# not a vzdump backup archive, so it's created with `pct create ... vztmpl`,
+# not restored with `pct restore` (that expects backup-archive metadata
+# this tarball doesn't have, and fails with "archive contains no
+# configuration file").
+remote_dir="/var/lib/vz/import"
+remote_filename="${flake_target}.raw"
+if [[ "$type" == "lxc" ]]; then
+  remote_dir="/var/lib/vz/template/cache"
+  remote_filename="${flake_target}.tar.xz"
+fi
+remote_path="${remote_dir}/${remote_filename}"
+
+# --- ensure the flake repo (+ tooling) exists on the node, and is current --
+# Bootstraps once (git clone from this checkout's own `origin`, then
+# scripts/codex-setup.sh installs Nix + friends) if ${remote_repo_dir}
+# doesn't exist yet on the node; otherwise just `git pull`s it, so the image
+# built there reflects what's actually committed and pushed. Only called
+# right before an actual remote build below -- reusing an image already on
+# the node, or an explicit --image, never touch the node's checkout at all.
+ensure_remote_repo() {
+  echo
+  echo "==> Ensuring ${remote_repo_dir} exists and is current on ${node}..."
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "[dry-run] would ensure ${remote_repo_dir} exists on ${node} (clone if missing, git pull if present), and would verify/bootstrap build tooling there (scripts/codex-setup.sh) if \`nix\` isn't already on PATH -- and if that bootstrap actually ran, would also configure ${node} as a nix-cache client (scripts/proxmox/configure-nix-cache-client.sh)"
+    return
+  fi
+
+  if ssh "$ssh_target" "test -d '${remote_repo_dir}/.git'"; then
+    echo "Repo present -- pulling latest..."
+    ssh "$ssh_target" "cd '${remote_repo_dir}' && git pull --ff-only"
+  else
+    local origin_url
+    origin_url="$(git -C "$repo_root" remote get-url origin 2>/dev/null || true)"
+    if [[ -z "$origin_url" ]]; then
+      echo "ERROR: ${remote_repo_dir} doesn't exist on ${node}, and this checkout has no" >&2
+      echo "'origin' remote to clone from. Set one (git remote add origin <url>) or create" >&2
+      echo "${remote_repo_dir} on ${node} yourself (e.g. git clone), then re-run." >&2
+      exit 1
+    fi
+    echo "Not present -- cloning from ${origin_url}..."
+    ssh "$ssh_target" "git clone '${origin_url}' '${remote_repo_dir}'"
+  fi
+
+  # Trivial check, run every time (not just right after a fresh clone) --
+  # confirmed live: a first bootstrap can clone the repo successfully and
+  # still leave the node without a working `nix` (e.g. the node had no
+  # `sudo`, which the Nix installer's root path depends on -- see the fix
+  # in scripts/codex-setup.sh), and a later run with the repo already
+  # present would otherwise never retry it. Sources
+  # scripts/lib/nix-bootstrap.sh's ensure_nix_profile first -- a
+  # single-user Nix install typically only gets sourced into login shells,
+  # and ssh's non-interactive command execution is neither, so a
+  # freshly-installed `nix` still wouldn't be on PATH here without it.
+  #
+  # Just `nix` today -- the only thing the remote build commands below
+  # actually invoke -- but a list (not a single hardcoded check) so a
+  # future remote step needing another tool can add itself here instead of
+  # growing a parallel check.
+  local remote_required_cmds=(nix)
+  local tooling_check_cmd="cd '${remote_repo_dir}' && . scripts/lib/nix-bootstrap.sh && ensure_nix_profile"
+  local cmd
+  for cmd in "${remote_required_cmds[@]}"; do
+    tooling_check_cmd="${tooling_check_cmd} && command -v ${cmd}"
+  done
+
+  if ssh "$ssh_target" "$tooling_check_cmd" >/dev/null 2>&1; then
+    echo "Build tooling already present on ${node}."
+  else
+    echo "==> Bootstrapping build tooling on ${node} (scripts/codex-setup.sh)..."
+    ssh "$ssh_target" "cd '${remote_repo_dir}' && bash scripts/codex-setup.sh"
+
+    # Only on this first-time bootstrap, not every run -- a node that
+    # already has tooling either already went through this once, or had
+    # it configured some other way, and re-running is harmless but
+    # pointless. Non-fatal: this only makes the node's own builds faster
+    # (substitute from nix-cache instead of building from source) and
+    # offloadable to it as a remote builder -- worth trying, not worth
+    # aborting the image build over if nix-cache happens to be down right
+    # now. Needs ensure_nix_profile first, same as the tooling_check_cmd
+    # above -- ssh's non-interactive command execution won't have picked
+    # up a freshly single-user-installed `nix` otherwise.
+    echo "==> Configuring ${node} as a nix-cache substituter/remote-builder client..."
+    if ! ssh "$ssh_target" "cd '${remote_repo_dir}' && . scripts/lib/nix-bootstrap.sh && ensure_nix_profile && bash scripts/proxmox/configure-nix-cache-client.sh"; then
+      echo "WARNING: configure-nix-cache-client.sh failed on ${node} -- continuing without it (${node} will build from source / against cache.nixos.org only)." >&2
+    fi
+  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_remote_host_keys() {
+  echo
+  echo "==> Syncing host-keys/ 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/"
+    return
+  fi
+  ssh "$ssh_target" "mkdir -p '${remote_repo_dir}/host-keys'"
+  scp -pr "${repo_root}/host-keys/." "${ssh_target}:${remote_repo_dir}/host-keys/"
+}
+
+# --- build (or reuse an image already on the node) ------------------------
+echo
+local_image=""
+image_already_remote=0
+
+if [[ -n "$image" ]]; then
+  [[ -f "$image" ]] || { echo "ERROR: --image '${image}' not found." >&2; exit 1; }
+  local_image="$image"
+  echo "Using provided image: ${local_image}"
+elif [[ "$force_rebuild" -eq 1 ]]; then
+  echo "--force-rebuild: skipping the existing-image check on ${node}."
+else
+  echo "==> Checking whether ${node} already has ${remote_path}..."
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "[dry-run] would check: ssh ${ssh_target} -- test -f ${remote_path}"
+  elif ssh "$ssh_target" "test -f '${remote_path}'" 2>/dev/null; then
+    echo "Found it -- reusing, skipping build (use --force-rebuild to override)."
+    image_already_remote=1
+  else
+    echo "Not found -- will build."
+  fi
+fi
+
+if [[ "$image_already_remote" -eq 0 && -z "$local_image" ]]; then
+  ensure_remote_repo
+  sync_remote_host_keys
+
+  # Relayed into the remote build below exactly as decided by the local
+  # nix_extra_opts call earlier in this script -- that decision (whether
+  # nix-cache is reachable) is made once, locally, same as it always has
+  # been; only *where* the resulting "${NIX_OPTS[@]}" gets used as a `nix
+  # build` flag moves to the node. NIX_EXTRA_OPTS is already a %q-quoted
+  # string built for exactly this eval-based reconstruction (see env.sh).
+  nix_opts_display=""
+  if [[ ${#NIX_OPTS[@]} -gt 0 ]]; then
+    printf -v nix_opts_display '%q ' "${NIX_OPTS[@]}"
+    nix_opts_display=" ${nix_opts_display% }"
+  fi
+
+  if [[ "$type" == "lxc" ]]; then
+    if [[ "$dry_run" -eq 1 ]]; then
+      echo "[dry-run] would build on ${node}: NIXOS_HOST_KEYS_DIR=\$(pwd)/host-keys nix build --impure \\"
+      echo "[dry-run]   --no-use-registries --no-accept-flake-config${nix_opts_display} \\"
+      echo "[dry-run]   .#nixosConfigurations.${flake_target}.config.system.build.tarball"
+      echo "[dry-run] would stage the result at ${remote_path}"
+      local_image="<built-tarball>"
+    else
+      echo "==> Building LXC tarball for ${flake_target} on ${node}..."
+      # Built as a single already-%q-quoted command string, not separate ssh
+      # argv elements -- ssh joins remote command args with plain spaces and
+      # hands the result to the remote shell to re-split, which would
+      # otherwise scatter NIX_EXTRA_OPTS (itself several space-separated,
+      # %q-quoted tokens) across the wrong positional parameters below.
+      printf -v remote_cmd 'bash -s -- %q %q %q %q %q' \
+        "$remote_repo_dir" "$flake_target" "$remote_dir" "$remote_filename" "$NIX_EXTRA_OPTS"
+      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="$5"
+declare -a NIX_OPTS=()
+[[ -n "$nix_extra_opts_str" ]] && eval "NIX_OPTS=(${nix_extra_opts_str})"
+cd "$repo_dir"
+# A single-user Nix install only gets sourced into login shells; this ssh
+# session is neither, so `nix` wouldn't otherwise be on PATH here even
+# right after a successful install.
+. scripts/lib/nix-bootstrap.sh
+ensure_nix_profile
+NIXOS_HOST_KEYS_DIR="$(pwd)/host-keys" nix build --impure \
+  --no-use-registries --no-accept-flake-config "${NIX_OPTS[@]}" \
+  ".#nixosConfigurations.${target}.config.system.build.tarball" \
+  --out-link "result-${target}"
+built="$(find "result-${target}/tarball" -maxdepth 1 -type f | head -1)"
+if [[ -z "$built" ]]; then
+  echo "ERROR: no tarball found under result-${target}/tarball after build." >&2
+  exit 1
+fi
+mkdir -p "$dest_dir"
+cp "$built" "${dest_dir}/${dest_name}"
+echo "Built and staged: ${dest_dir}/${dest_name}"
+REMOTE_SCRIPT
+      local_image="$remote_path"
+      echo "Built on ${node}: ${remote_path}"
+    fi
+  else
+    # PROXMOX_SSH_USER defaults to root (env.sh), which needs no sudo and
+    # can't assume it's even installed on a minimal node -- only shell out
+    # through sudo when actually running as a non-root SSH user.
+    sudo_prefix="sudo"
+    sudo_display="sudo "
+    if [[ "$PROXMOX_SSH_USER" == "root" ]]; then
+      sudo_prefix=""
+      sudo_display=""
+    fi
+    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]   .#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}"
+      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" "$sudo_prefix"
+      ssh "$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_prefix="$6"
+declare -a NIX_OPTS=()
+[[ -n "$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_prefix "./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 ${repo_dir} after build." >&2
+  exit 1
+fi
+mkdir -p "$dest_dir"
+mv "$built" "${dest_dir}/${dest_name}"
+echo "Built and staged: ${dest_dir}/${dest_name}"
+REMOTE_SCRIPT
+      local_image="$remote_path"
+      echo "Built on ${node}: ${remote_path}"
+    fi
+  fi
+fi
+
+# --- upload -- only for an explicit --image; a build above stages its
+# result directly at ${remote_path} on the node already, and reusing an
+# image already on the node needs nothing transferred either. ------------
+echo
+if [[ -n "$image" ]]; then
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "[dry-run] would upload: scp ${local_image} ${ssh_target}:${remote_path}"
+  else
+    echo "==> Uploading to ${node}:${remote_path}..."
+    ssh "$ssh_target" "mkdir -p ${remote_dir}"
+    scp "$local_image" "${ssh_target}:${remote_path}"
+  fi
+fi
+
+# --- create -----------------------------------------------------------------
+echo
+if [[ "$type" == "lxc" ]]; then
+  echo "==> Creating LXC container ${vmid} (${name})..."
+  local_disk_size="${disk_size:-$PROXMOX_DEFAULT_LXC_DISK_GB}"
+  # --memory doesn't touch swap -- it silently stays at Proxmox's own
+  # 512M default otherwise (confirmed live: --memory 2048 left swap at
+  # 512). Default to matching whatever --memory resolved to above.
+  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.
+  privileged_eval="$(flake_target_lxc_privileged "$repo_root" "$flake_target")"
+  unprivileged_flag=1
+  [[ "$privileged_eval" == "true" ]] && unprivileged_flag=0
+  #
+  # --features nesting=1,keyctl=1: required for a modern (v247+) systemd
+  # guest to actually boot unprivileged -- confirmed live: without this,
+  # AppArmor denies the nested user namespaces and credential mounts
+  # systemd routinely uses (even plain getty units), and every getty
+  # crash-loops on a denied mount every ~3s (visible as garbage on the
+  # console) while core services like nsncd fail the same way.
+  #
+  # ...,mount=nfs;nfs4: without it AppArmor blanket-denies the `nfs`/
+  # `rpc_pipefs` mount syscalls any NFS client share needs -- confirmed
+  # live on lxc-docker: `mount: /var/lib/nfs/rpc_pipefs: permission
+  # denied`. The value's `;` (Proxmox's own multi-fstype separator for
+  # this one feature, per PVE::LXC's use of PVE::ParseUtils::split_list)
+  # must stay single-quoted here: create_cmd is sent to `remote()`, which
+  # hands the whole string to `ssh` as a single command for the *remote*
+  # shell to parse -- unquoted, that `;` would be read as a remote
+  # command separator and silently truncate this into two commands.
+  create_cmd="pct create ${vmid} ${iso_storage}:vztmpl/${remote_filename} --unprivileged ${unprivileged_flag} --features '${PROXMOX_DEFAULT_LXC_FEATURES}' --rootfs ${storage}:${local_disk_size} --hostname ${name} --cores ${cores} --memory ${memory} --swap ${local_swap} --net0 name=eth0,bridge=${bridge},ip=dhcp"
+  remote "$create_cmd"
+  remote "pct start ${vmid}"
+else
+  echo "==> Creating VM ${vmid} (${name})..."
+  # pre-enrolled-keys=0 disables OVMF's Secure Boot key pre-enrollment --
+  # required, or systemd-boot (unsigned) can't be trusted by the firmware.
+  # --agent 1: wires up the virtio-serial channel QEMU exposes to the guest.
+  # modules/common/configuration.nix sets services.qemuGuest.enable = true
+  # on every host, so the guest-side qemu-ga daemon is already running --
+  # without this flag Proxmox never creates the channel it listens on, so
+  # `qm guest exec`/`qm agent` and the UI's IP-address display silently
+  # never work for any VM this script creates.
+  remote "qm create ${vmid} --name ${name} --memory ${memory} --cores ${cores} \
+--net0 virtio,bridge=${bridge} --bios ovmf --machine q35 --scsihw virtio-scsi-pci \
+--efidisk0 ${storage}:1,efitype=4m,pre-enrolled-keys=0 --agent enabled=1"
+
+  if [[ "$dry_run" -eq 1 ]]; then
+    echo "[dry-run] ssh ${ssh_target} -- qm importdisk ${vmid} ${remote_path} ${storage}"
+    echo "[dry-run] (would parse the resulting disk identifier from that output)"
+    echo "[dry-run] ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<parsed-disk-id>"
+  else
+    importdisk_output="$(ssh "$ssh_target" "qm importdisk ${vmid} ${remote_path} ${storage}")"
+    echo "$importdisk_output"
+    disk_id="$(echo "$importdisk_output" | grep -oP "(?<=Successfully imported disk as ')[^']+" | sed 's/^unused[0-9]*://')"
+    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
+      echo "  ssh ${ssh_target} -- qm set ${vmid} --scsi0 ${storage}:<disk-id-from-output-above>" >&2
+      echo "  ssh ${ssh_target} -- qm set ${vmid} --boot order=scsi0" >&2
+      exit 1
+    fi
+    remote "qm set ${vmid} --scsi0 ${disk_id}"
+  fi
+  remote "qm set ${vmid} --boot order=scsi0"
+  remote "qm start ${vmid}"
+fi
+
+echo
+if [[ "$dry_run" -eq 1 ]]; then
+  echo "[dry-run] Nothing was built, uploaded, or created."
+else
+  echo "Done. ${name} (VMID ${vmid}) should be booting on ${node}."
+fi

