chore(main): release 0.35.0 (#872)

* Single user/password for selfhosted

* fix revision id latest migration

.gitignore

@@ -23,3 +23,5 @@ www/.env.production
 docs/pnpm-lock.yaml
 .secrets
 opencode.json
+
+vibedocs/

.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

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ repos:
       - id: format
         name: run format
         language: system
-        entry: bash -c 'cd www && pnpm format'
+        entry: bash -c 'source "$HOME/.nvm/nvm.sh" && cd www && pnpm format'
         pass_filenames: false
         files: ^www/
 

CHANGELOG.md

@@ -1,5 +1,56 @@
 # Changelog
 
+## [0.35.0](https://github.com/Monadical-SAS/reflector/compare/v0.34.0...v0.35.0) (2026-02-23)
+
+
+### Features
+
+* Add Single User authentication to Selfhosted ([#870](https://github.com/Monadical-SAS/reflector/issues/870)) ([c8db373](https://github.com/Monadical-SAS/reflector/commit/c8db37362b6cfd8f772aee8857de2909f283c029))
+
+## [0.34.0](https://github.com/Monadical-SAS/reflector/compare/v0.33.0...v0.34.0) (2026-02-20)
+
+
+### Features
+
+* add Caddy reverse proxy with auto HTTPS for LAN access and auto-derive WebSocket URL ([#863](https://github.com/Monadical-SAS/reflector/issues/863)) ([7f2a401](https://github.com/Monadical-SAS/reflector/commit/7f2a4013cbb3d3ee3e76885f28d73331dcaf325c))
+* add change_seq to transcripts for ingestion support ([#868](https://github.com/Monadical-SAS/reflector/issues/868)) ([d4cc6be](https://github.com/Monadical-SAS/reflector/commit/d4cc6be1fed56ea7fba06acb8d50c9de43b26b07))
+* local llm support + standalone-script doc/draft ([#856](https://github.com/Monadical-SAS/reflector/issues/856)) ([b468427](https://github.com/Monadical-SAS/reflector/commit/b468427f1bb12634f5840990e9d64b2c145d7c1a))
+* remove network_mode host for standalone WebRTC ([#864](https://github.com/Monadical-SAS/reflector/issues/864)) ([9dbf155](https://github.com/Monadical-SAS/reflector/commit/9dbf155be4de7c059035a75f90c7bf0845344b74))
+* standalone frontend uses production build instead of dev server ([#862](https://github.com/Monadical-SAS/reflector/issues/862)) ([5bca925](https://github.com/Monadical-SAS/reflector/commit/5bca92510a5c33f8baeeaac2c346fb1978366ac8))
+
+
+### Bug Fixes
+
+* auto-rebuild standalone images and blank Hatchet vars ([3d13e5d](https://github.com/Monadical-SAS/reflector/commit/3d13e5d42fc53ce3c005841265ed1e8735a61518))
+* check compose version output, not just exit code ([e57c618](https://github.com/Monadical-SAS/reflector/commit/e57c6186f92d66e4525786e56b018c08cf792d2f))
+* check for Docker BuildKit (buildx) before building images ([14a8b58](https://github.com/Monadical-SAS/reflector/commit/14a8b5808e5aed860e55aaed35a0fdf8b2f4afa3))
+* check for Docker Compose plugin before running standalone setup ([36a8dae](https://github.com/Monadical-SAS/reflector/commit/36a8daee61c2b7a0937fd0914d51fb4ea8212ae7))
+* live flow real-time updates during processing ([#861](https://github.com/Monadical-SAS/reflector/issues/861)) ([972a52d](https://github.com/Monadical-SAS/reflector/commit/972a52d22f989f9e2c6f52362b3f1a4e17773663))
+* remove max_tokens cap to support thinking models (Kimi-K2.5) ([#869](https://github.com/Monadical-SAS/reflector/issues/869)) ([527a069](https://github.com/Monadical-SAS/reflector/commit/527a069ba9eff6717ccd4bb1e839674edebffceb))
+* standalone on ubuntu ([#865](https://github.com/Monadical-SAS/reflector/issues/865)) ([a8ad237](https://github.com/Monadical-SAS/reflector/commit/a8ad237d8571d5ef5c78fb4427c538592d6a7b43))
+* standalone server networking and setup diagnostics ([695f3c4](https://github.com/Monadical-SAS/reflector/commit/695f3c49285254869f6a6cbd5f860d1169fa4daa))
+
+## [0.33.0](https://github.com/Monadical-SAS/reflector/compare/v0.32.2...v0.33.0) (2026-02-05)
+
+
+### Features
+
+* Daily+hatchet default ([#846](https://github.com/Monadical-SAS/reflector/issues/846)) ([15ab2e3](https://github.com/Monadical-SAS/reflector/commit/15ab2e306eacf575494b4b5d2b2ad779d44a1c7f))
+
+
+### Bug Fixes
+
+* websocket tests ([#825](https://github.com/Monadical-SAS/reflector/issues/825)) ([1ce1c7a](https://github.com/Monadical-SAS/reflector/commit/1ce1c7a910b6c374115d2437b17f9d288ef094dc))
+
+## [0.32.2](https://github.com/Monadical-SAS/reflector/compare/v0.32.1...v0.32.2) (2026-02-03)
+
+
+### Bug Fixes
+
+* increase TIMEOUT_MEDIUM from 2m to 5m for LLM tasks ([#843](https://github.com/Monadical-SAS/reflector/issues/843)) ([4acde4b](https://github.com/Monadical-SAS/reflector/commit/4acde4b7fdef88cc02ca12cf38c9020b05ed96ac))
+* make caddy optional ([#841](https://github.com/Monadical-SAS/reflector/issues/841)) ([a2ed7d6](https://github.com/Monadical-SAS/reflector/commit/a2ed7d60d557b551a5b64e4dfd909b63a791d9fc))
+* use Daily API recording.duration as master source for transcript duration ([#844](https://github.com/Monadical-SAS/reflector/issues/844)) ([8707c66](https://github.com/Monadical-SAS/reflector/commit/8707c6694a80c939b6214bbc13331741f192e082))
+
 ## [0.32.1](https://github.com/Monadical-SAS/reflector/compare/v0.32.0...v0.32.1) (2026-01-30)
 
 

Caddyfile.selfhosted.example

@@ -0,0 +1,25 @@
+# Reflector self-hosted production — HTTPS via Caddy reverse proxy
+# Copy to Caddyfile: cp Caddyfile.selfhosted.example Caddyfile
+# Run: ./scripts/setup-selfhosted.sh --ollama-gpu --garage --caddy
+#
+# DOMAIN defaults to localhost (self-signed cert).
+# Set to your real domain for automatic Let's Encrypt:
+#   export DOMAIN=reflector.example.com
+#
+# TLS_MODE defaults to "internal" (self-signed).
+# Set to "" for automatic Let's Encrypt (requires real domain + ports 80/443 open):
+#   export TLS_MODE=""
+
+{$DOMAIN:localhost} {
+    tls {$TLS_MODE:internal}
+
+    handle /v1/* {
+        reverse_proxy server:1250
+    }
+    handle /health {
+        reverse_proxy server:1250
+    }
+    handle {
+        reverse_proxy web:3000
+    }
+}

Caddyfile.standalone.example

@@ -0,0 +1,42 @@
+# Reflector standalone — HTTPS via Caddy (droplet / IP access)
+# Copy to Caddyfile: cp Caddyfile.standalone.example Caddyfile
+# Run: docker compose -f docker-compose.standalone.yml --profile ollama-cpu up -d
+#
+# :443 = catch-all inside container; Docker maps host port 3043 → container 443
+# on_demand = generate self-signed cert for IP/SNI on first request (required for bare IP access)
+# Browser will warn. Click Advanced → Proceed.
+# Access at https://localhost:3043 (or https://YOUR_IP:3043 on droplet)
+# Update www/.env.local with: API_URL=https://YOUR_IP:3043, WEBSOCKET_URL=wss://YOUR_IP:3043, SITE_URL=https://YOUR_IP:3043, NEXTAUTH_URL=https://YOUR_IP:3043
+
+:443 {
+    tls internal {
+        on_demand
+    }
+    handle /v1/* {
+        reverse_proxy server:1250
+    }
+    handle /health {
+        reverse_proxy server:1250
+    }
+    handle {
+        reverse_proxy web:3000
+    }
+}
+
+# Option B: localhost (comment Option A, uncomment this)
+# app.localhost {
+#     tls internal
+#     reverse_proxy web:3000
+# }
+# api.localhost {
+#     tls internal
+#     reverse_proxy server:1250
+# }
+
+# Option C: Real domain (uncomment and replace example.com)
+# app.example.com {
+#     reverse_proxy web:3000
+# }
+# api.example.com {
+#     reverse_proxy server:1250
+# }

README.md

@@ -44,22 +44,100 @@ Reflector is a web application that utilizes local models to process audio conte
 - **Topic Detection & Summarization**: Extract key topics and generate concise summaries using LLMs
 - **Meeting Recording**: Create permanent records of meetings with searchable transcripts
 
-Currently we provide [modal.com](https://modal.com/) gpu template to deploy.
+## Architecture
 
-## Background
+The project consists of three primary components:
 
-The project architecture consists of three primary components:
+- **Back-End**: Python FastAPI server with async database operations and background processing, found in `server/`.
+- **Front-End**: Next.js 14 React application with Chakra UI, located in `www/`.
+- **GPU Models**: Specialized ML models for transcription, diarization, translation, and summarization.
 
-- **Back-End**: Python server that offers an API and data persistence, found in `server/`.
-- **Front-End**: NextJS React project hosted on Vercel, located in `www/`.
-- **GPU implementation**: Providing services such as speech-to-text transcription, topic generation, automated summaries, and translations.
+Currently, Reflector supports two input methods:
+- **Screenshare capture**: Real-time audio capture from your browser via WebRTC
+- **Audio file upload**: Upload pre-recorded audio files for processing
 
-It also uses authentik for authentication if activated.
+## Installation
 
-## Contribution Guidelines
+For full deployment instructions, see the [Self-Hosted Production Guide](docsv2/selfhosted-production.md) and the [Architecture Reference](docsv2/selfhosted-architecture.md).
 
-All new contributions should be made in a separate branch, and goes through a Pull Request.
-[Conventional commits](https://www.conventionalcommits.org/en/v1.0.0/) must be used for the PR title and commits.
+### Self-Hosted Deployment
+
+The self-hosted setup script configures and launches everything on a single server:
+
+```bash
+# GPU with local Ollama LLM, local S3 storage, and Caddy reverse proxy
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# With a custom domain (enables Let's Encrypt auto-HTTPS)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --domain reflector.example.com
+
+# CPU-only mode (slower, no NVIDIA GPU required)
+./scripts/setup-selfhosted.sh --cpu --ollama-cpu --garage --caddy
+
+# With password authentication
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+```
+
+The script is idempotent and safe to re-run. See `./scripts/setup-selfhosted.sh --help` for all options.
+
+### Authentication
+
+Reflector supports three authentication modes:
+
+- **Password authentication (recommended for self-hosted / single-user)**: Use the `--password` flag in the setup script. This creates an `admin@localhost` user with the provided password. Users must log in to create, edit, or delete transcripts.
+
+  ```bash
+  ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+  ```
+
+- **Authentik OIDC**: For multi-user or enterprise deployments, Reflector supports [Authentik](https://goauthentik.io/) as an OAuth/OIDC provider. This enables SSO, LDAP/AD integration, and centralized user management. Requires configuring `AUTH_BACKEND=jwt` on the backend and `AUTH_PROVIDER=authentik` on the frontend. See the [Self-Hosted Production Guide](docsv2/selfhosted-production.md) for details.
+
+- **Public mode (default when no auth is configured)**: If neither password nor Authentik is set up, Reflector runs in public mode. In this mode, no login is required — anyone with access to the URL can use the application. Transcripts are created anonymously (not tied to any user account), which means they **cannot be edited or deleted** through the UI or API. Anonymous transcripts are automatically cleaned up after 7 days. This mode is suitable for demos or testing but not recommended for production use.
+
+### Development Setup
+
+```bash
+# Backend
+cd server
+uv sync
+docker compose up -d redis
+uv run alembic upgrade head
+uv run -m reflector.app --reload
+
+# In a separate terminal — start the worker
+cd server
+uv run celery -A reflector.worker.app worker --loglevel=info
+
+# Frontend
+cd www
+pnpm install
+cp .env_template .env
+pnpm dev
+```
+
+### Modal.com GPU (Optional)
+
+Reflector also supports deploying specialized models (transcription, diarization) to [Modal.com](https://modal.com/) for serverless GPU processing. This is **not integrated into the self-hosted setup script** and must be configured manually.
+
+See [Modal.com Setup Guide](docs/docs/installation/modal-setup.md) for deployment instructions.
+
+## Audio Processing Commands
+
+### Process a local audio file
+
+```bash
+cd server
+uv run python -m reflector.tools.process path/to/audio.wav
+```
+
+### Reprocess an existing transcription
+
+Re-run the processing pipeline on a previously uploaded transcription by its UUID:
+
+```bash
+cd server
+uv run -m reflector.tools.process_transcript <transcript-uuid> --sync
+```
 
 ## Usage
 
@@ -87,96 +165,9 @@ Note: We currently do not have instructions for Windows users.
 - Then goto `System Preferences -> Sound` and choose the devices created from the Output and Input tabs.
 - The input from your local microphone, the browser run meeting should be aggregated into one virtual stream to listen to and the output should be fed back to your specified output devices if everything is configured properly.
 
-## Installation
-
-*Note: we're working toward better installation, theses instructions are not accurate for now*
-
-### Frontend
-
-Start with `cd www`.
-
-**Installation**
-
-```bash
-pnpm install
-cp .env.example .env
-```
-
-Then, fill in the environment variables in `.env` as needed. If you are unsure on how to proceed, ask in Zulip.
-
-**Run in development mode**
-
-```bash
-pnpm dev
-```
-
-Then (after completing server setup and starting it) open [http://localhost:3000](http://localhost:3000) to view it in the browser.
-
-**OpenAPI Code Generation**
-
-To generate the TypeScript files from the openapi.json file, make sure the python server is running, then run:
-
-```bash
-pnpm openapi
-```
-
-### Backend
-
-Start with `cd server`.
-
-**Run in development mode**
-
-```bash
-docker compose up -d redis
-
-# on the first run, or if the schemas changed
-uv run alembic upgrade head
-
-# start the worker
-uv run celery -A reflector.worker.app worker --loglevel=info
-
-# start the app
-uv run -m reflector.app --reload
-```
-
-Then fill `.env` with the omitted values (ask in Zulip).
-
-**Crontab (optional)**
-
-For crontab (only healthcheck for now), start the celery beat (you don't need it on your local dev environment):
-
-```bash
-uv run celery -A reflector.worker.app beat
-```
-
-### GPU models
-
-Currently, reflector heavily use custom local models, deployed on modal. All the micro services are available in server/gpu/
-
-To deploy llm changes to modal, you need:
-- a modal account
-- set up the required secret in your modal account (REFLECTOR_GPU_APIKEY)
-- install the modal cli
-- connect your modal cli to your account if not done previously
-- `modal run path/to/required/llm`
-
-## Using local files
-
-You can manually process an audio file by calling the process tool:
-
-```bash
-uv run python -m reflector.tools.process path/to/audio.wav
-```
-
-## Reprocessing any transcription
-
-```bash
-uv run -m reflector.tools.process_transcript 81ec38d1-9dd7-43d2-b3f8-51f4d34a07cd --sync
-```
-
 ## Build-time env variables
 
-Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a ccustomizable prebuild docker container.
+Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a customizable prebuilt docker container.
 
 Instead, all the variables are runtime. Variables needed to the frontend are served to the frontend app at initial render.
 
@@ -211,3 +202,16 @@ FEATURE_BROWSE=false
 # Enable Zulip integration
 FEATURE_SEND_TO_ZULIP=true
 ```
+
+## Contribution Guidelines
+
+All new contributions should be made in a separate branch, and goes through a Pull Request.
+[Conventional commits](https://www.conventionalcommits.org/en/v1.0.0/) must be used for the PR title and commits.
+
+## Future Plans
+
+- **Daily.co integration with multitrack processing**: Support for Daily.co live rooms with per-participant audio tracks for improved diarization and transcription quality.
+
+## Legacy Documentation
+
+The `docs/` folder contains an older Docusaurus-based documentation site. These docs are **no longer actively maintained** and may be outdated. For current installation and deployment instructions, refer to the [`docsv2/`](docsv2/) folder instead.

docker-compose.selfhosted.yml

@@ -0,0 +1,321 @@
+# Self-hosted production Docker Compose — single file for everything.
+#
+# Usage: ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+#   or:  docker compose -f docker-compose.selfhosted.yml --profile gpu [--profile ollama-gpu] [--profile garage] [--profile caddy] up -d
+#
+# Specialized models (pick ONE — required):
+#   --profile gpu          NVIDIA GPU for transcription/diarization/translation
+#   --profile cpu          CPU-only for transcription/diarization/translation
+#
+# Local LLM (optional — for summarization/topics):
+#   --profile ollama-gpu   Local Ollama with NVIDIA GPU
+#   --profile ollama-cpu   Local Ollama on CPU only
+#
+# Other optional services:
+#   --profile garage       Local S3-compatible storage (Garage)
+#   --profile caddy        Reverse proxy with auto-SSL
+#
+# Prerequisites:
+#   1. Run ./scripts/setup-selfhosted.sh to generate env files and secrets
+#   2. Or manually create server/.env and www/.env from the .selfhosted.example templates
+
+services:
+  # ===========================================================
+  # Always-on core services (no profile required)
+  # ===========================================================
+
+  server:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:1250:1250"
+      - "50000-50100:50000-50100/udp"
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: server
+      # Docker-internal overrides (always correct inside compose network)
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      HATCHET_CLIENT_SERVER_URL: ""
+      HATCHET_CLIENT_HOST_PORT: ""
+      # Specialized models via gpu/cpu container (aliased as "transcription")
+      TRANSCRIPT_BACKEND: modal
+      TRANSCRIPT_URL: http://transcription:8000
+      TRANSCRIPT_MODAL_API_KEY: selfhosted
+      DIARIZATION_BACKEND: modal
+      DIARIZATION_URL: http://transcription:8000
+      TRANSLATION_BACKEND: modal
+      TRANSLATE_URL: http://transcription:8000
+      # WebRTC: fixed UDP port range for ICE candidates (mapped above)
+      WEBRTC_PORT_RANGE: "50000-50100"
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    volumes:
+      - server_data:/app/data
+
+  worker:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: worker
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      HATCHET_CLIENT_SERVER_URL: ""
+      HATCHET_CLIENT_HOST_PORT: ""
+      TRANSCRIPT_BACKEND: modal
+      TRANSCRIPT_URL: http://transcription:8000
+      TRANSCRIPT_MODAL_API_KEY: selfhosted
+      DIARIZATION_BACKEND: modal
+      DIARIZATION_URL: http://transcription:8000
+      TRANSLATION_BACKEND: modal
+      TRANSLATE_URL: http://transcription:8000
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    volumes:
+      - server_data:/app/data
+
+  beat:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: beat
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+
+  web:
+    build:
+      context: ./www
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-frontend:latest
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:3000:3000"
+    env_file:
+      - ./www/.env
+    environment:
+      NODE_ENV: production
+      NODE_TLS_REJECT_UNAUTHORIZED: "0"
+      SERVER_API_URL: http://server:1250
+      KV_URL: redis://redis:6379
+      KV_USE_TLS: "false"
+      NEXTAUTH_URL_INTERNAL: http://localhost:3000
+    depends_on:
+      - redis
+
+  redis:
+    image: redis:7.2-alpine
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 30s
+      timeout: 3s
+      retries: 3
+    volumes:
+      - redis_data:/data
+
+  postgres:
+    image: postgres:17-alpine
+    restart: unless-stopped
+    environment:
+      POSTGRES_USER: reflector
+      POSTGRES_PASSWORD: reflector
+      POSTGRES_DB: reflector
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U reflector"]
+      interval: 30s
+      timeout: 3s
+      retries: 3
+
+  # ===========================================================
+  # Specialized model containers (transcription, diarization, translation)
+  # Both gpu and cpu get alias "transcription" so server config never changes.
+  # ===========================================================
+
+  gpu:
+    build:
+      context: ./gpu/self_hosted
+      dockerfile: Dockerfile
+    profiles: [gpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:8000:8000"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-}
+    volumes:
+      - gpu_cache:/root/.cache
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+    networks:
+      default:
+        aliases:
+          - transcription
+
+  cpu:
+    build:
+      context: ./gpu/self_hosted
+      dockerfile: Dockerfile.cpu
+    profiles: [cpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:8000:8000"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-}
+    volumes:
+      - gpu_cache:/root/.cache
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+    networks:
+      default:
+        aliases:
+          - transcription
+
+  # ===========================================================
+  # Ollama — local LLM for summarization & topic detection
+  # Only started with --ollama-gpu or --ollama-cpu modes.
+  # ===========================================================
+
+  ollama:
+    image: ollama/ollama:latest
+    profiles: [ollama-gpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:11435:11435"
+    volumes:
+      - ollama_data:/root/.ollama
+    environment:
+      OLLAMA_HOST: "0.0.0.0:11435"
+      OLLAMA_KEEP_ALIVE: "24h"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  ollama-cpu:
+    image: ollama/ollama:latest
+    profiles: [ollama-cpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:11435:11435"
+    volumes:
+      - ollama_data:/root/.ollama
+    environment:
+      OLLAMA_HOST: "0.0.0.0:11435"
+      OLLAMA_KEEP_ALIVE: "24h"         # keep model loaded to avoid reload delays
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  # ===========================================================
+  # Garage — local S3-compatible object storage (optional)
+  # ===========================================================
+
+  garage:
+    image: dxflrs/garage:v1.1.0
+    profiles: [garage]
+    restart: unless-stopped
+    ports:
+      - "3900:3900"   # S3 API
+      - "3903:3903"   # Admin API
+    volumes:
+      - garage_data:/var/lib/garage/data
+      - garage_meta:/var/lib/garage/meta
+      - ./data/garage.toml:/etc/garage.toml:ro
+    healthcheck:
+      test: ["CMD", "/garage", "stats"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+
+  # ===========================================================
+  # Caddy — reverse proxy with automatic SSL (optional)
+  # Maps 80:80 and 443:443 — only exposed ports in the stack.
+  # ===========================================================
+
+  caddy:
+    image: caddy:2-alpine
+    profiles: [caddy]
+    restart: unless-stopped
+    ports:
+      - "80:80"
+      - "443:443"
+    volumes:
+      - ./Caddyfile:/etc/caddy/Caddyfile:ro
+      - caddy_data:/data
+      - caddy_config:/config
+    depends_on:
+      - web
+      - server
+
+volumes:
+  postgres_data:
+  redis_data:
+  server_data:
+  gpu_cache:
+  garage_data:
+  garage_meta:
+  ollama_data:
+  caddy_data:
+  caddy_config:
+
+networks:
+  default:
+    attachable: true

docker-compose.standalone.yml

@@ -0,0 +1,241 @@
+# Self-contained standalone compose for fully local deployment (no external dependencies).
+# Usage: docker compose -f docker-compose.standalone.yml up -d
+#
+# On Linux with NVIDIA GPU, also pass: --profile ollama-gpu
+# On Linux without GPU:                --profile ollama-cpu
+# On Mac: Ollama runs natively (Metal GPU) — no profile needed, services here unused.
+
+services:
+  caddy:
+    image: caddy:2-alpine
+    restart: unless-stopped
+    ports:
+      - "3043:443"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - ./Caddyfile:/etc/caddy/Caddyfile:ro
+      - caddy_data:/data
+      - caddy_config:/config
+    depends_on:
+      - web
+      - server
+
+  server:
+    build:
+      context: server
+    ports:
+      - "1250:1250"
+      - "50000-50100:50000-50100/udp"
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - ./server/:/app/
+      - /app/.venv
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: server
+      # Docker DNS names instead of localhost
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      # Standalone doesn't run Hatchet
+      HATCHET_CLIENT_SERVER_URL: ""
+      HATCHET_CLIENT_HOST_PORT: ""
+      # Self-hosted transcription/diarization via CPU service
+      TRANSCRIPT_BACKEND: modal
+      TRANSCRIPT_URL: http://cpu:8000
+      TRANSCRIPT_MODAL_API_KEY: local
+      DIARIZATION_BACKEND: modal
+      DIARIZATION_URL: http://cpu:8000
+      # Caddy reverse proxy prefix
+      ROOT_PATH: /server-api
+      # WebRTC: fixed UDP port range for ICE candidates (mapped above).
+      # WEBRTC_HOST is set by setup-standalone.sh in server/.env (LAN IP detection).
+      WEBRTC_PORT_RANGE: "50000-50100"
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+
+  worker:
+    build:
+      context: server
+    volumes:
+      - ./server/:/app/
+      - /app/.venv
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: worker
+      HATCHET_CLIENT_SERVER_URL: ""
+      HATCHET_CLIENT_HOST_PORT: ""
+      TRANSCRIPT_BACKEND: modal
+      TRANSCRIPT_URL: http://cpu:8000
+      TRANSCRIPT_MODAL_API_KEY: local
+      DIARIZATION_BACKEND: modal
+      DIARIZATION_URL: http://cpu:8000
+    depends_on:
+      redis:
+        condition: service_started
+
+  beat:
+    build:
+      context: server
+    volumes:
+      - ./server/:/app/
+      - /app/.venv
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: beat
+    depends_on:
+      redis:
+        condition: service_started
+
+  redis:
+    image: redis:7.2
+    ports:
+      - 6379:6379
+
+  postgres:
+    image: postgres:17
+    command: postgres -c 'max_connections=200'
+    ports:
+      - 5432:5432
+    environment:
+      POSTGRES_USER: reflector
+      POSTGRES_PASSWORD: reflector
+      POSTGRES_DB: reflector
+    volumes:
+      - ./data/postgres:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -d reflector -U reflector"]
+      interval: 5s
+      timeout: 5s
+      retries: 10
+      start_period: 15s
+
+  web:
+    image: reflector-frontend-standalone
+    build:
+      context: ./www
+    ports:
+      - "3000:3000"
+    command: ["node", "server.js"]
+    env_file:
+      - ./www/.env.local
+    environment:
+      NODE_ENV: production
+      # API_URL, WEBSOCKET_URL, SITE_URL, NEXTAUTH_URL from www/.env.local (allows HTTPS)
+      # Server-side URLs (docker-network internal)
+      SERVER_API_URL: http://server:1250
+      KV_URL: redis://redis:6379
+      KV_USE_TLS: "false"
+      # Standalone: no external auth provider
+      FEATURE_REQUIRE_LOGIN: "false"
+      FEATURE_ROOMS: "false"
+      NEXTAUTH_SECRET: standalone-local-secret
+      # Nullify partial auth vars inherited from base env_file
+      AUTHENTIK_ISSUER: ""
+      AUTHENTIK_REFRESH_TOKEN_URL: ""
+
+  garage:
+    image: dxflrs/garage:v1.1.0
+    ports:
+      - "3900:3900"   # S3 API
+      - "3903:3903"   # Admin API
+    volumes:
+      - garage_data:/var/lib/garage/data
+      - garage_meta:/var/lib/garage/meta
+      - ./data/garage.toml:/etc/garage.toml:ro
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "/garage", "stats"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+
+  cpu:
+    build:
+      context: ./gpu/self_hosted
+      dockerfile: Dockerfile.cpu
+    ports:
+      - "8100:8000"
+    volumes:
+      - gpu_cache:/root/.cache
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+
+  gpu-nvidia:
+    build:
+      context: ./gpu/self_hosted
+    profiles: ["gpu-nvidia"]
+    volumes:
+      - gpu_cache:/root/.cache
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+
+  ollama:
+    image: ollama/ollama:latest
+    profiles: ["ollama-gpu"]
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama_data:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  ollama-cpu:
+    image: ollama/ollama:latest
+    profiles: ["ollama-cpu"]
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama_data:/root/.ollama
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+volumes:
+  garage_data:
+  garage_meta:
+  ollama_data:
+  gpu_cache:
+  caddy_data:
+  caddy_config:

docker-compose.yml

@@ -2,8 +2,7 @@ services:
   server:
     build:
       context: server
-    ports:
-      - 1250:1250
+    network_mode: host
     volumes:
       - ./server/:/app/
       - /app/.venv
@@ -11,6 +10,12 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: server
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@localhost:5432/reflector
+      REDIS_HOST: localhost
+      CELERY_BROKER_URL: redis://localhost:6379/1
+      CELERY_RESULT_BACKEND: redis://localhost:6379/1
+      HATCHET_CLIENT_SERVER_URL: http://localhost:8889
+      HATCHET_CLIENT_HOST_PORT: localhost:7078
 
   worker:
     build:
@@ -22,6 +27,11 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: worker
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
+    depends_on:
+      redis:
+        condition: service_started
 
   beat:
     build:
@@ -33,6 +43,9 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: beat
+    depends_on:
+      redis:
+        condition: service_started
 
   hatchet-worker-cpu:
     build:
@@ -44,6 +57,8 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: hatchet-worker-cpu
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
     depends_on:
       hatchet:
         condition: service_healthy
@@ -57,6 +72,8 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: hatchet-worker-llm
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
     depends_on:
       hatchet:
         condition: service_healthy
@@ -75,10 +92,16 @@ services:
     volumes:
       - ./www:/app/
       - /app/node_modules
+      - next_cache:/app/.next
     env_file:
       - ./www/.env.local
     environment:
       - NODE_ENV=development
+      - SERVER_API_URL=http://host.docker.internal:1250
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    depends_on:
+      - server
 
   postgres:
     image: postgres:17
@@ -94,13 +117,14 @@ services:
       - ./server/docker/init-hatchet-db.sql:/docker-entrypoint-initdb.d/init-hatchet-db.sql:ro
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -d reflector -U reflector"]
-      interval: 10s
-      timeout: 10s
-      retries: 5
-      start_period: 10s
+      interval: 5s
+      timeout: 5s
+      retries: 10
+      start_period: 15s
 
   hatchet:
     image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
+    restart: on-failure
     ports:
       - "8889:8888"
       - "7078:7077"
@@ -108,7 +132,7 @@ services:
       postgres:
         condition: service_healthy
     environment:
-      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable"
+      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable&connect_timeout=30"
       SERVER_AUTH_COOKIE_DOMAIN: localhost
       SERVER_AUTH_COOKIE_INSECURE: "t"
       SERVER_GRPC_BIND_ADDRESS: "0.0.0.0"
@@ -128,6 +152,5 @@ services:
       retries: 5
       start_period: 30s
 
