feat: OPTIC-1749: Only send 5XX API Exceptions to Sentry (#7217)

Co-authored-by: robot-ci-heartex <[email protected]>

Author: mcanu

label_studio/core/label_config.py

@@ -14,10 +14,8 @@
 import xmljson
 from django.conf import settings
 from label_studio_sdk._extensions.label_studio_tools.core import label_config
+from rest_framework.exceptions import ValidationError
 
-from label_studio.core.utils.exceptions import (
-    LabelStudioValidationErrorSentryIgnored,
-)
 from label_studio.core.utils.io import find_file
 
 logger = logging.getLogger(__name__)
@@ -110,7 +108,7 @@ def validate_label_config(config_string: Union[str, None]) -> None:
         config, cleaned_config_string = parse_config_to_json(config_string)
         jsonschema.validate(config, _LABEL_CONFIG_SCHEMA_DATA)
     except (etree.ParseError, ValueError) as exc:
-        raise LabelStudioValidationErrorSentryIgnored(str(exc))
+        raise ValidationError(str(exc))
     except jsonschema.exceptions.ValidationError as exc:
         # jsonschema4 validation error now includes all errors from "anyOf" subschemas
         # check https://python-jsonschema.readthedocs.io/en/latest/errors/#jsonschema.exceptions.ValidationError.context
@@ -119,20 +117,20 @@ def validate_label_config(config_string: Union[str, None]) -> None:
         error_message = 'Validation failed on {}: {}'.format(
             '/'.join(map(str, exc.path)), error_message.replace('@', '')
         )
-        raise LabelStudioValidationErrorSentryIgnored(error_message)
+        raise ValidationError(error_message)
 
     # unique names in config # FIXME: 'name =' (with spaces) won't work
     all_names = re.findall(r'name="([^"]*)"', cleaned_config_string)
     if len(set(all_names)) != len(all_names):
-        raise LabelStudioValidationErrorSentryIgnored('Label config contains non-unique names')
+        raise ValidationError('Label config contains non-unique names')
 
     # toName points to existent name
     names = set(all_names)
     toNames = re.findall(r'toName="([^"]*)"', cleaned_config_string)
     for toName_ in toNames:
         for toName in toName_.split(','):
             if toName not in names:
-                raise LabelStudioValidationErrorSentryIgnored(f'toName="{toName}" not found in names: {sorted(names)}')
+                raise ValidationError(f'toName="{toName}" not found in names: {sorted(names)}')
 
 
 def extract_data_types(label_config):

label_studio/core/settings/base.py

@@ -388,16 +388,14 @@
 FRONTEND_SENTRY_DSN = get_env('FRONTEND_SENTRY_DSN', None)
 FRONTEND_SENTRY_RATE = get_env('FRONTEND_SENTRY_RATE', 0.01)
 FRONTEND_SENTRY_ENVIRONMENT = get_env('FRONTEND_SENTRY_ENVIRONMENT', 'stage.opensource')
+
+# Exceptions that should not be logged to Sentry and aren't children of drf's APIException class
 SENTRY_IGNORED_EXCEPTIONS = [
     'Http404',
-    'NotAuthenticated',
-    'AuthenticationFailed',
-    'NotFound',
     'XMLSyntaxError',
     'FileUpload.DoesNotExist',
     'Forbidden',
     'KeyboardInterrupt',
-    'PermissionDenied',
 ]
 
 ROOT_URLCONF = 'core.urls'

label_studio/core/utils/common.py

@@ -52,7 +52,7 @@
 from packaging.version import parse as parse_version
 from pyboxen import boxen
 from rest_framework import status
-from rest_framework.exceptions import ErrorDetail
+from rest_framework.exceptions import APIException, ErrorDetail
 from rest_framework.views import Response, exception_handler
 
 import label_studio
@@ -89,7 +89,17 @@ def custom_exception_handler(exc, context):
     :return: response with error desc
     """
     exception_id = uuid.uuid4()
-    logger.error('{} {}'.format(exception_id, exc), exc_info=True)
+
+    sentry_skip = False
+    if isinstance(exc, APIException) and exc.status_code < 500:
+        # Skipping Sentry for non-500 unhandled exceptions
+        sentry_skip = True
+
+    logger.error(
+        '{} {}'.format(exception_id, exc),
+        exc_info=True,
+        extra={'sentry_skip': sentry_skip, 'exception_id': exception_id},
+    )
 
     exc = _override_exceptions(exc)
 