scripts/secrets/backup-admin-key.sh

@@ -0,0 +1,150 @@
+#!/usr/bin/env bash
+# Backs up the local sops age key (the private key that decrypts
+# secrets/*.yaml -- normally the one trusted as &admin) to an arbitrary
+# destination path, e.g. a USB drive or other offline storage, so it can
+# later be restored and handed to rotate-admin-key.sh if this machine's
+# copy is ever lost, or to run either script from a different machine.
+#
+# Usage:
+#   scripts/secrets/backup-admin-key.sh <dest-path> [--key-file <path>] [--force] [--dry-run]
+#
+# Source key resolution matches sops/age's own default order:
+#   $SOPS_AGE_KEY (inline identity text) if set, else
+#   --key-file if given, else
+#   $SOPS_AGE_KEY_FILE if set, else
+#   ${XDG_CONFIG_HOME:-$HOME/.config}/sops/age/keys.txt
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+sops_yaml="${repo_root}/.sops.yaml"
+
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/sops-age.sh
+source "${repo_root}/scripts/lib/sops-age.sh"
+
+# Pin cwd for the same reason rotate-admin-key.sh does: age/sops calls
+# below should never depend on wherever the caller's shell happened to be.
+cd "$repo_root"
+
+usage() {
+  cat <<EOF
+Usage: $0 <dest-path> [--key-file <path>] [--force] [--dry-run]
+
+  <dest-path>        Where to write the backup. Parent directories are
+                     created as needed. Written with 0600 permissions.
+  --key-file <path>  Read the key from here instead of the default
+                     sops/age resolution (\$SOPS_AGE_KEY_FILE, then
+                     \${XDG_CONFIG_HOME:-\$HOME/.config}/sops/age/keys.txt).
+                     Ignored if \$SOPS_AGE_KEY is set (that always wins,
+                     same precedence sops/age itself uses).
+  --force            Overwrite <dest-path> if it already exists.
+  --dry-run          Print what would happen; write nothing.
+EOF
+}
+
+dry_run=0
+force=0
+key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
+args=()
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --dry-run)
+      dry_run=1
+      shift
+      ;;
+    --force)
+      force=1
+      shift
+      ;;
+    --key-file)
+      key_file="${2:?--key-file requires a path}"
+      shift 2
+      ;;
+    -h | --help)
+      usage
+      exit 0
+      ;;
+    --*)
+      echo "Unknown option: $1" >&2
+      usage >&2
+      exit 1
+      ;;
+    *)
+      args+=("$1")
+      shift
+      ;;
+  esac
+done
+
+if [[ "${#args[@]}" -ne 1 ]]; then
+  usage >&2
+  exit 1
+fi
+dest="${args[0]}"
+
+nix_extra_opts
+
+if [[ -n "${SOPS_AGE_KEY:-}" ]]; then
+  echo "==> Source: \$SOPS_AGE_KEY (inline identity from the environment)."
+  src_content="$SOPS_AGE_KEY"
+else
+  [[ -s "$key_file" ]] || {
+    echo "ERROR: no key found. \$SOPS_AGE_KEY is unset and ${key_file} doesn't exist or is empty." >&2
+    exit 1
+  }
+  echo "==> Source: ${key_file}"
+  src_content="$(cat "$key_file")"
+fi
+
+# Round-trip through a private scratch file (rather than trusting the
+# source string as-is) so age-keygen -y validates it's a real identity
+# before anything is written to <dest-path>.
+scratch="$(mktemp)"
+trap 'rm -f "$scratch"' EXIT
+( umask 077; printf '%s\n' "$src_content" > "$scratch" )
+
+src_pub="$(age_pubkey_from_identity_file "$scratch")" || {
+  echo "ERROR: source doesn't look like a valid age identity (age-keygen -y failed)." >&2
+  exit 1
+}
+echo "    public key: ${src_pub}"
+
+current_admin_pub="$(sops_yaml_admin_pubkey "$sops_yaml")"
+if [[ -n "$current_admin_pub" && "$current_admin_pub" != "$src_pub" ]]; then
+  echo "NOTE: this key does not match .sops.yaml's current &admin entry (${current_admin_pub})."
+  echo "      Backing it up anyway -- this script doesn't require it to be the admin key."
+fi
+
+if [[ -e "$dest" && "$force" -ne 1 ]]; then
+  echo "ERROR: ${dest} already exists. Pass --force to overwrite." >&2
+  exit 1
+fi
+
+if [[ "$dry_run" -eq 1 ]]; then
+  echo
+  echo "[dry-run] would write $(wc -c <"$scratch" | tr -d ' ') bytes to ${dest} (mode 0600)"
+  [[ -e "$dest" ]] && echo "[dry-run] would overwrite existing file (--force given)"
+  echo "[dry-run] Nothing was written. Re-run without --dry-run to apply this."
+  exit 0
+fi
+
+mkdir -p "$(dirname "$dest")"
+install -m 600 "$scratch" "$dest"
+
+dest_pub="$(age_pubkey_from_identity_file "$dest")"
+if [[ "$dest_pub" != "$src_pub" ]]; then
+  echo "ERROR: ${dest} was written but its public key doesn't match the source -- investigate before relying on this backup." >&2
+  exit 1
+fi
+
+cat <<EOF
+
+Done. Backed up to: ${dest}
+  public key: ${dest_pub}
+
+This is a private key -- store it somewhere offline/secure, not in this
+repo or anywhere it'd get committed. Restore it with:
+  scripts/secrets/rotate-admin-key.sh ${dest}
+EOF

scripts/secrets/prepare-host-key.sh

@@ -2,7 +2,7 @@
 # Generates a new machine's SSH host key by an arbitrary name, before it
 # necessarily has a flake target yet -- prints the .sops.yaml snippet to
 # add by hand. For any host that already has a flake target,
-# scripts/sync-host-keys.sh <target> does this same job plus the
+# scripts/secrets/sync-host-keys.sh <target> does this same job plus the
 # .sops.yaml/key_groups registration and re-encryption automatically; use
 # this script only to pre-generate a key ahead of adding the flake target
 # itself.
@@ -22,9 +22,13 @@
 # new machine.
 set -euo pipefail
 
-repo_root="$(cd "$(dirname "$0")/.." && pwd)"
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/ssh-host-keys.sh
+source "${repo_root}/scripts/lib/ssh-host-keys.sh"
 
-hostname="${1:?usage: scripts/prepare-host-key.sh <hostname>}"
+hostname="${1:?usage: scripts/secrets/prepare-host-key.sh <hostname>}"
 sops_yaml="${repo_root}/.sops.yaml"
 
 if [[ ! -f "$sops_yaml" ]]; then
@@ -41,9 +45,10 @@ if [[ -f "$keyfile" ]]; then
   exit 1
 fi
 
-nix-shell -p openssh --run "ssh-keygen -t ed25519 -N '' -C '${hostname}' -f '${keyfile}'" >/dev/null
+nix_extra_opts
+generate_host_ed25519_key "$hostname" "$keyfile"
 
-age_pub="$(nix-shell -p ssh-to-age --run "ssh-to-age -i '${keyfile}.pub'")"
+age_pub="$(ssh_pubkey_to_age "${keyfile}.pub")"
 
