capability: agent privileged-capability self-probe (manifest + build-test + runtime snapshot) v0.44.0

New internal/capability: Manifest of required sudo -n grants + Prober that LISTS each via 'sudo -n -l' (never executes) + binary-exists check → ok/degraded snapshot on the hub report. Build-time test asserts manifest⊆sudoers (red-proof: dropping lxc-info FAILs the gate). Startup logs N/N ok + ERROR per degraded. Serve-degraded; no allowlist change. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EPZ4GJ8L5Jqf8UiPwbn1kt
2026-06-29 18:43:49 +02:00
parent 19582046ba
commit 25024d9dda
10 changed files with 584 additions and 11 deletions
@@ -0,0 +1,92 @@
+// 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.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.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", "blank-device format (ext4)", "/usr/sbin/mkfs.ext4", []string{"-F", "/dev/sda"}, true},
+	{"disk-mkfs-xfs", "blank-device format (xfs)", "/usr/sbin/mkfs.xfs", []string{"-f", "/dev/sda"}, 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.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},
+}
@@ -0,0 +1,181 @@
+package capability
+
+import (
+	"os"
+	"regexp"
+	"strings"
+	"testing"
+)
+
+// sudoersPath is the in-repo allowlist, relative to this test file (internal/capability/).
+const sudoersPath = "../../configs/felhom-agent.sudoers"
+
+// parseSudoersEntries returns every command pattern from the Cmnd_Alias blocks, with the sudoers
+// escapes (`\,` `\:`) unescaped. It joins continuation lines and splits the alias RHS on commas
+// that are NOT backslash-escaped (escaped commas are literal arg chars, e.g. the lvs `-o` list).
+func parseSudoersEntries(t *testing.T, text string) []string {
+	t.Helper()
+	// 1. Collapse line continuations, keeping only Cmnd_Alias RHS text.
+	var rhs strings.Builder
+	lines := strings.Split(text, "\n")
+	inAlias := false
+	for _, ln := range lines {
+		trimmed := strings.TrimSpace(ln)
+		if strings.HasPrefix(trimmed, "#") {
+			continue
+		}
+		if strings.HasPrefix(trimmed, "Cmnd_Alias ") {
+			inAlias = true
+			if eq := strings.IndexByte(trimmed, '='); eq >= 0 {
+				trimmed = trimmed[eq+1:]
+			}
+		} else if !inAlias {
+			continue
+		}
+		// The final NOPASSWD line ("felhom-agent ALL=...") ends the alias region.
+		if strings.Contains(trimmed, "ALL=(") {
+			inAlias = false
+			continue
+		}
+		cont := strings.HasSuffix(trimmed, "\\")
+		rhs.WriteString(strings.TrimSuffix(trimmed, "\\"))
+		rhs.WriteString(" ")
+		if !cont {
+			// A non-continued line is the last entry of this alias. Emit a comma so it does not
+			// merge with the next alias's first entry when all RHS text is concatenated.
+			rhs.WriteString(", ")
+			inAlias = false
+		}
+	}
+	// 2. Split on unescaped commas → individual command entries.
+	raw := rhs.String()
+	var entries []string
+	var cur strings.Builder
+	for i := 0; i < len(raw); i++ {
+		c := raw[i]
+		if c == '\\' && i+1 < len(raw) {
+			cur.WriteByte(raw[i+1]) // unescape: keep the next char literally (\, → , ; \: → :)
+			i++
+			continue
+		}
+		if c == ',' {
+			entries = appendTrimmed(entries, cur.String())
+			cur.Reset()
+			continue
+		}
+		cur.WriteByte(c)
+	}
+	entries = appendTrimmed(entries, cur.String())
+	return entries
+}
+
+func appendTrimmed(entries []string, s string) []string {
+	if t := strings.Join(strings.Fields(s), " "); t != "" {
+		return append(entries, t)
+	}
+	return entries
+}
+
+// globToRegex translates a sudoers fnmatch pattern to an anchored regex. It is NOT a perfect sudo
+// emulator — it only needs to catch a removed/renamed grant (the real failure mode). `*` → `.*`,
+// `[...]` char classes pass through (valid regex), regex metachars are escaped.
