admin
3f382bf762
From AUDIT-blast-radius-hostroot-localapi-2026-07-02.md. Each fix ships with a non-hollow test + a companion red-proof (shown failing on the pre-fix impl). Sudoers install-source grants became globs — deploy the sudoers drop-in with the binary. A1 (stale-lock pool-membership) deliberately excluded (spike). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
105 lines
9.8 KiB
Go
105 lines
9.8 KiB
Go
// Package capability is the agent's privileged-capability self-check (slice 1 of agent
|
|
// self-health). It declares the MANIFEST — the (binary, representative-arg-vector) pairs the
|
|
// non-root agent depends on running via `sudo -n` — and a PROBE that lists each against the live
|
|
// sudoers policy (`sudo -n -l`, never executing) + checks the binary exists. The result is a
|
|
// snapshot the agent attaches to its hub report; the hub owns the ok→degraded transition + alert.
|
|
//
|
|
// Why this exists: the 2026-06-28 root→non-root cutover dropped several grants from
|
|
// configs/felhom-agent.sudoers (lxc-info, make-private, restart dnsmasq, …). Each broke a feature
|
|
// silently until a user hit it (the multi-drive flapping incident, audit 2026-06-29). A non-root
|
|
// agent that can't run a command it depends on is DEGRADED and must SAY so — at cutover, not days
|
|
// later. The companion build-time test (manifest_test.go) asserts every manifest vector is covered
|
|
// by a sudoers pattern, catching authoring gaps in CI before they ship.
|
|
package capability
|
|
|
|
// Capability is one privileged command the agent depends on. Name is a stable id; Feature is the
|
|
// human-readable thing that breaks if the grant is missing (used in logs + the operator alert).
|
|
// Binary is the absolute path the runner invokes; ReprArgs is a CONCRETE argument vector that
|
|
// matches the corresponding sudoers glob (e.g. a vmid "9201" matches `[0-9]*`, a device "/dev/sda"
|
|
// matches `/dev/*`). Critical marks the user-facing ones — the hub alerts only when a Critical
|
|
// capability is degraded (non-critical degradations still ride the report snapshot + agent log).
|
|
type Capability struct {
|
|
Name string
|
|
Feature string
|
|
Binary string
|
|
ReprArgs []string
|
|
Critical bool
|
|
}
|
|
|
|
// Manifest is the required set, seeded from the 2026-06-29 sudoers audit (felhom-agent/REPORT.md):
|
|
// the OK + newly-CLOSED rows. The SURFACED/DEFERRED rows are deliberately EXCLUDED — they are not
|
|
// required capabilities: the general `pct exec <vmid> -- *` (controller-swap; arbitrary exec, an
|
|
// open operator decision), `pct create` (golden build, maintenance, no daemon caller), `mount
|
|
// UUID=…` (legacy/unreferenced), and the callerless `sensors -j`. Adding them here would assert
|
|
// grants the agent neither has nor should depend on.
|
|
//
|
|
// Each ReprArgs is a representative instance; the probe LISTS it (`sudo -n -l`) and never runs it,
|
|
// so even mkfs/pct-set entries are side-effect-free to probe.
