agent v0.86.0: DR-tier-by-default — capability inactive state (GatedBy/GateActive, pbsdr gate via DRConfigured) + F-3 root-run provision parent ownership

Claude-Session: https://claude.ai/code/session_01NptTCFtu7dz2Ru89qHRagN
This commit is contained in:
2026-07-12 20:06:27 +02:00
parent bcb8dad2aa
commit c20814e6c2
11 changed files with 403 additions and 148 deletions
+86 -62
View File
@@ -12,6 +12,8 @@
// by a sudoers pattern, catching authoring gaps in CI before they ship.
package capability
import "strings"
// 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
@@ -24,8 +26,16 @@ type Capability struct {
Binary string
ReprArgs []string
Critical bool
// GatedBy names the config gate this capability sits behind ("" = always active). A healthy
// probe of a gated capability whose gate is OFF reports StatusInactive instead of ok — see
// Prober.GateActive. Broken plumbing stays degraded regardless of the gate.
GatedBy string
}
// GatePBSDR is the gate id for the PBS-DR tier: active when this box carries a live (enabled)
// pbs_dr descriptor or a previously-converged marker (pbsdr.Manager.DRConfigured).
const GatePBSDR = "pbs_dr"
// 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
@@ -35,7 +45,21 @@ type Capability struct {
//
// 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 }
//
// Gating (v0.86.0): every `pbsdr-*` capability is behind GatePBSDR — the whole pbsdr vector IS
// the DR-tier apply path, so the gate rides the stable name prefix (a new pbsdr-* op is gated
// automatically; nothing else ever is). Applied here, not in the literals, to keep the manifest
// entries positional.
func Manifest() []Capability {
out := make([]Capability, len(manifest))
copy(out, manifest)
for i := range out {
if strings.HasPrefix(out[i].Name, "pbsdr-") {
out[i].GatedBy = GatePBSDR
}
}
return out
}
// reprFingerprint is a shape-valid all-zero SHA-256 colon fingerprint for list-mode repr vectors
// (matches the wrapper's fingerprint validation; never executed).
@@ -43,102 +67,102 @@ const reprFingerprint = "00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:00:0
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},
{"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},
{"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},
{"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, ""},
// ---- Network storage re-arm + cleanup (CAMPAIGN-3 F10/F1) ----
{"netmount-reset-failed", "NAS automount re-arm after start-limit (F10)", "/usr/bin/systemctl", []string{"reset-failed", "--", "mnt-felhom\\x2ddrives-media.automount"}, false},
{"netmount-rmdir", "removed-share mountpoint cleanup (F1)", "/usr/bin/rmdir", []string{"/mnt/felhom-drives/media"}, false},
{"netmount-reset-failed", "NAS automount re-arm after start-limit (F10)", "/usr/bin/systemctl", []string{"reset-failed", "--", "mnt-felhom\\x2ddrives-media.automount"}, false, ""},
{"netmount-rmdir", "removed-share mountpoint cleanup (F1)", "/usr/bin/rmdir", []string{"/mnt/felhom-drives/media"}, false, ""},
// ---- Node self-heal (CAMPAIGN-3 F12-class, appliance-gated in code) ----
{"selfheal-networking-start", "appliance networking recovery at boot (F12 defense in depth)", "/usr/bin/systemctl", []string{"start", "networking.service"}, false},
{"selfheal-networking-start", "appliance networking recovery at boot (F12 defense in depth)", "/usr/bin/systemctl", []string{"start", "networking.service"}, 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},
{"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},
{"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},
{"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},
{"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},
{"stalelock-unlock", "reboot-during-backup stale-lock recovery", "/usr/sbin/pct", []string{"unlock", "9201"}, true, ""},
// ---- Offsite WG tunnel (FELHOM_WG, S3/v0.64.0; Critical FLIPPED in S4/v0.66.0 — offsite
// backups now RIDE the tunnel, so a degraded tunnel capability is operator-alert-worthy: the
