Skip to content

UN-2733 [FIX] Allow file processing to continue on cleanup related errors #1503

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chandrasekharan-zipstack merged 3 commits into from
Aug 25, 2025
Merged

UN-2733 [FIX] Allow file processing to continue on cleanup related errors #1503

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e3da9d8
UN-2733 Error handling fix for file processing related celery task
chandrasekharan-zipstack Aug 25, 2025
d919d04
Minor improvement in logging traceback too
chandrasekharan-zipstack Aug 25, 2025
9812c6a
Merge branch 'main' into UN-2733-fix-file-processing-err-handling
chandrasekharan-zipstack Aug 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 13 additions & 6 deletions backend/workflow_manager/workflow_v2/file_execution_tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -557,7 +557,7 @@ def _process_file(
result=result,
workflow_file_execution=None,
error=error_msg,
is_api=destination.is_api,
is_api=destination.is_api if destination else False,
Comment thread
chandrasekharan-zipstack marked this conversation as resolved.
destination=destination,
)
except Exception as error:
Expand All @@ -578,7 +578,7 @@ def _process_file(
result=result,
workflow_file_execution=workflow_file_execution,
error=error_msg,
is_api=destination.is_api,
is_api=destination.is_api if destination else False,
destination=destination,
)

Expand Down Expand Up @@ -1136,10 +1136,17 @@ def _build_final_result(
)

if destination:
logger.info(
f"Deleting file execution directory for file: '{file_hash.file_name}'"
)
destination.delete_file_execution_directory()
try:
logger.info(
f"Deleting file execution directory for file: '{file_hash.file_name}'"
)
destination.delete_file_execution_directory()
except Exception as cleanup_error:
logger.exception(
f"[Execution ID: {workflow_execution.id}, File Execution ID: {workflow_file_execution.id}] "
f"Failed to delete file execution directory for '{file_hash.file_name}': {cleanup_error}. "
f"This is non-critical and needs to be cleaned up later."
)

status = (
FileExecutionStageStatus.SUCCESS
Expand Down
8 changes: 5 additions & 3 deletions unstract/core/src/unstract/core/file_execution_tracker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,10 +191,12 @@ def get_cache_key(self, execution_id: str, file_execution_id: str) -> str:
def set_data(self, data: FileExecutionData, ttl_in_second: int | None = None) -> None:
data.validate()
key = self.get_cache_key(data.execution_id, data.file_execution_id)
logger.info(f"Setting file execution data for {key}: {data}")
logger.info(f"Setting file execution data for '{key}': {data}")
self.redis_client.hset(key, mapping=data.to_serializable())
ttl = ttl_in_second or self.CACHE_TTL_IN_SECOND
logger.info(f"Setting file execution data for {key} to expire in {ttl} seconds")
logger.info(
f"Setting file execution data for '{key}' to expire in '{ttl}' seconds"
)
self.redis_client.expire(key, ttl)

def exists(self, execution_id: str, file_execution_id: str) -> bool:
Expand Down Expand Up @@ -229,7 +231,7 @@ def update_stage_status(
execution_id=execution_id,
file_execution_id=file_execution_id,
)
logger.info(f"Existing data for {key}: {existing_data}")
logger.info(f"Existing data for '{key}': {existing_data}")
if not existing_data:
raise FileExecutionTrackerNotFound()

Expand Down