feat: add LLM_ENABLE_THINKING env var for thinking-mode LLMs

Some LLMs (e.g. GLM-4.5-Air) default to thinking mode which returns
content in reasoning_content instead of content field, breaking
structured output parsing. This setting passes enable_thinking through
extra_body to control the behavior per deployment.

Three states: None (default, don't send), True, False.

.gitleaksignore

@@ -4,3 +4,4 @@ docs/docs/installation/daily-setup.md:curl-auth-header:277
 gpu/self_hosted/DEV_SETUP.md:curl-auth-header:74
 gpu/self_hosted/DEV_SETUP.md:curl-auth-header:83
 server/reflector/worker/process.py:generic-api-key:465
+server/reflector/worker/process.py:generic-api-key:594

CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## [0.33.0](https://github.com/Monadical-SAS/reflector/compare/v0.32.2...v0.33.0) (2026-02-05)
+
+
+### Features
+
+* Daily+hatchet default ([#846](https://github.com/Monadical-SAS/reflector/issues/846)) ([15ab2e3](https://github.com/Monadical-SAS/reflector/commit/15ab2e306eacf575494b4b5d2b2ad779d44a1c7f))
+
+
+### Bug Fixes
+
+* websocket tests ([#825](https://github.com/Monadical-SAS/reflector/issues/825)) ([1ce1c7a](https://github.com/Monadical-SAS/reflector/commit/1ce1c7a910b6c374115d2437b17f9d288ef094dc))
+
 ## [0.32.2](https://github.com/Monadical-SAS/reflector/compare/v0.32.1...v0.32.2) (2026-02-03)
 
 

gpu/self_hosted/Dockerfile

@@ -4,27 +4,31 @@ ENV PYTHONUNBUFFERED=1 \
     UV_LINK_MODE=copy \
     UV_NO_CACHE=1
 
+# patch until nvidia updates the sha1 repo
+ADD sequoia.config /etc/crypto-policies/back-ends/sequoia.config
+
 WORKDIR /tmp
-RUN apt-get update \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+ --mount=type=cache,target=/var/lib/apt,sharing=locked \
+ apt-get update \
  && apt-get install -y \
     ffmpeg \
     curl \
     ca-certificates \
     gnupg \
-    wget \
- && apt-get clean
+    wget
 # Add NVIDIA CUDA repo for Debian 12 (bookworm) and install cuDNN 9 for CUDA 12
 ADD https://developer.download.nvidia.com/compute/cuda/repos/debian12/x86_64/cuda-keyring_1.1-1_all.deb /cuda-keyring.deb
-RUN dpkg -i /cuda-keyring.deb \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+ --mount=type=cache,target=/var/lib/apt,sharing=locked \
+ dpkg -i /cuda-keyring.deb \
  && rm /cuda-keyring.deb \
  && apt-get update \
  && apt-get install -y --no-install-recommends \
     cuda-cudart-12-6 \
     libcublas-12-6 \
     libcudnn9-cuda-12 \
-    libcudnn9-dev-cuda-12 \
- && apt-get clean \
- && rm -rf /var/lib/apt/lists/*
+    libcudnn9-dev-cuda-12
 ADD https://astral.sh/uv/install.sh /uv-installer.sh
 RUN sh /uv-installer.sh && rm /uv-installer.sh
 ENV PATH="/root/.local/bin/:$PATH"
@@ -39,6 +43,13 @@ COPY ./app /app/app
 COPY ./main.py /app/
 COPY ./runserver.sh /app/
 
+# prevent uv failing with too many open files on big cpus
+ENV UV_CONCURRENT_INSTALLS=16
+
+# first install
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --compile-bytecode --locked
+
 EXPOSE 8000
 
 CMD ["sh", "/app/runserver.sh"]

gpu/self_hosted/sequoia.config

@@ -0,0 +1,2 @@
+[hash_algorithms]
+sha1 = "always"

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/llm.py

@@ -206,6 +206,12 @@ class LLM:
         """Configure llamaindex Settings with OpenAILike LLM"""
         session_id = llm_session_id.get() or f"fallback-{uuid4().hex}"
 
+        extra_body: dict = {"litellm_session_id": session_id}
+        # Only send enable_thinking when explicitly set (not None/unset).
+        # Models that don't support it will ignore the param.
+        if self.settings_obj.LLM_ENABLE_THINKING is not None:
+            extra_body["enable_thinking"] = self.settings_obj.LLM_ENABLE_THINKING
+
         Settings.llm = OpenAILike(
             model=self.model_name,
             api_base=self.url,
@@ -215,7 +221,7 @@ class LLM:
             is_function_calling_model=False,
             temperature=self.temperature,
             max_tokens=self.max_tokens,
-            additional_kwargs={"extra_body": {"litellm_session_id": session_id}},
+            additional_kwargs={"extra_body": extra_body},
         )
 
     async def get_response(

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
-        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:
+        # Multitrack processing always uses Hatchet (no Celery fallback)
         # 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(
-                        transcript.workflow_run_id
-                    )
+                await HatchetClientManager.replay_workflow(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(
-                        transcript.workflow_run_id
-                    )
+                await HatchetClientManager.cancel_workflow(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(
-                    transcript, {"workflow_run_id": None}
-                )
+            await transcripts_controller.update(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
 
 
@@ -75,6 +75,7 @@ class Settings(BaseSettings):
     LLM_URL: str | None = None
     LLM_API_KEY: str | None = None
     LLM_CONTEXT_WINDOW: int = 16000
+    LLM_ENABLE_THINKING: bool | None = None
 
     LLM_PARSE_MAX_RETRIES: int = (
         3  # Max retries for JSON/validation errors (total attempts = retries + 1)
@@ -155,7 +156,7 @@ 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
-    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:
+    # Multitrack processing always uses Hatchet (no Celery fallback)
     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(
-            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),
-    )
+    await transcripts_controller.update(transcript, {"workflow_run_id": workflow_id})
 
 
 @shared_task
@@ -1072,10 +1049,7 @@ async def reprocess_failed_daily_recordings():
                 )
                 continue
 
-            use_celery = room and room.use_celery
-            use_hatchet = not use_celery
-
-            if use_hatchet:
+            # Multitrack reprocessing always uses Hatchet (no Celery fallback)
             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/reflector/ws_manager.py

@@ -11,7 +11,6 @@ broadcast messages to all connected websockets.
 
 import asyncio
 import json
-import threading
 
 import redis.asyncio as redis
 from fastapi import WebSocket
@@ -98,6 +97,7 @@ class WebsocketManager:
 
     async def _pubsub_data_reader(self, pubsub_subscriber):
         while True:
+            # timeout=1.0 prevents tight CPU loop when no messages available
             message = await pubsub_subscriber.get_message(
                 ignore_subscribe_messages=True
             )
@@ -109,29 +109,38 @@ class WebsocketManager:
                     await socket.send_json(data)
 
 
+# Process-global singleton to ensure only one WebsocketManager instance exists.
+# Multiple instances would cause resource leaks and CPU issues.
+_ws_manager: WebsocketManager | None = None
+
+
 def get_ws_manager() -> WebsocketManager:
     """
-    Returns the WebsocketManager instance for managing websockets.
+    Returns the global WebsocketManager singleton.
 
-    This function initializes and returns the WebsocketManager instance,
-    which is responsible for managing websockets and handling websocket
-    connections.
+    Creates instance on first call, subsequent calls return cached instance.
+    Thread-safe via GIL. Concurrent initialization may create duplicate
+    instances but last write wins (acceptable for this use case).
 
     Returns:
-        WebsocketManager: The initialized WebsocketManager instance.
-
-    Raises:
-        ImportError: If the 'reflector.settings' module cannot be imported.
-        RedisConnectionError: If there is an error connecting to the Redis server.
+        WebsocketManager: The global WebsocketManager instance.
     """
-    local = threading.local()
-    if hasattr(local, "ws_manager"):
-        return local.ws_manager
+    global _ws_manager
 
+    if _ws_manager is not None:
+        return _ws_manager
+
+    # No lock needed - GIL makes this safe enough
+    # Worst case: race creates two instances, last assignment wins
     pubsub_client = RedisPubSubManager(
         host=settings.REDIS_HOST,
         port=settings.REDIS_PORT,
     )
-    ws_manager = WebsocketManager(pubsub_client=pubsub_client)
-    local.ws_manager = ws_manager
-    return ws_manager
+    _ws_manager = WebsocketManager(pubsub_client=pubsub_client)
+    return _ws_manager
+
+
+def reset_ws_manager() -> None:
+    """Reset singleton for testing. DO NOT use in production."""
+    global _ws_manager
+    _ws_manager = None

server/tests/conftest.py

@@ -1,11 +1,10 @@
 import os
 from contextlib import asynccontextmanager
-from tempfile import NamedTemporaryFile
 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)
@@ -15,6 +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
 
 
@@ -333,10 +333,13 @@ def celery_enable_logging():
 
 @pytest.fixture(scope="session")
 def celery_config():
-    with NamedTemporaryFile() as f:
+    redis_host = os.environ.get("REDIS_HOST", "localhost")
+    redis_port = os.environ.get("REDIS_PORT", "6379")
+    # Use db 2 to avoid conflicts with main app
+    redis_url = f"redis://{redis_host}:{redis_port}/2"
     yield {
-            "broker_url": "memory://",
-            "result_backend": f"db+sqlite:///{f.name}",
+        "broker_url": redis_url,
+        "result_backend": redis_url,
     }
 
 
@@ -370,9 +373,12 @@ async def ws_manager_in_memory(monkeypatch):
         def __init__(self, queue: asyncio.Queue):
             self.queue = queue
 
-        async def get_message(self, ignore_subscribe_messages: bool = True):
+        async def get_message(
+            self, ignore_subscribe_messages: bool = True, timeout: float | None = None
+        ):
+            wait_timeout = timeout if timeout is not None else 0.05
             try:
-                return await asyncio.wait_for(self.queue.get(), timeout=0.05)
+                return await asyncio.wait_for(self.queue.get(), timeout=wait_timeout)
             except Exception:
                 return None
 

server/tests/test_llm_retry.py

@@ -8,6 +8,7 @@ from pydantic import BaseModel, Field
 from workflows.errors import WorkflowRuntimeError, WorkflowTimeoutError
 
 from reflector.llm import LLM, LLMParseError, StructuredOutputWorkflow
+from reflector.settings import Settings
 from reflector.utils.retry import RetryException
 
