format

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>

.gitignore

@@ -1,6 +1,5 @@
 .DS_Store
 server/.env
-server/.env.production
 .env
 Caddyfile
 server/exportdanswer

.gitleaksignore

@@ -4,4 +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/tests/test_recording_request_flow.py:generic-api-key:121
+server/reflector/worker/process.py:generic-api-key:594

CHANGELOG.md

@@ -1,20 +1,5 @@
 # Changelog
 
-## [0.32.1](https://github.com/Monadical-SAS/reflector/compare/v0.32.0...v0.32.1) (2026-01-30)
-
-
-### Bug Fixes
-
-* daily multitrack pipeline finalze dependency fix ([23eb137](https://github.com/Monadical-SAS/reflector/commit/23eb1371cb9348c4b81eb12ad506b582f8a4799e))
-* match httpx pad with hatchet audio timeout ([c05d1f0](https://github.com/Monadical-SAS/reflector/commit/c05d1f03cd8369fc06efd455527e50246887efd0))
-
-## [0.32.0](https://github.com/Monadical-SAS/reflector/compare/v0.31.0...v0.32.0) (2026-01-30)
-
-
-### Features
-
-* modal padding ([#837](https://github.com/Monadical-SAS/reflector/issues/837)) ([7fde64e](https://github.com/Monadical-SAS/reflector/commit/7fde64e2529a1d37b0f7507c62d983a7bd0b5b89))
-
 ## [0.31.0](https://github.com/Monadical-SAS/reflector/compare/v0.30.0...v0.31.0) (2026-01-23)
 
 

Caddyfile.example

@@ -1,8 +1,6 @@
-# Reflector Caddyfile (optional reverse proxy)
+# Reflector Caddyfile
-# Use this only when you run Caddy via: docker compose -f docker-compose.prod.yml --profile caddy up -d
+# Replace example.com with your actual domains
-# If Coolify, Traefik, or nginx already use ports 80/443, do NOT start Caddy; point your proxy at web:3000 and server:1250.
+# CORS is handled by the backend - Caddy just proxies
-#
-# Replace example.com with your actual domains. CORS is handled by the backend - Caddy just proxies.
 #
 # For environment variable substitution, set:
 #   FRONTEND_DOMAIN=app.example.com

docker-compose.prod.yml

@@ -1,14 +1,9 @@
 # Production Docker Compose configuration
 # Usage: docker compose -f docker-compose.prod.yml up -d
 #
-# Caddy (reverse proxy on ports 80/443) is OPTIONAL and behind the "caddy" profile:
-# - With Caddy (self-hosted, you manage SSL): docker compose -f docker-compose.prod.yml --profile caddy up -d
-# - Without Caddy (Coolify/Traefik/nginx already on 80/443): docker compose -f docker-compose.prod.yml up -d
-#   Then point your proxy at web:3000 (frontend) and server:1250 (API).
-#
 # Prerequisites:
 # 1. Copy .env.example to .env and configure for both server/ and www/
-# 2. If using Caddy: copy Caddyfile.example to Caddyfile and edit your domains
+# 2. Copy Caddyfile.example to Caddyfile and edit with your domains
 # 3. Deploy Modal GPU functions (see gpu/modal_deployments/deploy-all.sh)
 
 services:
@@ -89,8 +84,6 @@ services:
       retries: 3
 
   caddy:
-    profiles:
-      - caddy
     image: caddy:2-alpine
     restart: unless-stopped
     ports:

docs/docs/installation/docker-setup.md

@@ -11,15 +11,15 @@ This page documents the Docker Compose configuration for Reflector. For the comp
 
 The `docker-compose.prod.yml` includes these services:
 
-| Service    | Image                             | Purpose                                                                     |
+| Service | Image | Purpose |
-| ---------- | --------------------------------- | --------------------------------------------------------------------------- |
+|---------|-------|---------|
-| `web`      | `monadicalsas/reflector-frontend` | Next.js frontend                                                            |
+| `web` | `monadicalsas/reflector-frontend` | Next.js frontend |
-| `server`   | `monadicalsas/reflector-backend`  | FastAPI backend                                                             |
+| `server` | `monadicalsas/reflector-backend` | FastAPI backend |
-| `worker`   | `monadicalsas/reflector-backend`  | Celery worker for background tasks                                          |
+| `worker` | `monadicalsas/reflector-backend` | Celery worker for background tasks |
-| `beat`     | `monadicalsas/reflector-backend`  | Celery beat scheduler                                                       |
+| `beat` | `monadicalsas/reflector-backend` | Celery beat scheduler |
-| `redis`    | `redis:7.2-alpine`                | Message broker and cache                                                    |
+| `redis` | `redis:7.2-alpine` | Message broker and cache |
-| `postgres` | `postgres:17-alpine`              | Primary database                                                            |
+| `postgres` | `postgres:17-alpine` | Primary database |
-| `caddy`    | `caddy:2-alpine`                  | Reverse proxy with auto-SSL (optional; see [Caddy profile](#caddy-profile)) |
+| `caddy` | `caddy:2-alpine` | Reverse proxy with auto-SSL |
 
 ## Environment Files
 
@@ -30,7 +30,6 @@ Reflector uses two separate environment files:
 Used by: `server`, `worker`, `beat`
 
 Key variables:
-
 ```env
 # Database connection
 DATABASE_URL=postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
@@ -55,7 +54,6 @@ TRANSCRIPT_MODAL_API_KEY=...
 Used by: `web`
 
 Key variables:
-
 ```env
 # Domain configuration
 SITE_URL=https://app.example.com
@@ -72,42 +70,26 @@ Note: `API_URL` is used client-side (browser), `SERVER_API_URL` is used server-s
 
 ## Volumes
 
-| Volume          | Purpose                       |
+| Volume | Purpose |
-| --------------- | ----------------------------- |
+|--------|---------|
-| `redis_data`    | Redis persistence             |
+| `redis_data` | Redis persistence |
-| `postgres_data` | PostgreSQL data               |
+| `postgres_data` | PostgreSQL data |
-| `server_data`   | Uploaded files, local storage |
+| `server_data` | Uploaded files, local storage |
-| `caddy_data`    | SSL certificates              |
+| `caddy_data` | SSL certificates |
-| `caddy_config`  | Caddy configuration           |
+| `caddy_config` | Caddy configuration |
 
 ## Network
 
 All services share the default network. The network is marked `attachable: true` to allow external containers (like Authentik) to join.
 
-## Caddy profile
-
-Caddy (ports 80 and 443) is **optional** and behind the `caddy` profile so it does not conflict with an existing reverse proxy (e.g. Coolify, Traefik, nginx).
-
-- **With Caddy** (you want Reflector to handle SSL):
-  `docker compose -f docker-compose.prod.yml --profile caddy up -d`
-- **Without Caddy** (Coolify or another proxy already on 80/443):
-  `docker compose -f docker-compose.prod.yml up -d`
-  Then configure your proxy to send traffic to `web:3000` (frontend) and `server:1250` (API).
-
 ## Common Commands
 
 ### Start all services
-
 ```bash
-# Without Caddy (e.g. when using Coolify)
 docker compose -f docker-compose.prod.yml up -d
-
-# With Caddy as reverse proxy
-docker compose -f docker-compose.prod.yml --profile caddy up -d
 ```
 
 ### View logs
-
 ```bash
 # All services
 docker compose -f docker-compose.prod.yml logs -f
@@ -117,7 +99,6 @@ docker compose -f docker-compose.prod.yml logs server --tail 50
 ```
 
 ### Restart a service
-
 ```bash
 # Quick restart (doesn't reload .env changes)
 docker compose -f docker-compose.prod.yml restart server
@@ -127,32 +108,27 @@ docker compose -f docker-compose.prod.yml up -d server
 ```
 
 ### Run database migrations
-
 ```bash
 docker compose -f docker-compose.prod.yml exec server uv run alembic upgrade head
 ```
 
 ### Access database
-
 ```bash
 docker compose -f docker-compose.prod.yml exec postgres psql -U reflector
 ```
 
 ### Pull latest images
-
 ```bash
 docker compose -f docker-compose.prod.yml pull
 docker compose -f docker-compose.prod.yml up -d
 ```
 
 ### Stop all services
-
 ```bash
 docker compose -f docker-compose.prod.yml down
 ```
 
 ### Full reset (WARNING: deletes data)
-
 ```bash
 docker compose -f docker-compose.prod.yml down -v
 ```
@@ -211,7 +187,6 @@ The Caddyfile supports environment variable substitution:
 Set `FRONTEND_DOMAIN` and `API_DOMAIN` environment variables, or edit the file directly.
 
 ### Reload Caddy after changes
-
 ```bash
 docker compose -f docker-compose.prod.yml exec caddy caddy reload --config /etc/caddy/Caddyfile
 ```

docs/docs/installation/overview.md

@@ -26,7 +26,7 @@ flowchart LR
 
 Before starting, you need:
 
-- **Production server** - 4+ cores, 8GB+ RAM, public IP
+- **Production server** -  4+ cores, 8GB+ RAM, public IP
 - **Two domain names** - e.g., `app.example.com` (frontend) and `api.example.com` (backend)
 - **GPU processing** - Choose one:
   - Modal.com account, OR
@@ -60,17 +60,16 @@ Type: A    Name: api    Value: <your-server-ip>
 
 Reflector requires GPU processing for transcription and speaker diarization. Choose one option:
 
-|              | **Modal.com (Cloud)**             | **Self-Hosted GPU**          |
+| | **Modal.com (Cloud)** | **Self-Hosted GPU** |
-| ------------ | --------------------------------- | ---------------------------- |
+|---|---|---|
 | **Best for** | No GPU hardware, zero maintenance | Own GPU server, full control |
-| **Pricing**  | Pay-per-use                       | Fixed infrastructure cost    |
+| **Pricing** | Pay-per-use | Fixed infrastructure cost |
 
 ### Option A: Modal.com (Serverless Cloud GPU)
 
 #### Accept HuggingFace Licenses
 
 Visit both pages and click "Accept":
-
 - https://huggingface.co/pyannote/speaker-diarization-3.1
 - https://huggingface.co/pyannote/segmentation-3.0
 
@@ -180,7 +179,6 @@ Save these credentials - you'll need them in the next step.
 ## Configure Environment
 
 Reflector has two env files:
-
 - `server/.env` - Backend configuration
 - `www/.env` - Frontend configuration
 
@@ -192,7 +190,6 @@ nano server/.env
 ```
 
 **Required settings:**
-
 ```env
 # Database (defaults work with docker-compose.prod.yml)
 DATABASE_URL=postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
@@ -252,7 +249,6 @@ nano www/.env
 ```
 
 **Required settings:**
-
 ```env
 # Your domains
 SITE_URL=https://app.example.com
@@ -270,11 +266,7 @@ FEATURE_REQUIRE_LOGIN=false
 
 ---
 
-## Reverse proxy (Caddy or existing)
+## Configure Caddy
-
-**If Coolify, Traefik, or nginx already use ports 80/443** (e.g. Coolify on your host): skip Caddy. Start the stack without the Caddy profile (see [Start Services](#start-services) below), then point your proxy at `web:3000` (frontend) and `server:1250` (API).
-
-**If you want Reflector to provide the reverse proxy and SSL:**
 
 ```bash
 cp Caddyfile.example Caddyfile
@@ -297,18 +289,10 @@ Replace `example.com` with your domains. The `{$VAR:default}` syntax uses Caddy'
 
 ## Start Services
 
-**Without Caddy** (e.g. Coolify already on 80/443):
-
 ```bash
 docker compose -f docker-compose.prod.yml up -d
 ```
 
-**With Caddy** (Reflector handles SSL):
-
-```bash
-docker compose -f docker-compose.prod.yml --profile caddy up -d
-```
-
 Wait for containers to start (first run may take 1-2 minutes to pull images and initialize).
 
 ---
@@ -316,21 +300,18 @@ Wait for containers to start (first run may take 1-2 minutes to pull images and
 ## Verify Deployment
 
 ### Check services
-
 ```bash
 docker compose -f docker-compose.prod.yml ps
 # All should show "Up"
 ```
 
 ### Test API
-
 ```bash
 curl https://api.example.com/health
 # Should return: {"status":"healthy"}
 ```
 
 ### Test Frontend
-
 - Visit https://app.example.com
 - You should see the Reflector interface
 - Try uploading an audio file to test transcription
@@ -346,7 +327,6 @@ By default, Reflector is open (no login required). **Authentication is required
 See [Authentication Setup](./auth-setup) for full Authentik OAuth configuration.
 
 Quick summary:
-
 1. Deploy Authentik on your server
 2. Create OAuth provider in Authentik
 3. Extract public key for JWT verification
@@ -378,7 +358,6 @@ DAILYCO_STORAGE_AWS_ROLE_ARN=<arn:aws:iam::ACCOUNT:role/DailyCo>
 ```
 
 Reload env and restart:
-
 ```bash
 docker compose -f docker-compose.prod.yml up -d server worker
 ```
@@ -388,43 +367,35 @@ docker compose -f docker-compose.prod.yml up -d server worker
 ## Troubleshooting
 
 ### Check logs for errors
-
 ```bash
 docker compose -f docker-compose.prod.yml logs server --tail 20
 docker compose -f docker-compose.prod.yml logs worker --tail 20
 ```
 
 ### Services won't start
-
 ```bash
 docker compose -f docker-compose.prod.yml logs
 ```
 
 ### CORS errors in browser
-
 - Verify `CORS_ORIGIN` in `server/.env` matches your frontend domain exactly (including `https://`)
 - Reload env: `docker compose -f docker-compose.prod.yml up -d server`
 
-### SSL certificate errors (when using Caddy)
+### SSL certificate errors
-
 - Caddy auto-provisions Let's Encrypt certificates
-- Ensure ports 80 and 443 are open and not used by another proxy
+- Ensure ports 80 and 443 are open
 - Check: `docker compose -f docker-compose.prod.yml logs caddy`
-- If port 80 is already in use (e.g. by Coolify), run without Caddy: `docker compose -f docker-compose.prod.yml up -d` and use your existing proxy
 
 ### Transcription not working
-
 - Check Modal dashboard: https://modal.com/apps
 - Verify URLs in `server/.env` match deployed functions
 - Check worker logs: `docker compose -f docker-compose.prod.yml logs worker`
 
 ### "Login required" but auth not configured
-
 - Set `FEATURE_REQUIRE_LOGIN=false` in `www/.env`
 - Rebuild frontend: `docker compose -f docker-compose.prod.yml up -d --force-recreate web`
 
 ### Database migrations or connectivity issues
-
 Migrations run automatically on server startup. To check database connectivity or debug migration failures:
 
 ```bash
@@ -437,3 +408,4 @@ docker compose -f docker-compose.prod.yml exec server uv run python -c "from ref
 # Manually run migrations (if needed)
 docker compose -f docker-compose.prod.yml exec server uv run alembic upgrade head
 ```
+

gpu/modal_deployments/deploy-all.sh

@@ -131,15 +131,6 @@ if [ -z "$DIARIZER_URL" ]; then
 fi
 echo "  -> $DIARIZER_URL"
 
-echo ""
-echo "Deploying padding (CPU audio processing via Modal SDK)..."
-modal deploy reflector_padding.py
-if [ $? -ne 0 ]; then
-    echo "Error: Failed to deploy padding. Check Modal dashboard for details."
-    exit 1
-fi
-echo "  -> reflector-padding.pad_track (Modal SDK function)"
-
 # --- Output Configuration ---
 echo ""
 echo "=========================================="
@@ -156,6 +147,4 @@ echo ""
 echo "DIARIZATION_BACKEND=modal"
 echo "DIARIZATION_URL=$DIARIZER_URL"
 echo "DIARIZATION_MODAL_API_KEY=$API_KEY"
-echo ""
-echo "# Padding uses Modal SDK (requires MODAL_TOKEN_ID/SECRET in worker containers)"
 echo "# --- End Modal Configuration ---"

gpu/modal_deployments/reflector_padding.py

@@ -1,277 +0,0 @@
-"""
-Reflector GPU backend - audio padding
-======================================
-
-CPU-intensive audio padding service for adding silence to audio tracks.
-Uses PyAV filter graph (adelay) for precise track synchronization.
-
-IMPORTANT: This padding logic is duplicated from server/reflector/utils/audio_padding.py
-for Modal deployment isolation (Modal can't import from server/reflector/). If you modify
-the PyAV filter graph or padding algorithm, you MUST update both:
-  - gpu/modal_deployments/reflector_padding.py (this file)
-  - server/reflector/utils/audio_padding.py
-
-Constants duplicated from server/reflector/utils/audio_constants.py for same reason.
-"""
-
-import os
-import tempfile
-from fractions import Fraction
-import math
-import asyncio
-
-import modal
-
-S3_TIMEOUT = 60 # happens 2 times
-PADDING_TIMEOUT = 600 + (S3_TIMEOUT * 2)
-SCALEDOWN_WINDOW = 60  # The maximum duration (in seconds) that individual containers can remain idle when scaling down.
-DISCONNECT_CHECK_INTERVAL = 2  # Check for client disconnect
-
-
-app = modal.App("reflector-padding")
-
-# CPU-based image
-image = (
-    modal.Image.debian_slim(python_version="3.12")
-    .apt_install("ffmpeg")  # Required by PyAV
-    .pip_install(
-        "av==13.1.0",  # PyAV for audio processing
-        "requests==2.32.3",  # HTTP for presigned URL downloads/uploads
-        "fastapi==0.115.12",  # API framework
-    )
-)
-
-# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
-OPUS_STANDARD_SAMPLE_RATE = 48000
-# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
-OPUS_DEFAULT_BIT_RATE = 128000
-
-
-@app.function(
-    cpu=2.0,
-    timeout=PADDING_TIMEOUT,
-    scaledown_window=SCALEDOWN_WINDOW,
-    image=image,
-)
-@modal.asgi_app()
-def web():
-    from fastapi import FastAPI, Request, HTTPException
-    from pydantic import BaseModel
-
-    class PaddingRequest(BaseModel):
-        track_url: str
-        output_url: str
-        start_time_seconds: float
-        track_index: int
-
-    class PaddingResponse(BaseModel):
-        size: int
-        cancelled: bool = False
-
-    web_app = FastAPI()
-
-    @web_app.post("/pad")
-    async def pad_track_endpoint(request: Request, req: PaddingRequest) -> PaddingResponse:
-        """Modal web endpoint for padding audio tracks with disconnect detection.
-        """
-        import logging
-
-        logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
-        logger = logging.getLogger(__name__)
-
-        if not req.track_url:
-            raise HTTPException(status_code=400, detail="track_url cannot be empty")
-        if not req.output_url:
-            raise HTTPException(status_code=400, detail="output_url cannot be empty")
-        if req.start_time_seconds <= 0:
-            raise HTTPException(status_code=400, detail=f"start_time_seconds must be positive, got {req.start_time_seconds}")
-        if req.start_time_seconds > 18000:
-            raise HTTPException(status_code=400, detail=f"start_time_seconds exceeds maximum 18000s (5 hours)")
-
-        logger.info(f"Padding request: track {req.track_index}, delay={req.start_time_seconds}s")
-
-        # Thread-safe cancellation flag shared between async disconnect checker and blocking thread
-        import threading
-        cancelled = threading.Event()
-
-        async def check_disconnect():
-            """Background task to check for client disconnect every 2 seconds."""
-            while not cancelled.is_set():
-                await asyncio.sleep(DISCONNECT_CHECK_INTERVAL)
-                if await request.is_disconnected():
-                    logger.warning("Client disconnected, setting cancellation flag")
-                    cancelled.set()
-                    break
-
-        # Start disconnect checker in background
-        disconnect_task = asyncio.create_task(check_disconnect())
-
-        try:
-            result = await asyncio.get_event_loop().run_in_executor(
-                None, _pad_track_blocking, req, cancelled, logger
-            )
-            return PaddingResponse(**result)
-        finally:
-            cancelled.set()
-            disconnect_task.cancel()
-            try:
-                await disconnect_task
-            except asyncio.CancelledError:
-                pass
-
-    def _pad_track_blocking(req, cancelled, logger) -> dict:
-        """Blocking CPU-bound padding work with periodic cancellation checks.
-
-        Args:
-            cancelled: threading.Event for thread-safe cancellation signaling
-        """
-        import av
-        import requests
-        from av.audio.resampler import AudioResampler
-        import time
-
-        temp_dir = tempfile.mkdtemp()
-        input_path = None
-        output_path = None
-        last_check = time.time()
-
-        try:
-            logger.info("Downloading track for padding")
-            response = requests.get(req.track_url, stream=True, timeout=S3_TIMEOUT)
-            response.raise_for_status()
-
-            input_path = os.path.join(temp_dir, "track.webm")
-            total_bytes = 0
-            chunk_count = 0
-            with open(input_path, "wb") as f:
-                for chunk in response.iter_content(chunk_size=8192):
-                    if chunk:
-                        f.write(chunk)
-                        total_bytes += len(chunk)
-                        chunk_count += 1
-
-                        # Check for cancellation every arbitrary amount of chunks
-                        if chunk_count % 12 == 0:
-                            now = time.time()
-                            if now - last_check >= DISCONNECT_CHECK_INTERVAL:
-                                if cancelled.is_set():
-                                    logger.info("Cancelled during download, exiting early")
-                                    return {"size": 0, "cancelled": True}
-                                last_check = now
-            logger.info(f"Track downloaded: {total_bytes} bytes")
-
-            if cancelled.is_set():
-                logger.info("Cancelled after download, exiting early")
-                return {"size": 0, "cancelled": True}
-
-            # Apply padding using PyAV
-            output_path = os.path.join(temp_dir, "padded.webm")
-            delay_ms = math.floor(req.start_time_seconds * 1000)
-            logger.info(f"Padding track {req.track_index} with {delay_ms}ms delay using PyAV")
-
-            in_container = av.open(input_path)
-            in_stream = next((s for s in in_container.streams if s.type == "audio"), None)
-            if in_stream is None:
-                raise ValueError("No audio stream in input")
-
-            with av.open(output_path, "w", format="webm") as out_container:
-                out_stream = out_container.add_stream("libopus", rate=OPUS_STANDARD_SAMPLE_RATE)
-                out_stream.bit_rate = OPUS_DEFAULT_BIT_RATE
-                graph = av.filter.Graph()
-
-                abuf_args = (
-                    f"time_base=1/{OPUS_STANDARD_SAMPLE_RATE}:"
-                    f"sample_rate={OPUS_STANDARD_SAMPLE_RATE}:"
-                    f"sample_fmt=s16:"
-                    f"channel_layout=stereo"
-                )
-                src = graph.add("abuffer", args=abuf_args, name="src")
-                aresample_f = graph.add("aresample", args="async=1", name="ares")
-                delays_arg = f"{delay_ms}|{delay_ms}"
-                adelay_f = graph.add("adelay", args=f"delays={delays_arg}:all=1", name="delay")
-                sink = graph.add("abuffersink", name="sink")
-
-                src.link_to(aresample_f)
-                aresample_f.link_to(adelay_f)
-                adelay_f.link_to(sink)
-                graph.configure()
-
-                resampler = AudioResampler(
-                    format="s16", layout="stereo", rate=OPUS_STANDARD_SAMPLE_RATE
-                )
-
-                for frame in in_container.decode(in_stream):
-                    # Check for cancellation periodically
-                    now = time.time()
-                    if now - last_check >= DISCONNECT_CHECK_INTERVAL:
-                        if cancelled.is_set():
-                            logger.info("Cancelled during processing, exiting early")
-                            in_container.close()
-                            return {"size": 0, "cancelled": True}
-                        last_check = now
-
-                    out_frames = resampler.resample(frame) or []
-                    for rframe in out_frames:
-                        rframe.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                        rframe.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                        src.push(rframe)
-
-                        while True:
-                            try:
-                                f_out = sink.pull()
-                            except Exception:
-                                break
-                            f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                            f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                            for packet in out_stream.encode(f_out):
-                                out_container.mux(packet)
-
-                # Flush filter graph
-                src.push(None)
-                while True:
-                    try:
-                        f_out = sink.pull()
-                    except Exception:
-                        break
-                    f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                    f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                    for packet in out_stream.encode(f_out):
-                        out_container.mux(packet)
-
-                # Flush encoder
-                for packet in out_stream.encode(None):
-                    out_container.mux(packet)
-
-            in_container.close()
-
-            file_size = os.path.getsize(output_path)
-            logger.info(f"Padding complete: {file_size} bytes")
-
-            logger.info("Uploading padded track to S3")
-
-            with open(output_path, "rb") as f:
-                upload_response = requests.put(req.output_url, data=f, timeout=S3_TIMEOUT)
-
-            upload_response.raise_for_status()
-            logger.info(f"Upload complete: {file_size} bytes")
-
-            return {"size": file_size}
-
-        finally:
-            if input_path and os.path.exists(input_path):
-                try:
-                    os.unlink(input_path)
-                except Exception as e:
-                    logger.warning(f"Failed to cleanup input file: {e}")
-            if output_path and os.path.exists(output_path):
-                try:
-                    os.unlink(output_path)
-                except Exception as e:
-                    logger.warning(f"Failed to cleanup output file: {e}")
-            try:
-                os.rmdir(temp_dir)
-            except Exception as e:
-                logger.warning(f"Failed to cleanup temp directory: {e}")
-
-    return web_app
-

server/docs/DAILY_REFLECTOR_DATA_MODEL.md

@@ -86,7 +86,7 @@ Daily.co Room: "daily-private-igor-20260110042117"
 | **Purpose** | Tracks active session state | Links recordings, transcripts, participants |
 | **Scope** | Per room instance | Per Reflector room + timestamp |
 
-**Critical Limitation:** Daily.co's recordings API often does NOT return `mtgSessionId` (can be null), requiring time-based matching (see [Time-Based Matching](#time-based-matching)).
+**Critical Limitation:** Daily.co's recordings API often does NOT return `mtgSessionId`, requiring time-based matching (see [Time-Based Matching](#time-based-matching)).
 
 ### Recording
 
@@ -101,30 +101,6 @@ Daily.co Room: "daily-private-igor-20260110042117"
 
 **Critical Behavior:** Recording **stops/restarts** create **separate recording objects** with unique IDs.
 
-### instanceId (Reflector-Generated)
-
-**Definition:** UUID we generate and send when starting recording via REST API.
-
-**Generation:** Deterministic from meeting_id
-- Cloud: `instanceId = meeting_id` directly
-- Raw-tracks: `instanceId = UUIDv5(meeting_id, namespace)`
-
-**Key behaviors:**
-- ✅ **Reuse allowed:** Same instanceId can be used after stop (validated 2026-01-20)
-- ❌ **Not returned:** Daily.co does NOT echo instanceId back in GET /recordings response
-- ✅ **Present in error webhooks:** `recording.error` webhook includes instanceId
-- **Purpose:** Allows multiple concurrent recordings (cloud + raw-tracks) in same room
-
-**Stop/restart example:**
-```
-Recording 1: POST /start with instanceId="779e6376..." → recording_id="ee00c4e8..."
-Stop recording
-Recording 2: POST /start with instanceId="779e6376..." (SAME) → recording_id="b702f509..." (DIFFERENT)
-✅ Both succeed, different recording_ids returned
-```
-
-**Implication:** Cannot match recordings by instanceId (not in response) - must use recording_id.
-
 ---
 
 ## Entity Relationships
@@ -220,19 +196,6 @@ Daily.co Room: "daily-private-igor-20260110042117"
 
 `mtgSessionId` identifies a **Daily.co meeting session** (not individual participants, not a room).
 
-**Reliability:** Can be null or present in GET /recordings response (unreliable).
-
-**When present:** Multiple recordings from same session (stop/restart with participants connected) share same mtgSessionId.
-
-**Example (validated 2026-01-20):**
-```json
-Recording 1: {"id": "ee00c4e8...", "mtgSessionId": "92c4136a-a8da-41c5-9c45-e9a2baae6bd6"}
-Recording 2: {"id": "b702f509...", "mtgSessionId": "92c4136a-a8da-41c5-9c45-e9a2baae6bd6"}
-// Same mtgSessionId (stop/restart in same session)
-```
-
-**When null:** Common - Daily.co API does not reliably populate this field.
-
 ### session_id (Per-Participant)
 
 **Different concept:** Per-participant connection identifier from webhooks.
@@ -257,24 +220,16 @@ TABLE daily_participant_session (
 
 Daily.co's recordings API does not reliably return `mtgSessionId`, making it impossible to directly link recordings to meetings via Daily.co's identifiers.
 
-**Example API response (mtgSessionId can be null OR present):**
+**Example API response:**
 ```json
 {
   "id": "recording-uuid",
   "room_name": "daily-private-igor-20260110042117",
   "start_ts": 1768018896,
-  "mtgSessionId": null  // ← Often null (unreliable)
+  "mtgSessionId": null  ← Missing!
-}
-
-// OR (when present):
-{
-  "id": "recording-uuid",
-  "mtgSessionId": "92c4136a-a8da-41c5-9c45-e9a2baae6bd6"  // ← Sometimes present
 }
 ```
 
-**Key insight:** Cannot rely on mtgSessionId for matching (unreliable). instanceId also not returned. Only reliable identifier is recording.id.
-
 ### Solution: Time-Based Matching
 
 **Implementation:** `reflector/db/meetings.py:get_by_room_name_and_time()`
@@ -536,10 +491,6 @@ UI: User sees 3 separate transcripts
 
 
 ---
-**Document Version:** 1.1
+**Document Version:** 1.0
-**Last Updated:** 2026-01-20
+**Last Verified:** 2026-01-15
-**Data Source:** Production database + Daily.co API inspection + empirical testing
+**Data Source:** Production database + Daily.co API inspection
-**Changes in 1.1:**
-- Added instanceId behavior documentation (reuse allowed, not returned in API)
-- Clarified mtgSessionId reliability (can be null or present)
-- Added empirical validation of stop/restart behavior

server/migrations/versions/f5b008fa8a14_add_daily_recording_requests.py

@@ -1,67 +0,0 @@
-"""add_daily_recording_requests
-
-Revision ID: f5b008fa8a14
-Revises: 1b1e6a6fc465
-Create Date: 2026-01-20 22:32:06.697144
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "f5b008fa8a14"
-down_revision: Union[str, None] = "1b1e6a6fc465"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "daily_recording_request",
-        sa.Column("recording_id", sa.String(), nullable=False),
-        sa.Column("meeting_id", sa.String(), nullable=False),
-        sa.Column("instance_id", sa.String(), nullable=False),
-        sa.Column("type", sa.String(), nullable=False),
-        sa.Column("requested_at", sa.DateTime(timezone=True), nullable=False),
-        sa.ForeignKeyConstraint(["meeting_id"], ["meeting.id"], ondelete="CASCADE"),
-        sa.PrimaryKeyConstraint("recording_id"),
-    )
-    op.create_index("idx_meeting_id", "daily_recording_request", ["meeting_id"])
-    op.create_index("idx_instance_id", "daily_recording_request", ["instance_id"])
-
-    # Clean up orphaned recordings before adding FK constraint
-    op.execute("""
-        UPDATE recording SET status = 'orphan', meeting_id = NULL
-        WHERE meeting_id IS NOT NULL
-        AND meeting_id NOT IN (SELECT id FROM meeting)
-    """)
-
-    # Add FK constraint to recording table (cascade delete recordings when meeting deleted)
-    op.execute("""
-        ALTER TABLE recording ADD CONSTRAINT fk_recording_meeting
-          FOREIGN KEY (meeting_id) REFERENCES meeting(id) ON DELETE CASCADE
-    """)
-
-    # Add CHECK constraints to enforce orphan invariants
-    op.execute("""
-        ALTER TABLE recording ADD CONSTRAINT chk_orphan_no_meeting
-          CHECK (status != 'orphan' OR meeting_id IS NULL)
-    """)
-    op.execute("""
-        ALTER TABLE recording ADD CONSTRAINT chk_non_orphan_has_meeting
-          CHECK (status = 'orphan' OR meeting_id IS NOT NULL)
-    """)
-
-
-def downgrade() -> None:
-    op.execute("ALTER TABLE recording DROP CONSTRAINT IF EXISTS chk_orphan_no_meeting")
-    op.execute(
-        "ALTER TABLE recording DROP CONSTRAINT IF EXISTS chk_non_orphan_has_meeting"
-    )
-    op.execute("ALTER TABLE recording DROP CONSTRAINT IF EXISTS fk_recording_meeting")
-    op.drop_index("idx_instance_id", table_name="daily_recording_request")
-    op.drop_index("idx_meeting_id", table_name="daily_recording_request")
-    op.drop_table("daily_recording_request")

server/pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 dependencies = [
     "aiohttp>=3.9.0",
     "aiohttp-cors>=0.7.0",
-    "av>=15.0.0",
+    "av>=10.0.0",
     "requests>=2.31.0",
     "aiortc>=1.5.0",
     "sortedcontainers>=2.4.0",

server/reflector/dailyco_api/recording_orphans.py

@@ -1,56 +0,0 @@
-"""Utility for creating orphan recordings."""
-
-import os
-from datetime import datetime, timezone
-
-from reflector.db.recordings import Recording, recordings_controller
-from reflector.logger import logger
-from reflector.utils.string import NonEmptyString
-
-
-async def create_and_log_orphan(
-    recording_id: NonEmptyString,
-    bucket_name: str,
-    room_name: str,
-    start_ts: int,
-    track_keys: list[str] | None,
-    source: str,
-) -> bool:
-    """Create orphan recording and log if first occurrence.
-
-    Args:
-        recording_id: Daily.co recording ID
-        bucket_name: S3 bucket (empty string for cloud recordings)
-        room_name: Daily.co room name
-        start_ts: Unix timestamp
-        track_keys: Track keys for raw-tracks, None for cloud
-        source: "webhook" or "polling" for logging
-
-    Returns:
-        True if created (first poller), False if already exists
-    """
-    if track_keys:
-        object_key = os.path.dirname(track_keys[0]) if track_keys else room_name
-    else:
-        object_key = room_name
-
-    created = await recordings_controller.create_orphan(
-        Recording(
-            id=recording_id,
-            bucket_name=bucket_name,
-            object_key=object_key,
-            recorded_at=datetime.fromtimestamp(start_ts, tz=timezone.utc),
-            track_keys=track_keys,
-            meeting_id=None,
-            status="orphan",
-        )
-    )
-
-    if created:
-        logger.error(
-            f"Orphan recording ({source})",
-            recording_id=recording_id,
-            room_name=room_name,
-        )
-
-    return created

server/reflector/db/__init__.py

@@ -26,7 +26,6 @@ def get_database() -> databases.Database:
 # import models
 import reflector.db.calendar_events  # noqa
 import reflector.db.daily_participant_sessions  # noqa
-import reflector.db.daily_recording_requests  # noqa
 import reflector.db.meetings  # noqa
 import reflector.db.recordings  # noqa
 import reflector.db.rooms  # noqa

server/reflector/db/daily_recording_requests.py

@@ -1,111 +0,0 @@
-from datetime import datetime
-from typing import Literal
-from uuid import UUID
-
-import sqlalchemy as sa
-from pydantic import BaseModel
-from sqlalchemy.dialects.postgresql import insert
-
-from reflector.db import get_database, metadata
-from reflector.utils.string import NonEmptyString
-
-daily_recording_requests = sa.Table(
-    "daily_recording_request",
-    metadata,
-    sa.Column("recording_id", sa.String, primary_key=True),
-    sa.Column(
-        "meeting_id",
-        sa.String,
-        sa.ForeignKey("meeting.id", ondelete="CASCADE"),
-        nullable=False,
-    ),
-    sa.Column("instance_id", sa.String, nullable=False),
-    sa.Column("type", sa.String, nullable=False),
-    sa.Column("requested_at", sa.DateTime(timezone=True), nullable=False),
-    sa.Index("idx_meeting_id", "meeting_id"),
-    sa.Index("idx_instance_id", "instance_id"),
-)
-
-
-class DailyRecordingRequest(BaseModel):
-    recording_id: NonEmptyString
-    meeting_id: NonEmptyString
-    instance_id: UUID
-    type: Literal["cloud", "raw-tracks"]
-    requested_at: datetime
-
-
-class DailyRecordingRequestsController:
-    async def create(self, request: DailyRecordingRequest) -> None:
-        stmt = insert(daily_recording_requests).values(
-            recording_id=request.recording_id,
-            meeting_id=request.meeting_id,
-            instance_id=str(request.instance_id),
-            type=request.type,
-            requested_at=request.requested_at,
-        )
-        stmt = stmt.on_conflict_do_nothing(index_elements=["recording_id"])
-        await get_database().execute(stmt)
-
-    async def find_by_recording_id(
-        self,
-        recording_id: NonEmptyString,
-    ) -> tuple[NonEmptyString, Literal["cloud", "raw-tracks"]] | None:
-        query = daily_recording_requests.select().where(
-            daily_recording_requests.c.recording_id == recording_id
-        )
-        result = await get_database().fetch_one(query)
-
-        if not result:
-            return None
-
-        req = DailyRecordingRequest(
-            recording_id=result["recording_id"],
-            meeting_id=result["meeting_id"],
-            instance_id=UUID(result["instance_id"]),
-            type=result["type"],
-            requested_at=result["requested_at"],
-        )
-        return (req.meeting_id, req.type)
-
-    async def find_by_instance_id(
-        self,
-        instance_id: UUID,
-    ) -> list[DailyRecordingRequest]:
-        """Multiple recordings can have same instance_id (stop/restart)."""
-        query = daily_recording_requests.select().where(
-            daily_recording_requests.c.instance_id == str(instance_id)
-        )
-        results = await get_database().fetch_all(query)
-        return [
-            DailyRecordingRequest(
-                recording_id=r["recording_id"],
-                meeting_id=r["meeting_id"],
-                instance_id=UUID(r["instance_id"]),
-                type=r["type"],
-                requested_at=r["requested_at"],
-            )
-            for r in results
-        ]
-
-    async def get_by_meeting_id(
-        self,
-        meeting_id: NonEmptyString,
-    ) -> list[DailyRecordingRequest]:
-        query = daily_recording_requests.select().where(
-            daily_recording_requests.c.meeting_id == meeting_id
-        )
-        results = await get_database().fetch_all(query)
-        return [
-            DailyRecordingRequest(
-                recording_id=r["recording_id"],
-                meeting_id=r["meeting_id"],
-                instance_id=UUID(r["instance_id"]),
-                type=r["type"],
-                requested_at=r["requested_at"],
-            )
-            for r in results
-        ]
-
-
-daily_recording_requests_controller = DailyRecordingRequestsController()

server/reflector/db/meetings.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timedelta
 from typing import Any, Literal
 
 import sqlalchemy as sa
@@ -183,6 +183,84 @@ class MeetingController:
         results = await get_database().fetch_all(query)
         return [Meeting(**r) for r in results]
 
+    async def get_by_room_name_and_time(
+        self,
+        room_name: NonEmptyString,
+        recording_start: datetime,
+        time_window_hours: int = 168,
+    ) -> Meeting | None:
+        """
+        Get meeting by room name closest to recording timestamp.
+
+        HACK ALERT: Daily.co doesn't return instanceId in recordings API response,
+        and mtgSessionId is separate from our instanceId. Time-based matching is
+        the least-bad workaround.
+
+        This handles edge case of duplicate room_name values in DB (race conditions,
+        double-clicks, etc.) by matching based on temporal proximity.
+
+        Algorithm:
+        1. Find meetings within time_window_hours of recording_start
+        2. Return meeting with start_date closest to recording_start
+        3. If tie, return first by meeting.id (deterministic)
+
+        Args:
+            room_name: Daily.co room name from recording
+            recording_start: Timezone-aware datetime from recording.start_ts
+            time_window_hours: Search window (default 168 = 1 week)
+
+        Returns:
+            Meeting closest to recording timestamp, or None if no matches
+
+        Failure modes:
+        - Multiple meetings in same room within ~5 minutes: picks closest
+        - All meetings outside time window: returns None
+        - Clock skew between Daily.co and DB: 1-week window tolerates this
+
+        Why 1 week window:
+        - Handles webhook failures (recording discovered days later)
+        - Tolerates clock skew
+        - Rejects unrelated meetings from weeks ago
+
+        """
+        # Validate timezone-aware datetime
+        if recording_start.tzinfo is None:
+            raise ValueError(
+                f"recording_start must be timezone-aware, got naive datetime: {recording_start}"
+            )
+
+        window_start = recording_start - timedelta(hours=time_window_hours)
+        window_end = recording_start + timedelta(hours=time_window_hours)
+
+        query = (
+            meetings.select()
+            .where(
+                sa.and_(
+                    meetings.c.room_name == room_name,
+                    meetings.c.start_date >= window_start,
+                    meetings.c.start_date <= window_end,
+                )
+            )
+            .order_by(meetings.c.start_date)
+        )
+
+        results = await get_database().fetch_all(query)
+        if not results:
+            return None
+
+        candidates = [Meeting(**r) for r in results]
+
+        # Find meeting with start_date closest to recording_start
+        closest = min(
+            candidates,
+            key=lambda m: (
+                abs((m.start_date - recording_start).total_seconds()),
+                m.id,  # Tie-breaker: deterministic by UUID
+            ),
+        )
+
+        return closest
+
     async def get_active(self, room: Room, current_time: datetime) -> Meeting | None:
         """
         Get latest active meeting for a room.
@@ -272,6 +350,44 @@ class MeetingController:
         query = meetings.update().where(meetings.c.id == meeting_id).values(**kwargs)
         await get_database().execute(query)
 
+    async def set_cloud_recording_if_missing(
+        self,
+        meeting_id: NonEmptyString,
+        s3_key: NonEmptyString,
+        duration: int,
+    ) -> bool:
+        """
+        Set cloud recording only if not already set.
+
+        Returns True if updated, False if already set.
+        Prevents webhook/polling race condition via atomic WHERE clause.
+        """
+        # Check current value before update to detect actual change
+        meeting_before = await self.get_by_id(meeting_id)
+        if not meeting_before:
+            return False
+
+        was_null = meeting_before.daily_composed_video_s3_key is None
+
+        query = (
+            meetings.update()
+            .where(
+                sa.and_(
+                    meetings.c.id == meeting_id,
+                    meetings.c.daily_composed_video_s3_key.is_(None),
+                )
+            )
+            .values(
+                daily_composed_video_s3_key=s3_key,
+                daily_composed_video_duration=duration,
+            )
+        )
+        await get_database().execute(query)
+
+        # Return True only if value was NULL before (actual update occurred)
+        # If was_null=False, the WHERE clause prevented the update
+        return was_null
+
     async def increment_num_clients(self, meeting_id: str) -> None:
         """Atomically increment participant count."""
         query = (
@@ -351,27 +467,6 @@ class MeetingConsentController:
         result = await get_database().fetch_one(query)
         return result is not None
 
-    async def set_cloud_recording_if_missing(
-        self,
-        meeting_id: NonEmptyString,
-        s3_key: NonEmptyString,
-        duration: int,
-    ) -> bool:
-        """Returns True if updated, False if already set."""
-        query = (
-            meetings.update()
-            .where(
-                meetings.c.id == meeting_id,
-                meetings.c.daily_composed_video_s3_key.is_(None),
-            )
-            .values(
-                daily_composed_video_s3_key=s3_key,
-                daily_composed_video_duration=duration,
-            )
-        )
-        result = await get_database().execute(query)
-        return result.rowcount > 0
-
 
 meetings_controller = MeetingController()
 meeting_consent_controller = MeetingConsentController()

server/reflector/db/recordings.py

@@ -4,10 +4,10 @@ from typing import Literal
 import sqlalchemy as sa
 from pydantic import BaseModel, Field
 from sqlalchemy import or_
-from sqlalchemy.dialects.postgresql import insert
 
 from reflector.db import get_database, metadata
 from reflector.utils import generate_uuid4
+from reflector.utils.string import NonEmptyString
 
 recordings = sa.Table(
     "recording",
@@ -31,13 +31,14 @@ recordings = sa.Table(
 class Recording(BaseModel):
     id: str = Field(default_factory=generate_uuid4)
     bucket_name: str
+    # for single-track
     object_key: str
     recorded_at: datetime
-    status: Literal["pending", "processing", "completed", "failed", "orphan"] = (
+    status: Literal["pending", "processing", "completed", "failed"] = "pending"
-        "pending"
-    )
     meeting_id: str | None = None
-    # None = single-track, [] = multitrack with no audio, [keys...] = multitrack with audio
+    # for multitrack reprocessing
+    # track_keys can be empty list [] if recording finished but no audio was captured (silence/muted)
+    # None means not a multitrack recording, [] means multitrack with no tracks
     track_keys: list[str] | None = None
 
     @property
@@ -71,6 +72,20 @@ class RecordingController:
         query = recordings.delete().where(recordings.c.id == id)
         await get_database().execute(query)
 
+    async def set_meeting_id(
+        self,
+        recording_id: NonEmptyString,
+        meeting_id: NonEmptyString,
+    ) -> None:
+        """Link recording to meeting."""
+        query = (
+            recordings.update()
+            .where(recordings.c.id == recording_id)
+            .values(meeting_id=meeting_id)
+        )
+        await get_database().execute(query)
+
+    # no check for existence
     async def get_by_ids(self, recording_ids: list[str]) -> list[Recording]:
         if not recording_ids:
             return []
@@ -89,12 +104,9 @@ class RecordingController:
 
         This is more efficient than fetching all recordings and filtering in Python.
         """
-        # INLINE IMPORT REQUIRED: Circular dependency
+        from reflector.db.transcripts import (
-        # - recordings.py needs transcripts table for JOIN query
+            transcripts,  # noqa: PLC0415 cyclic import
-        # - transcripts.py imports recordings_controller
+        )
-        # - db/__init__.py loads recordings before transcripts (line 31 vs 33)
-        # - Top-level import would fail during module initialization
-        from reflector.db.transcripts import transcripts
 
         query = (
             recordings.select()
@@ -112,27 +124,5 @@ class RecordingController:
         recordings_list = [Recording(**row) for row in results]
         return [r for r in recordings_list if r.is_multitrack]
 
-    async def try_create_with_meeting(self, recording: Recording) -> bool:
-        """Returns True if created, False if already exists."""
-        assert recording.meeting_id is not None, "meeting_id required for non-orphan"
-        assert recording.status != "orphan", "use create_orphan for orphans"
-
-        stmt = insert(recordings).values(**recording.model_dump())
-        stmt = stmt.on_conflict_do_nothing(index_elements=["id"])
-        result = await get_database().execute(stmt)
-
-        return result.rowcount > 0
-
-    async def create_orphan(self, recording: Recording) -> bool:
-        """Returns True if created, False if already exists."""
-        assert recording.status == "orphan", "status must be 'orphan'"
-        assert recording.meeting_id is None, "meeting_id must be NULL for orphan"
-
-        stmt = insert(recordings).values(**recording.model_dump())
-        stmt = stmt.on_conflict_do_nothing(index_elements=["id"])
-        result = await get_database().execute(stmt)
-
-        return result.rowcount > 0
-
 
 recordings_controller = RecordingController()

server/reflector/hatchet/constants.py

@@ -8,7 +8,8 @@ from enum import StrEnum
 class TaskName(StrEnum):
     GET_RECORDING = "get_recording"
     GET_PARTICIPANTS = "get_participants"
-    PROCESS_TRACKS = "process_tracks"
+    PROCESS_PADDINGS = "process_paddings"
+    PROCESS_TRANSCRIPTIONS = "process_transcriptions"
     MIXDOWN_TRACKS = "mixdown_tracks"
     GENERATE_WAVEFORM = "generate_waveform"
     DETECT_TOPICS = "detect_topics"
@@ -35,9 +36,7 @@ LLM_RATE_LIMIT_PER_SECOND = 10
 
 # Task execution timeouts (seconds)
 TIMEOUT_SHORT = 60  # Quick operations: API calls, DB updates
-TIMEOUT_MEDIUM = (
+TIMEOUT_MEDIUM = 120  # Single LLM calls, waveform generation
-    300  # Single LLM calls, waveform generation (5m for slow LLM responses)
-)
 TIMEOUT_LONG = 180  # Action items (larger context LLM)
-TIMEOUT_AUDIO = 720  # Audio processing: padding, mixdown
+TIMEOUT_AUDIO = 300  # Audio processing: padding, mixdown
 TIMEOUT_HEAVY = 600  # Transcription, fan-out LLM tasks

server/reflector/hatchet/run_workers_cpu.py

@@ -1,9 +1,9 @@
 """
 CPU-heavy worker pool for audio processing tasks.
-Handles ONLY: mixdown_tracks
+Handles: mixdown_tracks only (serialized with max_runs=1)
 
 Configuration:
-- slots=1: Only mixdown (already serialized globally with max_runs=1)
+- slots=1: Only one mixdown at a time
 - Worker affinity: pool=cpu-heavy
 """
 
@@ -26,7 +26,7 @@ def main():
 
     cpu_worker = hatchet.worker(
         "cpu-worker-pool",
-        slots=1,  # Only 1 mixdown at a time (already serialized globally)
+        slots=1,
         labels={
             "pool": "cpu-heavy",
         },

server/reflector/hatchet/run_workers_llm.py

@@ -1,15 +1,16 @@
 """
 LLM/I/O worker pool for all non-CPU tasks.
-Handles: all tasks except mixdown_tracks (transcription, LLM inference, orchestration)
+Handles: all tasks except mixdown_tracks (padding, transcription, LLM inference, orchestration)
 """
 
 from reflector.hatchet.client import HatchetClientManager
 from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     daily_multitrack_pipeline,
 )
+from reflector.hatchet.workflows.padding_workflow import padding_workflow
 from reflector.hatchet.workflows.subject_processing import subject_workflow
 from reflector.hatchet.workflows.topic_chunk_processing import topic_chunk_workflow
-from reflector.hatchet.workflows.track_processing import track_workflow
+from reflector.hatchet.workflows.transcription_workflow import transcription_workflow
 from reflector.logger import logger
 
 SLOTS = 10
@@ -29,7 +30,7 @@ def main():
 
     llm_worker = hatchet.worker(
         WORKER_NAME,
-        slots=SLOTS,  # not all slots are probably used
+        slots=SLOTS,
         labels={
             "pool": POOL,
         },
@@ -37,7 +38,8 @@ def main():
             daily_multitrack_pipeline,
             topic_chunk_workflow,
             subject_workflow,
-            track_workflow,
+            padding_workflow,
+            transcription_workflow,
         ],
     )
 

server/reflector/hatchet/workflows/__init__.py

@@ -4,6 +4,10 @@ from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     PipelineInput,
     daily_multitrack_pipeline,
 )
+from reflector.hatchet.workflows.padding_workflow import (
+    PaddingInput,
+    padding_workflow,
+)
 from reflector.hatchet.workflows.subject_processing import (
     SubjectInput,
     subject_workflow,
@@ -12,15 +16,20 @@ from reflector.hatchet.workflows.topic_chunk_processing import (
     TopicChunkInput,
     topic_chunk_workflow,
 )
-from reflector.hatchet.workflows.track_processing import TrackInput, track_workflow
+from reflector.hatchet.workflows.transcription_workflow import (
+    TranscriptionInput,
+    transcription_workflow,
+)
 
 __all__ = [
     "daily_multitrack_pipeline",
     "subject_workflow",
     "topic_chunk_workflow",
-    "track_workflow",
+    "padding_workflow",
+    "transcription_workflow",
     "PipelineInput",
     "SubjectInput",
     "TopicChunkInput",
-    "TrackInput",
+    "PaddingInput",
+    "TranscriptionInput",
 ]

server/reflector/hatchet/workflows/daily_multitrack_pipeline.py

@@ -54,8 +54,9 @@ from reflector.hatchet.workflows.models import (
     PadTrackResult,
     ParticipantInfo,
     ParticipantsResult,
+    ProcessPaddingsResult,
     ProcessSubjectsResult,
-    ProcessTracksResult,
+    ProcessTranscriptionsResult,
     RecapResult,
     RecordingResult,
     SubjectsResult,
@@ -68,6 +69,7 @@ from reflector.hatchet.workflows.models import (
     WebhookResult,
     ZulipResult,
 )
+from reflector.hatchet.workflows.padding_workflow import PaddingInput, padding_workflow
 from reflector.hatchet.workflows.subject_processing import (
     SubjectInput,
     subject_workflow,
@@ -76,7 +78,10 @@ from reflector.hatchet.workflows.topic_chunk_processing import (
     TopicChunkInput,
     topic_chunk_workflow,
 )
-from reflector.hatchet.workflows.track_processing import TrackInput, track_workflow
+from reflector.hatchet.workflows.transcription_workflow import (
+    TranscriptionInput,
+    transcription_workflow,
+)
 from reflector.logger import logger
 from reflector.pipelines import topic_processing
 from reflector.processors import AudioFileWriterProcessor
@@ -322,7 +327,6 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
     mtg_session_id = recording.mtg_session_id
     async with fresh_db_connection():
         from reflector.db.transcripts import (  # noqa: PLC0415
-            TranscriptDuration,
             TranscriptParticipant,
             transcripts_controller,
         )
@@ -331,26 +335,15 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
         if not transcript:
             raise ValueError(f"Transcript {input.transcript_id} not found")
         # Note: title NOT cleared - preserves existing titles
-        # Duration from Daily API (seconds -> milliseconds) - master source
-        duration_ms = recording.duration * 1000 if recording.duration else 0
         await transcripts_controller.update(
             transcript,
             {
                 "events": [],
                 "topics": [],
                 "participants": [],
-                "duration": duration_ms,
             },
         )
 
