R-982 (D4): root SSH from the LAN by key only — a bundle drop-in, checked and reloaded by felhom-os-apply; R-1204: the heartbeat reports a future-stamped tunnel handshake; unreleased

CHANGELOG.md

@@ -1,3 +1,20 @@
+## Unreleased (2026-10-22 night) — root SSH from the LAN by key only (R-982, operator ruling D4); the tunnel's future-stamped handshake is reported (R-1204) — COMMITTED, NOT RELEASED (no agent release tonight)
+
+- **R-982 / D4 — the host's own sshd: root by key only.** New bundle file `/etc/ssh/sshd_config.d/10-felhom-root-key-only.conf`
+  (`PermitRootLogin prohibit-password`; source `configs/felhom-root-ssh-key-only.conf`, policy `replace`). Debian's
+  `sshd_config` reads that folder before its own `PermitRootLogin yes`, and the first value wins (read on demo-hp).
+  The root password still works on the console; the operator's door (felhom-sshd, port 8822) reads only
+  `/etc/felhom-sshd/sshd_config`, which includes nothing from there. `felhom-os-apply`: a new content check `sshd`
+  (`sshd -t -f` on the snippet, and the snippet must set exactly `PermitRootLogin prohibit-password` — `yes` undoes the
+  ruling, `no` would shut the root KEY out too), and after an install that wrote it: `sshd -t` (the whole config; a
+  failure is a refusal and the bundle undo puts the old files back), then `systemctl reload ssh` (open sessions stay).
+  A new box gets it from the installer's `--install-bundle` (the same bundle). Tests `RootKeyOnly` (3) in
+  `configs/test_felhom_config_bundle.py`, red-proved both ways.
+- **R-1204 — `wireguard.handshake_future_s`.** A box that ran once with its clock ahead keeps a handshake stamped in the
+  future; ep0 refuses every newer one, and `last_handshake_age_s` (clamped at 0) read „just now" for ever. The heartbeat
+  now carries how many seconds the handshake lies ahead (> 60 s only); the age keeps its clamp. The hub alarms on it
+  (felhom.eu hub `wg_tunnel_stale`). Test `TestR1204_AFutureHandshakeIsReported`, red-proved.
+
 ## v0.162.0 — every guest may swap as much as its RAM (R-1192, the 8 GB freeze); the host's swap is reported and checked; no false „operator access degraded" on a fresh box (R-1194) (2026-10-22) — RELEASED on the operator's yes; the vouch is the operator's
 
 Released 2026-10-22 07:40 UTC (operator yes, the morning answers) with `scripts/release-agent.sh` from a clean clone at

