feat(monitoring): dashboard Grafana + règles d'alerte prospection

Consomme les métriques poussées par le pipeline prospection au Pushgateway
(job=prospection, déjà scrapé). Additif — n'affecte aucun dashboard existant.

- grafana : provider + dashboard « Prospection — pipeline BI missions » inliné
  (grafana.dashboards.prospection, json) — vue d'ensemble (fraîcheur/statut/durée/
  erreurs/missions/score), collecte par étape (table + historique), modèle de
  données (opportunités A/B, offres/entités), livraison (brief/Telegram) + panneau
  Alertes actives. Inline plutôt que ConfigMap externe : grafana est déployé via un
  HelmChart CRD (tool lib), l'inline évite toute hypothèse de namespace.
- prometheus : groupe d'alertes `prospection` (serverFiles.alerting_rules.yml) —
  RunStale (>25h), RunFailed, StepError, NoOffers, BriefNotSent.

NB : la livraison des alertes (Alertmanager → Telegram) n'est pas câblée dans le
cluster (server.alertmanagers vide, aucun receiver) ; les règles restent visibles
dans Prometheus /alerts + le dashboard. Câblage delivery = décision séparée.

Co-Authored-By: Claude Opus 4.8 <[email protected]>

grafana/values.yaml

@@ -703,6 +703,14 @@ grafana: &grafana_config
           editable: true
           options:
             path: /var/lib/grafana/dashboards/grafana-dashboards-kubernetes
+        - name: 'prospection'
+          orgId: 1
+          folder: 'Prospection'
+          type: file
+          disableDeletion: false
+          editable: true
+          options:
+            path: /var/lib/grafana/dashboards/prospection
 
