address comments

Author: cameledev

src/backend/core/api/viewsets.py

@@ -363,7 +363,7 @@ def start_room_recording(self, request, pk=None):  # pylint: disable=unused-argu
         ):
             try:
                 MetadataCollectorService().start(recording)
-                logger.info("Started MetadataCollectorService")
+                logger.debug("Started MetadataCollectorService")
             except MetadataCollectorException:
                 logger.warning("Failed to start MetadataCollectorService")
 

src/backend/core/recording/event/notification.py

@@ -204,7 +204,7 @@ def _notify_summary_service(recording):
             .first()
         )
 
-        output_folder = settings.METADATA_COLLECTOR_AWS_S3_OUTPUT_FOLDER
+        output_folder = settings.METADATA_COLLECTOR_OUTPUT_FOLDER
         metadata_filename = f"{output_folder}/{recording.id}-metadata.json"
 
         if not owner_access:

src/backend/meet/settings.py

@@ -817,9 +817,9 @@ class Base(Configuration):
         environ_name="METADATA_COLLECTOR_AGENT_NAME",
         environ_prefix=None,
     )
-    METADATA_COLLECTOR_AWS_S3_OUTPUT_FOLDER = values.Value(
+    METADATA_COLLECTOR_OUTPUT_FOLDER = values.Value(
         "metadata",
-        environ_name="METADATA_COLLECTOR_AWS_S3_OUTPUT_FOLDER",
+        environ_name="METADATA_COLLECTOR_OUTPUT_FOLDER",
         environ_prefix=None,
     )
 

src/summary/summary/core/celery_worker.py

@@ -296,14 +296,19 @@ def process_audio_transcribe_summarize_v2(
                 recording_start_dt,
                 recording_end_dt,
             )
-            transcription = assignment_result.apply(
-                {
-                    "segments": transcription.segments,
-                    "word_segments": transcription.word_segments,
-                }
+            transcription = assignment_result.rewrite_diarization(
+                transcription = assignment_result.apply(transcription.model_dump())
             )
         except FileServiceException as exc:
-            logger.error("Error reading metadata: %s. Skipping speaker assignment", exc)
+            logger.error(
+                "Error reading metadata for task %s; skipping speaker assignment. Error: %s", 
+                task_id, exc
+                )
+        except Exception as exc:  # noqa: BLE001
+            logger.exception(
+                "assign_speakers failed for task %s; skipping speaker assignment. Error: %s",
+                task_id, exc
+            )
     else:
         logger.debug("Skipping assign_speakers")
 

src/summary/summary/core/file_service.py

@@ -244,6 +244,8 @@ def read_json(self, object_name: str) -> dict:
             raise FileServiceException(
                 "Unexpected error while reading JSON object."
             ) from e
+        except (json.JSONDecodeError, UnicodeDecodeError) as e:
+            raise FileServiceException("Invalid JSON content.") from e
         finally:
             if response:
                 response.close()

src/summary/summary/core/user_assign.py

@@ -46,7 +46,7 @@ class AssignmentResult:
     assignments: list[SpeakerAssignment] = field(default_factory=list)
     unassigned_speakers: list[str] = field(default_factory=list)
 
-    def apply(self, diarization: dict[str, Any]) -> dict[str, Any]:
+    def rewrite_diarization(self, diarization: dict[str, Any]) -> dict[str, Any]:
         """Return a copy of diarization with speaker labels replaced by names.
 
         Replaces `"speaker"` fields in segments and word_segments with the

src/summary/tests/unit/test_user_assign.py

@@ -492,7 +492,7 @@ def test_replaces_speakers_in_segments_and_words(self):
                 SpeakerAssignment("SPEAKER_01", "id-b", "Bob", 0.8),
             ],
         )
-        result = assignment.apply(diarization)
+        result = assignment.rewrite_diarization(diarization)
 
         assert result["segments"][0]["speaker"] == "Alice"
         assert result["segments"][0]["words"][0]["speaker"] == "Alice"
@@ -513,7 +513,7 @@ def test_unassigned_speakers_unchanged(self):
             ],
             unassigned_speakers=["SPEAKER_02"],
         )
-        result = assignment.apply(diarization)
+        result = assignment.rewrite_diarization(diarization)
         assert result["segments"][0]["speaker"] == "SPEAKER_02"
 
     def test_preserves_extra_keys(self):
@@ -523,6 +523,6 @@ def test_preserves_extra_keys(self):
             "language": "en",
             "custom_field": 42,
         }
-        result = AssignmentResult().apply(diarization)
+        result = AssignmentResult().rewrite_diarization(diarization)
         assert result["language"] == "en"
         assert result["custom_field"] == 42