nix/host-modules/glue-matrix-bao-token.nix

@@ -77,21 +77,6 @@ in
         deployCfg.bao.package
         pkgs.coreutils
       ];
-      # Sized for the race this loses, not for an unseal. `swarm-bao` comes up
-      # seconds before this unit asks, and the cert-auth role it logs in
-      # against is written seconds after — so a few short attempts cover it.
-      # ⚠️ `swarm-bao-controller-policy`'s 2880 × 30s is NOT the model to copy.
-      # That unit blocks nothing; this one is `Before=` the homeserver's
-      # container, and whether that ordering waits across an auto-restart is
-      # unverified — so an hours-long window would be a bet on an unknown,
-      # where a minute is not. A store still sealed after it keeps the degrade
-      # below, as today.
-      #
-      # `StartLimit*` are `[Unit]` settings, so they go here and not in
-      # `serviceConfig` — systemd ignores them under `[Service]`. The window
-      # has to exceed `RestartSec × burst`.
-      startLimitBurst = 4;
-      startLimitIntervalSec = 300;
       serviceConfig = {
         Type = "oneshot";
         RemainAfterExit = true;
@@ -99,8 +84,6 @@ in
         # left to systemd's default, so the number a boot waits on is in
         # the file that waits.
         TimeoutStartSec = 30;
-        Restart = "on-failure";
-        RestartSec = 15;
       };
       environment = {
         BAO_ADDR = "https://${baoCfg.domain}:${toString baoCfg.port}";
@@ -134,11 +117,6 @@ in
         # presents; without a token `bao` asks its token helper instead, and
         # that is a `sh` this unit's `path` does not carry. `-token-only`
         # answers on stdout and skips the helper on both sides.
-        #
-        # Fails LOUDLY, unlike the read below: the three states a login failure
-        # covers — store not up, sealed, role not written yet — are all things
-        # a retry fixes, and `Restart=on-failure` above is what retries. Exiting
-        # 0 here spends the whole boot on a condition that was seconds old.
         if ! BAO_TOKEN="$(bao login -method=cert -token-only 2>"$err")"; then
           echo "could not log in to swarm-bao with this host's certificate; keeping the token hive-matrix already has." >&2
           if [ -s "$err" ]; then
@@ -146,7 +124,7 @@ in
           else
             echo "bao failed without writing a diagnostic." >&2
           fi
-          exit 1
+          exit 0
         fi
         export BAO_TOKEN
 

nix/module-eval.nix

@@ -1127,27 +1127,6 @@ let
         && !(holdsTokenFirst "# bao login -method=cert -token-only goes here\nbao kv get secret/x")
         && holdsTokenFirst "BAO_TOKEN=\"$(bao login -method=cert -token-only)\"\nbao kv get secret/x";
     }
-    {
-      # A login failure is the store being unreachable, sealed, or not yet
-      # holding this host's role — all of which a retry fixes. A read that
-      # answers "nothing there" is not, so only the first is allowed to fail
-      # the unit.
-      name = "the matrix token reader retries a failed login and still degrades on an empty read";
-      ok =
-        let
-          u = baoWithMatrix.systemd.services.swarm-bao-matrix-token;
-          # Everything between the login's failure branch and the read's, which
-          # is where the exit that decides "retry or give up" lives.
-          afterLogin = lib.last (lib.splitString "bao login" u.script);
-          loginBranch = lib.head (lib.splitString "bao kv get" afterLogin);
-        in
-        u.serviceConfig.Restart or null == "on-failure"
-        && u.startLimitBurst or 0 > 0
-        # The window has to outlast every attempt, or the burst is unreachable.
-        && u.startLimitIntervalSec or 0 > (u.serviceConfig.RestartSec or 0) * (u.startLimitBurst or 0)
-        && lib.hasInfix "exit 1" loginBranch
-        && lib.hasInfix "exit 0" (lib.last (lib.splitString "bao kv get" u.script));
-    }
     {
       # The doctrine three glue files state, as a property a rewrite has to
       # keep: a client is defined by holding a certificate the store accepts,