// conf install, unit enable/restart and the handshake read gate the backup path. apt-install
// (one-time bootstrap) and disable (revocation, a deliberate teardown) stay non-critical. The
// handshake read is the ONLY wg invocation (never `dump`). ----
{"wg-tools-install", "wireguard-tools package install", "/usr/bin/apt-get", []string{"install", "-y", "-q", "wireguard-tools"}, false},
{"wg-conf-install", "wg-felhom conf install", "/usr/bin/install", []string{"-o", "root", "-g", "root", "-m", "0600", "--", "/var/lib/felhom-agent/wg/wg-felhom.conf", "/etc/wireguard/wg-felhom.conf"}, true},
{"wg-enable", "wg-quick@wg-felhom enable", "/usr/bin/systemctl", []string{"enable", "--now", "wg-quick@wg-felhom"}, true},
{"wg-restart", "wg-quick@wg-felhom restart (conf change)", "/usr/bin/systemctl", []string{"restart", "wg-quick@wg-felhom"}, true},
{"wg-disable", "wg-quick@wg-felhom disable (revocation)", "/usr/bin/systemctl", []string{"disable", "--now", "wg-quick@wg-felhom"}, false},
{"wg-handshake-read", "tunnel handshake-age read", "/usr/bin/wg", []string{"show", "wg-felhom", "latest-handshakes"}, true},
{"wg-tools-install", "wireguard-tools package install", "/usr/bin/apt-get", []string{"install", "-y", "-q", "wireguard-tools"}, false, ""},
{"wg-conf-install", "wg-felhom conf install", "/usr/bin/install", []string{"-o", "root", "-g", "root", "-m", "0600", "--", "/var/lib/felhom-agent/wg/wg-felhom.conf", "/etc/wireguard/wg-felhom.conf"}, true, ""},
{"wg-enable", "wg-quick@wg-felhom enable", "/usr/bin/systemctl", []string{"enable", "--now", "wg-quick@wg-felhom"}, true, ""},
{"wg-restart", "wg-quick@wg-felhom restart (conf change)", "/usr/bin/systemctl", []string{"restart", "wg-quick@wg-felhom"}, true, ""},
{"wg-disable", "wg-quick@wg-felhom disable (revocation)", "/usr/bin/systemctl", []string{"disable", "--now", "wg-quick@wg-felhom"}, false, ""},
{"wg-handshake-read", "tunnel handshake-age read", "/usr/bin/wg", []string{"show", "wg-felhom", "latest-handshakes"}, true, ""},
// ---- PBS DR tier apply (FELHOM_PBSDR, slice 2). NON-critical (the selfupdate rationale):
// applying the tier is an occasional hub-driven provisioning op, not a steady-state serving
// path — a degraded grant means "can't provision/reconcile the PBS entry" (the bridge reports
// loudly anyway), not a serving outage. The steady-state backup path is covered by the wg +
// storage capabilities. List-mode representations only; never executed. ----
{"pbsdr-create", "PBS DR storage-entry create (K autogen)", "/usr/local/sbin/felhom-pbs-apply", []string{"create", "felhom-pbs", "10.77.0.1", "felhom-offsite", "ns0", "felhom@pbs!ns0", reprFingerprint, "/etc/pve/priv/storage"}, false},
{"pbsdr-reconcile", "PBS DR storage-entry reconcile (set-only)", "/usr/local/sbin/felhom-pbs-apply", []string{"reconcile", "felhom-pbs", "10.77.0.1", "ns0", "felhom@pbs!ns0", reprFingerprint, "/etc/pve/priv/storage"}, false},
{"pbsdr-grant", "PBS DR storage ACL self-grant", "/usr/local/sbin/felhom-pbs-apply", []string{"grant", "felhom-pbs"}, false},
{"pbsdr-create", "PBS DR storage-entry create (K autogen)", "/usr/local/sbin/felhom-pbs-apply", []string{"create", "felhom-pbs", "10.77.0.1", "felhom-offsite", "ns0", "felhom@pbs!ns0", reprFingerprint, "/etc/pve/priv/storage"}, false, ""},
{"pbsdr-reconcile", "PBS DR storage-entry reconcile (set-only)", "/usr/local/sbin/felhom-pbs-apply", []string{"reconcile", "felhom-pbs", "10.77.0.1", "ns0", "felhom@pbs!ns0", reprFingerprint, "/etc/pve/priv/storage"}, false, ""},
{"pbsdr-grant", "PBS DR storage ACL self-grant", "/usr/local/sbin/felhom-pbs-apply", []string{"grant", "felhom-pbs"}, false, ""},
// ---- Agent self-update (FELHOM_SELFUPDATE, D1). NON-critical: self-update is an occasional
// operator-driven op, not a steady-state serving path — a degraded grant means "can't
// self-update" (fall back to a manual SSH deploy), not a serving outage. The apply repr uses a
// staging-dir path + a placeholder sha (list-mode never runs it). ----
{"selfupdate-apply", "agent self-update apply (A/B flip)", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"apply", "/var/lib/felhom-agent/selfupdate/felhom-agent-0.0.0", "0000000000000000000000000000000000000000000000000000000000000000"}, false},
{"selfupdate-commit", "agent self-update commit", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"commit"}, false},
{"selfupdate-rollback", "agent self-update rollback", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"rollback"}, false},
{"selfupdate-apply", "agent self-update apply (A/B flip)", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"apply", "/var/lib/felhom-agent/selfupdate/felhom-agent-0.0.0", "0000000000000000000000000000000000000000000000000000000000000000"}, false, ""},
{"selfupdate-commit", "agent self-update commit", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"commit"}, false, ""},
{"selfupdate-rollback", "agent self-update rollback", "/usr/local/sbin/felhom-selfupdate-guarded", []string{"rollback"}, false, ""},
}
+29 -6
View File
@@ -8,19 +8,30 @@ import (
// Status is one capability's live result — the wire shape the agent attaches to its hub report
// (HostReport.Capabilities). The hub mirrors this struct field-for-field and keys its alert on
// Critical+degraded. Reason is empty when ok.
//
// "inactive" (v0.86.0, DR-tier-by-default): a config-GATED capability whose plumbing is HEALTHY
// (binary present, sudo granted) but whose gating feature is disabled by configuration. Distinct
// from degraded on purpose — disabled ≠ broken; the hub renders it as a neutral chip, never red.
// Broken plumbing (binary missing / grant denied) stays DEGRADED even when the gate is off: an
// un-migrated box must never look deliberately disabled.
type Status struct {
Name string `json:"name"`
Feature string `json:"feature"`
Critical bool `json:"critical"`
Status string `json:"status"` // "ok" | "degraded"
Status string `json:"status"` // "ok" | "degraded" | "inactive"
Reason string `json:"reason,omitempty"`
}
const (
StatusOK = "ok"
StatusDegraded = "degraded"
StatusInactive = "inactive"
)
// ReasonInactive is the fixed reason string for the inactive state (the hub + operator docs
// reference it verbatim).
const ReasonInactive = "disabled by configuration"
// Runner is the minimal exec seam the probe needs (satisfied by proxmox.ExecRunner). The probe
// runs `sudo -n -l -- <binary> <args…>` LITERALLY — a sudo POLICY LIST that never executes the
// command — so the Runner MUST be a DIRECT runner (RunnerDirect), not the sudo-prepending one
@@ -31,9 +42,13 @@ type Runner interface {
// Prober checks the manifest against the live host. Exists defaults to an os.Stat check on the
// absolute binary path (what `command -v` would resolve for an absolute path) when nil.
// GateActive answers "is the feature behind this gate id configured on?" for GATED capabilities
// (Capability.GatedBy). nil, or a gate it answers true for, keeps the historical behavior; false
// downgrades a HEALTHY probe to StatusInactive (broken plumbing stays degraded regardless).
type Prober struct {
Runner Runner
Exists func(path string) bool // nil → os.Stat
Runner Runner
Exists func(path string) bool // nil → os.Stat
GateActive func(gate string) bool // nil → every gate treated active
}
// Probe lists every manifest capability against the sudo policy and checks its binary exists,
@@ -72,6 +87,11 @@ func (p Prober) Probe(ctx context.Context) []Status {
case p.Runner != nil && !p.granted(ctx, c):
s.Status, s.Reason = StatusDegraded, "sudo policy denied"
}
// Config gate (v0.86.0): only a HEALTHY probe is downgraded to inactive — a degraded one
// stays degraded (missing binary/grant = un-migrated or mis-installed box, never "off").
if s.Status == StatusOK && c.GatedBy != "" && p.GateActive != nil && !p.GateActive(c.GatedBy) {
s.Status, s.Reason = StatusInactive, ReasonInactive
}
out = append(out, s)
}
return out
@@ -85,13 +105,16 @@ func (p Prober) granted(ctx context.Context, c Capability) bool {
return err == nil
}
// Summarize returns (okCount, total, degraded) for logging. degraded lists every non-ok status.
