fix(BRE2-940): additional Nebius capacity error mapping

Author: patelspratik

v1/providers/nebius/errors.go

@@ -6,6 +6,7 @@ import (
 
 	v1 "github.com/brevdev/cloud/v1"
 	"github.com/nebius/gosdk/operations"
+	"github.com/nebius/gosdk/serviceerror"
 	"google.golang.org/grpc/codes"
 	"google.golang.org/grpc/status"
 )
@@ -37,6 +38,17 @@ func handleErrToCloudErr(e error) error {
 	if e == nil {
 		return nil
 	}
+	var serviceErr *serviceerror.Error
+	if errors.As(e, &serviceErr) {
+		for _, detail := range serviceErr.Details {
+			switch detail.(type) {
+			case *serviceerror.NotEnoughResources:
+				return v1.ErrInsufficientResources
+			case *serviceerror.QuotaFailure:
+				return v1.ErrOutOfQuota
+			}
+		}
+	}
 	// Check for Nebius operations.Error for ResourceExhausted (returned by operation.Wait on async failures)
 	var opErr *operations.Error
 	if errors.As(e, &opErr) {

v1/providers/nebius/errors_test.go

@@ -0,0 +1,68 @@
+package v1
+
+import (
+	"errors"
+	"testing"
+
+	cloudv1 "github.com/brevdev/cloud/v1"
+	common "github.com/nebius/gosdk/proto/nebius/common/v1"
+	"github.com/nebius/gosdk/serviceerror"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+)
+
+func TestHandleErrToCloudErrMapsNotEnoughResourcesToInsufficientResources(t *testing.T) {
+	t.Parallel()
+
+	err := &serviceerror.Error{
+		Wrapped: status.Error(codes.ResourceExhausted, "operation failed"),
+		Details: []serviceerror.Detail{
+			serviceerror.NewDetail(&common.ServiceError{
+				Service: "compute",
+				Code:    "NotEnoughResources",
+				Details: &common.ServiceError_NotEnoughResources{
+					NotEnoughResources: &common.NotEnoughResources{
+						Violations: []*common.NotEnoughResources_Violation{
+							{
+								ResourceType: "virtualMachine",
+								Requested:    "1gpu-16vcpu-64gb",
+								Message:      "VM schedule timeout, most likely due to insufficient hardware resources",
+							},
+						},
+					},
+				},
+			}),
+		},
+	}
+
+	require.True(t, errors.Is(handleErrToCloudErr(err), cloudv1.ErrInsufficientResources))
+}
+
+func TestHandleErrToCloudErrMapsQuotaFailureToOutOfQuota(t *testing.T) {
+	t.Parallel()
+
+	err := &serviceerror.Error{
+		Wrapped: status.Error(codes.ResourceExhausted, "operation failed"),
+		Details: []serviceerror.Detail{
+			serviceerror.NewDetail(&common.ServiceError{
+				Service: "compute",
+				Code:    "QuotaFailure",
+				Details: &common.ServiceError_QuotaFailure{
+					QuotaFailure: &common.QuotaFailure{
+						Violations: []*common.QuotaFailure_Violation{
+							{
+								Quota:     "compute.instance.gpu.h100",
+								Limit:     "0",
+								Requested: "1",
+								Message:   "quota exceeded",
+							},
+						},
+					},
+				},
+			}),
+		},
+	}
+
+	require.True(t, errors.Is(handleErrToCloudErr(err), cloudv1.ErrOutOfQuota))
+}

v1/providers/nebius/instance.go

@@ -868,7 +868,6 @@ func matchesTagFilters(instanceTags map[string]string, tagFilters map[string][]s
 	return true
 }
 
-//nolint:dupl // StopInstance and StartInstance have similar structure but different operations
 func (c *NebiusClient) StopInstance(ctx context.Context, instanceID v1.CloudProviderInstanceID) error {
 	c.logger.Debug(ctx, "initiating instance stop operation",
 		v1.LogField("instanceID", instanceID))
@@ -906,7 +905,6 @@ func (c *NebiusClient) StopInstance(ctx context.Context, instanceID v1.CloudProv
 	return nil
 }
 
-//nolint:dupl // StartInstance and StopInstance have similar structure but different operations
 func (c *NebiusClient) StartInstance(ctx context.Context, instanceID v1.CloudProviderInstanceID) error {
 	c.logger.Debug(ctx, "initiating instance start operation",
 		v1.LogField("instanceID", instanceID))
@@ -916,17 +914,18 @@ func (c *NebiusClient) StartInstance(ctx context.Context, instanceID v1.CloudPro
 		Id: string(instanceID),
 	})
 	if err != nil {
-		return fmt.Errorf("failed to initiate instance start: %w", err)
+		return fmt.Errorf("failed to initiate instance start: %w", handleErrToCloudErr(err))
 	}
 
 	// Wait for the start operation to complete
 	finalOp, err := operation.Wait(ctx)
 	if err != nil {
-		return fmt.Errorf("failed to wait for instance start: %w", err)
+		return fmt.Errorf("failed to wait for instance start: %w", handleErrToCloudErr(err))
 	}
 
 	if !finalOp.Successful() {
-		return fmt.Errorf("instance start failed: %v", finalOp.Status())
+		statusErr := fmt.Errorf("instance start failed: %v", finalOp.Status())
+		return handleErrToCloudErr(statusErr)
 	}
 
 	c.logger.Debug(ctx, "start operation completed, waiting for instance to reach RUNNING state",