fix(#2332): add After=hive-tls-ca to resign service — prevent first-boot CA race

On a fresh deploy Persistent=true causes the weekly timer to fire
immediately. Without this ordering hive-tls-resign can race
hive-tls-ca before the CA key is written, failing the resign.
CA is always valid when this runs; resign is a no-op if the leaf
is still within its half-life margin.

Suggested by argus (review) + requested by mara.

nix/modules/hive-tls.nix

@@ -73,13 +73,10 @@ in
         when it is missing or near expiry; because it shares the CA
         anchor, a rotation does not disturb consumer trust. Agents and
         federation peers validate against the CA, not browser CA/B-forum
-        limits. NOTE: at this short a window the re-sign must run more
-        often than the leaf lifetime. Today `hive-tls-ca` re-signs at
-        service activation (boot/rebuild) only — there is no periodic
-        re-sign timer yet — so a hive that does not reboot within the
-        validity window would let the leaf expire. Keep that in mind (or
-        add a re-sign timer) when running a hive that stays up for long
-        stretches without a rebuild.
+        limits. The weekly `hive-tls-resign` timer re-signs the leaf once
+        it is within half its validity of expiry and propagates the new
+        leaf into the running gateway, so a long-uptime host renews
+        automatically without a reboot.
       '';
     };
   };
@@ -165,6 +162,109 @@ in
       '';
     };
 
+    # Weekly re-sign of the gateway leaf so short-lived leaves renew
+    # without depending on a reboot.
+    #
+    # `hive-tls-ca` only re-signs at service activation (boot/rebuild); a
+    # long-uptime host would otherwise let a 30-day leaf lapse silently.
+    # This service re-signs the leaf directly (not by bouncing hive-tls-ca)
+    # and propagates the new leaf into the running gateway container when
+    # the file actually changed.
+    #
+    # Propagation mechanism: nginx in the gateway container serves a *copy*
+    # of the leaf written by `hive-gateway-self-signed-cert` (which runs at
+    # container start). A host-side `systemctl -M hive-gateway` call
+    # triggers the re-import + reload, mirroring how hive-c0re reloads the
+    # gateway after each agents.conf write. A path unit *inside* the
+    # container was tried first but does not work: IN_MOVED_TO from an
+    # atomic rename on the host does not propagate across the nspawn
+    # mount-namespace boundary.
+    #
+    # `|| true` on propagation so a stopped gateway never fails the unit —
+    # its next boot will import the already-rotated leaf anyway.
+    systemd.services.hive-tls-resign = {
+      description = "Re-sign the gateway TLS leaf and propagate it into the gateway container";
+      # hive-tls-ca must have run first so the CA key exists before we try
+      # to re-sign under it. On first boot `Persistent=true` on the weekly
+      # timer fires immediately; without this ordering the resign could race
+      # the CA initialisation and fail with "no such file" on the CA key.
+      after = [ "hive-tls-ca.service" ];
+      path = [
+        pkgs.openssl
+        pkgs.coreutils
+        pkgs.systemd
+      ];
+      serviceConfig = {
+        Type = "oneshot";
+        UMask = "0077";
+        SyslogIdentifier = "hive-tls-resign";
+      };
+      script = ''
+        set -euo pipefail
+        d=${lib.escapeShellArg cfg.stateDir}
+        ca="$d/ca.pem"
+        cak="$d/ca-key.pem"
+        leaf="$d/gateway.pem"
+        leafk="$d/gateway-key.pem"
+
+        # Re-sign only when the leaf is within half its validity of expiry.
+        # The weekly cadence catches this window well before the leaf lapses.
+        halflife=$(( ${toString cfg.leafValidityDays} * 86400 / 2 ))
+        if [ -s "$leaf" ] && \
+            openssl x509 -in "$leaf" -noout -checkend "$halflife" >/dev/null 2>&1; then
+          echo "gateway leaf valid for more than half its lifetime — no resign needed"
+          exit 0
+        fi
+
+        echo "gateway leaf missing or near expiry — re-signing under current CA"
+        before="$(sha256sum "$leaf" 2>/dev/null || true)"
+
+        csr="$(mktemp "$d/gateway.csr.XXXXXX")"
+        ext="$(mktemp "$d/leaf.ext.XXXXXX")"
+        trap 'rm -f "$csr" "$ext"' EXIT
+
+        openssl req -newkey rsa:4096 -nodes -sha256 \
+          -keyout "$leafk" -out "$csr" \
+          -subj "/CN=${domain}"
+
+        {
+          printf 'subjectAltName=DNS:%s,DNS:forge.%s,DNS:matrix.%s,DNS:*.%s\n' \
+            ${lib.escapeShellArg domain} ${lib.escapeShellArg domain} \
+            ${lib.escapeShellArg domain} ${lib.escapeShellArg domain}
+          printf 'basicConstraints=critical,CA:FALSE\n'
+          printf 'keyUsage=critical,digitalSignature,keyEncipherment\n'
+          printf 'extendedKeyUsage=serverAuth\n'
+        } > "$ext"
+
+        openssl x509 -req -in "$csr" -CA "$ca" -CAkey "$cak" \
+          -CAcreateserial -days ${toString cfg.leafValidityDays} -sha256 \
+          -extfile "$ext" -out "$leaf"
+        chmod 0600 "$leafk"
+        chmod 0644 "$leaf"
+
+        after="$(sha256sum "$leaf" 2>/dev/null || true)"
+        if [ "$before" != "$after" ]; then
+          echo "gateway leaf rotated — propagating into hive-gateway"
+          systemctl -M hive-gateway restart hive-gateway-self-signed-cert.service || true
+          systemctl -M hive-gateway reload nginx.service || true
+        else
+          echo "gateway leaf unchanged (already up to date)"
+        fi
+      '';
+    };
+
+    systemd.timers.hive-tls-resign = {
+      description = "Weekly gateway-leaf re-sign and propagation";
+      wantedBy = [ "timers.target" ];
+      timerConfig = {
+        # Run weekly; Persistent=true fires a missed run on next boot if
+        # the timer was not active (e.g. the host was off on the scheduled
+        # day), preventing a dormant timer from letting the leaf lapse.
+        OnCalendar = "weekly";
+        Persistent = true;
+      };
+    };
+
     # Signal the hive-c0re lifecycle that a hive CA exists: it bind-mounts
     # this file (read-only, the CA cert ONLY — never the key) into each
     # agent container so agents + their tools can trust the gateway's