⚠ remove ClusterObjectSet Ready RetryableError reason

api/v1/clusterobjectset_types.go

@@ -34,7 +34,6 @@ const (
 	ClusterObjectSetReasonObjectsNotReady   = "ObjectsNotReady"
 	ClusterObjectSetReasonSuperseded        = "Superseded"
 	ClusterObjectSetReasonObjectCollision   = "ObjectCollision"
-	ClusterObjectSetReasonRetryableError    = "RetryableError"
 	ClusterObjectSetReasonValidationFailure = "ValidationFailure"
 	ClusterObjectSetReasonAllObjectsReady   = "AllObjectsReady"
 )
@@ -506,10 +505,12 @@ type ClusterObjectSetStatus struct {
 	//   - False with reason ObjectCollision: one or more objects are controlled by another owner, or are unowned while collision protection prevents adoption, so this revision cannot take ownership of them.
 	//   - False with reason ValidationFailure: the revision failed a pre-apply check (an invalid revision/phase object or probe, preflight validation, a mutable referenced Secret, or changed referenced content) and requires manual intervention.
 	//   - False with reason ProgressDeadlineExceeded: the revision did not roll out within spec.progressDeadlineMinutes.
-	//   - False with reason RetryableError: the revision encountered a transient error that may resolve on a subsequent reconciliation.
 	//   - False with reason Archiving: the revision is being archived and its owned objects are still being torn down.
 	//   - False with reason Archived: the revision has been archived and its objects have been torn down.
 	//
+	// A transient internal error leaves the Ready condition unchanged and is retried
+	// with backoff; it is not reported as a distinct reason.
+	//
 	// Rollout completion is recorded separately by status.completedAt.
 	//
 	// +listType=map

docs/draft/concepts/clusterobjectsets.md

@@ -221,11 +221,12 @@ Indicates whether all objects in the revision have been successfully rolled out
 | False | `Superseded` | One or more objects have been adopted by a newer revision of the object set |
 | False | `ObjectCollision` | One or more objects are controlled by another owner, or are unowned and collision protection prevents adoption |
 | False | `ValidationFailure` | A pre-apply check failed (an invalid revision/phase object or probe, preflight validation, a mutable referenced Secret, or changed referenced content); requires manual intervention |
-| Unknown | `RetryableError` | Error prevented probe observation |
 | False | `Archiving` | The revision is being archived; owned objects are still being torn down |
 | False | `Archived` | Objects torn down after archival |
 | Unknown | `Migrated` | Migrated from existing release; probes not yet observed |
 
+A transient internal error (e.g. an API read failure) leaves the `Ready` condition unchanged and is retried with backoff; it is not reported as a distinct reason, so on a first reconcile the condition may remain absent (`Unknown`).
+
 ### Succeeded
 
 A terminal condition set once the rollout completes. It persists even if the revision later becomes unavailable, marking that this version was successfully deployed at least once.

docs/draft/concepts/large-bundle-support.md

@@ -416,8 +416,8 @@ The reconciler distinguishes two failure modes:
 
 - A referenced **Secret that does not exist yet** — for example, informer cache lag
   after creation, or a partially completed creation sequence — is treated as a
-  transient error. The ClusterObjectSet reports `Ready=False, Reason=RetryableError`
-  and the controller retries with backoff.
+  transient error. The ClusterObjectSet leaves its `Ready` condition unchanged and the
+  controller returns the error so it retries with backoff.
 - **Invalid referenced content** — a missing key, a malformed manifest, or content
   that has changed since first rollout — is a validation failure. The ClusterObjectSet
   reports `Ready=False, Reason=ValidationFailure`. Because referenced Secrets are not

helm/olmv1/base/object-controller/crd/experimental/olm.operatorframework.io_clusterobjectsets.yaml

@@ -564,10 +564,12 @@ spec:
                     - False with reason ObjectCollision: one or more objects are controlled by another owner, or are unowned while collision protection prevents adoption, so this revision cannot take ownership of them.
                     - False with reason ValidationFailure: the revision failed a pre-apply check (an invalid revision/phase object or probe, preflight validation, a mutable referenced Secret, or changed referenced content) and requires manual intervention.
                     - False with reason ProgressDeadlineExceeded: the revision did not roll out within spec.progressDeadlineMinutes.
-                    - False with reason RetryableError: the revision encountered a transient error that may resolve on a subsequent reconciliation.
                     - False with reason Archiving: the revision is being archived and its owned objects are still being torn down.
                     - False with reason Archived: the revision has been archived and its objects have been torn down.
 
+                  A transient internal error leaves the Ready condition unchanged and is retried
+                  with backoff; it is not reported as a distinct reason.
+
                   Rollout completion is recorded separately by status.completedAt.
                 items:
                   description: Condition contains details for one aspect of the current

internal/object-controller/controllers/clusterobjectset_controller.go

@@ -149,10 +149,9 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 			markAsNotReady(cos, ocv1.ClusterObjectSetReasonValidationFailure, err.Error())
 			return ctrl.Result{RequeueAfter: validationRetryInterval}, nil
 		}
-		// A Secret read error is transient; surface it as retryable and requeue with backoff.
-		werr := fmt.Errorf("verifying referenced Secrets: %v", err)
-		setRetryableErrorConditions(cos, werr.Error(), isDeadlineExceeded)
-		return ctrl.Result{}, werr
+		// A Secret read error is transient; leave the Ready condition unchanged and
+		// return the error for rate-limited backoff.
+		return ctrl.Result{}, fmt.Errorf("verifying referenced Secrets: %v", err)
 	}
 
 	phases, currentPhases, opts, err := c.buildBoxcutterPhases(ctx, cos)
@@ -174,7 +173,6 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 			markAsNotReady(cos, ocv1.ClusterObjectSetReasonValidationFailure, err.Error())
 			return ctrl.Result{}, nil
 		}
-		setRetryableErrorConditions(cos, err.Error(), isDeadlineExceeded)
 		return ctrl.Result{}, fmt.Errorf("converting to boxcutter revision: %v", err)
 	}
 
@@ -191,7 +189,6 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 
 	revisionEngine, err := c.RevisionEngineFactory.CreateRevisionEngine(ctx, cos)
 	if err != nil {
-		setRetryableErrorConditions(cos, err.Error(), isDeadlineExceeded)
 		return ctrl.Result{}, fmt.Errorf("failed to create revision engine: %v", err)
 	}
 
@@ -205,7 +202,6 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 
 	if cos.Spec.LifecycleState == ocv1.ClusterObjectSetLifecycleStateArchived {
 		if err := c.TrackingCache.Free(ctx, cos); err != nil {
-			markAsNotReady(cos, ocv1.ClusterObjectSetReasonRetryableError, err.Error())
 			return ctrl.Result{}, fmt.Errorf("error stopping informers: %v", err)
 		}
 		return c.archive(ctx, revisionEngine, cos, revision)
@@ -216,9 +212,7 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 	}
 
 	if err := c.establishWatch(ctx, cos, revision); err != nil {
-		werr := fmt.Errorf("establish watch: %v", err)
-		setRetryableErrorConditions(cos, werr.Error(), isDeadlineExceeded)
-		return ctrl.Result{}, werr
+		return ctrl.Result{}, fmt.Errorf("establish watch: %v", err)
 	}
 
 	rres, err := revisionEngine.Reconcile(ctx, revision, opts...)
@@ -227,7 +221,6 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 			// Log detailed reconcile reports only in debug mode (V(1)) to reduce verbosity.
 			l.V(1).Info("reconcile report", "report", rres.String())
 		}
-		setRetryableErrorConditions(cos, err.Error(), isDeadlineExceeded)
 		return ctrl.Result{}, fmt.Errorf("revision reconcile: %v", err)
 	}
 
@@ -389,7 +382,6 @@ func (c *ClusterObjectSetReconciler) reconcile(ctx context.Context, cos *ocv1.Cl
 
 func (c *ClusterObjectSetReconciler) delete(ctx context.Context, cos *ocv1.ClusterObjectSet) (ctrl.Result, error) {
 	if err := c.TrackingCache.Free(ctx, cos); err != nil {
-		markAsNotReady(cos, ocv1.ClusterObjectSetReasonRetryableError, err.Error())
 		return ctrl.Result{}, fmt.Errorf("error stopping informers: %v", err)
 	}
 	if err := c.removeFinalizer(ctx, cos, clusterObjectSetTeardownFinalizer); err != nil {
@@ -401,9 +393,9 @@ func (c *ClusterObjectSetReconciler) delete(ctx context.Context, cos *ocv1.Clust
 func (c *ClusterObjectSetReconciler) archive(ctx context.Context, revisionEngine RevisionEngine, cos *ocv1.ClusterObjectSet, revision boxcutter.RevisionBuilder) (ctrl.Result, error) {
 	tdres, err := revisionEngine.Teardown(ctx, revision, machinerytypes.WithObserveAfterIncomplete{})
 	if err != nil {
-		err = fmt.Errorf("error archiving revision: %v", err)
-		setRetryableErrorConditions(cos, err.Error(), false)
-		return ctrl.Result{}, err
+		// Transient teardown error: leave the Ready condition unchanged and return
+		// the error for rate-limited backoff.
+		return ctrl.Result{}, fmt.Errorf("error archiving revision: %v", err)
 	}
 	if tdres != nil && !tdres.IsComplete() {
 		markAsArchiving(cos)
@@ -769,10 +761,6 @@ func setReadyWithDeadline(cos *ocv1.ClusterObjectSet, status metav1.ConditionSta
 	})
 }
 
-func setRetryableErrorConditions(cos *ocv1.ClusterObjectSet, message string, isDeadlineExceeded bool) {
-	setReadyWithDeadline(cos, metav1.ConditionFalse, ocv1.ClusterObjectSetReasonRetryableError, message, isDeadlineExceeded)
-}
-
 func markAsReady(cos *ocv1.ClusterObjectSet, reason, message string) bool {
 	return meta.SetStatusCondition(&cos.Status.Conditions, metav1.Condition{
 		Type:               ocv1.ClusterObjectSetTypeReady,