-        await append_event_and_broadcast(
-            input.transcript_id,
-            transcript,
-            "DURATION",
-            TranscriptDuration(duration=duration_ms),
-            logger=logger,
-        )
-
         mtg_session_id = assert_non_none_and_non_empty(
             mtg_session_id, "mtg_session_id is required"
         )
@@ -416,72 +409,115 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
     execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
     retries=3,
 )
-@with_error_handling(TaskName.PROCESS_TRACKS)
+@with_error_handling(TaskName.PROCESS_PADDINGS)
-async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksResult:
+async def process_paddings(input: PipelineInput, ctx: Context) -> ProcessPaddingsResult:
-    """Spawn child workflows for each track (dynamic fan-out)."""
+    """Spawn child workflows for each track to apply padding (dynamic fan-out)."""
-    ctx.log(f"process_tracks: spawning {len(input.tracks)} track workflows")
+    ctx.log(f"process_paddings: spawning {len(input.tracks)} padding workflows")
-
-    participants_result = ctx.task_output(get_participants)
-    source_language = participants_result.source_language
 
     bulk_runs = [
-        track_workflow.create_bulk_run_item(
+        padding_workflow.create_bulk_run_item(
-            input=TrackInput(
+            input=PaddingInput(
                 track_index=i,
                 s3_key=track["s3_key"],
                 bucket_name=input.bucket_name,
                 transcript_id=input.transcript_id,
-                language=source_language,
             )
         )
         for i, track in enumerate(input.tracks)
     ]
 
-    results = await track_workflow.aio_run_many(bulk_runs)
+    results = await padding_workflow.aio_run_many(bulk_runs)
 
-    target_language = participants_result.target_language
-
-    track_words: list[list[Word]] = []
     padded_tracks = []
-    created_padded_files = set()
+    created_padded_files = []
 
     for result in results:
-        transcribe_result = TranscribeTrackResult(**result[TaskName.TRANSCRIBE_TRACK])
-        track_words.append(transcribe_result.words)
-
         pad_result = PadTrackResult(**result[TaskName.PAD_TRACK])
 
-        # Store S3 key info (not presigned URL) - consumer tasks presign on demand
+        padded_tracks.append(
-        if pad_result.padded_key:
+            PaddedTrackInfo(
-            padded_tracks.append(
+                key=pad_result.padded_key,
-                PaddedTrackInfo(
+                bucket_name=pad_result.bucket_name,
-                    key=pad_result.padded_key, bucket_name=pad_result.bucket_name
+                track_index=pad_result.track_index,
-                )
             )
+        )
 
         if pad_result.size > 0:
             storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{pad_result.track_index}.webm"
-            created_padded_files.add(storage_path)
+            created_padded_files.append(storage_path)
 
-    all_words = [word for words in track_words for word in words]
+    ctx.log(f"process_paddings complete: {len(padded_tracks)} padded tracks")
-    all_words.sort(key=lambda w: w.start)
 
-    ctx.log(
+    return ProcessPaddingsResult(
-        f"process_tracks complete: {len(all_words)} words from {len(input.tracks)} tracks"
-    )
-
-    return ProcessTracksResult(
-        all_words=all_words,
         padded_tracks=padded_tracks,
-        word_count=len(all_words),
         num_tracks=len(input.tracks),
-        target_language=target_language,
         created_padded_files=list(created_padded_files),
     )
 
 
 @daily_multitrack_pipeline.task(
-    parents=[process_tracks],
+    parents=[process_paddings],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+)
+@with_error_handling(TaskName.PROCESS_TRANSCRIPTIONS)
+async def process_transcriptions(
+    input: PipelineInput, ctx: Context
+) -> ProcessTranscriptionsResult:
+    """Spawn child workflows for each padded track to transcribe (dynamic fan-out)."""
+    participants_result = ctx.task_output(get_participants)
+    paddings_result = ctx.task_output(process_paddings)
+
+    source_language = participants_result.source_language
+    if not source_language:
+        raise ValueError("source_language is required for transcription")
+
+    target_language = participants_result.target_language
+    padded_tracks = paddings_result.padded_tracks
+
+    if not padded_tracks:
+        raise ValueError("No padded tracks available for transcription")
+
+    ctx.log(
+        f"process_transcriptions: spawning {len(padded_tracks)} transcription workflows"
+    )
+
+    bulk_runs = [
+        transcription_workflow.create_bulk_run_item(
+            input=TranscriptionInput(
+                track_index=padded_track.track_index,
+                padded_key=padded_track.key,
+                bucket_name=padded_track.bucket_name,
+                language=source_language,
+            )
+        )
+        for padded_track in padded_tracks
+    ]
+
+    results = await transcription_workflow.aio_run_many(bulk_runs)
+
+    track_words: list[list[Word]] = []
+    for result in results:
+        transcribe_result = TranscribeTrackResult(**result[TaskName.TRANSCRIBE_TRACK])
+        track_words.append(transcribe_result.words)
+
+    all_words = [word for words in track_words for word in words]
+    all_words.sort(key=lambda w: w.start)
+
+    ctx.log(
+        f"process_transcriptions complete: {len(all_words)} words from {len(padded_tracks)} tracks"
+    )
+
+    return ProcessTranscriptionsResult(
+        all_words=all_words,
+        word_count=len(all_words),
+        num_tracks=len(input.tracks),
+        target_language=target_language,
+    )
+
+
+@daily_multitrack_pipeline.task(
+    parents=[process_paddings],
     execution_timeout=timedelta(seconds=TIMEOUT_AUDIO),
     retries=3,
     desired_worker_labels={
@@ -501,12 +537,12 @@ async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksRes
 )
 @with_error_handling(TaskName.MIXDOWN_TRACKS)
 async def mixdown_tracks(input: PipelineInput, ctx: Context) -> MixdownResult:
-    """Mix all padded tracks into single audio file using PyAV (same as Celery)."""
+    """Mix all padded tracks into single audio file using PyAV."""
     ctx.log("mixdown_tracks: mixing padded tracks into single audio file")
 
-    track_result = ctx.task_output(process_tracks)
+    paddings_result = ctx.task_output(process_paddings)
     recording_result = ctx.task_output(get_recording)
-    padded_tracks = track_result.padded_tracks
+    padded_tracks = paddings_result.padded_tracks
 
     # Dynamic timeout: scales with track count and recording duration
     # Base 300s + 60s per track + 1s per 10s of recording
@@ -660,7 +696,7 @@ async def generate_waveform(input: PipelineInput, ctx: Context) -> WaveformResul
 
 
 @daily_multitrack_pipeline.task(
-    parents=[process_tracks],
+    parents=[process_transcriptions],
     execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
     retries=3,
 )
@@ -669,8 +705,8 @@ async def detect_topics(input: PipelineInput, ctx: Context) -> TopicsResult:
     """Detect topics using parallel child workflows (one per chunk)."""
     ctx.log("detect_topics: analyzing transcript for topics")
 
-    track_result = ctx.task_output(process_tracks)
+    transcriptions_result = ctx.task_output(process_transcriptions)
-    words = track_result.all_words
+    words = transcriptions_result.all_words
 
     if not words:
         ctx.log("detect_topics: no words, returning empty topics")
@@ -1107,7 +1143,7 @@ async def identify_action_items(
 
 
 @daily_multitrack_pipeline.task(
-    parents=[process_tracks, generate_title, generate_recap, identify_action_items],
+    parents=[generate_title, generate_recap, identify_action_items],
     execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
     retries=3,
 )
@@ -1120,10 +1156,15 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
     """
     ctx.log("finalize: saving transcript and setting status to 'ended'")
 
-    track_result = ctx.task_output(process_tracks)
+    mixdown_result = ctx.task_output(mixdown_tracks)
+    transcriptions_result = ctx.task_output(process_transcriptions)
+    paddings_result = ctx.task_output(process_paddings)
+
+    duration = mixdown_result.duration
+    all_words = transcriptions_result.all_words
 
     # Cleanup temporary padded S3 files (deferred until finalize for semantic parity with Celery)
-    created_padded_files = track_result.created_padded_files
+    created_padded_files = paddings_result.created_padded_files
     if created_padded_files:
         ctx.log(f"Cleaning up {len(created_padded_files)} temporary S3 files")
         storage = _spawn_storage()
@@ -1141,6 +1182,7 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
 
     async with fresh_db_connection():
         from reflector.db.transcripts import (  # noqa: PLC0415
+            TranscriptDuration,
             TranscriptText,
             transcripts_controller,
         )
@@ -1149,6 +1191,8 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
         if transcript is None:
             raise ValueError(f"Transcript {input.transcript_id} not found in database")
 
+        merged_transcript = TranscriptType(words=all_words, translation=None)
+
         await append_event_and_broadcast(
             input.transcript_id,
             transcript,
@@ -1160,15 +1204,21 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
             logger=logger,
         )
 
-        # Clear workflow_run_id (workflow completed successfully)
+        # Save duration and clear workflow_run_id (workflow completed successfully)
-        # Note: title/long_summary/short_summary/duration already saved by their callbacks
+        # Note: title/long_summary/short_summary already saved by their callbacks
         await transcripts_controller.update(
             transcript,
             {
+                "duration": duration,
                 "workflow_run_id": None,  # Clear on success - no need to resume
             },
         )
 
+        duration_data = TranscriptDuration(duration=duration)
+        await append_event_and_broadcast(
+            input.transcript_id, transcript, "DURATION", duration_data, logger=logger
+        )
+
         await set_status_and_broadcast(input.transcript_id, "ended", logger=logger)
 
         ctx.log(

server/reflector/hatchet/workflows/models.py

@@ -21,12 +21,14 @@ class ParticipantInfo(BaseModel):
 
 
 class PadTrackResult(BaseModel):
-    """Result from pad_track task."""
+    """Result from pad_track task.
 
-    padded_key: NonEmptyString  # S3 key (not presigned URL) - presign on demand to avoid stale URLs on replay
+    If size=0, track required no padding and padded_key contains original S3 key.
-    bucket_name: (
+    If size>0, track was padded and padded_key contains new padded file S3 key.
-        NonEmptyString | None
+    """
-    )  # None means use default transcript storage bucket
+
+    padded_key: NonEmptyString
+    bucket_name: NonEmptyString | None
     size: int
     track_index: int
 
@@ -59,18 +61,25 @@ class PaddedTrackInfo(BaseModel):
     """Info for a padded track - S3 key + bucket for on-demand presigning."""
 
     key: NonEmptyString
-    bucket_name: NonEmptyString | None  # None = use default storage bucket
+    bucket_name: NonEmptyString | None
+    track_index: int
 
 
-class ProcessTracksResult(BaseModel):
+class ProcessPaddingsResult(BaseModel):
-    """Result from process_tracks task."""
+    """Result from process_paddings task."""
+
+    padded_tracks: list[PaddedTrackInfo]
+    num_tracks: int
+    created_padded_files: list[NonEmptyString]
+
+
+class ProcessTranscriptionsResult(BaseModel):
+    """Result from process_transcriptions task."""
 
     all_words: list[Word]
-    padded_tracks: list[PaddedTrackInfo]  # S3 keys, not presigned URLs
     word_count: int
     num_tracks: int
     target_language: NonEmptyString
-    created_padded_files: list[NonEmptyString]
 
 
 class MixdownResult(BaseModel):

server/reflector/hatchet/workflows/padding_workflow.py

@@ -1,9 +1,11 @@
 """
 Hatchet child workflow: PaddingWorkflow
-Handles individual audio track padding via Modal.com backend.
+Handles individual audio track padding only.
 """
 
+import tempfile
 from datetime import timedelta
+from pathlib import Path
 
 import av
 from hatchet_sdk import Context
@@ -14,7 +16,10 @@ from reflector.hatchet.constants import TIMEOUT_AUDIO
 from reflector.hatchet.workflows.models import PadTrackResult
 from reflector.logger import logger
 from reflector.utils.audio_constants import PRESIGNED_URL_EXPIRATION_SECONDS
-from reflector.utils.audio_padding import extract_stream_start_time_from_container
+from reflector.utils.audio_padding import (
+    apply_audio_padding_to_file,
+    extract_stream_start_time_from_container,
+)
 
 
 class PaddingInput(BaseModel):
@@ -63,83 +68,61 @@ async def pad_track(input: PaddingInput, ctx: Context) -> PadTrackResult:
             bucket=input.bucket_name,
         )
 
-        # Extract start_time to determine if padding needed
         with av.open(source_url) as in_container:
-            if in_container.duration:
+            with av.open(source_url) as in_container:
-                try:
+                if in_container.duration:
-                    duration = timedelta(seconds=in_container.duration // 1_000_000)
+                    try:
-                    ctx.log(
+                        duration = timedelta(seconds=in_container.duration // 1_000_000)
-                        f"pad_track: track {input.track_index}, duration={duration}"
+                        ctx.log(
-                    )
+                            f"pad_track: track {input.track_index}, duration={duration}"
-                except (ValueError, TypeError, OverflowError) as e:
+                        )
-                    ctx.log(
+                    except (ValueError, TypeError, OverflowError) as e:
-                        f"pad_track: track {input.track_index}, duration error: {str(e)}"
+                        ctx.log(
-                    )
+                            f"pad_track: track {input.track_index}, duration error: {str(e)}"
+                        )
 
             start_time_seconds = extract_stream_start_time_from_container(
                 in_container, input.track_index, logger=logger
             )
 
-        if start_time_seconds <= 0:
+            if start_time_seconds <= 0:
-            logger.info(
+                logger.info(
-                f"Track {input.track_index} requires no padding",
+                    f"Track {input.track_index} requires no padding",
-                track_index=input.track_index,
+                    track_index=input.track_index,
-            )
+                )
-            return PadTrackResult(
+                return PadTrackResult(
-                padded_key=input.s3_key,
+                    padded_key=input.s3_key,
-                bucket_name=input.bucket_name,
+                    bucket_name=input.bucket_name,
-                size=0,
+                    size=0,
-                track_index=input.track_index,
+                    track_index=input.track_index,
-            )
+                )
 
-        storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
+            storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
 
-        # Presign PUT URL for output (Modal will upload directly)
+            with tempfile.NamedTemporaryFile(suffix=".webm", delete=False) as temp_file:
-        output_url = await storage.get_file_url(
+                temp_path = temp_file.name
-            storage_path,
-            operation="put_object",
-            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-        )
 
-        import httpx  # noqa: PLC0415
+            try:
+                apply_audio_padding_to_file(
+                    in_container,
+                    temp_path,
+                    start_time_seconds,
+                    input.track_index,
+                    logger=logger,
+                )
 
-        from reflector.processors.audio_padding_modal import (  # noqa: PLC0415
+                file_size = Path(temp_path).stat().st_size
-            AudioPaddingModalProcessor,
-        )
 
-        try:
+                with open(temp_path, "rb") as padded_file:
-            processor = AudioPaddingModalProcessor()
+                    await storage.put_file(storage_path, padded_file)
-            result = await processor.pad_track(
-                track_url=source_url,
-                output_url=output_url,
-                start_time_seconds=start_time_seconds,
-                track_index=input.track_index,
-            )
-            file_size = result.size
 
-            ctx.log(f"pad_track: Modal returned size={file_size}")
+                logger.info(
-        except httpx.HTTPStatusError as e:
+                    f"Uploaded padded track to S3",
-            error_detail = e.response.text if hasattr(e.response, "text") else str(e)
+                    key=storage_path,
-            logger.error(
+                    size=file_size,
-                "[Hatchet] Modal padding HTTP error",
+                )
-                transcript_id=input.transcript_id,
+            finally:
-                track_index=input.track_index,
+                Path(temp_path).unlink(missing_ok=True)
-                status_code=e.response.status_code if hasattr(e, "response") else None,
-                error=error_detail,
-                exc_info=True,
-            )
-            raise Exception(
-                f"Modal padding failed: HTTP {e.response.status_code}"
-            ) from e
-        except httpx.TimeoutException as e:
-            logger.error(
-                "[Hatchet] Modal padding timeout",
-                transcript_id=input.transcript_id,
-                track_index=input.track_index,
-                error=str(e),
-                exc_info=True,
-            )
-            raise Exception("Modal padding timeout") from e
 