+func globToRegex(pat string) *regexp.Regexp {
+	var b strings.Builder
+	b.WriteString("^")
+	for i := 0; i < len(pat); i++ {
+		c := pat[i]
+		switch {
+		case c == '*':
+			b.WriteString(".*")
+		case c == '[': // copy the char class verbatim (valid in regex too)
+			if j := strings.IndexByte(pat[i:], ']'); j > 0 {
+				b.WriteString(pat[i : i+j+1])
+				i += j
+				continue
+			}
+			b.WriteString("\\[")
+		case strings.IndexByte(`.+()|{}^$\?`, c) >= 0:
+			b.WriteByte('\\')
+			b.WriteByte(c)
+		default:
+			b.WriteByte(c)
+		}
+	}
+	b.WriteString("$")
+	return regexp.MustCompile(b.String())
+}
+
+// matchesAny reports whether cmdline matches at least one sudoers entry pattern.
+func matchesAny(cmdline string, entries []string) bool {
+	for _, e := range entries {
+		if globToRegex(e).MatchString(cmdline) {
+			return true
+		}
+	}
+	return false
+}
+
+// TestManifestCoveredBySudoers is the headline build-time gate: EVERY manifest capability's
+// representative command line must be permitted by at least one sudoers pattern. This is exactly
+// the check that would have caught the lxc-info / make-private grants being dropped at the
+// 2026-06-28 cutover — in CI, before shipping.
+func TestManifestCoveredBySudoers(t *testing.T) {
+	data, err := os.ReadFile(sudoersPath)
+	if err != nil {
+		t.Fatalf("read sudoers %s: %v", sudoersPath, err)
+	}
+	entries := parseSudoersEntries(t, string(data))
+	if len(entries) < 20 {
+		t.Fatalf("parsed only %d sudoers entries — parser likely broke", len(entries))
+	}
+	for _, c := range Manifest() {
+		cmdline := strings.TrimSpace(c.Binary + " " + strings.Join(c.ReprArgs, " "))
+		if !matchesAny(cmdline, entries) {
+			t.Errorf("capability %q (%s) NOT covered by any sudoers grant:\n  %s",
+				c.Name, c.Feature, cmdline)
+		}
+	}
+}
+
+// TestRedProof_DroppedGrantFailsCheck is the companion red-proof: with the lxc-info line removed
+// from an in-memory copy of the sudoers, the coverage check for guest-init-pid MUST fail. Proves
+// the build gate actually catches the regression (a green test that can never go red is hollow).
+func TestRedProof_DroppedGrantFailsCheck(t *testing.T) {
+	data, err := os.ReadFile(sudoersPath)
+	if err != nil {
+		t.Fatalf("read sudoers: %v", err)
+	}
+	// Drop the lxc-info grant line.
+	var kept []string
+	for _, ln := range strings.Split(string(data), "\n") {
+		if strings.Contains(ln, "lxc-info") {
+			continue
+		}
+		kept = append(kept, ln)
+	}
+	mutated := strings.Join(kept, "\n")
+	if strings.Contains(mutated, "lxc-info") {
+		t.Fatal("setup: lxc-info line not removed")
+	}
+	entries := parseSudoersEntries(t, mutated)
+
+	var guestInit Capability
+	for _, c := range Manifest() {
+		if c.Name == "guest-init-pid" {
+			guestInit = c
+		}
+	}
+	if guestInit.Name == "" {
+		t.Fatal("manifest missing guest-init-pid")
+	}
+	cmdline := guestInit.Binary + " " + strings.Join(guestInit.ReprArgs, " ")
+	if matchesAny(cmdline, entries) {
+		t.Errorf("red-proof FAILED: guest-init-pid still matches after dropping the lxc-info grant — the build gate would NOT catch the regression")
+	}
+
+	// Sanity: the UNMUTATED file MUST cover it (so the failure above is specific to the drop).
+	full := parseSudoersEntries(t, string(data))
+	if !matchesAny(cmdline, full) {
+		t.Errorf("guest-init-pid should be covered by the real sudoers")
+	}
+}
@@ -0,0 +1,99 @@
+package capability
+
+import (
+	"context"
+	"os"
+)
+
+// 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.
+type Status struct {
+	Name     string `json:"name"`
+	Feature  string `json:"feature"`
+	Critical bool   `json:"critical"`
+	Status   string `json:"status"` // "ok" | "degraded"
+	Reason   string `json:"reason,omitempty"`
