PPHA-785: create 500 error alarms only

docs/infrastructure/create-environment.md

@@ -133,3 +133,16 @@ Add the infrastructure secrets to the _inf_ key vault `kv-lungcs-[environment]-i
 
 - assign yourself "Key Vault Secrets User" to application key vault to run the terraform code from the CLI inside the AVD when first trying to deploy the application.
 - assign yourself "Data Blob Reader" to State file storage account to run the terraform code from the CLI inside the AVD when first trying to deploy the application.
+
+## Connect to Postgres Database
+
+- Add your user as a member to the respective Entra ID group:
+  - `postgres_lungcs_[environment]_uks_admin`
+- Log into the correct ADV for your environment type (either nonlive or live)
+- Run the following commands on the CLI to log into the database: -
+  - `export PGPASSWORD="$(az account get-access-token --resource https://ossrdbms-aad.database.windows.net --query accessToken --output tsv)"`
+  - `psql "host=postgres-lungcs-[environment]-uks.postgres.database.azure.com \
+      port=5432 \
+      dbname=[database] \
+      user=postgres_lungcs_[environment]_uks_admin \
+      sslmode=require"`

infrastructure/modules/container-apps/alerts.tf

@@ -0,0 +1,35 @@
+resource "azurerm_monitor_scheduled_query_rules_alert_v2" "five_hundred_error_alert" {
+  count = var.enable_alerting ? 1 : 0
+
+  auto_mitigation_enabled          = false
+  description                      = "An alert triggered by 500 errors logged in code"
+  enabled                          = var.enable_alerting
+  evaluation_frequency             = "PT5M"
+  location                         = var.region
+  name                             = "${var.app_short_name}-500-error-alert"
+  resource_group_name              = azurerm_resource_group.main.name
+  scopes                           = [var.action_group_id]
+  severity                         = 2
+  skip_query_validation            = false
+  window_duration                  = "PT5M"
+  workspace_alerts_storage_enabled = false
+
+  action {
+    action_groups = [var.action_group_id]
+  }
+
+  criteria {
+    operator                = "GreaterThan"
+    query                   = <<-QUERY
+      ContainerAppConsoleLogs_CL
+      | where Log contains "[ERROR]"
+      QUERY
+    threshold               = 0
+    time_aggregation_method = "Count"
+
+    failing_periods {
+      minimum_failing_periods_to_trigger_alert = 1
+      number_of_evaluation_periods             = 1
+    }
+  }
+}

scripts/config/vale/styles/config/vocabularies/words/accept.txt

@@ -30,3 +30,4 @@ yaml
 jq
 choco
 CLI
+nonlive