|
|
func Manifest() []Capability { return manifest }
|
|
|
|
var manifest = []Capability{
|
|
// ---- Intermediary drive model (the multi-drive path — mostly Critical) ----
|
|
{"guest-init-pid", "drive-gate guest-sees check (multi-drive concurrency)", "/usr/bin/lxc-info", []string{"-n", "9201", "-p", "-H"}, true},
|
|
{"parent-self-bind", "intermediary shared-parent self-bind", "/usr/bin/mount", []string{"--bind", "/mnt/felhom-drives", "/mnt/felhom-drives"}, true},
|
|
{"parent-make-shared", "intermediary shared-parent propagation", "/usr/bin/mount", []string{"--make-shared", "/mnt/felhom-drives"}, true},
|
|
{"parent-make-private", "intermediary shared-parent peer-group isolation", "/usr/bin/mount", []string{"--make-private", "/mnt/felhom-drives"}, true},
|
|
{"drive-bind", "drive attach (felhom-data bind under parent)", "/usr/bin/mount", []string{"--bind", "/mnt/felhom-usb/felhom-data", "/mnt/felhom-drives/felhom-usb"}, true},
|
|
{"drive-umount", "drive detach (fail-closed unmount)", "/usr/bin/umount", []string{"/mnt/felhom-drives/felhom-usb"}, true},
|
|
{"drives-mkdir-parent", "stable parent dir create", "/usr/bin/mkdir", []string{"-p", "/mnt/felhom-drives"}, false},
|
|
{"drives-mkdir-sub", "per-drive stable dir create", "/usr/bin/mkdir", []string{"-p", "/mnt/felhom-drives/felhom-usb"}, false},
|
|
{"drives-mkdir-data", "felhom-data namespace create", "/usr/bin/mkdir", []string{"-p", "/mnt/felhom-usb/felhom-data"}, false},
|
|
{"drives-chown-data", "felhom-data guest-root chown", "/usr/bin/chown", []string{"100000:100000", "/mnt/felhom-usb/felhom-data"}, false},
|
|
{"parent-script-install", "shared-parent boot script install", "/usr/bin/install", []string{"-m", "0755", "--", "/tmp/felhom-shared-parent-123456789.sh", "/usr/local/sbin/felhom-shared-parent.sh"}, false},
|
|
{"parent-unit-install", "shared-parent boot unit install", "/usr/bin/install", []string{"-m", "0644", "--", "/tmp/felhom-shared-parent-123456789.service", "/etc/systemd/system/felhom-shared-parent.service"}, false},
|
|
{"parent-unit-enable", "shared-parent boot-persistence enable", "/usr/bin/systemctl", []string{"enable", "felhom-shared-parent.service"}, false},
|
|
{"parent-bind-mp8", "parent bind into guest at provision", "/usr/sbin/pct", []string{"set", "9201", "-mp8", "/mnt/felhom-drives"}, false},
|
|
|
|
// ---- Disk inspect / format gate (Critical: the data-bearing classifier + format) ----
|
|
{"disk-blkid", "disk data-bearing classify (format gate)", "/usr/sbin/blkid", []string{"-p", "-o", "export", "/dev/sda"}, true},
|
|
{"disk-lsblk", "disk topology read (format gate)", "/usr/bin/lsblk", []string{"-J", "-o", "NAME,FSTYPE,PTTYPE,MOUNTPOINT", "/dev/sda"}, true},
|
|
{"disk-mkfs-ext4", "guarded format (ext4)", "/usr/local/sbin/felhom-mkfs-guarded", []string{"/dev/sda", "ext4"}, true},
|
|
{"disk-mkfs-xfs", "guarded format (xfs)", "/usr/local/sbin/felhom-mkfs-guarded", []string{"/dev/sda", "xfs"}, false},
|
|
{"disk-smart", "disk SMART health read", "/usr/sbin/smartctl", []string{"-a", "-j", "/dev/sda"}, false},
|
|
{"disk-lvs", "thin-pool usage read", "/usr/sbin/lvs", []string{"--reportformat", "json", "--units", "b", "-o", "lv_name,data_percent,metadata_percent", "--", "pve/data"}, false},
|
|
|
|
// ---- Storage mount units (watchdog re-mount) ----
|
|
{"mount-unit-install", "fs-UUID mount unit install", "/usr/bin/install", []string{"-o", "root", "-g", "root", "-m", "0644", "--", "/var/lib/felhom-agent/units/felhom-x.mount", "/etc/systemd/system/felhom-x.mount"}, false},
|
|
{"mount-daemon-reload", "systemd reload after unit write", "/usr/bin/systemctl", []string{"daemon-reload"}, false},
|
|
{"mount-unit-enable", "mount unit enable", "/usr/bin/systemctl", []string{"enable", "--now", "--", "felhom-x.mount"}, false},
|
|
{"mount-unit-disable", "mount unit disable", "/usr/bin/systemctl", []string{"disable", "--", "felhom-x.mount"}, false},