-networks:
-  default:
-    attachable: true
+volumes:
+  next_cache:

docs/docs/installation/setup-standalone.md

@@ -0,0 +1,310 @@
+---
+sidebar_position: 2
+title: Standalone Local Setup
+---
+
+# Standalone Local Setup
+
+**The goal**: a clueless user clones the repo, runs one script, and has a working Reflector instance locally. No cloud accounts, no API keys, no manual env file editing.
+
+```bash
+git clone https://github.com/monadical-sas/reflector.git
+cd reflector
+./scripts/setup-standalone.sh
+```
+
+On Ubuntu, the setup script installs Docker automatically if missing.
+
+The script is idempotent — safe to re-run at any time. It detects what's already set up and skips completed steps.
+
+## Prerequisites
+
+- Docker with Compose V2 plugin (Docker Desktop, OrbStack, or Docker Engine + compose plugin)
+- Mac (Apple Silicon) or Linux
+- 16GB+ RAM (32GB recommended for 14B LLM models)
+- **Mac only**: [Ollama](https://ollama.com/download) installed (`brew install ollama`)
+
+### Installing Docker (if not already installed)
+
+**Ubuntu**: The setup script runs `install-docker-ubuntu.sh` automatically when Docker is missing. Or run it manually:
+
+```bash
+./scripts/install-docker-ubuntu.sh
+```
+
+**Mac**: Install [Docker Desktop](https://www.docker.com/products/docker-desktop/) or [OrbStack](https://orbstack.dev/).
+
+## What the script does
+
+### 1. LLM inference via Ollama
+
+**Mac**: starts Ollama natively (Metal GPU acceleration). Pulls the LLM model. Docker containers reach it via `host.docker.internal:11435`.
+
+**Linux**: starts containerized Ollama via `docker-compose.standalone.yml` profile (`ollama-gpu` with NVIDIA, `ollama-cpu` without). Pulls model inside the container.
+
+### 2. Environment files
+
+Generates `server/.env` and `www/.env.local` with standalone defaults:
+
+**`server/.env`** — key settings:
+
+| Variable              | Value                                              | Why                                 |
+| --------------------- | -------------------------------------------------- | ----------------------------------- |
+| `DATABASE_URL`        | `postgresql+asyncpg://...@postgres:5432/reflector` | Docker-internal hostname            |
+| `REDIS_HOST`          | `redis`                                            | Docker-internal hostname            |
+| `CELERY_BROKER_URL`   | `redis://redis:6379/1`                             | Docker-internal hostname            |
+| `AUTH_BACKEND`        | `none`                                             | No Authentik in standalone          |
+| `TRANSCRIPT_BACKEND`  | `modal`                                            | HTTP API to self-hosted CPU service |
+| `TRANSCRIPT_URL`      | `http://cpu:8000`                                  | Docker-internal CPU service         |
+| `DIARIZATION_BACKEND` | `modal`                                            | HTTP API to self-hosted CPU service |
+| `DIARIZATION_URL`     | `http://cpu:8000`                                  | Docker-internal CPU service         |
+| `TRANSLATION_BACKEND` | `passthrough`                                      | No Modal                            |
+| `LLM_URL`             | `http://host.docker.internal:11435/v1` (Mac)       | Ollama endpoint                     |
+
+**`www/.env.local`** — key settings:
+
+| Variable                | Value                                      |
+| ----------------------- | ------------------------------------------ |
+| `API_URL`               | `https://localhost:3043` or `https://YOUR_IP:3043` (Linux) |
+| `SERVER_API_URL`        | `http://server:1250`                       |
+| `WEBSOCKET_URL`         | `auto`                                    |
+| `FEATURE_REQUIRE_LOGIN` | `false`                                    |
+| `NEXTAUTH_SECRET`       | `standalone-dev-secret-not-for-production` |
+
+If env files already exist (including symlinks from worktree setup), the script resolves symlinks and ensures all standalone-critical vars are set. Existing vars not related to standalone are preserved.
+
+### 3. Object storage (Garage)
+
+Standalone uses [Garage](https://garagehq.deuxfleurs.fr/) — a lightweight S3-compatible object store running in Docker. The setup script starts Garage, initializes the layout, creates a bucket and access key, and writes the credentials to `server/.env`.
+
+**`server/.env`** — storage settings added by the script:
+
+| Variable                                   | Value                | Why                                   |
+| ------------------------------------------ | -------------------- | ------------------------------------- |
+| `TRANSCRIPT_STORAGE_BACKEND`               | `aws`                | Uses the S3-compatible storage driver |
+| `TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL`      | `http://garage:3900` | Docker-internal Garage S3 API         |
+| `TRANSCRIPT_STORAGE_AWS_BUCKET_NAME`       | `reflector-media`    | Created by the script                 |
+| `TRANSCRIPT_STORAGE_AWS_REGION`            | `garage`             | Must match Garage config              |
+| `TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID`     | _(auto-generated)_   | Created by `garage key create`        |
+| `TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY` | _(auto-generated)_   | Created by `garage key create`        |
+
+The `TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL` setting enables S3-compatible backends. When set, the storage driver uses path-style addressing and routes all requests to the custom endpoint. When unset (production AWS), behavior is unchanged.
+
+Garage config template lives at `scripts/garage.toml`. The setup script generates `data/garage.toml` (gitignored) with a random RPC secret and mounts it read-only into the container. Single-node, `replication_factor=1`.
+
+> **Note**: Presigned URLs embed the Garage Docker hostname (`http://garage:3900`). This is fine — the server proxies S3 responses to the browser. Modal GPU workers cannot reach internal Garage, but standalone doesn't use Modal.
+
+### 4. Transcription and diarization
+
+Standalone runs the self-hosted ML service (`gpu/self_hosted/`) in a CPU-only Docker container named `cpu`. This is the same FastAPI service used for Modal.com GPU deployments, but built with `Dockerfile.cpu` (no NVIDIA CUDA dependencies). The compose service is named `cpu` (not `gpu`) to make clear it runs without GPU acceleration; the source code lives in `gpu/self_hosted/` because it's shared with the GPU deployment.
+
+The `modal` backend name is reused — it just means "HTTP API client". Setting `TRANSCRIPT_URL` / `DIARIZATION_URL` to `http://cpu:8000` routes requests to the local container instead of Modal.com.
+
+On first start, the service downloads pyannote speaker diarization models (~1GB) from a public S3 bundle. Models are cached in a Docker volume (`gpu_cache`) so subsequent starts are fast. No HuggingFace token or API key needed.
+
+> **Performance**: CPU-only transcription and diarization work but are slow (~15 min for a 3 min file). For faster processing on Linux with NVIDIA GPU, use `--profile gpu-nvidia` instead (see `docker-compose.standalone.yml`).
+
+### 5. Docker services
+
+```bash
+docker compose up -d postgres redis garage cpu server worker beat web
+```
+
+All services start in a single command. Garage and `cpu` are already started by earlier steps but included for idempotency. No Hatchet in standalone mode — LLM processing (summaries, topics, titles) runs via Celery tasks.
+
+### 6. Database migrations
+
+Run automatically by the `server` container on startup (`runserver.sh` calls `alembic upgrade head`). No manual step needed.
+
+### 7. Health check
+
+Verifies:
+
+- CPU service responds (transcription + diarization ready)
+- Server responds at `http://localhost:1250/health`
+- Frontend serves at `http://localhost:3000` (or via Caddy at `https://localhost:3043`)
+- LLM endpoint reachable from inside containers
+
+## Services
+
+| Service    | Port       | Purpose                                            |
+| ---------- | ---------- | -------------------------------------------------- |
+| `caddy`    | 3043       | Reverse proxy (HTTPS, self-signed cert)            |
+| `server`   | 1250       | FastAPI backend (runs migrations on start)         |
+| `web`      | 3000       | Next.js frontend                                   |
+| `postgres` | 5432       | PostgreSQL database                                |
+| `redis`    | 6379       | Cache + Celery broker                              |
+| `garage`   | 3900, 3903 | S3-compatible object storage (S3 API + admin API)  |
+| `cpu`      | —          | Self-hosted transcription + diarization (CPU-only) |
+| `worker`   | —          | Celery worker (live pipeline post-processing)      |
+| `beat`     | —          | Celery beat (scheduled tasks)                      |
+
+## Testing programmatically
+
+After the setup script completes, verify the full pipeline (upload, transcription, diarization, LLM summary) via the API:
+
+```bash
+# 1. Create a transcript
+TRANSCRIPT_ID=$(curl -s -X POST 'http://localhost:1250/v1/transcripts' \
+  -H 'Content-Type: application/json' \
+  -d '{"name":"test-upload"}' | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
+echo "Created: $TRANSCRIPT_ID"
+
+# 2. Upload an audio file (single-chunk upload)
+curl -s "http://localhost:1250/v1/transcripts/${TRANSCRIPT_ID}/record/upload?chunk_number=0&total_chunks=1" \
+  -X POST -F "chunk=@/path/to/audio.mp3"
+
+# 3. Poll until processing completes (status: ended or error)
+while true; do
+  STATUS=$(curl -s "http://localhost:1250/v1/transcripts/${TRANSCRIPT_ID}" \
+    | python3 -c "import sys,json; print(json.load(sys.stdin)['status'])")
+  echo "Status: $STATUS"
+  case "$STATUS" in ended|error) break;; esac
+  sleep 10
+done
+
+# 4. Check the result
+curl -s "http://localhost:1250/v1/transcripts/${TRANSCRIPT_ID}" | python3 -m json.tool
+```
+
+Expected result: status `ended`, auto-generated `title`, `short_summary`, `long_summary`, and `transcript` text with `Speaker 0` / `Speaker 1` labels.
+
+CPU-only processing is slow (~15 min for a 3 min audio file). Diarization finishes in ~3 min, transcription takes the rest.
+
+## Enabling HTTPS (droplet via IP)
+
+To serve Reflector over HTTPS on a droplet accessed by IP (self-signed certificate):
+
+1. **Copy the Caddyfile** (no edits needed — `:443` catches all HTTPS inside container, mapped to host port 3043):
+   ```bash
+   cp Caddyfile.standalone.example Caddyfile
+   ```
+
+2. **Update `www/.env.local`** with HTTPS URLs (port 3043):
+   ```env
+   API_URL=https://YOUR_IP:3043
+   WEBSOCKET_URL=wss://YOUR_IP:3043
+   SITE_URL=https://YOUR_IP:3043
+   NEXTAUTH_URL=https://YOUR_IP:3043
+   ```
+
+3. **Restart services**:
+   ```bash
+   docker compose -f docker-compose.standalone.yml --profile ollama-cpu up -d
+   ```
+   (Use `ollama-gpu` instead of `ollama-cpu` if you have an NVIDIA GPU.)
+
+4. **Access** at `https://YOUR_IP:3043`. The browser will warn about the self-signed cert — click **Advanced** → **Proceed to YOUR_IP (unsafe)**. All traffic (page, API, WebSocket) uses the same origin, so accepting once is enough.
+
+## Troubleshooting
+
+### ERR_SSL_PROTOCOL_ERROR when accessing https://YOUR_IP
+
+You do **not** need a domain — the setup works with an IP address. This error usually means Caddy isn't serving TLS on port 3043. Check in order:
+
+1. **Caddyfile** — must use the `:443` catch-all (container-internal; Docker maps host 3043 → container 443):
+   ```bash
+   cp Caddyfile.standalone.example Caddyfile
+   ```
+
+2. **Firewall** — allow port 3043 (common on DigitalOcean):
+   ```bash
+   sudo ufw allow 3043
+   sudo ufw status
+   ```
+
+3. **Caddy running** — verify and restart:
+   ```bash
+   docker compose -f docker-compose.standalone.yml ps
+   docker compose -f docker-compose.standalone.yml logs caddy --tail 20
+   docker compose -f docker-compose.standalone.yml --profile ollama-cpu up -d
+   ```
+
+4. **Test from the droplet** — if this works, the issue is external (firewall, network):
+   ```bash
+   curl -vk https://localhost:3043
+   ```
+
+5. **localhost works but external IP fails** — Re-run the setup script; it generates a Caddyfile with your droplet IP explicitly, so Caddy provisions the cert at startup:
+   ```bash
+   ./scripts/setup-standalone.sh
+   ```
+   Or manually create `Caddyfile` with your IP (replace 138.197.162.116):
+   ```
+   https://138.197.162.116, localhost {
+       tls internal
+       handle /v1/* { reverse_proxy server:1250 }
+       handle /health { reverse_proxy server:1250 }
+       handle { reverse_proxy web:3000 }
+   }
+   ```
+   Then restart: `docker compose -f docker-compose.standalone.yml --profile ollama-cpu up -d`
+
+6. **Still failing?** Try HTTP (no TLS) — create `Caddyfile`:
+   ```
+   :80 {
+       handle /v1/* { reverse_proxy server:1250 }
+       handle /health { reverse_proxy server:1250 }
+       handle { reverse_proxy web:3000 }
+   }
+   ```
+   Update `www/.env.local`: `API_URL=http://YOUR_IP:3043`, `WEBSOCKET_URL=ws://YOUR_IP:3043`, `SITE_URL=http://YOUR_IP:3043`, `NEXTAUTH_URL=http://YOUR_IP:3043`. Restart, then access `http://YOUR_IP:3043`.
+
+### Docker not ready
+
+If setup fails with "Docker not ready", on Ubuntu run `./scripts/install-docker-ubuntu.sh`. If Docker is installed but you're not root, run `newgrp docker` then run the setup script again.
+
+### Port conflicts (most common issue)
+
+If the frontend or backend behaves unexpectedly (e.g., env vars seem ignored, changes don't take effect), **check for port conflicts first**:
+
+```bash
+# Check what's listening on key ports
+lsof -i :3000   # frontend
+lsof -i :1250   # backend
+lsof -i :5432   # postgres
+lsof -i :3900   # Garage S3 API
+lsof -i :6379   # Redis
+
+# Kill stale processes on a port
+lsof -ti :3000 | xargs kill
+```
+
+Common causes:
+
+- A stale `next dev` or `pnpm dev` process from another terminal/worktree
+- Another Docker Compose project (different worktree) with containers on the same ports — the setup script only manages its own project; containers from other projects must be stopped manually (`docker ps` to find them, `docker stop` to kill them)
+
+The setup script checks ports 3000, 1250, 5432, 6379, 3900, 3903 for conflicts before starting services. It ignores OrbStack/Docker Desktop port forwarding processes (which always bind these ports but are not real conflicts).
+
+### OrbStack false port-conflict warnings (Mac)
+
+If you use OrbStack as your Docker runtime, `lsof` will show OrbStack binding ports like 3000, 1250, etc. even when no containers are running. This is OrbStack's port forwarding mechanism — not a real conflict. The setup script filters these out automatically.
+
+### Re-enabling authentication
+
+Standalone runs without authentication (`FEATURE_REQUIRE_LOGIN=false`, `AUTH_BACKEND=none`). To re-enable:
+
+1. In `www/.env.local`: set `FEATURE_REQUIRE_LOGIN=true`, uncomment `AUTHENTIK_ISSUER` and `AUTHENTIK_REFRESH_TOKEN_URL`
+2. In `server/.env`: set `AUTH_BACKEND=authentik` (or your backend), configure `AUTH_JWT_AUDIENCE`
+3. Restart: `docker compose -f docker-compose.standalone.yml up -d --force-recreate web server`
+
+## What's NOT covered
+
+These require external accounts and infrastructure that can't be scripted:
+
+- **Live meeting rooms** — requires Daily.co account, S3 bucket, IAM roles
+- **Authentication** — requires Authentik deployment and OAuth configuration
+- **Hatchet workflows** — requires separate Hatchet setup for multitrack processing
+- **Production deployment** — see [Deployment Guide](./overview)
+
+## Current status
+
+All steps implemented. The setup script handles everything end-to-end:
+
+- Step 1 (Ollama/LLM) — implemented
+- Step 2 (environment files) — implemented
+- Step 3 (object storage / Garage) — implemented
+- Step 4 (transcription/diarization) — implemented (self-hosted GPU service)
+- Steps 5-7 (Docker, migrations, health) — implemented
+- **Unified script**: `scripts/setup-standalone.sh`

docsv2/selfhosted-architecture.md

@@ -0,0 +1,472 @@
+# How the Self-Hosted Setup Works
+
+This document explains the internals of the self-hosted deployment: how the setup script orchestrates everything, how the Docker Compose profiles work, how services communicate, and how configuration flows from flags to running containers.
+
+> For quick-start instructions and flag reference, see [Self-Hosted Production Deployment](selfhosted-production.md).
+
+## Table of Contents
+
+- [Overview](#overview)
+- [The Setup Script Step by Step](#the-setup-script-step-by-step)
+- [Docker Compose Profile System](#docker-compose-profile-system)
+- [Service Architecture](#service-architecture)
+- [Configuration Flow](#configuration-flow)
+- [Storage Architecture](#storage-architecture)
+- [SSL/TLS and Reverse Proxy](#ssltls-and-reverse-proxy)
+- [Build vs Pull Workflow](#build-vs-pull-workflow)
+- [Background Task Processing](#background-task-processing)
+- [Network and Port Layout](#network-and-port-layout)
+
+---
+
+## Overview
+
+The self-hosted deployment runs the entire Reflector platform on a single server using Docker Compose. A single bash script (`scripts/setup-selfhosted.sh`) handles all configuration and orchestration. The key design principles are:
+
+- **One command to deploy** — flags select which features to enable
+- **Idempotent** — safe to re-run without losing existing configuration
+- **Profile-based composition** — Docker Compose profiles activate optional services
+- **No external dependencies required** — with `--garage` and `--ollama-*`, everything runs locally
+
+## The Setup Script Step by Step
+
+The script (`scripts/setup-selfhosted.sh`) runs 7 sequential steps. Here's what each one does and why.
+
+### Step 0: Prerequisites
+
+Validates the environment before doing anything:
+
+- **Docker Compose V2** — checks `docker compose version` output (not the legacy `docker-compose`)
+- **Docker daemon** — verifies `docker info` succeeds
+- **NVIDIA GPU** — only checked when `--gpu` or `--ollama-gpu` is used; runs `nvidia-smi` to confirm drivers are installed
+- **Compose file** — verifies `docker-compose.selfhosted.yml` exists at the expected path
+
+If any check fails, the script exits with a clear error message and remediation steps.
+
+### Step 1: Generate Secrets
+
+Creates cryptographic secrets needed by the backend and frontend:
+
+- **`SECRET_KEY`** — used by the FastAPI server for session signing (64 hex chars via `openssl rand -hex 32`)
+- **`NEXTAUTH_SECRET`** — used by Next.js NextAuth for JWT signing
+
+Secrets are only generated if they don't already exist or are still set to the placeholder value `changeme`. This is what makes the script idempotent for secrets.
+
+If `--password` is passed, this step also generates a PBKDF2-SHA256 password hash from the provided password. The hash is computed using Python's stdlib (`hashlib.pbkdf2_hmac`) with 100,000 iterations and a random 16-byte salt, producing a hash in the format `pbkdf2:sha256:100000$<salt_hex>$<hash_hex>`.
+
+### Step 2: Generate `server/.env`
+
+Creates or updates the backend environment file from `server/.env.selfhosted.example`. Sets:
+
+- **Infrastructure** — PostgreSQL URL, Redis host, Celery broker (all pointing to Docker-internal hostnames)
+- **Public URLs** — `BASE_URL` and `CORS_ORIGIN` computed from the domain (if `--domain`), IP (if detected on Linux), or `localhost`
+- **WebRTC** — `WEBRTC_HOST` set to the server's LAN IP so browsers can reach UDP ICE candidates
+- **Specialized models** — always points to `http://transcription:8000` (the Docker network alias shared by GPU and CPU containers)
+- **HuggingFace token** — prompts interactively for pyannote model access; writes to root `.env` so Docker Compose can inject it into GPU/CPU containers
+- **LLM** — if `--ollama-*` is used, configures `LLM_URL` pointing to the Ollama container. Otherwise, warns that the user needs to configure an external LLM
+- **Public mode** — sets `PUBLIC_MODE=true` so the app is accessible without authentication by default
+- **Password auth** — if `--password` is passed, sets `AUTH_BACKEND=password`, `PUBLIC_MODE=false`, `ADMIN_EMAIL=admin@localhost`, and `ADMIN_PASSWORD_HASH` (the hash generated in Step 1). The admin user is provisioned in the database on container startup via `runserver.sh`
+
+The script uses `env_set` for each variable, which either updates an existing line or appends a new one. This means re-running the script updates values in-place without duplicating keys.
+
+### Step 3: Generate `www/.env`
+
+Creates or updates the frontend environment file from `www/.env.selfhosted.example`. Sets:
+
+- **`SITE_URL` / `NEXTAUTH_URL` / `API_URL`** — all set to the same public-facing URL (with `https://` if Caddy is enabled)
+- **`WEBSOCKET_URL`** — set to `auto`, which tells the frontend to derive the WebSocket URL from the page URL automatically
+- **`SERVER_API_URL`** — always `http://server:1250` (Docker-internal, used for server-side rendering)
+- **`KV_URL`** — Redis URL for Next.js caching
+- **`FEATURE_REQUIRE_LOGIN`** — `false` by default (matches `PUBLIC_MODE=true` on the backend)
+- **Password auth** — if `--password` is passed, sets `FEATURE_REQUIRE_LOGIN=true` and `AUTH_PROVIDER=credentials`, which tells the frontend to use a local email/password login form instead of Authentik OAuth
+
+### Step 4: Storage Setup
+
+Branches based on whether `--garage` was passed:
+
+**With `--garage` (local S3):**
+
+1. Generates `data/garage.toml` from a template, injecting a random RPC secret
+2. Starts only the Garage container (`docker compose --profile garage up -d garage`)
+3. Waits for the Garage admin API to respond on port 3903
+4. Assigns the node to a storage layout (1GB capacity, zone `dc1`)
+5. Creates the `reflector-media` bucket
+6. Creates an access key named `reflector` and grants it read/write on the bucket
+7. Writes all S3 credentials (`ENDPOINT_URL`, `BUCKET_NAME`, `REGION`, `ACCESS_KEY_ID`, `SECRET_ACCESS_KEY`) to `server/.env`
+
+The Garage endpoint is `http://garage:3900` (Docker-internal), and the region is set to `garage` (arbitrary, Garage ignores it). The boto3 client uses path-style addressing when an endpoint URL is configured, which is required for S3-compatible services like Garage.
+
+**Without `--garage` (external S3):**
+
+1. Checks `server/.env` for the four required S3 variables
+2. If any are missing, prompts interactively for each one
+3. Optionally prompts for an endpoint URL (for MinIO, Backblaze B2, etc.)
+
+### Step 5: Caddyfile
+
+Only runs when `--caddy` or `--domain` is used. Generates a Caddy configuration file:
+
+**With `--domain`:** Creates a named site block (`reflector.example.com { ... }`). Caddy automatically provisions a Let's Encrypt certificate for this domain. Requires DNS pointing to the server and ports 80/443 open.
+
+**Without `--domain` (IP access):** Creates a catch-all `:443 { tls internal ... }` block. Caddy generates a self-signed certificate. Browsers will show a security warning.
+
+Both configurations route:
+- `/v1/*` and `/health` to the backend (`server:1250`)
+- Everything else to the frontend (`web:3000`)
+
+### Step 6: Start Services
+
+1. **Always builds the GPU/CPU model image** — these are never prebuilt because they contain ML model download logic specific to the host's hardware
+2. **With `--build`:** Also builds backend (server, worker, beat) and frontend (web) images from source
+3. **Without `--build`:** Pulls prebuilt images from the Docker registry (`monadicalsas/reflector-backend:latest`, `monadicalsas/reflector-frontend:latest`)
+4. **Starts all services** — `docker compose up -d` with the active profiles
+5. **Quick sanity check** — after 3 seconds, checks for any containers that exited immediately
+
+### Step 7: Health Checks
+
+Waits for each service in order, with generous timeouts:
+
+| Service | Check | Timeout | Notes |
+|---------|-------|---------|-------|
+| GPU/CPU models | `curl http://localhost:8000/docs` | 10 min (120 x 5s) | First start downloads ~1GB of models |
+| Ollama | `curl http://localhost:11435/api/tags` | 3 min (60 x 3s) | Then pulls the selected model |
+| Server API | `curl http://localhost:1250/health` | 7.5 min (90 x 5s) | First start runs database migrations |
+| Frontend | `curl http://localhost:3000` | 1.5 min (30 x 3s) | Next.js build on first start |
+| Caddy | `curl -k https://localhost` | Quick check | After other services are up |
+
+If the server container exits during the health check, the script dumps diagnostics (container statuses + logs) before exiting.
+
+After the Ollama health check passes, the script checks if the selected model is already pulled. If not, it runs `ollama pull <model>` inside the container.
+
+---
+
+## Docker Compose Profile System
+
+The compose file (`docker-compose.selfhosted.yml`) uses Docker Compose profiles to make services optional. Only services whose profiles match the active `--profile` flags are started.
+
+### Always-on Services (no profile)
+
+These start regardless of which flags you pass:
+
+| Service | Role | Image |
+|---------|------|-------|
+| `server` | FastAPI backend, API endpoints, WebRTC | `monadicalsas/reflector-backend:latest` |
+| `worker` | Celery worker for background processing | Same image, `ENTRYPOINT=worker` |
+| `beat` | Celery beat scheduler for periodic tasks | Same image, `ENTRYPOINT=beat` |
+| `web` | Next.js frontend | `monadicalsas/reflector-frontend:latest` |
+| `redis` | Message broker + caching | `redis:7.2-alpine` |
+| `postgres` | Primary database | `postgres:17-alpine` |
+
+### Profile-Based Services
+
+| Profile | Service | Role |
+|---------|---------|------|
+| `gpu` | `gpu` | NVIDIA GPU-accelerated transcription/diarization/translation |
+| `cpu` | `cpu` | CPU-only transcription/diarization/translation |
+| `ollama-gpu` | `ollama` | Local Ollama LLM with GPU |
+| `ollama-cpu` | `ollama-cpu` | Local Ollama LLM on CPU |
+| `garage` | `garage` | Local S3-compatible object storage |
+| `caddy` | `caddy` | Reverse proxy with SSL |
+
+### The "transcription" Alias
+
+Both the `gpu` and `cpu` services define a Docker network alias of `transcription`. This means the backend always connects to `http://transcription:8000` regardless of which profile is active. The alias is defined in the compose file's `networks.default.aliases` section.
+
+---
+
+## Service Architecture
+
+```
+                    ┌─────────────┐
+  Internet ────────>│    Caddy     │ :80/:443   (profile: caddy)
+                    └──────┬──────┘
+                           │
+              ┌────────────┼────────────┐
+              │            │            │
+              v            v            │
+         ┌─────────┐  ┌─────────┐      │
+         │   web   │  │ server  │      │
+         │ :3000   │  │ :1250   │      │
+         └─────────┘  └────┬────┘      │
+                           │            │
+                      ┌────┴────┐       │
+                      │ worker  │       │
+                      │  beat   │       │
+                      └────┬────┘       │
+                           │            │
+            ┌──────────────┼────────────┤
+            │              │            │
+            v              v            v
+      ┌───────────┐  ┌─────────┐  ┌─────────┐
+      │transcription│ │postgres │  │  redis  │
+      │ (gpu/cpu) │  │ :5432   │  │ :6379   │
+      │ :8000     │  └─────────┘  └─────────┘
+      └───────────┘
+            │
+      ┌─────┴─────┐     ┌─────────┐
+      │  ollama   │     │ garage  │
+      │(optional) │     │(optional│
+      │ :11435    │     │  S3)    │
+      └───────────┘     └─────────┘
+```
+
+### How Services Interact
+
+1. **User request** hits Caddy (if enabled), which routes to `web` (pages) or `server` (API)
+2. **`web`** renders pages server-side using `SERVER_API_URL=http://server:1250` and client-side using the public `API_URL`
+3. **`server`** handles API requests, file uploads, WebRTC streaming. Dispatches background work to Celery via Redis
+4. **`worker`** picks up Celery tasks (transcription pipelines, audio processing). Calls `transcription:8000` for ML inference and uploads results to S3 storage
+5. **`beat`** schedules periodic tasks (cleanup, webhook retries) by pushing them onto the Celery queue
+6. **`transcription` (gpu/cpu)** runs Whisper/Parakeet (transcription), Pyannote (diarization), and translation models. Stateless HTTP API
+7. **`ollama`** provides an OpenAI-compatible API for summarization and topic detection. Called by the worker during post-processing
+8. **`garage`** provides S3-compatible storage for audio files and processed results. Accessed by the worker via boto3
+
+---
+
+## Configuration Flow
+
+Environment variables flow through multiple layers. Understanding this prevents confusion when debugging:
+
+```
+Flags (--gpu, --garage, etc.)
+  │
+  ├── setup-selfhosted.sh interprets flags
+  │     │
+  │     ├── Writes server/.env (backend config)
+  │     ├── Writes www/.env (frontend config)
+  │     ├── Writes .env (HF_TOKEN for compose interpolation)
+  │     └── Writes Caddyfile (proxy routes)
+  │
+  └── docker-compose.selfhosted.yml reads:
+        ├── env_file: ./server/.env   (loaded into server, worker, beat)
+        ├── env_file: ./www/.env      (loaded into web)
+        ├── .env                      (compose variable interpolation, e.g. ${HF_TOKEN})
+        └── environment: {...}        (hardcoded overrides, always win over env_file)
+```
+
+### Precedence Rules
+
+Docker Compose `environment:` keys **always override** `env_file:` values. This is by design — the compose file hardcodes infrastructure values that must be correct inside the Docker network (like `DATABASE_URL=postgresql+asyncpg://...@postgres:5432/...`) regardless of what's in `server/.env`.
+
+The `server/.env` file is still useful for:
+- Values not overridden in the compose file (LLM config, storage credentials, auth settings)
+- Running the server outside Docker during development
+
+### The Three `.env` Files
+
+| File | Used By | Contains |
+|------|---------|----------|
+| `server/.env` | server, worker, beat | Backend config: database, Redis, S3, LLM, auth, public URLs |
+| `www/.env` | web | Frontend config: site URL, auth, feature flags |
+| `.env` (root) | Docker Compose interpolation | Only `HF_TOKEN` — injected into GPU/CPU container env |
+
+---
+
+## Storage Architecture
+
+All audio files and processing results are stored in S3-compatible object storage. The backend uses boto3 (via aioboto3) with automatic path-style addressing when a custom endpoint URL is configured.
+
+### How Garage Works
+
+Garage is a lightweight, self-hosted S3-compatible storage engine. In this deployment:
+
+- Runs as a single-node cluster with 1GB capacity allocation
+- Listens on port 3900 (S3 API) and 3903 (admin API)
+- Data persists in Docker volumes (`garage_data`, `garage_meta`)
+- Accessed by the worker at `http://garage:3900` (Docker-internal)
+
+The setup script creates:
+- A bucket called `reflector-media`
+- An access key called `reflector` with read/write permissions on that bucket
+
+### Path-Style vs Virtual-Hosted Addressing
+
+AWS S3 uses virtual-hosted addressing by default (`bucket.s3.amazonaws.com`). S3-compatible services like Garage require path-style addressing (`endpoint/bucket`). The `AwsStorage` class detects this automatically: when `TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL` is set, it configures boto3 with `addressing_style: "path"`.
+
+---
+
+## SSL/TLS and Reverse Proxy
+
+### With `--domain` (Production)
+
+Caddy automatically obtains and renews a Let's Encrypt certificate. Requirements:
+- DNS A record pointing to the server
+- Ports 80 (HTTP challenge) and 443 (HTTPS) open to the internet
+
+The generated Caddyfile uses the domain as the site address, which triggers Caddy's automatic HTTPS.
+
+### Without `--domain` (Development/LAN)
+
+Caddy generates a self-signed certificate and listens on `:443` as a catch-all. Browsers will show a security warning that must be accepted manually.
+
+### Without `--caddy` (BYO Proxy)
+
+No ports are exposed to the internet. The services listen on `127.0.0.1` only:
+- Frontend: `localhost:3000`
+- Backend API: `localhost:1250`
+
+You can point your own reverse proxy (nginx, Traefik, etc.) at these ports.
+
+### WebRTC and UDP
+
+The server exposes UDP ports 50000-50100 for WebRTC ICE candidates. The `WEBRTC_HOST` variable tells the server which IP to advertise in ICE candidates — this must be the server's actual IP address (not a domain), because WebRTC uses UDP which doesn't go through the HTTP reverse proxy.
+
+---
+
+## Build vs Pull Workflow
+
+### Default (no `--build` flag)
+
+```
+GPU/CPU model image: Always built from source (./gpu/self_hosted/)
+Backend image:       Pulled from monadicalsas/reflector-backend:latest
+Frontend image:      Pulled from monadicalsas/reflector-frontend:latest
+```
+
+The GPU/CPU image is always built because it contains hardware-specific build steps and ML model download logic.
+
+### With `--build`
+
+```
+GPU/CPU model image: Built from source (./gpu/self_hosted/)
+Backend image:       Built from source (./server/)
+Frontend image:      Built from source (./www/)
+```
+
+Use `--build` when:
+- You've made local code changes
+- The prebuilt registry images are outdated
+- You want to verify the build works on your hardware
+
+### Rebuilding Individual Services
+
+```bash
+# Rebuild just the backend
+docker compose -f docker-compose.selfhosted.yml build server worker beat
+
+# Rebuild just the frontend
+docker compose -f docker-compose.selfhosted.yml build web
+
+# Rebuild the GPU model container
+docker compose -f docker-compose.selfhosted.yml build gpu
+
+# Force a clean rebuild (no cache)
+docker compose -f docker-compose.selfhosted.yml build --no-cache server
+```
+
+---
+
+## Background Task Processing
+
+### Celery Architecture
+
+The backend uses Celery for all background work, with Redis as the message broker:
+
+- **`worker`** — picks up tasks from the Redis queue and executes them
+- **`beat`** — schedules periodic tasks (cron-like) by pushing them onto the queue
+- **`Redis`** — acts as both message broker and result backend
+
+### The Audio Processing Pipeline
+
+When a file is uploaded, the worker runs a multi-step pipeline:
+
+```
+Upload → Extract Audio → Upload to S3
+                           │
+                    ┌──────┼──────┐
+                    │      │      │
+                    v      v      v
+              Transcribe  Diarize  Waveform
+                    │      │      │
+                    └──────┼──────┘
+                           │
+                       Assemble
+                           │
+                    ┌──────┼──────┐
+                    v      v      v
+                Topics  Title  Summaries
+                           │
+                         Done
+```
+
+Transcription, diarization, and waveform generation run in parallel. After assembly, topic detection, title generation, and summarization also run in parallel. Each step calls the appropriate service (transcription container for ML, Ollama/external LLM for text generation, S3 for storage).
+
+### Event Loop Management
+
+Each Celery task runs in its own `asyncio.run()` call, which creates a fresh event loop. The `asynctask` decorator in `server/reflector/asynctask.py` handles:
+
+1. **Database connections** — resets the connection pool before each task (connections from a previous event loop would cause "Future attached to a different loop" errors)
+2. **Redis connections** — resets the WebSocket manager singleton so Redis pub/sub reconnects on the current loop
+3. **Cleanup** — disconnects the database and clears the context variable in the `finally` block
+
+---
+
+## Network and Port Layout
+
+All services communicate over Docker's default bridge network. Only specific ports are exposed to the host:
+
+| Port | Service | Binding | Purpose |
+|------|---------|---------|---------|
+| 80 | Caddy | `0.0.0.0:80` | HTTP (redirect to HTTPS / Let's Encrypt challenge) |
+| 443 | Caddy | `0.0.0.0:443` | HTTPS (main entry point) |
+| 1250 | Server | `127.0.0.1:1250` | Backend API (localhost only) |
+| 3000 | Web | `127.0.0.1:3000` | Frontend (localhost only) |
+| 3900 | Garage | `0.0.0.0:3900` | S3 API (for admin/debug access) |
+| 3903 | Garage | `0.0.0.0:3903` | Garage admin API |
+| 8000 | GPU/CPU | `127.0.0.1:8000` | ML model API (localhost only) |
+| 11435 | Ollama | `127.0.0.1:11435` | Ollama API (localhost only) |
+| 50000-50100/udp | Server | `0.0.0.0:50000-50100` | WebRTC ICE candidates |
+
+Services bound to `127.0.0.1` are only accessible from the host itself (not from the network). Caddy is the only service exposed to the internet on standard HTTP/HTTPS ports.
+
+### Docker-Internal Hostnames
+
+Inside the Docker network, services reach each other by their compose service name:
+
+| Hostname | Resolves To |
+|----------|-------------|
+| `server` | Backend API container |
+| `web` | Frontend container |
+| `postgres` | PostgreSQL container |
+| `redis` | Redis container |
+| `transcription` | GPU or CPU container (network alias) |
+| `ollama` / `ollama-cpu` | Ollama container |
+| `garage` | Garage S3 container |
+
+---
+
+## Diagnostics and Error Handling
+
+The setup script includes an `ERR` trap that automatically dumps diagnostics when any command fails:
+
+1. Lists all container statuses
+2. Shows the last 30 lines of logs for any stopped/exited containers
+3. Shows the last 40 lines of the specific failing service
+
+This means if something goes wrong during setup, you'll see the relevant logs immediately without having to run manual debug commands.
+
+### Common Debug Commands
+
+```bash
+# Overall status
+docker compose -f docker-compose.selfhosted.yml ps
+
+# Logs for a specific service
+docker compose -f docker-compose.selfhosted.yml logs server --tail 50
+docker compose -f docker-compose.selfhosted.yml logs worker --tail 50
+
+# Check environment inside a container
+docker compose -f docker-compose.selfhosted.yml exec server env | grep TRANSCRIPT
+
+# Health check from inside the network
+docker compose -f docker-compose.selfhosted.yml exec server curl http://localhost:1250/health
+
+# Check S3 storage connectivity
+docker compose -f docker-compose.selfhosted.yml exec server curl http://garage:3900
+
+# Database access
+docker compose -f docker-compose.selfhosted.yml exec postgres psql -U reflector -c "SELECT id, status FROM transcript ORDER BY created_at DESC LIMIT 5;"
+
+# List files in server data directory
+docker compose -f docker-compose.selfhosted.yml exec server ls -la /app/data/
+```

