# felhom-agent sudoers allowlist — the NARROW host-root surface (slice 5 Phase B, doc 03 §3/§7).
#
# Install as a drop-in: /etc/sudoers.d/felhom-agent (mode 0440, root:root), validated with
# `visudo -cf`. The agent runs as the non-root `felhom-agent` service user and shells out via
# `sudo -n` with FIXED argument vectors (no shell). The fine-grained validation is done IN
# the agent BEFORE exec (internal/storage/validate.go): UUIDs against a strict hex regex,
# mount paths confined+traversal-checked, SMART devices whitelisted to raw disks, LVM names
# charset-checked. These sudoers wildcards are the COARSE allowlist; the agent is the fine
# gate, so a wildcard can never be abused by a value the agent didn't already validate.
#
# Binary paths MUST match the agent config (privileged.systemctl/install/smartctl/lvs). Adjust
# for your distro (Debian/PVE shown). A missing/declined entry degrades the agent with a
# warning (SMART→UNKNOWN, mount→logged error), it does not crash.

Cmnd_Alias FELHOM_MOUNT = \
  /usr/bin/install -o root -g root -m 0644 -- /var/lib/felhom-agent/units/* /etc/systemd/system/*.mount, \
  /usr/bin/systemctl daemon-reload, \
  /usr/bin/systemctl enable --now -- *.mount, \
  /usr/bin/systemctl disable -- *.mount, \
  /usr/bin/systemctl stop -- *.mount

Cmnd_Alias FELHOM_DISK = \
  /usr/sbin/smartctl -a -j /dev/sd[a-z]*, \
  /usr/sbin/smartctl -a -j /dev/nvme[0-9]*n[0-9]*, \
  /usr/sbin/smartctl -a -j /dev/vd[a-z]*, \
  /usr/sbin/smartctl -a -j /dev/hd[a-z]*, \
  /usr/sbin/lvs --reportformat json --units b -o lv_name\,data_percent\,metadata_percent -- *

# Provisioning back-half (slice 8A, doc 03 §6): populate a guest's bootstrap config mount
# host-side (internal/provision). These are host-root ops the API token cannot do — a bind mount
# is root@pam-only, and the chown maps the 0600 bootstrap.json to the unprivileged-LXC guest-root
# (uid/gid 100000, spike gotcha 1). The host dir is AGENT-OWNED state under /var/lib/felhom-agent/
# (the wildcard only ever names a path the agent itself created), and the bootstrap file the agent
# writes there is the only thing these touch. ':' is escaped per sudoers grammar.
Cmnd_Alias FELHOM_PROVISION = \
  /usr/bin/chown -R 100000\:100000 /var/lib/felhom-agent/guests/*, \
  /usr/sbin/pct set [0-9]* -mp[0-9]* /var/lib/felhom-agent/guests/*, \
  /usr/sbin/pct set [0-9]* -onboot 1

# Disk inspection + format (slice 8C). blkid/lsblk read the device's data-bearing evidence (the
# agent decides data-bearing-ness from THIS, never the caller's claim); mkfs.* formats a device the
# agent already classified blank (a data-bearing format is refused pending an operator signature).
# The agent fine-validates the device path (ValidateBlockDevice: raw disk / partition under /dev
# only) + fstype before any exec — the wildcard is the coarse allowlist, the agent is the fine gate.
Cmnd_Alias FELHOM_FORMAT = \
  /usr/sbin/blkid -p -o export /dev/*, \
  /usr/bin/lsblk -J -o NAME\,FSTYPE\,PTTYPE\,MOUNTPOINT /dev/*, \
  /usr/sbin/mkfs.ext4 -F /dev/*, \
  /usr/sbin/mkfs.xfs -f /dev/*

# LAN split-horizon resolver (internal/lanresolver): the agent manages a host-side dnsmasq that
# answers *.<customer-domain> with each guest's live LAN IP. install only ever writes felhom-*.conf
# drop-ins (from agent-written /tmp temp files); the two `pct exec` reads are FIXED command vectors
# (the guest's eth0 IPv4 + the controller's pulled controller.yaml for the domain) — NOT a general
# `pct exec`. systemctl is scoped to the dnsmasq unit only. The agent never edits /etc/resolv.conf.
Cmnd_Alias FELHOM_DNSMASQ = \
  /usr/bin/apt-get install -y -q dnsmasq, \
  /usr/bin/install -m 0644 /tmp/felhom-resolver-*.conf /etc/dnsmasq.d/felhom-*.conf, \
  /usr/bin/systemctl enable --now dnsmasq, \
  /usr/bin/systemctl reload dnsmasq, \
  /usr/bin/systemctl restart dnsmasq, \
  /usr/bin/rm -f /etc/dnsmasq.d/felhom-*.conf, \
  /usr/sbin/pct exec [0-9]* -- ip -4 -o addr show dev eth0, \
  /usr/sbin/pct exec [0-9]* -- docker exec felhom-controller cat /opt/docker/felhom-controller/controller.yaml