 cat <<EOF
 

scripts/secrets/rotate-admin-key.sh

@@ -0,0 +1,193 @@
+#!/usr/bin/env bash
+# Rotates the &admin sops age key: decrypts with a backed-up copy of the
+# key CURRENTLY trusted as &admin, replaces .sops.yaml's &admin entry with
+# a new key already present in this environment, and re-encrypts every
+# secrets/*.yaml for the new recipient set. After this runs, the old key
+# can no longer decrypt anything -- this is a real, one-way handoff of
+# trust, not a preview.
+#
+# This is the automation for the manual steps create-proxmox-resource.sh /
+# sync-host-keys.sh print when they bootstrap a brand-new, not-yet-trusted
+# age key on a machine that's never had admin access before:
+#
+#   scripts/secrets/rotate-admin-key.sh /path/to/backed-up/admin/keys.txt
+#
+# The backup key's *public* key must match .sops.yaml's current &admin
+# entry -- this script verifies that by deriving it, it doesn't just trust
+# the filename or take it on faith. The new key defaults to wherever sops
+# itself would already look ($SOPS_AGE_KEY_FILE, then the XDG default), so
+# the common case is just pointing this at the restored backup.
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+sops_yaml="${repo_root}/.sops.yaml"
+
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/sops-age.sh
+source "${repo_root}/scripts/lib/sops-age.sh"
+
+# sops resolves .sops.yaml by walking up from the process's cwd, not from
+# the target file's own path -- if this script were invoked from somewhere
+# other than the repo root (or from inside another checkout/worktree that
+# happens to have its own .sops.yaml), `sops updatekeys` would silently
+# re-encrypt against the WRONG config's recipient list instead of this
+# repo's. Pin cwd here so every sops/age call below is unambiguous
+# regardless of where the caller's shell started out.
+cd "$repo_root"
+
+usage() {
+  cat <<EOF
+Usage: $0 <path-to-backed-up-admin-key> [--new-key-file <path>] [--dry-run]
+
+  <path-to-backed-up-admin-key>  age identity file for the key CURRENTLY
+                                 trusted as &admin. Only ever read -- never
+                                 copied or modified.
+  --new-key-file <path>          age identity file for the key to promote
+                                 to &admin. Defaults to \$SOPS_AGE_KEY_FILE,
+                                 then
+                                 \${XDG_CONFIG_HOME:-\$HOME/.config}/sops/age/keys.txt
+                                 (sops/age's own default resolution order).
+  --dry-run                      Print what would change; touches nothing
+                                  (.sops.yaml untouched, no sops updatekeys
+                                  calls).
+EOF
+}
+
+dry_run=0
+new_key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
+args=()
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --dry-run)
+      dry_run=1
+      shift
+      ;;
+    --new-key-file)
+      new_key_file="${2:?--new-key-file requires a path}"
+      shift 2
+      ;;
+    -h | --help)
+      usage
+      exit 0
+      ;;
+    --*)
+      echo "Unknown option: $1" >&2
+      usage >&2
+      exit 1
+      ;;
+    *)
+      args+=("$1")
+      shift
+      ;;
+  esac
+done
+
+if [[ "${#args[@]}" -ne 1 ]]; then
+  usage >&2
+  exit 1
+fi
+backup_key="${args[0]}"
+
+[[ -s "$backup_key" ]] || { echo "ERROR: backup key file not found or empty: ${backup_key}" >&2; exit 1; }
+[[ -s "$new_key_file" ]] || { echo "ERROR: new key file not found or empty: ${new_key_file}" >&2; exit 1; }
+
+nix_extra_opts
+
+echo "==> Deriving public keys..."
+old_pub="$(age_pubkey_from_identity_file "$backup_key")"
+new_pub="$(age_pubkey_from_identity_file "$new_key_file")"
+echo "    backup (old admin) key: ${old_pub}"
+echo "    new admin key:          ${new_pub}"
+
+if [[ "$old_pub" == "$new_pub" ]]; then
+  echo "ERROR: backup key and new key are identical -- nothing to rotate." >&2
+  exit 1
+fi
+
+current_admin_pub="$(sops_yaml_admin_pubkey "$sops_yaml")"
+if [[ -z "$current_admin_pub" ]]; then
+  echo "ERROR: couldn't find a '&admin age1...' line in ${sops_yaml}." >&2
+  exit 1
+fi
+
+if [[ "$current_admin_pub" != "$old_pub" ]]; then
+  echo "ERROR: ${backup_key} doesn't match the current &admin key in .sops.yaml." >&2
+  echo "  .sops.yaml &admin: ${current_admin_pub}" >&2
+  echo "  backup key pubkey: ${old_pub}" >&2
+  echo "Wrong backup file, or .sops.yaml has already moved on -- not touching anything." >&2
+  exit 1
+fi
+
+mapfile -t secrets_files < <(find "${repo_root}/secrets" -maxdepth 1 -name '*.yaml' | sort)
+if [[ "${#secrets_files[@]}" -eq 0 ]]; then
+  echo "ERROR: no secrets/*.yaml files found under ${repo_root}/secrets." >&2
+  exit 1
+fi
+
+# sops_can_decrypt <key-file> <secrets-file>: used both to confirm the
+# backup key still works before touching anything, and again after
+# rotation to confirm the new key does too.
+sops_can_decrypt() {
+  local key_file="$1" secrets_file="$2"
+  SOPS_AGE_KEY_FILE="$key_file" nix-shell "${NIX_OPTS[@]}" -p sops --run \
+    "sops -d '${secrets_file}'" >/dev/null
+}
+
+echo "==> Confirming the backup key can actually decrypt..."
+if ! sops_can_decrypt "$backup_key" "${secrets_files[0]}"; then
+  echo "ERROR: backup key failed to decrypt $(basename "${secrets_files[0]}") -- aborting." >&2
+  exit 1
+fi
+echo "    OK: decrypted $(basename "${secrets_files[0]}")"
+
+if [[ "$dry_run" -eq 1 ]]; then
+  echo
+  echo "[dry-run] would replace .sops.yaml's &admin line:"
+  echo "[dry-run]   - ${current_admin_pub}"
+  echo "[dry-run]   + ${new_pub}"
+  echo "[dry-run] would then re-encrypt (sops updatekeys --yes) for the new recipient set:"
+  for f in "${secrets_files[@]}"; do
+    echo "[dry-run]   secrets/$(basename "$f")"
+  done
+  echo
+  echo "[dry-run] Nothing was changed. Re-run without --dry-run to apply this."
+  exit 0
+fi
+
+echo "==> Rotating .sops.yaml's &admin key..."
+sed -i "s|^  - &admin age1[a-z0-9]*|  - \&admin ${new_pub}|" "$sops_yaml"
+grep -qF "$new_pub" "$sops_yaml" || {
+  echo "ERROR: sed edit didn't take -- .sops.yaml left unchanged, check it by hand." >&2
+  exit 1
+}
+echo "    Updated."
+
+echo "==> Re-encrypting secrets/*.yaml for the new recipient set..."
+for f in "${secrets_files[@]}"; do
+  echo "==> $(basename "$f")"
+  sops_updatekeys "$f" "$backup_key"
+done
+
+echo "==> Verifying the new key can decrypt everything..."
+for f in "${secrets_files[@]}"; do
+  if ! sops_can_decrypt "$new_key_file" "$f"; then
+    echo "ERROR: new key failed to decrypt $(basename "$f") after rotation -- investigate before committing." >&2
+    exit 1
+  fi
+  echo "    OK: $(basename "$f")"
+done
+
+cat <<EOF
+
+Done. .sops.yaml's &admin key is now:
+  ${new_pub}
+
+The old key (${old_pub}) can no longer decrypt any secrets/*.yaml
+re-encrypted above.
+
+Review the diff, then commit:
+  git add .sops.yaml secrets/*.yaml
+  git commit -m "Rotate sops admin age key"
+EOF

scripts/secrets/sync-host-keys.sh

@@ -24,13 +24,21 @@
 # ever touches keys it itself manages.
 set -euo pipefail
 
-repo_root="$(cd "$(dirname "$0")/.." && pwd)"
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
 sops_yaml="${repo_root}/.sops.yaml"
 keydir="${repo_root}/host-keys"
 editor="${repo_root}/scripts/lib/sync-host-keys-edit-sops.py"
 
-# shellcheck source=env.sh
+# shellcheck source=../env.sh
 source "${repo_root}/scripts/env.sh"
+# shellcheck source=../lib/nix-eval.sh
+source "${repo_root}/scripts/lib/nix-eval.sh"
+# shellcheck source=../lib/ssh-host-keys.sh
+source "${repo_root}/scripts/lib/ssh-host-keys.sh"
+# shellcheck source=../lib/sops-age.sh
+source "${repo_root}/scripts/lib/sops-age.sh"
+# shellcheck source=../lib/confirm.sh
+source "${repo_root}/scripts/lib/confirm.sh"
 
 mkdir -p "$keydir"
 
@@ -74,7 +82,7 @@ ensure_admin_decrypt_key() {
     return
   fi
 
-  local key_file="${SOPS_AGE_KEY_FILE:-${XDG_CONFIG_HOME:-$HOME/.config}/sops/age/keys.txt}"
+  local key_file="$DEFAULT_SOPS_AGE_KEY_FILE"
 
   if [[ -s "$key_file" ]]; then
     echo "Found existing sops age key at ${key_file}."
@@ -93,7 +101,7 @@ ensure_admin_decrypt_key() {
   mkdir -p "$(dirname "$key_file")"
   nix-shell "${NIX_OPTS[@]}" -p age --run "age-keygen -o '${key_file}'" 2>&1 | grep -v "^Public key:" || true
   local new_pub
-  new_pub="$(nix-shell "${NIX_OPTS[@]}" -p age --run "age-keygen -y '${key_file}'")"
+  new_pub="$(age_pubkey_from_identity_file "$key_file")"
 
   cat <<EOF
 
@@ -118,12 +126,10 @@ EOF
 }
 
 discover_targets() {
-  nix eval --json --no-use-registries --no-accept-flake-config \
-    "${repo_root}#nixosConfigurations" --apply builtins.attrNames \
-  | jq -r '.[] | select(. != "installer")'
   # installer is the one nixosConfigurations target that doesn't import
   # sops-nix at all (see CLAUDE.md's "Security Notes" -- hardcoded login
   # password instead) -- config.sops.secrets doesn't exist for it.
+  list_flake_targets "$repo_root" | grep -v '^installer$'
 }
 
 locally_managed_hosts() {
@@ -159,7 +165,7 @@ queue_host_sync() {
       echo "[dry-run] ${host}: would generate host key"
     else
       echo "==> ${host}: generating host key"
-      nix-shell "${NIX_OPTS[@]}" -p openssh --run "ssh-keygen -t ed25519 -N '' -C '${host}' -f '${keyfile}'" >/dev/null
+      generate_host_ed25519_key "$host" "$keyfile"
     fi
   else
     echo "==> ${host}: host key already present"
@@ -170,7 +176,7 @@ queue_host_sync() {
     if [[ "$dry_run" -eq 1 ]]; then
       age_pub="dry-run-placeholder-not-a-real-key"
     else
-      age_pub="$(nix-shell "${NIX_OPTS[@]}" -p ssh-to-age --run "ssh-to-age -i '${keyfile}.pub'")"
+      age_pub="$(ssh_pubkey_to_age "${keyfile}.pub")"
     fi
     add_keys_json="$(jq --arg host "$host" --arg key "$age_pub" \
       '. + [{host: $host, age_key: $key}]' <<<"$add_keys_json")"
@@ -237,7 +243,7 @@ apply_edit_plan() {
       while IFS= read -r basename; do
         [[ -z "$basename" ]] && continue
         echo "==> secrets/${basename}"
-        nix-shell "${NIX_OPTS[@]}" -p sops --run "sops updatekeys --yes '${repo_root}/secrets/${basename}'"
+        sops_updatekeys "${repo_root}/secrets/${basename}"
       done <<<"$changed"
     fi
   fi
@@ -357,8 +363,7 @@ cmd_regenerate_all() {
   echo "image/tarball before it can decrypt secrets again."
 