docsv2/selfhosted-production.md

@@ -0,0 +1,519 @@
+# Self-Hosted Production Deployment
+
+Deploy Reflector on a single server with everything running in Docker. Transcription, diarization, and translation use specialized ML models (Whisper/Parakeet, Pyannote); only summarization and topic detection require an LLM.
+
+> For a detailed walkthrough of how the setup script and infrastructure work under the hood, see [How the Self-Hosted Setup Works](selfhosted-architecture.md).
+
+## Prerequisites
+
+### Hardware
+- **With GPU**: Linux server with NVIDIA GPU (8GB+ VRAM recommended), 16GB+ RAM, 50GB+ disk
+- **CPU-only**: 8+ cores, 32GB+ RAM (transcription is slower but works)
+- Disk space for ML models (~2GB on first run) + audio storage
+
+### Software
+- Docker Engine 24+ with Compose V2
+- NVIDIA drivers + `nvidia-container-toolkit` (GPU modes only)
+- `curl`, `openssl` (usually pre-installed)
+
+### Accounts & Credentials (depending on options)
+
+**Always recommended:**
+- **HuggingFace token** — For downloading pyannote speaker diarization models. Get one at https://huggingface.co/settings/tokens and accept the model licenses:
+  - https://huggingface.co/pyannote/speaker-diarization-3.1
+  - https://huggingface.co/pyannote/segmentation-3.0
+  - The setup script will prompt for this. If skipped, diarization falls back to a public model bundle (may be less reliable).
+
+**LLM for summarization & topic detection (pick one):**
+- **With `--ollama-gpu` or `--ollama-cpu`**: Nothing extra — Ollama runs locally and pulls the model automatically
+- **Without `--ollama-*`**: An OpenAI-compatible LLM API key and endpoint. Examples:
+  - OpenAI: `LLM_URL=https://api.openai.com/v1`, `LLM_API_KEY=sk-...`, `LLM_MODEL=gpt-4o-mini`
+  - Anthropic, Together, Groq, or any OpenAI-compatible API
+  - A self-managed vLLM or Ollama instance elsewhere on the network
+
+**Object storage (pick one):**
+- **With `--garage`**: Nothing extra — Garage (local S3-compatible storage) is auto-configured by the script
+- **Without `--garage`**: S3-compatible storage credentials. The script will prompt for these, or you can pre-fill `server/.env`. Options include:
+  - **AWS S3**: Access Key ID, Secret Access Key, bucket name, region
+  - **MinIO**: Same credentials + `TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://your-minio:9000`
+  - **Any S3-compatible provider** (Backblaze B2, Cloudflare R2, DigitalOcean Spaces, etc.): same fields + custom endpoint URL
+
+**Optional add-ons (configure after initial setup):**
+- **Daily.co** (live meeting rooms): Requires a Daily.co account (https://www.daily.co/), API key, subdomain, and an AWS S3 bucket + IAM Role for recording storage. See [Enabling Daily.co Live Rooms](#enabling-dailyco-live-rooms) below.
+- **Authentik** (user authentication): Requires an Authentik instance with an OAuth2/OIDC application configured for Reflector. See [Enabling Authentication](#enabling-authentication-authentik) below.
+
+## Quick Start
+
+```bash
+git clone https://github.com/Monadical-SAS/reflector.git
+cd reflector
+
+# GPU + local Ollama LLM + local Garage storage + Caddy SSL (with domain):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --domain reflector.example.com
+
+# Same but without a domain (self-signed cert, access via IP):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# CPU-only (same, but slower):
+./scripts/setup-selfhosted.sh --cpu --ollama-cpu --garage --caddy
+
+# With password authentication (single admin user):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+
+# Build from source instead of pulling prebuilt images:
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --build
+```
+
+That's it. The script generates env files, secrets, starts all containers, waits for health checks, and prints the URL.
+
+## Specialized Models (Required)
+
+Pick `--gpu` or `--cpu`. This determines how **transcription, diarization, and translation** run:
+
+| Flag | What it does | Requires |
+|------|-------------|----------|
+| `--gpu` | NVIDIA GPU acceleration for ML models | NVIDIA GPU + drivers + `nvidia-container-toolkit` |
+| `--cpu` | CPU-only (slower but works without GPU) | 8+ cores, 32GB+ RAM recommended |
+
+## Local LLM (Optional)
+
+Optionally add `--ollama-gpu` or `--ollama-cpu` for a **local Ollama instance** that handles summarization and topic detection. If omitted, configure an external OpenAI-compatible LLM in `server/.env`.
+
+| Flag | What it does | Requires |
+|------|-------------|----------|
+| `--ollama-gpu` | Local Ollama with NVIDIA GPU acceleration | NVIDIA GPU |
+| `--ollama-cpu` | Local Ollama on CPU only | Nothing extra |
+| `--llm-model MODEL` | Choose which Ollama model to download (default: `qwen2.5:14b`) | `--ollama-gpu` or `--ollama-cpu` |
+| *(omitted)* | User configures external LLM (OpenAI, Anthropic, etc.) | LLM API key |
+
+### Choosing an Ollama model
+
+The default model is `qwen2.5:14b` (~9GB download, good multilingual support and summary quality). Override with `--llm-model`:
+
+```bash
+# Default (qwen2.5:14b)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# Mistral — good balance of speed and quality (~4.1GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model mistral --garage --caddy
+
+# Phi-4 — smaller and faster (~9.1GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model phi4 --garage --caddy
+
+# Llama 3.3 70B — best quality, needs 48GB+ RAM or GPU VRAM (~43GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model llama3.3:70b --garage --caddy
+
+# Gemma 2 9B (~5.4GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model gemma2 --garage --caddy
+
+# DeepSeek R1 8B — reasoning model, verbose but thorough summaries (~4.9GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model deepseek-r1:8b --garage --caddy
+```
+
+Browse all available models at https://ollama.com/library.
+
+### Recommended combinations
+
+- **`--gpu --ollama-gpu`**: Best for servers with NVIDIA GPU. Fully self-contained, no external API keys needed.
+- **`--cpu --ollama-cpu`**: No GPU available but want everything self-contained. Slower but works.
+- **`--gpu --ollama-cpu`**: GPU for transcription, CPU for LLM. Saves GPU VRAM for ML models.
+- **`--gpu`**: Have NVIDIA GPU but prefer a cloud LLM (faster/better summaries with GPT-4, Claude, etc.).
+- **`--cpu`**: No GPU, prefer cloud LLM. Slowest transcription but best summary quality.
+
+## Other Optional Flags
+
+| Flag | What it does |
+|------|-------------|
+| `--garage` | Starts Garage (local S3-compatible storage). Auto-configures bucket, keys, and env vars. |
+| `--caddy` | Starts Caddy reverse proxy on ports 80/443 with self-signed cert. |
+| `--domain DOMAIN` | Use a real domain with Let's Encrypt auto-HTTPS (implies `--caddy`). Requires DNS A record pointing to this server and ports 80/443 open. |
+| `--password PASS` | Enable password authentication with an `admin@localhost` user. Sets `AUTH_BACKEND=password`, `PUBLIC_MODE=false`. See [Enabling Password Authentication](#enabling-password-authentication). |
+| `--build` | Build backend (server, worker, beat) and frontend (web) Docker images from source instead of pulling prebuilt images from the registry. Useful for development or when running a version with local changes. |
+
+Without `--garage`, you **must** provide S3-compatible credentials (the script will prompt interactively or you can pre-fill `server/.env`).
+
+Without `--caddy` or `--domain`, no ports are exposed. Point your own reverse proxy at `web:3000` (frontend) and `server:1250` (API).
+
+**Using a domain (recommended for production):** Point a DNS A record at your server's IP, then pass `--domain your.domain.com`. Caddy will automatically obtain and renew a Let's Encrypt certificate. Ports 80 and 443 must be open.
+
+**Without a domain:** `--caddy` alone uses a self-signed certificate. Browsers will show a security warning that must be accepted.
+
+## What the Script Does
+
+1. **Prerequisites check** — Docker, NVIDIA GPU (if needed), compose file exists
+2. **Generate secrets** — `SECRET_KEY`, `NEXTAUTH_SECRET` via `openssl rand`
+3. **Generate `server/.env`** — From template, sets infrastructure defaults, configures LLM based on mode, enables `PUBLIC_MODE`
+4. **Generate `www/.env`** — Auto-detects server IP, sets URLs
+5. **Storage setup** — Either initializes Garage (bucket, keys, permissions) or prompts for external S3 credentials
+6. **Caddyfile** — Generates domain-specific (Let's Encrypt) or IP-specific (self-signed) configuration
+7. **Build & start** — Always builds GPU/CPU model image from source. With `--build`, also builds backend and frontend from source; otherwise pulls prebuilt images from the registry
+8. **Health checks** — Waits for each service, pulls Ollama model if needed, warns about missing LLM config
+
+> For a deeper dive into each step, see [How the Self-Hosted Setup Works](selfhosted-architecture.md).
+
+## Configuration Reference
+
+### Server Environment (`server/.env`)
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `DATABASE_URL` | PostgreSQL connection | Auto-set (Docker internal) |
+| `REDIS_HOST` | Redis hostname | Auto-set (`redis`) |
+| `SECRET_KEY` | App secret | Auto-generated |
+| `AUTH_BACKEND` | Authentication method (`none`, `password`, `jwt`) | `none` |
+| `PUBLIC_MODE` | Allow unauthenticated access | `true` |
+| `ADMIN_EMAIL` | Admin email for password auth | *(unset)* |
+| `ADMIN_PASSWORD_HASH` | PBKDF2 hash for password auth | *(unset)* |
+| `WEBRTC_HOST` | IP advertised in WebRTC ICE candidates | Auto-detected (server IP) |
+| `TRANSCRIPT_URL` | Specialized model endpoint | `http://transcription:8000` |
+| `LLM_URL` | OpenAI-compatible LLM endpoint | Auto-set for Ollama modes |
+| `LLM_API_KEY` | LLM API key | `not-needed` for Ollama |
+| `LLM_MODEL` | LLM model name | `qwen2.5:14b` for Ollama (override with `--llm-model`) |
+| `CELERY_BEAT_POLL_INTERVAL` | Override all worker polling intervals (seconds). `0` = use individual defaults | `300` (selfhosted), `0` (other) |
+| `TRANSCRIPT_STORAGE_BACKEND` | Storage backend | `aws` |
+| `TRANSCRIPT_STORAGE_AWS_*` | S3 credentials | Auto-set for Garage |
+
+### Frontend Environment (`www/.env`)
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `SITE_URL` | Public-facing URL | Auto-detected |
+| `API_URL` | API URL (browser-side) | Same as SITE_URL |
+| `SERVER_API_URL` | API URL (server-side) | `http://server:1250` |
+| `NEXTAUTH_SECRET` | Auth secret | Auto-generated |
+| `FEATURE_REQUIRE_LOGIN` | Require authentication | `false` |
+| `AUTH_PROVIDER` | Auth provider (`authentik` or `credentials`) | *(unset)* |
+
+## Storage Options
+
+### Garage (Recommended for Self-Hosted)
+
+Use `--garage` flag. The script automatically:
+- Generates `data/garage.toml` with a random RPC secret
+- Starts the Garage container
+- Creates the `reflector-media` bucket
+- Creates an access key with read/write permissions
+- Writes all S3 credentials to `server/.env`
+
+### External S3 (AWS, MinIO, etc.)
+
+Don't use `--garage`. The script will prompt for:
+- Access Key ID
+- Secret Access Key
+- Bucket Name
+- Region
+- Endpoint URL (for non-AWS like MinIO)
+
+Or pre-fill in `server/.env`:
+```env
+TRANSCRIPT_STORAGE_BACKEND=aws
+TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID=your-key
+TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY=your-secret
+TRANSCRIPT_STORAGE_AWS_BUCKET_NAME=reflector-media
+TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
+# For non-AWS S3 (MinIO, etc.):
+TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://minio:9000
+```
+
+## What Authentication Enables
+
+By default, Reflector runs in **public mode** (`AUTH_BACKEND=none`, `PUBLIC_MODE=true`) — anyone can create and view transcripts without logging in. Transcripts are anonymous (not linked to any user) and cannot be edited or deleted after creation.
+
+Enabling authentication (either password or Authentik) unlocks:
+
+| Feature | Public mode (no auth) | With authentication |
+|---------|----------------------|---------------------|
+| Create transcripts (record/upload) | Yes (anonymous, unowned) | Yes (owned by user) |
+| View transcripts | All transcripts visible | Own transcripts + shared rooms |
+| Edit/delete transcripts | No | Yes (owner only) |
+| Privacy controls (private/semi-private/public) | No (everything public) | Yes (owner can set share mode) |
+| Speaker reassignment and merging | No | Yes (owner only) |
+| Participant management (add/edit/delete) | Read-only | Full CRUD (owner only) |
+| Create rooms | No | Yes |
+| Edit/delete rooms | No | Yes (owner only) |
+| Room calendar (ICS) sync | No | Yes (owner only) |
+| API key management | No | Yes |
+| Post to Zulip | No | Yes (owner only) |
+| Real-time WebSocket notifications | No (connection closed) | Yes (transcript create/delete events) |
+| Meeting host access (Daily.co token) | No | Yes (room owner) |
+
+In short: public mode is "demo-friendly" — great for trying Reflector out. Authentication adds **ownership, privacy, and management** of your data.
+
+## Authentication Options
+
+Reflector supports three authentication backends:
+
+| Backend | `AUTH_BACKEND` | Use case |
+|---------|---------------|----------|
+| `none` | `none` | Public/demo mode, no login required |
+| `password` | `password` | Single-user self-hosted, simple email/password login |
+| `jwt` | `jwt` | Multi-user via Authentik (OAuth2/OIDC) |
+
+## Enabling Password Authentication
+
+The simplest way to add authentication. Creates a single admin user with email/password login — no external identity provider needed.
+
+### Quick setup (recommended)
+
+Pass `--password` to the setup script:
+
+```bash
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+```
+
+This automatically:
+- Sets `AUTH_BACKEND=password` and `PUBLIC_MODE=false` in `server/.env`
+- Creates an `admin@localhost` user with the given password
+- Sets `FEATURE_REQUIRE_LOGIN=true` and `AUTH_PROVIDER=credentials` in `www/.env`
+- Provisions the admin user in the database on container startup
+
+### Manual setup
+
+If you prefer to configure manually or want to change the admin email:
+
+1. Generate a password hash:
+   ```bash
+   cd server
+   uv run python -m reflector.tools.create_admin --hash-only --password yourpassword
+   ```
+
+2. Update `server/.env`:
+   ```env
+   AUTH_BACKEND=password
+   PUBLIC_MODE=false
+   ADMIN_EMAIL=admin@yourdomain.com
+   ADMIN_PASSWORD_HASH=pbkdf2:sha256:100000$<salt>$<hash>
+   ```
+
+3. Update `www/.env`:
+   ```env
+   FEATURE_REQUIRE_LOGIN=true
+   AUTH_PROVIDER=credentials
+   ```
+
+4. Restart:
+   ```bash
+   docker compose -f docker-compose.selfhosted.yml down
+   ./scripts/setup-selfhosted.sh <same-flags>
+   ```
+
+### How it works
+
+- The backend issues HS256 JWTs (signed with `SECRET_KEY`) on successful login via `POST /v1/auth/login`
+- Tokens expire after 24 hours; the user must log in again after expiry
+- The frontend shows a login page at `/login` with email and password fields
+- A rate limiter blocks IPs after 10 failed login attempts within 5 minutes
+- The admin user is provisioned automatically on container startup from `ADMIN_EMAIL` and `ADMIN_PASSWORD_HASH` environment variables
+- Passwords are hashed with PBKDF2-SHA256 (100,000 iterations) — no additional dependencies required
+
+### Changing the admin password
+
+```bash
+cd server
+uv run python -m reflector.tools.create_admin --email admin@localhost --password newpassword
+```
+
+Or update `ADMIN_PASSWORD_HASH` in `server/.env` and restart the containers.
+
+## Enabling Authentication (Authentik)
+
+For multi-user deployments with SSO. Requires an external Authentik instance.
+
+By default, authentication is disabled (`AUTH_BACKEND=none`, `FEATURE_REQUIRE_LOGIN=false`). To enable:
+
+1. Deploy an Authentik instance (see [Authentik docs](https://goauthentik.io/docs/installation))
+2. Create an OAuth2/OIDC application for Reflector
+3. Update `server/.env`:
+   ```env
+   AUTH_BACKEND=jwt
+   AUTH_JWT_AUDIENCE=your-client-id
+   ```
+4. Update `www/.env`:
+   ```env
+   FEATURE_REQUIRE_LOGIN=true
+   AUTH_PROVIDER=authentik
+   AUTHENTIK_ISSUER=https://authentik.example.com/application/o/reflector
+   AUTHENTIK_REFRESH_TOKEN_URL=https://authentik.example.com/application/o/token/
+   AUTHENTIK_CLIENT_ID=your-client-id
+   AUTHENTIK_CLIENT_SECRET=your-client-secret
+   ```
+5. Restart: `docker compose -f docker-compose.selfhosted.yml down && ./scripts/setup-selfhosted.sh <same-flags>`
+
+## Enabling Daily.co Live Rooms
+
+Daily.co enables real-time meeting rooms with automatic recording and transcription.
+
+1. Create a [Daily.co](https://www.daily.co/) account
+2. Add to `server/.env`:
+   ```env
+   DEFAULT_VIDEO_PLATFORM=daily
+   DAILY_API_KEY=your-daily-api-key
+   DAILY_SUBDOMAIN=your-subdomain
+   DAILY_WEBHOOK_SECRET=your-webhook-secret
+   DAILYCO_STORAGE_AWS_BUCKET_NAME=reflector-dailyco
+   DAILYCO_STORAGE_AWS_REGION=us-east-1
+   DAILYCO_STORAGE_AWS_ROLE_ARN=arn:aws:iam::role/DailyCoAccess
+   ```
+3. Restart the server: `docker compose -f docker-compose.selfhosted.yml restart server worker`
+
+## Enabling Real Domain with Let's Encrypt
+
+By default, Caddy uses self-signed certificates. For a real domain:
+
+1. Point your domain's DNS to your server's IP
+2. Ensure ports 80 and 443 are open
+3. Edit `Caddyfile`:
+   ```
+   reflector.example.com {
+       handle /v1/* {
+           reverse_proxy server:1250
+       }
+       handle /health {
+           reverse_proxy server:1250
+       }
+       handle {
+           reverse_proxy web:3000
+       }
+   }
+   ```
+4. Update `www/.env`:
+   ```env
+   SITE_URL=https://reflector.example.com
+   NEXTAUTH_URL=https://reflector.example.com
+   API_URL=https://reflector.example.com
+   ```
+5. Restart Caddy: `docker compose -f docker-compose.selfhosted.yml restart caddy web`
+
+## Worker Polling Frequency
+
+The selfhosted setup defaults all background worker polling intervals to **300 seconds (5 minutes)** to reduce CPU and memory usage. This controls how often the beat scheduler triggers tasks like recording discovery, meeting reconciliation, and calendar sync.
+
+To change the interval, edit `server/.env`:
+
+```env
+# Poll every 60 seconds (more responsive, uses more resources)
+CELERY_BEAT_POLL_INTERVAL=60
+
+# Poll every 5 minutes (default for selfhosted)
+CELERY_BEAT_POLL_INTERVAL=300
+
+# Use individual per-task defaults (production SaaS behavior)
+CELERY_BEAT_POLL_INTERVAL=0
+```
+
+After changing, restart the beat and worker containers:
+
+```bash
+docker compose -f docker-compose.selfhosted.yml restart beat worker
+```
+
+**Affected tasks when `CELERY_BEAT_POLL_INTERVAL` is set:**
+
+| Task | Default (no override) | With override |
+|------|-----------------------|---------------|
+| SQS message polling | 60s | Override value |
+| Daily.co recording discovery | 15s (no webhook) / 180s (webhook) | Override value |
+| Meeting reconciliation | 30s | Override value |
+| ICS calendar sync | 60s | Override value |
+| Upcoming meeting creation | 30s | Override value |
+
+> **Note:** Daily crontab tasks (failed recording reprocessing at 05:00 UTC, public data cleanup at 03:00 UTC) and healthcheck pings (10 min) are **not** affected by this setting.
+
+## Troubleshooting
+
+### Check service status
+```bash
+docker compose -f docker-compose.selfhosted.yml ps
+```
+
+### View logs for a specific service
+```bash
+docker compose -f docker-compose.selfhosted.yml logs server --tail 50
+docker compose -f docker-compose.selfhosted.yml logs gpu --tail 50
+docker compose -f docker-compose.selfhosted.yml logs web --tail 50
+```
+
+### GPU service taking too long
+First start downloads ~1-2GB of ML models. Check progress:
+```bash
+docker compose -f docker-compose.selfhosted.yml logs gpu -f
+```
+
+### Server exits immediately
+Usually a database migration issue. Check:
+```bash
+docker compose -f docker-compose.selfhosted.yml logs server --tail 50
+```
+
+### Caddy certificate issues
+For self-signed certs, your browser will warn. Click Advanced > Proceed.
+For Let's Encrypt, ensure ports 80/443 are open and DNS is pointed correctly.
+
+### Summaries/topics not generating
+Check LLM configuration:
+```bash
+grep LLM_ server/.env
+```
+If you didn't use `--ollama-gpu` or `--ollama-cpu`, you must set `LLM_URL`, `LLM_API_KEY`, and `LLM_MODEL`.
+
+### Health check from inside containers
+```bash
+docker compose -f docker-compose.selfhosted.yml exec server curl http://localhost:1250/health
+docker compose -f docker-compose.selfhosted.yml exec gpu curl http://localhost:8000/docs
+```
+
+## Updating
+
+```bash
+# Option A: Pull latest prebuilt images and restart
+docker compose -f docker-compose.selfhosted.yml down
+./scripts/setup-selfhosted.sh <same-flags-as-before>
+
+# Option B: Build from source (after git pull) and restart
+git pull
+docker compose -f docker-compose.selfhosted.yml down
+./scripts/setup-selfhosted.sh <same-flags-as-before> --build
+
+# Rebuild only the GPU/CPU model image (picks up model updates)
+docker compose -f docker-compose.selfhosted.yml build gpu  # or cpu
+```
+
+The setup script is idempotent — it won't overwrite existing secrets or env vars that are already set.
+
+## Architecture Overview
+
+```
+                    ┌─────────┐
+  Internet ────────>│  Caddy  │ :80/:443
+                    └────┬────┘
+                         │
+            ┌────────────┼────────────┐
+            │            │            │
+            v            v            │
+       ┌─────────┐  ┌─────────┐      │
+       │   web   │  │ server  │      │
+       │ :3000   │  │ :1250   │      │
+       └─────────┘  └────┬────┘      │
+                         │            │
+                    ┌────┴────┐       │
+                    │ worker  │       │
+                    │  beat   │       │
+                    └────┬────┘       │
+                         │            │
+          ┌──────────────┼────────────┤
+          │              │            │
+          v              v            v
+    ┌───────────┐  ┌─────────┐  ┌─────────┐
+    │transcription│  │postgres │  │  redis  │
+    │(gpu/cpu)  │  │ :5432   │  │ :6379   │
+    │ :8000     │  └─────────┘  └─────────┘
+    └───────────┘
+          │
+    ┌─────┴─────┐     ┌─────────┐
+    │  ollama   │     │ garage  │
+    │ (optional)│     │(optional│
+    │ :11435    │     │ S3)     │
+    └───────────┘     └─────────┘
+```
+
+All services communicate over Docker's internal network. Only Caddy (if enabled) exposes ports to the internet.

gpu/self_hosted/Dockerfile

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

gpu/self_hosted/Dockerfile.cpu

@@ -0,0 +1,39 @@
+FROM python:3.12-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    UV_LINK_MODE=copy \
+    UV_NO_CACHE=1
+
+WORKDIR /tmp
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+ --mount=type=cache,target=/var/lib/apt,sharing=locked \
+ apt-get update \
+ && apt-get install -y \
+    ffmpeg \
+    curl \
+    ca-certificates \
+    gnupg \
+    wget
+ADD https://astral.sh/uv/install.sh /uv-installer.sh
+RUN sh /uv-installer.sh && rm /uv-installer.sh
+ENV PATH="/root/.local/bin/:$PATH"
+
+RUN mkdir -p /app
+WORKDIR /app
+COPY pyproject.toml uv.lock /app/
+
+
+COPY ./app /app/app
+COPY ./main.py /app/
+COPY ./runserver.sh /app/
+
+# prevent uv failing with too many open files on big cpus
+ENV UV_CONCURRENT_INSTALLS=16
+
+# first install
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --compile-bytecode --locked
+
+EXPOSE 8000
+
+CMD ["sh", "/app/runserver.sh"]

gpu/self_hosted/app/auth.py

@@ -3,14 +3,14 @@ import os
 from fastapi import Depends, HTTPException, status
 from fastapi.security import OAuth2PasswordBearer
 
-oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
+oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token", auto_error=False)
 
 
-def apikey_auth(apikey: str = Depends(oauth2_scheme)):
+def apikey_auth(apikey: str | None = Depends(oauth2_scheme)):
     required_key = os.environ.get("REFLECTOR_GPU_APIKEY")
     if not required_key:
         return
-    if apikey == required_key:
+    if apikey and apikey == required_key:
         return
     raise HTTPException(
         status_code=status.HTTP_401_UNAUTHORIZED,

gpu/self_hosted/app/services/diarizer.py

@@ -1,10 +1,65 @@
+import logging
 import os
+import tarfile
 import threading
+from pathlib import Path
+from urllib.request import urlopen
 
 import torch
 import torchaudio
+import yaml
 from pyannote.audio import Pipeline
 
+logger = logging.getLogger(__name__)
+
+S3_BUNDLE_URL = "https://reflector-public.s3.us-east-1.amazonaws.com/pyannote-speaker-diarization-3.1.tar.gz"
+BUNDLE_CACHE_DIR = Path("/root/.cache/pyannote-bundle")
+
+
+def _ensure_model(cache_dir: Path) -> str:
+    """Download and extract S3 model bundle if not cached."""
+    model_dir = cache_dir / "pyannote-speaker-diarization-3.1"
+    config_path = model_dir / "config.yaml"
+
+    if config_path.exists():
+        logger.info("Using cached model bundle at %s", model_dir)
+        return str(model_dir)
+
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    tarball_path = cache_dir / "model.tar.gz"
+
+    logger.info("Downloading model bundle from %s", S3_BUNDLE_URL)
+    with urlopen(S3_BUNDLE_URL) as response, open(tarball_path, "wb") as f:
+        while chunk := response.read(8192):
+            f.write(chunk)
+
+    logger.info("Extracting model bundle")
+    with tarfile.open(tarball_path, "r:gz") as tar:
+        tar.extractall(path=cache_dir, filter="data")
+    tarball_path.unlink()
+
+    _patch_config(model_dir, cache_dir)
+    return str(model_dir)
+
+
+def _patch_config(model_dir: Path, cache_dir: Path) -> None:
+    """Rewrite config.yaml to reference local pytorch_model.bin paths."""
+    config_path = model_dir / "config.yaml"
+    with open(config_path) as f:
+        config = yaml.safe_load(f)
+
+    config["pipeline"]["params"]["segmentation"] = str(
+        cache_dir / "pyannote-segmentation-3.0" / "pytorch_model.bin"
+    )
+    config["pipeline"]["params"]["embedding"] = str(
+        cache_dir / "pyannote-wespeaker-voxceleb-resnet34-LM" / "pytorch_model.bin"
+    )
+
+    with open(config_path, "w") as f:
+        yaml.dump(config, f)
+
+    logger.info("Patched config.yaml with local model paths")
+
 
 class PyannoteDiarizationService:
     def __init__(self):
@@ -14,10 +69,20 @@ class PyannoteDiarizationService:
 
     def load(self):
         self._device = "cuda" if torch.cuda.is_available() else "cpu"
-        self._pipeline = Pipeline.from_pretrained(
-            "pyannote/speaker-diarization-3.1",
-            use_auth_token=os.environ.get("HF_TOKEN"),
-        )
+        hf_token = os.environ.get("HF_TOKEN")
+
+        if hf_token:
+            logger.info("Loading pyannote model from HuggingFace (HF_TOKEN set)")
+            self._pipeline = Pipeline.from_pretrained(
+                "pyannote/speaker-diarization-3.1",
+                use_auth_token=hf_token,
+            )
+        else:
+            logger.info("HF_TOKEN not set — loading model from S3 bundle")
+            model_path = _ensure_model(BUNDLE_CACHE_DIR)
+            config_path = Path(model_path) / "config.yaml"
+            self._pipeline = Pipeline.from_pretrained(str(config_path))
+
         self._pipeline.to(torch.device(self._device))
 
     def diarize_file(self, file_path: str, timestamp: float = 0.0) -> dict:

gpu/self_hosted/sequoia.config

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

node_modules/.yarn-integrity

@@ -0,0 +1,10 @@
+{
+  "systemParams": "darwin-x64-83",
+  "modulesFolders": [],
+  "flags": [],
+  "linkedModules": [],
+  "topLevelPatterns": [],
+  "lockfileEntries": {},
+  "files": [],
+  "artifacts": {}
+}

scripts/garage.toml

@@ -0,0 +1,14 @@
+metadata_dir = "/var/lib/garage/meta"
+data_dir = "/var/lib/garage/data"
+replication_factor = 1
+
+rpc_secret = "__GARAGE_RPC_SECRET__"
+rpc_bind_addr = "[::]:3901"
+
+[s3_api]
+api_bind_addr = "[::]:3900"
+s3_region = "garage"
+root_domain = ".s3.garage.localhost"
+
+[admin]
+api_bind_addr = "[::]:3903"

scripts/install-docker-ubuntu.sh

@@ -0,0 +1,87 @@
+#!/usr/bin/env bash
+#
+# Install Docker Engine + Compose plugin on Ubuntu.
+# Ubuntu's default repos don't include docker-compose-plugin, so we add Docker's official repo.
+#
+# Usage:
+#   ./scripts/install-docker-ubuntu.sh
+#
+# Requires: root or sudo
+#
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# --- Colors ---
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+CYAN='\033[0;36m'
+NC='\033[0m'
+
+info()  { echo -e "${CYAN}==>${NC} $*"; }
+ok()    { echo -e "${GREEN}  ✓${NC} $*"; }
+warn()  { echo -e "${YELLOW}  !${NC} $*"; }
+err()   { echo -e "${RED}  ✗${NC} $*" >&2; }
+
+# Use sudo if available and not root; otherwise run directly
+if [[ $(id -u) -eq 0 ]]; then
+    MAYBE_SUDO=""
+elif command -v sudo &>/dev/null; then
+    MAYBE_SUDO="sudo "
+else
+    err "Need root. Run as root or install sudo: apt install sudo"
+    exit 1
+fi
+
+# Check Ubuntu
+if [[ ! -f /etc/os-release ]]; then
+    err "Cannot detect OS. This script is for Ubuntu."
+    exit 1
+fi
+source /etc/os-release
+if [[ "${ID:-}" != "ubuntu" ]] && [[ "${ID_LIKE:-}" != *"ubuntu"* ]]; then
+    err "This script is for Ubuntu. Detected: ${ID:-unknown}"
+    exit 1
+fi
+
+info "Adding Docker's official repository..."
+${MAYBE_SUDO}apt update
+${MAYBE_SUDO}apt install -y ca-certificates curl
+${MAYBE_SUDO}install -m 0755 -d /etc/apt/keyrings
+${MAYBE_SUDO}rm -f /etc/apt/sources.list.d/docker.list /etc/apt/sources.list.d/docker.sources
+curl -fsSL https://download.docker.com/linux/ubuntu/gpg | ${MAYBE_SUDO}tee /etc/apt/keyrings/docker.asc > /dev/null
+${MAYBE_SUDO}chmod a+r /etc/apt/keyrings/docker.asc
+CODENAME="$(. /etc/os-release && echo "${UBUNTU_CODENAME:-${VERSION_CODENAME:-}}")"
+[[ -z "$CODENAME" ]] && { err "Could not detect Ubuntu version codename."; exit 1; }
+${MAYBE_SUDO}tee /etc/apt/sources.list.d/docker.sources > /dev/null <<EOF
+Types: deb
+URIs: https://download.docker.com/linux/ubuntu
+Suites: ${CODENAME}
+Components: stable
+Signed-By: /etc/apt/keyrings/docker.asc
+EOF
+
+info "Installing Docker Engine and Compose plugin..."
+${MAYBE_SUDO}apt update
+${MAYBE_SUDO}apt install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
+
+if [[ -d /run/systemd/system ]]; then
+    info "Enabling and starting Docker..."
+    ${MAYBE_SUDO}systemctl enable --now docker
+else
+    err "No systemd. This script requires Ubuntu with systemd (e.g. DigitalOcean droplet)."
+    exit 1
+fi
+
+DOCKER_USER="${SUDO_USER:-${USER:-root}}"
+if [[ "$DOCKER_USER" != "root" ]]; then
+    info "Adding $DOCKER_USER to docker group..."
+    ${MAYBE_SUDO}usermod -aG docker "$DOCKER_USER"
+fi
+
+ok "Docker installed successfully."
+echo ""
+echo "  Log out and back in (or run: newgrp docker) so the group change takes effect."
+echo "  Then verify with: docker compose version"
+echo ""

