engine/direct: recover from a failed Create during Recreate

NEXT_CHANGELOG.md

@@ -5,5 +5,6 @@
 ### CLI
 
 ### Bundles
+* engine/direct: Drop the deployment state entry on a recreate before the follow-up `Create`, so a `Create` failure no longer leaves a broken state with `invalid state: empty id` on the next `bundle plan` ([#5173](https://github.com/databricks/cli/pull/5173)).
 
 ### Dependency updates

acceptance/bundle/resources/vector_search_endpoints/recreate/create-fails/databricks.yml.tmpl

@@ -0,0 +1,14 @@
+bundle:
+  name: recreate-create-fails-$UNIQUE_NAME
+
+sync:
+  paths: []
+
+resources:
+  vector_search_endpoints:
+    my_endpoint:
+      name: vs-endpoint-a-$UNIQUE_NAME
+      endpoint_type: STANDARD
+    blocker_endpoint:
+      name: vs-endpoint-b-$UNIQUE_NAME
+      endpoint_type: STORAGE_OPTIMIZED

acceptance/bundle/resources/vector_search_endpoints/recreate/create-fails/output.txt

@@ -0,0 +1,42 @@
+
+=== Initial deploy creates two endpoints with distinct names
+>>> [CLI] bundle deploy
+Uploading bundle files to /Workspace/Users/[USERNAME]/.bundle/recreate-create-fails-[UNIQUE_NAME]/default/files...
+Deploying resources...
+Updating deployment state...
+Deployment complete!
+
+=== Edit my_endpoint: rename onto blocker_endpoint's name and switch endpoint_type to trigger Recreate
+>>> update_file.py databricks.yml vs-endpoint-a-[UNIQUE_NAME] vs-endpoint-b-[UNIQUE_NAME]
+
+>>> update_file.py databricks.yml       endpoint_type: STANDARD       endpoint_type: STORAGE_OPTIMIZED
+
+=== Deploy: Recreate of my_endpoint runs Delete (ok) then Create (409, name taken by blocker)
+>>> [CLI] bundle deploy --auto-approve
+Uploading bundle files to /Workspace/Users/[USERNAME]/.bundle/recreate-create-fails-[UNIQUE_NAME]/default/files...
+Deploying resources...
+Error: cannot recreate resources.vector_search_endpoints.my_endpoint: Vector search endpoint with name vs-endpoint-b-[UNIQUE_NAME] already exists (409 RESOURCE_ALREADY_EXISTS)
+
+Endpoint: POST [DATABRICKS_URL]/api/2.0/vector-search/endpoints
+HTTP Status: 409 Conflict
+API error_code: RESOURCE_ALREADY_EXISTS
+API message: Vector search endpoint with name vs-endpoint-b-[UNIQUE_NAME] already exists
+
+Updating deployment state...
+
+Exit code: 1
+
+=== Subsequent plan recovers: my_endpoint state was dropped, replan as Create
+>>> [CLI] bundle plan
+create vector_search_endpoints.my_endpoint
+
+Plan: 1 to add, 0 to change, 0 to delete, 1 unchanged
+
+>>> [CLI] bundle destroy --auto-approve
+The following resources will be deleted:
+  delete resources.vector_search_endpoints.blocker_endpoint
+
+All files and directories at the following location will be deleted: /Workspace/Users/[USERNAME]/.bundle/recreate-create-fails-[UNIQUE_NAME]/default
+
+Deleting files...
+Destroy complete!

acceptance/bundle/resources/vector_search_endpoints/recreate/create-fails/script

@@ -0,0 +1,20 @@
+envsubst < databricks.yml.tmpl > databricks.yml
+
+cleanup() {
+    trace $CLI bundle destroy --auto-approve || true
+    rm -f out.requests.txt
+}
+trap cleanup EXIT
+
+title "Initial deploy creates two endpoints with distinct names"
+trace $CLI bundle deploy
+
+title "Edit my_endpoint: rename onto blocker_endpoint's name and switch endpoint_type to trigger Recreate"
+trace update_file.py databricks.yml "vs-endpoint-a-$UNIQUE_NAME" "vs-endpoint-b-$UNIQUE_NAME"
+trace update_file.py databricks.yml "      endpoint_type: STANDARD" "      endpoint_type: STORAGE_OPTIMIZED"
+
+title "Deploy: Recreate of my_endpoint runs Delete (ok) then Create (409, name taken by blocker)"
+errcode trace $CLI bundle deploy --auto-approve
+
+title "Subsequent plan recovers: my_endpoint state was dropped, replan as Create"
+trace $CLI bundle plan

acceptance/bundle/resources/vector_search_endpoints/recreate/create-fails/test.toml

@@ -0,0 +1 @@
+Cloud = false

bundle/direct/apply.go

@@ -86,7 +86,9 @@ func (d *DeploymentUnit) Recreate(ctx context.Context, db *dstate.DeploymentStat
 		return fmt.Errorf("deleting old id=%s: %w", oldID, err)
 	}
 
-	err = db.SaveState(d.ResourceKey, "", nil, nil)
+	// Drop the state entry so a subsequent failure of Create leaves no malformed
+	// (empty-id) entry behind. The next plan will see "no state" and retry as Create.
+	err = db.DeleteState(d.ResourceKey)
 	if err != nil {
 		return fmt.Errorf("deleting state: %w", err)
 	}

bundle/direct/bundle_plan.go

@@ -181,16 +181,15 @@ func (b *DeploymentBundle) CalculatePlan(ctx context.Context, client *databricks
 		}
 
 		dbentry, hasEntry := b.StateDB.GetResourceEntry(resourceKey)
-		if !hasEntry {
+		// Tolerate empty-id entries from older partial-recreate failures
+		// (apply.Recreate now deletes state on the way through, but pre-fix
+		// state files may still carry a malformed entry). Treat as missing
+		// and let the resource be re-created on this plan.
+		if !hasEntry || dbentry.ID == "" {
 			entry.Action = deployplan.Create
 			return true
 		}
 
-		if dbentry.ID == "" {
-			logdiag.LogError(ctx, fmt.Errorf("%s: invalid state: empty id", errorPrefix))
-			return false
-		}
-
 		savedState, err := parseState(adapter.StateType(), dbentry.State)
 		if err != nil {
 			logdiag.LogError(ctx, fmt.Errorf("%s: interpreting state: %w", errorPrefix, err))