(backend) add metadata collection of VAD, connection and chat events

Introduce MetadataCollector and MetadataCollectorService classes to
centralize the collection and storage of user connections, VAD events,
and chat messages. This creates a structured foundation for future speaker
assignment logic based on voice activity detection. Add tests for this new
feature.
This commit is contained in:
leo
2026-04-07 12:11:32 +02:00
committed by aleb_the_flash
parent aaf21e97e8
commit 8507cdd2b6
13 changed files with 674 additions and 4 deletions
+13
View File
@@ -45,6 +45,10 @@ from core.recording.event.exceptions import (
)
from core.recording.event.notification import notification_service
from core.recording.event.parsers import get_parser
from core.recording.services.metadata_collector import (
MetadataCollectorException,
MetadataCollectorService,
)
from core.recording.worker.exceptions import (
RecordingStartError,
RecordingStopError,
@@ -338,6 +342,15 @@ class RoomViewSet(
status=drf_status.HTTP_500_INTERNAL_SERVER_ERROR,
)
if settings.METADATA_COLLECTOR_ENABLED and (
recording.mode == models.RecordingModeChoices.TRANSCRIPT
or recording.options.get("transcribe", False)
):
try:
MetadataCollectorService().start(recording)
except MetadataCollectorException:
logger.warning("Failed to start MetadataCollectorService")
return drf_response.Response(
{"message": f"Recording successfully started for room {room.slug}"},
status=drf_status.HTTP_201_CREATED,
@@ -0,0 +1,91 @@
"""Meeting metadata collection service."""
from logging import getLogger
from django.conf import settings
from asgiref.sync import async_to_sync, sync_to_async
from livekit.protocol.agent_dispatch import (
CreateAgentDispatchRequest,
)
from core import utils
from core.models import Recording
logger = getLogger(__name__)
class MetadataCollectorException(Exception):
"""Generic exception in the metadata collector."""
class MetadataCollectorService:
"""Service for dispatching and managing the metadata collector agent."""
@async_to_sync
async def start(self, recording: Recording):
"""Explicitly dispatch the metadata collector agent to a room."""
lkapi = utils.create_livekit_client()
room_id = str(recording.room.id)
try:
response = await lkapi.agent_dispatch.create_dispatch(
CreateAgentDispatchRequest(
agent_name=settings.METADATA_COLLECTOR_AGENT_NAME,
room=room_id,
metadata=str(recording.id),
)
)
except Exception as e:
logger.exception(
"Failed to create metadata collector agent for room %s", room_id
)
raise MetadataCollectorException(
"Failed to create metadata collector agent"
) from e
finally:
await lkapi.aclose()
dispatch_id = getattr(response, "id", None)
if not dispatch_id:
logger.error("LiveKit response missing dispatch ID for room %s", room_id)
raise MetadataCollectorException(
f"LiveKit did not return a dispatch_id for room {room_id}"
)
recording.options["metadata_collector_dispatch_id"] = dispatch_id
await sync_to_async(recording.save)(update_fields=["options"])
return dispatch_id
@async_to_sync
async def stop(self, recording: Recording):
"""Stop and delete the agent dispatch associated to the room."""
room_id = str(recording.room.id)
dispatch_id = recording.options.get("metadata_collector_dispatch_id")
lkapi = utils.create_livekit_client()
try:
if not dispatch_id:
logger.warning(
"No metadata collector dispatch ID stored for room %s", room_id
)
return None
await lkapi.agent_dispatch.delete_dispatch(
dispatch_id=str(dispatch_id), room_name=room_id
)
except Exception as e:
logger.exception(
"Failed to stop metadata collector agent dispatch for room %s",
room_id,
)
raise MetadataCollectorException(
f"Failed to stop metadata collector agent for room {room_id}"
) from e
finally:
await lkapi.aclose()
@@ -7,6 +7,7 @@ from logging import getLogger
from livekit import api
from core import models, utils
from core.models import Recording
logger = getLogger(__name__)
@@ -19,7 +20,7 @@ class RecordingEventsService:
"""Handles recording-related LiveKit webhook events."""