         # - name: 'default'
         #   orgId: 1
@@ -757,6 +765,222 @@ grafana: &grafana_config
       k8s-views-pods:
         url: https://raw.githubusercontent.com/dotdc/grafana-dashboards-kubernetes/master/dashboards/k8s-views-pods.json
         token: ''
+    prospection:
+      prospection:
+        json: |
+          {
+            "__inputs": [],
+            "annotations": { "list": [] },
+            "editable": true,
+            "graphTooltip": 1,
+            "schemaVersion": 39,
+            "tags": ["prospection", "arcodange"],
+            "title": "Prospection — pipeline BI missions",
+            "uid": "prospection-pipeline",
+            "time": { "from": "now-14d", "to": "now" },
+            "refresh": "5m",
+            "templating": {
+              "list": [
+                {
+                  "name": "DS_PROMETHEUS",
+                  "label": "Datasource",
+                  "type": "datasource",
+                  "query": "prometheus",
+                  "current": {},
+                  "hide": 0,
+                  "refresh": 1
+                }
+              ]
+            },
+            "panels": [
+              {
+                "type": "row", "title": "Vue d'ensemble du dernier run",
+                "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 }, "id": 1, "collapsed": false
+              },
+              {
+                "type": "stat", "title": "Dernier run réussi il y a", "id": 2,
+                "gridPos": { "h": 4, "w": 5, "x": 0, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "time() - prospection_run_timestamp_seconds", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": {
+                  "unit": "s",
+                  "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 86400 }, { "color": "red", "value": 90000 } ] }
+                }, "overrides": [] },
+                "options": { "colorMode": "background", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] }, "textMode": "auto" }
+              },
+              {
+                "type": "stat", "title": "Statut du run", "id": 3,
+                "gridPos": { "h": 4, "w": 4, "x": 5, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_run_success", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": {
+                  "mappings": [ { "type": "value", "options": { "0": { "text": "ÉCHEC", "color": "red", "index": 0 }, "1": { "text": "OK", "color": "green", "index": 1 } } } ],
+                  "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "green", "value": 1 } ] }
+                }, "overrides": [] },
+                "options": { "colorMode": "background", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] }, "textMode": "auto" }
+              },
+              {
+                "type": "stat", "title": "Durée du run", "id": 4,
+                "gridPos": { "h": 4, "w": 5, "x": 9, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_run_duration_seconds", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "unit": "s", "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 1200 }, { "color": "red", "value": 1700 } ] } }, "overrides": [] },
+                "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Étapes en erreur", "id": 5,
+                "gridPos": { "h": 4, "w": 4, "x": 14, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_run_errors_total", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 1 } ] } }, "overrides": [] },
+                "options": { "colorMode": "background", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Missions A qualifiées", "id": 6,
+                "gridPos": { "h": 4, "w": 3, "x": 18, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_opportunities_total{kind=\"A\"}", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "yellow", "value": 1 }, { "color": "green", "value": 10 } ] } }, "overrides": [] },
+                "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Meilleur score", "id": 7,
+                "gridPos": { "h": 4, "w": 3, "x": 21, "y": 1 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_opportunity_top_score", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "min": 0, "max": 100, "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "yellow", "value": 65 }, { "color": "green", "value": 85 } ] } }, "overrides": [] },
+                "options": { "colorMode": "value", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "row", "title": "Collecte par étape",
+                "gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 }, "id": 8, "collapsed": false
+              },
+              {
+                "type": "table", "title": "Étapes — dernier run", "id": 9,
+                "gridPos": { "h": 9, "w": 12, "x": 0, "y": 6 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [
+                  { "refId": "Statut", "expr": "prospection_step_status", "instant": true, "format": "table", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "Items", "expr": "prospection_step_items", "instant": true, "format": "table", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "Durée", "expr": "prospection_step_duration_seconds", "instant": true, "format": "table", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } }
+                ],
+                "transformations": [
+                  { "id": "merge", "options": {} },
+                  { "id": "organize", "options": {
+                    "excludeByName": { "Time": true, "__name__": true, "job": true, "instance": true },
+                    "renameByName": { "step": "Étape", "Value #Statut": "Statut", "Value #Items": "Items", "Value #Durée": "Durée (s)" },
+                    "indexByName": { "step": 0, "Value #Statut": 1, "Value #Items": 2, "Value #Durée": 3 }
+                  } }
+                ],
+                "fieldConfig": { "defaults": { "custom": { "align": "auto" } }, "overrides": [
+                  { "matcher": { "id": "byName", "options": "Statut" }, "properties": [
+                    { "id": "mappings", "value": [ { "type": "value", "options": { "0": { "text": "⛔ erreur", "color": "red", "index": 0 }, "1": { "text": "✅ ok", "color": "green", "index": 1 }, "2": { "text": "⏭️ skip", "color": "blue", "index": 2 } } } ] },
+                    { "id": "custom.cellOptions", "value": { "type": "color-text" } }
+                  ] },
+                  { "matcher": { "id": "byName", "options": "Durée (s)" }, "properties": [ { "id": "unit", "value": "s" } ] }
+                ] },
+                "options": { "showHeader": true, "sortBy": [ { "displayName": "Durée (s)", "desc": true } ] }
+              },
+              {
+                "type": "timeseries", "title": "Items collectés par étape (historique)", "id": 10,
+                "gridPos": { "h": 9, "w": 12, "x": 12, "y": 6 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_step_items > 0", "legendFormat": "{{step}}", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "custom": { "drawStyle": "bars", "fillOpacity": 40, "stacking": { "mode": "none" }, "lineWidth": 1 } }, "overrides": [] },
+                "options": { "legend": { "displayMode": "table", "placement": "right", "calcs": ["lastNotNull"] }, "tooltip": { "mode": "multi", "sort": "desc" } }
+              },
+              {
+                "type": "row", "title": "Modèle de données & scoring",
+                "gridPos": { "h": 1, "w": 24, "x": 0, "y": 15 }, "id": 11, "collapsed": false
+              },
+              {
+                "type": "timeseries", "title": "Opportunités — missions A / cibles B", "id": 12,
+                "gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [
+                  { "refId": "A", "expr": "prospection_opportunities_total{kind=\"A\"}", "legendFormat": "Missions A", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "B", "expr": "prospection_opportunities_total{kind=\"B\"}", "legendFormat": "Cibles B", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } }
+                ],
+                "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10, "lineWidth": 2, "pointSize": 5, "showPoints": "always" } }, "overrides": [] },
+                "options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } }
+              },
+              {
+                "type": "timeseries", "title": "Offres & entités collectées (historique)", "id": 13,
+                "gridPos": { "h": 8, "w": 8, "x": 12, "y": 16 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [
+                  { "refId": "A", "expr": "prospection_offers_total", "legendFormat": "Offres (missions)", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "B", "expr": "prospection_entities_total", "legendFormat": "Entités (territoire)", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "C", "expr": "prospection_scores_total", "legendFormat": "Offres scorées", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } }
+                ],
+                "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10, "lineWidth": 2, "showPoints": "auto" } }, "overrides": [] },
+                "options": { "legend": { "displayMode": "list", "placement": "bottom" }, "tooltip": { "mode": "multi" } }
+              },
+              {
+                "type": "bargauge", "title": "Modèle — dernier run", "id": 14,
+                "gridPos": { "h": 8, "w": 4, "x": 20, "y": 16 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [
+                  { "refId": "A", "expr": "prospection_signals_total", "legendFormat": "Signaux", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "B", "expr": "prospection_entities_total", "legendFormat": "Entités", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "C", "expr": "prospection_offers_total", "legendFormat": "Offres", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } },
+                  { "refId": "D", "expr": "prospection_scores_total", "legendFormat": "Scorées", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } }
+                ],
+                "fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [ { "color": "blue", "value": null } ] } }, "overrides": [] },
+                "options": { "displayMode": "gradient", "orientation": "horizontal", "reduceOptions": { "calcs": ["lastNotNull"] }, "legend": { "showLegend": false } }
+              },
+              {
+                "type": "row", "title": "Livraison & alertes",
+                "gridPos": { "h": 1, "w": 24, "x": 0, "y": 24 }, "id": 15, "collapsed": false
+              },
+              {
+                "type": "stat", "title": "Brief rendu", "id": 16,
+                "gridPos": { "h": 5, "w": 4, "x": 0, "y": 25 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_brief_rendered", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "mappings": [ { "type": "value", "options": { "0": { "text": "non", "color": "red", "index": 0 }, "1": { "text": "oui", "color": "green", "index": 1 } } } ], "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "green", "value": 1 } ] } }, "overrides": [] },
+                "options": { "colorMode": "background", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Poussé sur Telegram", "id": 17,
+                "gridPos": { "h": 5, "w": 4, "x": 4, "y": 25 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_brief_telegram_pushed", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "mappings": [ { "type": "value", "options": { "0": { "text": "non", "color": "red", "index": 0 }, "1": { "text": "oui", "color": "green", "index": 1 } } } ], "thresholds": { "mode": "absolute", "steps": [ { "color": "red", "value": null }, { "color": "green", "value": 1 } ] } }, "overrides": [] },
+                "options": { "colorMode": "background", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Messages / mission", "id": 18,
+                "gridPos": { "h": 5, "w": 4, "x": 8, "y": 25 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_telegram_messages_sent", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [ { "color": "blue", "value": null } ] } }, "overrides": [] },
+                "options": { "colorMode": "value", "graphMode": "area", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "stat", "title": "Vidéo brief", "id": 19,
+                "gridPos": { "h": 5, "w": 4, "x": 12, "y": 25 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "prospection_brief_video_kb * 1024", "instant": true, "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "fieldConfig": { "defaults": { "unit": "bytes", "thresholds": { "mode": "absolute", "steps": [ { "color": "blue", "value": null } ] } }, "overrides": [] },
+                "options": { "colorMode": "value", "graphMode": "none", "reduceOptions": { "calcs": ["lastNotNull"] } }
+              },
+              {
+                "type": "table", "title": "Alertes prospection actives", "id": 20,
+                "gridPos": { "h": 5, "w": 8, "x": 16, "y": 25 },
+                "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" },
+                "targets": [ { "refId": "A", "expr": "ALERTS{alertname=~\"Prospection.*\", alertstate=\"firing\"}", "instant": true, "format": "table", "datasource": { "type": "prometheus", "uid": "${DS_PROMETHEUS}" } } ],
+                "transformations": [
+                  { "id": "organize", "options": {
+                    "excludeByName": { "Time": true, "Value": true, "__name__": true, "job": true, "instance": true, "alertstate": true },
+                    "renameByName": { "alertname": "Alerte", "severity": "Sévérité" }
+                  } }
+                ],
+                "fieldConfig": { "defaults": { "custom": { "align": "auto" } }, "overrides": [] },
+                "options": { "showHeader": true, "footer": { "show": false } }
+              }
+            ]
+          }
 