+}
+
+const (
+	StatusOK       = "ok"
+	StatusDegraded = "degraded"
+)
+
+// 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
+// (else it would double-sudo). exit 0 ⇔ the command is permitted under the NOPASSWD allowlist.
+type Runner interface {
+	Run(ctx context.Context, name string, args ...string) (stdout, stderr []byte, err error)
+}
+
+// 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.
+type Prober struct {
+	Runner Runner
+	Exists func(path string) bool // nil → os.Stat
+}
+
+// Probe lists every manifest capability against the sudo policy and checks its binary exists,
+// mapping to ok/degraded (§8 of the spec). It NEVER executes a probed command and NEVER returns a
+// fatal error (serve-degraded): a probe failure is reported, not raised. If sudo itself is
+// unavailable for the agent (the drop-in is missing / the user has no sudo at all), it collapses
+// to ONE aggregate degraded signal instead of N identical ones.
+func (p Prober) Probe(ctx context.Context) []Status {
+	exists := p.Exists
+	if exists == nil {
+		exists = func(path string) bool { _, err := os.Stat(path); return err == nil }
+	}
+	caps := Manifest()
+
+	// Preflight: a bare `sudo -n -l` lists the user's allowed commands. For our NOPASSWD service
+	// user it exits 0; if it fails, the drop-in isn't installed (or sudo is gone) and EVERY vector
+	// would individually fail — collapse to one aggregate signal so the operator gets one alert.
+	if p.Runner != nil {
+		if _, _, err := p.Runner.Run(ctx, "sudo", "-n", "-l"); err != nil {
+			return []Status{{
+				Name:     "sudo",
+				Feature:  "the entire privileged surface (mount/format/pct/dnsmasq/lxc-info)",
+				Critical: true,
+				Status:   StatusDegraded,
+				Reason:   "sudoers drop-in not installed / sudo unavailable",
+			}}
+		}
+	}
+
+	out := make([]Status, 0, len(caps))
+	for _, c := range caps {
+		s := Status{Name: c.Name, Feature: c.Feature, Critical: c.Critical, Status: StatusOK}
+		switch {
+		case !exists(c.Binary):
+			s.Status, s.Reason = StatusDegraded, "binary not found"
+		case p.Runner != nil && !p.granted(ctx, c):
+			s.Status, s.Reason = StatusDegraded, "sudo policy denied"
+		}
+		out = append(out, s)
+	}
+	return out
+}
+
+// granted reports whether `sudo -n -l -- <binary> <reprArgs…>` is permitted (exit 0). List-mode is
+// side-effect-free — the command is matched against the policy, never run.
+func (p Prober) granted(ctx context.Context, c Capability) bool {
+	args := append([]string{"-n", "-l", "--", c.Binary}, c.ReprArgs...)
+	_, _, err := p.Runner.Run(ctx, "sudo", args...)
+	return err == nil
+}
+
+// Summarize returns (okCount, total, degraded) for logging. degraded lists every non-ok status.
+func Summarize(statuses []Status) (ok, total int, degraded []Status) {
+	total = len(statuses)
+	for _, s := range statuses {
+		if s.Status == StatusOK {
+			ok++
+		} else {
+			degraded = append(degraded, s)
+		}
+	}
+	return ok, total, degraded
+}
@@ -0,0 +1,117 @@
+package capability
+
+import (
+	"context"
+	"errors"
+	"strings"
+	"testing"
+)
+
+// fakeRunner returns a canned error per (command line) and records calls. deny holds binaries (or
+// the bare "sudo -n -l" preflight) that should fail; everything else exits 0.
+type fakeRunner struct {
+	preflightErr error
+	denyBinary   map[string]bool // binary path → policy-denied
+	calls        int
+	executedReal bool // set if a probed command was ever run WITHOUT -l (must never happen)
+}
+
+func (f *fakeRunner) Run(_ context.Context, name string, args ...string) ([]byte, []byte, error) {
+	f.calls++
+	// Preflight is `sudo -n -l` (exactly 2 args, no `--`).
+	if name == "sudo" && len(args) == 2 && args[0] == "-n" && args[1] == "-l" {