configs/felhom-os-apply

@@ -165,7 +165,8 @@ KERNEL_ACTIVE = ("staged", "oneshot", "judging", "reverting")
 #   dest: (source file under configs/, mode, check, policy)
 # check:  the content check BEFORE anything is written (R18): sudoers → visudo -cf; sh / bash → -n; python → compile;
 #         unit → a [Unit]/[Service]/[Timer] section; unit-nort → that, and never RuntimeDirectory= (the G1 incident);
-#         agent-unit → User=felhom-agent; dropin → a [Unit] section (SF-3); nft → nft -c -f; plain → none.
+#         agent-unit → User=felhom-agent; dropin → a [Unit] section (SF-3); nft → nft -c -f; plain → none;
+#         sshd → `sshd -t -f` on the snippet alone (R-982).
 # policy: replace → always written when it differs; if-absent → only when the box has none (a setting the operator may
 #         have tuned); oob → only on a box with the OOB belt (/etc/felhom-sshd exists — the installer's --no-oob leaves none).
 # Order matters: the sudoers files come LAST, so a referenced wrapper is in place before the line that allows it.
@@ -221,6 +222,9 @@ BUNDLE_FILES = [
     ("/etc/systemd/system/felhom-sshd.service", "felhom-sshd.service", 0o644, "unit-nort", "oob"),
     ("/etc/felhom-oob.nft", "felhom-oob.nft", 0o644, "nft", "oob"),
     ("/etc/systemd/system/felhom-oob-nft.service", "felhom-oob-nft.service", 0o644, "unit", "oob"),
+    # R-982, operator ruling D4 (2026-10-22): the host's own sshd (port 22, the LAN): root by key only. The console
+    # password stays; felhom-sshd (the operator's door) reads nothing from sshd_config.d. Reloaded in after_install.
+    ("/etc/ssh/sshd_config.d/10-felhom-root-key-only.conf", "felhom-root-ssh-key-only.conf", 0o644, "sshd", "replace"),
     ("/etc/sudoers.d/felhom-op", "felhom-op.sudoers", 0o440, "sudoers", "oob"),
     ("/etc/sudoers.d/felhom-agent", "felhom-agent.sudoers", 0o440, "sudoers", "replace"),
 ]
@@ -434,7 +438,8 @@ class Runner:
     def check_content(self, kind, data):
         """Run an external syntax check on a root-only temp copy. Returns (rc, message)."""
         import tempfile
-        cmd = {"sudoers": ["visudo", "-cf"], "sh": ["sh", "-n"], "bash": ["bash", "-n"], "nft": ["nft", "-c", "-f"]}[kind]
+        cmd = {"sudoers": ["visudo", "-cf"], "sh": ["sh", "-n"], "bash": ["bash", "-n"], "nft": ["nft", "-c", "-f"],
+               "sshd": ["/usr/sbin/sshd", "-t", "-f"]}[kind]
         with tempfile.TemporaryDirectory(prefix="felhom-bundle-") as d:
             p = os.path.join(d, "f")
             with open(p, "wb") as f:
@@ -1932,10 +1937,16 @@ class Bundle:
             text = content.decode("utf-8")
         except UnicodeDecodeError:
             raise Refused("R18", f"{dest} is not UTF-8 text")
-        if check in ("sudoers", "sh", "bash", "nft"):
+        if check in ("sudoers", "sh", "bash", "nft", "sshd"):
             rc, msg = self.r.check_content(check, content)
             if rc != 0:
                 raise Refused("R18", f"{dest} fails its {check} check: {msg}")
+        if check == "sshd":
+            # R-982: the drop-in may only ever make root KEY-ONLY. `no` would also shut the root key out (Proxmox's own
+            # node-to-node SSH and the LAN key route), `yes` would undo the ruling — both refused.
+            vals = re.findall(r"^\s*PermitRootLogin\s+(\S+)\s*$", text, re.M | re.I)
+            if vals != ["prohibit-password"]:
+                raise Refused("R18", f"{dest} must set exactly `PermitRootLogin prohibit-password` (found {vals})")
         elif check == "python":
             try:
                 compile(text, dest, "exec")
@@ -2073,6 +2084,12 @@ class Bundle:
                       "enable the crash guard")
         if "/etc/systemd/system/felhom-mgmt-watchdog.timer" in dests:
             self.must(["systemctl", "enable", "--now", "felhom-mgmt-watchdog.timer"], "enable the mgmt watchdog timer")
+        # R-982: the host's sshd takes the root-key-only drop-in. The WHOLE config is tested first (a failure is a
+        # refusal, and the bundle undo puts the old files back); `reload` keeps every open session, including the
+        # operator's. felhom-sshd is not touched.
+        if "/etc/ssh/sshd_config.d/10-felhom-root-key-only.conf" in written:
+            self.must(["/usr/sbin/sshd", "-t"], "sshd -t (the host's whole sshd config)")
+            self.must(["systemctl", "reload", "ssh"], "systemctl reload ssh")
 
     def must(self, argv, what):
         rc, out, err = self.r.host(argv, 120)

configs/felhom-root-ssh-key-only.conf

@@ -0,0 +1,7 @@
+# MANAGED BY FELHOM (the agent's config bundle) — R-982, operator ruling D4 (2026-10-22).
+# The Proxmox host's OWN sshd — the listener the household network reaches on port 22: root logs in with a KEY only.
+# The root password still works on the console (the break-glass password, `03` §8a). The operator's door
+# (felhom-sshd, port 8822, /etc/felhom-sshd/sshd_config) is a separate daemon whose config includes nothing from
+# here, so it is not changed. Debian's sshd_config reads this folder BEFORE its own `PermitRootLogin yes`, and for
+# sshd the first value wins.
+PermitRootLogin prohibit-password

configs/test_felhom_config_bundle.py

@@ -429,6 +429,48 @@ class SelfCheckUndo(unittest.TestCase):
         self.assert_restored(box, before, rep)
 
