chore(fleet): sync operator memory, hatch menu dialogs, and watchdog alerts

bin/cdp-relay-watchdog.sh

@@ -13,10 +13,14 @@
 # Pattern mirrors chromebox-watchdog.sh (stage-specific logging, rotation).
 set -euo pipefail
 LOCK="/tmp/cdp-relay-watchdog.lock"
-exec 9>"$LOCK"
-if ! flock -n 9; then
-  echo "[$(date -u +%FT%TZ)] another relay watchdog run in progress, skipping" >&2
-  exit 0
+# Tests source this file with CDP_RELAY_WATCHDOG_LIB_ONLY=1: they call
+# helpers without running checks, so no lock is needed.
+if [ "${CDP_RELAY_WATCHDOG_LIB_ONLY:-}" != "1" ]; then
+  exec 9>"$LOCK"
+  if ! flock -n 9; then
+    echo "[$(date -u +%FT%TZ)] another relay watchdog run in progress, skipping" >&2
+    exit 0
+  fi
 fi
 
 NETVM_BIN="/home/super/Projects/NetVM/bin"
@@ -37,16 +41,16 @@ log() { echo "[$(date -u +%FT%TZ)] $*" | tee -a "$LOG"; }
 
 # node -> "veth_ip:port" via netvm-names.sh (hash-derived, don't hardcode)
 relay_target() {
-  local node="$1"
+  local node="$1" reg_port=""
   # shellcheck disable=SC1091
   . "$NETVM_BIN/netvm-names.sh"
   netvm_names "$node" || return 1
-  # CDP_PORT_OVERRIDE pins registry ports; fall back to hash-derived
-  local port="${CDP_PORT_OVERRIDE:-$CDP_PORT}"
-  case "$node" in
-    muse) port=9410 ;; pip) port=9420 ;; 646) port=9430 ;; opm) port=9440 ;;
-  esac
-  echo "$PEER_IP:$port"
+  # The registry is the source of truth for ports (new nodes propagate
+  # automatically); netvm-names pinning is the fallback.
+  if reg_port=$("$NETVM_BIN/netvm-registry.py" "$node" 2>/dev/null); then
+    [ -n "$reg_port" ] && CDP_PORT="$reg_port"
+  fi
+  echo "$PEER_IP:$CDP_PORT"
 }
 node_port() { echo "${1##*:}"; }
 
@@ -103,8 +107,25 @@ restart_relay() {
   fi
 }
 
+# Registry-driven node list: every active node gets relay supervision
+# (the old hardcoded 4-node list left def/dev unsupervised — 2026-10-06).
+watched_nodes() {
+  "$NETVM_BIN/netvm-registry.py" 2>/dev/null | cut -d: -f1
+}
+
+# Allow sourcing for tests without running checks.
+if [ "${CDP_RELAY_WATCHDOG_LIB_ONLY:-}" = "1" ]; then
+  return 0 2>/dev/null || exit 0
+fi
+
 FAILED=0
-for node in muse pip 646 opm; do
+NODES="$(watched_nodes)"
+if [ -z "$NODES" ]; then
+  log "FAIL_LOUD: node registry empty/unreadable, skipping run"
+  exit 1
+fi
+# shellcheck disable=SC2086 (intended word splitting: one node per word)
+for node in $NODES; do
   # Stage 1: host veth IP. Fail loud, skip relay restart (pointless).
   if ! veth_healthy "$node"; then
     read -r veth gw <<< "$(node_veth "$node")"