   if [[ "$dry_run" -ne 1 ]]; then
-    read -rp "Type REGENERATE to confirm: " confirm
+    if ! confirm_typed "REGENERATE" "Type REGENERATE to confirm: "; then
-    if [[ "$confirm" != "REGENERATE" ]]; then
       echo "Cancelled."
       return
     fi

scripts/secrets/sync-nix-cache-host-key.sh

@@ -0,0 +1,110 @@
+#!/usr/bin/env bash
+# Detects and fixes drift between the ed25519 SSH host key nix-cache is
+# actually serving right now and vars.nixCacheHostKey (variables.nix) --
+# the value modules/nix-cache/remote-builder-client.nix bakes into every
+# client's declarative programs.ssh.knownHosts, and
+# scripts/proxmox/configure-nix-cache-client.sh hardcodes as its own
+# default for non-NixOS clients.
+#
+# This value has no automatic source of truth: nix-cache's host key is
+# generated once (first boot / container recreate) and never touches this
+# repo again unless someone remembers to update it by hand afterwards. It
+# drifted silently once already -- confirmed live: variables.nix recorded
+# a key that no longer matched what nix-cache actually presented, which
+# would fail every real client's SSH host-key verification for
+# distributed builds without ever producing an obvious error pointing
+# back here (a client just sees "Host key verification failed" against
+# *some* key, with no hint that the trusted value itself was stale).
+#
+# codex-maintenance.sh runs this in --check mode on every invocation so
+# that drift surfaces as a warning instead of a future debugging session.
+#
+# Usage:
+#   scripts/secrets/sync-nix-cache-host-key.sh [--check] [--dry-run] [--host <name>]
+#
+#   --check     Only report drift (exit 1 if found, 2 if nix-cache is
+#               unreachable); never writes. For CI/maintenance use.
+#   --dry-run   Show what would change; never writes.
+#   --host      Override the hostname to scan (default: variables.nix's
+#               nixCacheHost / env.sh's NIX_CACHE_HOST).
+set -euo pipefail
+
+repo_root="$(cd "$(dirname "$0")/../.." && pwd)"
+variables_nix="${repo_root}/variables.nix"
+client_script="${repo_root}/scripts/proxmox/configure-nix-cache-client.sh"
+
+# shellcheck source=../env.sh
+source "${repo_root}/scripts/env.sh"
+
+check_only=0
+dry_run=0
+host="${NIX_CACHE_HOST}"
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --check) check_only=1; shift ;;
+    --dry-run) dry_run=1; shift ;;
+    --host)
+      host="${2:?--host requires a hostname}"
+      shift 2
+      ;;
+    -h|--help)
+      sed -n '2,23p' "$0"
+      exit 0
+      ;;
+    *)
+      echo "ERROR: unknown argument: $1" >&2
+      exit 1
+      ;;
+  esac
+done
+
+current_value="$(grep -oE 'nixCacheHostKey = "[^"]+"' "$variables_nix" | sed -E 's/nixCacheHostKey = "(.*)"/\1/')"
+if [[ -z "$current_value" ]]; then
+  echo "ERROR: couldn't find nixCacheHostKey in $variables_nix" >&2
+  exit 1
+fi
+current_type_blob="$(awk '{print $1, $2}' <<<"$current_value")"
+current_label="$(awk '{print $3}' <<<"$current_value")"
+
+echo "Scanning ${host} for its current ed25519 SSH host key..."
+nix_extra_opts
+scanned="$(nix-shell "${NIX_OPTS[@]}" -p openssh --run "ssh-keyscan -t ed25519 -T 5 '${host}'" 2>/dev/null | grep -v '^#' | head -1 || true)"
+if [[ -z "$scanned" ]]; then
+  echo "ERROR: couldn't reach ${host} (or got no ed25519 host key back) via ssh-keyscan." >&2
+  exit 2
+fi
+scanned_type_blob="$(awk '{print $2, $3}' <<<"$scanned")"
+
+if [[ "$current_type_blob" == "$scanned_type_blob" ]]; then
+  echo "Up to date: ${host}'s host key matches variables.nix's nixCacheHostKey."
+  exit 0
+fi
+
+echo "DRIFT DETECTED:"
+echo "  variables.nix has: $current_type_blob"
+echo "  ${host} is now:    $scanned_type_blob"
+
+if [[ "$check_only" -eq 1 ]]; then
+  echo
+  echo "Run 'scripts/secrets/sync-nix-cache-host-key.sh' (no flags) to fix." >&2
+  exit 1
+fi
+
+new_value="${scanned_type_blob} ${current_label}"
+
+if [[ "$dry_run" -eq 1 ]]; then
+  echo "(--dry-run: would update variables.nix and ${client_script##*/} to:)"
+  echo "  $new_value"
+  exit 0
+fi
+
+sed -i "s|nixCacheHostKey = \"[^\"]*\"|nixCacheHostKey = \"${new_value}\"|" "$variables_nix"
+sed -i "s|NIX_CACHE_HOST_KEY:=[^}]*}|NIX_CACHE_HOST_KEY:=${new_value}}|" "$client_script"
+
+echo "Updated variables.nix and ${client_script##*/} to:"
+echo "  $new_value"
+echo
+echo "This only takes effect on already-deployed NixOS clients after their"
+echo "next rebuild (programs.ssh.knownHosts is declarative). Review with"
+echo "'git diff', then run 'bash scripts/codex-maintenance.sh' before committing."

