(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
@@ -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(