 
@@ -26,6 +27,57 @@ def make_completion_response(text: str):
     return response
 
 
+class TestLLMEnableThinking:
+    """Test that LLM_ENABLE_THINKING setting is passed through to OpenAILike"""
+
+    def test_enable_thinking_false_passed_in_extra_body(self):
+        """enable_thinking=False should be in extra_body when LLM_ENABLE_THINKING=False"""
+        settings = Settings(
+            LLM_ENABLE_THINKING=False,
+            LLM_URL="http://fake",
+            LLM_API_KEY="fake",
+        )
+
+        with (
+            patch("reflector.llm.OpenAILike") as mock_openai,
+            patch("reflector.llm.Settings"),
+        ):
+            LLM(settings=settings)
+            extra_body = mock_openai.call_args.kwargs["additional_kwargs"]["extra_body"]
+            assert extra_body["enable_thinking"] is False
+
+    def test_enable_thinking_true_passed_in_extra_body(self):
+        """enable_thinking=True should be in extra_body when LLM_ENABLE_THINKING=True"""
+        settings = Settings(
+            LLM_ENABLE_THINKING=True,
+            LLM_URL="http://fake",
+            LLM_API_KEY="fake",
+        )
+
+        with (
+            patch("reflector.llm.OpenAILike") as mock_openai,
+            patch("reflector.llm.Settings"),
+        ):
+            LLM(settings=settings)
+            extra_body = mock_openai.call_args.kwargs["additional_kwargs"]["extra_body"]
+            assert extra_body["enable_thinking"] is True
+
+    def test_enable_thinking_none_not_in_extra_body(self):
+        """enable_thinking should not be in extra_body when LLM_ENABLE_THINKING is None (default)"""
+        settings = Settings(
+            LLM_URL="http://fake",
+            LLM_API_KEY="fake",
+        )
+
+        with (
+            patch("reflector.llm.OpenAILike") as mock_openai,
+            patch("reflector.llm.Settings"),
+        ):
+            LLM(settings=settings)
+            extra_body = mock_openai.call_args.kwargs["additional_kwargs"]["extra_body"]
+            assert "enable_thinking" not in extra_body
+
+
 class TestLLMParseErrorRecovery:
     """Test parse error recovery with Workflow feedback loop"""
 

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"
-        ) as mock_multitrack_pipeline,
+            "reflector.services.transcript_process.HatchetClientManager"
+        ) 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"
-        ) as mock_multitrack_pipeline,
+            "reflector.services.transcript_process.HatchetClientManager"
+        ) 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
-        mock_multitrack_pipeline.delay.assert_called_once_with(
-            transcript_id=transcript.id,
-            bucket_name="daily-bucket",
-            track_keys=track_keys,
-        )
+        # Daily.co multitrack recordings should use Hatchet workflow
+        mock_hatchet.start_workflow.assert_called_once()
+        call_kwargs = mock_hatchet.start_workflow.call_args.kwargs
+        assert call_kwargs["workflow_name"] == "DiarizationPipeline"
+        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()

server/tests/test_transcripts_rtc_ws.py

@@ -115,9 +115,7 @@ def appserver(tmpdir, setup_database, celery_session_app, celery_session_worker)
     settings.DATA_DIR = DATA_DIR
 
 
-@pytest.fixture(scope="session")
-def celery_includes():
-    return ["reflector.pipelines.main_live_pipeline"]
+# Using celery_includes from conftest.py which includes both pipelines
 
 
 @pytest.mark.usefixtures("setup_database")

server/tests/test_user_websocket_auth.py

@@ -56,7 +56,12 @@ def appserver_ws_user(setup_database):
 
     if server_instance:
         server_instance.should_exit = True
-        server_thread.join(timeout=30)
+        server_thread.join(timeout=2.0)
+
+    # Reset global singleton for test isolation
+    from reflector.ws_manager import reset_ws_manager
+
+    reset_ws_manager()
 
 
 @pytest.fixture(autouse=True)
@@ -133,6 +138,8 @@ async def test_user_ws_accepts_valid_token_and_receives_events(appserver_ws_user
 
     # Connect and then trigger an event via HTTP create
     async with aconnect_ws(base_ws, subprotocols=subprotocols) as ws:
+        await asyncio.sleep(0.2)
+
         # Emit an event to the user's room via a standard HTTP action
         from httpx import AsyncClient
 
@@ -150,6 +157,7 @@ async def test_user_ws_accepts_valid_token_and_receives_events(appserver_ws_user
             "email": "user-abc@example.com",
         }
 
+        # Use in-memory client (global singleton makes it share ws_manager)
         async with AsyncClient(app=app, base_url=f"http://{host}:{port}/v1") as ac:
             # Create a transcript as this user so that the server publishes TRANSCRIPT_CREATED to user room
             resp = await ac.post("/transcripts", json={"name": "WS Test"})