// Summarize returns (okCount, total, degraded) for logging. degraded lists DEGRADED statuses
// only — inactive is a deliberate, healthy state and must not land in the error log (it is
// counted via len(statuses)-ok-len(degraded) by callers that want it).
func Summarize(statuses []Status) (ok, total int, degraded []Status) {
total = len(statuses)
for _, s := range statuses {
if s.Status == StatusOK {
switch s.Status {
case StatusOK:
ok++
} else {
case StatusDegraded:
degraded = append(degraded, s)
}
}
+79
View File
@@ -115,3 +115,82 @@ func TestProbe_NilRunnerNoPanic(t *testing.T) {
t.Fatalf("nil-runner probe returned %d statuses, want %d", got, len(Manifest()))
}
}
// ── DR-tier gate (v0.86.0) ─────────────────────────────────────────────────────────────────────
// Gate OFF + healthy plumbing → the gated pbsdr-* capabilities report INACTIVE (the neutral
// "disabled by configuration" state), NOT ok and NOT degraded — Scenario B of the DR-by-default
// spec. Ungated siblings are untouched. Red-proof partner: collapse inactive into ok (drop the
// gate branch in Probe) → this fails while TestProbe_GateOffBinaryMissingStaysDegraded passes.
func TestProbe_GateOffHealthyIsInactive(t *testing.T) {
r := &fakeRunner{denyBinary: map[string]bool{}}
p := Prober{
Runner: r,
Exists: func(string) bool { return true },
GateActive: func(gate string) bool { return gate != GatePBSDR }, // DR tier OFF
}
statuses := p.Probe(context.Background())
for _, name := range []string{"pbsdr-create", "pbsdr-reconcile", "pbsdr-grant"} {
s := find(statuses, name)
if s.Status != StatusInactive || s.Reason != ReasonInactive {
t.Fatalf("%s = %+v, want inactive/%q", name, s, ReasonInactive)
}
}
// An ungated sibling stays plain ok.
if s := find(statuses, "drive-bind"); s.Status != StatusOK {
t.Fatalf("drive-bind = %+v, want ok (ungated)", s)
}
// Summarize must NOT count inactive as degraded (it is not error-log-worthy).
ok, total, degraded := Summarize(statuses)
if len(degraded) != 0 {
t.Fatalf("inactive leaked into degraded: %+v", degraded)
}
if ok != total-3 {
t.Fatalf("ok=%d total=%d, want exactly the 3 gated ones non-ok", ok, total)
}
}
// Gate OFF + BROKEN plumbing (binary missing) → DEGRADED stays degraded. An un-migrated
// pre-v1.15.0 box must never masquerade as deliberately disabled ("never silently pretend").
func TestProbe_GateOffBinaryMissingStaysDegraded(t *testing.T) {
r := &fakeRunner{denyBinary: map[string]bool{}}
p := Prober{
Runner: r,
Exists: func(path string) bool { return path != "/usr/local/sbin/felhom-pbs-apply" },
GateActive: func(gate string) bool { return gate != GatePBSDR }, // DR tier OFF
}
statuses := p.Probe(context.Background())
for _, name := range []string{"pbsdr-create", "pbsdr-reconcile", "pbsdr-grant"} {
s := find(statuses, name)
if s.Status != StatusDegraded || s.Reason != "binary not found" {
t.Fatalf("%s = %+v, want degraded/binary not found even with the gate off", name, s)
}
}
}
// Gate ON (DR configured) + healthy plumbing → plain ok, exactly the pre-v0.86.0 behavior.