         logger.info(
             "[Hatchet] pad_track complete",

server/reflector/hatchet/workflows/track_processing.py

@@ -1,205 +0,0 @@
-"""
-Hatchet child workflow: TrackProcessing
-
-Handles individual audio track processing: padding and transcription.
-Spawned dynamically by the main diarization pipeline for each track.
-
-Architecture note: This is a separate workflow (not inline tasks in DailyMultitrackPipeline)
-because Hatchet workflow DAGs are defined statically, but the number of tracks varies
-at runtime. Child workflow spawning via `aio_run()` + `asyncio.gather()` is the
-standard pattern for dynamic fan-out. See `process_tracks` in daily_multitrack_pipeline.py.
-
-Note: This file uses deferred imports (inside tasks) intentionally.
-Hatchet workers run in forked processes; fresh imports per task ensure
-storage/DB connections are not shared across forks.
-"""
-
-from datetime import timedelta
-
-import av
-from hatchet_sdk import Context
-from pydantic import BaseModel
-
-from reflector.hatchet.client import HatchetClientManager
-from reflector.hatchet.constants import TIMEOUT_AUDIO, TIMEOUT_HEAVY
-from reflector.hatchet.workflows.models import PadTrackResult, TranscribeTrackResult
-from reflector.logger import logger
-from reflector.utils.audio_constants import PRESIGNED_URL_EXPIRATION_SECONDS
-from reflector.utils.audio_padding import extract_stream_start_time_from_container
-
-
-class TrackInput(BaseModel):
-    """Input for individual track processing."""
-
-    track_index: int
-    s3_key: str
-    bucket_name: str
-    transcript_id: str
-    language: str = "en"
-
-
-hatchet = HatchetClientManager.get_client()
-
-track_workflow = hatchet.workflow(name="TrackProcessing", input_validator=TrackInput)
-
-
-@track_workflow.task(execution_timeout=timedelta(seconds=TIMEOUT_AUDIO), retries=3)
-async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
-    """Pad single audio track with silence for alignment.
-
-    Extracts stream.start_time from WebM container metadata and applies
-    silence padding using PyAV filter graph (adelay).
-    """
-    ctx.log(f"pad_track: track {input.track_index}, s3_key={input.s3_key}")
-    logger.info(
-        "[Hatchet] pad_track",
-        track_index=input.track_index,
-        s3_key=input.s3_key,
-        transcript_id=input.transcript_id,
-    )
-
-    try:
-        # Create fresh storage instance to avoid aioboto3 fork issues
-        from reflector.settings import settings  # noqa: PLC0415
-        from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
-
-        storage = AwsStorage(
-            aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
-            aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
-            aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
-            aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
-        )
-
-        source_url = await storage.get_file_url(
-            input.s3_key,
-            operation="get_object",
-            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-            bucket=input.bucket_name,
-        )
-
-        with av.open(source_url) as in_container:
-            start_time_seconds = extract_stream_start_time_from_container(
-                in_container, input.track_index, logger=logger
-            )
-
-        # If no padding needed, return original S3 key
-        if start_time_seconds <= 0:
-            logger.info(
-                f"Track {input.track_index} requires no padding",
-                track_index=input.track_index,
-            )
-            return PadTrackResult(
-                padded_key=input.s3_key,
-                bucket_name=input.bucket_name,
-                size=0,
-                track_index=input.track_index,
-            )
-
-        storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
-
-        # Presign PUT URL for output (Modal uploads directly)
-        output_url = await storage.get_file_url(
-            storage_path,
-            operation="put_object",
-            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-        )
-
-        from reflector.processors.audio_padding_modal import (  # noqa: PLC0415
-            AudioPaddingModalProcessor,
-        )
-
-        processor = AudioPaddingModalProcessor()
-        result = await processor.pad_track(
-            track_url=source_url,
-            output_url=output_url,
-            start_time_seconds=start_time_seconds,
-            track_index=input.track_index,
-        )
-        file_size = result.size
-
-        ctx.log(f"pad_track complete: track {input.track_index} -> {storage_path}")
-        logger.info(
-            "[Hatchet] pad_track complete",
-            track_index=input.track_index,
-            padded_key=storage_path,
-        )
-
-        # Return S3 key (not presigned URL) - consumer tasks presign on demand
-        # This avoids stale URLs when workflow is replayed
-        return PadTrackResult(
-            padded_key=storage_path,
-            bucket_name=None,  # None = use default transcript storage bucket
-            size=file_size,
-            track_index=input.track_index,
-        )
-
-    except Exception as e:
-        logger.error("[Hatchet] pad_track failed", error=str(e), exc_info=True)
-        raise
-
-
-@track_workflow.task(
-    parents=[pad_track], execution_timeout=timedelta(seconds=TIMEOUT_HEAVY), retries=3
-)
-async def transcribe_track(input: TrackInput, ctx: Context) -> TranscribeTrackResult:
-    """Transcribe audio track using GPU (Modal.com) or local Whisper."""
-    ctx.log(f"transcribe_track: track {input.track_index}, language={input.language}")
-    logger.info(
-        "[Hatchet] transcribe_track",
-        track_index=input.track_index,
-        language=input.language,
-    )
-
-    try:
-        pad_result = ctx.task_output(pad_track)
-        padded_key = pad_result.padded_key
-        bucket_name = pad_result.bucket_name
-
-        if not padded_key:
-            raise ValueError("Missing padded_key from pad_track")
-
-        # Presign URL on demand (avoids stale URLs on workflow replay)
-        from reflector.settings import settings  # noqa: PLC0415
-        from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
-
-        storage = AwsStorage(
-            aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
-            aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
-            aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
-            aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
-        )
-
-        audio_url = await storage.get_file_url(
-            padded_key,
-            operation="get_object",
-            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-            bucket=bucket_name,
-        )
-
-        from reflector.pipelines.transcription_helpers import (  # noqa: PLC0415
-            transcribe_file_with_processor,
-        )
-
-        transcript = await transcribe_file_with_processor(audio_url, input.language)
-
-        # Tag all words with speaker index
-        for word in transcript.words:
-            word.speaker = input.track_index
-
-        ctx.log(
-            f"transcribe_track complete: track {input.track_index}, {len(transcript.words)} words"
-        )
-        logger.info(
-            "[Hatchet] transcribe_track complete",
-            track_index=input.track_index,
-            word_count=len(transcript.words),
-        )
-
-        return TranscribeTrackResult(
-            words=transcript.words,
-            track_index=input.track_index,
-        )
-
-    except Exception as e:
-        logger.error("[Hatchet] transcribe_track failed", error=str(e), exc_info=True)
-        raise

server/reflector/hatchet/workflows/transcription_workflow.py

@@ -0,0 +1,98 @@
+"""
+Hatchet child workflow: TranscriptionWorkflow
+Handles individual audio track transcription only.
+"""
+
+from datetime import timedelta
+
+from hatchet_sdk import Context
+from pydantic import BaseModel
+
+from reflector.hatchet.client import HatchetClientManager
+from reflector.hatchet.constants import TIMEOUT_HEAVY
+from reflector.hatchet.workflows.models import TranscribeTrackResult
+from reflector.logger import logger
+from reflector.utils.audio_constants import PRESIGNED_URL_EXPIRATION_SECONDS
+
+
+class TranscriptionInput(BaseModel):
+    """Input for individual track transcription."""
+
+    track_index: int
+    padded_key: str  # S3 key from padding step
+    bucket_name: str | None  # None = use default bucket
+    language: str = "en"
+
+
+hatchet = HatchetClientManager.get_client()
+
+transcription_workflow = hatchet.workflow(
+    name="TranscriptionWorkflow", input_validator=TranscriptionInput
+)
+
+
+@transcription_workflow.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY), retries=3
+)
+async def transcribe_track(
+    input: TranscriptionInput, ctx: Context
+) -> TranscribeTrackResult:
+    """Transcribe audio track using GPU (Modal.com) or local Whisper."""
+    ctx.log(f"transcribe_track: track {input.track_index}, language={input.language}")
+    logger.info(
+        "[Hatchet] transcribe_track",
+        track_index=input.track_index,
+        language=input.language,
+    )
+
+    try:
+        from reflector.settings import settings  # noqa: PLC0415
+        from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
+
+        storage = AwsStorage(
+            aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
+            aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
+            aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
+            aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
+        )
+
+        audio_url = await storage.get_file_url(
+            input.padded_key,
+            operation="get_object",
+            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
+            bucket=input.bucket_name,
+        )
+
+        from reflector.pipelines.transcription_helpers import (  # noqa: PLC0415
+            transcribe_file_with_processor,
+        )
+
+        transcript = await transcribe_file_with_processor(audio_url, input.language)
+
+        for word in transcript.words:
+            word.speaker = input.track_index
+
+        ctx.log(
+            f"transcribe_track complete: track {input.track_index}, {len(transcript.words)} words"
+        )
+        logger.info(
+            "[Hatchet] transcribe_track complete",
+            track_index=input.track_index,
+            word_count=len(transcript.words),
+        )
+
+        return TranscribeTrackResult(
+            words=transcript.words,
+            track_index=input.track_index,
+        )
+
+    except Exception as e:
+        logger.error(
+            "[Hatchet] transcribe_track failed",
+            track_index=input.track_index,
+            padded_key=input.padded_key,
+            language=input.language,
+            error=str(e),
+            exc_info=True,
+        )
+        raise

server/reflector/processors/audio_padding_modal.py

@@ -1,113 +0,0 @@
-"""
-Modal.com backend for audio padding.
-"""
-
-import asyncio
-import os
-
-import httpx
-from pydantic import BaseModel
-
-from reflector.hatchet.constants import TIMEOUT_AUDIO
-from reflector.logger import logger
-
-
-class PaddingResponse(BaseModel):
-    size: int
-    cancelled: bool = False
-
-
-class AudioPaddingModalProcessor:
-    """Audio padding processor using Modal.com CPU backend via HTTP."""
-
-    def __init__(
-        self, padding_url: str | None = None, modal_api_key: str | None = None
-    ):
-        self.padding_url = padding_url or os.getenv("PADDING_URL")
-        if not self.padding_url:
-            raise ValueError(
-                "PADDING_URL required to use AudioPaddingModalProcessor. "
-                "Set PADDING_URL environment variable or pass padding_url parameter."
-            )
-
-        self.modal_api_key = modal_api_key or os.getenv("MODAL_API_KEY")
-
-    async def pad_track(
-        self,
-        track_url: str,
-        output_url: str,
-        start_time_seconds: float,
-        track_index: int,
-    ) -> PaddingResponse:
-        """Pad audio track with silence via Modal backend.
-
-        Args:
-            track_url: Presigned GET URL for source audio track
-            output_url: Presigned PUT URL for output WebM
-            start_time_seconds: Amount of silence to prepend
-            track_index: Track index for logging
-        """
-        if not track_url:
-            raise ValueError("track_url cannot be empty")
-        if start_time_seconds <= 0:
-            raise ValueError(
-                f"start_time_seconds must be positive, got {start_time_seconds}"
-            )
-
-        log = logger.bind(track_index=track_index, padding_seconds=start_time_seconds)
-        log.info("Sending Modal padding HTTP request")
-
-        url = f"{self.padding_url}/pad"
-
-        headers = {}
-        if self.modal_api_key:
-            headers["Authorization"] = f"Bearer {self.modal_api_key}"
-
-        try:
-            async with httpx.AsyncClient(timeout=TIMEOUT_AUDIO) as client:
-                response = await client.post(
-                    url,
-                    headers=headers,
-                    json={
-                        "track_url": track_url,
-                        "output_url": output_url,
-                        "start_time_seconds": start_time_seconds,
-                        "track_index": track_index,
-                    },
-                    follow_redirects=True,
-                )
-
-                if response.status_code != 200:
-                    error_body = response.text
-                    log.error(
-                        "Modal padding API error",
-                        status_code=response.status_code,
-                        error_body=error_body,
-                    )
-
-                response.raise_for_status()
-                result = response.json()
-
-            # Check if work was cancelled
-            if result.get("cancelled"):
-                log.warning("Modal padding was cancelled by disconnect detection")
-                raise asyncio.CancelledError(
-                    "Padding cancelled due to client disconnect"
-                )
-
-            log.info("Modal padding complete", size=result["size"])
-            return PaddingResponse(**result)
-        except asyncio.CancelledError:
-            log.warning(
-                "Modal padding cancelled (Hatchet timeout, disconnect detected on Modal side)"
-            )
-            raise
-        except httpx.TimeoutException as e:
-            log.error("Modal padding timeout", error=str(e), exc_info=True)
-            raise Exception(f"Modal padding timeout: {e}") from e
-        except httpx.HTTPStatusError as e:
-            log.error("Modal padding HTTP error", error=str(e), exc_info=True)
-            raise Exception(f"Modal padding HTTP error: {e}") from e
-        except Exception as e:
-            log.error("Modal padding unexpected error", error=str(e), exc_info=True)
-            raise

server/reflector/settings.py

@@ -98,10 +98,6 @@ class Settings(BaseSettings):
     # Diarization: local pyannote.audio
     DIARIZATION_PYANNOTE_AUTH_TOKEN: str | None = None
 
-    # Audio Padding (Modal.com backend)
-    PADDING_URL: str | None = None
-    PADDING_MODAL_API_KEY: str | None = None
-
     # Sentry
     SENTRY_DSN: str | None = None
 

server/reflector/utils/audio_constants.py

@@ -5,9 +5,7 @@ Used by both Hatchet workflows and Celery pipelines for consistent audio encodin
 """
 
 # Opus codec settings
-# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
 OPUS_STANDARD_SAMPLE_RATE = 48000
-# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
 OPUS_DEFAULT_BIT_RATE = 128000  # 128kbps for good speech quality
 
 # S3 presigned URL expiration

server/reflector/views/daily.py

@@ -1,6 +1,4 @@
 import json
-import os
-from datetime import datetime, timezone
 from typing import assert_never
 
 from fastapi import APIRouter, HTTPException, Request
@@ -14,10 +12,7 @@ from reflector.dailyco_api import (
     RecordingReadyEvent,
     RecordingStartedEvent,
 )
-from reflector.dailyco_api.recording_orphans import create_and_log_orphan
-from reflector.db.daily_recording_requests import daily_recording_requests_controller
 from reflector.db.meetings import meetings_controller
-from reflector.db.recordings import Recording, recordings_controller
 from reflector.logger import logger as _logger
 from reflector.settings import settings
 from reflector.video_platforms.factory import create_platform_client
@@ -217,73 +212,10 @@ async def _handle_recording_ready(event: RecordingReadyEvent):
 
         track_keys = [t.s3Key for t in tracks if t.type == "audio"]
 
-        # Lookup request
-        match = await daily_recording_requests_controller.find_by_recording_id(
-            recording_id
-        )
-
-        if not match:
-            await create_and_log_orphan(
-                recording_id=recording_id,
-                bucket_name=bucket_name,
-                room_name=room_name,
-                start_ts=event.payload.start_ts,
-                track_keys=track_keys,
-                source="webhook",
-            )
-            return
-
-        meeting_id, _ = match
-
-        # Verify meeting exists
-        meeting = await meetings_controller.get_by_id(meeting_id)
-        if not meeting:
-            logger.error(
-                "Meeting not found (webhook)",
-                recording_id=recording_id,
-                meeting_id=meeting_id,
-            )
-            await create_and_log_orphan(
-                recording_id=recording_id,
-                bucket_name=bucket_name,
-                room_name=room_name,
-                start_ts=event.payload.start_ts,
-                track_keys=track_keys,
-                source="webhook",
-            )
-            return
-
-        # Create recording atomically
-        created = await recordings_controller.try_create_with_meeting(
-            Recording(
-                id=recording_id,
-                bucket_name=bucket_name,
-                object_key=(
-                    os.path.dirname(track_keys[0]) if track_keys else room_name
-                ),
-                recorded_at=datetime.fromtimestamp(
-                    event.payload.start_ts, tz=timezone.utc
-                ),
-                track_keys=track_keys,
-                meeting_id=meeting_id,
-                status="pending",
-            )
-        )
-
-        if not created:
-            # Already created (polling got it first)
-            logger.debug(
-                "Recording already exists (webhook late)",
-                recording_id=recording_id,
-                meeting_id=meeting_id,
-            )
-            return
-
         logger.info(
-            "Raw-tracks recording queuing processing (webhook)",
+            "Raw-tracks recording queuing processing",
             recording_id=recording_id,
             room_name=room_name,
-            meeting_id=meeting_id,
             num_tracks=len(track_keys),
         )
 

server/reflector/views/meetings.py

@@ -1,5 +1,4 @@
 import json
-import logging
 from datetime import datetime, timezone
 from typing import Annotated, Any, Optional
 from uuid import UUID
@@ -10,21 +9,16 @@ from pydantic import BaseModel
 import reflector.auth as auth
 from reflector.dailyco_api import RecordingType
 from reflector.dailyco_api.client import DailyApiError
-from reflector.db.daily_recording_requests import (
-    DailyRecordingRequest,
-    daily_recording_requests_controller,
-)
 from reflector.db.meetings import (
     MeetingConsent,
     meeting_consent_controller,
     meetings_controller,
 )
 from reflector.db.rooms import rooms_controller
+from reflector.logger import logger
 from reflector.utils.string import NonEmptyString
 from reflector.video_platforms.factory import create_platform_client
 
-logger = logging.getLogger(__name__)
-
 router = APIRouter()
 
 
@@ -108,6 +102,13 @@ async def start_recording(
     if not meeting:
         raise HTTPException(status_code=404, detail="Meeting not found")
 
+    log = logger.bind(
+        meeting_id=meeting_id,
+        room_name=meeting.room_name,
+        recording_type=body.type,
+        instance_id=body.instanceId,
+    )
+
     try:
         client = create_platform_client("daily")
         result = await client.start_recording(
@@ -116,30 +117,9 @@ async def start_recording(
             instance_id=body.instanceId,
         )
 
-        recording_id = result["id"]
+        log.info(f"Started {body.type} recording via REST API")
 
-        await daily_recording_requests_controller.create(
+        return {"status": "ok", "result": result}
-            DailyRecordingRequest(
-                recording_id=recording_id,
-                meeting_id=meeting_id,
-                instance_id=body.instanceId,
-                type=body.type,
-                requested_at=datetime.now(timezone.utc),
-            )
-        )
-
-        logger.info(
-            f"Started {body.type} recording via REST API",
-            extra={
-                "meeting_id": meeting_id,
-                "room_name": meeting.room_name,
-                "recording_type": body.type,
-                "instance_id": body.instanceId,
-                "recording_id": recording_id,
-            },
-        )
-
-        return {"status": "ok", "recording_id": recording_id}
 
     except DailyApiError as e:
         # Parse Daily.co error response to detect "has an active stream"
@@ -150,42 +130,22 @@ async def start_recording(
             # "has an active stream" means recording already started by another participant
             # This is SUCCESS from business logic perspective - return 200
             if "has an active stream" in error_info:
-                logger.info(
+                log.info(
-                    f"{body.type} recording already active (started by another participant)",
+                    f"{body.type} recording already active (started by another participant)"
-                    extra={
-                        "meeting_id": meeting_id,
-                        "room_name": meeting.room_name,
-                        "recording_type": body.type,
-                        "instance_id": body.instanceId,
-                    },
                 )
                 return {"status": "already_active", "instanceId": str(body.instanceId)}
         except (json.JSONDecodeError, KeyError):
             pass  # Fall through to error handling
 
         # All other Daily.co API errors
-        logger.error(
+        log.error(f"Failed to start {body.type} recording", error=str(e))
-            f"Failed to start {body.type} recording",
-            extra={
-                "meeting_id": meeting_id,
-                "recording_type": body.type,
-                "error": str(e),
-            },
-        )
         raise HTTPException(
             status_code=500, detail=f"Failed to start recording: {str(e)}"
         )
 
     except Exception as e:
         # Non-Daily.co errors
-        logger.error(
+        log.error(f"Failed to start {body.type} recording", error=str(e))
-            f"Failed to start {body.type} recording",
-            extra={
-                "meeting_id": meeting_id,
-                "recording_type": body.type,
-                "error": str(e),
-            },
-        )
         raise HTTPException(
             status_code=500, detail=f"Failed to start recording: {str(e)}"
         )

server/reflector/worker/process.py

@@ -1,5 +1,6 @@
 import json
 import os
+import re
 from datetime import datetime, timezone
 from typing import List, Literal
 from urllib.parse import unquote
@@ -12,12 +13,10 @@ from celery.utils.log import get_task_logger
 from pydantic import ValidationError
 
 from reflector.dailyco_api import FinishedRecordingResponse, RecordingResponse
-from reflector.dailyco_api.recording_orphans import create_and_log_orphan
 from reflector.db.daily_participant_sessions import (
     DailyParticipantSession,
     daily_participant_sessions_controller,
 )
-from reflector.db.daily_recording_requests import daily_recording_requests_controller
 from reflector.db.meetings import meetings_controller
 from reflector.db.recordings import Recording, recordings_controller
 from reflector.db.rooms import rooms_controller
@@ -231,44 +230,79 @@ async def _process_multitrack_recording_inner(
     recording_start_ts: int,
 ):
     """
-    Process multitrack recording.
+    Process multitrack recording (first time or reprocessing).
 