+		return nil, nil, f.preflightErr
+	}
+	// Every real probe must be a LIST: `sudo -n -l -- <binary> …`.
+	if name != "sudo" || len(args) < 4 || args[0] != "-n" || args[1] != "-l" || args[2] != "--" {
+		f.executedReal = true
+		return nil, nil, nil
+	}
+	binary := args[3]
+	if f.denyBinary[binary] {
+		return nil, nil, errors.New("sudo: a password is required")
+	}
+	return nil, nil, nil
+}
+
+func find(statuses []Status, name string) Status {
+	for _, s := range statuses {
+		if s.Name == name {
+			return s
+		}
+	}
+	return Status{}
+}
+
+// §7-A: all grants present + binaries exist → every capability ok.
+func TestProbe_AllOK(t *testing.T) {
+	r := &fakeRunner{denyBinary: map[string]bool{}}
+	p := Prober{Runner: r, Exists: func(string) bool { return true }}
+	statuses := p.Probe(context.Background())
+	ok, total, degraded := Summarize(statuses)
+	if total != len(Manifest()) {
+		t.Fatalf("total=%d want %d", total, len(Manifest()))
+	}
+	if ok != total || len(degraded) != 0 {
+		t.Fatalf("expected all ok, got %d/%d (degraded: %+v)", ok, total, degraded)
+	}
+	if r.executedReal {
+		t.Fatal("probe executed a command without -l (must be list-only)")
+	}
+}
+
+// §7-B: one grant denied → that capability degraded "sudo policy denied", others ok. Serve-degraded.
+func TestProbe_OneDenied(t *testing.T) {
+	r := &fakeRunner{denyBinary: map[string]bool{"/usr/bin/lxc-info": true}}
+	p := Prober{Runner: r, Exists: func(string) bool { return true }}
+	statuses := p.Probe(context.Background())
+
+	gi := find(statuses, "guest-init-pid")
+	if gi.Status != StatusDegraded || gi.Reason != "sudo policy denied" {
+		t.Fatalf("guest-init-pid = %+v, want degraded/sudo policy denied", gi)
+	}
+	if !gi.Critical {
+		t.Fatal("guest-init-pid should be Critical")
+	}
+	// A sibling stays ok.
+	if s := find(statuses, "drive-bind"); s.Status != StatusOK {
+		t.Fatalf("drive-bind = %+v, want ok", s)
+	}
+	ok, total, _ := Summarize(statuses)
+	if ok != total-1 {
+		t.Fatalf("expected exactly one degraded, got ok=%d total=%d", ok, total)
+	}
+}
+
+// §7-D: binary missing but policy granted → degraded "binary not found".
+func TestProbe_BinaryMissing(t *testing.T) {
+	r := &fakeRunner{denyBinary: map[string]bool{}}
+	p := Prober{Runner: r, Exists: func(path string) bool { return path != "/usr/bin/lxc-info" }}
+	statuses := p.Probe(context.Background())
+	gi := find(statuses, "guest-init-pid")
+	if gi.Status != StatusDegraded || gi.Reason != "binary not found" {
+		t.Fatalf("guest-init-pid = %+v, want degraded/binary not found", gi)
+	}
+}
+
+// §8 aggregate: sudo itself unavailable for the user → ONE aggregate degraded, not N.
+func TestProbe_SudoUnavailableAggregates(t *testing.T) {
+	r := &fakeRunner{preflightErr: errors.New("Sorry, user felhom-agent may not run sudo"), denyBinary: map[string]bool{}}
+	p := Prober{Runner: r, Exists: func(string) bool { return true }}
+	statuses := p.Probe(context.Background())
+	if len(statuses) != 1 {
+		t.Fatalf("expected 1 aggregate status, got %d", len(statuses))
+	}
+	s := statuses[0]
+	if s.Name != "sudo" || s.Status != StatusDegraded || !s.Critical || !strings.Contains(s.Reason, "drop-in not installed") {
+		t.Fatalf("aggregate = %+v, want critical degraded sudo-unavailable", s)
+	}
+}
+
+// Probe must never raise — even with a nil runner (e.g. a dev path) it returns statuses.
+func TestProbe_NilRunnerNoPanic(t *testing.T) {
+	p := Prober{Runner: nil, Exists: func(string) bool { return true }}
+	if got := len(p.Probe(context.Background())); got != len(Manifest()) {
+		t.Fatalf("nil-runner probe returned %d statuses, want %d", got, len(Manifest()))
+	}
+}
@@ -6,6 +6,7 @@ import (
 	"log/slog"
 	"time"

