feat: delete recording with transcript (#547)

* Delete recording with transcript

* Delete confirmation dialog

* Use aws storage abstraction for recording deletion

* Test recording deleted with transcript

* Use get transcript storage

* Fix the test

* Add env vars for recording storage

server/reflector/db/recordings.py

@@ -53,5 +53,9 @@ class RecordingController:
         result = await get_database().fetch_one(query)
         return Recording(**result) if result else None
 
+    async def remove_by_id(self, id: str) -> None:
+        query = recordings.delete().where(recordings.c.id == id)
+        await get_database().execute(query)
+
 
 recordings_controller = RecordingController()

server/reflector/db/transcripts.py

@@ -16,11 +16,12 @@ from sqlalchemy.dialects.postgresql import TSVECTOR
 from sqlalchemy.sql import false, or_
 
 from reflector.db import get_database, metadata
+from reflector.db.recordings import recordings_controller
 from reflector.db.rooms import rooms
 from reflector.db.utils import is_postgresql
 from reflector.processors.types import Word as ProcessorWord
 from reflector.settings import settings
-from reflector.storage import get_transcripts_storage
+from reflector.storage import get_transcripts_storage, get_recordings_storage
 from reflector.utils import generate_uuid4
 from reflector.utils.webvtt import topics_to_webvtt
 
@@ -593,7 +594,39 @@ class TranscriptController:
             return
         if user_id is not None and transcript.user_id != user_id:
             return
+        if transcript.audio_location == "storage" and not transcript.audio_deleted:
+            try:
+                await get_transcripts_storage().delete_file(
+                    transcript.storage_audio_path
+                )
+            except Exception as e:
+                logger.warning(
+                    "Failed to delete transcript audio from storage",
+                    error=str(e),
+                    transcript_id=transcript.id,
+                )
         transcript.unlink()
+        if transcript.recording_id:
+            try:
+                recording = await recordings_controller.get_by_id(
+                    transcript.recording_id
+                )
+                if recording:
+                    try:
+                        await get_recordings_storage().delete_file(recording.object_key)
+                    except Exception as e:
+                        logger.warning(
+                            "Failed to delete recording object from S3",
+                            error=str(e),
+                            recording_id=transcript.recording_id,
+                        )
+                    await recordings_controller.remove_by_id(transcript.recording_id)
+            except Exception as e:
+                logger.warning(
+                    "Failed to delete recording row",
+                    error=str(e),
+                    recording_id=transcript.recording_id,
+                )
         query = transcripts.delete().where(transcripts.c.id == transcript_id)
         await get_database().execute(query)
 

server/reflector/settings.py

@@ -39,6 +39,15 @@ class Settings(BaseSettings):
     TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID: str | None = None
     TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY: str | None = None
 
+    # Recording storage
+    RECORDING_STORAGE_BACKEND: str | None = None
+
+    # Recording storage configuration for AWS
+    RECORDING_STORAGE_AWS_BUCKET_NAME: str = "recording-bucket"
+    RECORDING_STORAGE_AWS_REGION: str = "us-east-1"
+    RECORDING_STORAGE_AWS_ACCESS_KEY_ID: str | None = None
+    RECORDING_STORAGE_AWS_SECRET_ACCESS_KEY: str | None = None
+
     # Translate into the target language
     TRANSLATION_BACKEND: str = "passthrough"
     TRANSLATE_URL: str | None = None
@@ -104,7 +113,6 @@ class Settings(BaseSettings):
     WHEREBY_API_URL: str = "https://api.whereby.dev/v1"
     WHEREBY_API_KEY: str | None = None
     WHEREBY_WEBHOOK_SECRET: str | None = None
-    AWS_WHEREBY_S3_BUCKET: str | None = None
     AWS_WHEREBY_ACCESS_KEY_ID: str | None = None
     AWS_WHEREBY_ACCESS_KEY_SECRET: str | None = None
     AWS_PROCESS_RECORDING_QUEUE_URL: str | None = None

server/reflector/storage/__init__.py

@@ -1,10 +1,16 @@
 from .base import Storage  # noqa
+from reflector.settings import settings
 
 
 def get_transcripts_storage() -> Storage:
-    from reflector.settings import settings
-
     return Storage.get_instance(
         name=settings.TRANSCRIPT_STORAGE_BACKEND,
         settings_prefix="TRANSCRIPT_STORAGE_",
     )
+
+
+def get_recordings_storage() -> Storage:
+    return Storage.get_instance(
+        name=settings.RECORDING_STORAGE_BACKEND,
+        settings_prefix="RECORDING_STORAGE_",
+    )

server/reflector/whereby.py

@@ -23,7 +23,7 @@ async def create_meeting(room_name_prefix: str, end_date: datetime, room: Room):
             "type": room.recording_type,
             "destination": {
                 "provider": "s3",
-                "bucket": settings.AWS_WHEREBY_S3_BUCKET,
+                "bucket": settings.RECORDING_STORAGE_AWS_BUCKET_NAME,
                 "accessKeyId": settings.AWS_WHEREBY_ACCESS_KEY_ID,
                 "accessKeySecret": settings.AWS_WHEREBY_ACCESS_KEY_SECRET,
                 "fileFormat": "mp4",

server/reflector/worker/process.py

@@ -185,7 +185,7 @@ async def reprocess_failed_recordings():
     reprocessed_count = 0
     try:
         paginator = s3.get_paginator("list_objects_v2")
-        bucket_name = settings.AWS_WHEREBY_S3_BUCKET
+        bucket_name = settings.RECORDING_STORAGE_AWS_BUCKET_NAME
         pages = paginator.paginate(Bucket=bucket_name)
 
         for page in pages: