From d1d0a09c875fe89cb09753d5a11ed9607bb8c940 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Mon, 15 Jun 2026 16:40:10 +0000
Subject: [PATCH] fix(file-based): classify CSV encoding errors as config_error
 to prevent unnecessary retries

The AirbyteTracedException raised for UnicodeError in csv_parser.py
was missing failure_type, defaulting to system_error (retriable).
This caused up to 5 unnecessary retry attempts for encoding mismatch
errors that will never succeed without a config change.

- Add failure_type=FailureType.config_error
- Add internal_message with file URI, encoding, and original error
- Pass exception parameter and chain with 'from e'
- Update test to verify all new exception attributes

Co-Authored-By: bot_apk <apk@cognition.ai>
---
 airbyte_cdk/sources/file_based/file_types/csv_parser.py  | 9 ++++++---
 .../sources/file_based/file_types/test_csv_parser.py     | 9 ++++++---
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/airbyte_cdk/sources/file_based/file_types/csv_parser.py b/airbyte_cdk/sources/file_based/file_types/csv_parser.py
index b8c720642a..dfb2c9bfea 100644
--- a/airbyte_cdk/sources/file_based/file_types/csv_parser.py
+++ b/airbyte_cdk/sources/file_based/file_types/csv_parser.py
@@ -73,10 +73,13 @@ def read_data(
                     headers, raw_headers = self._read_and_validate_headers(
                         fp, config_format, dialect_name
                     )
-                except UnicodeError:
+                except UnicodeError as e:
                     raise AirbyteTracedException(
-                        message=f"{FileBasedSourceError.ENCODING_ERROR.value} Expected encoding: {config_format.encoding}",
-                    )
+                        message=f"{FileBasedSourceError.ENCODING_ERROR.value} Expected encoding: {config_format.encoding}.",
+                        internal_message=f"UnicodeError reading file {file.uri} with encoding {config_format.encoding}: {e}",
+                        failure_type=FailureType.config_error,
+                        exception=e,
+                    ) from e
 
                 rows_to_skip = (
                     config_format.skip_rows_before_header
diff --git a/unit_tests/sources/file_based/file_types/test_csv_parser.py b/unit_tests/sources/file_based/file_types/test_csv_parser.py
index f12f6613e8..2e5a38286f 100644
--- a/unit_tests/sources/file_based/file_types/test_csv_parser.py
+++ b/unit_tests/sources/file_based/file_types/test_csv_parser.py
@@ -648,15 +648,18 @@ def test_read_data_with_encoding_error(self) -> None:
         self._stream_reader.open_file.return_value = (
             CsvFileBuilder().with_data(["something"]).build()
         )
-        self._csv_reader._read_and_validate_headers = Mock(
-            side_effect=UnicodeDecodeError("encoding", b"", 0, 1, "reason")
-        )
+        unicode_error = UnicodeDecodeError("utf-8", b"\x9d", 0, 1, "invalid start byte")
+        self._csv_reader._read_and_validate_headers = Mock(side_effect=unicode_error)
 
         with pytest.raises(AirbyteTracedException) as ate:
             data_generator = self._read_data()
             assert len(list(data_generator)) == 0
 
         assert "encoding" in ate.value.message
+        assert ate.value.failure_type == FailureType.config_error
+        assert self._file.uri in ate.value.internal_message
+        assert "utf-8" in ate.value.internal_message
+        assert ate.value.__cause__ is unicode_error
         assert self._csv_reader._read_and_validate_headers.called
 
     def _read_data(self) -> Generator[Dict[str, str], None, None]: