split docker-compose into core and observability stacks; add ntfy, alertmanager, blackbox exporter, and otel-collector services; configure prometheus alerting pipeline

prometheus/alert.rules.yml

@@ -0,0 +1,11 @@
+groups:
+  - name: uptime_alerts
+    rules:
+      - alert: ServiceDown
+        expr: probe_success{job="blackbox_http"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "{{ $labels.instance }} est down"
+          description: "Le service {{ $labels.instance }} ne répond plus depuis plus d'1 minute."

prometheus/alertmanager/alertmanager.yml

@@ -0,0 +1,11 @@
+route:
+  receiver: ntfy
+  group_by: ['alertname']
+  repeat_interval: 8760h
+  group_wait: 10s
+
+receivers:
+  - name: ntfy
+    webhook_configs:
+      - url: http://ntfy:80/alerts?template=alertmanager
+        send_resolved: true

prometheus/prometheus.yml

@@ -0,0 +1,33 @@
+global:
+  scrape_interval: 10s
+
+rule_files:
+  - /etc/prometheus/alert.rules.yml
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          - alertmanager:9093
+
+scrape_configs:
+ - job_name: alertmanager
+   static_configs:
+    - targets:
+      - alertmanager:9093
+ - job_name: blackbox_http
+   metrics_path: /probe
+   params:
+     module: [http_2xx]
+   static_configs:
+    - targets:
+      - https://www.qpismont.fr
+      - https://gitea.qpismont.fr
+      - https://woodpecker.qpismont.fr
+   relabel_configs:
+    - source_labels: [__address__]
+      target_label: __param_target
+    - source_labels: [__param_target]
+      target_label: instance
+    - target_label: __address__
+      replacement: blackbox_exporter:9115