<@U04S8PLJWMT> in sftp-bulk destination connector ...
# ask-ai
p
@kapa.ai in sftp-bulk destination connector if files are not found during review schema check fields existing schema is removed wihtout approval.
k
I'm sorry, but the knowledge sources do not contain explicit information about the SFTP Bulk destination connector automatically removing fields from the existing schema without approval if files are not found during the schema review or check process. There are references to schema changes and the need to review and approve them during migrations or connector updates, such as in the SFTP Bulk migration guide, which instructs users to review and approve detected schema changes before saving the connection. However, there is no mention of fields being removed from the schema without user approval specifically due to missing files during schema checks. If you are experiencing this behavior, it may be a bug or an undocumented feature, and I recommend raising it with the Airbyte support or community for further investigation [SFTP Bulk Migration Guide](https://docs.airbyte.com/integrations/sources/sftp-bulk-migrations#sftp-bulk-migration-guide).
p
@kapa.ai why sync fails if file is not found
k
A message from kapa.ai
A sync fails if a file is not found because Airbyte expects the specified files to be present at the configured location during the sync process. If the file or folder is missing, the connector cannot read the data, resulting in a "FileNotFoundError" or similar error, which causes the sync to fail. This is evident from user reports where the sync fails with errors like "No such file or directory" when the file path does not exist or is not accessible by the connector. For example, in Kubernetes deployments, if the file is not mounted correctly or the path is incorrect, Airbyte cannot locate the file and the sync fails [File source cannot add File source (local filesystem) as source in airbyte (k8s deployment)](https://github.com/airbytehq/airbyte/issues/55863). This behavior is expected because Airbyte needs to access the source files to extract and sync data. If the files are missing, there is no data to process, and the sync cannot proceed.