feat: add Log Analytics workspace and diagnostics for deployment infrastructure (#300)

* feat: add Log Analytics workspace and diagnostics for deployment container

- Added a Log Analytics workspace resource to monitor deployment activities.
- Implemented diagnostic settings for the deployment container and blob service.
- Updated variables for log analytics retention and included options for enabling/disabling log analytics.
- Adjusted scale capacity for cognitive deployments to avoid exceeding quotas.
- Enhanced troubleshooting documentation for deployment errors and quota issues.

* feat: add search index configuration script with data fetching and uploading functionality

* feat: add time sleep resources for network readiness and OpenAI provisioning, and create private endpoint for Azure OpenAI service

* fix: adjust dependency declaration for OpenAI provisioning wait and add triggers for readiness check

* fix: update AZURE_ENV_NAME to handle pull request context

* feat: add diagnostic settings for Azure resources to enhance monitoring and logging capabilities

* fix: remove unused azd_env_seed variable from naming configuration

* fix: update naming conventions for Power Platform NSGs in diagnostic settings

* fix: update comment for Azure AI Search Service diagnostic settings and remove unused categories

Author: mawasile

docs/app_registration_setup.md

@@ -7,7 +7,7 @@ To enable secure automation and integration with Azure and Power Platform, you n
 1. Login to your Power Platform:
 
       ```shell
-      pac auth create
+      pac auth create --deviceCode
       ```
 
 1. Create new **App Registration**:

docs/cicd.md

@@ -13,7 +13,7 @@ All infrastructure for CI/CD lives under `cicd/` and can be customized to meet y
 
 ## Prerequisites
 
-- Working local environment of this template. If you do not have one, Follow the step by step instructions for setting up your [**Local Environment**](../README.md#local-environment)
+- Working local environment of this template. If you do not have one, Follow the step by step instructions for setting up your [**Local Environment**](../README.md#local-environment).
 - An Azure subscription with either User Access Administrator or Owner permissions to create workload identity resources like service principal, and OIDC to be used by the GitHub Actions.
 - GitHub CLI (`gh`) installed and authenticated to trigger the bootstrap workflow from your terminal.
 

docs/troubleshooting.md

@@ -0,0 +1,13 @@
+# Troubleshooting tips
+
+## Quota error during deployment
+
+If you see an InsufficientQuota error mentioning "Tokens Per Minute", the requested `scale.capacity` (thousands of TPM) exceeds your subscription's available quota — lower `scale.capacity` in TFVARS or request a quota increase in the Azure portal.
+
+## Private endpoint fails with AccountProvisioningStateInvalid
+
+This occurs when Terraform tries to create the private endpoint before the Azure OpenAI (Cognitive Services) account leaves the `Accepted` state; wait until the resource shows `Succeeded` (portal or `az resource show`) and re-run the provisioning (`azd provision`).
+
+## Use GitHub Copilot to help troubleshoot
+
+If you're unsure how to fix a deployment error, open the relevant files in VS Code and use GitHub Copilot for suggestions. Copilot can propose TFVARS overrides, sample values, terraform plan snippets, or concise support-request wording; always review and test generated suggestions before applying them.

infra/main.ai.tf

@@ -1,6 +1,14 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT license.
 
+# Wait for network infrastructure to be ready
+resource "time_sleep" "wait_for_network_ready" {
+  depends_on = [
+    module.copilot_studio
+  ]
+  create_duration = "30s"
+}
+
 module "azure_open_ai" {
   # checkov:skip=CKV2_AZURE_22: Customer-managed keys should be added in production usage but are not included here for simplicity.
   # checkov:skip=CKV_AZURE_236: The Power Platform AI Search connector only supports service principal, API key, or interactive auth. 
@@ -32,19 +40,41 @@ module "azure_open_ai" {
     ]
   }
 
-  private_endpoints = {
-    pe_endpoint = {
-      name                            = "pe-${azurecaf_name.main_names.results["azurerm_cognitive_account"]}"
-      private_service_connection_name = "pe_endpoint_connection"
-      subnet_resource_id              = local.pe_primary_subnet_id
-    }
-  }
   managed_identities = {
     system_assigned = true
   }
   tags = var.tags
 
-  depends_on = [module.copilot_studio]
+  depends_on = [time_sleep.wait_for_network_ready]
+}
+
+# Wait for Azure OpenAI service to be fully provisioned
+resource "time_sleep" "wait_for_openai_provisioning" {
+  depends_on      = [module.azure_open_ai]
+  create_duration = "60s"
+
+  # Ensure the OpenAI service is in a ready state before proceeding with private endpoint creation
+  triggers = {
+    openai_id = module.azure_open_ai.resource.id
+  }
+}
+
+# Create private endpoint separately to ensure OpenAI service is fully ready
+resource "azurerm_private_endpoint" "openai_pe" {
+  name                = "pe-${azurecaf_name.main_names.results["azurerm_cognitive_account"]}"
+  location            = local.primary_azure_region
+  resource_group_name = local.resource_group_name
+  subnet_id           = local.pe_primary_subnet_id
+  tags                = var.tags
+
+  private_service_connection {
+    name                           = "pe_endpoint_connection"
+    private_connection_resource_id = module.azure_open_ai.resource.id
+    subresource_names              = ["account"]
+    is_manual_connection           = false
+  }
+
+  depends_on = [time_sleep.wait_for_openai_provisioning]
 }
 
 # Private DNS zone for Azure OpenAI private endpoint resolution
@@ -69,12 +99,12 @@ resource "azurerm_private_dns_zone_virtual_network_link" "aoai_dns_links" {
 }
 
 # DNS A record for Azure OpenAI private endpoint
-# The module creates the private endpoint, so we reference it from the module outputs
+# Reference the separately created private endpoint
 resource "azurerm_private_dns_a_record" "aoai_dns_record" {
   name                = module.azure_open_ai.resource.name
   zone_name           = azurerm_private_dns_zone.aoai_dns.name
   resource_group_name = local.resource_group_name
   ttl                 = 10
-  records             = [module.azure_open_ai.private_endpoints["pe_endpoint"].private_service_connection[0].private_ip_address]
+  records             = [azurerm_private_endpoint.openai_pe.private_service_connection[0].private_ip_address]
   tags                = var.tags
 }

infra/main.app_insights.tf

@@ -3,13 +3,27 @@
 
 resource "random_uuid" "uid" {}
 
+resource "azurerm_log_analytics_workspace" "monitoring" {
+  count = var.include_log_analytics ? 1 : 0
+
+  daily_quota_gb      = -1
+  location            = local.primary_azure_region
+  name                = azurecaf_name.main_names.results["azurerm_log_analytics_workspace"]
+  resource_group_name = local.resource_group_name
+  retention_in_days   = var.log_analytics_retention_in_days
+  sku                 = "PerGB2018"
+  tags                = var.tags
+}
+
 resource "azurerm_application_insights" "insights" {
   count = var.include_app_insights ? 1 : 0
 
   application_type    = "web"
   location            = local.primary_azure_region
   name                = "${var.resource_prefix}-appinsights-${var.resource_suffix}"
   resource_group_name = local.resource_group_name
+  workspace_id        = var.include_log_analytics ? azurerm_log_analytics_workspace.monitoring[0].id : null
+  tags                = var.tags
 }
 
 resource "azurerm_application_insights_workbook" "workbook" {