feat: Daily+hatchet default (#846)

* feat: set Daily as default video platform

Daily.co has been battle-tested and is ready to be the default.
Whereby remains available for rooms that explicitly set it.

* feat: enforce Hatchet for all multitrack processing

Remove use_celery option from rooms - multitrack (Daily) recordings
now always use Hatchet workflows. Celery remains for single-track
(Whereby) file processing only.

- Remove use_celery column from room table
- Simplify dispatch logic to always use Hatchet for multitracks
- Update tests to mock Hatchet instead of Celery

* fix: update whereby test to patch Hatchet instead of removed Celery import

---------

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>

server/migrations/versions/3aa20b96d963_drop_use_celery_column.py

@@ -0,0 +1,35 @@
+"""drop_use_celery_column
+
+Revision ID: 3aa20b96d963
+Revises: e69f08ead8ea
+Create Date: 2026-02-05 10:12:44.065279
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "3aa20b96d963"
+down_revision: Union[str, None] = "e69f08ead8ea"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    with op.batch_alter_table("room", schema=None) as batch_op:
+        batch_op.drop_column("use_celery")
+
+
+def downgrade() -> None:
+    with op.batch_alter_table("room", schema=None) as batch_op:
+        batch_op.add_column(
+            sa.Column(
+                "use_celery",
+                sa.Boolean(),
+                server_default=sa.text("false"),
+                nullable=False,
+            )
+        )

server/reflector/db/rooms.py

@@ -57,12 +57,6 @@ rooms = sqlalchemy.Table(
         sqlalchemy.String,
         nullable=False,
     ),
-    sqlalchemy.Column(
-        "use_celery",
-        sqlalchemy.Boolean,
-        nullable=False,
-        server_default=false(),
-    ),
     sqlalchemy.Column(
         "skip_consent",
         sqlalchemy.Boolean,
@@ -97,7 +91,6 @@ class Room(BaseModel):
     ics_last_sync: datetime | None = None
     ics_last_etag: str | None = None
     platform: Platform = Field(default_factory=lambda: settings.DEFAULT_VIDEO_PLATFORM)
-    use_celery: bool = False
     skip_consent: bool = False
 
 

server/reflector/services/transcript_process.py

@@ -15,14 +15,10 @@ from hatchet_sdk.clients.rest.exceptions import ApiException, NotFoundException
 from hatchet_sdk.clients.rest.models import V1TaskStatus
 
 from reflector.db.recordings import recordings_controller
-from reflector.db.rooms import rooms_controller
 from reflector.db.transcripts import Transcript, transcripts_controller
 from reflector.hatchet.client import HatchetClientManager
 from reflector.logger import logger
 from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
-from reflector.pipelines.main_multitrack_pipeline import (
-    task_pipeline_multitrack_process,
-)
 from reflector.utils.string import NonEmptyString
 
 
@@ -181,21 +177,7 @@ async def dispatch_transcript_processing(
     Returns AsyncResult for Celery tasks, None for Hatchet workflows.
     """
     if isinstance(config, MultitrackProcessingConfig):
-        use_celery = False
+        # Multitrack processing always uses Hatchet (no Celery fallback)
-        if config.room_id:
-            room = await rooms_controller.get_by_id(config.room_id)
-            use_celery = room.use_celery if room else False
-
-        use_hatchet = not use_celery
-
-        if use_celery:
-            logger.info(
-                "Room uses legacy Celery processing",
-                room_id=config.room_id,
-                transcript_id=config.transcript_id,
-            )
-
-        if use_hatchet:
         # First check if we can replay (outside transaction since it's read-only)
         transcript = await transcripts_controller.get_by_id(config.transcript_id)
         if transcript and transcript.workflow_run_id and not force:
@@ -203,9 +185,7 @@ async def dispatch_transcript_processing(
                 transcript.workflow_run_id
             )
             if can_replay:
-                    await HatchetClientManager.replay_workflow(
+                await HatchetClientManager.replay_workflow(transcript.workflow_run_id)
-                        transcript.workflow_run_id
-                    )
                 logger.info(
                     "Replaying Hatchet workflow",
                     workflow_id=transcript.workflow_run_id,
@@ -233,9 +213,7 @@ async def dispatch_transcript_processing(
         # Force: cancel old workflow if exists
         if force and transcript and transcript.workflow_run_id:
             try:
-                    await HatchetClientManager.cancel_workflow(
+                await HatchetClientManager.cancel_workflow(transcript.workflow_run_id)
-                        transcript.workflow_run_id
-                    )
                 logger.info(
                     "Cancelled old workflow (--force)",
                     workflow_id=transcript.workflow_run_id,
@@ -245,9 +223,7 @@ async def dispatch_transcript_processing(
                     "Old workflow already deleted (--force)",
                     workflow_id=transcript.workflow_run_id,
                 )
-                await transcripts_controller.update(
+            await transcripts_controller.update(transcript, {"workflow_run_id": None})
-                    transcript, {"workflow_run_id": None}
-                )
 