secrets/common.yaml

@@ -5,76 +5,130 @@ sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBpWjNSdEdZbUUzamswa08w
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBIakJkWDQ2TjVIS1Q1UlRJ
-            aCtzSHB0bFVZMnYxTkpuM1psdVYzWW55SzMwCkliMWVOUlBqRG5wOGZjQVg4MkFz
+            elVLNmhEVUpMNjROWmN6VC8wTnZzeWhLb0hFCmxmTXp3ZVdQMUhDeGlscThSdFhP
-            NEVkMXdkTjhWRlZmVGlzZElid2pUMXMKLS0tIGtHUmRCNXNhVmloUHYzQnE5YlBS
+            eWNZSkFpeEg0cUUxbGFyQWIrTkJkc0EKLS0tIGRBTHdaZ2d5eHhxd3BtWVBLbFlo
-            YnVSQjJlT3JnQ1RNMm9xV2xKOGRZUDAKc4VTl9NEI9Rv8+4J3JTeHTt2h8Dr2IJv
+            OVJlYnQ0N09qWFp2TmtXb2E0Wkk2bzQKTxA4rfkF3qlGpDqaZF/J9tgTx1UZ7ZFt
-            tfvoNJQM/w6RAJWNTkaDmzZa9OnUW+grDlBQKlDuAnr6fZmuNTH2hQ==
+            W1KevMq/Klnkjb9XDuTEx7zgrjILoViVspe6eGI14myBNYtAP4nLSA==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age10nd382a9klsn2mrs60emdtsxe43pht3a0m9p29phfrhy0wfyt3vsq9r667
+          recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBOR25UN1c0aE5SYWphbU0y
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBUWXYyUG5UdHdFa2NDZmtt
-            SHRTZ1B0WC9NU3Z5VHpzTXpLSUxHTDI1ZFE0CnFpYUN1eGZQejJMblZPd1ROeUth
+            ZG1GSmxVbTg5Qnh4UGxJaitmTmFqK2J1cUV3CmdPSU5GTC9hWkROTkJzMk5Tcmpw
-            dklZYVVNa1ZNZ1d4dW9vMCsvQWp1RkEKLS0tIERxakx5L0JrQitib1EyNDRMbDQ5
+            ODJzdlIvNkp0ZXdZNlRlUHBkOGVoR1kKLS0tIGsvUWxpU2hkanFNaExJWGozMTJL
-            Z3hDWUFEazdxczVhaHJYK3VZeEJSSDgKkw9T4ZuT+VHIF4WopqRHt8vW30kOysJ3
+            bndPNkpQNktmQVNKNEhGOEtHSlRBRXMK9rr6NHf3H91GIqTmckjD1eV94FW1vk9G
-            vOq6EZ3Fqkgmoxm69Zp2gFnuE9GZIBy3VPQVLU2k6dZGJ3IvmLYeBA==
+            h2KauyebWPyBe8hsCExiPd45ZGqKF0g8pEtWUzonMq9NU/MNVL8YVQ==
             -----END AGE ENCRYPTED FILE-----
           recipient: age19gfn2yedg76dmztm4hncr7vf3r3c9j0qpt4rap7y7gersjk4m3ks2lhd0e
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA0THJzMFBTTCtDMWRmZ25M
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBXdnpGR2ZnaFRSUUNlOUVy
-            dU55OVhBb0trWWRUNlArTnEzRjhiYngvRENNCjF4d0M5NlYyQW50TTdMRXpuUjRr
+            ME9pWkFJRTl6ampuZTR0QlQ2TUVEVHV3dkRFCmxML1NSV2dwanRPK3AySDJiUU9P
-            M1NwV05JOHV6T2cxT2FheVpuZ0w2T0kKLS0tIFBxdlVpVEoxOUpSWjk1ejRsK1NM
+            a2VKZ09EaktYU2xvWWpESWtrU3oxalEKLS0tIEt1aWxuNmlaV3l1OGNqS2RtMmhm
-            V1UwTU1scG91L2FIemtwSW5JbFlmeG8K/1WIlaIidy3x3ptoRpS/DG88064LQ6Mq
+            Rk9SUEpBaXY0RG9uMk53ejdJdVZ4NDQKfn4paPsHrfU3Ki2AgPBB8aLBbmD2yh1O
-            GbfB0jfq5PILDQMMuZu5oIBY31SxwnhZ02Ns7gA67kgNIRSCmk9WyQ==
+            9rDxv/6xSsDXNTquP11smPOKsRG7mDMDHVByn6GieZrpSxUf9vu3Iw==
             -----END AGE ENCRYPTED FILE-----
           recipient: age1ll6hj5ggruetgjwjfnplpn5xtq35uhlcdflksx3xmnjm6s3uad9sz70jkf
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBmRURQVGw1a1E1MkIzV2pa
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArNHZpMDV5a2JCN1NxY2hF
-            RG5HSkM0c0huUGVWcnFZOGlacGlGOHFMTVFrCm5OS09HRFc3TGVUYmtzTStxL0Q5
+            MWxtNUNVQXp6K3lWYndTRU85Wjh4YlN3UFFrCnNZbHA2Z2RUSmxITm4yeU9rYnV0
-            N2hRMEcxUE9MTmZXL0wvME5EZXF1Z00KLS0tIHdHMVVHcTZzMmdXU0s4QlVqSS9Y
+            TTFkZUczcTZLU2pJRDQ3TVl5ZGErWDgKLS0tIDJGbzZZNjQ2RXUzRmUwKzdiUHlK
-            ZUVmcWhPaURIUFJGR0V4bUZwKzM1bm8KlvGMNEClbLlfvJqNQHhd0dI4ihShLChF
+            TEU5VERpZ1p3bU1KcnEvRDRCSVNqT2MKQPfu0lskXaEAYgecmN1a0kPHF+fGEm7R
-            GI/fydgrBruw3Otv6KLZu3CBC7iNcKlvZxz+YGD2qbicmyQ5hAhDSQ==
+            wiY7TFNLeXM5aJqEnKARtOotJDetI+9VNssTT21X/Qaik6fqgM+b1A==
             -----END AGE ENCRYPTED FILE-----
           recipient: age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA5bWpFenBlQldna3RhSFpr
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBOUlp5MmcvSFRnaVdWZ1g0
-            bEJBaHJDMzM3OHlqTmozcWU0VDM1bTFUWFZzCnZtNHZjZ1U1RzNkUlBHZFozWXdt
+            NmwvS3pGa1JCd0RuQnFMeU5wZDZYK0NQR1FJClF0Z0VENThtTzZ1OUtmUjdDenV4
-            VVkxQjMvTDJtbFZnclpkUEd4TEVmNTAKLS0tIFlhV2ZSSzJLRVNoMmFyVktDOElR
+            Mko0T2o4UzVubVRCdUlCMERyV2w5WmcKLS0tIGZUallPeUhXUGtVMmNIWWRkaFVT
-            YUxqZUFoY1ZWeGlldGplMjVQa1A5aUUKWelY6yO7Mr6dRvj4MVMbq/Z9JgrAnahz
+            TVNVTjhiQzJkdlVQN3p1bnR1aUYyQmcKVnqbCuaSYEA7stk1MyfCzRbqt7EL+E5/
-            BDhHqObzJrOCtfDCTWiYuP+0yvIFWItMWhGSMw9MwwivvwnrEa+ZuQ==
+            jgxraiFmaZqjDI5mxG/e7eFdXfv53AtKzZm92TlzvV+4bfidj5SvYw==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age1qz9d4ka4xgexujyd247s7lp737sulp5fhxl5d65fj2ykvc4j4edqrsdks8
+          recipient: age1jy444f9d9stygj4p3w9kh54cqcfr654tvr75tdvee5cxsgtdtc9q3v60ep
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBiK2hKb2VaVnoyaEVYUHZZ
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCWTdCWHhTamI1VHpvUzZ3
-            OWVUSGtONGs5dEljTjJQdlhEcjNjdjViT2pVCkpaOHVZMlpXOFRveVlMeXZqWmoz
+            M2VnV3NFZTcrc2Jzazc0V3NsMDQ4RmtYZ0ZrCmVhV0pweTVLdzBLRnlJZURwNXVT
-            ZHJRQTR2dmJQSEozeTRGMEdUdFlmZ2MKLS0tIERWS1RVdW1jQytBZzlkb3puNjhH
+            YzN1aHZyTmRqc0dtYjJWekRaODZoR3MKLS0tIHZPV2ppSTVwb2VHWStRY0pKSTZ5
-            ZjdlZmtzNXVOQ25DeCthUzhRRm1MT2cKaxc7zGm57iJFSeYc2IPqF4Eaxa44nR37
+            MXVFSE1odzRMeW9LQjVQUytBTWhHUDAK+UUowhIQ3w5O4Y/m9Pq41X2l0DZQfzOT