     # default:
     #   some-dashboard:

prometheus/values.yaml

@@ -1115,7 +1115,59 @@ prometheus: &prometheus_config
   serverFiles:
     ## Alerts configuration
     ## Ref: https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/
-    alerting_rules.yml: {}
+    alerting_rules.yml:
+      groups:
+        # Pipeline prospection (métriques poussées au Pushgateway job=prospection en fin de
+        # run). NB : la LIVRAISON des alertes (Alertmanager → Telegram/…) n'est pas encore
+        # câblée dans ce cluster — ces règles s'évaluent et sont visibles dans Prometheus
+        # /alerts + le dashboard Grafana « Prospection » (panneau Alertes actives).
+        - name: prospection
+          rules:
+            - alert: ProspectionRunStale
+              expr: time() - prospection_run_timestamp_seconds > 90000   # > 25 h (cron quotidien)
+              for: 10m
+              labels:
+                severity: warning
+                app: prospection
+              annotations:
+                summary: "Prospection — aucun run réussi depuis plus de 25 h"
+                description: "Dernier run réussi il y a {{ $value | humanizeDuration }} ; le CronJob quotidien (~06:30 UTC) n'a pas abouti."
+            - alert: ProspectionRunFailed
+              expr: prospection_run_success == 0
+              for: 5m
+              labels:
+                severity: warning
+                app: prospection
+              annotations:
+                summary: "Prospection — le dernier run a échoué"
+                description: "prospection_run_success=0 : toutes les collectes ont échoué au dernier run."
+            - alert: ProspectionStepError
+              expr: prospection_step_status == 0
+              for: 5m
+              labels:
+                severity: info
+                app: prospection
+              annotations:
+                summary: "Prospection — étape {{ $labels.step }} en erreur"
+                description: "L'étape {{ $labels.step }} du pipeline a fini en erreur au dernier run."
+            - alert: ProspectionNoOffers
+              expr: prospection_offers_total == 0
+              for: 15m
+              labels:
+                severity: warning
+                app: prospection
+              annotations:
+                summary: "Prospection — 0 offre (mission) collectée"
+                description: "Aucune offre au dernier run : collecte France Travail / Free-Work potentiellement cassée."
+            - alert: ProspectionBriefNotSent
+              expr: prospection_brief_telegram_pushed == 0
+              for: 15m
+              labels:
+                severity: info
+                app: prospection
+              annotations:
+                summary: "Prospection — brief non poussé sur Telegram"
+                description: "Le brief vidéo n'a pas été diffusé sur Telegram au dernier run."
     # groups:
     #   - name: Instances
     #     rules: