fix(nix): drop the swarm-service-domain assertion, it asserted intent

Measured against a real config, not reasoned about: pinning
`swarm.forge.domain = "forge.<hive domain>"` while `swarm.domain` is a
different apex -- the documented way an existing deployment keeps its
names while joining a swarm -- FAILED eval under this assertion.

And the reason it gave was false. It said those names are certified by
the services sub-CA, "which is constrained to the swarm's own tree, so a
name outside it has no issuer here". The sub-CA is constrained to the
**configured names** (swarm-ca.nix builds its nameConstraints from the
derived list), and the swarm root carries no name constraints at all --
only basicConstraints and keyUsage. So any configured name is issuable,
and a legacy name under the hive domain is additionally signable by the
hive CA.

The assertion therefore encoded the shape I had in mind rather than a
constraint the code implements, and it rejected a configuration that
works. Removed rather than weakened: a narrower version would still
carry a claim nothing backs.

`serviceDomains` stays -- it feeds the sub-CA's name constraints, the
leaf's SANs and the per-vhost cert choice, and those three agreeing is
the thing that mattered. The (option, value) pairs collapse back to a
plain list, since the provenance existed only for the assertion message.

nix/host-modules/hive-gateway/default.nix

@@ -15,6 +15,10 @@
 let
   cfg = config.services.hyperhive.gateway;
   hyperhiveDomain = config.services.hyperhive.domain;
+  # Derived once in ../swarm.nix; the vhosts that get the swarm-services
+  # cert are exactly the names that cert is issued for, so both read the
+  # same list rather than each deciding what "a swarm service" means.
+  swarmServiceDomains = config.services.hyperhive.swarm.serviceDomains;
   matrixCfg = config.services.hyperhive.swarm.matrix;
   forgeCfg = config.services.hyperhive.swarm.forge;
   networkCfg = config.services.hyperhive.network;
@@ -263,6 +267,12 @@ in
             if cfg.tls.certDir != null then "/run/hive-tls/${cfg.tls.certName}" else "${tlsDir}/cert.pem";
           tlsKey =
             if cfg.tls.certDir != null then "/run/hive-tls/${cfg.tls.keyName}" else "${tlsDir}/key.pem";
+          # The swarm-services pair, used only by the vhosts whose names
+          # this hive's CA cannot sign. Self-signed mode only: with an
+          # operator cert or ACME the operator owns every name and there
+          # is no second issuer in the picture.
+          svcCert = "${tlsDir}/swarm-services.pem";
+          svcKey = "${tlsDir}/swarm-services-key.pem";
           nginxTree = import ./vhosts.nix {
             inherit
               lib
@@ -274,6 +284,9 @@ in
               swaggerUiTheme
               tlsCert
               tlsKey
+              svcCert
+              svcKey
+              swarmServiceDomains
               ;
             errorPages = import ./error-pages.nix { inherit pkgs; };
           };
@@ -362,6 +375,23 @@ in
               # Permission denied`, blocking the unit. Cert is world-read.
               install -m 0644 /run/hive-ca/gateway.pem ${tlsCert}
               install -m 0640 -g nginx /run/hive-ca/gateway-key.pem ${tlsKey}
+
+              # The swarm-services leaf, when this host issues one. It is
+              # a separate pair rather than more SANs on the one above
+              # because no hive CA can sign these names — each is
+              # constrained to its own hive's domain and the service
+              # names are siblings of it.
+              #
+              # Absent is a normal state, not a failure: the leaf exists
+              # only where the swarm CA is autoconfigured. Copying it
+              # conditionally keeps a hive whose certs come from its
+              # operator working unchanged.
+              if [ -s /run/hive-ca/swarm-services.pem ]; then
+                install -m 0644 /run/hive-ca/swarm-services.pem ${svcCert}
+                install -m 0640 -g nginx /run/hive-ca/swarm-services-key.pem ${svcKey}
+              else
+                rm -f ${svcCert} ${svcKey}
+              fi
             '';
           };
 

nix/host-modules/hive-gateway/vhosts.nix

@@ -15,6 +15,9 @@
   errorPages, # ./error-pages.nix: { notFound, unreachable, unauthorized }
   tlsCert,
   tlsKey,
+  svcCert, # swarm-services leaf, for names the hive CA cannot sign
+  svcKey,
+  swarmServiceDomains, # which vhosts those are (../swarm.nix derives it)
 }:
 let
   # The gateway always terminates TLS: self-signed is the implicit
@@ -51,6 +54,25 @@ let
         sslCertificateKey = tlsKey;
       };
 