# Guest mountpoint lifecycle (intermediary-mount re-architecture + C1 net). The pre-start self-heal hook
# wrapper is installed once into the PVE snippets dir (from an agent-written /tmp file) and registered
# per-guest; decommission/eject DELETE the dead mountpoint slot so a missing bind source can't brick the
# guest at next boot (the B3 C1 fix). The agent fine-validates the vmid (numeric) + slot (mp[0-9]+) and
# the snippet path is fixed — the wildcards are the coarse allowlist.
Cmnd_Alias FELHOM_GUESTHOOK = \
  /usr/bin/install -m 0755 -- /tmp/felhom-guest-hook.sh /var/lib/vz/snippets/felhom-guest-hook.sh, \
  /usr/sbin/pct set [0-9]* --hookscript local\:snippets/felhom-guest-hook.sh, \
  /usr/sbin/pct set [0-9]* --delete mp[0-9]*, \
  /usr/sbin/pct reboot [0-9]*

# Intermediary mount model (the drive hot-swap re-architecture). The agent keeps a SHARED host parent
# /mnt/felhom-drives (self-bind + make-shared + a boot-persistence systemd unit) and binds/unbinds each
# drive's felhom-data namespace UNDERNEATH it so the change propagates into the running guest live (no
# pct, no reboot). The agent fine-validates the drive name + confines paths before any exec; the trailing
# `*` (matching the comma-laden mp spec) mirrors the existing FELHOM_PROVISION pattern.
# `lxc-info -n <vmid> -p -H` resolves the guest init PID for the GuestSeesMount / bound_under_parent check
# (a READ — the drive-gate's "is the drive live in the guest?" signal); WITHOUT it the non-root agent gets
# an empty PID and reports every drive absent (multi-drive flapping, audit 2026-06-29). `make-private`
# isolates the parent's peer group on FIRST setup only (EnsureSharedParent guards on mountpoint, so it
# never re-churns a live parent); without it the parent stays in root's group and submounts double.
Cmnd_Alias FELHOM_INTERMEDIARY = \
  /usr/bin/mkdir -p /mnt/felhom-drives, \
  /usr/bin/mkdir -p /mnt/felhom-drives/*, \
  /usr/bin/mkdir -p /mnt/*/felhom-data, \
  /usr/bin/chown 100000\:100000 /mnt/*/felhom-data, \
  /usr/bin/mount --bind /mnt/felhom-drives /mnt/felhom-drives, \
  /usr/bin/mount --make-shared /mnt/felhom-drives, \
  /usr/bin/mount --make-private /mnt/felhom-drives, \
  /usr/bin/mount --bind /mnt/*/felhom-data /mnt/felhom-drives/*, \
  /usr/bin/umount /mnt/felhom-drives/*, \
  /usr/bin/install -m 0755 -- /tmp/felhom-shared-parent.sh /usr/local/sbin/felhom-shared-parent.sh, \
  /usr/bin/install -m 0644 -- /tmp/felhom-shared-parent.service /etc/systemd/system/felhom-shared-parent.service, \
  /usr/bin/systemctl enable felhom-shared-parent.service, \
  /usr/bin/lxc-info -n [0-9]* -p -H, \
  /usr/sbin/pct set [0-9]* -mp8 /mnt/felhom-drives*

# Controller-swap / managed auto-update (Option A, non-root). The agent owns the in-guest controller
# image SWAP (it survives the controller being killed mid-swap): read the baked image ref, check the
# pre-pulled target is present, rewrite /etc/felhom-controller-image, restart the bootstrap unit,
# health-check, roll back on failure. Each grant is bounded — NO general `pct exec` and NO `bash -c`:
#   cat <fixed file>            — read the current image ref (read-only)
#   docker image inspect *      — is the pre-pulled target present? (read-only)
#   docker inspect -f *         — container running/health/image (read-only; `*` spans the -f template
#                                 + container across spaces, spike-confirmed)
#   systemctl restart <fixed unit> — re-run the golden's bootstrap (the only state change)
#   tee <FIXED image file>      — WRITE the ref; content is fed on STDIN (no shell, no interpolation),
#                                 the agent strict-validates the ref (controllerImageRe) before the write.
# Validated GO: felhom.eu/documentation/audits/SPIKE-controllerswap-narrow-grants-2026-06-29.md.
Cmnd_Alias FELHOM_CONTROLLERSWAP = \
  /usr/sbin/pct exec [0-9]* -- cat /etc/felhom-controller-image, \
  /usr/sbin/pct exec [0-9]* -- docker image inspect *, \
  /usr/sbin/pct exec [0-9]* -- docker inspect -f *, \
  /usr/sbin/pct exec [0-9]* -- systemctl restart felhom-controller-bootstrap.service, \
  /usr/sbin/pct exec [0-9]* -- tee /etc/felhom-controller-image

# Stale-lock recovery (F2-b, v0.49.0). A host reboot DURING a vzdump backup leaves the guest with a
# `snapshot-delete`/`backup` lock + `onboot:1` then can't start it → the customer box stays DOWN. The
# agent clears the STALE lock at startup (only when no vzdump is in-flight). `pct unlock` is the one op
# with no API equivalent (snapshot-delete + start go through the API token); the agent fine-validates the
# vmid (numeric) before exec — the `[0-9]*` is the coarse allowlist.
Cmnd_Alias FELHOM_STALELOCK = \
  /usr/sbin/pct unlock [0-9]*

felhom-agent ALL=(root) NOPASSWD: FELHOM_MOUNT, FELHOM_DISK, FELHOM_PROVISION, FELHOM_FORMAT, FELHOM_DNSMASQ, FELHOM_GUESTHOOK, FELHOM_INTERMEDIARY, FELHOM_CONTROLLERSWAP, FELHOM_STALELOCK