@staticmethod
def handle_update(recording, egress_status):
def handle_update(recording: Recording, egress_status):
"""Handle egress status updates and sync recording state to room metadata."""
room_name = str(recording.room.id)
@@ -40,7 +41,7 @@ class RecordingEventsService:
logger.exception("Failed to update room's metadata: %s", e)
@staticmethod
def handle_limit_reached(recording):
def handle_limit_reached(recording: Recording):
"""Stop recording and notify participants when limit is reached."""
recording.status = models.RecordingStatusChoices.STOPPED
+13 -1
View File
@@ -12,6 +12,10 @@ from django.conf import settings
from livekit import api
from core import models, utils
from core.recording.services.metadata_collector import (
MetadataCollectorException,
MetadataCollectorService,
)
from core.recording.services.recording_events import (
RecordingEventsError,
RecordingEventsService,
@@ -158,7 +162,7 @@ class LiveKitEventsService:
"""Handle 'egress_ended' event."""
try:
recording = models.Recording.objects.get(
recording = models.Recording.objects.select_related("room").get(
worker_id=data.egress_info.egress_id
)
except models.Recording.DoesNotExist as err:
@@ -174,6 +178,14 @@ class LiveKitEventsService:
except utils.MetadataUpdateException as e:
logger.exception("Failed to update room's metadata: %s", e)
if settings.METADATA_COLLECTOR_ENABLED and recording.options.get(
"metadata_collector_dispatch_id"
):
try:
MetadataCollectorService().stop(recording)
except MetadataCollectorException:
logger.warning("Failed to stop the MetadataCollectorService")
if (
data.egress_info.status == api.EgressStatus.EGRESS_LIMIT_REACHED
and recording.status == models.RecordingStatusChoices.ACTIVE
@@ -277,6 +277,7 @@ def test_start_recording_options_transcribe_valid_true(
):
"""Should accept transcribe with any valid pydantic true values."""
settings.RECORDING_ENABLE = True
settings.METADATA_COLLECTOR_ENABLED = False
room = RoomFactory()
user = UserFactory()
room.accesses.create(user=user, role="owner")
@@ -487,6 +488,93 @@ def test_start_recording_options_original_mode_omitted(
assert recording.options == {}
def test_start_recording_calls_metadata_collector_start(
settings, mock_worker_service_factory, mock_worker_manager
):
"""Should call MetadataCollectorService.start when conditions are met."""
settings.RECORDING_ENABLE = True
settings.METADATA_COLLECTOR_ENABLED = True
room = RoomFactory()
user = UserFactory()
room.accesses.create(user=user, role="owner")
client = APIClient()
client.force_login(user)
with mock.patch(
"core.api.viewsets.MetadataCollectorService"
) as mock_collector_class:
mock_collector = mock.Mock()
mock_collector_class.return_value = mock_collector
response = client.post(
f"/api/v1.0/rooms/{room.id}/start-recording/",
{
"mode": "screen_recording",
"options": {"transcribe": True, "collect_metadata": True},
},
format="json",
)
assert response.status_code == 201
recording = Recording.objects.get(room=room)
mock_collector.start.assert_called_once_with(recording)
@pytest.mark.parametrize(
"metadata_enabled,options",
[
# Metadata collector disabled, regardless of transcribe option
(False, {"transcribe": True}),
(False, {"transcribe": False}),
(False, None),
# Metadata collector enabled, but transcribe is False or missing
(True, {"transcribe": False}),
(True, None),
# Metadata collector enabled, transcribe True, but collect_metadata explicitly False
(True, {"transcribe": True, "collect_metadata": False}),
],
)
def test_start_recording_does_not_call_metadata_collector_start_when_conditions_not_met(
settings,
mock_worker_service_factory,
mock_worker_manager,
metadata_enabled,
options,
):
"""Should not call MetadataCollectorService.start when conditions are not met."""