scripts/setup-standalone.sh

@@ -0,0 +1,675 @@
+#!/usr/bin/env bash
+#
+# Standalone local development setup for Reflector.
+# Takes a fresh clone to a working instance — no cloud accounts, no API keys.
+#
+# Usage:
+#   ./scripts/setup-standalone.sh
+#
+# Idempotent — safe to re-run at any time.
+#
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+SERVER_ENV="$ROOT_DIR/server/.env"
+WWW_ENV="$ROOT_DIR/www/.env.local"
+
+MODEL="${LLM_MODEL:-qwen2.5:14b}"
+OLLAMA_PORT="${OLLAMA_PORT:-11435}"
+
+OS="$(uname -s)"
+
+# --- Colors ---
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+CYAN='\033[0;36m'
+NC='\033[0m'
+
+info()  { echo -e "${CYAN}==>${NC} $*"; }
+ok()    { echo -e "${GREEN}  ✓${NC} $*"; }
+warn()  { echo -e "${YELLOW}  !${NC} $*"; }
+err()   { echo -e "${RED}  ✗${NC} $*" >&2; }
+
+# --- Helpers ---
+
+dump_diagnostics() {
+    local failed_svc="${1:-}"
+    echo ""
+    err "========== DIAGNOSTICS =========="
+
+    err "Container status:"
+    compose_cmd ps -a --format "table {{.Name}}\t{{.Status}}" 2>/dev/null || true
+    echo ""
+
+    # Show logs for any container that exited
+    local stopped
+    stopped=$(compose_cmd ps -a --format '{{.Name}}\t{{.Status}}' 2>/dev/null \
+        | grep -iv 'up\|running' | awk -F'\t' '{print $1}' || true)
+    for c in $stopped; do
+        err "--- Logs for $c (exited/unhealthy) ---"
+        docker logs --tail 30 "$c" 2>&1 || true
+        echo ""
+    done
+
+    # If a specific service failed, always show its logs
+    if [[ -n "$failed_svc" ]]; then
+        err "--- Logs for $failed_svc (last 40) ---"
+        compose_cmd logs "$failed_svc" --tail 40 2>&1 || true
+        echo ""
+        # Try health check from inside the container as extra signal
+        err "--- Internal health check ($failed_svc) ---"
+        compose_cmd exec -T "$failed_svc" \
+            curl -sf http://localhost:1250/health 2>&1 || echo "(not reachable internally either)"
+    fi
+
+    err "================================="
+}
+
+trap 'dump_diagnostics' ERR
+
+# Get the image ID for a compose service (works even when containers are not running).
+svc_image_id() {
+    local svc="$1"
+    # Extract image name from compose config YAML, fall back to <project>-<service>
+    local img_name
+    img_name=$(compose_cmd config 2>/dev/null \
+        | sed -n "/^  ${svc}:/,/^  [a-z]/p" | grep '^\s*image:' | awk '{print $2}')
+    img_name="${img_name:-reflector-$svc}"
+    docker images -q "$img_name" 2>/dev/null | head -1
+}
+
+# Ensure images with build contexts are up-to-date.
+# Docker layer cache makes this fast (~seconds) when source hasn't changed.
+rebuild_images() {
+    local svc
+    for svc in web cpu; do
+        local old_id
+        old_id=$(svc_image_id "$svc")
+        old_id="${old_id:-<none>}"
+
+        info "Building $svc..."
+        compose_cmd build "$svc"
+
+        local new_id
+        new_id=$(svc_image_id "$svc")
+
+        if [[ "$old_id" == "$new_id" ]]; then
+            ok "$svc unchanged (${new_id:0:12})"
+        else
+            ok "$svc rebuilt (${old_id:0:12} -> ${new_id:0:12})"
+        fi
+    done
+}
+
+detect_lan_ip() {
+    # Returns the host's LAN IP — used for WebRTC ICE candidate rewriting.
+    case "$OS" in
+        Darwin)
+            # Try common interfaces: en0 (Wi-Fi), en1 (Ethernet)
+            for iface in en0 en1 en2 en3; do
+                local ip
+                ip=$(ipconfig getifaddr "$iface" 2>/dev/null || true)
+                if [[ -n "$ip" ]]; then
+                    echo "$ip"
+                    return
+                fi
+            done
+            ;;
+        Linux)
+            ip route get 1.1.1.1 2>/dev/null | sed -n 's/.*src \([^ ]*\).*/\1/p'
+            return
+            ;;
+    esac
+    # Fallback — empty means "not detected"
+    echo ""
+}
+
+wait_for_url() {
+    local url="$1" label="$2" retries="${3:-30}" interval="${4:-2}"
+    for i in $(seq 1 "$retries"); do
+        if curl -sf "$url" > /dev/null 2>&1; then
+            return 0
+        fi
+        echo -ne "\r  Waiting for $label... ($i/$retries)"
+        sleep "$interval"
+    done
+    echo ""
+    err "$label not responding at $url after $retries attempts"
+    return 1
+}
+
+env_has_key() {
+    local file="$1" key="$2"
+    grep -q "^${key}=" "$file" 2>/dev/null
+}
+
+env_set() {
+    local file="$1" key="$2" value="$3"
+    if env_has_key "$file" "$key"; then
+        # Replace existing value (portable sed)
+        if [[ "$OS" == "Darwin" ]]; then
+            sed -i '' "s|^${key}=.*|${key}=${value}|" "$file"
+        else
+            sed -i "s|^${key}=.*|${key}=${value}|" "$file"
+        fi
+    else
+        echo "${key}=${value}" >> "$file"
+    fi
+}
+
+resolve_symlink() {
+    local file="$1"
+    if [[ -L "$file" ]]; then
+        warn "$(basename "$file") is a symlink — creating standalone copy"
+        cp -L "$file" "$file.tmp"
+        rm "$file"
+        mv "$file.tmp" "$file"
+    fi
+}
+
+compose_cmd() {
+    local compose_files="-f $ROOT_DIR/docker-compose.standalone.yml"
+    if [[ "$OS" == "Linux" ]] && [[ -n "${OLLAMA_PROFILE:-}" ]]; then
+        docker compose $compose_files --profile "$OLLAMA_PROFILE" "$@"
+    else
+        docker compose $compose_files "$@"
+    fi
+}
+
+# =========================================================
+# Step 1: LLM / Ollama
+# =========================================================
+step_llm() {
+    info "Step 1: LLM setup (Ollama + $MODEL)"
+
+    case "$OS" in
+        Darwin)
+            if ! command -v ollama &> /dev/null; then
+                err "Ollama not found. Install it:"
+                err "  brew install ollama"
+                err "  # or https://ollama.com/download"
+                exit 1
+            fi
+
+            # Start if not running
+            if ! curl -sf "http://localhost:$OLLAMA_PORT/api/tags" > /dev/null 2>&1; then
+                info "Starting Ollama..."
+                ollama serve &
+                disown
+            fi
+
+            wait_for_url "http://localhost:$OLLAMA_PORT/api/tags" "Ollama"
+            echo ""
+
+            # Pull model if not already present
+            if ollama list 2>/dev/null | awk '{print $1}' | grep -qxF "$MODEL"; then
+                ok "Model $MODEL already pulled"
+            else
+                info "Pulling model $MODEL (this may take a while)..."
+                ollama pull "$MODEL"
+            fi
+
+            LLM_URL_VALUE="http://host.docker.internal:$OLLAMA_PORT/v1"
+            ;;
+
+        Linux)
+            if command -v nvidia-smi &> /dev/null && nvidia-smi > /dev/null 2>&1; then
+                ok "NVIDIA GPU detected — using ollama-gpu profile"
+                OLLAMA_PROFILE="ollama-gpu"
+                OLLAMA_SVC="ollama"
+                LLM_URL_VALUE="http://ollama:$OLLAMA_PORT/v1"
+            else
+                warn "No NVIDIA GPU — using ollama-cpu profile"
+                OLLAMA_PROFILE="ollama-cpu"
+                OLLAMA_SVC="ollama-cpu"
+                LLM_URL_VALUE="http://ollama-cpu:$OLLAMA_PORT/v1"
+            fi
+
+            info "Starting Ollama container..."
+            compose_cmd up -d
+
+            wait_for_url "http://localhost:$OLLAMA_PORT/api/tags" "Ollama"
+            echo ""
+
+            # Pull model inside container
+            if compose_cmd exec "$OLLAMA_SVC" ollama list 2>/dev/null | awk '{print $1}' | grep -qxF "$MODEL"; then
+                ok "Model $MODEL already pulled"
+            else
+                info "Pulling model $MODEL inside container (this may take a while)..."
+                compose_cmd exec "$OLLAMA_SVC" ollama pull "$MODEL"
+            fi
+            ;;
+
+        *)
+            err "Unsupported OS: $OS"
+            exit 1
+            ;;
+    esac
+
+    ok "LLM ready ($MODEL via Ollama)"
+}
+
+# =========================================================
+# Step 2: Generate server/.env
+# =========================================================
+step_server_env() {
+    info "Step 2: Generating server/.env"
+
+    resolve_symlink "$SERVER_ENV"
+
+    if [[ -f "$SERVER_ENV" ]]; then
+        ok "server/.env already exists — ensuring standalone vars"
+    else
+        cat > "$SERVER_ENV" << 'ENVEOF'
+# Generated by setup-standalone.sh — standalone local development
+# Source of truth for settings: server/reflector/settings.py
+ENVEOF
+        ok "Created server/.env"
+    fi
+
+    # Ensure all standalone-critical vars (appends if missing, replaces if present)
+    env_set "$SERVER_ENV" "DATABASE_URL" "postgresql+asyncpg://reflector:reflector@postgres:5432/reflector"
+    env_set "$SERVER_ENV" "REDIS_HOST" "redis"
+    env_set "$SERVER_ENV" "CELERY_BROKER_URL" "redis://redis:6379/1"
+    env_set "$SERVER_ENV" "CELERY_RESULT_BACKEND" "redis://redis:6379/1"
+    env_set "$SERVER_ENV" "AUTH_BACKEND" "none"
+    env_set "$SERVER_ENV" "PUBLIC_MODE" "true"
+    # TRANSCRIPT_BACKEND, TRANSCRIPT_URL, DIARIZATION_BACKEND, DIARIZATION_URL
+    # are set via docker-compose.standalone.yml `environment:` overrides — not written here
+    # so we don't clobber the user's server/.env for non-standalone use.
+    env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "passthrough"
+    env_set "$SERVER_ENV" "LLM_URL" "$LLM_URL_VALUE"
+    env_set "$SERVER_ENV" "LLM_MODEL" "$MODEL"
+    env_set "$SERVER_ENV" "LLM_API_KEY" "not-needed"
+
+    # WebRTC: detect LAN IP for ICE candidate rewriting (bridge networking)
+    local lan_ip
+    lan_ip=$(detect_lan_ip)
+    if [[ -n "$lan_ip" ]]; then
+        env_set "$SERVER_ENV" "WEBRTC_HOST" "$lan_ip"
+        ok "WebRTC host IP: $lan_ip"
+    else
+        warn "Could not detect LAN IP — WebRTC recording from other devices may not work"
+        warn "Set WEBRTC_HOST=<your-lan-ip> in server/.env manually"
+    fi
+
+    ok "Standalone vars set (LLM_URL=$LLM_URL_VALUE)"
+}
+
+# =========================================================
+# Step 3: Object storage (Garage)
+# =========================================================
+step_storage() {
+    info "Step 3: Object storage (Garage)"
+
+    # Generate garage.toml from template (fill in RPC secret)
+    GARAGE_TOML="$ROOT_DIR/scripts/garage.toml"
+    GARAGE_TOML_RUNTIME="$ROOT_DIR/data/garage.toml"
+    mkdir -p "$ROOT_DIR/data"
+    if [[ -d "$GARAGE_TOML_RUNTIME" ]]; then
+        rm -rf "$GARAGE_TOML_RUNTIME"
+    fi
+    if [[ ! -f "$GARAGE_TOML_RUNTIME" ]]; then
+        RPC_SECRET=$(openssl rand -hex 32)
+        sed "s|__GARAGE_RPC_SECRET__|${RPC_SECRET}|" "$GARAGE_TOML" > "$GARAGE_TOML_RUNTIME"
+    fi
+
+    compose_cmd up -d garage
+
+    # Use /metrics for readiness — /health returns 503 until layout is applied
+    if ! wait_for_url "http://localhost:3903/metrics" "Garage admin API"; then
+        echo ""
+        err "Garage container logs:"
+        compose_cmd logs garage --tail 30 2>&1 || true
+        exit 1
+    fi
+    echo ""
+
+    # Layout: get node ID, assign, apply (skip if already applied)
+    NODE_ID=$(compose_cmd exec -T garage /garage node id -q 2>/dev/null | tr -d '[:space:]')
+    LAYOUT_STATUS=$(compose_cmd exec -T garage /garage layout show 2>&1 || true)
+    if echo "$LAYOUT_STATUS" | grep -q "No nodes"; then
+        compose_cmd exec -T garage /garage layout assign "$NODE_ID" -c 1G -z dc1
+        compose_cmd exec -T garage /garage layout apply --version 1
+    fi
+
+    # Create bucket (idempotent — skip if exists)
+    if ! compose_cmd exec -T garage /garage bucket info reflector-media &>/dev/null; then
+        compose_cmd exec -T garage /garage bucket create reflector-media
+    fi
+
+    # Create key (idempotent — skip if exists)
+    CREATED_KEY=false
+    if compose_cmd exec -T garage /garage key info reflector &>/dev/null; then
+        ok "Key 'reflector' already exists"
+    else
+        KEY_OUTPUT=$(compose_cmd exec -T garage /garage key create reflector)
+        CREATED_KEY=true
+    fi
+
+    # Grant bucket permissions (idempotent)
+    compose_cmd exec -T garage /garage bucket allow reflector-media --read --write --key reflector
+
+    # Set env vars (only parse key on first create — key info redacts the secret)
+    env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_BACKEND" "aws"
+    env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL" "http://garage:3900"
+    env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_AWS_BUCKET_NAME" "reflector-media"
+    env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_AWS_REGION" "garage"
+    if [[ "$CREATED_KEY" == "true" ]]; then
+        KEY_ID=$(echo "$KEY_OUTPUT" | grep -i "key id" | awk '{print $NF}')
+        KEY_SECRET=$(echo "$KEY_OUTPUT" | grep -i "secret key" | awk '{print $NF}')
+        env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID" "$KEY_ID"
+        env_set "$SERVER_ENV" "TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY" "$KEY_SECRET"
+    fi
+
+    ok "Object storage ready (Garage)"
+}
+
+# =========================================================
+# Step 4: Generate www/.env.local
+# =========================================================
+step_www_env() {
+    info "Step 4: Generating www/.env.local"
+
+    resolve_symlink "$WWW_ENV"
+
+    if [[ -f "$WWW_ENV" ]]; then
+        ok "www/.env.local already exists — ensuring standalone vars"
+    else
+        cat > "$WWW_ENV" << 'ENVEOF'
+# Generated by setup-standalone.sh — standalone local development
+ENVEOF
+        ok "Created www/.env.local"
+    fi
+
+    # Caddyfile.standalone.example serves API at /v1, /health — use base URL
+    if [[ -n "${PRIMARY_IP:-}" ]]; then
+        BASE_URL="https://$PRIMARY_IP:3043"
+    else
+        BASE_URL="https://localhost:3043"
+    fi
+    env_set "$WWW_ENV" "SITE_URL" "$BASE_URL"
+    env_set "$WWW_ENV" "NEXTAUTH_URL" "$BASE_URL"
+    env_set "$WWW_ENV" "NEXTAUTH_SECRET" "standalone-dev-secret-not-for-production"
+    env_set "$WWW_ENV" "API_URL" "$BASE_URL"
+    env_set "$WWW_ENV" "WEBSOCKET_URL" "auto"
+    env_set "$WWW_ENV" "SERVER_API_URL" "http://server:1250"
+    env_set "$WWW_ENV" "FEATURE_REQUIRE_LOGIN" "false"
+
+    ok "Standalone www vars set"
+}
+
+# =========================================================
+# Step 5: Start all services
+# =========================================================
+step_services() {
+    info "Step 5: Starting Docker services"
+
+    # Check for port conflicts — stale processes silently shadow Docker port mappings.
+    # OrbStack/Docker Desktop bind ports for forwarding; ignore those PIDs.
+    local ports_ok=true
+    for port in 3043 3000 1250 5432 6379 3900 3903; do
+        local pids
+        pids=$(lsof -ti :"$port" 2>/dev/null || true)
+        for pid in $pids; do
+            local pname
+            pname=$(ps -p "$pid" -o comm= 2>/dev/null || true)
+            # OrbStack and Docker Desktop own port forwarding — not real conflicts
+            if [[ "$pname" == *"OrbStack"* ]] || [[ "$pname" == *"com.docker"* ]] || [[ "$pname" == *"vpnkit"* ]]; then
+                continue
+            fi
+            warn "Port $port already in use by PID $pid ($pname)"
+            warn "Kill it with: lsof -ti :$port | xargs kill"
+            ports_ok=false
+        done
+    done
+    if [[ "$ports_ok" == "false" ]]; then
+        warn "Port conflicts detected — Docker containers may not be reachable"
+        warn "Continuing anyway (services will start but may be shadowed)"
+    fi
+
+    # Rebuild images if source has changed (Docker layer cache makes this fast when unchanged)
+    rebuild_images
+
+    # server runs alembic migrations on startup automatically (see runserver.sh)
+    compose_cmd up -d postgres redis garage cpu server worker beat web caddy
+    ok "Containers started"
+
+    # Quick sanity check — catch containers that exit immediately (bad image, missing file, etc.)
+    sleep 3
+    local exited
+    exited=$(compose_cmd ps -a --format '{{.Name}} {{.Status}}' 2>/dev/null \
+        | grep -i 'exit' || true)
+    if [[ -n "$exited" ]]; then
+        warn "Some containers exited immediately:"
+        echo "$exited" | while read -r line; do warn "  $line"; done
+        dump_diagnostics
+    fi
+
+    info "Server is running migrations (alembic upgrade head)..."
+}
+
+# =========================================================
+# Step 6: Health checks
+# =========================================================
+step_health() {
+    info "Step 6: Health checks"
+
+    # CPU service may take a while on first start (model download + load).
+    # No host port exposed — check via docker exec.
+    info "Waiting for CPU service (first start downloads ~1GB of models)..."
+    local cpu_ok=false
+    for i in $(seq 1 120); do
+        if compose_cmd exec -T cpu curl -sf http://localhost:8000/docs > /dev/null 2>&1; then
+            cpu_ok=true
+            break
+        fi
+        echo -ne "\r  Waiting for CPU service... ($i/120)"
+        sleep 5
+    done
+    echo ""
+    if [[ "$cpu_ok" == "true" ]]; then
+        ok "CPU service healthy (transcription + diarization)"
+    else
+        warn "CPU service not ready yet — it will keep loading in the background"
+        warn "Check with: docker compose logs cpu"
+    fi
+
+    # Server may take a long time on first run — alembic migrations run before uvicorn starts.
+    # Use docker exec so this works regardless of network_mode or port mapping.
+    info "Waiting for Server API (first run includes database migrations)..."
+    local server_ok=false
+    for i in $(seq 1 90); do
+        # Check if container is still running
+        local svc_status
+        svc_status=$(compose_cmd ps server --format '{{.Status}}' 2>/dev/null || true)
+        if [[ -z "$svc_status" ]] || echo "$svc_status" | grep -qi 'exit'; then
+            echo ""
+            err "Server container exited unexpectedly"
+            dump_diagnostics server
+            exit 1
+        fi
+        # Health check from inside container (avoids host networking issues)
+        if compose_cmd exec -T server curl -sf http://localhost:1250/health > /dev/null 2>&1; then
+            server_ok=true
+            break
+        fi
+        echo -ne "\r  Waiting for Server API... ($i/90)"
+        sleep 5
+    done
+    echo ""
+    if [[ "$server_ok" == "true" ]]; then
+        ok "Server API healthy"
+    else
+        err "Server API not ready after ~7 minutes"
+        dump_diagnostics server
+        exit 1
+    fi
+
+    wait_for_url "http://localhost:3000" "Frontend" 90 3
+    echo ""
+    ok "Frontend responding"
+
+    # Caddy reverse proxy (self-signed TLS — curl needs -k)
+    if curl -sfk "https://localhost:3043" > /dev/null 2>&1; then
+        ok "Caddy proxy healthy (https://localhost:3043)"
+    else
+        warn "Caddy proxy not responding on https://localhost:3043"
+        warn "Check with: docker compose logs caddy"
+    fi
+
+    # Check LLM reachability from inside a container
+    if compose_cmd exec -T server \
+        curl -sf "$LLM_URL_VALUE/models" > /dev/null 2>&1; then
+        ok "LLM reachable from containers"
+    else
+        warn "LLM not reachable from containers at $LLM_URL_VALUE"
+        warn "Summaries/topics/titles won't work until LLM is accessible"
+    fi
+}
+
+# =========================================================
+# Main
+# =========================================================
+main() {
+    echo ""
+    echo "=========================================="
+    echo " Reflector — Standalone Local Setup"
+    echo "=========================================="
+    echo ""
+
+    # Ensure we're in the repo root
+    if [[ ! -f "$ROOT_DIR/docker-compose.yml" ]]; then
+        err "docker-compose.yml not found in $ROOT_DIR"
+        err "Run this script from the repo root: ./scripts/setup-standalone.sh"
+        exit 1
+    fi
+
+    # Docker: Compose plugin, buildx, and daemon. On Ubuntu, auto-install if missing.
+    docker_ready() {
+        docker compose version 2>/dev/null | grep -qi compose \
+            && docker buildx version &>/dev/null \
+            && docker info &>/dev/null
+    }
+
+    if ! docker_ready; then
+        RAN_INSTALL=false
+        if [[ "$OS" == "Linux" ]] && [[ -f /etc/os-release ]] && (source /etc/os-release 2>/dev/null; [[ "${ID:-}" == "ubuntu" || "${ID_LIKE:-}" == *"ubuntu"* ]]); then
+            info "Docker not ready. Running install-docker-ubuntu.sh..."
+            "$SCRIPT_DIR/install-docker-ubuntu.sh" || true
+            RAN_INSTALL=true
+            [[ -d /run/systemd/system ]] && command -v systemctl &>/dev/null && systemctl start docker 2>/dev/null || true
+            sleep 2
+        fi
+        if ! docker_ready; then
+            # Docker may be installed but current shell lacks docker group (needs newgrp)
+            if [[ "$RAN_INSTALL" == "true" ]] && [[ $(id -u) -ne 0 ]] && command -v sg &>/dev/null && getent group docker &>/dev/null; then
+                info "Re-running with docker group..."
+                exec sg docker -c "$(printf '%q' "$0" && printf ' %q' "$@")"
+            fi
+            if [[ "$OS" == "Darwin" ]]; then
+                err "Docker not ready. Install Docker Desktop or OrbStack."
+            elif [[ "$OS" == "Linux" ]]; then
+                err "Docker not ready. Run: ./scripts/install-docker-ubuntu.sh"
+                err "Then run: newgrp docker   (or log out and back in), then run this script again."
+            else
+                err "Docker not ready. Install Docker with Compose V2 and buildx."
+            fi
+            exit 1
+        fi
+    fi
+
+    # LLM_URL_VALUE is set by step_llm, used by later steps
+    LLM_URL_VALUE=""
+    OLLAMA_PROFILE=""
+
+    # docker-compose.yml may reference env_files that don't exist yet;
+    # touch them so compose_cmd works before the steps that populate them.
+    touch "$SERVER_ENV" "$WWW_ENV"
+
+    # Ensure garage.toml exists before any compose up (step_llm starts all services including garage)
+    GARAGE_TOML="$ROOT_DIR/scripts/garage.toml"
+    GARAGE_TOML_RUNTIME="$ROOT_DIR/data/garage.toml"
+    mkdir -p "$ROOT_DIR/data"
+    if [[ -d "$GARAGE_TOML_RUNTIME" ]]; then
+        rm -rf "$GARAGE_TOML_RUNTIME"
+    fi
+    if [[ ! -f "$GARAGE_TOML_RUNTIME" ]]; then
+        RPC_SECRET=$(openssl rand -hex 32)
+        sed "s|__GARAGE_RPC_SECRET__|${RPC_SECRET}|" "$GARAGE_TOML" > "$GARAGE_TOML_RUNTIME"
+    fi
+
+    # Remove containers that may have bad mounts (was directory); force recreate
+    compose_cmd rm -f -s garage caddy 2>/dev/null || true
+
+    # Detect primary IP for droplet (used for Caddyfile, step_www_env, success message)
+    PRIMARY_IP=""
+    if [[ "$OS" == "Linux" ]]; then
+        PRIMARY_IP=$(hostname -I 2>/dev/null | awk '{print $1}' || true)
+        if [[ "$PRIMARY_IP" == "127."* ]] || [[ -z "$PRIMARY_IP" ]]; then
+            PRIMARY_IP=$(ip -4 route get 1 2>/dev/null | sed -n 's/.*src \([0-9.]*\).*/\1/p' || true)
+        fi
+    fi
+
+    # Ensure Caddyfile exists before any compose up (step_llm starts caddy)
+    # On droplet: explicit IP + localhost so Caddy provisions cert at startup (avoids on_demand/SNI issues)
+    CADDYFILE="$ROOT_DIR/Caddyfile"
+    if [[ -d "$CADDYFILE" ]]; then
+        rm -rf "$CADDYFILE"
+    fi
+    if [[ -n "$PRIMARY_IP" ]]; then
+        cat > "$CADDYFILE" << CADDYEOF
+# Generated by setup-standalone.sh — explicit IP for droplet (provisions cert at startup)
+https://$PRIMARY_IP, localhost {
+    tls internal
+    handle /v1/* {
+        reverse_proxy server:1250
+    }
+    handle /health {
+        reverse_proxy server:1250
+    }
+    handle {
+        reverse_proxy web:3000
+    }
+}
+CADDYEOF
+        ok "Created Caddyfile for $PRIMARY_IP and localhost"
+    elif [[ ! -f "$CADDYFILE" ]]; then
+        cp "$ROOT_DIR/Caddyfile.standalone.example" "$CADDYFILE"
+    fi
+
+    step_llm
+    echo ""
+    step_server_env
+    echo ""
+    step_storage
+    echo ""
+    step_www_env
+    echo ""
+    step_services
+    echo ""
+    step_health
+
+    echo ""
+    echo "=========================================="
+    echo -e " ${GREEN}Reflector is running!${NC}"
+    echo "=========================================="
+    echo ""
+    if [[ -n "$PRIMARY_IP" ]]; then
+        echo "  App:       https://$PRIMARY_IP:3043  (accept self-signed cert in browser)"
+        echo "  API:       https://$PRIMARY_IP:3043/v1/"
+        echo "  Local:     https://localhost:3043"
+    else
+        echo "  App:       https://localhost:3043  (accept self-signed cert in browser)"
+        echo "  API:       https://localhost:3043/v1/"
+    fi
+    echo ""
+    echo "  To stop:   docker compose down"
+    echo "  To re-run: ./scripts/setup-standalone.sh"
+    echo ""
+}
+
+main "$@"

server/.env.example

@@ -66,15 +66,22 @@ TRANSLATE_URL=https://monadical-sas--reflector-translator-web.modal.run
 ## LLM backend (Required)
 ##
 ## Responsible for generating titles, summaries, and topic detection
-## Requires OpenAI API key
+## Supports any OpenAI-compatible endpoint.
 ## =======================================================
 
-## OpenAI API key - get from https://platform.openai.com/account/api-keys
-LLM_API_KEY=sk-your-openai-api-key
-LLM_MODEL=gpt-4o-mini
+## --- Option A: Local LLM via Ollama (recommended for dev) ---
+## Setup: ./scripts/setup-standalone.sh
+## Mac: Ollama runs natively (Metal GPU). Containers reach it via host.docker.internal.
+## Linux: docker compose --profile ollama-gpu up -d (or ollama-cpu for no GPU)
+LLM_URL=http://host.docker.internal:11435/v1
+LLM_MODEL=qwen2.5:14b
+LLM_API_KEY=not-needed
+## Linux with containerized Ollama: LLM_URL=http://ollama:11435/v1
 
-## Optional: Custom endpoint (defaults to OpenAI)
-# LLM_URL=https://api.openai.com/v1
+## --- Option B: Remote/cloud LLM ---
+#LLM_API_KEY=sk-your-openai-api-key
+#LLM_MODEL=gpt-4o-mini
+## LLM_URL defaults to OpenAI when unset
 
 ## Context size for summary generation (tokens)
 LLM_CONTEXT_WINDOW=16000

server/.env.selfhosted.example

@@ -0,0 +1,115 @@
+# =======================================================
+# Reflector Self-Hosted Production — Backend Configuration
+# Generated by: ./scripts/setup-selfhosted.sh
+# Reference: server/reflector/settings.py
+# =======================================================
+
+# =======================================================
+# Database & Infrastructure
+# Pre-filled for Docker internal networking (docker-compose.selfhosted.yml)
+# =======================================================
+DATABASE_URL=postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+REDIS_HOST=redis
+REDIS_PORT=6379
+CELERY_BROKER_URL=redis://redis:6379/1
+CELERY_RESULT_BACKEND=redis://redis:6379/1
+
+# Secret key — auto-generated by setup script
+# Generate manually with: openssl rand -hex 32
+SECRET_KEY=changeme-generate-a-secure-random-string
+
+# =======================================================
+# Authentication
+# Disabled by default. Enable Authentik for multi-user access.
+# See docsv2/selfhosted-production.md for setup instructions.
+# =======================================================
+AUTH_BACKEND=none
+# AUTH_BACKEND=jwt
+# AUTH_JWT_AUDIENCE=
+# AUTH_BACKEND=password
+# ADMIN_EMAIL=admin@localhost
+# ADMIN_PASSWORD_HASH=pbkdf2:sha256:100000$<salt>$<hash>
+
+# =======================================================
+# Specialized Models (Transcription, Diarization, Translation)
+# These run in the gpu/cpu container — NOT an LLM.
+# The "modal" backend means "HTTP API client" — it talks to
+# the self-hosted container, not Modal.com cloud.
+# =======================================================
+TRANSCRIPT_BACKEND=modal
+TRANSCRIPT_URL=http://transcription:8000
+TRANSCRIPT_MODAL_API_KEY=selfhosted
+
+DIARIZATION_ENABLED=true
+DIARIZATION_BACKEND=modal
+DIARIZATION_URL=http://transcription:8000
+
+TRANSLATION_BACKEND=modal
+TRANSLATE_URL=http://transcription:8000
+
+# HuggingFace token — optional, for gated models (e.g. pyannote).
+# Falls back to public S3 model bundle if not set.
+# HF_TOKEN=hf_xxxxx
+
+# =======================================================
+# LLM for Summarization & Topic Detection
+# Only summaries and topics use an LLM. Everything else
+# (transcription, diarization, translation) uses specialized models above.
+#
+# Supports any OpenAI-compatible endpoint.
+# Auto-configured by setup script if using --ollama-gpu or --ollama-cpu.
+# For --gpu or --cpu modes, you MUST configure an external LLM.
+# =======================================================
+
+# --- Option A: External OpenAI-compatible API ---
+# LLM_URL=https://api.openai.com/v1
+# LLM_API_KEY=sk-your-api-key
+# LLM_MODEL=gpt-4o-mini
+
+# --- Option B: Local Ollama (auto-set by --ollama-gpu/--ollama-cpu) ---
+# LLM_URL=http://ollama:11435/v1
+# LLM_API_KEY=not-needed
+# LLM_MODEL=llama3.1
+
+LLM_CONTEXT_WINDOW=16000
+
+# =======================================================
+# S3 Storage (REQUIRED)
+# Where to store audio files and transcripts.
+#
+# Option A: Use --garage flag (auto-configured by setup script)
+# Option B: Any S3-compatible endpoint (AWS, MinIO, etc.)
+#           Set TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL for non-AWS endpoints.
+# =======================================================
+TRANSCRIPT_STORAGE_BACKEND=aws
+TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID=
+TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY=
+TRANSCRIPT_STORAGE_AWS_BUCKET_NAME=reflector-media
+TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
+
+# For non-AWS S3-compatible endpoints (Garage, MinIO, etc.):
+# TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://garage:3900
+
+# =======================================================
+# Daily.co Live Rooms (Optional)
+# Enable real-time meeting rooms with Daily.co integration.
+# Requires a Daily.co account: https://www.daily.co/
+# =======================================================
+# DEFAULT_VIDEO_PLATFORM=daily
+# DAILY_API_KEY=your-daily-api-key
+# DAILY_SUBDOMAIN=your-subdomain
+# DAILY_WEBHOOK_SECRET=your-daily-webhook-secret
+# DAILYCO_STORAGE_AWS_BUCKET_NAME=reflector-dailyco
+# DAILYCO_STORAGE_AWS_REGION=us-east-1
+# DAILYCO_STORAGE_AWS_ROLE_ARN=arn:aws:iam::role/DailyCoAccess
+
+# =======================================================
+# Feature Flags
+# =======================================================
+PUBLIC_MODE=true
+# FEATURE_ROOMS=true
+
+# =======================================================
+# Sentry (Optional)
+# =======================================================
+# SENTRY_DSN=