|
|
{"mount-unit-stop", "mount unit stop", "/usr/bin/systemctl", []string{"stop", "--", "felhom-x.mount"}, false},
|
|
|
|
// ---- Provisioning back-half ----
|
|
{"provision-chown", "bootstrap mount guest-root chown", "/usr/bin/chown", []string{"-R", "100000:100000", "/var/lib/felhom-agent/guests/9201"}, false},
|
|
{"provision-config-mount", "bootstrap config bind mount", "/usr/sbin/pct", []string{"set", "9201", "-mp0", "/var/lib/felhom-agent/guests/9201"}, false},
|
|
{"provision-onboot", "customer guest autostart (onboot)", "/usr/sbin/pct", []string{"set", "9201", "-onboot", "1"}, false},
|
|
|
|
// ---- Pre-start self-heal hook + guest lifecycle ----
|
|
{"guesthook-install", "pre-start hook snippet install", "/usr/bin/install", []string{"-m", "0755", "--", "/tmp/felhom-guest-hook-123456789.sh", "/var/lib/vz/snippets/felhom-guest-hook.sh"}, false},
|
|
{"guesthook-register", "pre-start hook register", "/usr/sbin/pct", []string{"set", "9201", "--hookscript", "local:snippets/felhom-guest-hook.sh"}, false},
|
|
{"guesthook-delete-mp", "dead mountpoint slot delete (C1 net)", "/usr/sbin/pct", []string{"set", "9201", "--delete", "mp0"}, false},
|
|
{"guest-reboot", "enroll activate-binds reboot", "/usr/sbin/pct", []string{"reboot", "9201"}, false},
|
|
|
|
// ---- LAN split-horizon resolver (dnsmasq) ----
|
|
{"dnsmasq-install", "dnsmasq package install", "/usr/bin/apt-get", []string{"install", "-y", "-q", "dnsmasq"}, false},
|
|
{"dnsmasq-write", "dnsmasq drop-in write", "/usr/bin/install", []string{"-m", "0644", "/tmp/felhom-resolver-x.conf", "/etc/dnsmasq.d/felhom-x.conf"}, false},
|
|
{"dnsmasq-enable", "dnsmasq enable", "/usr/bin/systemctl", []string{"enable", "--now", "dnsmasq"}, false},
|
|
{"dnsmasq-reload", "dnsmasq reload", "/usr/bin/systemctl", []string{"reload", "dnsmasq"}, false},
|
|
{"dnsmasq-restart", "dnsmasq restart (LAN-DNS self-heal)", "/usr/bin/systemctl", []string{"restart", "dnsmasq"}, false},
|
|
{"dnsmasq-rm", "dnsmasq drop-in remove (decommission)", "/usr/bin/rm", []string{"-f", "/etc/dnsmasq.d/felhom-x.conf"}, false},
|
|
{"dnsmasq-guest-ip", "guest LAN IP discovery", "/usr/sbin/pct", []string{"exec", "9201", "--", "ip", "-4", "-o", "addr", "show", "dev", "eth0"}, false},
|
|
{"dnsmasq-guest-domain", "guest domain discovery", "/usr/sbin/pct", []string{"exec", "9201", "--", "docker", "exec", "felhom-controller", "cat", "/opt/docker/felhom-controller/controller.yaml"}, false},
|
|
|
|
// ---- Controller-swap / managed auto-update (FELHOM_CONTROLLERSWAP, v0.45.0; Critical: a
|
|
// silently-broken fleet auto-update is operator-alert-worthy) ----
|
|
{"controllerswap-read", "controller-swap / managed auto-update", "/usr/sbin/pct", []string{"exec", "9201", "--", "cat", "/etc/felhom-controller-image"}, true},
|
|
{"controllerswap-image-inspect", "controller-swap / managed auto-update", "/usr/sbin/pct", []string{"exec", "9201", "--", "docker", "image", "inspect", "gitea.dooplex.hu/admin/felhom-controller:0.0.0"}, true},
|
|
{"controllerswap-inspect", "controller-swap / managed auto-update", "/usr/sbin/pct", []string{"exec", "9201", "--", "docker", "inspect", "-f", "{{.State.Running}}", "felhom-controller"}, true},
|
|
{"controllerswap-restart", "controller-swap / managed auto-update", "/usr/sbin/pct", []string{"exec", "9201", "--", "systemctl", "restart", "felhom-controller-bootstrap.service"}, true},
|
|
{"controllerswap-write", "controller-swap / managed auto-update", "/usr/sbin/pct", []string{"exec", "9201", "--", "tee", "/etc/felhom-controller-image"}, true},
|
|
|
|
// ---- Stale-lock recovery (FELHOM_STALELOCK, v0.49.0; Critical: a guest stuck behind a stale
|
|
// reboot-during-backup lock can't start → the customer box stays DOWN until this clears it) ----
|
|
{"stalelock-unlock", "reboot-during-backup stale-lock recovery", "/usr/sbin/pct", []string{"unlock", "9201"}, true},
|
|
}
|