night 2026-10-22: D4 as two ready patches (agent bundle + installer uninstall) — a push of the installer would publish it

2026-10-22 17:11:07 +02:00
parent e267c5e2cd
commit 1100a344d5
2 changed files with 166 additions and 0 deletions
@@ -0,0 +1,137 @@
+commit a0c88e5183838ebad04d5aad4acb3e05e1c1c153
+Author: kisfenyo <nagyfenyvesi.viktor@gmail.com>
+Date:   Thu Oct 22 16:58:45 2026 +0200
+
+    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
+
+diff --git a/configs/felhom-os-apply b/configs/felhom-os-apply
+index 81565fb..3b6fc9a 100755
+--- a/configs/felhom-os-apply
+++ b/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)
+diff --git a/configs/felhom-root-ssh-key-only.conf b/configs/felhom-root-ssh-key-only.conf
+new file mode 100644
+index 0000000..f2ff547
+--- /dev/null
+++ b/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
+diff --git a/configs/test_felhom_config_bundle.py b/configs/test_felhom_config_bundle.py
+index 1c5a6ab..74f983d 100644
+--- a/configs/test_felhom_config_bundle.py
+++ b/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()
@@ -0,0 +1,29 @@
+diff --git a/scripts/felhom-host-install.sh b/scripts/felhom-host-install.sh
+index 970109fd..349da0c5 100644
+--- a/scripts/felhom-host-install.sh
+++ b/scripts/felhom-host-install.sh
+@@ -1417,6 +1417,12 @@ run_uninstall() {
+     if [[ -f /etc/default/grub.d/zz-felhom-kernel-default.cfg ]]; then
+         log_info "  kept /etc/default/grub.d/zz-felhom-kernel-default.cfg (the kernel this box booted healthily stays the default)"
+     fi
+    # R-982 (operator ruling D4, 2026-10-22; agent bundle after v0.162.0): the host sshd's root-key-only drop-in. The
+    # uninstall gives the host back as Proxmox set it up, so the drop-in goes and sshd is reloaded (open sessions stay).
+    if [[ -f /etc/ssh/sshd_config.d/10-felhom-root-key-only.conf ]]; then
+        run rm -f /etc/ssh/sshd_config.d/10-felhom-root-key-only.conf
+        run systemctl reload ssh 2>/dev/null || true
+    fi
+     # 1.31.0 (R-840): the bundle's previous copies and the wrapper's nonce record.
+     if [[ -d /var/lib/felhom-os-apply ]]; then run rm -rf /var/lib/felhom-os-apply; fi
+     if [[ -f /var/lib/vz/snippets/felhom-guest-hook.sh ]]; then run rm -f /var/lib/vz/snippets/felhom-guest-hook.sh; fi
+diff --git a/scripts/test_hostinstall.py b/scripts/test_hostinstall.py
+index 3f7088a6..e9cf9ad9 100644
+--- a/scripts/test_hostinstall.py
+++ b/scripts/test_hostinstall.py
+@@ -60,6 +60,7 @@ BUNDLE_DESTS = [
+     "/etc/systemd/system/felhom-sshd.service",
+     "/etc/felhom-oob.nft",
+     "/etc/systemd/system/felhom-oob-nft.service",
+    "/etc/ssh/sshd_config.d/10-felhom-root-key-only.conf",   # R-982, operator ruling D4 (2026-10-22)
+     "/etc/sudoers.d/felhom-op",
+     "/etc/sudoers.d/felhom-agent",
+ ]