-            pWZw+erG4F9AAZ2F047q+oLKe0B8FLSF54IbcXdQhitgGNR7B2HVeA==
+            itFkXJRnvUmkCxWYRDFJjQ6FpHHaNDqs0BlQZ5QZ+chzcKuUAG+uEg==
             -----END AGE ENCRYPTED FILE-----
           recipient: age120whqj96g26lsgy4udvgsn8dc9lumh8jeu3a564fx79rjr5lxffqmrljuu
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA1ekhUTG5VOFErL3pFeWZM
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB2MEZxZTI3Y0xWSDdzanRC
-            RG9NVnN6NFl3bzlFeTQzdHFtZmhwem04alQ0ClpJRStObERMZ0w2V0NhR1FSeW96
+            RytNV2x0UkY0SnRzVnR0eFNvaDRJeUtpZjBjCko2T09qSTJsQm51aW9pR3JUbkRm
-            M1d2V2NjUkUrLzN2ZVNSbGY4bll5WmsKLS0tIC94dVFQcXJ6d3pLU0VHNEFGR0ls
+            NWRXODg0L08xdGNLdCtORXA1VWRteTAKLS0tIC90bkZEd2pOYWFCeGg3UW54TWxH
-            a1Q2UmNuSjVMNG5XZGZKV1VmNHFPQXcKQJrZGw/9fPnXeFZ4omrkEgrzwplhwvRW
+            Y1liQWVWS0t4WXBROENGNnpDVUpxRVUK57qCQ0l5Gw1ZqM50XSBNwVlXkue3QOT/
-            i0FXuepoU353sR7enyL34qPoOdm05ivowuPKNzkq8D4i5AF6vGv+YA==
+            BPmPFkMNpVIcUDENj+mJAS5GHuEm1MkZcMi/wN9Hp2KE05ZywPR2Zg==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age164px2a8e48ptsf9ngtan38aa6jls4jdl26mzrgzf6sn3vcvt49hqjrgr8w
+          recipient: age1xjst4frdh0th6q8m7p7u9g5af7ty5jqeum0p6z8a52a9q7st7ewqw8yl9j
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBoZ2lHM2RBQ3lUK216dkcr
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBCaGhvbE9EU1dMZitXYlZk
-            Y3RrcXR3QTdFVjJRWlhpQWVFQ1cyZWNabkRFClAwRi9PSHF5ZWFSUzJuRXF3bU1R
+            NVBEYWxHbzAwQ1FUU2JidjJPZDZLVDZLODI4CjYxaG9OSlVOeGQ5SmlGNWEzNG1n
-            b0U5TFRZaFdmR1NMS3RRT3E3M2hUdE0KLS0tIEtrUy8ydkNyVHBiOVR6WEdjV2VN
+            WU9PRVpVRk9rd1BvWDNnMFcrZFNJZDAKLS0tIEUzV0E3OGE5cWM4MjBwTk9Mb3Np
-            NVJHUVgwRkhxcmlwcFkrRlFwTEF6YVkKzXyJk0UnmUsvb+NzNVcf/gf7OEEt3P/K
+            cDJQZGNqNXlySjRLcWF4R0V0ZS9DVFEKS0CmXOfJ1qpUF24EJT6F5/6xzR7h593O
-            OIGxDrGfs/zNQgeKXNbQlQ4p4jOaybG8aCmX+A4qTk6/I8yY8LTJWg==
+            mLiMdOCeFYWlTtBwrD1dkweAzStiHlzTVEq3w9BFvAsr5x/NbQJUJA==
             -----END AGE ENCRYPTED FILE-----
           recipient: age10at8862478urh0eeuwh8hzln6ck78jgwtztgxatwqlzwagg77y5snm4xzg
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAzOUxYa2xOYlVYd1lWclR1
+            bDJFTEg1SjBhNjhFT0IwY0ZxZFRFTzRUVlhZCmpwL1VBMElZNzV3UkFCV0FWb3Jr
+            SlN2dTNmOFRXeGJVTFgwdjA4SmdSQXMKLS0tIHZOdjFzalRkL2N5eU1iSDkzbHYw
+            NEU3VWxBNE9NZy9hVFJwM0VnQ2RIbjQKc62J04UtVjqiU7p7GueMicdCDRTvM9zY
+            IPOJSwTCatRMWeuBJIsRNkbyOLeSAesQdfAXL5GoAE8mBtBdhJKaLA==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1ezk9x53zt8kcnscdm80jcyf0xq97vndv7jsn3rl8cc0cwm2jmpmq372dzs
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB1NkppWjNXRDlsVXZ6b1ND
+            OExFRXVOcXVSWmZXemNoK09EcXBHZ0JMYnd3CjlsaEM4MjdJT1lBZGFCZTNISHZV
+            MjBRTUlTVkZBQitFc1I3ekRLN0RtYzQKLS0tIC9oelk1TTRzeFNpbWQzL0pObXJq
+            eWxHbkF3anVPRFgyQ0kvSlJqQTdLQW8KLfZ+UIzas43ROGO51KKOmy58R2tl3jwh
+            M+1WXB8vIXA7DLQ6vMbzMPMhBnJ4kbZgRtxELg7fzSLQStLvkY+O9A==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1fxxzpnfse8nd9wz78ht3m0plrmraacf4cpga0pe8fm2tdnqcgy8q7qsyvp
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBWVm5uZU43cFFLcC8wVkZO
+            NmlOMmlocGpwbXFkUFlCMEl5Tkx1QWJIdVRjCnFBTzdWT3NaM0N2eGlCbDV2NUU3
+            Z3FnYktsZ3NHT3Y0b2hOd0xmRjlLMjgKLS0tIFBQVXVDeHkyeVNNek5CSldSMFlY
+            a0Q5bHVlRHUxMWduMCtLRjdnMUw5RG8KDJX8I21+bUpkJ5wnX+kGhsSa8mKqsR25
+            iNdOtVtb2WRxIAgyjR72yp1tLMrop9NkZN68MGvd/LsNM+6simyosQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age190htw7prp4vln076dxjx3gxxaq06h0zl0te7cqgpx79vl3lhkaes8suy05
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBHcmIxZVc4aGRmNEhSY3Iv
+            YXhzLzduWFdzVVlKZTR6WExzcDNtSWQza0FjCmlsZDVJUWpqY0pRSktQeGk2SlAy
+            cjZXL0JCVFRtQXpHNkNIejhyTnVtWjgKLS0tIHBSZ1JyMFBJVWZ3VWFLOUt5OHd6
+            YUI4ODhHc1I2UHVRQ0diSnhsSUhDelEK3hBBX1+Uwe/MusLqmt4oAy7Z6jOU96Cd
+            7zTe8YyLc0/DUDsyuFZ7a68riO9/My+zrFllwtKe/JPmPHLY0+3Pnw==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1ukpqxzl44mnjpy5r96sfuc5sqzm47u4k8ujjh5qdgy6jvl9uqgpspymqfk
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBZSE53Yy9FOHNpeVFtTmF1
+            UUExbzJlZktxMGR3Ukora3RpbVN2THlyVjNJCnFpWVEyK2U1N1diOWZQWm5Bb1lD
+            djV0U3QxamRJY3BRN3hBTmZ4SVRiV0UKLS0tIFU2Q0o1UTRjaEFaSTRVTm5MVW5T
+            QXdEbVB0Y3YwM3R5dGp5d1oxeUxHNGcKRj5hNLlXtZoT3IwXHTxaReJLu8k133n/
+            ZoCtv470LPL1M/kTjdPc/nWMgYOHDKkO90gr3WILfHg8idkVuCLT2Q==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age15kh7akxlx7zn00tey79rq2g8lgs4j5y77rcnyfxrxap8ckfu0a9sqvtdhh
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBQazFqSWpaVGtkNFhPU3A5
+            cE1oVXEvSU5RNnY5NU9mbFhGOFQycVFuL1U4CnNwRnVkYmxCNFZzNVZvM2N5eVN0
+            clNjUWY4RHZxbVNsMFlFSnZKcmI3dm8KLS0tIFBDZTRuRlprdzdVT1ZHejNsNDBJ
+            OUVjclpPSjl0RGtLVlZRSkpFeG02KzAKt0rcJunZppojjijrjbXsztLwRD9pgWRb
+            jYsn7dCvWGFZGVgeyxqfL0jfYNz6dW0yecRE/gbP5hIooxbcPcxfag==
+            -----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]
     unencrypted_suffix: _unencrypted

