fix: improve ERROR_READING_FILE message and raise AirbyteTracedException with system_error

Replace misleading credential-focused error message with accurate
'File read failed during availability check.' message. Raise
AirbyteTracedException with FailureType.system_error instead of
CheckAvailabilityError, since the error is not necessarily caused
by invalid credentials.

Resolves airbytehq/airbyte-internal-issues#16082

Co-Authored-By: bot_apk <apk@cognition.ai>

Author: devin-ai-integration[bot]

airbyte_cdk/sources/file_based/availability_strategy/default_file_based_availability_strategy.py

@@ -9,6 +9,7 @@
 from typing import TYPE_CHECKING, Optional, Tuple
 
 from airbyte_cdk import AirbyteTracedException
+from airbyte_cdk.models import FailureType
 from airbyte_cdk.sources import Source
 from airbyte_cdk.sources.file_based.availability_strategy import (
     AbstractFileBasedAvailabilityStrategy,
@@ -133,8 +134,10 @@ def _check_parse_record(
         except AirbyteTracedException as ate:
             raise ate
         except Exception as exc:
-            raise CheckAvailabilityError(
-                FileBasedSourceError.ERROR_READING_FILE, stream=stream.name, file=file.uri
+            raise AirbyteTracedException(
+                message=FileBasedSourceError.ERROR_READING_FILE.value,
+                internal_message=f"Error reading file {file.uri} in stream {stream.name}: {exc}",
+                failure_type=FailureType.system_error,
             ) from exc
 
         schema = stream.catalog_schema or stream.config.input_schema

airbyte_cdk/sources/file_based/exceptions.py

@@ -17,7 +17,7 @@ class FileBasedSourceError(Enum):
     ERROR_CASTING_VALUE_UNRECOGNIZED_TYPE = "Could not cast the value to the expected type because the type is not recognized. Valid types are null, array, boolean, integer, number, object, and string."
     ERROR_DECODING_VALUE = "Expected a JSON-decodeable value but could not decode record."
     ERROR_LISTING_FILES = "Error listing files. Please check the credentials provided in the config and verify that they provide permission to list files."
-    ERROR_READING_FILE = "Error opening file. Please check the credentials provided in the config and verify that they provide permission to read files."
+    ERROR_READING_FILE = "File read failed during availability check."
     ERROR_PARSING_RECORD = "Error parsing record. This could be due to a mismatch between the config's file type and the actual file type, or because the file or record is not parseable."
     ERROR_PARSING_USER_PROVIDED_SCHEMA = (
         "The provided schema could not be transformed into valid JSON Schema."

unit_tests/sources/file_based/scenarios/check_scenarios.py

@@ -3,6 +3,7 @@
 #
 
 from airbyte_cdk.sources.file_based.exceptions import FileBasedSourceError
+from airbyte_cdk.utils.traced_exception import AirbyteTracedException
 from unit_tests.sources.file_based.helpers import (
     FailingSchemaValidationPolicy,
     TestErrorListMatchingFilesInMemoryFilesStreamReader,
@@ -158,7 +159,7 @@
             )
         )
     )
-    .set_expected_check_error(None, FileBasedSourceError.ERROR_READING_FILE.value)
+    .set_expected_check_error(AirbyteTracedException, FileBasedSourceError.ERROR_READING_FILE.value)
 ).build()
 
 
@@ -222,5 +223,5 @@
             ],
         }
     )
-    .set_expected_check_error(None, FileBasedSourceError.ERROR_READING_FILE.value)
+    .set_expected_check_error(AirbyteTracedException, FileBasedSourceError.ERROR_READING_FILE.value)
 ).build()