         # Re-fetch and check for concurrent dispatch (optimistic approach).
         # No database lock - worst case is duplicate dispatch, but Hatchet
@@ -293,12 +269,6 @@ async def dispatch_transcript_processing(
         logger.info("Hatchet workflow dispatched", workflow_id=workflow_id)
         return None
 
-        # Celery pipeline (durable workflows disabled)
-        return task_pipeline_multitrack_process.delay(
-            transcript_id=config.transcript_id,
-            bucket_name=config.bucket_name,
-            track_keys=config.track_keys,
-        )
     elif isinstance(config, FileProcessingConfig):
         return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
     else:

server/reflector/settings.py

@@ -1,7 +1,7 @@
 from pydantic.types import PositiveInt
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
-from reflector.schemas.platform import WHEREBY_PLATFORM, Platform
+from reflector.schemas.platform import DAILY_PLATFORM, Platform
 from reflector.utils.string import NonEmptyString
 
 
@@ -155,7 +155,7 @@ class Settings(BaseSettings):
         None  # Webhook UUID for this environment. Not used by production code
     )
     # Platform Configuration
-    DEFAULT_VIDEO_PLATFORM: Platform = WHEREBY_PLATFORM
+    DEFAULT_VIDEO_PLATFORM: Platform = DAILY_PLATFORM
 
     # Zulip integration
     ZULIP_REALM: str | None = None

server/reflector/worker/process.py

@@ -27,9 +27,6 @@ from reflector.db.transcripts import (
 from reflector.hatchet.client import HatchetClientManager
 from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 from reflector.pipelines.main_live_pipeline import asynctask
-from reflector.pipelines.main_multitrack_pipeline import (
-    task_pipeline_multitrack_process,
-)
 from reflector.pipelines.topic_processing import EmptyPipeline
 from reflector.processors import AudioFileWriterProcessor
 from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
@@ -351,17 +348,7 @@ async def _process_multitrack_recording_inner(
             room_id=room.id,
         )
 
-    use_celery = room and room.use_celery
+    # Multitrack processing always uses Hatchet (no Celery fallback)
-    use_hatchet = not use_celery
-
-    if use_celery:
-        logger.info(
-            "Room uses legacy Celery processing",
-            room_id=room.id,
-            transcript_id=transcript.id,
-        )
-
-    if use_hatchet:
     workflow_id = await HatchetClientManager.start_workflow(
         workflow_name="DiarizationPipeline",
         input_data={
@@ -383,17 +370,7 @@ async def _process_multitrack_recording_inner(
         transcript_id=transcript.id,
     )
 
-        await transcripts_controller.update(
+    await transcripts_controller.update(transcript, {"workflow_run_id": workflow_id})
-            transcript, {"workflow_run_id": workflow_id}
-        )
-        return
-
-    # Celery pipeline (runs when durable workflows disabled)
-    task_pipeline_multitrack_process.delay(
-        transcript_id=transcript.id,
-        bucket_name=bucket_name,
-        track_keys=filter_cam_audio_tracks(track_keys),
-    )
 
 
 @shared_task
@@ -1072,10 +1049,7 @@ async def reprocess_failed_daily_recordings():
                 )
                 continue
 
-            use_celery = room and room.use_celery
+            # Multitrack reprocessing always uses Hatchet (no Celery fallback)
-            use_hatchet = not use_celery
-
-            if use_hatchet:
             if not transcript:
                 logger.warning(
                     "No transcript for Hatchet reprocessing, skipping",
@@ -1112,26 +1086,6 @@ async def reprocess_failed_daily_recordings():
                 room_name=meeting.room_name,
                 track_count=len(recording.track_keys),
             )
-            else:
-                logger.info(
-                    "Queueing Daily recording for Celery reprocessing",
-                    recording_id=recording.id,
-                    room_name=meeting.room_name,
-                    track_count=len(recording.track_keys),
-                    transcript_status=transcript.status if transcript else None,
-                )
-
-                # For reprocessing, pass actual recording time (though it's ignored - see _process_multitrack_recording_inner)
-                # Reprocessing uses recording.meeting_id directly instead of time-based matching
-                recording_start_ts = int(recording.recorded_at.timestamp())
-
-                process_multitrack_recording.delay(
-                    bucket_name=bucket_name,
-                    daily_room_name=meeting.room_name,
-                    recording_id=recording.id,
-                    track_keys=recording.track_keys,
-                    recording_start_ts=recording_start_ts,
-                )
 