secrets/gui.yaml

@@ -0,0 +1,34 @@
+wifi-password: ENC[AES256_GCM,data:SZQPtU6PYHbf9o83wq3KTupx,iv:FxO68Pn/+N58r/OPLfkAMYPFpP8TYxszMniFd/01E38=,tag:jwxaY6zDEcO5r9OWSfvUyw==,type:str]
+sops:
+    age:
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBrWFpRSURBR0gvRzVIMElk
+            ZlJGZlJvc3lFOVJIZ29YbFp3akFCNG42TWkwCjhNM0J6cjIwRXBzc3VWNVpZSGdL
+            Q1M1bm90OE1tTG9GbUxvS1dvRkZ0UGsKLS0tIE43L1dnbWhQOUhhYjg5bEIvZkVD
+            Zkh1NDhvZjlDc2c0cUZUYVRLdEozS2sKU/r6JnEnUs2WPj/J724B+lgiV84iteZa
+            uMlhgnwYJFLkH7ZyydQqjYcHL7xEInr0taYJN+M0nZIsZTvzAEi7iw==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBXZmYrVTZxWW1QKzhLWThX
+            UFAwSEhId24yMitmVk1kT215OGdqbGp4akFjCjRzN2dkTURXS0wzbzhYL0YxRW41
+            TWJ3UExXaHNhSUxaYkVsMFNCekZHZDgKLS0tIGQrSWNzalhCbGJZdkxvT1N5ZWlo
+            a0l0Nk9DY1BKYU9ReWovaHJ0Z2NyWGcKFoIYS1M4EbR6H6QG3Wjv2ZdX3r2W8zKp
+            S9f578O5ZLh2OWaawcSb0oecZJykT9pgudVcuKRunzZN7NQvFxBRnQ==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age190htw7prp4vln076dxjx3gxxaq06h0zl0te7cqgpx79vl3lhkaes8suy05
+        - enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBlWnpPUk10YW82TVRzbk80
+            WHJqbXVVSUFrSTVjMEdqUTdSQWwvdG1TcW1nClQ5T0E0akFtSlFGdC9WaU1LbGkw
+            allOSjJ2SjQ0MkVMcVNtdzN3cW1hVzgKLS0tIERlQ2l3NitPQndERTYrNVA3ajF0
+            bCtnYzhHcnZkalRNK1BHbjdIS2JLNmcK5RwFzeaK1KafO4cAtdFh5Tnz1lpZbj1Q
+            aeMmTGMkxJYVGzXKS6SRspVT3MvY4Fvay8B0MezjG5Y5HKNIv22Vog==
+            -----END AGE ENCRYPTED FILE-----
+          recipient: age1ehkswwz2pqaz4svzh7ela5tdnssl8kn6d4vwwxd6zwg8exfpd43syyrrjp
+    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
+    version: 3.13.2