+  # TLS attrs for one vhost, by name. A swarm service's name may sit
+  # outside this hive's domain — and then the hive CA is
+  # name-constrained out of it, so its vhost must serve the
+  # swarm-services leaf instead. Everything else keeps the hive leaf.
+  #
+  # Only in self-signed mode: with ACME or an operator cert there is a
+  # single issuer that already covers every name, and a second pair
+  # would be a cert nobody asked for.
+  vhostTlsFor =
+    host:
+    if !cfg.tls.acme.enable && cfg.tls.certDir == null && builtins.elem host swarmServiceDomains then
+      {
+        addSSL = true;
+        sslCertificate = svcCert;
+        sslCertificateKey = svcKey;
+      }
+    else
+      vhostTls;
+
   # Public-facing scheme + port-suffix for URLs the gateway
   # mints into responses (well-known JSON, the deprecated
   # `<hive>/matrix/*` 301 redirect, future absolute-URL needs):
@@ -85,7 +107,7 @@ let
   # `forge.sshPort`. See `docs/gateway.md`. Empty attrset when the
   # forge isn't behind the gateway.
   forgeVhost = lib.optionalAttrs (forgeCfg.behindGateway or false) {
-    "${forgeCfg.domain}" = vhostTls // {
+    "${forgeCfg.domain}" = (vhostTlsFor forgeCfg.domain) // {
       listen = vhostListen;
       extraConfig = securityHeaders;
       locations."/" = {
@@ -107,7 +129,7 @@ let
   # longer-prefix-wins puts `/_matrix/` ahead of `/`. See
   # `docs/gateway.md`. Empty attrset when matrix has no gateway host.
   matrixVhost = lib.optionalAttrs (matrixCfg.enable && matrixCfg.gatewayHost != null) {
-    "${matrixCfg.gatewayHost}" = vhostTls // {
+    "${matrixCfg.gatewayHost}" = (vhostTlsFor matrixCfg.gatewayHost) // {
       listen = vhostListen;
       extraConfig = securityHeaders;
       locations = {

nix/host-modules/hive-tls.nix

@@ -10,6 +10,10 @@ let
   gatewayCfg = config.services.hyperhive.gateway;
   swarmCaCfg = config.services.hyperhive.swarm.ca;
   domain = hyperhiveCfg.domain;
+  # Derived once in ./swarm.nix and read here + in ./swarm-ca.nix, so
+  # the names this leaf carries as SANs and the names the sub-CA is
+  # constrained to cannot disagree.
+  swarmServiceDomains = hyperhiveCfg.swarm.serviceDomains;
 
   # The host-managed hive CA is the trust anchor for self-signed mode.
   # It is only stood up when the gateway actually serves a self-signed
@@ -20,13 +24,6 @@ let
   # neither an operator cert (`tls.certDir`) nor ACME is set.
   active = hyperhiveCfg.enable && gatewayCfg.useSelfSigned;
 
-  # The leaf-signing action shared by the boot-time `hive-tls-ca`
-  # generation and the weekly `hive-tls-resign` renewal: fresh key +
-  # CSR, SAN ext-file, sign under the (stable) CA, tighten modes.
-  # Takes the TLS state dir as `$1`; each caller keeps its own
-  # when-to-sign condition. The leaf covers the bare hive domain plus
-  # `forge.`, `matrix.` and `*.<domain>` so all sub-domains validate
-  # under the same cert + the hive CA.
   # How this hive's CA comes into existence when it is missing — and it
   # is one of exactly two things, chosen by config rather than by what
   # happens to be on disk.
@@ -97,28 +94,36 @@ let
           -addext "keyUsage=critical,keyCertSign,cRLSign"
       '';
 
+  # Sign one leaf. Parameterised rather than hardcoded to `gateway.*`
+  # because there are now two: the hive's own leaf, issued by the hive
+  # CA, and the swarm-services leaf, issued by the services sub-CA that
+  # ./swarm-ca.nix maintains. Same ceremony, different issuer and names
+  # — and one script means the two cannot drift in how they are built.
+  #
+  #   $1 stateDir  $2 basename  $3 CN  $4 SAN list  $5 issuer cert  $6 issuer key
   signLeafScript = pkgs.writeShellScript "hive-tls-sign-leaf" ''
     set -euo pipefail
     d="$1"
-    ca="$d/ca.pem"
+    base="$2"
-    cak="$d/ca-key.pem"
+    cn="$3"
-    leaf="$d/gateway.pem"
+    sans="$4"
-    leafk="$d/gateway-key.pem"
+    ca="$5"
-    csr="$(mktemp "$d/gateway.csr.XXXXXX")"
+    cak="$6"
-    ext="$(mktemp "$d/leaf.ext.XXXXXX")"
+    leaf="$d/$base.pem"
-    only="$(mktemp "$d/gateway.leaf.XXXXXX")"
+    leafk="$d/$base-key.pem"
+    csr="$(mktemp "$d/$base.csr.XXXXXX")"
+    ext="$(mktemp "$d/$base.ext.XXXXXX")"
+    only="$(mktemp "$d/$base.leaf.XXXXXX")"
     trap 'rm -f "$csr" "$ext" "$only"' EXIT
 
     openssl req -newkey rsa:4096 -nodes -sha256 \
       -keyout "$leafk" -out "$csr" \
-      -subj "/CN=${domain}"
+      -subj "/CN=$cn"
 
     # printf (not a heredoc) so the ext-file lines carry no leading
     # whitespace once nix has stripped the indented-string indent.
     {
-      printf 'subjectAltName=DNS:%s,DNS:forge.%s,DNS:matrix.%s,DNS:*.%s\n' \
+      printf 'subjectAltName=%s\n' "$sans"
-        ${lib.escapeShellArg domain} ${lib.escapeShellArg domain} \
-        ${lib.escapeShellArg domain} ${lib.escapeShellArg domain}
       printf 'basicConstraints=critical,CA:FALSE\n'
       printf 'keyUsage=critical,digitalSignature,keyEncipherment\n'
       printf 'extendedKeyUsage=serverAuth\n'
@@ -140,6 +145,35 @@ let
     chmod 0600 "$leafk"
     chmod 0644 "$leaf"
   '';
+
+  # The hive's own leaf: signed by the hive CA, covering the hive domain
+  # and its sub-domains.
+  signHiveLeaf = ''
+    ${signLeafScript} "$d" gateway ${lib.escapeShellArg domain} \
+      ${lib.escapeShellArg "DNS:${domain},DNS:forge.${domain},DNS:matrix.${domain},DNS:*.${domain}"} \
+      "$d/ca.pem" "$d/ca-key.pem"
+  '';
+
+  # The swarm-services leaf: signed by the services sub-CA, covering the
+  # swarm's service names. Those are *siblings* of the hive domain, not
+  # children, so the hive CA is name-constrained out of them and cannot
+  # sign this however its SAN list is written.
+  #
+  # Skipped when the sub-CA isn't on disk: it only exists where the
+  # swarm CA is autoconfigured, and a hive that gets its certs from its
+  # operator has nothing for this to do.
+  signServicesLeaf = lib.optionalString (swarmServiceDomains != [ ]) ''
+    servicesCa=${lib.escapeShellArg "${swarmCaCfg.stateDir}/services-ca.pem"}
+    servicesCaKey=${lib.escapeShellArg "${swarmCaCfg.stateDir}/services-ca-key.pem"}
+    if [ -s "$servicesCa" ] && [ -s "$servicesCaKey" ]; then
+      ${signLeafScript} "$d" swarm-services \
+        ${lib.escapeShellArg (builtins.head swarmServiceDomains)} \
+        ${lib.escapeShellArg (lib.concatMapStringsSep "," (n: "DNS:${n}") swarmServiceDomains)} \
+        "$servicesCa" "$servicesCaKey"
+    else
+      echo "no swarm-services sub-CA at $servicesCa — skipping the services leaf"
+    fi
+  '';
 in
 {
   # Host-side TLS trust root for the self-signed gateway mode.
@@ -318,7 +352,8 @@ in
         if [ ! -s "$leaf" ] || [ ! -s "$leafk" ] \
             || ! openssl x509 -in "$leaf" -noout -checkend 2592000 >/dev/null 2>&1; then
           echo "signing fresh gateway leaf at $leaf"
-          ${signLeafScript} "$d"
+          ${signHiveLeaf}
+          ${signServicesLeaf}
         fi
 
         # --- Trust bundle: what a consumer must TRUST, as opposed to
@@ -389,22 +424,39 @@ in
         set -euo pipefail
         d=${lib.escapeShellArg cfg.stateDir}
         leaf="$d/gateway.pem"
+        # ⚠️ EVERY leaf this host issues must be listed here. A leaf that
+        # first-boot issuance creates and this unit does not know about
+        # looks perfect for its entire validity and then expires with no
+        # warning — the failure is invisible until it is total.
+        svcleaf="$d/swarm-services.pem"
 
-        # Re-sign only when the leaf is within half its validity of expiry.
+        # Re-sign only when a leaf is within half its validity of expiry.
-        # The weekly cadence catches this window well before the leaf lapses.
+        # The weekly cadence catches this window well before one lapses.
         halflife=$(( ${toString cfg.leafValidityDays} * 86400 / 2 ))
-        if [ -s "$leaf" ] && \
+
-            openssl x509 -in "$leaf" -noout -checkend "$halflife" >/dev/null 2>&1; then
+        fresh() { # a leaf is fresh if it exists and is not near expiry
-          echo "gateway leaf valid for more than half its lifetime — no resign needed"
+          [ -s "$1" ] && openssl x509 -in "$1" -noout -checkend "$halflife" >/dev/null 2>&1
+        }
+
+        # The services leaf is only expected where the sub-CA exists;
+        # elsewhere its absence is the correct state, not a stale leaf.
+        want_svc=${if swarmServiceDomains == [ ] then "0" else "1"}
+        if [ ! -s ${lib.escapeShellArg "${swarmCaCfg.stateDir}/services-ca.pem"} ]; then
+          want_svc=0
+        fi
+
+        if fresh "$leaf" && { [ "$want_svc" = 0 ] || fresh "$svcleaf"; }; then
+          echo "leaves valid for more than half their lifetime — no resign needed"
           exit 0
         fi
 
-        echo "gateway leaf missing or near expiry — re-signing under current CA"
+        echo "a leaf is missing or near expiry — re-signing under the current CAs"
-        before="$(sha256sum "$leaf" 2>/dev/null || true)"
+        before="$(sha256sum "$leaf" "$svcleaf" 2>/dev/null || true)"
 
-        ${signLeafScript} "$d"
+        ${signHiveLeaf}
+        ${signServicesLeaf}
 
-        after="$(sha256sum "$leaf" 2>/dev/null || true)"
+        after="$(sha256sum "$leaf" "$svcleaf" 2>/dev/null || true)"
         if [ "$before" != "$after" ]; then
           echo "gateway leaf rotated — propagating into hive-gateway"
           systemctl -M hive-gateway restart hive-gateway-self-signed-cert.service || true

nix/host-modules/swarm-ca.nix

@@ -50,6 +50,13 @@ let
       hyperhiveCfg.domain
     else
       "hyperhive";
+
+  # Derived once in ./swarm.nix, read here and by ./hive-tls.nix: the
+  # CA that name-constrains these and the leaf that carries them as SANs
+  # must agree exactly, and two modules each assembling the list is how
+  # they stop agreeing. It is also this unit's *rotation trigger* below,
+  # which is why the ordering is stable there rather than here.
+  serviceDomains = hyperhiveCfg.swarm.serviceDomains;
 in
 {
   options.services.hyperhive.swarm.ca = {
@@ -97,6 +104,23 @@ in
       '';
     };
 
