Fix telemetry "Unknown" errors: wrap string exceptions, add missing instrumentation, and catch-all decorato (#53)

* adding telemetry updates to update unknown

* Fix telemetry reporting: wrap string exceptions in Exception() and add catch-all decorator

- Replace all exception='string' calls with exception=Exception('string') across
  custom.py, _utils.py, and _precheckutils.py so that ExceptionName in telemetry
  shows 'Exception' instead of 'str'
- Add _telemetry_catch_all decorator to top-level command functions
  (create, delete, update, upgrade) to catch unhandled exceptions, log them
  to telemetry with proper ExceptionName/FaultType, and re-raise as
  CLIInternalError instead of letting them become 'UnknownError'

* Fix mypy and ruff: add type annotations to _telemetry_catch_all decorator and fix import sorting

* Apply ruff format to fix CI format check

* Remove accidentally committed files

Author: ashnanze

src/connectedk8s/azext_connectedk8s/_constants.py

@@ -148,6 +148,14 @@
 Agent_State_Succeeded = "Succeeded"
 Agent_State_Failed = "Failed"
 Agent_State_Timeout = 15
+Agent_State_Timeout_Fault_Type = "agent-state-timeout-error"
+Provisioned_Cluster_Operation_Fault_Type = "provisioned-cluster-unsupported-operation"
+Update_No_Params_Fault_Type = "update-no-parameters-specified"
+Update_Proxy_Conflict_Fault_Type = "update-proxy-parameters-conflict"
+Connected_Cluster_Resource_Id_None_Fault_Type = (
+    "connected-cluster-resource-id-none-error"
+)
+Custom_Locations_Enable_Failed_Fault_Type = "custom-locations-enable-failed"
 Get_Credentials_Failed_Fault_Type = "failed-to-get-list-cluster-user-credentials"
 Failed_To_Merge_Credentials_Fault_Type = "failed-to-merge-credentials"
 Kubeconfig_Failed_To_Load_Fault_Type = "failed-to-load-kubeconfig-file"

src/connectedk8s/azext_connectedk8s/_precheckutils.py

@@ -206,7 +206,7 @@ def executing_cluster_diagnostic_checks_job(
                         'cluster-diagnostic-checks -n azure-arc-release" and try onboarding again'
                     )
                     telemetry.set_exception(
-                        exception=error_kubectl_delete_helm.decode("ascii"),
+                        exception=Exception(error_kubectl_delete_helm.decode("ascii")),
                         fault_type=consts.Cluster_Diagnostic_Checks_Release_Cleanup_Failed,
                         summary="Error while executing Cluster Diagnostic Checks Job",
                     )
@@ -309,7 +309,9 @@ def executing_cluster_diagnostic_checks_job(
         # If job is not scheduled then we will delete the helm release
         if is_job_scheduled is False:
             telemetry.set_exception(
-                exception="Couldn't schedule Cluster Diagnostic Checks Job in the cluster",
+                exception=Exception(
+                    "Couldn't schedule Cluster Diagnostic Checks Job in the cluster"
+                ),
                 fault_type=consts.Cluster_Diagnostic_Checks_Job_Not_Scheduled,
                 summary="Couldn't schedule Cluster Diagnostic Checks Job in the cluster",
             )
@@ -390,7 +392,9 @@ def executing_cluster_diagnostic_checks_job(
                     )
 
             telemetry.set_exception(
-                exception="Couldn't complete Cluster Diagnostic Checks Job after scheduling in the cluster",
+                exception=Exception(
+                    "Couldn't complete Cluster Diagnostic Checks Job after scheduling in the cluster"
+                ),
                 fault_type=consts.Cluster_Diagnostic_Checks_Job_Not_Complete,
                 summary="Couldn't complete Cluster Diagnostic Checks Job after scheduling in the cluster",
             )
@@ -467,7 +471,7 @@ def helm_install_release_cluster_diagnostic_checks(
             telemetry.set_user_fault()
 
         telemetry.set_exception(
-            exception=error,
+            exception=Exception(error),
             fault_type=consts.Cluster_Diagnostic_Checks_Helm_Install_Failed_Fault_Type,
             summary="Unable to install cluster diagnostic checks helm release",
         )

src/connectedk8s/azext_connectedk8s/_utils.py

@@ -127,7 +127,7 @@ def validate_connect_rp_location(cmd: CLICommand, location: str) -> None:
             ]
             if location.lower() not in rp_locations:
                 telemetry.set_exception(
-                    exception="Location not supported",
+                    exception=Exception("Location not supported"),
                     fault_type=consts.Invalid_Location_Fault_Type,
                     summary="Provided location is not supported for creating connected clusters",
                 )
@@ -146,7 +146,9 @@ def validate_custom_token(
     if os.getenv("AZURE_ACCESS_TOKEN"):
         if os.getenv("AZURE_SUBSCRIPTION_ID") is None:
             telemetry.set_exception(
-                exception="Required environment variable SubscriptionId not set, for custom Azure access token",
+                exception=Exception(
+                    "Required environment variable SubscriptionId not set, for custom Azure access token"
+                ),
                 fault_type=consts.Custom_Access_Token_Env_Var_Sub_Id_Missing_Fault_Type,
                 summary="Required environment variable SubscriptionId not set, for custom Azure access token",
             )
@@ -155,7 +157,9 @@ def validate_custom_token(
             )
         if os.getenv("AZURE_TENANT_ID") is None:
             telemetry.set_exception(
-                exception="Required environment variable TenantId not set, for custom Azure access token",
+                exception=Exception(
+                    "Required environment variable TenantId not set, for custom Azure access token"
+                ),
                 fault_type=consts.Custom_Access_Token_Env_Var_Tenant_Id_Missing_Fault_Type,
                 summary="Required environment variable TenantId not set, for custom Azure access token",
             )
@@ -248,7 +252,7 @@ def pull_helm_chart(
         ):
             error_summary = "This CLI version does not support upgrading to Agents versions older than v1.14"
             telemetry.set_exception(
-                exception="Operation not supported on older Agents",
+                exception=Exception("Operation not supported on older Agents"),
                 fault_type=consts.Operation_Not_Supported_Fault_Type,
                 summary=error_summary,
             )
@@ -289,7 +293,7 @@ def pull_helm_chart(
             error = error_helm_chart_pull.decode("ascii")
             if i == retry_count - 1:
                 telemetry.set_exception(
-                    exception=error,
+                    exception=Exception(error),
                     fault_type=consts.Pull_HelmChart_Fault_Type,
                     summary=f"Unable to pull {chart_name} helm charts from the registry",
                 )
@@ -347,7 +351,7 @@ def save_cluster_diagnostic_checks_pod_description(
                             f.write(pod_description)
                 else:
                     telemetry.set_exception(
-                        exception=error_describe_job_pod.decode("ascii"),
+                        exception=Exception(error_describe_job_pod.decode("ascii")),
                         fault_type=consts.Cluster_Diagnostic_Checks_Pod_Description_Save_Failed,
                         summary="Failed to save cluster diagnostic checks pod description in the local machine",
                     )
@@ -415,7 +419,7 @@ def check_cluster_DNS(
                         + "\nWe found an issue with the DNS resolution on your cluster."
                     )
             telemetry.set_exception(
-                exception="DNS resolution check failed in the cluster",
+                exception=Exception("DNS resolution check failed in the cluster"),
                 fault_type=consts.DNS_Check_Failed,
                 summary="DNS check failed in the cluster",
             )
@@ -526,7 +530,9 @@ def check_cluster_outbound_connectivity(
                 )
                 telemetry.set_user_fault()
                 telemetry.set_exception(
-                    exception="Outbound network connectivity check failed for the Cluster Connect endpoint",
+                    exception=Exception(
+                        "Outbound network connectivity check failed for the Cluster Connect endpoint"
+                    ),
                     fault_type=consts.Outbound_Connectivity_Check_Failed_For_Cluster_Connect,
                     summary="Outbound network connectivity check failed for the Cluster Connect precheck endpoint",
                 )
@@ -595,7 +601,9 @@ def check_cluster_outbound_connectivity(
                         "required for onboarding."
                     )
             telemetry.set_exception(
-                exception="Outbound network connectivity check failed for onboarding",
+                exception=Exception(
+                    "Outbound network connectivity check failed for onboarding"
+                ),
                 fault_type=consts.Outbound_Connectivity_Check_Failed_For_Onboarding,
                 summary="Outbound network connectivity check for onboarding failed in the cluster",
             )
@@ -646,7 +654,7 @@ def check_cluster_outbound_connectivity(
                         + "\nWe found an issue with Outbound network connectivity from the cluster."
                     )
             telemetry.set_exception(
-                exception="Outbound network connectivity check failed",
+                exception=Exception("Outbound network connectivity check failed"),
                 fault_type=consts.Outbound_Connectivity_Check_Failed,
                 summary="Outbound network connectivity check failed in the cluster",
             )
@@ -769,7 +777,7 @@ def add_helm_repo(
     if response_helm_repo.returncode != 0:
         error = error_helm_repo.decode("ascii")
         telemetry.set_exception(
-            exception=error,
+            exception=Exception(error),
             fault_type=consts.Add_HelmRepo_Fault_Type,
             summary="Failed to add helm repository",
         )
@@ -820,7 +828,7 @@ def get_helm_registry(
             )
     else:
         telemetry.set_exception(
-            exception="No content in response",
+            exception=Exception("No content in response"),
             fault_type=consts.Get_HelmRegistery_Path_Fault_Type,
             summary="No content in acr path response",
         )
@@ -881,7 +889,7 @@ def get_helm_values(
             )
     else:
         telemetry.set_exception(
-            exception="No content in response",
+            exception=Exception("No content in response"),
             fault_type=consts.Get_HelmRegistery_Path_Fault_Type,
             summary="No content in acr path response",
         )
@@ -915,7 +923,7 @@ def health_check_dp(cmd: CLICommand, config_dp_endpoint: str) -> bool:
         return True
 