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)
-}
-
-// OR (when present):
-{
-  "id": "recording-uuid",
-  "mtgSessionId": "92c4136a-a8da-41c5-9c45-e9a2baae6bd6"  // ← Sometimes present
+  "mtgSessionId": null  ← Missing!
 }
 ```
 
-**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
-**Last Updated:** 2026-01-20
-**Data Source:** Production database + Daily.co API inspection + empirical testing
-**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
+**Document Version:** 1.0
+**Last Verified:** 2026-01-15
+**Data Source:** Production database + Daily.co API inspection

server/migrations/versions/3aa20b96d963_drop_use_celery_column.py

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

server/migrations/versions/623af934249a_add_change_seq_to_transcript.py

@@ -0,0 +1,74 @@
+"""add_change_seq_to_transcript
+
+Revision ID: 623af934249a
+Revises: 3aa20b96d963
+Create Date: 2026-02-19 18:53:12.315440
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "623af934249a"
+down_revision: Union[str, None] = "3aa20b96d963"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Sequence
+    op.execute("CREATE SEQUENCE IF NOT EXISTS transcript_change_seq;")
+
+    # Column (nullable first for backfill)
+    op.add_column("transcript", sa.Column("change_seq", sa.BigInteger(), nullable=True))
+
+    # Backfill existing rows with sequential values (ordered by created_at for determinism)
+    op.execute("""
+        UPDATE transcript SET change_seq = sub.seq FROM (
+            SELECT id, nextval('transcript_change_seq') AS seq
+            FROM transcript ORDER BY created_at ASC
+        ) sub WHERE transcript.id = sub.id;
+    """)
+
+    # Now make NOT NULL
+    op.alter_column("transcript", "change_seq", nullable=False)
+
+    # Default for any inserts between now and trigger creation
+    op.alter_column(
+        "transcript",
+        "change_seq",
+        server_default=sa.text("nextval('transcript_change_seq')"),
+    )
+
+    # Trigger function
+    op.execute("""
+        CREATE OR REPLACE FUNCTION set_transcript_change_seq()
+        RETURNS TRIGGER AS $$
+        BEGIN
+            NEW.change_seq := nextval('transcript_change_seq');
+            RETURN NEW;
+        END;
+        $$ LANGUAGE plpgsql;
+    """)
+
+    # Trigger (fires on every INSERT or UPDATE)
+    op.execute("""
+        CREATE TRIGGER trigger_transcript_change_seq
+            BEFORE INSERT OR UPDATE ON transcript
+            FOR EACH ROW
+            EXECUTE FUNCTION set_transcript_change_seq();
+    """)
+
+    # Index for efficient polling
+    op.create_index("idx_transcript_change_seq", "transcript", ["change_seq"])
+
+
+def downgrade() -> None:
+    op.execute("DROP TRIGGER IF EXISTS trigger_transcript_change_seq ON transcript;")
+    op.execute("DROP FUNCTION IF EXISTS set_transcript_change_seq();")
+    op.drop_index("idx_transcript_change_seq", table_name="transcript")
+    op.drop_column("transcript", "change_seq")
+    op.execute("DROP SEQUENCE IF EXISTS transcript_change_seq;")

server/migrations/versions/e1f093f7f124_add_password_hash_to_user.py

@@ -0,0 +1,25 @@
+"""add password_hash to user table
+
+Revision ID: e1f093f7f124
+Revises: 623af934249a
+Create Date: 2026-02-19 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "e1f093f7f124"
+down_revision: Union[str, None] = "623af934249a"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column("user", sa.Column("password_hash", sa.String(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("user", "password_hash")

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

@@ -68,7 +68,6 @@ evaluation = [
     "pydantic>=2.1.1",
 ]
 local = [
-    "pyannote-audio>=3.3.2",
     "faster-whisper>=0.10.0",
 ]
 silero-vad = [

server/reflector/app.py

@@ -8,6 +8,7 @@ from prometheus_fastapi_instrumentator import Instrumentator
 
 import reflector.auth  # noqa
 import reflector.db  # noqa
+from reflector.auth import router as auth_router
 from reflector.events import subscribers_shutdown, subscribers_startup
 from reflector.logger import logger
 from reflector.metrics import metrics_init
@@ -37,6 +38,13 @@ try:
 except ImportError:
     sentry_sdk = None
 
+# Patch aioice port range if configured (must happen before any RTCPeerConnection)
+if settings.WEBRTC_PORT_RANGE:
+    from reflector.webrtc_ports import parse_port_range, patch_aioice_port_range
+
+    _min, _max = parse_port_range(settings.WEBRTC_PORT_RANGE)
+    patch_aioice_port_range(_min, _max)
+
 
 # lifespan events
 @asynccontextmanager
@@ -59,7 +67,7 @@ else:
     logger.info("Sentry disabled")
 
 # build app
-app = FastAPI(lifespan=lifespan)
+app = FastAPI(lifespan=lifespan, root_path=settings.ROOT_PATH)
 app.add_middleware(
     CORSMiddleware,
     allow_credentials=settings.CORS_ALLOW_CREDENTIALS or False,
@@ -98,6 +106,8 @@ app.include_router(user_ws_router, prefix="/v1")
 app.include_router(zulip_router, prefix="/v1")
 app.include_router(whereby_router, prefix="/v1")
 app.include_router(daily_router, prefix="/v1/daily")
+if auth_router:
+    app.include_router(auth_router, prefix="/v1")
 add_pagination(app)
 
 # prepare celery

server/reflector/asynctask.py

@@ -4,8 +4,9 @@ from uuid import uuid4
 
 from celery import current_task
 
-from reflector.db import get_database
+from reflector.db import _database_context, get_database
 from reflector.llm import llm_session_id
+from reflector.ws_manager import reset_ws_manager
 
 
 def asynctask(f):
@@ -20,8 +21,18 @@ def asynctask(f):
                 return await f(*args, **kwargs)
             finally:
                 await database.disconnect()
+                _database_context.set(None)
+
+        if current_task:
+            # Reset cached connections before each Celery task.
+            # Each asyncio.run() creates a new event loop, making connections
+            # from previous tasks stale ("Future attached to a different loop").
+            _database_context.set(None)
+            reset_ws_manager()
 
         coro = run_with_db()
+        if current_task:
+            return asyncio.run(coro)
         try:
             loop = asyncio.get_running_loop()
         except RuntimeError:

server/reflector/auth/__init__.py

@@ -12,3 +12,8 @@ AccessTokenInfo = auth_module.AccessTokenInfo
 authenticated = auth_module.authenticated
 current_user = auth_module.current_user
 current_user_optional = auth_module.current_user_optional
+parse_ws_bearer_token = auth_module.parse_ws_bearer_token
+current_user_ws_optional = auth_module.current_user_ws_optional
+
+# Optional router (e.g. for /auth/login in password backend)
+router = getattr(auth_module, "router", None)

server/reflector/auth/auth_jwt.py

@@ -1,6 +1,9 @@
-from typing import Annotated, List, Optional
+from typing import TYPE_CHECKING, Annotated, List, Optional
 
 from fastapi import Depends, HTTPException
+
+if TYPE_CHECKING:
+    from fastapi import WebSocket
 from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
 from jose import JWTError, jwt
 from pydantic import BaseModel
@@ -124,3 +127,20 @@ async def current_user_optional(
     jwtauth: JWTAuth = Depends(),
 ):
     return await _authenticate_user(jwt_token, api_key, jwtauth)
+
+
+def parse_ws_bearer_token(
+    websocket: "WebSocket",
+) -> tuple[Optional[str], Optional[str]]:
+    raw = websocket.headers.get("sec-websocket-protocol") or ""
+    parts = [p.strip() for p in raw.split(",") if p.strip()]
+    if len(parts) >= 2 and parts[0].lower() == "bearer":
+        return parts[1], "bearer"
+    return None, None
+
+
+async def current_user_ws_optional(websocket: "WebSocket") -> Optional[UserInfo]:
+    token, _ = parse_ws_bearer_token(websocket)
+    if not token:
+        return None
+    return await _authenticate_user(token, None, JWTAuth())

server/reflector/auth/auth_none.py

@@ -1,11 +1,5 @@
-from typing import Annotated
-
-from fastapi import Depends
-from fastapi.security import OAuth2PasswordBearer
 from pydantic import BaseModel
 
-oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token", auto_error=False)
-
 
 class UserInfo(BaseModel):
     sub: str
@@ -15,13 +9,21 @@ class AccessTokenInfo(BaseModel):
     pass
 
 
-def authenticated(token: Annotated[str, Depends(oauth2_scheme)]):
+def authenticated():
     return None
 
 
-def current_user(token: Annotated[str, Depends(oauth2_scheme)]):
+def current_user():
     return None
 
 
-def current_user_optional(token: Annotated[str, Depends(oauth2_scheme)]):
+def current_user_optional():
+    return None
+
+
+def parse_ws_bearer_token(websocket):
+    return None, None
+
+
+async def current_user_ws_optional(websocket):
     return None

server/reflector/auth/auth_password.py

@@ -0,0 +1,198 @@
+"""Password-based authentication backend for selfhosted deployments.
+
+Issues HS256 JWTs signed with settings.SECRET_KEY. Provides a POST /auth/login
+endpoint for email/password authentication.
+"""
+
+import time
+from collections import defaultdict
+from datetime import datetime, timedelta, timezone
+from typing import TYPE_CHECKING, Annotated, Optional
+
+from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
+from jose import JWTError, jwt
+from pydantic import BaseModel
+
+from reflector.auth.password_utils import verify_password
+from reflector.db.user_api_keys import user_api_keys_controller
+from reflector.db.users import user_controller
+from reflector.logger import logger
+from reflector.settings import settings
+
+if TYPE_CHECKING:
+    from fastapi import WebSocket
+
+# --- FastAPI security schemes (same pattern as auth_jwt.py) ---
+oauth2_scheme = OAuth2PasswordBearer(tokenUrl="/v1/auth/login", auto_error=False)
+api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
+
+# --- JWT configuration ---
+JWT_ALGORITHM = "HS256"
+ACCESS_TOKEN_EXPIRE_MINUTES = 60 * 24  # 24 hours
+
+# --- Rate limiting (in-memory) ---
+_login_attempts: dict[str, list[float]] = defaultdict(list)
+RATE_LIMIT_WINDOW = 300  # 5 minutes
+RATE_LIMIT_MAX = 10  # max attempts per window
+
+
+def _check_rate_limit(key: str) -> bool:
+    """Return True if request is allowed, False if rate-limited."""
+    now = time.monotonic()
+    attempts = _login_attempts[key]
+    _login_attempts[key] = [t for t in attempts if now - t < RATE_LIMIT_WINDOW]
+    if len(_login_attempts[key]) >= RATE_LIMIT_MAX:
+        return False
+    _login_attempts[key].append(now)
+    return True
+
+
+# --- Pydantic models ---
+class UserInfo(BaseModel):
+    sub: str
+    email: Optional[str] = None
+
+    def __getitem__(self, key):
+        return getattr(self, key)
+
+
+class AccessTokenInfo(BaseModel):
+    exp: Optional[int] = None
+    sub: Optional[str] = None
+
+
+class LoginRequest(BaseModel):
+    email: str
+    password: str
+
+
+class LoginResponse(BaseModel):
+    access_token: str
+    token_type: str = "bearer"
+    expires_in: int
+
+
+# --- JWT token creation and verification ---
+def _create_access_token(user_id: str, email: str) -> tuple[str, int]:
+    """Create an HS256 JWT. Returns (token, expires_in_seconds)."""
+    expires_delta = timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES)
+    expire = datetime.now(timezone.utc) + expires_delta
+    payload = {
+        "sub": user_id,
+        "email": email,
+        "exp": expire,
+    }
+    token = jwt.encode(payload, settings.SECRET_KEY, algorithm=JWT_ALGORITHM)
+    return token, int(expires_delta.total_seconds())
+
+
+def _verify_token(token: str) -> dict:
+    """Verify and decode an HS256 JWT."""
+    return jwt.decode(token, settings.SECRET_KEY, algorithms=[JWT_ALGORITHM])
+
+
+# --- Authentication logic (mirrors auth_jwt._authenticate_user) ---
+async def _authenticate_user(
+    jwt_token: Optional[str],
+    api_key: Optional[str],
+) -> UserInfo | None:
+    user_infos: list[UserInfo] = []
+
+    if api_key:
+        user_api_key = await user_api_keys_controller.verify_key(api_key)
+        if user_api_key:
+            user_infos.append(UserInfo(sub=user_api_key.user_id, email=None))
+
+    if jwt_token:
+        try:
+            payload = _verify_token(jwt_token)
+            user_id = payload["sub"]
+            email = payload.get("email")
+            user_infos.append(UserInfo(sub=user_id, email=email))
+        except JWTError as e:
+            logger.error(f"JWT error: {e}")
+            raise HTTPException(status_code=401, detail="Invalid authentication")
+
+    if len(user_infos) == 0:
+        return None
+
+    if len(set(x.sub for x in user_infos)) > 1:
+        raise HTTPException(
+            status_code=401,
+            detail="Invalid authentication: more than one user provided",
+        )
+
+    return user_infos[0]
+
+
+# --- FastAPI dependencies (exported, required by auth/__init__.py) ---
+def authenticated(token: Annotated[str, Depends(oauth2_scheme)]):
+    if token is None:
+        raise HTTPException(status_code=401, detail="Not authenticated")
+    return None
+
+
+async def current_user(
+    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
+    api_key: Annotated[Optional[str], Depends(api_key_header)],
+):
+    user = await _authenticate_user(jwt_token, api_key)
+    if user is None:
+        raise HTTPException(status_code=401, detail="Not authenticated")
+    return user
+
+
+async def current_user_optional(
+    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
+    api_key: Annotated[Optional[str], Depends(api_key_header)],
+):
+    return await _authenticate_user(jwt_token, api_key)
+
+
+# --- WebSocket auth (same pattern as auth_jwt.py) ---
+def parse_ws_bearer_token(
+    websocket: "WebSocket",
+) -> tuple[Optional[str], Optional[str]]:
+    raw = websocket.headers.get("sec-websocket-protocol") or ""
+    parts = [p.strip() for p in raw.split(",") if p.strip()]
+    if len(parts) >= 2 and parts[0].lower() == "bearer":
+        return parts[1], "bearer"
+    return None, None
+
+
+async def current_user_ws_optional(websocket: "WebSocket") -> Optional[UserInfo]:
+    token, _ = parse_ws_bearer_token(websocket)
+    if not token:
+        return None
+    return await _authenticate_user(token, None)
+
+
+# --- Login router ---
+router = APIRouter(prefix="/auth", tags=["auth"])
+
+
+@router.post("/login", response_model=LoginResponse)
+async def login(request: Request, body: LoginRequest):
+    client_ip = request.client.host if request.client else "unknown"
+    if not _check_rate_limit(client_ip):
+        raise HTTPException(
+            status_code=429,
+            detail="Too many login attempts. Try again later.",
+        )
+
+    user = await user_controller.get_by_email(body.email)
+    if not user or not user.password_hash:
+        print("invalid email")
+        raise HTTPException(status_code=401, detail="Invalid email or password")
+
+    if not verify_password(body.password, user.password_hash):
+        print("invalid pass")
+        raise HTTPException(status_code=401, detail="Invalid email or password")
+
+    access_token, expires_in = _create_access_token(user.id, user.email)
+    return LoginResponse(
+        access_token=access_token,
+        token_type="bearer",
+        expires_in=expires_in,
+    )

server/reflector/auth/password_utils.py

@@ -0,0 +1,41 @@
+"""Password hashing utilities using PBKDF2-SHA256 (stdlib only)."""
+
+import hashlib
+import hmac
+import os
+
+PBKDF2_ITERATIONS = 100_000
+SALT_LENGTH = 16  # bytes, hex-encoded to 32 chars
+
+
+def hash_password(password: str) -> str:
+    """Hash a password using PBKDF2-SHA256 with a random salt.
+
+    Format: pbkdf2:sha256:<iterations>$<salt_hex>$<hash_hex>
+    """
+    salt = os.urandom(SALT_LENGTH).hex()
+    dk = hashlib.pbkdf2_hmac(
+        "sha256",
+        password.encode("utf-8"),
+        salt.encode("utf-8"),
+        PBKDF2_ITERATIONS,
+    )
+    return f"pbkdf2:sha256:{PBKDF2_ITERATIONS}${salt}${dk.hex()}"
+
+
+def verify_password(password: str, password_hash: str) -> bool:
+    """Verify a password against its hash using constant-time comparison."""
+    try:
+        header, salt, stored_hash = password_hash.split("$", 2)
+        _, algo, iterations_str = header.split(":")
+        iterations = int(iterations_str)
+
+        dk = hashlib.pbkdf2_hmac(
+            algo,
+            password.encode("utf-8"),
+            salt.encode("utf-8"),
+            iterations,
+        )
+        return hmac.compare_digest(dk.hex(), stored_hash)
+    except (ValueError, AttributeError):
+        return False

server/reflector/dailyco_api/client.py

@@ -146,6 +146,8 @@ class DailyApiClient:
             )
             raise DailyApiError(operation, response)
 
+        if not response.content:
+            return {}
         return response.json()
 
     # ============================================================================

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/dailyco_api/webhook_utils.py

@@ -99,7 +99,7 @@ def extract_room_name(event: DailyWebhookEvent) -> str | None:
         >>> event = DailyWebhookEvent(**webhook_payload)
         >>> room_name = extract_room_name(event)
     """
-    room = event.payload.get("room_name")
+    room = event.payload.get("room_name") or event.payload.get("room")
     # Ensure we return a string, not any falsy value that might be in payload
     return room if isinstance(room, str) else None
 

server/reflector/dailyco_api/webhooks.py

@@ -6,7 +6,7 @@ Reference: https://docs.daily.co/reference/rest-api/webhooks
 
 from typing import Annotated, Any, Dict, Literal, Union
 
-from pydantic import BaseModel, Field, field_validator
+from pydantic import AliasChoices, BaseModel, ConfigDict, Field, field_validator
 
 from reflector.utils.string import NonEmptyString
 
@@ -41,6 +41,8 @@ class DailyTrack(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/recordings
     """
 
+    model_config = ConfigDict(extra="ignore")
+
     type: Literal["audio", "video"]
     s3Key: NonEmptyString = Field(description="S3 object key for the track file")
     size: int = Field(description="File size in bytes")
@@ -54,6 +56,8 @@ class DailyWebhookEvent(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks
     """
 
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString = Field(
         description="Represents the version of the event. This uses semantic versioning to inform a consumer if the payload has introduced any breaking changes"
     )
@@ -82,7 +86,13 @@ class ParticipantJoinedPayload(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks/events/participant-joined
     """
 
-    room_name: NonEmptyString | None = Field(None, description="Daily.co room name")
+    model_config = ConfigDict(extra="ignore")
+
+    room_name: NonEmptyString | None = Field(
+        None,
+        description="Daily.co room name",
+        validation_alias=AliasChoices("room_name", "room"),
+    )
     session_id: NonEmptyString = Field(description="Daily.co session identifier")
     user_id: NonEmptyString = Field(description="User identifier (may be encoded)")
     user_name: NonEmptyString | None = Field(None, description="User display name")
@@ -100,7 +110,13 @@ class ParticipantLeftPayload(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks/events/participant-left
     """
 
-    room_name: NonEmptyString | None = Field(None, description="Daily.co room name")
+    model_config = ConfigDict(extra="ignore")
+
+    room_name: NonEmptyString | None = Field(
+        None,
+        description="Daily.co room name",
+        validation_alias=AliasChoices("room_name", "room"),
+    )
     session_id: NonEmptyString = Field(description="Daily.co session identifier")
     user_id: NonEmptyString = Field(description="User identifier (may be encoded)")
     user_name: NonEmptyString | None = Field(None, description="User display name")
@@ -112,6 +128,9 @@ class ParticipantLeftPayload(BaseModel):
     _normalize_joined_at = field_validator("joined_at", mode="before")(
         normalize_timestamp_to_int
     )
+    _normalize_duration = field_validator("duration", mode="before")(
+        normalize_timestamp_to_int
+    )
 
 
 class RecordingStartedPayload(BaseModel):
@@ -121,6 +140,8 @@ class RecordingStartedPayload(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-started
     """
 
+    model_config = ConfigDict(extra="ignore")
+
     room_name: NonEmptyString | None = Field(None, description="Daily.co room name")
     recording_id: NonEmptyString = Field(description="Recording identifier")
     start_ts: int | None = Field(None, description="Recording start timestamp")
@@ -138,7 +159,9 @@ class RecordingReadyToDownloadPayload(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-ready-to-download
     """
 
-    type: Literal["cloud", "raw-tracks"] = Field(
+    model_config = ConfigDict(extra="ignore")
+
+    type: Literal["cloud", "cloud-audio-only", "raw-tracks"] = Field(
         description="The type of recording that was generated"
     )
     recording_id: NonEmptyString = Field(
@@ -153,8 +176,9 @@ class RecordingReadyToDownloadPayload(BaseModel):
     status: Literal["finished"] = Field(
         description="The status of the given recording (always 'finished' in ready-to-download webhook, see RecordingStatus in responses.py for full API statuses)"
     )
-    max_participants: int = Field(
-        description="The number of participants on the call that were recorded"
+    max_participants: int | None = Field(
+        None,
+        description="The number of participants on the call that were recorded (optional; Daily may omit it in some webhook versions)",
     )
     duration: int = Field(description="The duration in seconds of the call")
     s3_key: NonEmptyString = Field(
@@ -180,6 +204,8 @@ class RecordingErrorPayload(BaseModel):
     Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-error
     """
 
+    model_config = ConfigDict(extra="ignore")
+
     action: Literal["clourd-recording-err", "cloud-recording-error"] = Field(
         description="A string describing the event that was emitted (both variants are documented)"
     )
@@ -200,6 +226,8 @@ class RecordingErrorPayload(BaseModel):
 
 
 class ParticipantJoinedEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString
     type: Literal["participant.joined"]
     id: NonEmptyString
@@ -212,6 +240,8 @@ class ParticipantJoinedEvent(BaseModel):
 
 
 class ParticipantLeftEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString
     type: Literal["participant.left"]
     id: NonEmptyString
@@ -224,6 +254,8 @@ class ParticipantLeftEvent(BaseModel):
 
 
 class RecordingStartedEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString
     type: Literal["recording.started"]
     id: NonEmptyString
@@ -236,6 +268,8 @@ class RecordingStartedEvent(BaseModel):
 
 
 class RecordingReadyEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString
     type: Literal["recording.ready-to-download"]
     id: NonEmptyString
@@ -248,6 +282,8 @@ class RecordingReadyEvent(BaseModel):
 
 
 class RecordingErrorEvent(BaseModel):
+    model_config = ConfigDict(extra="ignore")
+
     version: NonEmptyString
     type: Literal["recording.error"]
     id: NonEmptyString

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"] = (
-        "pending"
-    )
+    status: Literal["pending", "processing", "completed", "failed"] = "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
-        # - recordings.py needs transcripts table for JOIN query
-        # - 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
+        from reflector.db.transcripts import (
+            transcripts,  # noqa: PLC0415 cyclic import
+        )
 
         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/db/rooms.py

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

server/reflector/db/search.py

@@ -26,6 +26,7 @@ from reflector.db.rooms import rooms
 from reflector.db.transcripts import SourceKind, TranscriptStatus, transcripts
 from reflector.db.utils import is_postgresql
 from reflector.logger import logger
+from reflector.settings import settings
 from reflector.utils.string import NonEmptyString, try_parse_non_empty_string
 
 DEFAULT_SEARCH_LIMIT = 20
@@ -150,6 +151,7 @@ class SearchResultDB(BaseModel):
     title: str | None = None
     source_kind: SourceKind
     room_id: str | None = None
+    change_seq: int | None = None
     rank: float = Field(..., ge=0, le=1)
 
 
@@ -172,6 +174,7 @@ class SearchResult(BaseModel):
     total_match_count: NonNegativeInt = Field(
         default=0, description="Total number of matches found in the transcript"
     )
+    change_seq: int | None = None
 
     @field_serializer("created_at", when_used="json")
     def serialize_datetime(self, dt: datetime) -> str:
@@ -355,6 +358,7 @@ class SearchController:
             transcripts.c.user_id,
             transcripts.c.room_id,
             transcripts.c.source_kind,
+            transcripts.c.change_seq,
             transcripts.c.webvtt,
             transcripts.c.long_summary,
             sqlalchemy.case(
@@ -396,7 +400,7 @@ class SearchController:
                     transcripts.c.user_id == params.user_id, rooms.c.is_shared
                 )
             )
-        else:
+        elif not settings.PUBLIC_MODE:
             base_query = base_query.where(rooms.c.is_shared)
         if params.room_id:
             base_query = base_query.where(transcripts.c.room_id == params.room_id)

server/reflector/db/transcripts.py

@@ -5,7 +5,10 @@ import shutil
 from contextlib import asynccontextmanager
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
-from typing import Any, Literal, Sequence
+from typing import TYPE_CHECKING, Any, Literal, Sequence
+
+if TYPE_CHECKING:
+    from reflector.ws_events import TranscriptEventName
 
 import sqlalchemy
 from fastapi import HTTPException
@@ -32,6 +35,8 @@ class SourceKind(enum.StrEnum):
     FILE = enum.auto()
 
 
+transcript_change_seq = sqlalchemy.Sequence("transcript_change_seq", metadata=metadata)
+
 transcripts = sqlalchemy.Table(
     "transcript",
     metadata,
@@ -86,6 +91,12 @@ transcripts = sqlalchemy.Table(
     sqlalchemy.Column("webvtt", sqlalchemy.Text),
     # Hatchet workflow run ID for resumption of failed workflows
     sqlalchemy.Column("workflow_run_id", sqlalchemy.String),
+    sqlalchemy.Column(
+        "change_seq",
+        sqlalchemy.BigInteger,
+        transcript_change_seq,
+        server_default=transcript_change_seq.next_value(),
+    ),
     sqlalchemy.Index("idx_transcript_recording_id", "recording_id"),
     sqlalchemy.Index("idx_transcript_user_id", "user_id"),
     sqlalchemy.Index("idx_transcript_created_at", "created_at"),
@@ -184,7 +195,7 @@ class TranscriptWaveform(BaseModel):
 
 
 class TranscriptEvent(BaseModel):
-    event: str
+    event: str  # Typed at call sites via ws_events.TranscriptEventName; str here for DB compat
     data: dict
 
 
@@ -226,6 +237,7 @@ class Transcript(BaseModel):
     audio_deleted: bool | None = None
     webvtt: str | None = None
     workflow_run_id: str | None = None  # Hatchet workflow run ID for resumption
+    change_seq: int | None = None
 
     @field_serializer("created_at", when_used="json")
     def serialize_datetime(self, dt: datetime) -> str:
@@ -233,7 +245,9 @@ class Transcript(BaseModel):
             dt = dt.replace(tzinfo=timezone.utc)
         return dt.isoformat()
 
-    def add_event(self, event: str, data: BaseModel) -> TranscriptEvent:
+    def add_event(
+        self, event: "TranscriptEventName", data: BaseModel
+    ) -> TranscriptEvent:
         ev = TranscriptEvent(event=event, data=data.model_dump())
         self.events.append(ev)
         return ev
@@ -376,6 +390,7 @@ class TranscriptController:
         source_kind: SourceKind | None = None,
         room_id: str | None = None,
         search_term: str | None = None,
+        change_seq_from: int | None = None,
         return_query: bool = False,
         exclude_columns: list[str] = [
             "topics",
@@ -396,6 +411,7 @@ class TranscriptController:
         - `filter_recording`: filter out transcripts that are currently recording
         - `room_id`: filter transcripts by room ID
         - `search_term`: filter transcripts by search term
+        - `change_seq_from`: filter transcripts with change_seq > this value
         """
 
         query = transcripts.select().join(
@@ -406,7 +422,7 @@ class TranscriptController:
             query = query.where(
                 or_(transcripts.c.user_id == user_id, rooms.c.is_shared)
             )
-        else:
+        elif not settings.PUBLIC_MODE:
             query = query.where(rooms.c.is_shared)
 
         if source_kind:
@@ -418,6 +434,9 @@ class TranscriptController:
         if search_term:
             query = query.where(transcripts.c.title.ilike(f"%{search_term}%"))
 
+        if change_seq_from is not None:
+            query = query.where(transcripts.c.change_seq > change_seq_from)
+
         # Exclude heavy JSON columns from list queries
         transcript_columns = [
             col for col in transcripts.c if col.name not in exclude_columns
@@ -431,9 +450,10 @@ class TranscriptController:
         )
 
         if order_by is not None:
-            field = getattr(transcripts.c, order_by[1:])
             if order_by.startswith("-"):
-                field = field.desc()
+                field = getattr(transcripts.c, order_by[1:]).desc()
+            else:
+                field = getattr(transcripts.c, order_by)
             query = query.order_by(field)
 
         if filter_empty:
@@ -688,7 +708,7 @@ class TranscriptController:
     async def append_event(
         self,
         transcript: Transcript,
-        event: str,
+        event: "TranscriptEventName",
         data: Any,
     ) -> TranscriptEvent:
         """

server/reflector/db/users.py

@@ -1,4 +1,4 @@
-"""User table for storing Authentik user information."""
+"""User table for storing user information."""
 
 from datetime import datetime, timezone
 
@@ -15,6 +15,7 @@ users = sqlalchemy.Table(
     sqlalchemy.Column("id", sqlalchemy.String, primary_key=True),
     sqlalchemy.Column("email", sqlalchemy.String, nullable=False),
     sqlalchemy.Column("authentik_uid", sqlalchemy.String, nullable=False),
+    sqlalchemy.Column("password_hash", sqlalchemy.String, nullable=True),
     sqlalchemy.Column("created_at", sqlalchemy.DateTime(timezone=True), nullable=False),
     sqlalchemy.Column("updated_at", sqlalchemy.DateTime(timezone=True), nullable=False),
     sqlalchemy.Index("idx_user_authentik_uid", "authentik_uid", unique=True),
@@ -26,6 +27,7 @@ class User(BaseModel):
     id: NonEmptyString = Field(default_factory=generate_uuid4)
     email: NonEmptyString
     authentik_uid: NonEmptyString
+    password_hash: str | None = None
     created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
     updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
 
@@ -51,22 +53,29 @@ class UserController:
 
     @staticmethod
     async def create_or_update(
-        id: NonEmptyString, authentik_uid: NonEmptyString, email: NonEmptyString
+        id: NonEmptyString,
+        authentik_uid: NonEmptyString,
+        email: NonEmptyString,
+        password_hash: str | None = None,
     ) -> User:
         existing = await UserController.get_by_authentik_uid(authentik_uid)
         now = datetime.now(timezone.utc)
 
         if existing:
+            update_values: dict = {"email": email, "updated_at": now}
+            if password_hash is not None:
+                update_values["password_hash"] = password_hash
             query = (
                 users.update()
                 .where(users.c.authentik_uid == authentik_uid)
-                .values(email=email, updated_at=now)
+                .values(**update_values)
             )
             await get_database().execute(query)
             return User(
                 id=existing.id,
                 authentik_uid=authentik_uid,
                 email=email,
+                password_hash=password_hash or existing.password_hash,
                 created_at=existing.created_at,
                 updated_at=now,
             )
@@ -75,6 +84,7 @@ class UserController:
                 id=id,
                 authentik_uid=authentik_uid,
                 email=email,
+                password_hash=password_hash,
                 created_at=now,
                 updated_at=now,
             )
@@ -82,6 +92,16 @@ class UserController:
             await get_database().execute(query)
             return user
 
+    @staticmethod
+    async def set_password_hash(user_id: NonEmptyString, password_hash: str) -> None:
+        now = datetime.now(timezone.utc)
+        query = (
+            users.update()
+            .where(users.c.id == user_id)
+            .values(password_hash=password_hash, updated_at=now)
+        )
+        await get_database().execute(query)
+
     @staticmethod
     async def list_all() -> list[User]:
         query = users.select().order_by(users.c.created_at.desc())

server/reflector/hatchet/broadcast.py

@@ -12,10 +12,11 @@ import structlog
 
 from reflector.db.transcripts import Transcript, TranscriptEvent, transcripts_controller
 from reflector.utils.string import NonEmptyString
+from reflector.ws_events import TranscriptEventName
 from reflector.ws_manager import get_ws_manager
 
 # Events that should also be sent to user room (matches Celery behavior)
-USER_ROOM_EVENTS = {"STATUS", "FINAL_TITLE", "DURATION"}
+USER_ROOM_EVENTS: set[TranscriptEventName] = {"STATUS", "FINAL_TITLE", "DURATION"}
 
 
 async def broadcast_event(
@@ -81,8 +82,7 @@ async def set_status_and_broadcast(
 async def append_event_and_broadcast(
     transcript_id: NonEmptyString,
     transcript: Transcript,
-    event_name: NonEmptyString,
-    # TODO proper dictionary event => type
+    event_name: TranscriptEventName,
     data: Any,
     logger: structlog.BoundLogger,
 ) -> TranscriptEvent:

server/reflector/hatchet/client.py

@@ -12,7 +12,9 @@ import threading
 
 from hatchet_sdk import ClientConfig, Hatchet
 from hatchet_sdk.clients.rest.models import V1TaskStatus
+from hatchet_sdk.rate_limit import RateLimitDuration
 
+from reflector.hatchet.constants import LLM_RATE_LIMIT_KEY, LLM_RATE_LIMIT_PER_SECOND
 from reflector.logger import logger
 from reflector.settings import settings
 
@@ -113,3 +115,26 @@ class HatchetClientManager:
         """Reset the client instance (for testing)."""
         with cls._lock:
             cls._instance = None
+
+    @classmethod
+    async def ensure_rate_limit(cls) -> None:
+        """Ensure the LLM rate limit exists in Hatchet.
+
+        Uses the Hatchet SDK rate_limits client (aio_put). See:
+        https://docs.hatchet.run/sdks/python/feature-clients/rate_limits
+        """
+        logger.info(
+            "[Hatchet] Ensuring rate limit exists",
+            rate_limit_key=LLM_RATE_LIMIT_KEY,
+            limit=LLM_RATE_LIMIT_PER_SECOND,
+        )
+        client = cls.get_client()
+        await client.rate_limits.aio_put(
+            key=LLM_RATE_LIMIT_KEY,
+            limit=LLM_RATE_LIMIT_PER_SECOND,
+            duration=RateLimitDuration.SECOND,
+        )
+        logger.info(
+            "[Hatchet] Rate limit put successfully",
+            rate_limit_key=LLM_RATE_LIMIT_KEY,
+        )

server/reflector/hatchet/run_workers_llm.py

@@ -3,6 +3,8 @@ LLM/I/O worker pool for all non-CPU tasks.
 Handles: all tasks except mixdown_tracks (transcription, LLM inference, orchestration)
 """
 
+import asyncio
+
 from reflector.hatchet.client import HatchetClientManager
 from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     daily_multitrack_pipeline,
@@ -20,6 +22,15 @@ POOL = "llm-io"
 def main():
     hatchet = HatchetClientManager.get_client()
 
+    try:
+        asyncio.run(HatchetClientManager.ensure_rate_limit())
+    except Exception as e:
+        logger.warning(
+            "[Hatchet] Rate limit initialization failed, but continuing. "
+            "If workflows fail to register, rate limits may need to be created manually.",
+            error=str(e),
+        )
+
     logger.info(
         "Starting Hatchet LLM worker pool (all tasks except mixdown)",
         worker_name=WORKER_NAME,

server/reflector/hatchet/workflows/daily_multitrack_pipeline.py

@@ -171,11 +171,13 @@ async def set_workflow_error_status(transcript_id: NonEmptyString) -> bool:
 
 def _spawn_storage():
     """Create fresh storage instance."""
+    # TODO: replace direct AwsStorage construction with get_transcripts_storage() factory
     return 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,
+        aws_endpoint_url=settings.TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL,
     )
 
 

server/reflector/hatchet/workflows/padding_workflow.py

@@ -49,11 +49,13 @@ async def pad_track(input: PaddingInput, ctx: Context) -> PadTrackResult:
         from reflector.settings import settings  # noqa: PLC0415
         from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
 
