#!/bin/sh
# nats's entrypoint: run the server, and reload it in place when the mesh rewrites its
# configuration.
#
# **Why this exists inside the module** (novox/hq design 25 §5). The controller composes every
# 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.
#
# nats-server already reloads its own configuration on SIGHUP — accounts, permissions, everything
# the mesh composes — without dropping a connection. That is the server's own documented
# capability, not something built for the mesh. So the configuration is mounted as a directory
# (a directory's contents are not digest-tracked the way a directly-mounted file's are, novox/hq
# issue 103), and this watches the one file inside it and signals the server itself. The host's
# only job is what it already does for any directory: keep the file's content current. Nothing
# 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}"

# 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 "$USERS" 2>/dev/null | cut -d' ' -f1; }

nats-server --config "$CONF" "$@" &
server=$!

# Forward a stop to the server and let it drain, rather than dying and leaving it orphaned as
# PID 1's child.
stop() { kill -TERM "$server" 2>/dev/null || true; }
trap stop TERM INT

last=$(digest)
while kill -0 "$server" 2>/dev/null; do
  sleep "$POLL"
  now=$(digest)
  # An empty digest means the file is mid-write or briefly gone. Reloading on that would hand the
  # server a truncated configuration; the next tick sees the finished one.
  [ -n "$now" ] || continue
  if [ "$now" != "$last" ]; then
    last=$now
    echo "[nats] the mesh's user list changed; reloading in place"
    kill -HUP "$server" || true
  fi
done

# `wait` on an already-exited child still yields its status, which becomes this container's.
wait "$server"