SIENTIAPDE-1169

feat: add SDK metrics service and update telemetry configuration

- Introduced a new service for SDK metrics in values.yaml, enabling metrics collection on port 9091.
- Updated the worker.py to initialize a new runtime with Prometheus metrics configuration for the SDK metrics server.
- Adjusted environment variable for GITHUB_BRANCH to reflect the current focus on testing and performance design.

orchestrator/worker/worker.py

@@ -1,6 +1,6 @@
 from temporalio import workflow, client
 from temporalio.worker import Worker
-
+from temporalio.runtime import Runtime, TelemetryConfig, PrometheusConfig
 
 with workflow.unsafe.imports_passed_through():
     import os
@@ -26,6 +26,7 @@ with workflow.unsafe.imports_passed_through():
     from orchestrator import metrics
 
 POD_ID = os.getenv("POD_ID")
+SDK_METRICS_PORT = int(os.getenv('HTTP_SDK_METRICS_PORT', "9091"))
 
 
 async def main():
@@ -55,11 +56,21 @@ async def main():
         project_name=os.getenv('PROJECT_NAME', 'orchestrator'),
     )
 
+    logger.info(f'Starting SDK Metrics Server on port {SDK_METRICS_PORT}...')
+
+    new_runtime = Runtime(
+        telemetry=TelemetryConfig(
+            metrics=PrometheusConfig(
+                bind_address=f"0.0.0.0:{SDK_METRICS_PORT}")
+        )
+    )
+
     logger.info(f'Starting Temporal Client at {host}:{namespace}')
 
     temporal_client = await client.Client.connect(
         target_host=host,
-        namespace=namespace
+        namespace=os.getenv('TEMPORAL_NAMESPACE', 'laborious'),
+        runtime=new_runtime
     )
 
     logger.info('Starting Activities...')

values.yaml

@@ -112,6 +112,13 @@ tolerations: []
 affinity: {}
 
 services:
+  sdk-metrics:
+    enabled: true
+    type: ClusterIP
+    port: 9091
+    targetPort: 9091
+    name: sdk-metrics
+
   metrics:
     enabled: true
     type: ClusterIP
@@ -125,18 +132,18 @@ serviceMonitor:
   # Se true, um recurso ServiceMonitor será criado.
   enabled: true
   # O intervalo no qual as métricas devem ser coletadas (ex: 30s, 1m).
-  interval: 30s
+  endpoints:
-  # O path do endpoint de métricas na sua aplicação.
+  - port: metrics
-  path: /metrics
+    path: /metrics
-  # Labels adicionais para o recurso ServiceMonitor.
+    interval: 30s
-  # Essencial para que o Prometheus Operator o descubra. Se você usa o helm chart kube-prometheus-stack,
+    relabelings: []
-  # ele procura por ServiceMonitors com o label "release: kube-prometheus-stack".
+  - port: sdk-metrics
+    path: /metrics
+    interval: 30s
+    relabelings: []
+
   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:
@@ -144,7 +151,7 @@ env:
   - name: GITHUB_REPO_URL
     value: "git@github.com:Aignosi/sientia-dataops-orchestrator_temporal.git"
   - name: GITHUB_BRANCH
-    value: "SIENTIAPDE-1184-investigar-bugs-detectados-no-grafana"
+    value: "SIENTIAPDE-1169-pensar-e-projetar-testes-de-breakdown-e-performance"
   - name: PYTHON_APP
     value: "orchestrator.worker.worker"