// A nil GateActive must behave the same (fails ACTIVE).
func TestProbe_GateOnOrNilIsOK(t *testing.T) {
for _, gate := range []func(string) bool{nil, func(string) bool { return true }} {
r := &fakeRunner{denyBinary: map[string]bool{}}
p := Prober{Runner: r, Exists: func(string) bool { return true }, GateActive: gate}
statuses := p.Probe(context.Background())
if s := find(statuses, "pbsdr-create"); s.Status != StatusOK {
t.Fatalf("pbsdr-create = %+v, want ok (gate active/nil)", s)
}
}
}
// The gate rides the pbsdr- name prefix: exactly the pbsdr-* manifest entries are gated, nothing
// else (a regression here would silently un-gate the tier or gate an unrelated capability).
func TestManifest_ExactlyPBSDRGated(t *testing.T) {
for _, c := range Manifest() {
wantGated := strings.HasPrefix(c.Name, "pbsdr-")
if gated := c.GatedBy == GatePBSDR; gated != wantGated {
t.Fatalf("%s: GatedBy=%q, want gated=%v", c.Name, c.GatedBy, wantGated)
}
if c.GatedBy != "" && c.GatedBy != GatePBSDR {
t.Fatalf("%s: unknown gate id %q", c.Name, c.GatedBy)
}
}
}
+16
View File
@@ -125,6 +125,22 @@ func (m *Manager) Status() *hub.PBSDRStatus {
return m.status
}
// DRConfigured reports whether the DR tier is configured ON for this box — the capability
// prober's GatePBSDR answer (v0.86.0). True when the last-seen descriptor was enabled (any live
// status except "disabled"), or, before the first desired-state fetch of this process, when a
// previously-converged marker exists (so an applied box never flaps to inactive across an agent
// restart). False = no descriptor ever / descriptor disabled → healthy pbsdr capabilities report
// "inactive (disabled by configuration)" instead of ok.
func (m *Manager) DRConfigured() bool {
m.mu.Lock()
st := m.status
m.mu.Unlock()
if st != nil {
return st.State != "disabled"
}
return m.loadMarker() != nil
}
// descriptorHash is the idempotency key: sha256 of the canonical (struct-ordered) JSON.
func descriptorHash(b *hub.WirePBSDR) string {
j, _ := json.Marshal(b)
+40
View File
@@ -362,6 +362,46 @@ func TestOldHubAndDisabledCompat(t *testing.T) {
}
}
// DRConfigured (v0.86.0) — the capability prober's GatePBSDR answer. Walks the full lifecycle:
// unconfigured → enabled(applied) → restart(marker only) → disabled. Red-proof partner: make
// DRConfigured return status!=nil (ignore the "disabled" state) → the disabled case fails.
func TestDRConfigured_Lifecycle(t *testing.T) {
r := &fakeRunner{}
st := &fakeStorage{found: false, active: []bool{true}}
c := &fakeConsumer{secret: "S"}
m, _ := newTestManager(t, r, st, c)
// Fresh box, nothing fetched: not configured.
if m.DRConfigured() {
t.Fatal("fresh manager reports DR configured")
}
// Old hub / no descriptor: still not configured.
m.Apply(context.Background(), true, nil)
if m.DRConfigured() {
t.Fatal("nil-block reports DR configured")
}
// Enabled descriptor applied: configured.
m.Apply(context.Background(), true, testBlock())
if s := m.Status(); s == nil || s.State != "applied" {
t.Fatalf("precondition: status = %+v, want applied", s)
}
if !m.DRConfigured() {
t.Fatal("applied box reports DR NOT configured")
}
// Agent restart (fresh manager over the same state dir): the persisted marker must answer
// BEFORE the first desired-state fetch — an applied box never flaps to inactive at boot.
m2 := NewManager(r, st, c, filepath.Dir(m.stateDir), "/etc/pve/priv/storage", "",
slog.New(slog.NewTextHandler(io.Discard, nil)))
if !m2.DRConfigured() {
t.Fatal("restarted manager (marker on disk) reports DR NOT configured")
}
// Operator turns the tier OFF: descriptor disabled wins over the stale marker.
m2.Apply(context.Background(), true, &hub.WirePBSDR{Enabled: false, StorageID: "felhom-pbs"})
if m2.DRConfigured() {
t.Fatal("disabled descriptor still reports DR configured")
}
}
// TestWireFieldNames pins the cross-repo descriptor contract (hub/internal/web/pbsdr.go
// pbsDRDescriptor): the exact JSON the hub writes must land in WirePBSDR field-for-field.
func TestWireFieldNames(t *testing.T) {
+20
View File
@@ -52,6 +52,9 @@ type BackHalf struct {
logger *slog.Logger
}
// geteuid is the effective-uid seam (F-3): tests fake a root run without being root.
