Mejoras de sesion: estabilizacion, IA, Nexus Yonke y marketplace B2B

- F0 blindaje: Redis/Celery, pg_hba sin trust LAN, secretos a env 600, backups, webhook auth, jobs muertos
- F1 caja: bugs POS, reembolsos al corte, apartados, CFDI, topes de descuento en cotizacion/apartado
- F2/F7 IA de catalogo: autocategorizacion, dedup de SKUs con embeddings, OCR de facturas, descripciones, claves SAT, limpieza de fitment
- F3 IA en el flujo: vision Yonke, preguntas MeLi, venta cruzada, anomalias, sinonimos, busqueda semantica (rerank/embeddings)
- F4/F8 escala y cartera: /metrics+Prometheus+Grafana, pool, score de credito, churn, metricas multi-tenant
- Nexus Yonke (M1-M6): modelo de datos 1-de-1, alta por donador, vitrina publica, MeLi usado, consignacion, garantia por dias, reportes, etiquetas
- Marketplace B2B entre yonkes (catalogo + pedidos cross-tenant)
- Seguridad: auth en /api/admin/* (35 endpoints), alertas por tenant
- Migraciones v4.27/v4.28; timers expire-demos y rollup-metrics

docker/alertmanager/alertmanager.yml

@@ -1,7 +1,5 @@
 global:
-  smtp_smarthost: 'localhost:587'
-  smtp_from: 'alerts@nexus.local'
-  smtp_require_tls: false
+  resolve_timeout: 5m
 
 route:
   group_by: ['alertname', 'severity']
@@ -12,19 +10,14 @@ route:
 
 receivers:
   - name: 'default'
-    email_configs:
-      - to: 'admin@nexus.local'
-        subject: 'Nexus Alert: {{ .GroupLabels.alertname }}'
-        body: |
-          {{ range .Alerts }}
-          Alert: {{ .Annotations.summary }}
-          Description: {{ .Annotations.description }}
-          Severity: {{ .Labels.severity }}
-          Time: {{ .StartsAt }}
-          {{ end }}
     webhook_configs:
-      - url: 'http://localhost:5001/pos/api/notifications/webhook'
+      # El contenedor llega al host por el gateway del bridge docker
+      - url: 'http://172.17.0.1:5001/pos/api/notifications/webhook'
         send_resolved: true
+        http_config:
+          authorization:
+            type: Bearer
+            credentials: 'c58db62766712e618a881dbe8de580960812e57a069ef92c9dd00e7e69158cb2'
 
 inhibit_rules:
   - source_match:

docker/docker-compose.monitoring.yml

@@ -3,6 +3,8 @@ version: "3.8"
 services:
   prometheus:
     image: prom/prometheus:v2.51.0
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
     container_name: nexus-prometheus
     restart: unless-stopped
     ports:

docker/grafana/provisioning/dashboards/nexus-gunicorn.json

@@ -1,7 +1,7 @@
 {
   "uid": "nexus-app",
   "title": "Nexus — Application",
-  "tags": ["gunicorn", "flask"],
+  "tags": ["app", "flask", "nexus"],
   "timezone": "browser",
   "schemaVersion": 36,
   "refresh": "30s",
@@ -26,15 +26,15 @@
   "panels": [
     {
       "id": 1,
-      "title": "Request Rate (nginx)",
+      "title": "Request Rate (by app / status)",
       "type": "timeseries",
       "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
       "datasource": {"type": "prometheus", "uid": "${datasource}"},
       "targets": [
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "rate(nginx_http_requests_total[5m])",
-          "legendFormat": "Requests/sec",
+          "expr": "sum by (app, status) (rate(nexus_http_requests_total[5m]))",
+          "legendFormat": "{{app}} {{status}}",
           "refId": "A"
         }
       ],
@@ -49,20 +49,20 @@
     },
     {
       "id": 2,
-      "title": "Response Time (nginx)",
+      "title": "Response Time p95 / p99",
       "type": "timeseries",
       "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
       "datasource": {"type": "prometheus", "uid": "${datasource}"},
       "targets": [
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "histogram_quantile(0.95, sum(rate(nginx_http_request_duration_seconds_bucket[5m])) by (le))",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(nexus_http_request_duration_seconds_bucket[5m])))",
           "legendFormat": "p95",
           "refId": "A"
         },
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "histogram_quantile(0.99, sum(rate(nginx_http_request_duration_seconds_bucket[5m])) by (le))",
+          "expr": "histogram_quantile(0.99, sum by (le) (rate(nexus_http_request_duration_seconds_bucket[5m])))",
           "legendFormat": "p99",
           "refId": "B"
         }
@@ -78,15 +78,15 @@
     },
     {
       "id": 3,
-      "title": "Active Workers",
+      "title": "In-flight Requests",
       "type": "timeseries",
       "gridPos": {"h": 8, "w": 12, "x": 0, "y": 8},
       "datasource": {"type": "prometheus", "uid": "${datasource}"},
       "targets": [
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "count by (instance) (node_processes_state{state=\"S\", cmdline=~\".*gunicorn.*\"})",
-          "legendFormat": "Workers {{instance}}",
+          "expr": "sum by (app) (nexus_http_requests_in_flight)",
+          "legendFormat": "{{app}}",
           "refId": "A"
         }
       ],
@@ -108,8 +108,8 @@
       "targets": [
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "rate(nginx_http_requests_total{status=~\"5..\"}[5m])",
-          "legendFormat": "5xx/sec",
+          "expr": "sum by (app) (rate(nexus_http_requests_total{status=\"5xx\"}[5m]))",
+          "legendFormat": "{{app}} 5xx/s",
           "refId": "A"
         }
       ],
@@ -124,22 +124,22 @@
     },
     {
       "id": 5,
-      "title": "Memory per Worker",
+      "title": "Master DB Connections",
       "type": "timeseries",
       "gridPos": {"h": 8, "w": 24, "x": 0, "y": 16},
       "datasource": {"type": "prometheus", "uid": "${datasource}"},
       "targets": [
         {
           "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "expr": "process_resident_memory_bytes{cmdline=~\".*gunicorn.*\"} / 1024 / 1024",
-          "legendFormat": "{{cmdline}}",
+          "expr": "nexus_db_connections",
+          "legendFormat": "{{app}} ({{database}})",
           "refId": "A"
         }
       ],
       "fieldConfig": {
         "defaults": {
           "custom": {"drawStyle": "line", "lineWidth": 2, "fillOpacity": 10},
-          "unit": "mbytes",
+          "unit": "short",
           "min": 0
         },
         "overrides": []

docker/prometheus/prometheus.yml

@@ -19,7 +19,7 @@ scrape_configs:
 
   - job_name: 'node'
     static_configs:
-      - targets: ['node-exporter:9100']
+      - targets: ['host.docker.internal:9100']
 
   - job_name: 'postgres'
     static_configs:
@@ -29,12 +29,16 @@ scrape_configs:
     static_configs:
       - targets: ['redis-exporter:9121']
 
-  - job_name: 'nexus-pos'
-    static_configs:
-      - targets: ['host.docker.internal:5001']
+  # Métricas de aplicación expuestas por POS (gunicorn :5001) y dashboard (:5000)
+  # en el host; se alcanzan desde el contenedor por el gateway del bridge docker.
+  - job_name: 'nexus_pos'
     metrics_path: /metrics
+    static_configs:
+      - targets: ['172.17.0.1:5001']
 
-  - job_name: 'nexus-quart'
-    static_configs:
-      - targets: ['host.docker.internal:5002']
+  - job_name: 'nexus_dashboard'
     metrics_path: /metrics
+    static_configs:
+      - targets: ['172.17.0.1:5000']
+
+