+        # TODO: replace direct AwsStorage construction with get_transcripts_storage() factory
         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,
+            aws_endpoint_url=settings.TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL,
         )
 
         source_url = await storage.get_file_url(

server/reflector/hatchet/workflows/topic_chunk_processing.py

@@ -71,7 +71,7 @@ async def detect_chunk_topic(input: TopicChunkInput, ctx: Context) -> TopicChunk
     from reflector.settings import settings  # noqa: PLC0415
     from reflector.utils.text import clean_title  # noqa: PLC0415
 
-    llm = LLM(settings=settings, temperature=0.9, max_tokens=500)
+    llm = LLM(settings=settings, temperature=0.9)
 
     prompt = TOPIC_PROMPT.format(text=input.chunk_text)
     response = await llm.get_structured_response(

server/reflector/hatchet/workflows/track_processing.py

@@ -60,6 +60,7 @@ async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
 
     try:
         # Create fresh storage instance to avoid aioboto3 fork issues
+        # TODO: replace direct AwsStorage construction with get_transcripts_storage() factory
         from reflector.settings import settings  # noqa: PLC0415
         from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
 
@@ -68,6 +69,7 @@ async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
             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,
+            aws_endpoint_url=settings.TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL,
         )
 
         source_url = await storage.get_file_url(
@@ -159,6 +161,7 @@ async def transcribe_track(input: TrackInput, ctx: Context) -> TranscribeTrackRe
             raise ValueError("Missing padded_key from pad_track")
 
         # Presign URL on demand (avoids stale URLs on workflow replay)
+        # TODO: replace direct AwsStorage construction with get_transcripts_storage() factory
         from reflector.settings import settings  # noqa: PLC0415
         from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
 
@@ -167,6 +170,7 @@ async def transcribe_track(input: TrackInput, ctx: Context) -> TranscribeTrackRe
             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,
+            aws_endpoint_url=settings.TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL,
         )
 
         audio_url = await storage.get_file_url(

server/reflector/llm.py

@@ -144,7 +144,18 @@ class StructuredOutputWorkflow(Workflow, Generic[OutputT]):
         )
 
         # Network retries handled by OpenAILike (max_retries=3)
-        response = await Settings.llm.acomplete(json_prompt)
+        # response_format enables grammar-based constrained decoding on backends
+        # that support it (DMR/llama.cpp, vLLM, Ollama, OpenAI).
+        response = await Settings.llm.acomplete(
+            json_prompt,
+            response_format={
+                "type": "json_schema",
+                "json_schema": {
+                    "name": self.output_cls.__name__,
+                    "schema": self.output_cls.model_json_schema(),
+                },
+            },
+        )
         return ExtractionDone(output=response.text)
 
     @step
@@ -191,7 +202,9 @@ class StructuredOutputWorkflow(Workflow, Generic[OutputT]):
 
 
 class LLM:
-    def __init__(self, settings, temperature: float = 0.4, max_tokens: int = 2048):
+    def __init__(
+        self, settings, temperature: float = 0.4, max_tokens: int | None = None
+    ):
         self.settings_obj = settings
         self.model_name = settings.LLM_MODEL
         self.url = settings.LLM_URL
@@ -215,6 +228,7 @@ class LLM:
             is_function_calling_model=False,
             temperature=self.temperature,
             max_tokens=self.max_tokens,
+            timeout=self.settings_obj.LLM_REQUEST_TIMEOUT,
             additional_kwargs={"extra_body": {"litellm_session_id": session_id}},
         )
 

server/reflector/pipelines/main_live_pipeline.py

@@ -62,6 +62,8 @@ from reflector.processors.types import (
 from reflector.processors.types import Transcript as TranscriptProcessorType
 from reflector.settings import settings
 from reflector.storage import get_transcripts_storage
+from reflector.views.transcripts import GetTranscriptTopic
+from reflector.ws_events import TranscriptEventName
 from reflector.ws_manager import WebsocketManager, get_ws_manager
 from reflector.zulip import (
     get_zulip_message,
@@ -89,7 +91,11 @@ def broadcast_to_sockets(func):
         if transcript and transcript.user_id:
             # Emit only relevant events to the user room to avoid noisy updates.
             # Allowed: STATUS, FINAL_TITLE, DURATION. All are prefixed with TRANSCRIPT_
-            allowed_user_events = {"STATUS", "FINAL_TITLE", "DURATION"}
+            allowed_user_events: set[TranscriptEventName] = {
+                "STATUS",
+                "FINAL_TITLE",
+                "DURATION",
+            }
             if resp.event in allowed_user_events:
                 await self.ws_manager.send_json(
                     room_id=f"user:{transcript.user_id}",
@@ -244,13 +250,14 @@ class PipelineMainBase(PipelineRunner[PipelineMessage], Generic[PipelineMessage]
         )
         if isinstance(data, TitleSummaryWithIdProcessorType):
             topic.id = data.id
+        get_topic = GetTranscriptTopic.from_transcript_topic(topic)
         async with self.transaction():
             transcript = await self.get_transcript()
             await transcripts_controller.upsert_topic(transcript, topic)
             return await transcripts_controller.append_event(
                 transcript=transcript,
                 event="TOPIC",
-                data=topic,
+                data=get_topic,
             )
 
     @broadcast_to_sockets

server/reflector/processors/audio_diarization_pyannote.py

@@ -1,74 +0,0 @@
-import os
-
-import torch
-import torchaudio
-from pyannote.audio import Pipeline
-
-from reflector.processors.audio_diarization import AudioDiarizationProcessor
-from reflector.processors.audio_diarization_auto import AudioDiarizationAutoProcessor
-from reflector.processors.types import AudioDiarizationInput, DiarizationSegment
-
-
-class AudioDiarizationPyannoteProcessor(AudioDiarizationProcessor):
-    """Local diarization processor using pyannote.audio library"""
-
-    def __init__(
-        self,
-        model_name: str = "pyannote/speaker-diarization-3.1",
-        pyannote_auth_token: str | None = None,
-        device: str | None = None,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.model_name = model_name
-        self.auth_token = pyannote_auth_token or os.environ.get("HF_TOKEN")
-        self.device = device
-
-        if device is None:
-            self.device = "cuda" if torch.cuda.is_available() else "cpu"
-
-        self.logger.info(f"Loading pyannote diarization model: {self.model_name}")
-        self.diarization_pipeline = Pipeline.from_pretrained(
-            self.model_name, use_auth_token=self.auth_token
-        )
-        self.diarization_pipeline.to(torch.device(self.device))
-        self.logger.info(f"Diarization model loaded on device: {self.device}")
-
-    async def _diarize(self, data: AudioDiarizationInput) -> list[DiarizationSegment]:
-        try:
-            # Load audio file (audio_url is assumed to be a local file path)
-            self.logger.info(f"Loading local audio file: {data.audio_url}")
-            waveform, sample_rate = torchaudio.load(data.audio_url)
-            audio_input = {"waveform": waveform, "sample_rate": sample_rate}
-            self.logger.info("Running speaker diarization")
-            diarization = self.diarization_pipeline(audio_input)
-
-            # Convert pyannote diarization output to our format
-            segments = []
-            for segment, _, speaker in diarization.itertracks(yield_label=True):
-                # Extract speaker number from label (e.g., "SPEAKER_00" -> 0)
-                speaker_id = 0
-                if speaker.startswith("SPEAKER_"):
-                    try:
-                        speaker_id = int(speaker.split("_")[-1])
-                    except (ValueError, IndexError):
-                        # Fallback to hash-based ID if parsing fails
-                        speaker_id = hash(speaker) % 1000
-
-                segments.append(
-                    {
-                        "start": round(segment.start, 3),
-                        "end": round(segment.end, 3),
-                        "speaker": speaker_id,
-                    }
-                )
-
-            self.logger.info(f"Diarization completed with {len(segments)} segments")
-            return segments
-
-        except Exception as e:
-            self.logger.exception(f"Diarization failed: {e}")
-            raise
-
-
-AudioDiarizationAutoProcessor.register("pyannote", AudioDiarizationPyannoteProcessor)

server/reflector/processors/transcript_final_title.py

@@ -39,7 +39,7 @@ class TranscriptFinalTitleProcessor(Processor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
         self.chunks: list[TitleSummary] = []
-        self.llm = LLM(settings=settings, temperature=0.5, max_tokens=200)
+        self.llm = LLM(settings=settings, temperature=0.5)
 
     async def _push(self, data: TitleSummary):
         self.chunks.append(data)

server/reflector/processors/transcript_topic_detector.py

@@ -35,7 +35,7 @@ class TranscriptTopicDetectorProcessor(Processor):
         super().__init__(**kwargs)
         self.transcript = None
         self.min_transcript_length = min_transcript_length
-        self.llm = LLM(settings=settings, temperature=0.9, max_tokens=500)
+        self.llm = LLM(settings=settings, temperature=0.9)
 
     async def _push(self, data: Transcript):
         if self.transcript is None:

server/reflector/services/transcript_process.py

@@ -15,14 +15,10 @@ from hatchet_sdk.clients.rest.exceptions import ApiException, NotFoundException
 from hatchet_sdk.clients.rest.models import V1TaskStatus
 
 from reflector.db.recordings import recordings_controller
-from reflector.db.rooms import rooms_controller
 from reflector.db.transcripts import Transcript, transcripts_controller
 from reflector.hatchet.client import HatchetClientManager
 from reflector.logger import logger
 from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
-from reflector.pipelines.main_multitrack_pipeline import (
-    task_pipeline_multitrack_process,
-)
 from reflector.utils.string import NonEmptyString
 
 
@@ -101,8 +97,11 @@ async def validate_transcript_for_processing(
     if transcript.locked:
         return ValidationLocked(detail="Recording is locked")
 
-    # Check if recording is ready for processing
-    if transcript.status == "idle" and not transcript.workflow_run_id:
+    if (
+        transcript.status == "idle"
+        and not transcript.workflow_run_id
+        and not transcript.recording_id
+    ):
         return ValidationNotReady(detail="Recording is not ready for processing")
 
     # Check Celery tasks
@@ -181,124 +180,98 @@ async def dispatch_transcript_processing(
     Returns AsyncResult for Celery tasks, None for Hatchet workflows.
     """
     if isinstance(config, MultitrackProcessingConfig):
-        use_celery = False
-        if config.room_id:
-            room = await rooms_controller.get_by_id(config.room_id)
-            use_celery = room.use_celery if room else False
-
-        use_hatchet = not use_celery
-
-        if use_celery:
-            logger.info(
-                "Room uses legacy Celery processing",
-                room_id=config.room_id,
-                transcript_id=config.transcript_id,
+        # Multitrack processing always uses Hatchet (no Celery fallback)
+        # First check if we can replay (outside transaction since it's read-only)
+        transcript = await transcripts_controller.get_by_id(config.transcript_id)
+        if transcript and transcript.workflow_run_id and not force:
+            can_replay = await HatchetClientManager.can_replay(
+                transcript.workflow_run_id
             )
-
-        if use_hatchet:
-            # First check if we can replay (outside transaction since it's read-only)
-            transcript = await transcripts_controller.get_by_id(config.transcript_id)
-            if transcript and transcript.workflow_run_id and not force:
-                can_replay = await HatchetClientManager.can_replay(
-                    transcript.workflow_run_id
+            if can_replay:
+                await HatchetClientManager.replay_workflow(transcript.workflow_run_id)
+                logger.info(
+                    "Replaying Hatchet workflow",
+                    workflow_id=transcript.workflow_run_id,
                 )
-                if can_replay:
-                    await HatchetClientManager.replay_workflow(
-                        transcript.workflow_run_id
-                    )
-                    logger.info(
-                        "Replaying Hatchet workflow",
-                        workflow_id=transcript.workflow_run_id,
-                    )
-                    return None
-                else:
-                    # Workflow can't replay (CANCELLED, COMPLETED, or 404 deleted)
-                    # Log and proceed to start new workflow
-                    try:
-                        status = await HatchetClientManager.get_workflow_run_status(
-                            transcript.workflow_run_id
-                        )
-                        logger.info(
-                            "Old workflow not replayable, starting new",
-                            old_workflow_id=transcript.workflow_run_id,
-                            old_status=status.value,
-                        )
-                    except NotFoundException:
-                        # Workflow deleted from Hatchet but ID still in DB
-                        logger.info(
-                            "Old workflow not found in Hatchet, starting new",
-                            old_workflow_id=transcript.workflow_run_id,
-                        )
-
-            # Force: cancel old workflow if exists
-            if force and transcript and transcript.workflow_run_id:
-                try:
-                    await HatchetClientManager.cancel_workflow(
-                        transcript.workflow_run_id
-                    )
-                    logger.info(
-                        "Cancelled old workflow (--force)",
-                        workflow_id=transcript.workflow_run_id,
-                    )
-                except NotFoundException:
-                    logger.info(
-                        "Old workflow already deleted (--force)",
-                        workflow_id=transcript.workflow_run_id,
-                    )
-                await transcripts_controller.update(
-                    transcript, {"workflow_run_id": None}
-                )
-
-            # Re-fetch and check for concurrent dispatch (optimistic approach).
-            # No database lock - worst case is duplicate dispatch, but Hatchet
-            # workflows are idempotent so this is acceptable.
-            transcript = await transcripts_controller.get_by_id(config.transcript_id)
-            if transcript and transcript.workflow_run_id:
-                # Another process started a workflow between validation and now
+                return None
+            else:
+                # Workflow can't replay (CANCELLED, COMPLETED, or 404 deleted)
+                # Log and proceed to start new workflow
                 try:
                     status = await HatchetClientManager.get_workflow_run_status(
                         transcript.workflow_run_id
                     )
-                    if status in (V1TaskStatus.RUNNING, V1TaskStatus.QUEUED):
-                        logger.info(
-                            "Concurrent workflow detected, skipping dispatch",
-                            workflow_id=transcript.workflow_run_id,
-                        )
-                        return None
-                except ApiException:
-                    # Workflow might be gone (404) or API issue - proceed with new workflow
-                    pass
+                    logger.info(
+                        "Old workflow not replayable, starting new",
+                        old_workflow_id=transcript.workflow_run_id,
+                        old_status=status.value,
+                    )
+                except NotFoundException:
+                    # Workflow deleted from Hatchet but ID still in DB
+                    logger.info(
+                        "Old workflow not found in Hatchet, starting new",
+                        old_workflow_id=transcript.workflow_run_id,
+                    )
 
-            workflow_id = await HatchetClientManager.start_workflow(
-                workflow_name="DiarizationPipeline",
-                input_data={
-                    "recording_id": config.recording_id,
-                    "tracks": [{"s3_key": k} for k in config.track_keys],
-                    "bucket_name": config.bucket_name,
-                    "transcript_id": config.transcript_id,
-                    "room_id": config.room_id,
-                },
-                additional_metadata={
-                    "transcript_id": config.transcript_id,
-                    "recording_id": config.recording_id,
-                    "daily_recording_id": config.recording_id,
-                },
+        # Force: cancel old workflow if exists
+        if force and transcript and transcript.workflow_run_id:
+            try:
+                await HatchetClientManager.cancel_workflow(transcript.workflow_run_id)
+                logger.info(
+                    "Cancelled old workflow (--force)",
+                    workflow_id=transcript.workflow_run_id,
+                )
+            except NotFoundException:
+                logger.info(
+                    "Old workflow already deleted (--force)",
+                    workflow_id=transcript.workflow_run_id,
+                )
+            await transcripts_controller.update(transcript, {"workflow_run_id": None})
+
+        # Re-fetch and check for concurrent dispatch (optimistic approach).
+        # No database lock - worst case is duplicate dispatch, but Hatchet
+        # workflows are idempotent so this is acceptable.
+        transcript = await transcripts_controller.get_by_id(config.transcript_id)
+        if transcript and transcript.workflow_run_id:
+            # Another process started a workflow between validation and now
+            try:
+                status = await HatchetClientManager.get_workflow_run_status(
+                    transcript.workflow_run_id
+                )
+                if status in (V1TaskStatus.RUNNING, V1TaskStatus.QUEUED):
+                    logger.info(
+                        "Concurrent workflow detected, skipping dispatch",
+                        workflow_id=transcript.workflow_run_id,
+                    )
+                    return None
+            except ApiException:
+                # Workflow might be gone (404) or API issue - proceed with new workflow
+                pass
+
+        workflow_id = await HatchetClientManager.start_workflow(
+            workflow_name="DiarizationPipeline",
+            input_data={
+                "recording_id": config.recording_id,
+                "tracks": [{"s3_key": k} for k in config.track_keys],
+                "bucket_name": config.bucket_name,
+                "transcript_id": config.transcript_id,
+                "room_id": config.room_id,
+            },
+            additional_metadata={
+                "transcript_id": config.transcript_id,
+                "recording_id": config.recording_id,
+                "daily_recording_id": config.recording_id,
+            },
+        )
+
+        if transcript:
+            await transcripts_controller.update(
+                transcript, {"workflow_run_id": workflow_id}
             )
 
-            if transcript:
-                await transcripts_controller.update(
-                    transcript, {"workflow_run_id": workflow_id}
-                )
+        logger.info("Hatchet workflow dispatched", workflow_id=workflow_id)
+        return None
 
-            logger.info("Hatchet workflow dispatched", workflow_id=workflow_id)
-            return None
-
-        # Celery pipeline (durable workflows disabled)
-        return task_pipeline_multitrack_process.delay(
-            transcript_id=config.transcript_id,
-            bucket_name=config.bucket_name,
-            track_keys=config.track_keys,
-        )
     elif isinstance(config, FileProcessingConfig):
         return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
     else:

server/reflector/settings.py

@@ -1,7 +1,7 @@
 from pydantic.types import PositiveInt
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
-from reflector.schemas.platform import WHEREBY_PLATFORM, Platform
+from reflector.schemas.platform import DAILY_PLATFORM, Platform
 from reflector.utils.string import NonEmptyString
 
 
@@ -12,6 +12,17 @@ class Settings(BaseSettings):
         extra="ignore",
     )
 
+    ROOT_PATH: str = "/"
+
+    # WebRTC port range for ICE candidates (e.g. "50000-50100").
+    # When set, monkey-patches aioice to bind UDP sockets within this range,
+    # allowing Docker port mapping instead of network_mode: host.
+    WEBRTC_PORT_RANGE: str | None = None
+    # Host IP or hostname to advertise in ICE candidates instead of the
+    # container's internal IP. Use "host.docker.internal" in Docker with
+    # extra_hosts, or a specific LAN IP. Resolved at connection time.
+    WEBRTC_HOST: str | None = None
+
     # CORS
     UI_BASE_URL: str = "http://localhost:3000"
     CORS_ORIGIN: str = "*"
@@ -49,6 +60,7 @@ class Settings(BaseSettings):
     TRANSCRIPT_STORAGE_AWS_REGION: str = "us-east-1"
     TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID: str | None = None
     TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY: str | None = None
+    TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL: str | None = None
 
     # Platform-specific recording storage (follows {PREFIX}_STORAGE_AWS_{CREDENTIAL} pattern)
     # Whereby storage configuration
@@ -75,6 +87,7 @@ class Settings(BaseSettings):
     LLM_URL: str | None = None
     LLM_API_KEY: str | None = None
     LLM_CONTEXT_WINDOW: int = 16000
+    LLM_REQUEST_TIMEOUT: float = 300.0  # HTTP request timeout for LLM calls (seconds)
 
     LLM_PARSE_MAX_RETRIES: int = (
         3  # Max retries for JSON/validation errors (total attempts = retries + 1)
@@ -84,9 +97,7 @@ class Settings(BaseSettings):
     )
 
     # Diarization
-    # backends:
-    #   - pyannote: in-process model loading (no HTTP, runs in same process)
-    #   - modal: HTTP API client (works with Modal.com OR self-hosted gpu/self_hosted/)
+    # backend: modal — HTTP API client (works with Modal.com OR self-hosted gpu/self_hosted/)
     DIARIZATION_ENABLED: bool = True
     DIARIZATION_BACKEND: str = "modal"
     DIARIZATION_URL: str | None = None
@@ -95,9 +106,6 @@ class Settings(BaseSettings):
     # Diarization: modal backend
     DIARIZATION_MODAL_API_KEY: str | None = None
 
-    # 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
@@ -105,7 +113,7 @@ class Settings(BaseSettings):
     # Sentry
     SENTRY_DSN: str | None = None
 
-    # User authentication (none, jwt)
+    # User authentication (none, jwt, password)
     AUTH_BACKEND: str = "none"
 
     # User authentication using JWT
@@ -113,6 +121,10 @@ class Settings(BaseSettings):
     AUTH_JWT_PUBLIC_KEY: str | None = "authentik.monadical.com_public.pem"
     AUTH_JWT_AUDIENCE: str | None = None
 
+    # User authentication using password (selfhosted)
+    ADMIN_EMAIL: str | None = None
+    ADMIN_PASSWORD_HASH: str | None = None
+
     PUBLIC_MODE: bool = False
     PUBLIC_DATA_RETENTION_DAYS: PositiveInt = 7
 
@@ -146,6 +158,9 @@ class Settings(BaseSettings):
     WHEREBY_WEBHOOK_SECRET: str | None = None
     AWS_PROCESS_RECORDING_QUEUE_URL: str | None = None
     SQS_POLLING_TIMEOUT_SECONDS: int = 60
+    CELERY_BEAT_POLL_INTERVAL: int = (
+        0  # 0 = use individual defaults; set e.g. 300 for 5-min polling
+    )
 
     # Daily.co integration
     DAILY_API_KEY: str | None = None
@@ -155,7 +170,7 @@ class Settings(BaseSettings):
         None  # Webhook UUID for this environment. Not used by production code
     )
     # Platform Configuration
-    DEFAULT_VIDEO_PLATFORM: Platform = WHEREBY_PLATFORM
+    DEFAULT_VIDEO_PLATFORM: Platform = DAILY_PLATFORM
 
     # Zulip integration
     ZULIP_REALM: str | None = None

server/reflector/storage/storage_aws.py

@@ -53,6 +53,7 @@ class AwsStorage(Storage):
         aws_access_key_id: str | None = None,
         aws_secret_access_key: str | None = None,
         aws_role_arn: str | None = None,
+        aws_endpoint_url: str | None = None,
     ):
         if not aws_bucket_name:
             raise ValueError("Storage `aws_storage` require `aws_bucket_name`")
@@ -73,17 +74,26 @@ class AwsStorage(Storage):
         self._access_key_id = aws_access_key_id
         self._secret_access_key = aws_secret_access_key
         self._role_arn = aws_role_arn
+        self._endpoint_url = aws_endpoint_url
 
         self.aws_folder = ""
         if "/" in aws_bucket_name:
             self._bucket_name, self.aws_folder = aws_bucket_name.split("/", 1)
-        self.boto_config = Config(retries={"max_attempts": 3, "mode": "adaptive"})
+
+        config_kwargs: dict = {"retries": {"max_attempts": 3, "mode": "adaptive"}}
+        if aws_endpoint_url:
+            config_kwargs["s3"] = {"addressing_style": "path"}
+        self.boto_config = Config(**config_kwargs)
+
         self.session = aioboto3.Session(
             aws_access_key_id=aws_access_key_id,
             aws_secret_access_key=aws_secret_access_key,
             region_name=aws_region,
         )
-        self.base_url = f"https://{self._bucket_name}.s3.amazonaws.com/"
+        if aws_endpoint_url:
+            self.base_url = f"{aws_endpoint_url}/{self._bucket_name}/"
+        else:
+            self.base_url = f"https://{self._bucket_name}.s3.amazonaws.com/"
 
     # Implement credential properties
     @property
@@ -139,7 +149,9 @@ class AwsStorage(Storage):
         s3filename = f"{folder}/{filename}" if folder else filename
         logger.info(f"Uploading {filename} to S3 {actual_bucket}/{folder}")
 
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             if isinstance(data, bytes):
                 await client.put_object(Bucket=actual_bucket, Key=s3filename, Body=data)
             else:
@@ -162,7 +174,9 @@ class AwsStorage(Storage):
         actual_bucket = bucket or self._bucket_name
         folder = self.aws_folder
         s3filename = f"{folder}/{filename}" if folder else filename
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             presigned_url = await client.generate_presigned_url(
                 operation,
                 Params={"Bucket": actual_bucket, "Key": s3filename},
@@ -177,7 +191,9 @@ class AwsStorage(Storage):
         folder = self.aws_folder
         logger.info(f"Deleting {filename} from S3 {actual_bucket}/{folder}")
         s3filename = f"{folder}/{filename}" if folder else filename
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             await client.delete_object(Bucket=actual_bucket, Key=s3filename)
 
     @handle_s3_client_errors("download")
@@ -186,7 +202,9 @@ class AwsStorage(Storage):
         folder = self.aws_folder
         logger.info(f"Downloading {filename} from S3 {actual_bucket}/{folder}")
         s3filename = f"{folder}/{filename}" if folder else filename
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             response = await client.get_object(Bucket=actual_bucket, Key=s3filename)
             return await response["Body"].read()
 
@@ -201,7 +219,9 @@ class AwsStorage(Storage):
         logger.info(f"Listing objects from S3 {actual_bucket} with prefix '{s3prefix}'")
 
         keys = []
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             paginator = client.get_paginator("list_objects_v2")
             async for page in paginator.paginate(Bucket=actual_bucket, Prefix=s3prefix):
                 if "Contents" in page:
@@ -227,7 +247,9 @@ class AwsStorage(Storage):
         folder = self.aws_folder
         logger.info(f"Streaming {filename} from S3 {actual_bucket}/{folder}")
         s3filename = f"{folder}/{filename}" if folder else filename
-        async with self.session.client("s3", config=self.boto_config) as client:
+        async with self.session.client(
+            "s3", config=self.boto_config, endpoint_url=self._endpoint_url
+        ) as client:
             await client.download_fileobj(
                 Bucket=actual_bucket, Key=s3filename, Fileobj=fileobj
             )

server/reflector/tools/create_admin.py

@@ -0,0 +1,80 @@
+"""Create or update an admin user with password authentication.
+
+Usage:
+    uv run python -m reflector.tools.create_admin --email admin@localhost --password <pass>
+    uv run python -m reflector.tools.create_admin --email admin@localhost  # prompts for password
+    uv run python -m reflector.tools.create_admin --hash-only --password <pass>  # print hash only
+"""
+
+import argparse
+import asyncio
+import getpass
+import sys
+
+from reflector.auth.password_utils import hash_password
+from reflector.db.users import user_controller
+from reflector.utils import generate_uuid4
+
+
+async def create_admin(email: str, password: str) -> None:
+    from reflector.db import get_database
+
+    database = get_database()
+    await database.connect()
+
+    try:
+        password_hash = hash_password(password)
+
+        existing = await user_controller.get_by_email(email)
+        if existing:
+            await user_controller.set_password_hash(existing.id, password_hash)
+            print(f"Updated password for existing user: {email} (id={existing.id})")
+        else:
+            user = await user_controller.create_or_update(
+                id=generate_uuid4(),
+                authentik_uid=f"local:{email}",
+                email=email,
+                password_hash=password_hash,
+            )
+            print(f"Created admin user: {email} (id={user.id})")
+    finally:
+        await database.disconnect()
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Create or update an admin user")
+    parser.add_argument(
+        "--email", default="admin@localhost", help="Admin email address"
+    )
+    parser.add_argument(
+        "--password",
+        help="Admin password (will prompt if not provided)",
+    )
+    parser.add_argument(
+        "--hash-only",
+        action="store_true",
+        help="Print the password hash and exit (for ADMIN_PASSWORD_HASH env var)",
+    )
+    args = parser.parse_args()
+
+    password = args.password
+    if not password:
+        password = getpass.getpass("Password: ")
+        confirm = getpass.getpass("Confirm password: ")
+        if password != confirm:
+            print("Passwords do not match", file=sys.stderr)
+            sys.exit(1)
+
+    if not password:
+        print("Password cannot be empty", file=sys.stderr)
+        sys.exit(1)
+
+    if args.hash_only:
+        print(hash_password(password))
+        sys.exit(0)
+
+    asyncio.run(create_admin(args.email, password))
+
+
+if __name__ == "__main__":
+    main()

server/reflector/tools/process.py

@@ -24,6 +24,9 @@ from reflector.pipelines.main_live_pipeline import (
     pipeline_process as live_pipeline_process,
 )
 from reflector.storage import Storage
+from reflector.worker.app import (
+    app as celery_app,  # noqa: F401 - ensure Celery uses Redis broker
+)
 
 
 def validate_s3_bucket_name(bucket: str) -> None:

server/reflector/tools/provision_admin.py

@@ -0,0 +1,43 @@
+"""Provision admin user on server startup using environment variables.
+
+Reads ADMIN_EMAIL and ADMIN_PASSWORD_HASH from settings and creates or updates
+the admin user. Intended to be called from runserver.sh on container startup.
+"""
+
+import asyncio
+
+from reflector.db.users import user_controller
+from reflector.settings import settings
+from reflector.utils import generate_uuid4
+
+
+async def provision() -> None:
+    if not settings.ADMIN_EMAIL or not settings.ADMIN_PASSWORD_HASH:
+        return
+
+    from reflector.db import get_database
+
+    database = get_database()
+    await database.connect()
+
+    try:
+        existing = await user_controller.get_by_email(settings.ADMIN_EMAIL)
+        if existing:
+            await user_controller.set_password_hash(
+                existing.id, settings.ADMIN_PASSWORD_HASH
+            )
+            print(f"Updated admin user: {settings.ADMIN_EMAIL}")
+        else:
+            await user_controller.create_or_update(
+                id=generate_uuid4(),
+                authentik_uid=f"local:{settings.ADMIN_EMAIL}",
+                email=settings.ADMIN_EMAIL,
+                password_hash=settings.ADMIN_PASSWORD_HASH,
+            )
+            print(f"Created admin user: {settings.ADMIN_EMAIL}")
+    finally:
+        await database.disconnect()
+
+
+if __name__ == "__main__":
+    asyncio.run(provision())

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
@@ -85,7 +80,14 @@ async def webhook(request: Request):
     try:
         event = event_adapter.validate_python(body_json)
     except Exception as e:
-        logger.error("Failed to parse webhook event", error=str(e), body=body.decode())
+        err_detail = str(e)
+        if hasattr(e, "errors"):
+            err_detail = f"{err_detail}; errors={e.errors()!r}"
+        logger.error(
+            "Failed to parse webhook event",
+            error=err_detail,
+            body=body.decode(),
+        )
         raise HTTPException(status_code=422, detail="Invalid event format")
 
     match event:
@@ -217,73 +219,10 @@ 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(
-            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}
+        return {"status": "ok", "result": result}
 
     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(
-                    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,
-                    },
+                log.info(
+                    f"{body.type} recording already active (started by another participant)"
                 )
                 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(
-            f"Failed to start {body.type} recording",
-            extra={
-                "meeting_id": meeting_id,
-                "recording_type": body.type,
-                "error": str(e),
-            },
-        )
+        log.error(f"Failed to start {body.type} recording", 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(
-            f"Failed to start {body.type} recording",
-            extra={
-                "meeting_id": meeting_id,
-                "recording_type": body.type,
-                "error": str(e),
-            },
-        )
+        log.error(f"Failed to start {body.type} recording", error=str(e))
         raise HTTPException(
             status_code=500, detail=f"Failed to start recording: {str(e)}"
         )

server/reflector/views/rtc_offer.py

@@ -10,6 +10,7 @@ from pydantic import BaseModel
 from reflector.events import subscribers_shutdown
 from reflector.logger import logger
 from reflector.pipelines.runner import PipelineRunner
+from reflector.settings import settings
 
 sessions = []
 router = APIRouter()
@@ -123,7 +124,16 @@ async def rtc_offer_base(
     # update metrics
     m_rtc_sessions.inc()
 
-    return RtcOffer(sdp=pc.localDescription.sdp, type=pc.localDescription.type)
+    sdp = pc.localDescription.sdp
+
+    # Rewrite ICE candidate IPs when running behind Docker bridge networking
+    if settings.WEBRTC_HOST:
+        from reflector.webrtc_ports import resolve_webrtc_host, rewrite_sdp_host
+
+        host_ip = resolve_webrtc_host(settings.WEBRTC_HOST)
+        sdp = rewrite_sdp_host(sdp, host_ip)
+
+    return RtcOffer(sdp=sdp, type=pc.localDescription.type)
 
 
 @subscribers_shutdown.append

server/reflector/views/transcripts.py

@@ -111,6 +111,7 @@ class GetTranscriptMinimal(BaseModel):
     room_id: str | None = None
     room_name: str | None = None
     audio_deleted: bool | None = None
+    change_seq: int | None = None
 
 
 class TranscriptParticipantWithEmail(TranscriptParticipant):
@@ -266,12 +267,22 @@ async def transcripts_list(
     source_kind: SourceKind | None = None,
     room_id: str | None = None,
     search_term: str | None = None,
+    change_seq_from: int | None = None,
+    sort_by: Literal["created_at", "change_seq"] | None = None,
 ):
     if not user and not settings.PUBLIC_MODE:
