Allow users to provide implicit managed identity to Azure Batch (#6144) [ci fast]

Signed-off-by: adamrtalbot <12817534+adamrtalbot@users.noreply.github.com>
Signed-off-by: Adam Talbot <12817534+adamrtalbot@users.noreply.github.com>
Co-authored-by: Paolo Di Tommaso <paolo.ditommaso@gmail.com>

Author: adamrtalbot

docs/reference/config.md

@@ -417,7 +417,7 @@ The following settings are available:
 `azure.batch.poolIdentityClientId`
 : :::{versionadded} 25.05.0-edge
   :::
-: Specify the client ID for an Azure [managed identity](https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/overview) that is available on all Azure Batch node pools. This identity will be used for task-level authentication to Azure services. See {ref}`azure-managed-identities` for more details.
+: Specify the client ID for an Azure [managed identity](https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/overview) that is available on all Azure Batch node pools. This identity will be used by Fusion to authenticate to Azure storage. If set to `'auto'`, Fusion will use the first available managed identity.
 
 `azure.managedIdentity.clientId`
 : Specify the client ID for an Azure [managed identity](https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/overview). See {ref}`azure-managed-identities` for more details. Defaults to environment variable `AZURE_MANAGED_IDENTITY_USER`.

plugins/nf-azure/src/main/nextflow/cloud/azure/fusion/AzFusionEnv.groovy

@@ -64,7 +64,13 @@ class AzFusionEnv implements FusionEnv {
         // If pool has a managed identity, ONLY add the MSI client ID
         // DO NOT add any SAS token or reference cfg.storage().sasToken
         if (managedIdentityId) {
-            result.FUSION_AZ_MSI_CLIENT_ID = managedIdentityId
+            // Fusion will try and pick up a managed identity that is available.
+            // We recommend explicitly setting the config item to the managed ID so you know which one is being used.
+            // However if set to 'true' it will use whichever is available.
+            // This can be helpful if the pools have different managed identities.
+            if (managedIdentityId != 'auto') {
+                result.FUSION_AZ_MSI_CLIENT_ID = managedIdentityId
+            }
             // No SAS token is added or generated
             return result
         }

plugins/nf-azure/src/test/nextflow/cloud/azure/fusion/AzFusionEnvTest.groovy

@@ -243,4 +243,26 @@ class AzFusionEnvTest extends Specification {
         env.size() == 2  // Only account name and managed identity
     }
 
+    def 'should not provide explicit managed identity when pool identity is set to true'() {
+        given:
+        def NAME = 'myaccount'
+        Global.session = Mock(Session) {
+            getConfig() >> [azure: [
+                storage: [accountName: NAME],
+                batch: [poolIdentityClientId: 'auto']
+            ]]
+        }
+
+        when:
+        def config = Mock(FusionConfig)
+        def fusionEnv = new AzFusionEnv()
+        def env = fusionEnv.getEnvironment('az', config)
+
+        then:
+        env.AZURE_STORAGE_ACCOUNT == NAME
+        !env.FUSION_AZ_MSI_CLIENT_ID
+        !env.AZURE_STORAGE_SAS_TOKEN  // SAS token should NOT be present
+        env.size() == 1  // Only account name
+    }
+
 }