     telemetry.set_exception(
-        exception="Error while performing DP health check",
+        exception=Exception("Error while performing DP health check"),
         fault_type=consts.DP_Health_Check_Fault_Type,
         summary="Error while performing DP health check",
     )
@@ -977,7 +985,7 @@ def update_gateway_cluster_link(
         return True
 
     telemetry.set_exception(
-        exception=f"Gateway {operation_type} failed",
+        exception=Exception(f"Gateway {operation_type} failed"),
         fault_type=consts.GATEWAY_LINK_FAULT_TYPE,
         summary=f"Gateway {operation_type} failed",
     )
@@ -1230,7 +1238,7 @@ def delete_arc_agents(
         ):
             telemetry.set_user_fault()
         telemetry.set_exception(
-            exception=error_helm_delete.decode("ascii"),
+            exception=Exception(error_helm_delete.decode("ascii")),
             fault_type=consts.Delete_HelmRelease_Fault_Type,
             summary="Unable to delete helm release",
         )
@@ -1434,7 +1442,7 @@ def helm_install_release(
         ):
             telemetry.set_user_fault()
         telemetry.set_exception(
-            exception=helm_install_error_message,
+            exception=Exception(helm_install_error_message),
             fault_type=consts.Install_HelmRelease_Fault_Type,
             summary="Unable to install helm release",
         )
@@ -1548,7 +1556,7 @@ def get_release_namespace(
             telemetry.set_user_fault()
 
         telemetry.set_exception(
-            exception=error,
+            exception=Exception(error),
             fault_type=consts.List_HelmRelease_Fault_Type,
             summary="Unable to list helm release",
         )
@@ -1634,7 +1642,9 @@ def check_provider_registrations(
         ).registration_state
         if cc_registration_state not in consts.allowed_rp_registration_states:
             telemetry.set_exception(
-                exception=f"{consts.Connected_Cluster_Provider_Namespace} provider is not registered",
+                exception=Exception(
+                    f"{consts.Connected_Cluster_Provider_Namespace} provider is not registered"
+                ),
                 fault_type=consts.CC_Provider_Namespace_Not_Registered_Fault_Type,
                 summary=f"{consts.Connected_Cluster_Provider_Namespace} provider is not registered",
             )
@@ -1649,7 +1659,9 @@ def check_provider_registrations(
         if kc_registration_state not in consts.allowed_rp_registration_states:
             if is_workload_identity_enabled:
                 telemetry.set_exception(
-                    exception=f"{consts.Kubernetes_Configuration_Provider_Namespace} provider is not registered",
+                    exception=Exception(
+                        f"{consts.Kubernetes_Configuration_Provider_Namespace} provider is not registered"
+                    ),
                     fault_type=consts.Kubernetes_Configuration_Provider_Namespace_Not_Registered_Fault_Type,
                     summary=f"{consts.Kubernetes_Configuration_Provider_Namespace} provider is not registered",
                 )
@@ -1670,7 +1682,9 @@ def check_provider_registrations(
             ).registration_state
             if hc_registration_state not in consts.allowed_rp_registration_states:
                 telemetry.set_exception(
-                    exception=f"{consts.Hybrid_Compute_Provider_Namespace} provider is not registered",
+                    exception=Exception(
+                        f"{consts.Hybrid_Compute_Provider_Namespace} provider is not registered"
+                    ),
                     fault_type=consts.HC_Provider_Namespace_Not_Registered_Fault_Type,
                     summary=f"{consts.Hybrid_Compute_Provider_Namespace} provider is not registered",
                 )
@@ -1829,7 +1843,7 @@ def helm_update_agent(
         if "forbidden" in error or "timed out waiting for the condition" in error:
             telemetry.set_user_fault()
             telemetry.set_exception(
-                exception=error,
+                exception=Exception(error),
                 fault_type=consts.Get_Helm_Values_Failed,
                 summary="Error while doing helm get values azure-arc",
             )
@@ -1866,7 +1880,7 @@ def helm_update_agent(
         ):
             telemetry.set_user_fault()
         telemetry.set_exception(
-            exception=helm_upgrade_error_message,
+            exception=Exception(helm_upgrade_error_message),
             fault_type=consts.Install_HelmRelease_Fault_Type,
             summary="Unable to install helm release",
         )