modules/nats/entrypoint.sh

@@ -3,9 +3,9 @@
 # configuration.
 #
 # **Why this exists inside the module** (novox/hq design 25 §5). The controller composes every
-# account and permission into one configuration file, and that file changes whenever a module is
-# added, reassigned, or a person's access is granted or revoked — which is often, and on the one
-# server everything else depends on. The host has no way to say "reload this container": a
+# account and permission into one file, and that file changes whenever a module is added,
+# reassigned, or a person's access is granted or revoked — which is often, and on the one server
+# everything else depends on. The host has no way to say "reload this container": a
 # container resource has `restart-on` and nothing else, and a container's `restart-on` means
 # *recreate* — every connection dropped and every in-flight JetStream ack lost, mid-flight, for a
 # permission change. `reload-on` is real but it is a *service* field, not a container's.
@@ -19,21 +19,29 @@
 # here is declared `restart-on` or `reload-on`.
 set -eu
 
+# **Two files, and only one of them is the mesh's** (novox/hq design 25 §4, task 1.7). CONF is this
+# module's own — ports, TLS, JetStream — declared in its manifest, because those are properties of
+# the container this module raises. USERS is every account and permission, composed by the
+# controller, and CONF includes it. So what is watched here is the mesh's half: the module's own
+# does not change without a new declaration, and that recreates the container anyway.
 CONF="${MESH_NATS_CONF:-/etc/nats/nats.conf}"
+USERS="${MESH_NATS_USERS:-/etc/nats/accounts.conf}"
 POLL="${MESH_NATS_CONF_POLL_SECONDS:-5}"
 
-# The controller writes the configuration as part of the same declaration that creates this
-# container, but the two are not ordered against each other. Waiting is correct and starting
-# without one is not: nats-server would come up with its compiled-in defaults — no TLS, no
-# accounts, every subject open to anyone who can reach the port — and then be reloaded into
-# correctness a moment later. A bus that is briefly open to everything is not a bus that is
-# briefly wrong; it is an open bus.
-while [ ! -s "$CONF" ]; do
-  echo "[nats] waiting for the mesh to compose $CONF"
-  sleep 1
+# Both are written as part of the same declaration that creates this container, but none of the
+# three are ordered against each other. Waiting is correct and starting without them is not:
+# nats-server given a configuration whose include is missing refuses to start, and one given no
+# configuration at all comes up with its compiled-in defaults — no TLS, no accounts, every subject
+# open to anyone who can reach the port. A bus that is briefly open to everything is not a bus that
+# is briefly wrong; it is an open bus.
+for needed in "$CONF" "$USERS"; do
+  while [ ! -s "$needed" ]; do
+    echo "[nats] waiting for the mesh to write $needed"
+    sleep 1
+  done
 done
 
-digest() { sha256sum "$CONF" 2>/dev/null | cut -d' ' -f1; }
+digest() { sha256sum "$USERS" 2>/dev/null | cut -d' ' -f1; }
 
 nats-server --config "$CONF" "$@" &
 server=$!
@@ -52,7 +60,7 @@ while kill -0 "$server" 2>/dev/null; do
   [ -n "$now" ] || continue
   if [ "$now" != "$last" ]; then
     last=$now
-    echo "[nats] configuration changed; reloading in place"
+    echo "[nats] the mesh's user list changed; reloading in place"
     kill -HUP "$server" || true
   fi
 done

modules/nats/module.json

@@ -13,6 +13,7 @@
       "scope": "mesh"
     }
   ],
+  "bus-users": "/var/lib/nats-module/conf/accounts.conf",
   "capabilities": [
     "container-runtime"
   ],
@@ -42,6 +43,13 @@
       "path": "/var/lib/nats-module/conf",
       "mode": "0700"
     },
+    {
+      "id": "server-conf",
+      "type": "file",
+      "path": "/var/lib/nats-module/conf/nats.conf",
+      "content": "# The nats module's own server settings. Declared by the module, because a port, a TLS path\n# and a store directory are properties of the container this module raises: they live in its\n# image and its mounts and change when it does.\n#\n# The mesh writes accounts.conf beside this one and nothing else. A controller that wrote the\n# whole file would have to be kept in step with a Dockerfile it never sees.\n\nport: 4222\nhttp: 127.0.0.1:8222\n\ntls {\n  cert_file: \"/tls/tls.crt\"\n  key_file: \"/tls/tls.key\"\n  ca_file: \"/tls/ca.crt\"\n}\n\n# **No `verify`, deliberately, and it was `verify: true` until a probe ran this image.** That\n# setting makes the server demand a *client* certificate, and nothing in the mesh presents one: a\n# host pins this server's exact certificate and authenticates with the password the mesh minted\n# (novox/hq ADR 0004, design 25 \u00a74), and so does a module's runtime. With it on, every connection\n# in the mesh is refused at the TLS handshake, before any password is looked at \u2014 and the error is\n# \"client didn't provide a certificate\", which reads as a client fault.\n#\n# TLS is still required: a tls block is what makes it required, and verify only decides whether\n# client certificates are checked. What is given up is a second factor the mesh has no machinery\n# to issue or rotate \u2014 a certificate per module per node \u2014 and what is kept is stronger than a\n# name check in both directions: an exact pin outward, a per-user password inward.\n\njetstream {\n  store_dir: \"/data\"\n}\n\n# Every user of the mesh, composed by the controller and rewritten whenever a module is\n# assigned, a node enrols or a person's access changes.\n#\n# **Relative, and in this same directory, because it has to be.** An absolute include path is\n# resolved relative to the including file's directory, not from the root: nats-server given\n# `include /etc/nats/accounts.conf` from /etc/nats-server/nats.conf looks for\n# /etc/nats-server/etc/nats/accounts.conf and refuses to start. Verified against the server.\ninclude accounts.conf\n",
+      "mode": "0644"
+    },
     {
       "id": "server",
       "type": "container",