 
+
+class RootKeyOnly(unittest.TestCase):
+    """R-982, operator ruling D4 (2026-10-22): the bundle gives the host's own sshd a root-key-only drop-in, tests the
+    whole config and reloads sshd — only when the file was written; a drop-in that says anything but
+    `prohibit-password` is refused before anything is written.
+    RED-PROOF: with the after_install block removed, test_fresh_box_takes_the_dropin_and_reloads fails (no reload);
+    with the content rule removed, test_a_dropin_that_says_yes_or_no_is_refused fails — seen failing 2026-10-22."""
+    DEST = "/etc/ssh/sshd_config.d/10-felhom-root-key-only.conf"
+
+    def test_fresh_box_takes_the_dropin_and_reloads(self):
+        data, sha = real_bundle()
+        box = Box(data, signed_job(sha))
+        rc, rep = run(box)
+        self.assertEqual(rc, 0, rep)
+        self.assertIn(b"PermitRootLogin prohibit-password", box.files[self.DEST])
+        self.assertEqual(box.modes[self.DEST], 0o644)
+        self.assertIn(["/usr/sbin/sshd", "-t"], box.calls)
+        self.assertIn(["systemctl", "reload", "ssh"], box.calls)
+        self.assertLess(box.calls.index(["/usr/sbin/sshd", "-t"]), box.calls.index(["systemctl", "reload", "ssh"]))
+        self.assertFalse(any("felhom-sshd" in " ".join(c) for c in box.calls), "the operator's door must not be touched")
+
+    def test_an_unchanged_dropin_is_not_reloaded(self):
+        data, sha = real_bundle()
+        box = Box(data, signed_job(sha))
+        box.put(self.DEST, (REPO / "configs" / "felhom-root-ssh-key-only.conf").read_bytes(), 0o644)
+        rc, rep = run(box)
+        self.assertEqual(rc, 0, rep)
+        self.assertNotIn(["systemctl", "reload", "ssh"], box.calls)
+
+    def test_a_dropin_that_says_yes_or_no_is_refused(self):
+        for bad in (b"PermitRootLogin yes\n", b"PermitRootLogin no\n", b"# nothing\n",
+                    b"PermitRootLogin prohibit-password\nPermitRootLogin yes\n"):
+            def edit(files, bad=bad):
+                for e in files:
+                    if e["path"] == self.DEST:
+                        e["content_b64"] = base64.b64encode(bad).decode()
+            data, sha = edited_bundle(edit)
+            box = Box(data, signed_job(sha))
+            rc, rep = run(box)
+            self.assertNotEqual(rc, 0, bad)
+            self.assertNotIn(self.DEST, box.files, bad)
+
 class TrustBootstrap(unittest.TestCase):
     def test_missing_signers_verifies_against_the_pinned_key_and_creates_it(self):
         data, sha = real_bundle()

internal/hub/report.go

@@ -292,7 +292,11 @@ type WireguardStatus struct {
 	Registered        bool   `json:"registered"` // the registration marker exists
 	Active            bool   `json:"active"`     // wg-quick@wg-felhom is-active
 	LastHandshakeAgeS *int64 `json:"last_handshake_age_s,omitempty"`
-	AssignedIP        string `json:"assigned_ip,omitempty"` // from the marker, e.g. "10.77.0.2/32"
+	// HandshakeFutureS (R-1204): seconds the latest handshake lies in the FUTURE by this box's clock — set (> 0) only
+	// then. A box that ran once with its clock ahead keeps a handshake stamped in the future; WireGuard on ep0 then
+	// refuses every newer handshake, and LastHandshakeAgeS (clamped at 0) reads „just now" for ever. The hub alarms on it.
+	HandshakeFutureS *int64 `json:"handshake_future_s,omitempty"`
+	AssignedIP       string `json:"assigned_ip,omitempty"` // from the marker, e.g. "10.77.0.2/32"
 }
 