@@ -134,7 +144,9 @@ def custom_exception_handler(exc, context):
         if not settings.DEBUG_MODAL_EXCEPTIONS:
             exc_tb = None
         response_data['exc_info'] = exc_tb
+        # Thrown by sdk when label config is invalid
         if isinstance(exc, LabelStudioXMLSyntaxErrorSentryIgnored):
+            response_data['status_code'] = status.HTTP_400_BAD_REQUEST
             response = Response(status=status.HTTP_400_BAD_REQUEST, data=response_data)
         else:
             response = Response(status=status.HTTP_500_INTERNAL_SERVER_ERROR, data=response_data)

label_studio/core/utils/exceptions.py

@@ -1,7 +1,7 @@
 """This file and its contents are licensed under the Apache License 2.0. Please see the included NOTICE for copyright information and LICENSE for a copy of the license.
 """
 from rest_framework import status
-from rest_framework.exceptions import APIException, ValidationError
+from rest_framework.exceptions import APIException
 
 
 class LabelStudioError(Exception):
@@ -27,22 +27,6 @@ class ProjectExistException(LabelStudioAPIException):
     default_detail = 'Project with the same title already exists'
 
 
-class LabelStudioErrorSentryIgnored(Exception):
-    pass
-
-
-class LabelStudioAPIExceptionSentryIgnored(LabelStudioAPIException):
-    pass
-
-
-class LabelStudioValidationErrorSentryIgnored(ValidationError):
-    pass
-
-
-class LabelStudioXMLSyntaxErrorSentryIgnored(Exception):
-    pass
-
-
 class InvalidUploadUrlError(LabelStudioAPIException):
     default_detail = (
         'The provided URL was not valid. URLs must begin with http:// or https://, and cannot be local IPs.'

label_studio/data_import/api.py

@@ -14,7 +14,6 @@
 from core.permissions import ViewClassPermission, all_permissions
 from core.redis import start_job_async_or_sync
 from core.utils.common import retry_database_locked, timeit
-from core.utils.exceptions import LabelStudioValidationErrorSentryIgnored
 from core.utils.params import bool_from_request, list_of_strings_from_request
 from csp.decorators import csp
 from django.conf import settings
@@ -413,7 +412,7 @@ def create(self, request, *args, **kwargs):
         predictions = []
         for item in self.request.data:
             if item.get('task') not in tasks_ids:
-                raise LabelStudioValidationErrorSentryIgnored(
+                raise ValidationError(
                     f'{item} contains invalid "task" field: corresponding task ID couldn\'t be retrieved '
                     f'from project {project} tasks'
                 )

label_studio/projects/models.py

@@ -26,7 +26,6 @@
     merge_labels_counters,
 )
 from core.utils.db import fast_first
-from core.utils.exceptions import LabelStudioValidationErrorSentryIgnored
 from django.conf import settings
 from django.core.validators import MaxLengthValidator, MinLengthValidator
 from django.db import models, transaction
@@ -46,6 +45,7 @@
 )
 from projects.functions.utils import make_queryset_from_iterable
 from projects.signals import ProjectSignals
+from rest_framework.exceptions import ValidationError
 from tasks.models import (
     Annotation,
     AnnotationDraft,
@@ -546,7 +546,7 @@ def validate_config(self, config_string, strict=False):
             fields_from_data.discard(settings.DATA_UNDEFINED_NAME)
             if fields_from_data and not fields_from_config.issubset(fields_from_data):
                 different_fields = list(fields_from_config.difference(fields_from_data))
-                raise LabelStudioValidationErrorSentryIgnored(
+                raise ValidationError(
                     f'These fields are not present in the data: {",".join(different_fields)}'
                 )"""
 
@@ -585,7 +585,7 @@ def validate_config(self, config_string, strict=False):
                     )
             if len(diff_str) > 0:
                 diff_str = '\n'.join(diff_str)
-                raise LabelStudioValidationErrorSentryIgnored(
+                raise ValidationError(
                     f'Created annotations are incompatible with provided labeling schema, we found:\n{diff_str}'
                 )
 
@@ -611,7 +611,7 @@ def display_count(count: int, type: str) -> Optional[str]:
                 )
                 and not check_control_in_config_by_regex(config_string, control_tag_from_data)
             ):
-                raise LabelStudioValidationErrorSentryIgnored(
+                raise ValidationError(
                     f'There are {sum(labels_from_data.values(), 0)} annotation(s) created with tag '
                     f'"{control_tag_from_data}", you can\'t remove it'
                 )
@@ -651,7 +651,7 @@ def display_count(count: int, type: str) -> Optional[str]:
                     )
                 ):
                     # raise error if labels not dynamic and not in regex rules
-                    raise LabelStudioValidationErrorSentryIgnored(
+                    raise ValidationError(
                         f'These labels still exist in annotations or drafts:\n{diff_str}'
                         f'Please add labels to tag with name="{str(control_tag_from_data)}".'
                     )