var geteuid = os.Geteuid
// NewBackHalf builds the back-half. stateDir defaults to /var/lib/felhom-agent when empty.
func NewBackHalf(tokens TokenMinter, runner proxmox.Runner, stateDir string, logger *slog.Logger) *BackHalf {
if stateDir == "" {
@@ -135,6 +138,23 @@ func (b *BackHalf) Provision(ctx context.Context, in Input) (Result, error) {
if err := os.MkdirAll(hostDir, 0o700); err != nil {
return Result{}, fmt.Errorf("provision: config dir: %w", err)
}
// 3b. F-3 (DRILL-day0-vm-2026-07-12): a ROOT-run provision (the Day-0 one-shot) leaves the
// just-created guests/ + guests/<vmid>/ parents root:root 0700 inside the agent-owned
// state dir — the non-root daemon's lanresolver then can't traverse them ("permission
// denied"). Own the two PARENTS to whatever owns the state dir (chown --reference; the
// installer made that the agent user). NON-recursive on purpose: only the bootstrap leaf
// below belongs to the mapped guest-root. A daemon-run provision creates them as the
// agent user already — euid≠0 skips (and needs no sudoers vector for this shape).
if geteuid() == 0 {
guestsDir := filepath.Join(b.stateDir, "guests")
vmidDir := filepath.Join(guestsDir, strconv.Itoa(in.VMID))
if err := b.run(ctx, "chown", "--reference="+b.stateDir, guestsDir, vmidDir); err != nil {
// Warn-only: the drill's manual fix is a one-liner and lanresolver degrades visibly.
b.logger.Warn("provision: could not own guests parent dirs to the state-dir owner (F-3)",
"err", err)
}
}
bootPath := filepath.Join(hostDir, bootstrapFile)
if err := os.WriteFile(bootPath, rendered, 0o600); err != nil {
return Result{}, fmt.Errorf("provision: write bootstrap: %w", err)
+39
View File
@@ -157,6 +157,45 @@ func TestProvision_WritesChownsAndAttaches(t *testing.T) {
// F3: the provisioned customer guest must be set onboot:1 so it auto-starts after a host
// reboot/power-cut (the golden bakes onboot:0 as a template). Assert the exact pct invocation.
// F-3 (DRILL-day0-vm-2026-07-12): a ROOT-run provision must chown the guests/ + guests/<vmid>/
// PARENT dirs to the state-dir's owner (chown --reference, NON-recursive — the bootstrap leaf
// stays the mapped guest-root's). A non-root run must NOT issue it (the dirs are already
// agent-created). Companion red-proof: remove the geteuid()==0 chown block in Provision → the
// root case fails (no such invocation recorded); the non-root case alone stays green.
func TestProvision_RootRunOwnsGuestsParents(t *testing.T) {
orig := geteuid
defer func() { geteuid = orig }()
for _, tc := range []struct {
name string
euid int
want bool
}{
{"root run issues the parent chown", 0, true},
{"non-root run does not", 1001, false},
} {
t.Run(tc.name, func(t *testing.T) {
geteuid = func() int { return tc.euid }
dir := t.TempDir()
runner := &recRunner{}
bh := NewBackHalf(&mintMinter{token: "T"}, runner, dir, testLogger())
if _, err := bh.Provision(context.Background(), newInput()); err != nil {
t.Fatalf("provision: %v", err)
}
guestsDir := filepath.Join(dir, "guests")
vmidDir := filepath.Join(guestsDir, "8200")
got := runner.hasExact("chown", "--reference="+dir, guestsDir, vmidDir)
if got != tc.want {
t.Fatalf("parent chown issued=%v want=%v; recorded: %v", got, tc.want, runner.cmds)
}
// Never recursive — the guest-root bootstrap subtree must stay untouched.
if runner.hasExact("chown", "-R", "--reference="+dir, guestsDir, vmidDir) {
t.Fatal("parent chown ran recursively")
}
})
}
}
// Companion red-proof: removing the `b.run(... -onboot 1)` call in Provision makes this FAIL
// (no such invocation recorded) — re-applying the call turns it green.
func TestProvision_SetsOnbootOne(t *testing.T) {