         raise HTTPException(status_code=401, detail="Not authenticated")
 
     user_id = user["sub"] if user else None
 
+    # Default behavior preserved: sort_by=None → "-created_at"
+    if sort_by == "change_seq":
+        order_by = "change_seq"  # ASC (ascending for checkpoint-based polling)
+    elif sort_by == "created_at":
+        order_by = "-created_at"  # DESC (newest first, same as current default)
+    else:
+        order_by = "-created_at"  # default, backward compatible
+
     return await apaginate(
         get_database(),
         await transcripts_controller.get_all(
@@ -279,7 +290,8 @@ async def transcripts_list(
             source_kind=SourceKind(source_kind) if source_kind else None,
             room_id=room_id,
             search_term=search_term,
-            order_by="-created_at",
+            order_by=order_by,
+            change_seq_from=change_seq_from,
             return_query=True,
         ),
     )
@@ -512,6 +524,7 @@ async def transcript_get(
         "room_id": transcript.room_id,
         "room_name": room_name,
         "audio_deleted": transcript.audio_deleted,
+        "change_seq": transcript.change_seq,
         "participants": participants,
     }
 

server/reflector/views/transcripts_upload.py

@@ -5,7 +5,7 @@ from fastapi import APIRouter, Depends, HTTPException, UploadFile
 from pydantic import BaseModel
 
 import reflector.auth as auth
-from reflector.db.transcripts import transcripts_controller
+from reflector.db.transcripts import SourceKind, transcripts_controller
 from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 
 router = APIRouter()
@@ -88,8 +88,10 @@ async def transcript_record_upload(
     finally:
         container.close()
 
-    # set the status to "uploaded"
-    await transcripts_controller.update(transcript, {"status": "uploaded"})
+    # set the status to "uploaded" and mark as file source
+    await transcripts_controller.update(
+        transcript, {"status": "uploaded", "source_kind": SourceKind.FILE}
+    )
 
     # launch a background task to process the file
     task_pipeline_file_process.delay(transcript_id=transcript_id)

server/reflector/views/transcripts_websocket.py

@@ -4,18 +4,22 @@ Transcripts websocket API
 
 """
 
-from typing import Optional
-
-from fastapi import APIRouter, Depends, HTTPException, WebSocket, WebSocketDisconnect
+from fastapi import APIRouter, HTTPException, WebSocket, WebSocketDisconnect
 
 import reflector.auth as auth
 from reflector.db.transcripts import transcripts_controller
+from reflector.ws_events import TranscriptWsEvent
 from reflector.ws_manager import get_ws_manager
 
 router = APIRouter()
 
 
-@router.get("/transcripts/{transcript_id}/events")
+@router.get(
+    "/transcripts/{transcript_id}/events",
+    response_model=TranscriptWsEvent,
+    summary="Transcript WebSocket event schema",
+    description="Stub exposing the discriminated union of all transcript-level WS events for OpenAPI type generation. Real events are delivered over the WebSocket at the same path.",
+)
 async def transcript_get_websocket_events(transcript_id: str):
     pass
 
@@ -24,8 +28,9 @@ async def transcript_get_websocket_events(transcript_id: str):
 async def transcript_events_websocket(
     transcript_id: str,
     websocket: WebSocket,
-    user: Optional[auth.UserInfo] = Depends(auth.current_user_optional),
 ):
+    _, negotiated_subprotocol = auth.parse_ws_bearer_token(websocket)
+    user = await auth.current_user_ws_optional(websocket)
     user_id = user["sub"] if user else None
     transcript = await transcripts_controller.get_by_id_for_http(
         transcript_id, user_id=user_id
@@ -37,7 +42,9 @@ async def transcript_events_websocket(
     # use ts:transcript_id as room id
     room_id = f"ts:{transcript_id}"
     ws_manager = get_ws_manager()
-    await ws_manager.add_user_to_room(room_id, websocket)
+    await ws_manager.add_user_to_room(
+        room_id, websocket, subprotocol=negotiated_subprotocol
+    )
 
     try:
         # on first connection, send all events only to the current user

server/reflector/views/user_websocket.py

@@ -1,55 +1,48 @@
 from typing import Optional
 
-from fastapi import APIRouter, WebSocket
+from fastapi import APIRouter, WebSocket, WebSocketDisconnect
 
-from reflector.auth.auth_jwt import JWTAuth  # type: ignore
-from reflector.db.users import user_controller
+import reflector.auth as auth
+from reflector.ws_events import UserWsEvent
 from reflector.ws_manager import get_ws_manager
 
 router = APIRouter()
 
+
+@router.get(
+    "/events",
+    response_model=UserWsEvent,
+    summary="User WebSocket event schema",
+    description="Stub exposing the discriminated union of all user-level WS events for OpenAPI type generation. Real events are delivered over the WebSocket at the same path.",
+)
+async def user_get_websocket_events():
+    pass
+
+
 # Close code for unauthorized WebSocket connections
 UNAUTHORISED = 4401
 
 
 @router.websocket("/events")
 async def user_events_websocket(websocket: WebSocket):
-    # Browser can't send Authorization header for WS; use subprotocol: ["bearer", token]
-    raw_subprotocol = websocket.headers.get("sec-websocket-protocol") or ""
-    parts = [p.strip() for p in raw_subprotocol.split(",") if p.strip()]
-    token: Optional[str] = None
-    negotiated_subprotocol: Optional[str] = None
-    if len(parts) >= 2 and parts[0].lower() == "bearer":
-        negotiated_subprotocol = "bearer"
-        token = parts[1]
+    token, negotiated_subprotocol = auth.parse_ws_bearer_token(websocket)
 
-    user_id: Optional[str] = None
     if not token:
         await websocket.close(code=UNAUTHORISED)
         return
 
     try:
-        payload = JWTAuth().verify_token(token)
-        authentik_uid = payload.get("sub")
-
-        if authentik_uid:
-            user = await user_controller.get_by_authentik_uid(authentik_uid)
-            if user:
-                user_id = user.id
-            else:
-                await websocket.close(code=UNAUTHORISED)
-                return
-        else:
-            await websocket.close(code=UNAUTHORISED)
-            return
+        user = await auth.current_user_ws_optional(websocket)
     except Exception:
         await websocket.close(code=UNAUTHORISED)
         return
 
-    if not user_id:
+    if not user:
         await websocket.close(code=UNAUTHORISED)
         return
 
+    user_id: Optional[str] = user.sub if hasattr(user, "sub") else user["sub"]
+
     room_id = f"user:{user_id}"
     ws_manager = get_ws_manager()
 
@@ -60,6 +53,8 @@ async def user_events_websocket(websocket: WebSocket):
     try:
         while True:
             await websocket.receive()
+    except (RuntimeError, WebSocketDisconnect):
+        pass
     finally:
         if room_id:
             await ws_manager.remove_user_from_room(room_id, websocket)

server/reflector/webrtc_ports.py

@@ -0,0 +1,111 @@
+"""
+Monkey-patch aioice to use a fixed UDP port range for ICE candidates,
+and optionally rewrite SDP to advertise a different host IP.
+
+This allows running the server in Docker with bridge networking
+(no network_mode: host) by:
+  1. Restricting ICE UDP ports to a known range that can be mapped in Docker
+  2. Replacing container-internal IPs with the Docker host IP in SDP answers
+"""
+
+import asyncio
+import socket
+
+from reflector.logger import logger
+
+
+def parse_port_range(range_str: str) -> tuple[int, int]:
+    """Parse a 'min-max' string into (min_port, max_port)."""
+    parts = range_str.split("-")
+    if len(parts) != 2:
+        raise ValueError(f"WEBRTC_PORT_RANGE must be 'min-max', got: {range_str!r}")
+    min_port, max_port = int(parts[0]), int(parts[1])
+    if not (1024 <= min_port <= max_port <= 65535):
+        raise ValueError(
+            f"Invalid port range: {min_port}-{max_port} "
+            "(must be 1024-65535 with min <= max)"
+        )
+    return min_port, max_port
+
+
+def patch_aioice_port_range(min_port: int, max_port: int) -> None:
+    """
+    Monkey-patch aioice so that ICE candidate UDP sockets bind to ports
+    within [min_port, max_port] instead of OS-assigned ephemeral ports.
+
+    Works by temporarily wrapping loop.create_datagram_endpoint() during
+    aioice's get_component_candidates() to intercept bind(addr, 0) calls.
+    """
+    import aioice.ice as _ice
+
+    _original = _ice.Connection.get_component_candidates
+    _state = {"next_port": min_port}
+
+    async def _patched_get_component_candidates(self, component, addresses, timeout=5):
+        loop = asyncio.get_event_loop()
+        _orig_create = loop.create_datagram_endpoint
+
+        async def _create_with_port_range(*args, **kwargs):
+            local_addr = kwargs.get("local_addr")
+            if local_addr and local_addr[1] == 0:
+                addr = local_addr[0]
+                # Try each port in the range (wrapping around)
+                attempts = max_port - min_port + 1
+                for _ in range(attempts):
+                    port = _state["next_port"]
+                    _state["next_port"] = (
+                        min_port
+                        if _state["next_port"] >= max_port
+                        else _state["next_port"] + 1
+                    )
+                    try:
+                        kwargs["local_addr"] = (addr, port)
+                        return await _orig_create(*args, **kwargs)
+                    except OSError:
+                        continue
+                # All ports exhausted, fall back to OS assignment
+                logger.warning(
+                    "All WebRTC ports in range exhausted, falling back to OS",
+                    min_port=min_port,
+                    max_port=max_port,
+                )
+                kwargs["local_addr"] = (addr, 0)
+            return await _orig_create(*args, **kwargs)
+
+        loop.create_datagram_endpoint = _create_with_port_range
+        try:
+            return await _original(self, component, addresses, timeout)
+        finally:
+            loop.create_datagram_endpoint = _orig_create
+
+    _ice.Connection.get_component_candidates = _patched_get_component_candidates
+    logger.info(
+        "aioice patched for WebRTC port range",
+        min_port=min_port,
+        max_port=max_port,
+    )
+
+
+def resolve_webrtc_host(host: str) -> str:
+    """Resolve a hostname or IP to an IP address for ICE candidate rewriting."""
+    try:
+        ip = socket.gethostbyname(host)
+        logger.info("Resolved WEBRTC_HOST", host=host, ip=ip)
+        return ip
+    except socket.gaierror:
+        logger.warning("Could not resolve WEBRTC_HOST, using as-is", host=host)
+        return host
+
+
+def rewrite_sdp_host(sdp: str, target_ip: str) -> str:
+    """
+    Replace container-internal IPs in SDP with target_ip so that
+    ICE candidates advertise a routable address.
+    """
+    import aioice.ice
+
+    container_ips = aioice.ice.get_host_addresses(use_ipv4=True, use_ipv6=False)
+    for ip in container_ips:
+        if ip != "127.0.0.1" and ip != target_ip:
+            sdp = sdp.replace(ip, target_ip)
+    return sdp

server/reflector/worker/app.py

@@ -8,8 +8,21 @@ from reflector.settings import settings
 logger = structlog.get_logger(__name__)
 
 # Polling intervals (seconds)
+# CELERY_BEAT_POLL_INTERVAL overrides all sub-5-min intervals (e.g. 300 for selfhosted)
+_override = (
+    float(settings.CELERY_BEAT_POLL_INTERVAL)
+    if settings.CELERY_BEAT_POLL_INTERVAL > 0
+    else 0
+)
+
 # Webhook-aware: 180s when webhook configured (backup mode), 15s when no webhook (primary discovery)
-POLL_DAILY_RECORDINGS_INTERVAL_SEC = 180.0 if settings.DAILY_WEBHOOK_SECRET else 15.0
+POLL_DAILY_RECORDINGS_INTERVAL_SEC = _override or (
+    180.0 if settings.DAILY_WEBHOOK_SECRET else 15.0
+)
+SQS_POLL_INTERVAL = _override or float(settings.SQS_POLLING_TIMEOUT_SECONDS)
+RECONCILIATION_INTERVAL = _override or 30.0
+ICS_SYNC_INTERVAL = _override or 60.0
+UPCOMING_MEETINGS_INTERVAL = _override or 30.0
 
 if celery.current_app.main != "default":
     logger.info(f"Celery already configured ({celery.current_app})")
@@ -33,11 +46,11 @@ else:
     app.conf.beat_schedule = {
         "process_messages": {
             "task": "reflector.worker.process.process_messages",
-            "schedule": float(settings.SQS_POLLING_TIMEOUT_SECONDS),
+            "schedule": SQS_POLL_INTERVAL,
         },
         "process_meetings": {
             "task": "reflector.worker.process.process_meetings",
-            "schedule": float(settings.SQS_POLLING_TIMEOUT_SECONDS),
+            "schedule": SQS_POLL_INTERVAL,
         },
         "reprocess_failed_recordings": {
             "task": "reflector.worker.process.reprocess_failed_recordings",
@@ -53,15 +66,15 @@ else:
         },
         "trigger_daily_reconciliation": {
             "task": "reflector.worker.process.trigger_daily_reconciliation",
-            "schedule": 30.0,  # Every 30 seconds (queues poll tasks for all active meetings)
+            "schedule": RECONCILIATION_INTERVAL,
         },
         "sync_all_ics_calendars": {
             "task": "reflector.worker.ics_sync.sync_all_ics_calendars",
-            "schedule": 60.0,  # Run every minute to check which rooms need sync
+            "schedule": ICS_SYNC_INTERVAL,
         },
         "create_upcoming_meetings": {
             "task": "reflector.worker.ics_sync.create_upcoming_meetings",
-            "schedule": 30.0,  # Run every 30 seconds to create upcoming meetings
+            "schedule": UPCOMING_MEETINGS_INTERVAL,
         },
     }
 

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
@@ -28,9 +27,6 @@ from reflector.db.transcripts import (
 from reflector.hatchet.client import HatchetClientManager
 from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 from reflector.pipelines.main_live_pipeline import asynctask
-from reflector.pipelines.main_multitrack_pipeline import (
-    task_pipeline_multitrack_process,
-)
 from reflector.pipelines.topic_processing import EmptyPipeline
 from reflector.processors import AudioFileWriterProcessor
 from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
@@ -231,44 +227,79 @@ 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:
-        logger.error(
-            "Recording not found - should have been created by webhook/polling",
-            recording_id=recording_id,
-        )
-        return
+    if recording and recording.meeting_id:
+        # Reprocessing: recording exists with meeting already linked
+        meeting = await meetings_controller.get_by_id(recording.meeting_id)
+        if not meeting:
+            logger.error(
+                "Reprocessing: meeting not found for recording - skipping",
+                meeting_id=recording.meeting_id,
+                recording_id=recording_id,
+            )
+            return
 
-    if not recording.meeting_id:
-        logger.error(
-            "Recording has no meeting_id - orphan should not be queued",
+        logger.info(
+            "Reprocessing: using existing recording.meeting_id",
             recording_id=recording_id,
+            meeting_id=meeting.id,
+            room_name=daily_room_name,
         )
-        return
-
-    # Get meeting
-    meeting = await meetings_controller.get_by_id(recording.meeting_id)
-    if not meeting:
-        logger.error(
-            "Meeting not found for recording",
-            meeting_id=recording.meeting_id,
+    else:
+        # First processing: recording doesn't exist, need time-based matching
+        # (Daily.co doesn't return instanceId in API, must match by timestamp)
+        recording_start = datetime.fromtimestamp(recording_start_ts, tz=timezone.utc)
+        meeting = await meetings_controller.get_by_room_name_and_time(
+            room_name=daily_room_name,
+            recording_start=recording_start,
+            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 +307,33 @@ 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(
@@ -290,49 +348,29 @@ async def _process_multitrack_recording_inner(
             room_id=room.id,
         )
 
-    use_celery = room and room.use_celery
-    use_hatchet = not use_celery
-
-    if use_celery:
-        logger.info(
-            "Room uses legacy Celery processing",
-            room_id=room.id,
-            transcript_id=transcript.id,
-        )
-
-    if use_hatchet:
-        workflow_id = await HatchetClientManager.start_workflow(
-            workflow_name="DiarizationPipeline",
-            input_data={
-                "recording_id": recording_id,
-                "tracks": [{"s3_key": k} for k in filter_cam_audio_tracks(track_keys)],
-                "bucket_name": bucket_name,
-                "transcript_id": transcript.id,
-                "room_id": room.id,
-            },
-            additional_metadata={
-                "transcript_id": transcript.id,
-                "recording_id": recording_id,
-                "daily_recording_id": recording_id,
-            },
-        )
-        logger.info(
-            "Started Hatchet workflow",
-            workflow_id=workflow_id,
-            transcript_id=transcript.id,
-        )
-
-        await transcripts_controller.update(
-            transcript, {"workflow_run_id": workflow_id}
-        )
-        return
-
-    # Celery pipeline (runs when durable workflows disabled)
-    task_pipeline_multitrack_process.delay(
-        transcript_id=transcript.id,
-        bucket_name=bucket_name,
-        track_keys=filter_cam_audio_tracks(track_keys),
+    # Multitrack processing always uses Hatchet (no Celery fallback)
+    workflow_id = await HatchetClientManager.start_workflow(
+        workflow_name="DiarizationPipeline",
+        input_data={
+            "recording_id": recording_id,
+            "tracks": [{"s3_key": k} for k in filter_cam_audio_tracks(track_keys)],
+            "bucket_name": bucket_name,
+            "transcript_id": transcript.id,
+            "room_id": room.id,
+        },
+        additional_metadata={
+            "transcript_id": transcript.id,
+            "recording_id": recording_id,
+            "daily_recording_id": recording_id,
+        },
     )
+    logger.info(
+        "Started Hatchet workflow",
+        workflow_id=workflow_id,
+        transcript_id=transcript.id,
+    )
+
+    await transcripts_controller.update(transcript, {"workflow_run_id": workflow_id})
 
 
 @shared_task
@@ -461,7 +499,7 @@ 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 +512,155 @@ async def store_cloud_recording(
     Returns:
         True if stored, False if skipped/failed
     """
-    # Lookup request
-    match = await daily_recording_requests_controller.find_by_recording_id(recording_id)
+    recording_start = datetime.fromtimestamp(start_ts, tz=timezone.utc)
 
-    if not match:
-        # ORPHAN: No request found (pre-migration recording or failed request creation)
-        await create_and_log_orphan(
+    meeting = await meetings_controller.get_by_room_name_and_time(
+        room_name=room_name,
+        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,
-            track_keys=None,
-            source=source,
+            recording_start_ts=start_ts,
+            recording_start=recording_start.isoformat(),
         )
         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}",
-        meeting_id=meeting_id,
+        f"Cloud recording stored via {source} (time-based match)",
+        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.
-    Only first cloud recording per meeting is kept (existing behavior).
+    Uses time-based matching via store_cloud_recording().
     """
     if not cloud_recordings:
         return
 
-    for rec in cloud_recordings:
-        # Lookup request
-        match = await daily_recording_requests_controller.find_by_recording_id(rec.id)
-
-        if not match:
-            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:
+    stored_count = 0
+    for recording in cloud_recordings:
+        # 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 s3_key:
             logger.warning(
-                "Cloud recording already exists for meeting (stop/restart?)",
-                recording_id=rec.id,
-                meeting_id=meeting_id,
+                "Cloud recording: missing S3 key",
+                recording_id=recording.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,
-) -> None:
-    """Process raw-tracks (database deduplication, worker-agnostic)."""
+    bucket_name: str,
+):
+    """Queue raw-tracks recordings missing from DB (existing logic)."""
     if not raw_tracks_recordings:
         return
 
-    for rec in raw_tracks_recordings:
-        # Lookup request FIRST (before any DB writes)
-        match = await daily_recording_requests_controller.find_by_recording_id(rec.id)
+    recording_ids = [rec.id for rec in raw_tracks_recordings]
+    existing_recordings = await recordings_controller.get_by_ids(recording_ids)
+    existing_ids = {rec.id for rec in existing_recordings}
 
-        if not match:
-            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",
+    missing_recordings = [
+        rec for rec in raw_tracks_recordings if rec.id not in existing_ids
+    ]
+
+    if not missing_recordings:
+        logger.debug(
+            "All raw-tracks recordings already in DB",
+            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
-        meeting = await meetings_controller.get_by_id(meeting_id)
-        if not meeting:
-            logger.error(
-                "Meeting not found", recording_id=rec.id, meeting_id=meeting_id
-            )
-            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",
+        if not track_keys:
+            logger.warning(
+                "No audio tracks found in raw-tracks recording",
+                recording_id=recording.id,
+                room_name=recording.room_name,
+                total_tracks=len(recording.tracks),
             )
             continue
 
-        # DEDUPLICATION: Atomically create recording (single operation, no race window)
-        # ON CONFLICT → concurrent poller already got it, skip entire logic
-        track_keys = [t.s3Key for t in rec.tracks if t.type == "audio"]
-
-        created = await recordings_controller.try_create_with_meeting(
-            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",
-            )
+        logger.info(
+            "Queueing missing raw-tracks recording for processing",
+            recording_id=recording.id,
+            room_name=recording.room_name,
+            track_count=len(track_keys),
         )
 
-        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.
@@ -1026,66 +1049,43 @@ async def reprocess_failed_daily_recordings():
                 )
                 continue
 
-            use_celery = room and room.use_celery
-            use_hatchet = not use_celery
-
-            if use_hatchet:
-                if not transcript:
-                    logger.warning(
-                        "No transcript for Hatchet reprocessing, skipping",
-                        recording_id=recording.id,
-                    )
-                    continue
-
-                workflow_id = await HatchetClientManager.start_workflow(
-                    workflow_name="DiarizationPipeline",
-                    input_data={
-                        "recording_id": recording.id,
-                        "tracks": [
-                            {"s3_key": k}
-                            for k in filter_cam_audio_tracks(recording.track_keys)
-                        ],
-                        "bucket_name": bucket_name,
-                        "transcript_id": transcript.id,
-                        "room_id": room.id if room else None,
-                    },
-                    additional_metadata={
-                        "transcript_id": transcript.id,
-                        "recording_id": recording.id,
-                        "reprocess": True,
-                    },
-                )
-                await transcripts_controller.update(
-                    transcript, {"workflow_run_id": workflow_id}
-                )
-
-                logger.info(
-                    "Queued Daily recording for Hatchet reprocessing",
+            # Multitrack reprocessing always uses Hatchet (no Celery fallback)
+            if not transcript:
+                logger.warning(
+                    "No transcript for Hatchet reprocessing, skipping",
                     recording_id=recording.id,
-                    workflow_id=workflow_id,
-                    room_name=meeting.room_name,
-                    track_count=len(recording.track_keys),
-                )
-            else:
-                logger.info(
-                    "Queueing Daily recording for Celery reprocessing",
-                    recording_id=recording.id,
-                    room_name=meeting.room_name,
-                    track_count=len(recording.track_keys),
-                    transcript_status=transcript.status if transcript else None,
                 )
+                continue
 
-                # For reprocessing, pass actual recording time (though it's ignored - see _process_multitrack_recording_inner)
-                # Reprocessing uses recording.meeting_id directly instead of time-based matching
-                recording_start_ts = int(recording.recorded_at.timestamp())
+            workflow_id = await HatchetClientManager.start_workflow(
+                workflow_name="DiarizationPipeline",
+                input_data={
+                    "recording_id": recording.id,
+                    "tracks": [
+                        {"s3_key": k}
+                        for k in filter_cam_audio_tracks(recording.track_keys)
+                    ],
+                    "bucket_name": bucket_name,
+                    "transcript_id": transcript.id,
+                    "room_id": room.id if room else None,
+                },
+                additional_metadata={
+                    "transcript_id": transcript.id,
+                    "recording_id": recording.id,
+                    "reprocess": True,
+                },
+            )
+            await transcripts_controller.update(
+                transcript, {"workflow_run_id": workflow_id}
+            )
 
-                process_multitrack_recording.delay(
-                    bucket_name=bucket_name,
-                    daily_room_name=meeting.room_name,
-                    recording_id=recording.id,
-                    track_keys=recording.track_keys,
-                    recording_start_ts=recording_start_ts,
-                )
+            logger.info(
+                "Queued Daily recording for Hatchet reprocessing",
+                recording_id=recording.id,
+                workflow_id=workflow_id,
+                room_name=meeting.room_name,
+                track_count=len(recording.track_keys),
+            )
 
             reprocessed_count += 1
 

server/reflector/ws_events.py

@@ -0,0 +1,188 @@
+"""Typed WebSocket event models.
+
+Defines Pydantic models with Literal discriminators for all WS events.
+Exposed via stub GET endpoints so ``pnpm openapi`` generates TS discriminated unions.
+"""
+
+from typing import Annotated, Literal, Union
+
+from pydantic import BaseModel, Discriminator
+
+from reflector.db.transcripts import (
+    TranscriptActionItems,
+    TranscriptDuration,
+    TranscriptFinalLongSummary,
+    TranscriptFinalShortSummary,
+    TranscriptFinalTitle,
+    TranscriptStatus,
+    TranscriptText,
+    TranscriptWaveform,
+)
+from reflector.utils.string import NonEmptyString
+from reflector.views.transcripts import GetTranscriptTopic
+
+# ---------------------------------------------------------------------------
+# Transcript-level event name literal
+# ---------------------------------------------------------------------------
+
+TranscriptEventName = Literal[
+    "TRANSCRIPT",
+    "TOPIC",
+    "STATUS",
+    "FINAL_TITLE",
+    "FINAL_LONG_SUMMARY",
+    "FINAL_SHORT_SUMMARY",
+    "ACTION_ITEMS",
+    "DURATION",
+    "WAVEFORM",
+]
+
+# ---------------------------------------------------------------------------
+# Transcript-level WS event wrappers
+# ---------------------------------------------------------------------------
+
+
+class TranscriptWsTranscript(BaseModel):
+    event: Literal["TRANSCRIPT"] = "TRANSCRIPT"
+    data: TranscriptText
+
+
+class TranscriptWsTopic(BaseModel):
+    event: Literal["TOPIC"] = "TOPIC"
+    data: GetTranscriptTopic
+
+
+class TranscriptWsStatusData(BaseModel):
+    value: TranscriptStatus
+
+
+class TranscriptWsStatus(BaseModel):
+    event: Literal["STATUS"] = "STATUS"
+    data: TranscriptWsStatusData
+
+
+class TranscriptWsFinalTitle(BaseModel):
+    event: Literal["FINAL_TITLE"] = "FINAL_TITLE"
+    data: TranscriptFinalTitle
+
+
+class TranscriptWsFinalLongSummary(BaseModel):
+    event: Literal["FINAL_LONG_SUMMARY"] = "FINAL_LONG_SUMMARY"
+    data: TranscriptFinalLongSummary
+
+
+class TranscriptWsFinalShortSummary(BaseModel):
+    event: Literal["FINAL_SHORT_SUMMARY"] = "FINAL_SHORT_SUMMARY"
+    data: TranscriptFinalShortSummary
+
+
+class TranscriptWsActionItems(BaseModel):
+    event: Literal["ACTION_ITEMS"] = "ACTION_ITEMS"
+    data: TranscriptActionItems
+
+
+class TranscriptWsDuration(BaseModel):
+    event: Literal["DURATION"] = "DURATION"
+    data: TranscriptDuration
+
+
+class TranscriptWsWaveform(BaseModel):
+    event: Literal["WAVEFORM"] = "WAVEFORM"
+    data: TranscriptWaveform
+
+
+TranscriptWsEvent = Annotated[
+    Union[
+        TranscriptWsTranscript,
+        TranscriptWsTopic,
+        TranscriptWsStatus,
+        TranscriptWsFinalTitle,
+        TranscriptWsFinalLongSummary,
+        TranscriptWsFinalShortSummary,
+        TranscriptWsActionItems,
+        TranscriptWsDuration,
+        TranscriptWsWaveform,
+    ],
+    Discriminator("event"),
+]
+
+# ---------------------------------------------------------------------------
+# User-level event name literal
+# ---------------------------------------------------------------------------
+
+UserEventName = Literal[
+    "TRANSCRIPT_CREATED",
+    "TRANSCRIPT_DELETED",
+    "TRANSCRIPT_STATUS",
+    "TRANSCRIPT_FINAL_TITLE",
+    "TRANSCRIPT_DURATION",
+]
+
+# ---------------------------------------------------------------------------
+# User-level WS event data models
+# ---------------------------------------------------------------------------
+
+
+class UserTranscriptCreatedData(BaseModel):
+    id: NonEmptyString
+
+
+class UserTranscriptDeletedData(BaseModel):
+    id: NonEmptyString
+
+
+class UserTranscriptStatusData(BaseModel):
+    id: NonEmptyString
+    value: TranscriptStatus
+
+
+class UserTranscriptFinalTitleData(BaseModel):
+    id: NonEmptyString
+    title: NonEmptyString
+
+
+class UserTranscriptDurationData(BaseModel):
+    id: NonEmptyString
+    duration: float
+
+
+# ---------------------------------------------------------------------------
+# User-level WS event wrappers
+# ---------------------------------------------------------------------------
+
+
+class UserWsTranscriptCreated(BaseModel):
+    event: Literal["TRANSCRIPT_CREATED"] = "TRANSCRIPT_CREATED"
+    data: UserTranscriptCreatedData
+
+
+class UserWsTranscriptDeleted(BaseModel):
+    event: Literal["TRANSCRIPT_DELETED"] = "TRANSCRIPT_DELETED"
+    data: UserTranscriptDeletedData
+
+
+class UserWsTranscriptStatus(BaseModel):
+    event: Literal["TRANSCRIPT_STATUS"] = "TRANSCRIPT_STATUS"
+    data: UserTranscriptStatusData
+
+
+class UserWsTranscriptFinalTitle(BaseModel):
+    event: Literal["TRANSCRIPT_FINAL_TITLE"] = "TRANSCRIPT_FINAL_TITLE"
+    data: UserTranscriptFinalTitleData
+
+
+class UserWsTranscriptDuration(BaseModel):
+    event: Literal["TRANSCRIPT_DURATION"] = "TRANSCRIPT_DURATION"
+    data: UserTranscriptDurationData
+
+
+UserWsEvent = Annotated[
+    Union[
+        UserWsTranscriptCreated,
+        UserWsTranscriptDeleted,
+        UserWsTranscriptStatus,
+        UserWsTranscriptFinalTitle,
+        UserWsTranscriptDuration,
+    ],
+    Discriminator("event"),
+]

server/reflector/ws_manager.py

@@ -11,7 +11,6 @@ broadcast messages to all connected websockets.
 
 import asyncio
 import json
-import threading
 
 import redis.asyncio as redis
 from fastapi import WebSocket
@@ -49,7 +48,15 @@ class RedisPubSubManager:
         if not self.redis_connection:
             await self.connect()
         message = json.dumps(message)
-        await self.redis_connection.publish(room_id, message)
+        try:
+            await self.redis_connection.publish(room_id, message)
+        except RuntimeError:
+            # Celery workers run each task in a new event loop (asyncio.run),
+            # which closes the previous loop. Cached Redis connection is dead.
+            # Reconnect on the current loop and retry.
+            self.redis_connection = None
+            await self.connect()
+            await self.redis_connection.publish(room_id, message)
 
     async def subscribe(self, room_id: str) -> redis.Redis:
         await self.pubsub.subscribe(room_id)
@@ -98,6 +105,7 @@ class WebsocketManager:
 
     async def _pubsub_data_reader(self, pubsub_subscriber):
         while True:
+            # timeout=1.0 prevents tight CPU loop when no messages available
             message = await pubsub_subscriber.get_message(
                 ignore_subscribe_messages=True
             )
@@ -109,29 +117,38 @@ class WebsocketManager:
                     await socket.send_json(data)
 
 
+# Process-global singleton to ensure only one WebsocketManager instance exists.
+# Multiple instances would cause resource leaks and CPU issues.
+_ws_manager: WebsocketManager | None = None
+
+
 def get_ws_manager() -> WebsocketManager:
     """
-    Returns the WebsocketManager instance for managing websockets.
+    Returns the global WebsocketManager singleton.
 
-    This function initializes and returns the WebsocketManager instance,
-    which is responsible for managing websockets and handling websocket
-    connections.
+    Creates instance on first call, subsequent calls return cached instance.
+    Thread-safe via GIL. Concurrent initialization may create duplicate
+    instances but last write wins (acceptable for this use case).
 
     Returns:
-        WebsocketManager: The initialized WebsocketManager instance.
-
-    Raises:
-        ImportError: If the 'reflector.settings' module cannot be imported.
-        RedisConnectionError: If there is an error connecting to the Redis server.
+        WebsocketManager: The global WebsocketManager instance.
     """
-    local = threading.local()
-    if hasattr(local, "ws_manager"):
-        return local.ws_manager
+    global _ws_manager
 
+    if _ws_manager is not None:
+        return _ws_manager
+
+    # No lock needed - GIL makes this safe enough
+    # Worst case: race creates two instances, last assignment wins
     pubsub_client = RedisPubSubManager(
         host=settings.REDIS_HOST,
         port=settings.REDIS_PORT,
     )
-    ws_manager = WebsocketManager(pubsub_client=pubsub_client)
-    local.ws_manager = ws_manager
-    return ws_manager
+    _ws_manager = WebsocketManager(pubsub_client=pubsub_client)
+    return _ws_manager
+
+
+def reset_ws_manager() -> None:
+    """Reset singleton for testing. DO NOT use in production."""
+    global _ws_manager
+    _ws_manager = None

server/runserver.sh

@@ -2,6 +2,10 @@
 
 if [ "${ENTRYPOINT}" = "server" ]; then
     uv run alembic upgrade head
+    # Provision admin user if password auth is configured
+    if [ -n "${ADMIN_EMAIL:-}" ] && [ -n "${ADMIN_PASSWORD_HASH:-}" ]; then
+        uv run python -m reflector.tools.provision_admin
+    fi
     uv run uvicorn reflector.app:app --host 0.0.0.0 --port 1250
 elif [ "${ENTRYPOINT}" = "worker" ]; then
     uv run celery -A reflector.worker.app worker --loglevel=info

server/scripts/recreate_daily_webhook.py

@@ -15,8 +15,7 @@ from reflector.settings import settings
 
 async def setup_webhook(webhook_url: str):
     """
-    Create or update Daily.co webhook for this environment using dailyco_api module.
-    Uses DAILY_WEBHOOK_UUID to identify existing webhook.
+    Create Daily.co webhook. Deletes any existing webhooks first, then creates the new one.
     """
     if not settings.DAILY_API_KEY:
         print("Error: DAILY_API_KEY not set")
@@ -35,79 +34,37 @@ async def setup_webhook(webhook_url: str):
     ]
 
     async with DailyApiClient(api_key=settings.DAILY_API_KEY) as client:
-        webhook_uuid = settings.DAILY_WEBHOOK_UUID
+        webhooks = await client.list_webhooks()
+        for wh in webhooks:
+            await client.delete_webhook(wh.uuid)
+            print(f"Deleted webhook {wh.uuid}")
 
-        if webhook_uuid:
-            print(f"Updating existing webhook {webhook_uuid}...")
