Enhance K8s deployment health checks by adding "HealthyRecovery" to default log pattern categories in runbook.robot. Update Azure Service Bus log patterns in k8s_log.py to remove unnecessary conditions and introduce a new pattern for Azure Cosmos DB connection establishment, improving log analysis capabilities and clarity in monitoring Azure services. (#538)

Author: stewartshea

codebundles/k8s-deployment-healthcheck/runbook.robot

@@ -78,7 +78,7 @@ Suite Initialization
     ...    description=Comma-separated list of log pattern categories to scan for.
     ...    pattern=.*
     ...    example=GenericError,AppFailure,StackTrace,Connection
-    ...    default=GenericError,AppFailure,StackTrace,Connection,Timeout,Auth,Exceptions,Resource
+    ...    default=GenericError,AppFailure,StackTrace,Connection,Timeout,Auth,Exceptions,Resource,HealthyRecovery
     ${ANOMALY_THRESHOLD}=    RW.Core.Import User Variable    ANOMALY_THRESHOLD
     ...    type=string
     ...    description=The threshold for detecting event anomalies based on events per minute.

libraries/RW/K8sLog/k8s_log.py

@@ -211,7 +211,7 @@ def _load_error_patterns(self) -> Dict[str, Any]:
                 },
                 {
                     "name": "azure_servicebus_link_lifecycle",
-                    "pattern": r"(?i).*(?:Freeing resources due to error|link.*is force detached).*(?:IdleTimerExpired|Idle timeout)",
+                    "pattern": r"(?i).*(?:Freeing resources due to error|link.*is force detached)",
                     "description": "Azure Service Bus normal link lifecycle and cleanup",
                     "exclude": True
                 },
@@ -220,6 +220,12 @@ def _load_error_patterns(self) -> Dict[str, Any]:
                     "pattern": r"(?i).*Reactor selectable is being disposed.*connectionId",
                     "description": "Azure Service Bus normal reactor cleanup",
                     "exclude": True
+                },
+                {
+                    "name": "azure_cosmosdb_connection_establishment",
+                    "pattern": r"(?i).*Getting database account endpoint from.*\.documents\.azure\.com",
+                    "description": "Azure Cosmos DB normal connection establishment",
+                    "exclude": True
                 }
             ],
             "patterns": {
@@ -308,7 +314,7 @@ def _load_error_patterns(self) -> Dict[str, Any]:
                     },
                     {
                         "name": "azure_servicebus_link_lifecycle",
-                        "pattern": r"(?i).*(?:Freeing resources due to error|link.*is force detached).*(?:IdleTimerExpired|Idle timeout)",
+                        "pattern": r"(?i).*(?:Freeing resources due to error|link.*is force detached)",
                         "severity": 5,
                         "next_steps": ["This is normal Azure Service Bus link lifecycle management", "Links are cleaned up after idle timeout and recreated as needed", "No action required - this indicates healthy connection management"]
                     },