+    servicesValidityDays = lib.mkOption {
+      type = lib.types.int;
+      default = 1825;
+      description = ''
+        Validity window of the swarm-services sub-CA in days (~5y).
+        Deliberately far shorter than the root's: this CA is *meant* to
+        be re-issued — adding a swarm service changes its name
+        constraints and rotates it — so a long window buys nothing, and
+        a short one keeps the rotation path exercised rather than
+        theoretical.
+
+        Rotating it is cheap in the way rotating the root is not: it
+        touches only the swarm-service vhosts, and no peer hive holds it
+        as an anchor.
+      '';
+    };
+
     validityDays = lib.mkOption {
       type = lib.types.int;
       default = 10950;
@@ -166,5 +190,98 @@ in
         chmod 0644 "$root"
       '';
     };
+
+    # The swarm-services sub-CA: issues leaves for the swarm's own
+    # service names, which no hive CA can sign — each of those is
+    # name-constrained to its own hive's domain, and the service names
+    # are siblings of it, not children.
+    #
+    # Rotation is the point of it being separate (mara: "swarm services
+    # sub ca that can rotate independently of swarm root ca"): the
+    # constraint enumerates the exact service names, so adding a service
+    # re-issues *this* and never touches the root or any hive CA.
+    systemd.services.swarm-services-ca = {
+      description = "Issue the swarm-services sub-CA under the swarm root";
+      wantedBy = [ "multi-user.target" ];
+      after = [ "swarm-ca.service" ];
+      requires = [ "swarm-ca.service" ];
+      path = [ pkgs.openssl ];
+      serviceConfig = {
+        Type = "oneshot";
+        RemainAfterExit = true;
+        UMask = "0077";
+        SyslogIdentifier = "swarm-services-ca";
+      };
+      script = ''
+        set -euo pipefail
+        d=${lib.escapeShellArg cfg.stateDir}
+        root="$d/root.pem"
+        rootk="$d/root-key.pem"
+        ca="$d/services-ca.pem"
+        cak="$d/services-ca-key.pem"
+        # The name set this CA was last issued for. Comparing against it
+        # is what makes re-issuance happen exactly when the service
+        # names change — not every boot, and not never.
+        names="$d/services-ca.names"
+        want=${lib.escapeShellArg (lib.concatStringsSep "\n" serviceDomains)}
+
+        if [ -z "$want" ]; then
+          echo "no swarm service domains configured — nothing to issue for"
+          exit 0
+        fi
+
+        # Same half-provisioned guard as the root: a key beside a cert
+        # that did not sign it looks like it works and issues nothing
+        # anyone will trust.
+        if { [ -e "$ca" ] && [ ! -e "$cak" ]; } || { [ -e "$cak" ] && [ ! -e "$ca" ]; }; then
+          echo "services sub-CA half-provisioned ($ca / $cak) — refusing to generate over it" >&2
+          exit 1
+        fi
+
+        if [ -s "$ca" ] && [ -s "$cak" ] && [ -f "$names" ] \
+            && [ "$(cat "$names")" = "$want" ]; then
+          echo "services sub-CA present and covers the configured names — leaving it alone"
+          exit 0
+        fi
+
+        if [ ! -s "$root" ] || [ ! -s "$rootk" ]; then
+          echo "no swarm root CA at $root — cannot issue the services sub-CA under it" >&2
+          exit 1
+        fi
+
+        echo "issuing services sub-CA at $ca for: $(echo "$want" | tr '\n' ' ')"
+        csr="$(mktemp "$d/services-ca.csr.XXXXXX")"
+        ext="$(mktemp "$d/services-ca.ext.XXXXXX")"
+        trap 'rm -f "$csr" "$ext"' EXIT
+
+        openssl req -newkey rsa:4096 -nodes -sha256 \
+          -keyout "$cak" -out "$csr" \
+          -subj "/CN=swarm-services-ca ${swarmLabel}"
+
+        {
+          # pathlen:0 — this signs leaves and delegates no further.
+          printf 'basicConstraints=critical,CA:TRUE,pathlen:0\n'
+          printf 'keyUsage=critical,keyCertSign,cRLSign\n'
+          printf 'subjectKeyIdentifier=hash\n'
+          printf 'authorityKeyIdentifier=keyid:always\n'
+          # Constrained to the exact service names, not to the whole
+          # swarm domain: a leaked services CA should mint `forge.`,
+          # `chat.`, `auth.` and nothing else. The IP exclusions are not
+          # redundant — a DNS constraint says nothing about an
+          # iPAddress SAN, and an unconstrained name type is a name
+          # type this CA is unconstrained for.
+          printf 'nameConstraints=critical,permitted;%s,excluded;IP:0.0.0.0/0.0.0.0,excluded;IP:0:0:0:0:0:0:0:0/0:0:0:0:0:0:0:0\n' \
+            "$(echo "$want" | sed 's/^/DNS:/' | paste -sd, -)"
+        } > "$ext"
+
+        openssl x509 -req -in "$csr" -CA "$root" -CAkey "$rootk" \
+          -CAcreateserial -days ${toString cfg.servicesValidityDays} -sha256 \
+          -extfile "$ext" -out "$ca"
+
+        printf '%s' "$want" > "$names"
+        chmod 0600 "$cak"
+        chmod 0644 "$ca" "$names"
+      '';
+    };
   };
 }

nix/host-modules/swarm.nix

@@ -23,6 +23,23 @@
 let
   cfg = config.services.hyperhive;
   swarmCfg = cfg.swarm;
+
+  # Public hostnames of the swarm's own services, in declaration order.
+  # `serviceDomains` below is this set sorted + deduplicated.
+  #
+  # ⚠️ These are NOT required to be under `swarm.domain`. An earlier
+  # revision asserted that, reasoning that the services sub-CA is
+  # constrained to the swarm's tree — but the sub-CA is constrained to
+  # the **configured names** (./swarm-ca.nix) and the swarm root carries
+  # no name constraints at all, so any configured name is issuable. The
+  # assertion encoded an intended shape, not a property of the code, and
+  # it rejected the supported migration path: a hive pinning its old
+  # `forge.<hive domain>` while joining a swarm at a different apex.
+  serviceDomains' = [
+    swarmCfg.forge.domain
+    swarmCfg.matrix.gatewayHost
+    swarmCfg.authelia.domain
+  ];
 in
 {
   options.services.hyperhive.swarm.hives = lib.mkOption {
@@ -153,9 +170,31 @@ in
     '';
   };
 
+  options.services.hyperhive.swarm.serviceDomains = lib.mkOption {
+    type = lib.types.listOf lib.types.str;
+    readOnly = true;
+    internal = true;
+    description = ''
+      Read-only: the public hostnames of the swarm's own services, in a
+      stable sorted order. Second derived set alongside `peerHives`, and
+      here for the same reason — the CA that name-constrains these and
+      the leaf that carries them as SANs must agree exactly, and two
+      modules each assembling the list is how they stop agreeing.
+
+      Sorted and deduplicated deliberately: consumers compare this list
+      against what they issued last time to decide whether to re-issue,
+      so an unstable order would churn a certificate that other things
+      are meant to pin.
+    '';
+  };
+
   config = {
     services.hyperhive.swarm.peerHives = lib.filterAttrs (name: _: name != cfg.hiveName) swarmCfg.hives;
 
+    services.hyperhive.swarm.serviceDomains = lib.sort (a: b: a < b) (
+      lib.unique (lib.filter (d: d != null && d != "") serviceDomains')
+    );
+
     assertions = [
       {
         # Guarded on `hiveName != null` so the required-hiveName