[client] Back up corrupted state files and present them in the debug bundle (#3227)

client/internal/statemanager/manager.go

@@ -303,20 +303,29 @@ func (m *Manager) loadStateFile(deleteCorrupt bool) (map[string]json.RawMessage,
 
 	var rawStates map[string]json.RawMessage
 	if err := json.Unmarshal(data, &rawStates); err != nil {
-		if deleteCorrupt {
-			log.Warn("State file appears to be corrupted, attempting to delete it", err)
-			if err := os.Remove(m.filePath); err != nil {
-				log.Errorf("Failed to delete corrupted state file: %v", err)
-			} else {
-				log.Info("State file deleted")
-			}
-		}
+		m.handleCorruptedState(deleteCorrupt)
 		return nil, fmt.Errorf("unmarshal states: %w", err)
 	}
 
 	return rawStates, nil
 }
 
+// handleCorruptedState creates a backup of a corrupted state file by moving it
+func (m *Manager) handleCorruptedState(deleteCorrupt bool) {
+	if !deleteCorrupt {
+		return
+	}
+	log.Warn("State file appears to be corrupted, attempting to back it up")
+
+	backupPath := fmt.Sprintf("%s.corrupted.%d", m.filePath, time.Now().UnixNano())
+	if err := os.Rename(m.filePath, backupPath); err != nil {
+		log.Errorf("Failed to backup corrupted state file: %v", err)
+		return
+	}
+
+	log.Infof("Created backup of corrupted state file at: %s", backupPath)
+}
+
 // loadSingleRawState unmarshals a raw state into a concrete state object
 func (m *Manager) loadSingleRawState(name string, rawState json.RawMessage) (State, error) {
 	stateType, ok := m.stateTypes[name]

client/server/debug.go

@@ -196,6 +196,10 @@ func (s *Server) createArchive(bundlePath *os.File, req *proto.DebugBundleReques
 		log.Errorf("Failed to add state file to debug bundle: %v", err)
 	}
 
+	if err := s.addCorruptedStateFiles(archive); err != nil {
+		log.Errorf("Failed to add corrupted state files to debug bundle: %v", err)
+	}
+
 	if s.logFile != "console" {
 		if err := s.addLogfile(req, anonymizer, archive); err != nil {
 			return fmt.Errorf("add log file: %w", err)
@@ -407,6 +411,36 @@ func (s *Server) addStateFile(req *proto.DebugBundleRequest, anonymizer *anonymi
 	return nil
 }
 
+func (s *Server) addCorruptedStateFiles(archive *zip.Writer) error {
+	pattern := statemanager.GetDefaultStatePath()
+	if pattern == "" {
+		return nil
+	}
+	pattern += "*.corrupted.*"
+	matches, err := filepath.Glob(pattern)
+	if err != nil {
+		return fmt.Errorf("find corrupted state files: %w", err)
+	}
+
+	for _, match := range matches {
+		data, err := os.ReadFile(match)
+		if err != nil {
+			log.Warnf("Failed to read corrupted state file %s: %v", match, err)
+			continue
+		}
+
+		fileName := filepath.Base(match)
+		if err := addFileToZip(archive, bytes.NewReader(data), "corrupted_states/"+fileName); err != nil {
+			log.Warnf("Failed to add corrupted state file %s to zip: %v", fileName, err)
+			continue
+		}
+
+		log.Debugf("Added corrupted state file to debug bundle: %s", fileName)
+	}
+
+	return nil
+}
+
 func (s *Server) addLogfile(req *proto.DebugBundleRequest, anonymizer *anonymize.Anonymizer, archive *zip.Writer) error {
 	logDir := filepath.Dir(s.logFile)