secrets/nix-cache.yaml

@@ -4,31 +4,31 @@ sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBDbHd1Y1dpa2ZiQ2E1bXRP
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBPWE1HTUhiSUp5ZEUwWEpI
-            SnkrWHI0V2U1eGFKY0RZamZQQjluS0hGeENZCmduUFQyd1Q5RkZGMGFoenJhNmZh
+            bGpkZlBIMUo5ZlYrQ09SN3Q1a0ZkQ0ZnOEhVCnJPNEZQenVWWGZiODlzQzNEc1Zq
-            VmZ2OStNaFpJejFxQ2JUZXFpNThaMncKLS0tIEhJdGdQeXEzb25Nbk5YZktCWVUz
+            c3l4OWZJTElJc2Y2UE15OGtEUzhyY1EKLS0tIHNJUStyWnlQWjZBbEZjQ3UwdUpz
-            NUJDUWRoTkd5R2pFblZjS0NSbVR5dkkKDYeW+zRpha04/CasFM91K6v1PpkNGHRu
+            ZndoUDR6bisrNGJCUHk3TGI4bTZaMFUK87fFsm9ne9s+PK2pcwtrDjqyGBss2r2E
-            qAoKs9KSg9VxS7ya8RuLmylKRdpPkupm/8SXIJvQuCXp5LWmNJ4zkA==
+            8lhqoeiKZ2j96z8kP/7ChzovwTCmqdcmAQuyNQD+ZAFijseipSvfbQ==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age10nd382a9klsn2mrs60emdtsxe43pht3a0m9p29phfrhy0wfyt3vsq9r667
+          recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4UktiUUdmd092bnZMdFMz
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBUYi9SRFFGV3Z6cFd2Znk5
-            Q05xVlhnNzhPZUY4TjF5bjRCbklacTdJd1RBCnJ4bEVMaWRLZExIUFVEUDBXTnlV
+            b2FLbWtzTllJMDBUaGk0NTViOTNBa2hQclVZClZHKzNhbGVjQUJhWkFWdTFBMG5a
-            MDU4WUk5VlJjdlhVUVpzZXlnWHhqTjQKLS0tIE9iclhGVElPcU9OLzF0bEVjMjVp
+            cUFJdUdyVG5HQXJRRnJId3hqRTN2cXMKLS0tIEFMRjh3WE1ON0U2TTNTZ3hxMTR4
-            YzlQTGFYZEhLdTk3N3ZramVjVGRXREUKjOjqO/jX5iEKN43WiJ8qS/1mDfxdj8uO
+            ZGRlemlIbDZKeExmVHROc3Eyak5DdzQKaLwIVDi6BN4cxpVxJoqTYvJETPOp4thc
-            K7Yyc/Yj0qMvGwLNzphjmbT29P7dXk4Ht4TedqCd+8DfhpOgLVIaSA==
+            l9uVMvIGuEsEZgDsvShw1dYLljd+uGy/A+dXbcxIUCP/mmPkwmd1Pw==
             -----END AGE ENCRYPTED FILE-----
           recipient: age120le4a5l8dh3lyfgvmj3d9ksmej6ajs5mer5y7r0vfg3x9fn69dqf8xgzu
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBjaXpvQU9yRUc3ektPMmU5
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSArOWovSW9DeFpxL0VDUDQ3
-            Q0xLWU9mYXVOeTVBNGNsZzJPa1lkVlRUZHlvClhoSVV6YjB1Q3pTTzVvNFlNYkU4
+            SHUwTzJVZUtPV01ZRkdCUXZGL2lTRCtCNFNnCjBSNExqRW5mTEN5SFVucHJHSzZt
-            Y2RrbFk5SUFKSDVjeFU0Wlc2aGFUMFUKLS0tIDlVeXM4WWRUakg4Zk5mcjdJL3VC
+            cDlNc3BjY3M1c1k1Z2tkVEg4R1pacGsKLS0tIEFWbHNKZW0vbVh1Y2VhQW93OUwx
-            S1k5eFBpVnREQlZwYllpeTNhWW5GS1EKi2sMwyJJ0D8acjCZmxlcwdU1sglBuxR7
+            MWV0eW9sOXdQd0l2ZjlWOEVVc1dwcTgK2s4p9xoNkawH2OkGsl80bNIo3ad5vn4W
-            2SEMsctdGC+5E3ilPXvPpZ5RONZHbXxn6kQRBlBv6AJERpGDzsfgfA==
+            Z2w+jwppSoUmbQnD3WFbLmSSxmuobmU8HILwElv6SZu+KE3aspF6XA==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age164px2a8e48ptsf9ngtan38aa6jls4jdl26mzrgzf6sn3vcvt49hqjrgr8w
+          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]
     unencrypted_suffix: _unencrypted

secrets/server.yaml

@@ -3,22 +3,40 @@ sops:
     age:
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBxaFZURjAxMGRJZEJ5MW1x
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBaYU9HR0lETDhkYXR5NWlj
-            ZjVwWEQrQlkwNmRibVNiL2RpTTFLeUVDQ3hRCkVIamVnZkM1MnlueloxMHVFQnBF
+            L0diSE5JQU9KWjRoU3hrVjdqZ2tPNUtOdFZvCjdUVGNFbDVYa3pVSC9ZWVNORER4
-            RjV2bnUrZUo4WGZJTmR4Y0xITkxRUkUKLS0tIGlJdVQ5MFBubVhxRUVMWW0wSGpP
+            QWozUlhoSEtjTk9IRlM3VkZoYlc1RTAKLS0tIDlHS01WVWlOMWFEQU5GTVRLZVhV
-            UGdKNUNPYW9nek1UZ0tWbXd3QVNUNDgKIHOiKelITQdH5R4Nc3WF7mzz15D1f9on
+            VTcwekhrRHB3SlVYT2MzOW5GbE52dkkKKCWehPhpdGapdyzpll20NJUcZwvW/7X8
-            VaTdr5qkf8LNNvPI0fxsXA9is5cqeg+KbDRHtUumEhNp6Zrf8zWBkw==
+            KQ1EqAgI2fewnbwuIDYCleN0b0SLJNUeSV/tFKDDoTMnHWCdeD4ECg==
             -----END AGE ENCRYPTED FILE-----
-          recipient: age10nd382a9klsn2mrs60emdtsxe43pht3a0m9p29phfrhy0wfyt3vsq9r667
+          recipient: age1njap586hc0q43kr03g6c8eqhdsmk8zcafkl3f83xwlc2gqhlmfgs4tmwad
         - enc: |
             -----BEGIN AGE ENCRYPTED FILE-----
-            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSA3N0hvV01naytDSWVwK1B1
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSB4YndybFBTQ2p4SGZ4SDJs
-            MXM1ZkdpaVc2Q3FPV2VBcC83WmcvSjdGUGgwClJGSXZ6YW5JeFlValNJbjVhK29u
+            a2p0eFRQOVVWcGd2a25ESW9ESGx1RWw0Zno4CnhpVVh3cGI5UjY0YmFINFFPMTh4
-            bUFqN2dRQTI4ZkwyeXNWYk5JeWVJRXcKLS0tIDlMMkNBUnNUSTJwVVFmc2dlcEZS
+            b1B5SjJ3NTNvUE1QUmJjVFozY1dYS2MKLS0tIC9HZGNpOFZhZGNFZGt5blJuZXVV
-            VGQ1VHR2dXB0M3RsalppVWxiUUROM0UKZM/4QDTam3LDTzjnDs41Ije50R7Q7GC4
+            SXpkRzV4d2ppV3ZQZSt1dmxYNGVFMUEKmSe9dkrmkND81Hw2/ATAmFvcmhk1tUC1
-            IZbUZjs72rBzY8IkJDbN9JidadEc4NAtMOJwXiJbpZGiCBNfc8+SXw==
+            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

variables.nix

@@ -26,7 +26,7 @@
   # 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 AAAAC3NzaC1lZDI1NTE5AAAAIHrMKZlIGUd3pH9G3AqbsruqUGjxIXMAZw52u9MwiBCn lxc-nix-cache";
+  nixCacheHostKey = "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPeWgMsdaiz4axT/deFc1+0B5bN+GX/NOeW9bbQ0c/IT lxc-nix-cache";
 
   # 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
@@ -38,12 +38,27 @@
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIIGtOWOCS+ImHc7NehguoyD7PbonGosKMZqc9+QR3v/h root@nixos"
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIHxXTQxFnArK5HXG7czeoybZebCGfxpUdusJkPn+BCSp root@server"
     "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAICMJhrfFayLBG+gWtO6oAvgambw5nWWgztiTFEaaaVRH debian@surface"
+    "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIJEj26SL/emsVjW2YhRucJVp2kTz8WgcEQgjBEBLRikk root@claude"
   ];
 
   # 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";
 
+  # 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.
+  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".
+  guiRootDisk1 = "/dev/sda";
+  guiRootDisk2 = "/dev/sdb";
+
   # System
   timeZone = "Australia/Brisbane";
 
@@ -137,6 +152,14 @@
     # shortcuts on the gui build type (hosts/nixos/home.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.
+    torRelayOrPort = 9001;
   };
 
   # .raw disk image size for every proxmox-* host's standalone Disko image