From 7bb24b42f615d09482fe9c94be8e2b988a98f2c1 Mon Sep 17 00:00:00 2001
From: vitor-aignosi <vitor.santos@aignosi.com.br>
Date: Fri, 1 Aug 2025 12:01:03 -0300
Subject: [PATCH] SIENTIAPDE-1174  feat: update dependencies and enhance
 metrics integration

- Updated sientia-dataops-library dependency version from 1.3.5 to 1.3.7 in requirements.txt.
- Incremented image tag in values.yaml from 0.2.7 to 0.3.1.
- Added Prometheus metrics service configuration in values.yaml, enabling metrics collection.
- Implemented Prometheus client in worker.py to start a metrics server and track application health.
---
 orchestrator/metrics.py       | 16 ++++++++++++++
 orchestrator/worker/worker.py | 22 ++++++++++++++++++-
 requirements.txt              |  3 ++-
 values.yaml                   | 40 +++++++++++++++++++++++------------
 4 files changed, 66 insertions(+), 15 deletions(-)
 create mode 100644 orchestrator/metrics.py

diff --git a/orchestrator/metrics.py b/orchestrator/metrics.py
new file mode 100644
index 0000000..c7bc20e
--- /dev/null
+++ b/orchestrator/metrics.py
@@ -0,0 +1,16 @@
+from prometheus_client import Gauge, Counter
+
+APP_UP = Gauge(
+    "app_up",
+    "Indicates if the application is running (1) or shutting down (0)",
+    ["pod_id"],
+)
+
+CORE_LABELS = ["pod_id", "model_name", "pipeline_name"]
+
+
+EMAIL_SENT_COUNT = Counter(
+    "email_sent_count",
+    "Number of emails sent",
+    [*CORE_LABELS, "email_group"],
+)
diff --git a/orchestrator/worker/worker.py b/orchestrator/worker/worker.py
index fcd815d..89959e3 100644
--- a/orchestrator/worker/worker.py
+++ b/orchestrator/worker/worker.py
@@ -22,6 +22,10 @@ with workflow.unsafe.imports_passed_through():
     )
     from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
     from sientia_do.temporal.utils.logger import get_logger
+    from prometheus_client import start_http_server
+    from orchestrator import metrics
+
+POD_ID = os.getenv("POD_ID")
 
 
 async def main():
@@ -29,7 +33,10 @@ async def main():
     namespace = os.getenv('TEMPORAL_NAMESPACE', 'default')
     logger = get_logger(__name__)
 
-    logger.info('Starting Worker...')
+    logger.info(f'Starting Worker with POD_ID: {POD_ID}')
+
+    logger.info("Starting prometheus client...")
+    start_prometheus_server()
 
     logger.info('Starting Notification Handler...')
 
@@ -164,7 +171,20 @@ async def main():
         if activities:
             activities.shutdown()
         # Exit with a non-zero status code to indicate failure to Kubernetes
+        metrics.APP_UP.labels(pod_id=POD_ID).set(0)  # Mark app as DOWN
         sys.exit(1)
 
+
+def start_prometheus_server():
+    try:
+        port = int(os.getenv("HTTP_METRICS_PORT", 9090))
+        start_http_server(port)
+        print(f"Prometheus server started on port {port}.")
+        metrics.APP_UP.labels(pod_id=POD_ID).set(1)
+    except Exception as e:
+        print(f"Failed to start Prometheus server: {e}")
+        os._exit(1)
+
+
 if __name__ == '__main__':
     asyncio.run(main())
diff --git a/requirements.txt b/requirements.txt
index 166f96d..f7a80cf 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,4 +5,5 @@ redis
 couchbase
 pymongo
 jinja2
-git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.3.5
+git+ssh://git@github.com/Aignosi/sientia-dataops-library.git@1.3.7
+prometheus-client
diff --git a/values.yaml b/values.yaml
index 570ae29..802fba4 100644
--- a/values.yaml
+++ b/values.yaml
@@ -11,7 +11,7 @@ image:
   # This sets the pull policy for images.
   pullPolicy: Always
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "0.2.7"
+  tag: "0.3.1"
 
 # This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
 imagePullSecrets:
@@ -112,19 +112,31 @@ tolerations: []
 affinity: {}
 
 services:
-  api:
-    enabled: false
+  metrics:
+    enabled: true
     type: ClusterIP
-    port: 4841
-    targetPort: 4841
-    name: api
+    port: 9090
+    targetPort: 9090
+    name: metrics
 
-  opc:
-    enabled: false
-    type: ClusterIP
-    port: 4840
-    targetPort: 4840
-    name: server
+# Configuração do ServiceMonitor para o Prometheus Operator
+# ref: https://github.com/prometheus-operator/prometheus-operator
+serviceMonitor:
+  # Se true, um recurso ServiceMonitor será criado.
+  enabled: true
+  # O intervalo no qual as métricas devem ser coletadas (ex: 30s, 1m).
+  interval: 30s
+  # O path do endpoint de métricas na sua aplicação.
+  path: /metrics
+  # Labels adicionais para o recurso ServiceMonitor.
+  # Essencial para que o Prometheus Operator o descubra. Se você usa o helm chart kube-prometheus-stack,
+  # ele procura por ServiceMonitors com o label "release: kube-prometheus-stack".
+  additionalLabels:
+    release: kube-prometheus-stack
+  # Configurações de relabeling adicionais, se necessário.
+  # ref: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config
+  relabelings: []
+  port: metrics
   
 
 env:
@@ -132,7 +144,7 @@ env:
   - name: GITHUB_REPO_URL
     value: "git@github.com:Aignosi/sientia-dataops-orchestrator_temporal.git"
   - name: GITHUB_BRANCH
-    value: "SIENTIAPDE-1172-criar-pipeline-de-alertas-orquestrador"
+    value: "SIENTIAPDE-1174-mapear-e-implementar-metricas-a-serem-criadas"
   - name: PYTHON_APP
     value: "orchestrator.worker.worker"
 
@@ -203,6 +215,8 @@ env:
 
   - name: LOG_LEVEL
     value: "DEBUG"
+  - name: HTTP_METRICS_PORT
+    value: "9090"
   - name: PROJECT_NAME
     value: "sientia-orchestrator"