feat(hub): dashboard + deploy del scraper NATS server-level del cluster unibus

Add the unibus-nats Grafana dashboard and the per-node deploy script for the
unibus_exporter NATS-local mode, which surfaces the server-level NATS/JetStream
metrics that /healthz cannot (msgs/s, connections, KV bucket msgs, RAFT leader
per stream, memory, restarts).

- hub/dashboards/unibus-nats.json (uid unibus-nats, datasource victoriametrics):
  12 panels — NATS up, connections, msgs/s in, slow consumers, JetStream msgs,
  nats-server restarts (1h); msgs/s per node (in/out), connections per node,
  KV bucket msgs per bucket, nats-server memory per node; RAFT leader per stream
  table, JetStream per node table. Picked up automatically by the existing
  "fleet" dashboard provider (scans the dashboards path).
- hub/deploy_unibus_nats_exporter.sh: deploys unibus_exporter in NATS-local mode
  on a node. magnus pushes to the local VictoriaMetrics (no auth); homer/datardos
  push to the public ingest endpoint with basic auth (pass fleet/ingest-pass,
  never in argv). Installs unibus-exporter-nats.service and probes 8222 to warn if
  the monitoring endpoint is not yet open. Does NOT restart membershipd or touch
  the cluster — that is the consolidated 0.11.0 rollout.

The scraper code (unibus_exporter NATS-local mode) and the registry parser
(parse_nats_monitor_go_infra) ship in their own repos; see report
unibus-nats-metrics-clean for the integration order.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

hub/dashboards/unibus-nats.json

@@ -0,0 +1,148 @@
+{
+  "uid": "unibus-nats",
+  "title": "unibus — NATS server",
+  "tags": ["fleet", "unibus", "nats", "jetstream"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": { "from": "now-6h", "to": "now" },
+  "templating": { "list": [] },
+  "panels": [
+    {
+      "id": 1,
+      "type": "stat",
+      "title": "Nodos NATS up",
+      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_up[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "green" }, "noValue": "n/d (8222 cerrado)" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 2,
+      "type": "stat",
+      "title": "Conexiones (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_connections[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "blue" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "area", "textMode": "value" }
+    },
+    {
+      "id": 3,
+      "type": "stat",
+      "title": "Msgs/s entrada (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(rate(nats_msgs_in_total[5m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "cps", "color": { "mode": "fixed", "fixedColor": "purple" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "area", "textMode": "value" }
+    },
+    {
+      "id": 4,
+      "type": "stat",
+      "title": "Slow consumers",
+      "gridPos": { "h": 4, "w": 4, "x": 12, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_slow_consumers[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "background", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 5,
+      "type": "stat",
+      "title": "JetStream msgs (cluster)",
+      "gridPos": { "h": 4, "w": 4, "x": 16, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(last_over_time(nats_jetstream_messages[2m]))", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "color": { "mode": "fixed", "fixedColor": "blue" } }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "value", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 6,
+      "type": "stat",
+      "title": "Reinicios nats-server (1h)",
+      "gridPos": { "h": 4, "w": 4, "x": 20, "y": 0 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "sum(changes(nats_server_start_seconds[1h]))", "legendFormat": "reinicios", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 1 } ] }, "noValue": "0" }, "overrides": [] },
+      "options": { "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "colorMode": "background", "graphMode": "none", "textMode": "value" }
+    },
+    {
+      "id": 7,
+      "type": "timeseries",
+      "title": "Mensajes/s por nodo (in / out)",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [
+        { "refId": "A", "expr": "rate(nats_msgs_in_total[5m])", "legendFormat": "{{node}} · in", "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "B", "expr": "rate(nats_msgs_out_total[5m])", "legendFormat": "{{node}} · out", "datasource": { "type": "prometheus", "uid": "victoriametrics" } }
+      ],
+      "fieldConfig": { "defaults": { "unit": "cps", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2 } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 8,
+      "type": "timeseries",
+      "title": "Conexiones por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_connections", "legendFormat": "{{node}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 20, "showPoints": "never", "lineWidth": 2, "lineInterpolation": "stepAfter" } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 9,
+      "type": "timeseries",
+      "title": "KV bucket msgs (por bucket)",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "max by (bucket) (kv_bucket_msgs)", "legendFormat": "{{bucket}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "none", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2, "lineInterpolation": "stepAfter" } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 10,
+      "type": "timeseries",
+      "title": "Memoria nats-server por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_mem_bytes", "legendFormat": "{{node}}", "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "fieldConfig": { "defaults": { "unit": "bytes", "min": 0, "custom": { "drawStyle": "line", "fillOpacity": 10, "showPoints": "never", "lineWidth": 2 } }, "overrides": [] },
+      "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull", "max"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+    },
+    {
+      "id": 11,
+      "type": "table",
+      "title": "Leader RAFT por stream",
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 20 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [ { "refId": "A", "expr": "nats_jetstream_raft_leader == 1", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } } ],
+      "transformations": [
+        { "id": "organize", "options": { "excludeByName": { "Time": true, "instance": true, "__name__": true, "job": true, "Value": true }, "renameByName": { "stream": "Stream", "node": "Leader" }, "indexByName": { "stream": 0, "node": 1 } } }
+      ],
+      "fieldConfig": { "defaults": { "custom": { "align": "left" }, "noValue": "n/d (sin métricas NATS o sin quorum)" }, "overrides": [] },
+      "options": { "showHeader": true }
+    },
+    {
+      "id": 12,
+      "type": "table",
+      "title": "JetStream por nodo",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 20 },
+      "datasource": { "type": "prometheus", "uid": "victoriametrics" },
+      "targets": [
+        { "refId": "streams", "expr": "last_over_time(nats_jetstream_streams[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "messages", "expr": "last_over_time(nats_jetstream_messages[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "bytes", "expr": "last_over_time(nats_jetstream_bytes[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } },
+        { "refId": "subs", "expr": "last_over_time(nats_subscriptions[2m])", "format": "table", "instant": true, "datasource": { "type": "prometheus", "uid": "victoriametrics" } }
+      ],
+      "transformations": [
+        { "id": "joinByField", "options": { "byField": "node", "mode": "outer" } },
+        { "id": "organize", "options": { "excludeByName": { "Time": true, "Time 1": true, "Time 2": true, "Time 3": true, "Time 4": true, "instance": true, "instance 1": true, "instance 2": true, "instance 3": true, "instance 4": true, "__name__": true, "__name__ 1": true, "__name__ 2": true, "__name__ 3": true, "__name__ 4": true, "job": true, "job 1": true, "job 2": true, "job 3": true, "job 4": true }, "renameByName": { "node": "Nodo", "Value #streams": "streams", "Value #messages": "messages", "Value #bytes": "bytes", "Value #subs": "subs" } } }
+      ],
+      "fieldConfig": { "defaults": { "custom": { "align": "center" } }, "overrides": [ { "matcher": { "id": "byName", "options": "bytes" }, "properties": [ { "id": "unit", "value": "bytes" } ] } ] },
+      "options": { "showHeader": true }
+    }
+  ]
+}

hub/deploy_unibus_nats_exporter.sh

@@ -0,0 +1,94 @@
+#!/usr/bin/env bash
+# Despliega unibus_exporter en MODO NATS LOCAL en un nodo del cluster unibus.
+#
+# A diferencia del modo healthz (una sola instancia en magnus que sondea los 3
+# nodos por IP pública), el endpoint de monitoring de NATS (8222) es loopback-only
+# y sin auth, así que este modo corre EN CADA nodo y lee su propio 127.0.0.1:8222.
+# Por eso este script se ejecuta una vez por nodo.
+#
+# Uso: ./deploy_unibus_nats_exporter.sh <node_name> <ssh_host>
+#   node_name : etiqueta lógica del nodo (magnus | homer | datardos)
+#   ssh_host  : alias SSH del nodo (~/.ssh/config). magnus suele ser `om`.
+#
+# Requisitos:
+#   - Go instalado localmente (compila el binario amd64).
+#   - `pass fleet/ingest-pass` (password de ingesta, solo para nodos != magnus).
+#   - sudo -n (sin password) en el host remoto.
+#
+# PRECONDICIÓN CRÍTICA: el nodo debe correr unibus 0.11.0+ arrancado con
+# UNIBUS_NATS_MONITOR=1 (drop-in membershipd-cluster.service.d/nats-monitor.conf),
+# o /varz no responderá y el exporter emitirá nats_up=0. Este script NO reinicia
+# membershipd ni toca el cluster — eso es el rollout consolidado del binario 0.11.0.
+set -euo pipefail
+
+NODE="${1:?uso: deploy_unibus_nats_exporter.sh <node_name> <ssh_host>}"
+HOST="${2:?uso: deploy_unibus_nats_exporter.sh <node_name> <ssh_host>}"
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd)"          # projects/fleet_monitoring
+APP="$ROOT/apps/unibus_exporter"
+
+# magnus ES el hub: empuja a la VM local sin auth. El resto empuja al endpoint
+# público de ingesta con basic auth (mismo que metrics_agent).
+if [ "$NODE" = "magnus" ]; then
+  HUB="http://127.0.0.1:8428/api/v1/import/prometheus"
+  USER=""
+  PW=""
+else
+  HUB="https://metrics-dxaqj3ina6eqd5pjt85wkrrj.organic-machine.com/api/v1/import/prometheus"
+  USER="fleet"
+  PW="$(pass show fleet/ingest-pass | head -1)"
+fi
+
+echo ">> compilando unibus_exporter (linux/amd64)"
+mkdir -p "$APP/dist"
+( cd "$APP" && CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -ldflags="-s -w" -o dist/unibus_exporter_amd64 . )
+BIN="$APP/dist/unibus_exporter_amd64"
+
+echo ">> subiendo binario a $HOST"
+scp -q -o BatchMode=yes "$BIN" "$HOST:/tmp/unibus_exporter"
+
+echo ">> instalando servicio NATS-local en $NODE ($HOST)"
+ssh -o BatchMode=yes "$HOST" "NODE='$NODE' HUB='$HUB' VMUSER='$USER' PW='$PW' bash -s" <<'OUTER'
+set -e
+sudo -n mkdir -p /opt/unibus-exporter /etc/unibus-exporter
+sudo -n mv /tmp/unibus_exporter /opt/unibus-exporter/unibus_exporter
+sudo -n chmod 755 /opt/unibus-exporter/unibus_exporter
+sudo -n tee /etc/unibus-exporter/unibus.nats.json >/dev/null <<JSON
+{
+  "nats_monitor": { "enabled": true, "node": "${NODE}", "base_url": "http://127.0.0.1:8222" },
+  "hub_url": "${HUB}",
+  "user": "${VMUSER}",
+  "pass": "${PW}",
+  "interval_sec": 15,
+  "timeout_sec": 8,
+  "labels": { "job": "unibus_exporter" }
+}
+JSON
+sudo -n chmod 600 /etc/unibus-exporter/unibus.nats.json
+sudo -n tee /etc/systemd/system/unibus-exporter-nats.service >/dev/null <<'UNIT'
+[Unit]
+Description=unibus NATS local exporter (fleet_monitoring)
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+ExecStart=/opt/unibus-exporter/unibus_exporter -config /etc/unibus-exporter/unibus.nats.json
+Restart=always
+RestartSec=10
+NoNewPrivileges=true
+
+[Install]
+WantedBy=multi-user.target
+UNIT
+sudo -n systemctl daemon-reload
+sudo -n systemctl enable unibus-exporter-nats >/dev/null 2>&1
+sudo -n systemctl restart unibus-exporter-nats
+sleep 3
+echo -n "status: "; systemctl is-active unibus-exporter-nats || true
+echo "== nats_up local =="
+curl -fsS "http://127.0.0.1:8222/varz" >/dev/null 2>&1 && echo "8222 OK (monitoring abierto)" || echo "8222 NO responde — falta UNIBUS_NATS_MONITOR=1 en membershipd (nats_up=0 hasta el rollout)"
+OUTER
+
+echo ">> $NODE: unibus_exporter (modo NATS local) desplegado"
+echo ">> recuerda: nats_up=0 hasta que el nodo corra unibus 0.11.0+ con UNIBUS_NATS_MONITOR=1"