             reprocessed_count += 1
 

server/tests/conftest.py

@@ -4,7 +4,7 @@ from unittest.mock import patch
 
 import pytest
 
-from reflector.schemas.platform import WHEREBY_PLATFORM
+from reflector.schemas.platform import DAILY_PLATFORM, WHEREBY_PLATFORM
 
 
 @pytest.fixture(scope="session", autouse=True)
@@ -14,6 +14,7 @@ def register_mock_platform():
     from reflector.video_platforms.registry import register_platform
 
     register_platform(WHEREBY_PLATFORM, MockPlatformClient)
+    register_platform(DAILY_PLATFORM, MockPlatformClient)
     yield
 
 

server/tests/test_transcripts_process.py

@@ -1,6 +1,6 @@
 import asyncio
 import time
-from unittest.mock import patch
+from unittest.mock import AsyncMock, patch
 
 import pytest
 from httpx import ASGITransport, AsyncClient
@@ -142,17 +142,17 @@ async def test_whereby_recording_uses_file_pipeline(client):
             "reflector.services.transcript_process.task_pipeline_file_process"
         ) as mock_file_pipeline,
         patch(
-            "reflector.services.transcript_process.task_pipeline_multitrack_process"
+            "reflector.services.transcript_process.HatchetClientManager"
-        ) as mock_multitrack_pipeline,
+        ) as mock_hatchet,
     ):
         response = await client.post(f"/transcripts/{transcript.id}/process")
 
         assert response.status_code == 200
         assert response.json()["status"] == "ok"
 
-        # Whereby recordings should use file pipeline
+        # Whereby recordings should use file pipeline, not Hatchet
         mock_file_pipeline.delay.assert_called_once_with(transcript_id=transcript.id)
-        mock_multitrack_pipeline.delay.assert_not_called()
+        mock_hatchet.start_workflow.assert_not_called()
 
 
 @pytest.mark.usefixtures("setup_database")
@@ -177,8 +177,6 @@ async def test_dailyco_recording_uses_multitrack_pipeline(client):
         recording_trigger="automatic-2nd-participant",
         is_shared=False,
     )
-    # Force Celery backend for test
-    await rooms_controller.update(room, {"use_celery": True})
 
     transcript = await transcripts_controller.add(
         "",
@@ -213,18 +211,23 @@ async def test_dailyco_recording_uses_multitrack_pipeline(client):
             "reflector.services.transcript_process.task_pipeline_file_process"
         ) as mock_file_pipeline,
         patch(
-            "reflector.services.transcript_process.task_pipeline_multitrack_process"
+            "reflector.services.transcript_process.HatchetClientManager"
-        ) as mock_multitrack_pipeline,
+        ) as mock_hatchet,
     ):
+        mock_hatchet.start_workflow = AsyncMock(return_value="test-workflow-id")
+
         response = await client.post(f"/transcripts/{transcript.id}/process")
 
         assert response.status_code == 200
         assert response.json()["status"] == "ok"
 
-        # Daily.co multitrack recordings should use multitrack pipeline
+        # Daily.co multitrack recordings should use Hatchet workflow
-        mock_multitrack_pipeline.delay.assert_called_once_with(
+        mock_hatchet.start_workflow.assert_called_once()
-            transcript_id=transcript.id,
+        call_kwargs = mock_hatchet.start_workflow.call_args.kwargs
-            bucket_name="daily-bucket",
+        assert call_kwargs["workflow_name"] == "DiarizationPipeline"
-            track_keys=track_keys,
+        assert call_kwargs["input_data"]["transcript_id"] == transcript.id
-        )
+        assert call_kwargs["input_data"]["bucket_name"] == "daily-bucket"
+        assert call_kwargs["input_data"]["tracks"] == [
+            {"s3_key": k} for k in track_keys
+        ]
         mock_file_pipeline.delay.assert_not_called()