settings.RECORDING_ENABLE = True
settings.METADATA_COLLECTOR_ENABLED = metadata_enabled
room = RoomFactory()
user = UserFactory()
room.accesses.create(user=user, role="owner")
client = APIClient()
client.force_login(user)
payload = {"mode": "screen_recording"}
if options is not None:
payload["options"] = options
with mock.patch(
"core.api.viewsets.MetadataCollectorService"
) as mock_collector_class:
mock_collector = mock.Mock()
mock_collector_class.return_value = mock_collector
response = client.post(
f"/api/v1.0/rooms/{room.id}/start-recording/",
payload,
format="json",
)
assert response.status_code == 201
mock_collector.start.assert_not_called()
@pytest.mark.parametrize("value", ["invalid_mode", "foo", 123, "SCREEN_RECORDING"])
def test_start_recording_options_original_mode_invalid(settings, value):
"""Should reject invalid recording mode values for original_mode."""
@@ -269,6 +269,63 @@ def test_handle_egress_ended_recording_not_limit_reached(
assert recording.status == "stopped"
@mock.patch("core.services.livekit_events.MetadataCollectorService")
@mock.patch("core.utils.update_room_metadata")
def test_handle_egress_ended_calls_metadata_collector_stop_when_conditions_are_met(
mock_update_room_metadata, mock_collector_class, service, settings
):
"""Should call MetadataCollectorService.stop when it exists."""
settings.METADATA_COLLECTOR_ENABLED = True
recording = RecordingFactory(
worker_id="worker-1",
status="active",
options={"metadata_collector_dispatch_id": "dispatch-123"},
)
mock_data = mock.MagicMock()
mock_data.egress_info.egress_id = recording.worker_id
mock_data.egress_info.status = EgressStatus.EGRESS_COMPLETE
mock_collector = mock.Mock()
mock_collector_class.return_value = mock_collector
service._handle_egress_ended(mock_data)
mock_collector.stop.assert_called_once_with(recording)
@pytest.mark.parametrize(
"metadata_enabled,options",
[
(True, {}),
(False, {}),
],
)
@mock.patch("core.services.livekit_events.MetadataCollectorService")
@mock.patch("core.utils.update_room_metadata")
def test_handle_egress_ended_does_not_call_metadata_collector_stop_when_conditions_not_met(
_, mock_collector_class, metadata_enabled, options, service, settings
): # pylint: disable=too-many-arguments,too-many-positional-arguments
"""Should not call MetadataCollectorService.stop when it does not exist."""
settings.METADATA_COLLECTOR_ENABLED = metadata_enabled
recording = RecordingFactory(
worker_id="worker-1",
status="active",
options=options,
)
mock_data = mock.MagicMock()
mock_data.egress_info.egress_id = recording.worker_id
mock_data.egress_info.status = EgressStatus.EGRESS_COMPLETE
mock_collector = mock.Mock()
mock_collector_class.return_value = mock_collector
service._handle_egress_ended(mock_data)
mock_collector.stop.assert_not_called()
@mock.patch.object(LobbyService, "clear_room_cache")
@mock.patch.object(TelephonyService, "delete_dispatch_rule")
def test_handle_room_finished_clears_cache_and_deletes_dispatch_rule(
+10
View File
@@ -808,6 +808,16 @@ class Base(Configuration):
environ_prefix=None,
)
# Metadata collector settings
METADATA_COLLECTOR_ENABLED = values.BooleanValue(
False, environ_name="METADATA_COLLECTOR_ENABLED", environ_prefix=None
)
METADATA_COLLECTOR_AGENT_NAME = values.Value(
"metadata-collector",
environ_name="METADATA_COLLECTOR_AGENT_NAME",
environ_prefix=None,
)
# External Applications
APPLICATION_CLIENT_ID_LENGTH = values.PositiveIntegerValue(
40,