Convert some remaining error logs into errors with stack traces to im…

…prove error reporting (#348)

src/operator/controllers/intents_controller.go

@@ -262,6 +262,7 @@ func (r *IntentsReconciler) getIntentsToProtectedService(protectedService *otter
 	)
 	if err != nil {
 		logrus.Errorf("Failed to list client intents for client %s: %v", fullServerName, err)
+		// Intentionally no return - we are not able to return errors in this flow currently
 	}
 
 	intentsToReconcile = append(intentsToReconcile, intentsToServer.Items...)

src/operator/controllers/kafkaserverconfig_controller.go

@@ -147,6 +147,7 @@ func (r *KafkaServerConfigReconciler) getKSCsForProtectedService(ctx context.Con
 	)
 	if err != nil {
 		logrus.Errorf("Failed to list KSCs for server %s: %v", protectedService.Spec.Name, err)
+		// Intentionally no return - we are not able to return errors in this flow currently
 	}
 
 	kscsToReconcile = append(kscsToReconcile, kafkaServerConfigs.Items...)

src/operator/controllers/pod_reconcilers/pods.go

@@ -223,8 +223,7 @@ func (p *PodWatcher) addOtterizePodLabels(ctx context.Context, req ctrl.Request,
 	if hasUpdates {
 		err = p.Patch(ctx, updatedPod, client.MergeFrom(&pod))
 		if err != nil {
-			logrus.Errorf("Failed updating Otterize labels for pod %s in namespace %s", pod.Name, pod.Namespace)
-			return errors.Wrap(err)
+			return errors.Errorf("failed updating Otterize labels for pod %s in namespace %s: %w", pod.Name, pod.Namespace, err)
 		}
 	}
 	return nil

src/shared/otterizecloud/otterizecloudclient/cloud_client.go

@@ -4,9 +4,9 @@ import (
 	"context"
 	"crypto/tls"
 	"crypto/x509"
-	"errors"
 	"fmt"
 	"github.com/Khan/genqlient/graphql"
+	"github.com/otterize/intents-operator/src/shared/errors"
 	"github.com/otterize/intents-operator/src/shared/telemetries/componentinfo"
 	"github.com/sirupsen/logrus"
 	"github.com/spf13/viper"
@@ -26,10 +26,10 @@ func NewClient(ctx context.Context) (graphql.Client, bool, error) {
 		return nil, false, nil
 	}
 	if clientID == "" {
-		return nil, true, errors.New("missing cloud integration client ID")
+		return nil, false, errors.New("missing cloud integration client ID")
 	}
 	if secret == "" {
-		return nil, true, errors.New("missing cloud integration secret")
+		return nil, false, errors.New("missing cloud integration secret")
 	}
 
 	componentinfo.SetGlobalCloudClientId(clientID)
@@ -49,12 +49,11 @@ func NewClient(ctx context.Context) (graphql.Client, bool, error) {
 		logrus.Infof("Loading root CA from cert PEM file at '%s'", path)
 		cert, err := os.ReadFile(path)
 		if err != nil {
-			logrus.Errorf("Error loading cert PEM file at '%s', trying to continue without it: %s", path, err)
-			continue
+			return nil, false, errors.Errorf("error loading cert PEM file at '%s', trying to continue without it: %w", path, err)
 		}
 
 		if ok := rootCAs.AppendCertsFromPEM(cert); !ok {
-			logrus.Warnf("Failed appending cert PEM file at '%s', trying to continue without it", path)
+			return nil, false, errors.Errorf("Failed appending cert PEM file at '%s', trying to continue without it", path)
 		}
 	}
 

src/shared/telemetries/basicbatch/batcher.go

@@ -51,7 +51,11 @@ func (b *Batcher[T]) runForever() {
 	defer func() {
 		r := recover()
 		if r != nil {
-			logrus.Error("recovered from panic in batcher")
+			logger := logrus.WithField("panic", r)
+			if rErr, ok := r.(error); ok {
+				logger = logger.WithError(rErr)
+			}
+			logger.Error("recovered from panic in batcher: %r")
 		}
 	}()
 	defer errorreporter.AutoNotify()

src/shared/telemetries/telemetrysender/sender.go

@@ -7,7 +7,6 @@ import (
 	"github.com/otterize/intents-operator/src/shared/telemetries/basicbatch"
 	"github.com/otterize/intents-operator/src/shared/telemetries/telemetriesconfig"
 	"github.com/otterize/intents-operator/src/shared/telemetries/telemetriesgql"
-	"github.com/sirupsen/logrus"
 	"github.com/spf13/viper"
 	"net/http"
 	"time"
@@ -34,7 +33,7 @@ func newGqlClient() graphql.Client {
 func batchSendTelemetries(ctx context.Context, telemetriesClient graphql.Client, telemetries []telemetriesgql.TelemetryInput) error {
 	_, err := telemetriesgql.SendTelemetries(ctx, telemetriesClient, telemetries)
 	if err != nil {
-		logrus.Errorf("failed batch sending telemetries: %s", err)
+		return errors.Errorf("failed batch sending telemetries: %w", err)
 	}
 	return nil
 }