 // SystemInfo is the `system` stanza (see HostReport.System).

internal/wgtunnel/manager.go

@@ -661,6 +661,9 @@ func (m *Manager) Status(ctx context.Context) *hub.WireguardStatus {
 			if age, ok := parseHandshakeAge(string(out), m.now()); ok {
 				st.LastHandshakeAgeS = &age
 			}
+			if fut, ok := handshakeFuture(string(out), m.now()); ok {
+				st.HandshakeFutureS = &fut
+			}
 		}
 	}
 	if st.Pubkey == "" && !st.Registered && !st.Active {
@@ -669,6 +672,28 @@ func (m *Manager) Status(ctx context.Context) *hub.WireguardStatus {
 	return st
 }
 
+// handshakeFuture (R-1204) reports how many seconds the latest handshake lies in the future, ok only when it does
+// (by more than a minute — clock jitter is not the case). parseHandshakeAge clamps that case to 0 („just now"), which
+// is what made a box whose clock had run ahead look healthy while ep0 refused its tunnel. Pinned by
+// TestR1204_AFutureHandshakeIsReported.
+func handshakeFuture(out string, now time.Time) (int64, bool) {
+	for _, line := range strings.Split(strings.TrimSpace(out), "\n") {
+		f := strings.Fields(line)
+		if len(f) != 2 {
+			continue
+		}
+		epoch, err := strconv.ParseInt(f[1], 10, 64)
+		if err != nil || epoch <= 0 {
+			continue
+		}
+		if fut := epoch - now.Unix(); fut > 60 {
+			return fut, true
+		}
+		return 0, false
+	}
+	return 0, false
+}
+
 // parseHandshakeAge parses `wg show <if> latest-handshakes` output ("<peer-pub>\t<epoch>").
 // epoch 0 = no handshake yet → not ok (nil in the report; nil ≠ 0).
 func parseHandshakeAge(out string, now time.Time) (int64, bool) {

internal/wgtunnel/manager_test.go

@@ -696,3 +696,31 @@ func TestInitialResolveFailureNoTeardown(t *testing.T) {
 		t.Errorf("did not recover after DNS returned: %v", rr.calls)
 	}
 }
+
+// R-1204: a box that ran once with its clock ahead keeps a handshake stamped in the FUTURE — ep0 then refuses every
+// newer one. The age stays clamped at 0 (unchanged contract), and the new field says how far ahead it lies; a
+// handshake in the past (or within a minute of now) never sets it.
+// RED-PROOF: with Status not setting HandshakeFutureS the first assertion fails — seen failing 2026-10-22.
+func TestR1204_AFutureHandshakeIsReported(t *testing.T) {
+	fh := &fakeHub{}
+	m, _, active, _ := testManager(t, fh)
+	ctx := context.Background()
+	m.Apply(ctx, false, nil)
+	*active = true
+	m.now = func() time.Time { return time.Unix(1783107115-2*24*3600, 0) } // the clock came back two days earlier
+	st := m.Status(ctx)
+	if st.HandshakeFutureS == nil || *st.HandshakeFutureS != 2*24*3600 {
+		t.Fatalf("handshake_future_s = %v, want %d", st.HandshakeFutureS, 2*24*3600)
+	}
+	if st.LastHandshakeAgeS == nil || *st.LastHandshakeAgeS != 0 {
+		t.Fatalf("the age stays clamped at 0: %v", st.LastHandshakeAgeS)
+	}
+	m.now = func() time.Time { return time.Unix(1783107115+100, 0) }
+	if st = m.Status(ctx); st.HandshakeFutureS != nil {
+		t.Fatalf("a past handshake must not set handshake_future_s: %v", *st.HandshakeFutureS)
+	}
+	m.now = func() time.Time { return time.Unix(1783107115-30, 0) } // 30 s of jitter is not the case
+	if st = m.Status(ctx); st.HandshakeFutureS != nil {
+		t.Fatalf("clock jitter must not set handshake_future_s")
+	}
+}