+	"gitea.dooplex.hu/admin/felhom-agent/internal/capability"
 	"gitea.dooplex.hu/admin/felhom-agent/internal/proxmox"
 )

@@ -57,7 +58,8 @@ type Collector struct {
 	backups      BackupReporter
 	restoreTests RestoreTestReporter
 	pbs          PBSReporter
-	temp         TempReader // slice 9: host CPU/chassis temp (nil-safe → nil temp)
+	temp         TempReader                                    // slice 9: host CPU/chassis temp (nil-safe → nil temp)
+	capProbe     func(ctx context.Context) []capability.Status // v0.44.0: privileged-capability self-check (nil → empty)
 	hostID       string
 	agentVersion string
 	logger       *slog.Logger
@@ -92,6 +94,13 @@ func (c *Collector) SetTempReader(t TempReader) *Collector {
 	return c
 }

+// SetCapabilityProber wires the privileged-capability self-check (v0.44.0): each collect runs it
+// and attaches the snapshot. nil → the report carries an empty []. Returns the collector for chaining.
+func (c *Collector) SetCapabilityProber(probe func(ctx context.Context) []capability.Status) *Collector {
+	c.capProbe = probe
+	return c
+}
+
 // Collect builds the report. Best-effort liveness: a failed NodeStatus is a hard
 // error (no useful report — the cycle skips the POST); a failed per-guest
 // GuestConfig degrades that guest to status="unknown" without spec but still sends;
@@ -117,8 +126,9 @@ func (c *Collector) Collect(ctx context.Context) (*HostReport, error) {
 		RestoreTests:   c.collectRestoreTests(ctx),
 		PBSSnapshots:   c.collectPBSSnapshots(ctx),

-		AuditTail:   []AuditEntry{},
-		Cloudflared: Cloudflared{Status: c.cloudflaredStatus(ctx)},
+		AuditTail:    []AuditEntry{},
+		Cloudflared:  Cloudflared{Status: c.cloudflaredStatus(ctx)},
+		Capabilities: c.capabilities(ctx),
 	}
 	// DR recipe host-half — derived from the just-collected guest/storage/PBS facts (no new reads).
 	// Secret-free by construction (identifiers/intents/sizes/coordinates only).
@@ -126,6 +136,18 @@ func (c *Collector) Collect(ctx context.Context) (*HostReport, error) {
 	return report, nil
 }

+// capabilities runs the privileged-capability self-check for this report (v0.44.0), or returns an
+// empty (non-nil) slice when no prober is wired (dev/test). Never fatal — serve-degraded.
+func (c *Collector) capabilities(ctx context.Context) []capability.Status {
+	if c.capProbe == nil {
+		return []capability.Status{}
+	}
+	if s := c.capProbe(ctx); s != nil {
+		return s
+	}
+	return []capability.Status{}
+}
+
 // HostMetricsNow does a FRESH NodeStatus + CPU-temp read and returns just the host block (no
 // guests/storage). It is the source for the local API's GET /host/metrics (slice 9) — current
 // cpu%/temp, not the 15-min hub-report snapshot. Storage targets come from the observer
@@ -1,6 +1,10 @@
 package hub

-import "encoding/json"
+import (
+	"encoding/json"
+
+	"gitea.dooplex.hu/admin/felhom-agent/internal/capability"
+)

 // HostReport is the wire contract shared with the hub's ingest
 // (felhom.eu TASK-slice3-hub-ingest). Field NAMES must match the hub
@@ -27,6 +31,11 @@ type HostReport struct {
 	Cloudflared Cloudflared  `json:"cloudflared"`
 	AuditTail   []AuditEntry `json:"audit_tail"` // populated by a later slice

+	// Capabilities is the agent's privileged-capability self-check snapshot (v0.44.0): per required
+	// `sudo -n` grant, whether it is permitted + the binary exists. The hub keys its operator alert
+	// on a Critical capability flipping to "degraded". Non-nil so it marshals as [].
+	Capabilities []capability.Status `json:"capabilities"`
+
 	// DR recipe — the agent (storage/guest/PBS) half of the secret-free reconstruction recipe
 	// (SPIKE-dr-recipe-2026-06-16). Derived from the facts above; carries ONLY identifiers/intents/
 	// sizes/coordinates, never a secret. The hub assembles it with the controller's app half.
@@ -4,6 +4,8 @@ import (
 	"encoding/json"
 	"strings"
 	"testing"
+
+	"gitea.dooplex.hu/admin/felhom-agent/internal/capability"
 )

 func TestHostReport_FieldNamesAndEmptyCollections(t *testing.T) {
@@ -28,6 +30,7 @@ func TestHostReport_FieldNamesAndEmptyCollections(t *testing.T) {
 		PBSSnapshots:   []PBSSnapshot{},
 		AuditTail:      []AuditEntry{},
 		Cloudflared:    Cloudflared{Status: "active"},
+		Capabilities:   []capability.Status{},
 	}
 	// dr_recipe is always set on the real path (Collect); set it here too so the "no null" invariant
 	// covers it (empty pbs is omitempty → omitted, never null).
@@ -46,6 +49,7 @@ func TestHostReport_FieldNamesAndEmptyCollections(t *testing.T) {
 		`"cloudflared":{"status":"active"}`,
 		// empty collections must be [] not null
 		`"storage_targets":[]`, `"backups":[]`, `"restore_tests":[]`, `"pbs_snapshots":[]`, `"audit_tail":[]`,
+		`"capabilities":[]`,
 	} {
 		if !strings.Contains(got, field) {
 			t.Errorf("report JSON missing %s\n got: %s", field, got)
@@ -132,6 +132,7 @@
  ],
  "cloudflared": { "status": "active" },
  "audit_tail": [],
+  "capabilities": [],
  "dr_recipe": {
    "recipe_version": 1,
    "guests": [