-    Recording must already exist with meeting_id set (created by webhook/polling before queueing).
+    For first processing (webhook/polling):
+    - Uses recording_start_ts for time-based meeting matching (no instanceId available)
+
+    For reprocessing:
+    - Uses recording.meeting_id directly (already linked during first processing)
+    - recording_start_ts is ignored
     """
 
-    # Get recording (must exist - created by webhook/polling)
+    tz = timezone.utc
+    recorded_at = datetime.now(tz)
+    try:
+        if track_keys:
+            folder = os.path.basename(os.path.dirname(track_keys[0]))
+            ts_match = re.search(r"(\d{14})$", folder)
+            if ts_match:
+                ts = ts_match.group(1)
+                recorded_at = datetime.strptime(ts, "%Y%m%d%H%M%S").replace(tzinfo=tz)
+    except Exception as e:
+        logger.warning(
+            f"Could not parse recorded_at from keys, using now() {recorded_at}",
+            e,
+            exc_info=True,
+        )
+
+    # Check if recording already exists (reprocessing path)
     recording = await recordings_controller.get_by_id(recording_id)
 
-    if not recording:
+    if recording and recording.meeting_id:
-        logger.error(
+        # Reprocessing: recording exists with meeting already linked
-            "Recording not found - should have been created by webhook/polling",
+        meeting = await meetings_controller.get_by_id(recording.meeting_id)
-            recording_id=recording_id,
+        if not meeting:
-        )
+            logger.error(
-        return
+                "Reprocessing: meeting not found for recording - skipping",
+                meeting_id=recording.meeting_id,
+                recording_id=recording_id,
+            )
+            return
 
-    if not recording.meeting_id:
+        logger.info(
-        logger.error(
+            "Reprocessing: using existing recording.meeting_id",
-            "Recording has no meeting_id - orphan should not be queued",
             recording_id=recording_id,
+            meeting_id=meeting.id,
+            room_name=daily_room_name,
         )
-        return
+    else:
-
+        # First processing: recording doesn't exist, need time-based matching
-    # Get meeting
+        # (Daily.co doesn't return instanceId in API, must match by timestamp)
-    meeting = await meetings_controller.get_by_id(recording.meeting_id)
+        recording_start = datetime.fromtimestamp(recording_start_ts, tz=timezone.utc)
-    if not meeting:
+        meeting = await meetings_controller.get_by_room_name_and_time(
-        logger.error(
+            room_name=daily_room_name,
-            "Meeting not found for recording",
+            recording_start=recording_start,
-            meeting_id=recording.meeting_id,
+            time_window_hours=168,  # 1 week
+        )
+        if not meeting:
+            logger.error(
+                "Raw-tracks: no meeting found within 1-week window (time-based match) - skipping",
+                recording_id=recording_id,
+                room_name=daily_room_name,
+                recording_start_ts=recording_start_ts,
+                recording_start=recording_start.isoformat(),
+            )
+            return  # Skip processing, will retry on next poll
+        logger.info(
+            "First processing: found meeting via time-based matching",
+            meeting_id=meeting.id,
+            room_name=daily_room_name,
             recording_id=recording_id,
+            time_delta_seconds=abs(
+                (meeting.start_date - recording_start).total_seconds()
+            ),
         )
-        return
-
-    logger.info(
-        "Processing multitrack recording",
-        recording_id=recording_id,
-        meeting_id=meeting.id,
-        room_name=daily_room_name,
-    )
 
     room_name_base = extract_base_room_name(daily_room_name)
 
@@ -276,6 +310,33 @@ async def _process_multitrack_recording_inner(
     if not room:
         raise Exception(f"Room not found: {room_name_base}")
 
+    if not recording:
+        # Create recording (only happens during first processing)
+        object_key_dir = os.path.dirname(track_keys[0]) if track_keys else ""
+        recording = await recordings_controller.create(
+            Recording(
+                id=recording_id,
+                bucket_name=bucket_name,
+                object_key=object_key_dir,
+                recorded_at=recorded_at,
+                meeting_id=meeting.id,
+                track_keys=track_keys,
+            )
+        )
+    elif not recording.meeting_id:
+        # Recording exists but meeting_id is null (failed first processing)
+        # Update with meeting from time-based matching
+        await recordings_controller.set_meeting_id(
+            recording_id=recording.id,
+            meeting_id=meeting.id,
+        )
+        recording.meeting_id = meeting.id
+        logger.info(
+            "Updated existing recording with meeting_id",
+            recording_id=recording.id,
+            meeting_id=meeting.id,
+        )
+
     transcript = await transcripts_controller.get_by_recording_id(recording.id)
     if not transcript:
         transcript = await transcripts_controller.add(
@@ -461,7 +522,7 @@ async def store_cloud_recording(
     Store cloud recording reference in meeting table.
 
     Common function for both webhook and polling code paths.
-    Uses direct recording_id lookup via daily_recording_requests table.
+    Uses time-based matching to handle duplicate room_name values.
 
     Args:
         recording_id: Daily.co recording ID
@@ -474,170 +535,155 @@ async def store_cloud_recording(
     Returns:
         True if stored, False if skipped/failed
     """
-    # Lookup request
+    recording_start = datetime.fromtimestamp(start_ts, tz=timezone.utc)
-    match = await daily_recording_requests_controller.find_by_recording_id(recording_id)
 
-    if not match:
+    meeting = await meetings_controller.get_by_room_name_and_time(
-        # ORPHAN: No request found (pre-migration recording or failed request creation)
+        room_name=room_name,
-        await create_and_log_orphan(
+        recording_start=recording_start,
+        time_window_hours=168,  # 1 week
+    )
+
+    if not meeting:
+        logger.warning(
+            f"Cloud recording ({source}): no meeting found within 1-week window",
             recording_id=recording_id,
-            bucket_name="",
             room_name=room_name,
-            start_ts=start_ts,
+            recording_start_ts=start_ts,
-            track_keys=None,
+            recording_start=recording_start.isoformat(),
-            source=source,
         )
         return False
 
-    meeting_id, _ = match
-
     success = await meetings_controller.set_cloud_recording_if_missing(
-        meeting_id=meeting_id,
+        meeting_id=meeting.id,
         s3_key=s3_key,
         duration=duration,
     )
 
     if not success:
         logger.debug(
-            f"Cloud recording ({source}): already set (stop/restart?)",
+            f"Cloud recording ({source}): already set (race lost)",
             recording_id=recording_id,
             room_name=room_name,
-            meeting_id=meeting_id,
+            meeting_id=meeting.id,
         )
         return False
 
     logger.info(
-        f"Cloud recording stored via {source}",
+        f"Cloud recording stored via {source} (time-based match)",
-        meeting_id=meeting_id,
+        meeting_id=meeting.id,
         recording_id=recording_id,
         s3_key=s3_key,
         duration=duration,
+        time_delta_seconds=abs((meeting.start_date - recording_start).total_seconds()),
     )
     return True
 
 
 async def _poll_cloud_recordings(cloud_recordings: List[FinishedRecordingResponse]):
-    """Process cloud recordings (database deduplication, worker-agnostic).
+    """
+    Store cloud recordings missing from meeting table via polling.
 
-    Cloud recordings stored in meeting.daily_composed_video_s3_key, not recording table.
+    Uses time-based matching via store_cloud_recording().
-    Only first cloud recording per meeting is kept (existing behavior).
     """
     if not cloud_recordings:
         return
 
-    for rec in cloud_recordings:
+    stored_count = 0
-        # Lookup request
+    for recording in cloud_recordings:
-        match = await daily_recording_requests_controller.find_by_recording_id(rec.id)
+        # Extract S3 key from recording (cloud recordings use s3key field)
-
+        s3_key = recording.s3key or (recording.s3.key if recording.s3 else None)
-        if not match:
+        if not s3_key:
-            await create_and_log_orphan(
-                recording_id=rec.id,
-                bucket_name="",
-                room_name=rec.room_name,
-                start_ts=rec.start_ts,
-                track_keys=None,
-                source="polling",
-            )
-            continue
-
-        meeting_id, _ = match
-
-        if not rec.s3key:
-            logger.error("Cloud recording missing s3_key", recording_id=rec.id)
-            continue
-
-        # Store in meeting table (atomic, only if not already set)
-        success = await meetings_controller.set_cloud_recording_if_missing(
-            meeting_id=meeting_id,
-            s3_key=rec.s3key,
-            duration=rec.duration,
-        )
-
-        if success:
-            logger.info(
-                "Stored cloud recording", recording_id=rec.id, meeting_id=meeting_id
-            )
-        else:
             logger.warning(
-                "Cloud recording already exists for meeting (stop/restart?)",
+                "Cloud recording: missing S3 key",
-                recording_id=rec.id,
+                recording_id=recording.id,
-                meeting_id=meeting_id,
+                room_name=recording.room_name,
             )
+            continue
+
+        stored = await store_cloud_recording(
+            recording_id=recording.id,
+            room_name=recording.room_name,
+            s3_key=s3_key,
+            duration=recording.duration,
+            start_ts=recording.start_ts,
+            source="polling",
+        )
+        if stored:
+            stored_count += 1
+
+    logger.info(
+        "Cloud recording polling complete",
+        total=len(cloud_recordings),
+        stored=stored_count,
+    )
 
 
 async def _poll_raw_tracks_recordings(
     raw_tracks_recordings: List[FinishedRecordingResponse],
-    bucket_name: NonEmptyString,
+    bucket_name: str,
-) -> None:
+):
-    """Process raw-tracks (database deduplication, worker-agnostic)."""
+    """Queue raw-tracks recordings missing from DB (existing logic)."""
     if not raw_tracks_recordings:
         return
 
-    for rec in raw_tracks_recordings:
+    recording_ids = [rec.id for rec in raw_tracks_recordings]
-        # Lookup request FIRST (before any DB writes)
+    existing_recordings = await recordings_controller.get_by_ids(recording_ids)
-        match = await daily_recording_requests_controller.find_by_recording_id(rec.id)
+    existing_ids = {rec.id for rec in existing_recordings}
 
-        if not match:
+    missing_recordings = [
-            await create_and_log_orphan(
+        rec for rec in raw_tracks_recordings if rec.id not in existing_ids
-                recording_id=rec.id,
+    ]
-                bucket_name=bucket_name,
+
-                room_name=rec.room_name,
+    if not missing_recordings:
-                start_ts=rec.start_ts,
+        logger.debug(
-                track_keys=[t.s3Key for t in rec.tracks if t.type == "audio"],
+            "All raw-tracks recordings already in DB",
-                source="polling",
+            api_count=len(raw_tracks_recordings),
+            existing_count=len(existing_recordings),
+        )
+        return
+
+    logger.info(
+        "Found raw-tracks recordings missing from DB",
+        missing_count=len(missing_recordings),
+        total_api_count=len(raw_tracks_recordings),
+        existing_count=len(existing_recordings),
+    )
+
+    for recording in missing_recordings:
+        if not recording.tracks:
+            logger.warning(
+                "Finished raw-tracks recording has no tracks (no audio captured)",
+                recording_id=recording.id,
+                room_name=recording.room_name,
             )
             continue
 
-        meeting_id, _ = match
+        track_keys = [t.s3Key for t in recording.tracks if t.type == "audio"]
 
-        # Verify meeting exists
+        if not track_keys:
-        meeting = await meetings_controller.get_by_id(meeting_id)
+            logger.warning(
-        if not meeting:
+                "No audio tracks found in raw-tracks recording",
-            logger.error(
+                recording_id=recording.id,
-                "Meeting not found", recording_id=rec.id, meeting_id=meeting_id
+                room_name=recording.room_name,
-            )
+                total_tracks=len(recording.tracks),
-            await create_and_log_orphan(
-                recording_id=rec.id,
-                bucket_name=bucket_name,
-                room_name=rec.room_name,
-                start_ts=rec.start_ts,
-                track_keys=[t.s3Key for t in rec.tracks if t.type == "audio"],
-                source="polling",
             )
             continue
 
-        # DEDUPLICATION: Atomically create recording (single operation, no race window)
+        logger.info(
-        # ON CONFLICT → concurrent poller already got it, skip entire logic
+            "Queueing missing raw-tracks recording for processing",
-        track_keys = [t.s3Key for t in rec.tracks if t.type == "audio"]
+            recording_id=recording.id,
-
+            room_name=recording.room_name,
-        created = await recordings_controller.try_create_with_meeting(
+            track_count=len(track_keys),
-            Recording(
-                id=rec.id,
-                bucket_name=bucket_name,
-                object_key=os.path.dirname(track_keys[0]) if track_keys else "",
-                recorded_at=datetime.fromtimestamp(rec.start_ts, tz=timezone.utc),
-                track_keys=track_keys,
-                meeting_id=meeting_id,  # Set at creation (constraint-safe)
-                status="pending",
-            )
         )
 
-        if not created:
-            # Conflict: another poller already created/queued this
-            # Skip all remaining logic (match already done by winner)
-            continue
-
-        # Only winner reaches here - queue processing (works with Celery or Hatchet)
         process_multitrack_recording.delay(
-            recording_id=rec.id,
-            daily_room_name=rec.room_name,
-            recording_start_ts=rec.start_ts,
             bucket_name=bucket_name,
+            daily_room_name=recording.room_name,
+            recording_id=recording.id,
             track_keys=track_keys,
+            recording_start_ts=recording.start_ts,
         )
 
-        logger.info("Queued recording", recording_id=rec.id, meeting_id=meeting_id)
-
 
 async def poll_daily_room_presence(meeting_id: str) -> None:
     """Poll Daily.co room presence and reconcile with DB sessions. New presence is added, old presence is marked as closed.

server/test_daily_api_recordings.py

@@ -1,39 +0,0 @@
-#!/usr/bin/env python3
-"""Test script to fetch Daily.co recordings for a specific room and show raw API response."""
-
-import asyncio
-import json
-
-from reflector.video_platforms.factory import create_platform_client
-
-
-async def main():
-    room_name = "daily-private-igor-20260110042117"
-
-    print(f"\n=== Fetching recordings for room: {room_name} ===\n")
-
-    async with create_platform_client("daily") as client:
-        recordings = await client.list_recordings(room_name=room_name)
-
-    print(f"Found {len(recordings)} recording objects from Daily.co API\n")
-
-    for i, rec in enumerate(recordings, 1):
-        print(f"--- Recording #{i} ---")
-        print(f"ID: {rec.id}")
-        print(f"Room: {rec.room_name}")
-        print(f"Start TS: {rec.start_ts}")
-        print(f"Status: {rec.status}")
-        print(f"Duration: {rec.duration}")
-        print(f"Type: {rec.type}")
-        print(f"Tracks count: {len(rec.tracks)}")
-
-        if rec.tracks:
-            print(f"Tracks:")
-            for j, track in enumerate(rec.tracks, 1):
-                print(f"  Track {j}: {track.s3Key}")
-
-        print(f"\nRaw JSON:\n{json.dumps(rec.model_dump(), indent=2, default=str)}\n")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

server/tests/test_daily_recording_requests.py

@@ -1,258 +0,0 @@
-from datetime import datetime, timezone
-from uuid import UUID
-
-import pytest
-
-from reflector.db.daily_recording_requests import (
-    DailyRecordingRequest,
-    daily_recording_requests_controller,
-)
-from reflector.db.meetings import Meeting, meetings_controller
-from reflector.db.recordings import Recording, recordings_controller
-from reflector.db.rooms import Room, rooms_controller
-
-
-@pytest.mark.asyncio
-async def test_create_request():
-    """Test creating a recording request."""
-    # Create meeting first
-    room = Room(id="test-room", name="Test Room", slug="test-room", user_id="test-user")
-    await rooms_controller.create(room)
-
-    meeting = Meeting(
-        id="meeting-123",
-        room_name="test-room",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="cloud",
-    )
-    await meetings_controller.create(meeting)
-
-    request = DailyRecordingRequest(
-        recording_id="rec-1",
-        meeting_id="meeting-123",
-        instance_id=UUID("a1b2c3d4-e5f6-7890-abcd-ef1234567890"),
-        type="cloud",
-        requested_at=datetime.now(timezone.utc),
-    )
-
-    await daily_recording_requests_controller.create(request)
-
-    result = await daily_recording_requests_controller.find_by_recording_id("rec-1")
-    assert result is not None
-    assert result[0] == "meeting-123"
-    assert result[1] == "cloud"
-
-
-@pytest.mark.asyncio
-async def test_multiple_recordings_same_meeting():
-    """Test stop/restart creates multiple request rows."""
-    # Create room and meeting
-    room = Room(
-        id="test-room-2", name="Test Room 2", slug="test-room-2", user_id="test-user"
-    )
-    await rooms_controller.create(room)
-
-    meeting_id = "meeting-456"
-    meeting = Meeting(
-        id=meeting_id,
-        room_name="test-room-2",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="cloud",
-    )
-    await meetings_controller.create(meeting)
-
-    instance_id = UUID("b1c2d3e4-f5a6-7890-abcd-ef1234567890")
-
-    # First recording
-    await daily_recording_requests_controller.create(
-        DailyRecordingRequest(
-            recording_id="rec-1",
-            meeting_id=meeting_id,
-            instance_id=instance_id,
-            type="cloud",
-            requested_at=datetime.now(timezone.utc),
-        )
-    )
-
-    # Stop, then restart (new recording_id, same instance_id)
-    await daily_recording_requests_controller.create(
-        DailyRecordingRequest(
-            recording_id="rec-2",  # DIFFERENT
-            meeting_id=meeting_id,
-            instance_id=instance_id,  # SAME
-            type="cloud",
-            requested_at=datetime.now(timezone.utc),
-        )
-    )
-
-    # Both exist
-    requests = await daily_recording_requests_controller.get_by_meeting_id(meeting_id)
-    assert len(requests) == 2
-    assert {r.recording_id for r in requests} == {"rec-1", "rec-2"}
-
-
-@pytest.mark.asyncio
-async def test_deduplication_via_database():
-    """Test concurrent pollers use database for deduplication."""
-    # Create room and meeting
-    room = Room(
-        id="test-room-3", name="Test Room 3", slug="test-room-3", user_id="test-user"
-    )
-    await rooms_controller.create(room)
-
-    meeting = Meeting(
-        id="meeting-789",
-        room_name="test-room-3",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="raw-tracks",
-    )
-    await meetings_controller.create(meeting)
-
-    recording_id = "rec-123"
-
-    # Poller 1
-    created1 = await recordings_controller.try_create_with_meeting(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="test-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id="meeting-789",
-            status="pending",
-            track_keys=["track1.webm", "track2.webm"],
-        )
-    )
-    assert created1 is True  # First wins
-
-    # Poller 2 (concurrent)
-    created2 = await recordings_controller.try_create_with_meeting(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="test-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id="meeting-789",
-            status="pending",
-            track_keys=["track1.webm", "track2.webm"],
-        )
-    )
-    assert created2 is False  # Conflict, skip
-
-
-@pytest.mark.asyncio
-async def test_orphan_logged_once():
-    """Test orphan marked once, skipped on re-poll."""
-    # First poll
-    created1 = await recordings_controller.create_orphan(
-        Recording(
-            id="orphan-123",
-            bucket_name="test-bucket",
-            object_key="orphan-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=None,
-            status="orphan",
-            track_keys=None,
-        )
-    )
-    assert created1 is True
-
-    # Second poll (same orphan discovered again)
-    created2 = await recordings_controller.create_orphan(
-        Recording(
-            id="orphan-123",
-            bucket_name="test-bucket",
-            object_key="orphan-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=None,
-            status="orphan",
-            track_keys=None,
-        )
-    )
-    assert created2 is False  # Already exists
-
-    # Verify it exists
-    existing = await recordings_controller.get_by_id("orphan-123")
-    assert existing is not None
-    assert existing.status == "orphan"
-
-
-@pytest.mark.asyncio
-async def test_orphan_constraints():
-    """Test orphan invariants are enforced."""
-    # Can't create orphan with meeting_id
-    with pytest.raises(AssertionError, match="meeting_id must be NULL"):
-        await recordings_controller.create_orphan(
-            Recording(
-                id="bad-orphan-1",
-                bucket_name="test",
-                object_key="test",
-                recorded_at=datetime.now(timezone.utc),
-                meeting_id="meeting-123",  # Should be None
-                status="orphan",
-                track_keys=None,
-            )
-        )
-
-    # Can't create orphan with wrong status
-    with pytest.raises(AssertionError, match="status must be 'orphan'"):
-        await recordings_controller.create_orphan(
-            Recording(
-                id="bad-orphan-2",
-                bucket_name="test",
-                object_key="test",
-                recorded_at=datetime.now(timezone.utc),
-                meeting_id=None,
-                status="pending",  # Should be "orphan"
-                track_keys=None,
-            )
-        )
-
-
-@pytest.mark.asyncio
-async def test_try_create_with_meeting_constraints():
-    """Test try_create_with_meeting enforces constraints."""
-    # Create room and meeting
-    room = Room(
-        id="test-room-4", name="Test Room 4", slug="test-room-4", user_id="test-user"
-    )
-    await rooms_controller.create(room)
-
-    meeting = Meeting(
-        id="meeting-999",
-        room_name="test-room-4",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="cloud",
-    )
-    await meetings_controller.create(meeting)
-
-    # Can't create with orphan status
-    with pytest.raises(AssertionError, match="use create_orphan"):
-        await recordings_controller.try_create_with_meeting(
-            Recording(
-                id="bad-rec-1",
-                bucket_name="test",
-                object_key="test",
-                recorded_at=datetime.now(timezone.utc),
-                meeting_id="meeting-999",
-                status="orphan",  # Should not be orphan
-                track_keys=None,
-            )
-        )
-
-    # Can't create without meeting_id
-    with pytest.raises(AssertionError, match="meeting_id required"):
-        await recordings_controller.try_create_with_meeting(
-            Recording(
-                id="bad-rec-2",
-                bucket_name="test",
-                object_key="test",
-                recorded_at=datetime.now(timezone.utc),
-                meeting_id=None,  # Should have meeting_id
-                status="pending",
-                track_keys=None,
-            )
-        )

server/tests/test_recording_request_flow.py

@@ -1,300 +0,0 @@
-"""
-Integration tests for recording request flow.
-
-These tests verify the end-to-end flow of:
-1. Starting a recording (creates request)
-2. Webhook/polling discovering recording (matches via request)
-3. Recording processing (uses existing meeting_id)
-"""
-
-from datetime import datetime, timezone
-from uuid import UUID, uuid4
-
-import pytest
-
-from reflector.db.daily_recording_requests import (
-    DailyRecordingRequest,
-    daily_recording_requests_controller,
-)
-from reflector.db.meetings import Meeting, meetings_controller
-from reflector.db.recordings import Recording, recordings_controller
-from reflector.db.rooms import Room, rooms_controller
-
-
-@pytest.mark.asyncio
-async def test_recording_request_flow_cloud(client):
-    """Test full cloud recording flow: start -> webhook -> match"""
-    # Create room and meeting
-    room = Room(id="test-room", name="Test Room", slug="test-room", user_id="test-user")
-    await rooms_controller.create(room)
-
-    meeting_id = f"meeting-{uuid4()}"
-    meeting = Meeting(
-        id=meeting_id,
-        room_name="test-room",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="cloud",
-    )
-    await meetings_controller.create(meeting)
-
-    # Simulate recording start (what endpoint does)
-    recording_id = "rec-cloud-123"
-    instance_id = UUID("a1b2c3d4-e5f6-7890-abcd-ef1234567890")
-
-    request = DailyRecordingRequest(
-        recording_id=recording_id,
-        meeting_id=meeting_id,
-        instance_id=instance_id,
-        type="cloud",
-        requested_at=datetime.now(timezone.utc),
-    )
-    await daily_recording_requests_controller.create(request)
-
-    # Verify request exists
-    match = await daily_recording_requests_controller.find_by_recording_id(recording_id)
-    assert match is not None
-    assert match[0] == meeting_id
-    assert match[1] == "cloud"
-
-    # Simulate webhook/polling storing cloud recording
-    success = await meetings_controller.set_cloud_recording_if_missing(
-        meeting_id=meeting_id,
-        s3_key="s3://bucket/recording.mp4",
-        duration=120,
-    )
-    assert success is True
-
-    # Verify meeting updated
-    updated_meeting = await meetings_controller.get_by_id(meeting_id)
-    assert updated_meeting.daily_composed_video_s3_key == "s3://bucket/recording.mp4"
-    assert updated_meeting.daily_composed_video_duration == 120
-
-
-@pytest.mark.asyncio
-async def test_recording_request_flow_raw_tracks(client):
-    """Test full raw-tracks recording flow: start -> webhook/polling -> process"""
-    # Create room and meeting
-    room = Room(
-        id="test-room-2",
-        name="Test Room 2",
-        slug="test-room-2",
-        user_id="test-user",
-    )
-    await rooms_controller.create(room)
-
-    meeting_id = f"meeting-{uuid4()}"
-    meeting = Meeting(
-        id=meeting_id,
-        room_name="test-room-2",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="raw-tracks",
-    )
-    await meetings_controller.create(meeting)
-
-    # Simulate recording start
-    recording_id = "rec-raw-456"
-    instance_id = UUID("b1c2d3e4-f5a6-7890-abcd-ef1234567890")
-
-    request = DailyRecordingRequest(
-        recording_id=recording_id,
-        meeting_id=meeting_id,
-        instance_id=instance_id,
-        type="raw-tracks",
-        requested_at=datetime.now(timezone.utc),
-    )
-    await daily_recording_requests_controller.create(request)
-
-    # Simulate webhook/polling discovering recording
-    match = await daily_recording_requests_controller.find_by_recording_id(recording_id)
-    assert match is not None
-    found_meeting_id, recording_type = match
-    assert found_meeting_id == meeting_id
-    assert recording_type == "raw-tracks"
-
-    # Create recording (what webhook/polling does)
-    created = await recordings_controller.try_create_with_meeting(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="recordings/20260120/",
-            recorded_at=datetime.now(timezone.utc),
-            track_keys=["track1.webm", "track2.webm"],
-            meeting_id=meeting_id,
-            status="pending",
-        )
-    )
-    assert created is True
-
-    # Verify recording exists with meeting_id
-    recording = await recordings_controller.get_by_id(recording_id)
-    assert recording is not None
-    assert recording.meeting_id == meeting_id
-    assert recording.status == "pending"
-    assert len(recording.track_keys) == 2
-
-
-@pytest.mark.asyncio
-async def test_stop_restart_creates_multiple_requests(client):
-    """Test stop/restart creates multiple request rows with same instance_id"""
-    # Create room and meeting
-    room = Room(
-        id="test-room-3",
-        name="Test Room 3",
-        slug="test-room-3",
-        user_id="test-user",
-    )
-    await rooms_controller.create(room)
-
-    meeting_id = f"meeting-{uuid4()}"
-    meeting = Meeting(
-        id=meeting_id,
-        room_name="test-room-3",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="cloud",
-    )
-    await meetings_controller.create(meeting)
-
-    instance_id = UUID("c1d2e3f4-a5b6-7890-abcd-ef1234567890")
-
-    # First recording
-    await daily_recording_requests_controller.create(
-        DailyRecordingRequest(
-            recording_id="rec-first",
-            meeting_id=meeting_id,
-            instance_id=instance_id,
-            type="cloud",
-            requested_at=datetime.now(timezone.utc),
-        )
-    )
-
-    # Stop, then restart (new recording_id, same instance_id)
-    await daily_recording_requests_controller.create(
-        DailyRecordingRequest(
-            recording_id="rec-second",  # DIFFERENT
-            meeting_id=meeting_id,
-            instance_id=instance_id,  # SAME
-            type="cloud",
-            requested_at=datetime.now(timezone.utc),
-        )
-    )
-
-    # Both exist
-    requests = await daily_recording_requests_controller.get_by_meeting_id(meeting_id)
-    assert len(requests) == 2
-    assert {r.recording_id for r in requests} == {"rec-first", "rec-second"}
-    assert all(r.instance_id == instance_id for r in requests)
-
-
-@pytest.mark.asyncio
-async def test_orphan_recording_no_request(client):
-    """Test orphan recording (no request found)"""
-    # Simulate polling discovering recording with no request
-    recording_id = "rec-orphan"
-
-    match = await daily_recording_requests_controller.find_by_recording_id(recording_id)
-    assert match is None  # No request
-
-    # Mark as orphan
-    created = await recordings_controller.create_orphan(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="orphan-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=None,
-            status="orphan",
-            track_keys=None,
-        )
-    )
-    assert created is True
-
-    # Verify orphan exists
-    recording = await recordings_controller.get_by_id(recording_id)
-    assert recording is not None
-    assert recording.status == "orphan"
-    assert recording.meeting_id is None
-
-    # Second poll - already exists
-    created_again = await recordings_controller.create_orphan(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="orphan-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=None,
-            status="orphan",
-            track_keys=None,
-        )
-    )
-    assert created_again is False  # Already exists
-
-
-@pytest.mark.asyncio
-async def test_concurrent_polling_deduplication(client):
-    """Test concurrent pollers only queue once"""
-    # Create room and meeting
-    room = Room(
-        id="test-room-4",
-        name="Test Room 4",
-        slug="test-room-4",
-        user_id="test-user",
-    )
-    await rooms_controller.create(room)
-
-    meeting_id = f"meeting-{uuid4()}"
-    meeting = Meeting(
-        id=meeting_id,
-        room_name="test-room-4",
-        start_date=datetime.now(timezone.utc),
-        end_date=None,
-        recording_type="raw-tracks",
-    )
-    await meetings_controller.create(meeting)
-
-    # Create request
-    recording_id = "rec-concurrent"
-    await daily_recording_requests_controller.create(
-        DailyRecordingRequest(
-            recording_id=recording_id,
-            meeting_id=meeting_id,
-            instance_id=UUID("d1e2f3a4-b5c6-7890-abcd-ef1234567890"),
-            type="raw-tracks",
-            requested_at=datetime.now(timezone.utc),
-        )
-    )
-
-    # Poller 1
-    created1 = await recordings_controller.try_create_with_meeting(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="test-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=meeting_id,
-            status="pending",
-            track_keys=["track1.webm"],
-        )
-    )
-    assert created1 is True  # First wins
-
-    # Poller 2 (concurrent)
-    created2 = await recordings_controller.try_create_with_meeting(
-        Recording(
-            id=recording_id,
-            bucket_name="test-bucket",
-            object_key="test-key",
-            recorded_at=datetime.now(timezone.utc),
-            meeting_id=meeting_id,
-            status="pending",
-            track_keys=["track1.webm"],
-        )
-    )
-    assert created2 is False  # Conflict, skip
-
-    # Only one recording exists
-    recording = await recordings_controller.get_by_id(recording_id)
-    assert recording is not None
-    assert recording.meeting_id == meeting_id

server/tests/test_time_based_meeting_matching.py

@@ -0,0 +1,374 @@
+"""
+Integration tests for time-based meeting-to-recording matching.
+
+Tests the critical path for matching Daily.co recordings to meetings when
+API doesn't return instanceId.
+"""
+
+from datetime import datetime, timedelta, timezone
+
+import pytest
+
+from reflector.db.meetings import meetings_controller
+from reflector.db.rooms import rooms_controller
+
+
+@pytest.fixture
+async def test_room():
+    """Create a test room for meetings."""
+    room = await rooms_controller.add(
+        name="test-room-time",
+        user_id="test-user-id",
+        zulip_auto_post=False,
+        zulip_stream="",
+        zulip_topic="",
+        is_locked=False,
+        room_mode="normal",
+        recording_type="cloud",
+        recording_trigger="automatic",
+        is_shared=False,
+        platform="daily",
+    )
+    return room
+
+
+@pytest.fixture
+def base_time():
+    """Fixed timestamp for deterministic tests."""
+    return datetime(2026, 1, 14, 9, 0, 0, tzinfo=timezone.utc)
+
+
+class TestTimeBasedMatching:
+    """Test get_by_room_name_and_time() matching logic."""
+
+    async def test_exact_time_match(self, test_room, base_time):
+        """Recording timestamp exactly matches meeting start_date."""
+        meeting = await meetings_controller.create(
+            id="meeting-exact",
+            room_name="daily-test-20260114090000",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-20260114090000",
+            recording_start=base_time,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == meeting.id
+
+    async def test_recording_slightly_after_meeting_start(self, test_room, base_time):
+        """Recording started 1 minute after meeting (participants joined late)."""
+        meeting = await meetings_controller.create(
+            id="meeting-late",
+            room_name="daily-test-20260114090100",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        recording_start = base_time + timedelta(minutes=1)
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-20260114090100",
+            recording_start=recording_start,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == meeting.id
+
+    async def test_duplicate_room_names_picks_closest(self, test_room, base_time):
+        """
+        Two meetings with same room_name (duplicate/race condition).
+        Should pick closest by timestamp.
+        """
+        meeting1 = await meetings_controller.create(
+            id="meeting-1-first",
+            room_name="daily-duplicate-room",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        meeting2 = await meetings_controller.create(
+            id="meeting-2-second",
+            room_name="daily-duplicate-room",  # Same room_name!
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time + timedelta(seconds=0.99),  # 0.99s later
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        # Recording started 0.5s after meeting1
+        # Distance: meeting1 = 0.5s, meeting2 = 0.49s → meeting2 is closer
+        recording_start = base_time + timedelta(seconds=0.5)
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-duplicate-room",
+            recording_start=recording_start,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == meeting2.id  # meeting2 is closer (0.49s vs 0.5s)
+
+    async def test_outside_time_window_returns_none(self, test_room, base_time):
+        """Recording outside 1-week window returns None."""
+        await meetings_controller.create(
+            id="meeting-old",
+            room_name="daily-test-old",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        # Recording 8 days later (outside 7-day window)
+        recording_start = base_time + timedelta(days=8)
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-old",
+            recording_start=recording_start,
+            time_window_hours=168,
+        )
+
+        assert result is None
+
+    async def test_tie_breaker_deterministic(self, test_room, base_time):
+        """When time delta identical, tie-breaker by meeting.id is deterministic."""
+        meeting_z = await meetings_controller.create(
+            id="zzz-last-uuid",
+            room_name="daily-test-tie",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        meeting_a = await meetings_controller.create(
+            id="aaa-first-uuid",
+            room_name="daily-test-tie",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,  # Exact same start_date
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-tie",
+            recording_start=base_time,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        # Tie-breaker: lexicographically first UUID
+        assert result.id == "aaa-first-uuid"
+
+    async def test_timezone_naive_datetime_raises(self, test_room, base_time):
+        """Timezone-naive datetime raises ValueError."""
+        await meetings_controller.create(
+            id="meeting-tz",
+            room_name="daily-test-tz",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        # Naive datetime (no timezone)
+        naive_dt = datetime(2026, 1, 14, 9, 0, 0)
+
+        with pytest.raises(ValueError, match="timezone-aware"):
+            await meetings_controller.get_by_room_name_and_time(
+                room_name="daily-test-tz",
+                recording_start=naive_dt,
+                time_window_hours=168,
+            )
+
+    async def test_one_week_boundary_after_included(self, test_room, base_time):
+        """Meeting 1-week AFTER recording is included (window_end boundary)."""
+        meeting_time = base_time + timedelta(hours=168)
+
+        await meetings_controller.create(
+            id="meeting-boundary-after",
+            room_name="daily-test-boundary-after",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=meeting_time,
+            end_date=meeting_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-boundary-after",
+            recording_start=base_time,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == "meeting-boundary-after"
+
+    async def test_one_week_boundary_before_included(self, test_room, base_time):
+        """Meeting 1-week BEFORE recording is included (window_start boundary)."""
+        meeting_time = base_time - timedelta(hours=168)
+
+        await meetings_controller.create(
+            id="meeting-boundary-before",
+            room_name="daily-test-boundary-before",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=meeting_time,
+            end_date=meeting_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-boundary-before",
+            recording_start=base_time,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == "meeting-boundary-before"
+
+    async def test_recording_before_meeting_start(self, test_room, base_time):
+        """Recording started before meeting (clock skew or early join)."""
+        await meetings_controller.create(
+            id="meeting-early",
+            room_name="daily-test-early",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        recording_start = base_time - timedelta(minutes=2)
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-early",
+            recording_start=recording_start,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == "meeting-early"
+
+    async def test_mixed_inside_outside_window(self, test_room, base_time):
+        """Multiple meetings, only one inside window - returns the inside one."""
+        await meetings_controller.create(
+            id="meeting-old",
+            room_name="daily-test-mixed",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time - timedelta(days=10),
+            end_date=base_time - timedelta(days=10, hours=-1),
+            room=test_room,
+        )
+
+        await meetings_controller.create(
+            id="meeting-inside",
+            room_name="daily-test-mixed",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time - timedelta(days=2),
+            end_date=base_time - timedelta(days=2, hours=-1),
+            room=test_room,
+        )
+
+        await meetings_controller.create(
+            id="meeting-future",
+            room_name="daily-test-mixed",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time + timedelta(days=10),
+            end_date=base_time + timedelta(days=10, hours=1),
+            room=test_room,
+        )
+
+        result = await meetings_controller.get_by_room_name_and_time(
+            room_name="daily-test-mixed",
+            recording_start=base_time,
+            time_window_hours=168,
+        )
+
+        assert result is not None
+        assert result.id == "meeting-inside"
+
+
+class TestAtomicCloudRecordingUpdate:
+    """Test atomic update prevents race conditions."""
+
+    async def test_first_update_succeeds(self, test_room, base_time):
+        """First call to set_cloud_recording_if_missing succeeds."""
+        meeting = await meetings_controller.create(
+            id="meeting-atomic-1",
+            room_name="daily-test-atomic",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        success = await meetings_controller.set_cloud_recording_if_missing(
+            meeting_id=meeting.id,
+            s3_key="first-s3-key",
+            duration=100,
+        )
+
+        assert success is True
+
+        updated = await meetings_controller.get_by_id(meeting.id)
+        assert updated.daily_composed_video_s3_key == "first-s3-key"
+        assert updated.daily_composed_video_duration == 100
+
+    async def test_second_update_fails_atomically(self, test_room, base_time):
+        """Second call to update same meeting doesn't overwrite (atomic check)."""
+        meeting = await meetings_controller.create(
+            id="meeting-atomic-2",
+            room_name="daily-test-atomic2",
+            room_url="https://example.daily.co/test",
+            host_room_url="https://example.daily.co/test?t=host",
+            start_date=base_time,
+            end_date=base_time + timedelta(hours=1),
+            room=test_room,
+        )
+
+        success1 = await meetings_controller.set_cloud_recording_if_missing(
+            meeting_id=meeting.id,
+            s3_key="first-s3-key",
+            duration=100,
+        )
+
+        assert success1 is True
+
+        after_first = await meetings_controller.get_by_id(meeting.id)
+        assert after_first.daily_composed_video_s3_key == "first-s3-key"
+
+        success2 = await meetings_controller.set_cloud_recording_if_missing(
+            meeting_id=meeting.id,
+            s3_key="bucket/path/should-not-overwrite",
+            duration=200,
+        )
+
+        assert success2 is False
+
+        final = await meetings_controller.get_by_id(meeting.id)
+        assert final.daily_composed_video_s3_key == "first-s3-key"
+        assert final.daily_composed_video_duration == 100

server/uv.lock

@@ -159,20 +159,21 @@ wheels = [
 
 [[package]]
 name = "aiortc"
-version = "1.14.0"
+version = "1.13.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aioice" },
     { name = "av" },
+    { name = "cffi" },
     { name = "cryptography" },
     { name = "google-crc32c" },
     { name = "pyee" },
     { name = "pylibsrtp" },
     { name = "pyopenssl" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/51/9c/4e027bfe0195de0442da301e2389329496745d40ae44d2d7c4571c4290ce/aiortc-1.14.0.tar.gz", hash = "sha256:adc8a67ace10a085721e588e06a00358ed8eaf5f6b62f0a95358ff45628dd762", size = 1180864 }
+sdist = { url = "https://files.pythonhosted.org/packages/62/03/bc947d74c548e0c17cf94e5d5bdacaed0ee9e5b2bb7b8b8cf1ac7a7c01ec/aiortc-1.13.0.tar.gz", hash = "sha256:5d209975c22d0910fb5a0f0e2caa828f2da966c53580f7c7170ac3a16a871620", size = 1179894 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/57/ab/31646a49209568cde3b97eeade0d28bb78b400e6645c56422c101df68932/aiortc-1.14.0-py3-none-any.whl", hash = "sha256:4b244d7e482f4e1f67e685b3468269628eca1ec91fa5b329ab517738cfca086e", size = 93183 },
+    { url = "https://files.pythonhosted.org/packages/87/29/765633cab5f1888890f5f172d1d53009b9b14e079cdfa01a62d9896a9ea9/aiortc-1.13.0-py3-none-any.whl", hash = "sha256:9ccccec98796f6a96bd1c3dd437a06da7e0f57521c96bd56e4b965a91b03a0a0", size = 92910 },
 ]
 
 [[package]]
@@ -326,24 +327,28 @@ wheels = [
 
 [[package]]
 name = "av"
-version = "16.1.0"
+version = "14.4.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/78/cd/3a83ffbc3cc25b39721d174487fb0d51a76582f4a1703f98e46170ce83d4/av-16.1.0.tar.gz", hash = "sha256:a094b4fd87a3721dacf02794d3d2c82b8d712c85b9534437e82a8a978c175ffd", size = 4285203 }
+sdist = { url = "https://files.pythonhosted.org/packages/86/f6/0b473dab52dfdea05f28f3578b1c56b6c796ce85e76951bab7c4e38d5a74/av-14.4.0.tar.gz", hash = "sha256:3ecbf803a7fdf67229c0edada0830d6bfaea4d10bfb24f0c3f4e607cd1064b42", size = 3892203 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/48/d0/b71b65d1b36520dcb8291a2307d98b7fc12329a45614a303ff92ada4d723/av-16.1.0-cp311-cp311-macosx_11_0_x86_64.whl", hash = "sha256:e88ad64ee9d2b9c4c5d891f16c22ae78e725188b8926eb88187538d9dd0b232f", size = 26927747 },
+    { url = "https://files.pythonhosted.org/packages/18/8a/d57418b686ffd05fabd5a0a9cfa97e63b38c35d7101af00e87c51c8cc43c/av-14.4.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5b21d5586a88b9fce0ab78e26bd1c38f8642f8e2aad5b35e619f4d202217c701", size = 19965048 },
-    { url = "https://files.pythonhosted.org/packages/2f/79/720a5a6ccdee06eafa211b945b0a450e3a0b8fc3d12922f0f3c454d870d2/av-16.1.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:cb296073fa6935724de72593800ba86ae49ed48af03960a4aee34f8a611f442b", size = 21492232 },
+    { url = "https://files.pythonhosted.org/packages/f5/aa/3f878b0301efe587e9b07bb773dd6b47ef44ca09a3cffb4af50c08a170f3/av-14.4.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:cf8762d90b0f94a20c9f6e25a94f1757db5a256707964dfd0b1d4403e7a16835", size = 23750064 },
-    { url = "https://files.pythonhosted.org/packages/8e/4f/a1ba8d922f2f6d1a3d52419463ef26dd6c4d43ee364164a71b424b5ae204/av-16.1.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:720edd4d25aa73723c1532bb0597806d7b9af5ee34fc02358782c358cfe2f879", size = 39291737 },
+    { url = "https://files.pythonhosted.org/packages/9a/b4/6fe94a31f9ed3a927daa72df67c7151968587106f30f9f8fcd792b186633/av-14.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0ac9f08920c7bbe0795319689d901e27cb3d7870b9a0acae3f26fc9daa801a6", size = 33648775 },
-    { url = "https://files.pythonhosted.org/packages/1a/31/fc62b9fe8738d2693e18d99f040b219e26e8df894c10d065f27c6b4f07e3/av-16.1.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:c7f2bc703d0df260a1fdf4de4253c7f5500ca9fc57772ea241b0cb241bcf972e", size = 40846822 },
+    { url = "https://files.pythonhosted.org/packages/6c/f3/7f3130753521d779450c935aec3f4beefc8d4645471159f27b54e896470c/av-14.4.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a56d9ad2afdb638ec0404e962dc570960aae7e08ae331ad7ff70fbe99a6cf40e", size = 32216915 },
-    { url = "https://files.pythonhosted.org/packages/53/10/ab446583dbce730000e8e6beec6ec3c2753e628c7f78f334a35cad0317f4/av-16.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d69c393809babada7d54964d56099e4b30a3e1f8b5736ca5e27bd7be0e0f3c83", size = 40675604 },
+    { url = "https://files.pythonhosted.org/packages/f8/9a/8ffabfcafb42154b4b3a67d63f9b69e68fa8c34cb39ddd5cb813dd049ed4/av-14.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6bed513cbcb3437d0ae47743edc1f5b4a113c0b66cdd4e1aafc533abf5b2fbf2", size = 35287279 },
-    { url = "https://files.pythonhosted.org/packages/31/d7/1003be685277005f6d63fd9e64904ee222fe1f7a0ea70af313468bb597db/av-16.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:441892be28582356d53f282873c5a951592daaf71642c7f20165e3ddcb0b4c63", size = 42015955 },
+    { url = "https://files.pythonhosted.org/packages/ad/11/7023ba0a2ca94a57aedf3114ab8cfcecb0819b50c30982a4c5be4d31df41/av-14.4.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d030c2d3647931e53d51f2f6e0fcf465263e7acf9ec6e4faa8dbfc77975318c3", size = 36294683 },
-    { url = "https://files.pythonhosted.org/packages/2f/4a/fa2a38ee9306bf4579f556f94ecbc757520652eb91294d2a99c7cf7623b9/av-16.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:273a3e32de64819e4a1cd96341824299fe06f70c46f2288b5dc4173944f0fd62", size = 31750339 },
+    { url = "https://files.pythonhosted.org/packages/3d/fa/b8ac9636bd5034e2b899354468bef9f4dadb067420a16d8a493a514b7817/av-14.4.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:1cc21582a4f606271d8c2036ec7a6247df0831050306c55cf8a905701d0f0474", size = 34552391 },
-    { url = "https://files.pythonhosted.org/packages/9c/84/2535f55edcd426cebec02eb37b811b1b0c163f26b8d3f53b059e2ec32665/av-16.1.0-cp312-cp312-macosx_11_0_x86_64.whl", hash = "sha256:640f57b93f927fba8689f6966c956737ee95388a91bd0b8c8b5e0481f73513d6", size = 26945785 },
+    { url = "https://files.pythonhosted.org/packages/fb/29/0db48079c207d1cba7a2783896db5aec3816e17de55942262c244dffbc0f/av-14.4.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:ce7c9cd452153d36f1b1478f904ed5f9ab191d76db873bdd3a597193290805d4", size = 37265250 },
-    { url = "https://files.pythonhosted.org/packages/b6/17/ffb940c9e490bf42e86db4db1ff426ee1559cd355a69609ec1efe4d3a9eb/av-16.1.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:ae3fb658eec00852ebd7412fdc141f17f3ddce8afee2d2e1cf366263ad2a3b35", size = 21481147 },
+    { url = "https://files.pythonhosted.org/packages/1c/55/715858c3feb7efa4d667ce83a829c8e6ee3862e297fb2b568da3f968639d/av-14.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:fd261e31cc6b43ca722f80656c39934199d8f2eb391e0147e704b6226acebc29", size = 27925845 },
-    { url = "https://files.pythonhosted.org/packages/15/c1/e0d58003d2d83c3921887d5c8c9b8f5f7de9b58dc2194356a2656a45cfdc/av-16.1.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:27ee558d9c02a142eebcbe55578a6d817fedfde42ff5676275504e16d07a7f86", size = 39517197 },
+    { url = "https://files.pythonhosted.org/packages/a6/75/b8641653780336c90ba89e5352cac0afa6256a86a150c7703c0b38851c6d/av-14.4.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:a53e682b239dd23b4e3bc9568cfb1168fc629ab01925fdb2e7556eb426339e94", size = 19954125 },
-    { url = "https://files.pythonhosted.org/packages/32/77/787797b43475d1b90626af76f80bfb0c12cfec5e11eafcfc4151b8c80218/av-16.1.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:7ae547f6d5fa31763f73900d43901e8c5fa6367bb9a9840978d57b5a7ae14ed2", size = 41174337 },
+    { url = "https://files.pythonhosted.org/packages/99/e6/37fe6fa5853a48d54d749526365780a63a4bc530be6abf2115e3a21e292a/av-14.4.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:5aa0b901751a32703fa938d2155d56ce3faf3630e4a48d238b35d2f7e49e5395", size = 23751479 },
-    { url = "https://files.pythonhosted.org/packages/8e/ac/d90df7f1e3b97fc5554cf45076df5045f1e0a6adf13899e10121229b826c/av-16.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8cf065f9d438e1921dc31fc7aa045790b58aee71736897866420d80b5450f62a", size = 40817720 },
+    { url = "https://files.pythonhosted.org/packages/f7/75/9a5f0e6bda5f513b62bafd1cff2b495441a8b07ab7fb7b8e62f0c0d1683f/av-14.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a3b316fed3597675fe2aacfed34e25fc9d5bb0196dc8c0b014ae5ed4adda48de", size = 33801401 },
-    { url = "https://files.pythonhosted.org/packages/80/6f/13c3a35f9dbcebafd03fe0c4cbd075d71ac8968ec849a3cfce406c35a9d2/av-16.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:a345877a9d3cc0f08e2bc4ec163ee83176864b92587afb9d08dff50f37a9a829", size = 42267396 },
+    { url = "https://files.pythonhosted.org/packages/6a/c9/e4df32a2ad1cb7f3a112d0ed610c5e43c89da80b63c60d60e3dc23793ec0/av-14.4.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a587b5c5014c3c0e16143a0f8d99874e46b5d0c50db6111aa0b54206b5687c81", size = 32364330 },
-    { url = "https://files.pythonhosted.org/packages/c8/b9/275df9607f7fb44317ccb1d4be74827185c0d410f52b6e2cd770fe209118/av-16.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:f49243b1d27c91cd8c66fdba90a674e344eb8eb917264f36117bf2b6879118fd", size = 31752045 },
+    { url = "https://files.pythonhosted.org/packages/ca/f0/64e7444a41817fde49a07d0239c033f7e9280bec4a4bb4784f5c79af95e6/av-14.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10d53f75e8ac1ec8877a551c0db32a83c0aaeae719d05285281eaaba211bbc30", size = 35519508 },
+    { url = "https://files.pythonhosted.org/packages/c2/a8/a370099daa9033a3b6f9b9bd815304b3d8396907a14d09845f27467ba138/av-14.4.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c8558cfde79dd8fc92d97c70e0f0fa8c94c7a66f68ae73afdf58598f0fe5e10d", size = 36448593 },
+    { url = "https://files.pythonhosted.org/packages/27/bb/edb6ceff8fa7259cb6330c51dbfbc98dd1912bd6eb5f7bc05a4bb14a9d6e/av-14.4.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:455b6410dea0ab2d30234ffb28df7d62ca3cdf10708528e247bec3a4cdcced09", size = 34701485 },
+    { url = "https://files.pythonhosted.org/packages/a7/8a/957da1f581aa1faa9a5dfa8b47ca955edb47f2b76b949950933b457bfa1d/av-14.4.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:1661efbe9d975f927b8512d654704223d936f39016fad2ddab00aee7c40f412c", size = 37521981 },
+    { url = "https://files.pythonhosted.org/packages/28/76/3f1cf0568592f100fd68eb40ed8c491ce95ca3c1378cc2d4c1f6d1bd295d/av-14.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:fbbeef1f421a3461086853d6464ad5526b56ffe8ccb0ab3fd0a1f121dfbf26ad", size = 27925944 },
 ]
 
 [[package]]
@@ -3262,7 +3267,7 @@ requires-dist = [
     { name = "aiohttp-cors", specifier = ">=0.7.0" },
     { name = "aiortc", specifier = ">=1.5.0" },
     { name = "alembic", specifier = ">=1.11.3" },
-    { name = "av", specifier = ">=15.0.0" },
+    { name = "av", specifier = ">=10.0.0" },
     { name = "celery", specifier = ">=5.3.4" },
     { name = "databases", extras = ["aiosqlite", "asyncpg"], specifier = ">=0.7.0" },
     { name = "fastapi", extras = ["standard"], specifier = ">=0.100.1" },