-            try:
-                # Note: Daily.co doesn't support PATCH well, so we delete + recreate
-                await client.delete_webhook(webhook_uuid)
-                print(f"Deleted old webhook {webhook_uuid}")
+        request = CreateWebhookRequest(
+            url=webhook_url,
+            eventTypes=event_types,
+            hmac=settings.DAILY_WEBHOOK_SECRET,
+        )
+        result = await client.create_webhook(request)
+        webhook_uuid = result.uuid
 
-                request = CreateWebhookRequest(
-                    url=webhook_url,
-                    eventTypes=event_types,
-                    hmac=settings.DAILY_WEBHOOK_SECRET,
-                )
-                result = await client.create_webhook(request)
+        print(f"✓ Created webhook {webhook_uuid} (state: {result.state})")
+        print(f"  URL: {result.url}")
 
-                print(
-                    f"✓ Created replacement webhook {result.uuid} (state: {result.state})"
-                )
-                print(f"  URL: {result.url}")
+        env_file = Path(__file__).parent.parent / ".env"
+        if env_file.exists():
+            lines = env_file.read_text().splitlines()
+            updated = False
+            for i, line in enumerate(lines):
+                if line.startswith("DAILY_WEBHOOK_UUID="):
+                    lines[i] = f"DAILY_WEBHOOK_UUID={webhook_uuid}"
+                    updated = True
+                    break
+            if not updated:
+                lines.append(f"DAILY_WEBHOOK_UUID={webhook_uuid}")
+            env_file.write_text("\n".join(lines) + "\n")
+            print("✓ Saved DAILY_WEBHOOK_UUID to .env")
 
-                webhook_uuid = result.uuid
-
-            except Exception as e:
-                if hasattr(e, "response") and e.response.status_code == 404:
-                    print(f"Webhook {webhook_uuid} not found, creating new one...")
-                    webhook_uuid = None  # Fall through to creation
-                else:
-                    print(f"Error updating webhook: {e}")
-                    return 1
-
-        if not webhook_uuid:
-            print("Creating new webhook...")
-            request = CreateWebhookRequest(
-                url=webhook_url,
-                eventTypes=event_types,
-                hmac=settings.DAILY_WEBHOOK_SECRET,
-            )
-            result = await client.create_webhook(request)
-            webhook_uuid = result.uuid
-
-            print(f"✓ Created webhook {webhook_uuid} (state: {result.state})")
-            print(f"  URL: {result.url}")
-            print()
-            print("=" * 60)
-            print("IMPORTANT: Add this to your environment variables:")
-            print("=" * 60)
-            print(f"DAILY_WEBHOOK_UUID: {webhook_uuid}")
-            print("=" * 60)
-            print()
-
-            # Try to write UUID to .env file
-            env_file = Path(__file__).parent.parent / ".env"
-            if env_file.exists():
-                lines = env_file.read_text().splitlines()
-                updated = False
-
-                # Update existing DAILY_WEBHOOK_UUID line or add it
-                for i, line in enumerate(lines):
-                    if line.startswith("DAILY_WEBHOOK_UUID="):
-                        lines[i] = f"DAILY_WEBHOOK_UUID={webhook_uuid}"
-                        updated = True
-                        break
-
-                if not updated:
-                    lines.append(f"DAILY_WEBHOOK_UUID={webhook_uuid}")
-
-                env_file.write_text("\n".join(lines) + "\n")
-                print(f"✓ Also saved to local .env file")
-            else:
-                print(f"⚠ Local .env file not found - please add manually")
-
-            return 0
+        return 0
 
 
 if __name__ == "__main__":
@@ -117,11 +74,7 @@ if __name__ == "__main__":
             "Example: python recreate_daily_webhook.py https://example.com/v1/daily/webhook"
         )
         print()
-        print("Behavior:")
-        print("  - If DAILY_WEBHOOK_UUID set: Deletes old webhook, creates new one")
-        print(
-            "  - If DAILY_WEBHOOK_UUID empty: Creates new webhook, saves UUID to .env"
-        )
+        print("Deletes all existing webhooks, then creates a new one.")
         sys.exit(1)
 
     sys.exit(asyncio.run(setup_webhook(sys.argv[1])))

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/conftest.py

@@ -1,11 +1,10 @@
 import os
 from contextlib import asynccontextmanager
-from tempfile import NamedTemporaryFile
 from unittest.mock import patch
 
 import pytest
 
-from reflector.schemas.platform import WHEREBY_PLATFORM
+from reflector.schemas.platform import DAILY_PLATFORM, WHEREBY_PLATFORM
 
 
 @pytest.fixture(scope="session", autouse=True)
@@ -15,6 +14,7 @@ def register_mock_platform():
     from reflector.video_platforms.registry import register_platform
 
     register_platform(WHEREBY_PLATFORM, MockPlatformClient)
+    register_platform(DAILY_PLATFORM, MockPlatformClient)
     yield
 
 
@@ -333,11 +333,14 @@ def celery_enable_logging():
 
 @pytest.fixture(scope="session")
 def celery_config():
-    with NamedTemporaryFile() as f:
-        yield {
-            "broker_url": "memory://",
-            "result_backend": f"db+sqlite:///{f.name}",
-        }
+    redis_host = os.environ.get("REDIS_HOST", "localhost")
+    redis_port = os.environ.get("REDIS_PORT", "6379")
+    # Use db 2 to avoid conflicts with main app
+    redis_url = f"redis://{redis_host}:{redis_port}/2"
+    yield {
+        "broker_url": redis_url,
+        "result_backend": redis_url,
+    }
 
 
 @pytest.fixture(scope="session")
@@ -370,9 +373,12 @@ async def ws_manager_in_memory(monkeypatch):
         def __init__(self, queue: asyncio.Queue):
             self.queue = queue
 
-        async def get_message(self, ignore_subscribe_messages: bool = True):
+        async def get_message(
+            self, ignore_subscribe_messages: bool = True, timeout: float | None = None
+        ):
+            wait_timeout = timeout if timeout is not None else 0.05
             try:
-                return await asyncio.wait_for(self.queue.get(), timeout=0.05)
+                return await asyncio.wait_for(self.queue.get(), timeout=wait_timeout)
             except Exception:
                 return None
 

server/tests/test_auth_password.py

@@ -0,0 +1,201 @@
+"""Tests for the password auth backend."""
+
+import pytest
+from httpx import AsyncClient
+from jose import jwt
+
+from reflector.auth.password_utils import hash_password
+from reflector.settings import settings
+
+
+@pytest.fixture
+async def password_app():
+    """Create a minimal FastAPI app with the password auth router."""
+    from fastapi import FastAPI
+
+    from reflector.auth import auth_password
+
+    app = FastAPI()
+    app.include_router(auth_password.router, prefix="/v1")
+    # Reset rate limiter between tests
+    auth_password._login_attempts.clear()
+    return app
+
+
+@pytest.fixture
+async def password_client(password_app):
+    """Create a test client for the password auth app."""
+    async with AsyncClient(app=password_app, base_url="http://test/v1") as client:
+        yield client
+
+
+async def _create_user_with_password(email: str, password: str):
+    """Helper to create a user with a password hash in the DB."""
+    from reflector.db.users import user_controller
+    from reflector.utils import generate_uuid4
+
+    pw_hash = hash_password(password)
+    return await user_controller.create_or_update(
+        id=generate_uuid4(),
+        authentik_uid=f"local:{email}",
+        email=email,
+        password_hash=pw_hash,
+    )
+
+
+@pytest.mark.asyncio
+async def test_login_success(password_client, setup_database):
+    await _create_user_with_password("admin@test.com", "testpass123")
+
+    response = await password_client.post(
+        "/auth/login",
+        json={"email": "admin@test.com", "password": "testpass123"},
+    )
+
+    assert response.status_code == 200
+    data = response.json()
+    assert "access_token" in data
+    assert data["token_type"] == "bearer"
+    assert data["expires_in"] > 0
+
+    # Verify the JWT is valid
+    payload = jwt.decode(
+        data["access_token"],
+        settings.SECRET_KEY,
+        algorithms=["HS256"],
+    )
+    assert payload["email"] == "admin@test.com"
+    assert "sub" in payload
+    assert "exp" in payload
+
+
+@pytest.mark.asyncio
+async def test_login_wrong_password(password_client, setup_database):
+    await _create_user_with_password("user@test.com", "correctpassword")
+
+    response = await password_client.post(
+        "/auth/login",
+        json={"email": "user@test.com", "password": "wrongpassword"},
+    )
+
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_login_nonexistent_user(password_client, setup_database):
+    response = await password_client.post(
+        "/auth/login",
+        json={"email": "nobody@test.com", "password": "anything"},
+    )
+
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_login_user_without_password_hash(password_client, setup_database):
+    """User exists but has no password_hash (e.g. Authentik user)."""
+    from reflector.db.users import user_controller
+    from reflector.utils import generate_uuid4
+
+    await user_controller.create_or_update(
+        id=generate_uuid4(),
+        authentik_uid="authentik:abc123",
+        email="oidc@test.com",
+    )
+
+    response = await password_client.post(
+        "/auth/login",
+        json={"email": "oidc@test.com", "password": "anything"},
+    )
+
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_login_rate_limiting(password_client, setup_database):
+    from reflector.auth import auth_password
+
+    # Reset rate limiter
+    auth_password._login_attempts.clear()
+
+    for _ in range(10):
+        await password_client.post(
+            "/auth/login",
+            json={"email": "fake@test.com", "password": "wrong"},
+        )
+
+    # 11th attempt should be rate-limited
+    response = await password_client.post(
+        "/auth/login",
+        json={"email": "fake@test.com", "password": "wrong"},
+    )
+
+    assert response.status_code == 429
+
+
+@pytest.mark.asyncio
+async def test_jwt_create_and_verify():
+    from reflector.auth.auth_password import _create_access_token, _verify_token
+
+    token, expires_in = _create_access_token("user-123", "test@example.com")
+    assert expires_in > 0
+
+    payload = _verify_token(token)
+    assert payload["sub"] == "user-123"
+    assert payload["email"] == "test@example.com"
+    assert "exp" in payload
+
+
+@pytest.mark.asyncio
+async def test_authenticate_user_with_jwt():
+    from reflector.auth.auth_password import (
+        _authenticate_user,
+        _create_access_token,
+    )
+
+    token, _ = _create_access_token("user-abc", "abc@test.com")
+    user = await _authenticate_user(token, None)
+
+    assert user is not None
+    assert user.sub == "user-abc"
+    assert user.email == "abc@test.com"
+
+
+@pytest.mark.asyncio
+async def test_authenticate_user_invalid_jwt():
+    from fastapi import HTTPException
+
+    from reflector.auth.auth_password import _authenticate_user
+
+    with pytest.raises(HTTPException) as exc_info:
+        await _authenticate_user("invalid.jwt.token", None)
+    assert exc_info.value.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_authenticate_user_no_credentials():
+    from reflector.auth.auth_password import _authenticate_user
+
+    user = await _authenticate_user(None, None)
+    assert user is None
+
+
+@pytest.mark.asyncio
+async def test_current_user_raises_without_token():
+    """Verify that current_user dependency raises 401 without token."""
+    from fastapi import Depends, FastAPI
+    from fastapi.testclient import TestClient
+
+    from reflector.auth import auth_password
+
+    app = FastAPI()
+
+    @app.get("/test")
+    async def test_endpoint(user=Depends(auth_password.current_user)):
+        return {"user": user.sub}
+
+    # Use sync TestClient for simplicity
+    client = TestClient(app)
+    response = client.get("/test")
+    # OAuth2PasswordBearer with auto_error=False returns None, then current_user raises 401
+    assert response.status_code == 401

server/tests/test_create_admin.py

@@ -0,0 +1,97 @@
+"""Tests for admin user creation logic (used by create_admin CLI tool)."""
+
+import pytest
+
+from reflector.auth.password_utils import hash_password, verify_password
+from reflector.db.users import user_controller
+from reflector.utils import generate_uuid4
+
+
+async def _provision_admin(email: str, password: str):
+    """Mirrors the logic in create_admin.create_admin() without managing DB connections."""
+    password_hash = hash_password(password)
+
+    existing = await user_controller.get_by_email(email)
+    if existing:
+        await user_controller.set_password_hash(existing.id, password_hash)
+    else:
+        await user_controller.create_or_update(
+            id=generate_uuid4(),
+            authentik_uid=f"local:{email}",
+            email=email,
+            password_hash=password_hash,
+        )
+
+
+@pytest.mark.asyncio
+async def test_create_admin_new_user(setup_database):
+    await _provision_admin("newadmin@test.com", "password123")
+
+    user = await user_controller.get_by_email("newadmin@test.com")
+    assert user is not None
+    assert user.email == "newadmin@test.com"
+    assert user.authentik_uid == "local:newadmin@test.com"
+    assert user.password_hash is not None
+    assert verify_password("password123", user.password_hash)
+
+
+@pytest.mark.asyncio
+async def test_create_admin_updates_existing(setup_database):
+    # Create first
+    await _provision_admin("admin@test.com", "oldpassword")
+    user1 = await user_controller.get_by_email("admin@test.com")
+
+    # Update password
+    await _provision_admin("admin@test.com", "newpassword")
+    user2 = await user_controller.get_by_email("admin@test.com")
+
+    assert user1.id == user2.id  # same user, not duplicated
+    assert verify_password("newpassword", user2.password_hash)
+    assert not verify_password("oldpassword", user2.password_hash)
+
+
+@pytest.mark.asyncio
+async def test_create_admin_idempotent(setup_database):
+    await _provision_admin("admin@test.com", "samepassword")
+    await _provision_admin("admin@test.com", "samepassword")
+
+    # Should only have one user
+    users = await user_controller.list_all()
+    admin_users = [u for u in users if u.email == "admin@test.com"]
+    assert len(admin_users) == 1
+
+
+@pytest.mark.asyncio
+async def test_create_or_update_with_password_hash(setup_database):
+    """Test the extended create_or_update method with password_hash parameter."""
+    pw_hash = hash_password("test123")
+    user = await user_controller.create_or_update(
+        id=generate_uuid4(),
+        authentik_uid="local:test@example.com",
+        email="test@example.com",
+        password_hash=pw_hash,
+    )
+
+    assert user.password_hash == pw_hash
+
+    fetched = await user_controller.get_by_email("test@example.com")
+    assert fetched is not None
+    assert verify_password("test123", fetched.password_hash)
+
+
+@pytest.mark.asyncio
+async def test_set_password_hash(setup_database):
+    """Test the set_password_hash method."""
+    user = await user_controller.create_or_update(
+        id=generate_uuid4(),
+        authentik_uid="local:pw@test.com",
+        email="pw@test.com",
+    )
+    assert user.password_hash is None
+
+    pw_hash = hash_password("newpass")
+    await user_controller.set_password_hash(user.id, pw_hash)
+
+    updated = await user_controller.get_by_email("pw@test.com")
+    assert updated is not None
+    assert verify_password("newpass", updated.password_hash)

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_hatchet_dispatch.py

@@ -255,7 +255,7 @@ async def test_validation_locked_transcript():
 @pytest.mark.usefixtures("setup_database")
 @pytest.mark.asyncio
 async def test_validation_idle_transcript():
-    """Test that validation rejects idle transcripts (not ready)."""
+    """Test that validation rejects idle transcripts without recording (file upload not ready)."""
     from reflector.services.transcript_process import (
         ValidationNotReady,
         validate_transcript_for_processing,
@@ -274,6 +274,34 @@ async def test_validation_idle_transcript():
     assert "not ready" in result.detail.lower()
 
 
+@pytest.mark.usefixtures("setup_database")
+@pytest.mark.asyncio
+async def test_validation_idle_transcript_with_recording_allowed():
+    """Test that validation allows idle transcripts with recording_id (multitrack ready/retry)."""
+    from reflector.services.transcript_process import (
+        ValidationOk,
+        validate_transcript_for_processing,
+    )
+
+    mock_transcript = Transcript(
+        id="test-transcript-id",
+        name="Test",
+        status="idle",
+        source_kind="room",
+        recording_id="test-recording-id",
+    )
+
+    with patch(
+        "reflector.services.transcript_process.task_is_scheduled_or_active"
+    ) as mock_celery_check:
+        mock_celery_check.return_value = False
+
+        result = await validate_transcript_for_processing(mock_transcript)
+
+    assert isinstance(result, ValidationOk)
+    assert result.recording_id == "test-recording-id"
+
+
 @pytest.mark.usefixtures("setup_database")
 @pytest.mark.asyncio
 async def test_prepare_multitrack_config():

server/tests/test_password_utils.py

@@ -0,0 +1,58 @@
+"""Tests for password hashing utilities."""
+
+from reflector.auth.password_utils import hash_password, verify_password
+
+
+def test_hash_and_verify():
+    pw = "my-secret-password"
+    h = hash_password(pw)
+    assert verify_password(pw, h) is True
+
+
+def test_wrong_password():
+    h = hash_password("correct")
+    assert verify_password("wrong", h) is False
+
+
+def test_hash_format():
+    h = hash_password("test")
+    parts = h.split("$")
+    assert len(parts) == 3
+    assert parts[0] == "pbkdf2:sha256:100000"
+    assert len(parts[1]) == 32  # 16 bytes hex = 32 chars
+    assert len(parts[2]) == 64  # sha256 hex = 64 chars
+
+
+def test_different_salts():
+    h1 = hash_password("same")
+    h2 = hash_password("same")
+    assert h1 != h2  # different salts produce different hashes
+    assert verify_password("same", h1) is True
+    assert verify_password("same", h2) is True
+
+
+def test_malformed_hash():
+    assert verify_password("test", "garbage") is False
+    assert verify_password("test", "") is False
+    assert verify_password("test", "pbkdf2:sha256:100000$short") is False
+
+
+def test_empty_password():
+    h = hash_password("")
+    assert verify_password("", h) is True
+    assert verify_password("notempty", h) is False
+
+
+def test_unicode_password():
+    pw = "p\u00e4ssw\u00f6rd\U0001f512"
+    h = hash_password(pw)
+    assert verify_password(pw, h) is True
+    assert verify_password("password", h) is False
+
+
+def test_constant_time_comparison():
+    """Verify that hmac.compare_digest is used (structural test)."""
+    import inspect
+
+    source = inspect.getsource(verify_password)
+    assert "hmac.compare_digest" in source

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_storage.py

@@ -319,3 +319,51 @@ def test_aws_storage_constructor_rejects_mixed_auth():
             aws_secret_access_key="test-secret",
             aws_role_arn="arn:aws:iam::123456789012:role/test-role",
         )
+
+
+@pytest.mark.asyncio
+async def test_aws_storage_custom_endpoint_url():
+    """Test that custom endpoint_url configures path-style addressing and passes endpoint to client."""
+    storage = AwsStorage(
+        aws_bucket_name="reflector-media",
+        aws_region="garage",
+        aws_access_key_id="GKtest",
+        aws_secret_access_key="secret",
+        aws_endpoint_url="http://garage:3900",
+    )
+    assert storage._endpoint_url == "http://garage:3900"
+    assert storage.boto_config.s3["addressing_style"] == "path"
+    assert storage.base_url == "http://garage:3900/reflector-media/"
+    # retries config preserved (merge, not replace)
+    assert storage.boto_config.retries["max_attempts"] == 3
+
+    mock_client = AsyncMock()
+    mock_client.put_object = AsyncMock()
+    mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+    mock_client.__aexit__ = AsyncMock(return_value=None)
+    mock_client.generate_presigned_url = AsyncMock(
+        return_value="http://garage:3900/reflector-media/test.txt"
+    )
+
+    with patch.object(
+        storage.session, "client", return_value=mock_client
+    ) as mock_session_client:
+        await storage.put_file("test.txt", b"data")
+        mock_session_client.assert_called_with(
+            "s3", config=storage.boto_config, endpoint_url="http://garage:3900"
+        )
+
+
+@pytest.mark.asyncio
+async def test_aws_storage_none_endpoint_url():
+    """Test that None endpoint preserves current AWS behavior."""
+    storage = AwsStorage(
+        aws_bucket_name="reflector-bucket",
+        aws_region="us-east-1",
+        aws_access_key_id="AKIAtest",
+        aws_secret_access_key="secret",
+    )
+    assert storage._endpoint_url is None
+    assert storage.base_url == "https://reflector-bucket.s3.amazonaws.com/"
+    # No s3 addressing_style override — boto_config should only have retries
+    assert not hasattr(storage.boto_config, "s3") or storage.boto_config.s3 is None

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/tests/test_transcripts_process.py

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

server/tests/test_transcripts_rtc_ws.py

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

server/tests/test_user_websocket_auth.py

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

server/uv.lock

@@ -235,12 +235,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", size = 13643 },
 ]
 
-[[package]]
-name = "antlr4-python3-runtime"
-version = "4.9.3"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/3e/38/7859ff46355f76f8d19459005ca000b6e7012f2f1ca597746cbcd1fbfe5e/antlr4-python3-runtime-4.9.3.tar.gz", hash = "sha256:f224469b4168294902bb1efa80a8bf7855f24c99aef99cbefc1bcd3cce77881b", size = 117034 }
-
 [[package]]
 name = "anyio"
 version = "4.9.0"
@@ -267,21 +261,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2f/f5/c36551e93acba41a59939ae6a0fb77ddb3f2e8e8caa716410c65f7341f72/asgi_lifespan-2.1.0-py3-none-any.whl", hash = "sha256:ed840706680e28428c01e14afb3875d7d76d3206f3d5b2f2294e059b5c23804f", size = 10895 },
 ]
 
-[[package]]
-name = "asteroid-filterbanks"
-version = "0.4.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/90/fa/5c2be1f96dc179f83cdd3bb267edbd1f47d08f756785c016d5c2163901a7/asteroid-filterbanks-0.4.0.tar.gz", hash = "sha256:415f89d1dcf2b13b35f03f7a9370968ac4e6fa6800633c522dac992b283409b9", size = 24599 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/c5/7c/83ff6046176a675e6a1e8aeefed8892cd97fe7c46af93cc540d1b24b8323/asteroid_filterbanks-0.4.0-py3-none-any.whl", hash = "sha256:4932ac8b6acc6e08fb87cbe8ece84215b5a74eee284fe83acf3540a72a02eaf5", size = 29912 },
-]
-
 [[package]]
 name = "async-timeout"
 version = "5.0.1"
@@ -603,56 +582,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934", size = 46018 },
 ]
 
-[[package]]
-name = "colorlog"
-version = "6.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/d3/7a/359f4d5df2353f26172b3cc39ea32daa39af8de522205f512f458923e677/colorlog-6.9.0.tar.gz", hash = "sha256:bfba54a1b93b94f54e1f4fe48395725a3d92fd2a4af702f6bd70946bdc0c6ac2", size = 16624 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e3/51/9b208e85196941db2f0654ad0357ca6388ab3ed67efdbfc799f35d1f83aa/colorlog-6.9.0-py3-none-any.whl", hash = "sha256:5906e71acd67cb07a71e779c47c4bcb45fb8c2993eebe9e5adcd6a6f1b283eff", size = 11424 },
-]
-
-[[package]]
-name = "contourpy"
-version = "1.3.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/58/01/1253e6698a07380cd31a736d248a3f2a50a7c88779a1813da27503cadc2a/contourpy-1.3.3.tar.gz", hash = "sha256:083e12155b210502d0bca491432bb04d56dc3432f95a979b429f2848c3dbe880", size = 13466174 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/91/2e/c4390a31919d8a78b90e8ecf87cd4b4c4f05a5b48d05ec17db8e5404c6f4/contourpy-1.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:709a48ef9a690e1343202916450bc48b9e51c049b089c7f79a267b46cffcdaa1", size = 288773 },
-    { url = "https://files.pythonhosted.org/packages/0d/44/c4b0b6095fef4dc9c420e041799591e3b63e9619e3044f7f4f6c21c0ab24/contourpy-1.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:23416f38bfd74d5d28ab8429cc4d63fa67d5068bd711a85edb1c3fb0c3e2f381", size = 270149 },
-    { url = "https://files.pythonhosted.org/packages/30/2e/dd4ced42fefac8470661d7cb7e264808425e6c5d56d175291e93890cce09/contourpy-1.3.3-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:929ddf8c4c7f348e4c0a5a3a714b5c8542ffaa8c22954862a46ca1813b667ee7", size = 329222 },
-    { url = "https://files.pythonhosted.org/packages/f2/74/cc6ec2548e3d276c71389ea4802a774b7aa3558223b7bade3f25787fafc2/contourpy-1.3.3-cp311-cp311-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9e999574eddae35f1312c2b4b717b7885d4edd6cb46700e04f7f02db454e67c1", size = 377234 },
-    { url = "https://files.pythonhosted.org/packages/03/b3/64ef723029f917410f75c09da54254c5f9ea90ef89b143ccadb09df14c15/contourpy-1.3.3-cp311-cp311-manylinux_2_26_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0bf67e0e3f482cb69779dd3061b534eb35ac9b17f163d851e2a547d56dba0a3a", size = 380555 },
-    { url = "https://files.pythonhosted.org/packages/5f/4b/6157f24ca425b89fe2eb7e7be642375711ab671135be21e6faa100f7448c/contourpy-1.3.3-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:51e79c1f7470158e838808d4a996fa9bac72c498e93d8ebe5119bc1e6becb0db", size = 355238 },
-    { url = "https://files.pythonhosted.org/packages/98/56/f914f0dd678480708a04cfd2206e7c382533249bc5001eb9f58aa693e200/contourpy-1.3.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:598c3aaece21c503615fd59c92a3598b428b2f01bfb4b8ca9c4edeecc2438620", size = 1326218 },
-    { url = "https://files.pythonhosted.org/packages/fb/d7/4a972334a0c971acd5172389671113ae82aa7527073980c38d5868ff1161/contourpy-1.3.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:322ab1c99b008dad206d406bb61d014cf0174df491ae9d9d0fac6a6fda4f977f", size = 1392867 },
-    { url = "https://files.pythonhosted.org/packages/75/3e/f2cc6cd56dc8cff46b1a56232eabc6feea52720083ea71ab15523daab796/contourpy-1.3.3-cp311-cp311-win32.whl", hash = "sha256:fd907ae12cd483cd83e414b12941c632a969171bf90fc937d0c9f268a31cafff", size = 183677 },
-    { url = "https://files.pythonhosted.org/packages/98/4b/9bd370b004b5c9d8045c6c33cf65bae018b27aca550a3f657cdc99acdbd8/contourpy-1.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:3519428f6be58431c56581f1694ba8e50626f2dd550af225f82fb5f5814d2a42", size = 225234 },
-    { url = "https://files.pythonhosted.org/packages/d9/b6/71771e02c2e004450c12b1120a5f488cad2e4d5b590b1af8bad060360fe4/contourpy-1.3.3-cp311-cp311-win_arm64.whl", hash = "sha256:15ff10bfada4bf92ec8b31c62bf7c1834c244019b4a33095a68000d7075df470", size = 193123 },
-    { url = "https://files.pythonhosted.org/packages/be/45/adfee365d9ea3d853550b2e735f9d66366701c65db7855cd07621732ccfc/contourpy-1.3.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b08a32ea2f8e42cf1d4be3169a98dd4be32bafe4f22b6c4cb4ba810fa9e5d2cb", size = 293419 },
-    { url = "https://files.pythonhosted.org/packages/53/3e/405b59cfa13021a56bba395a6b3aca8cec012b45bf177b0eaf7a202cde2c/contourpy-1.3.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:556dba8fb6f5d8742f2923fe9457dbdd51e1049c4a43fd3986a0b14a1d815fc6", size = 273979 },
-    { url = "https://files.pythonhosted.org/packages/d4/1c/a12359b9b2ca3a845e8f7f9ac08bdf776114eb931392fcad91743e2ea17b/contourpy-1.3.3-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:92d9abc807cf7d0e047b95ca5d957cf4792fcd04e920ca70d48add15c1a90ea7", size = 332653 },
-    { url = "https://files.pythonhosted.org/packages/63/12/897aeebfb475b7748ea67b61e045accdfcf0d971f8a588b67108ed7f5512/contourpy-1.3.3-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b2e8faa0ed68cb29af51edd8e24798bb661eac3bd9f65420c1887b6ca89987c8", size = 379536 },
-    { url = "https://files.pythonhosted.org/packages/43/8a/a8c584b82deb248930ce069e71576fc09bd7174bbd35183b7943fb1064fd/contourpy-1.3.3-cp312-cp312-manylinux_2_26_s390x.manylinux_2_28_s390x.whl", hash = "sha256:626d60935cf668e70a5ce6ff184fd713e9683fb458898e4249b63be9e28286ea", size = 384397 },
-    { url = "https://files.pythonhosted.org/packages/cc/8f/ec6289987824b29529d0dfda0d74a07cec60e54b9c92f3c9da4c0ac732de/contourpy-1.3.3-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4d00e655fcef08aba35ec9610536bfe90267d7ab5ba944f7032549c55a146da1", size = 362601 },
-    { url = "https://files.pythonhosted.org/packages/05/0a/a3fe3be3ee2dceb3e615ebb4df97ae6f3828aa915d3e10549ce016302bd1/contourpy-1.3.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:451e71b5a7d597379ef572de31eeb909a87246974d960049a9848c3bc6c41bf7", size = 1331288 },
-    { url = "https://files.pythonhosted.org/packages/33/1d/acad9bd4e97f13f3e2b18a3977fe1b4a37ecf3d38d815333980c6c72e963/contourpy-1.3.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:459c1f020cd59fcfe6650180678a9993932d80d44ccde1fa1868977438f0b411", size = 1403386 },
-    { url = "https://files.pythonhosted.org/packages/cf/8f/5847f44a7fddf859704217a99a23a4f6417b10e5ab1256a179264561540e/contourpy-1.3.3-cp312-cp312-win32.whl", hash = "sha256:023b44101dfe49d7d53932be418477dba359649246075c996866106da069af69", size = 185018 },
-    { url = "https://files.pythonhosted.org/packages/19/e8/6026ed58a64563186a9ee3f29f41261fd1828f527dd93d33b60feca63352/contourpy-1.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:8153b8bfc11e1e4d75bcb0bff1db232f9e10b274e0929de9d608027e0d34ff8b", size = 226567 },
-    { url = "https://files.pythonhosted.org/packages/d1/e2/f05240d2c39a1ed228d8328a78b6f44cd695f7ef47beb3e684cf93604f86/contourpy-1.3.3-cp312-cp312-win_arm64.whl", hash = "sha256:07ce5ed73ecdc4a03ffe3e1b3e3c1166db35ae7584be76f65dbbe28a7791b0cc", size = 193655 },
-    { url = "https://files.pythonhosted.org/packages/a5/29/8dcfe16f0107943fa92388c23f6e05cff0ba58058c4c95b00280d4c75a14/contourpy-1.3.3-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:cd5dfcaeb10f7b7f9dc8941717c6c2ade08f587be2226222c12b25f0483ed497", size = 278809 },
-    { url = "https://files.pythonhosted.org/packages/85/a9/8b37ef4f7dafeb335daee3c8254645ef5725be4d9c6aa70b50ec46ef2f7e/contourpy-1.3.3-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:0c1fc238306b35f246d61a1d416a627348b5cf0648648a031e14bb8705fcdfe8", size = 261593 },
-    { url = "https://files.pythonhosted.org/packages/0a/59/ebfb8c677c75605cc27f7122c90313fd2f375ff3c8d19a1694bda74aaa63/contourpy-1.3.3-pp311-pypy311_pp73-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70f9aad7de812d6541d29d2bbf8feb22ff7e1c299523db288004e3157ff4674e", size = 302202 },
-    { url = "https://files.pythonhosted.org/packages/3c/37/21972a15834d90bfbfb009b9d004779bd5a07a0ec0234e5ba8f64d5736f4/contourpy-1.3.3-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5ed3657edf08512fc3fe81b510e35c2012fbd3081d2e26160f27ca28affec989", size = 329207 },
-    { url = "https://files.pythonhosted.org/packages/0c/58/bd257695f39d05594ca4ad60df5bcb7e32247f9951fd09a9b8edb82d1daa/contourpy-1.3.3-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:3d1a3799d62d45c18bafd41c5fa05120b96a28079f2393af559b843d1a966a77", size = 225315 },
-]
-
 [[package]]
 name = "coverage"
 version = "7.9.2"
@@ -753,15 +682,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ec/4c/0ecd260233290bee4b2facec4d8e755e57d8781d68f276e1248433993c9f/ctranslate2-4.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:511cdf810a5bf6a2cec735799e5cd47966e63f8f7688fdee1b97fed621abda00", size = 19470040 },
 ]
 
-[[package]]
-name = "cycler"
-version = "0.12.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a9/95/a3dbbb5028f35eafb79008e7522a75244477d2838f38cbb722248dabc2a8/cycler-0.12.1.tar.gz", hash = "sha256:88bb128f02ba341da8ef447245a9e138fae777f6a23943da4540077d3601eb1c", size = 7615 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e7/05/c19819d5e3d95294a6f5947fb9b9629efb316b96de511b418c53d245aae6/cycler-0.12.1-py3-none-any.whl", hash = "sha256:85cef7cff222d8644161529808465972e51340599459b8ac3ccbac5a854e0d30", size = 8321 },
-]
-
 [[package]]
 name = "databases"
 version = "0.8.0"
@@ -874,12 +794,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e3/26/57c6fb270950d476074c087527a558ccb6f4436657314bfb6cdf484114c4/docker-7.1.0-py3-none-any.whl", hash = "sha256:c96b93b7f0a746f9e77d325bcfb87422a3d8bd4f03136ae8a85b37f1898d5fc0", size = 147774 },
 ]
 
-[[package]]
-name = "docopt"
-version = "0.6.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a2/55/8f8cab2afd404cf578136ef2cc5dfb50baa1761b68c9da1fb1e4eed343c9/docopt-0.6.2.tar.gz", hash = "sha256:49b3a825280bd66b3aa83585ef59c4a8c82f2c8a522dbe754a8bc8d08c85c491", size = 25901 }
-
 [[package]]
 name = "ecdsa"
 version = "0.19.1"
@@ -892,15 +806,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/cb/a3/460c57f094a4a165c84a1341c373b0a4f5ec6ac244b998d5021aade89b77/ecdsa-0.19.1-py2.py3-none-any.whl", hash = "sha256:30638e27cf77b7e15c4c4cc1973720149e1033827cfd00661ca5c8cc0cdb24c3", size = 150607 },
 ]
 
-[[package]]
-name = "einops"
-version = "0.8.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/e5/81/df4fbe24dff8ba3934af99044188e20a98ed441ad17a274539b74e82e126/einops-0.8.1.tar.gz", hash = "sha256:de5d960a7a761225532e0f1959e5315ebeafc0cd43394732f103ca44b9837e84", size = 54805 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/87/62/9773de14fe6c45c23649e98b83231fffd7b9892b6cf863251dc2afa73643/einops-0.8.1-py3-none-any.whl", hash = "sha256:919387eb55330f5757c6bea9165c5ff5cfe63a642682ea788a6d472576d81737", size = 64359 },
-]
-
 [[package]]
 name = "email-validator"
 version = "2.2.0"
@@ -1034,31 +939,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b8/25/155f9f080d5e4bc0082edfda032ea2bc2b8fab3f4d25d46c1e9dd22a1a89/flatbuffers-25.2.10-py2.py3-none-any.whl", hash = "sha256:ebba5f4d5ea615af3f7fd70fc310636fbb2bbd1f566ac0a23d98dd412de50051", size = 30953 },
 ]
 
-[[package]]
-name = "fonttools"
-version = "4.59.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/0d/a5/fba25f9fbdab96e26dedcaeeba125e5f05a09043bf888e0305326e55685b/fonttools-4.59.2.tar.gz", hash = "sha256:e72c0749b06113f50bcb80332364c6be83a9582d6e3db3fe0b280f996dc2ef22", size = 3540889 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f8/53/742fcd750ae0bdc74de4c0ff923111199cc2f90a4ee87aaddad505b6f477/fonttools-4.59.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:511946e8d7ea5c0d6c7a53c4cb3ee48eda9ab9797cd9bf5d95829a398400354f", size = 2774961 },
-    { url = "https://files.pythonhosted.org/packages/57/2a/976f5f9fa3b4dd911dc58d07358467bec20e813d933bc5d3db1a955dd456/fonttools-4.59.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8e5e2682cf7be766d84f462ba8828d01e00c8751a8e8e7ce12d7784ccb69a30d", size = 2344690 },
-    { url = "https://files.pythonhosted.org/packages/c1/8f/b7eefc274fcf370911e292e95565c8253b0b87c82a53919ab3c795a4f50e/fonttools-4.59.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5729e12a982dba3eeae650de48b06f3b9ddb51e9aee2fcaf195b7d09a96250e2", size = 5026910 },
-    { url = "https://files.pythonhosted.org/packages/69/95/864726eaa8f9d4e053d0c462e64d5830ec7c599cbdf1db9e40f25ca3972e/fonttools-4.59.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c52694eae5d652361d59ecdb5a2246bff7cff13b6367a12da8499e9df56d148d", size = 4971031 },
-    { url = "https://files.pythonhosted.org/packages/24/4c/b8c4735ebdea20696277c70c79e0de615dbe477834e5a7c2569aa1db4033/fonttools-4.59.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f1f1bbc23ba1312bd8959896f46f667753b90216852d2a8cfa2d07e0cb234144", size = 5006112 },
-    { url = "https://files.pythonhosted.org/packages/3b/23/f9ea29c292aa2fc1ea381b2e5621ac436d5e3e0a5dee24ffe5404e58eae8/fonttools-4.59.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1a1bfe5378962825dabe741720885e8b9ae9745ec7ecc4a5ec1f1ce59a6062bf", size = 5117671 },
-    { url = "https://files.pythonhosted.org/packages/ba/07/cfea304c555bf06e86071ff2a3916bc90f7c07ec85b23bab758d4908c33d/fonttools-4.59.2-cp311-cp311-win32.whl", hash = "sha256:e937790f3c2c18a1cbc7da101550a84319eb48023a715914477d2e7faeaba570", size = 2218157 },
-    { url = "https://files.pythonhosted.org/packages/d7/de/35d839aa69db737a3f9f3a45000ca24721834d40118652a5775d5eca8ebb/fonttools-4.59.2-cp311-cp311-win_amd64.whl", hash = "sha256:9836394e2f4ce5f9c0a7690ee93bd90aa1adc6b054f1a57b562c5d242c903104", size = 2265846 },
-    { url = "https://files.pythonhosted.org/packages/ba/3d/1f45db2df51e7bfa55492e8f23f383d372200be3a0ded4bf56a92753dd1f/fonttools-4.59.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:82906d002c349cad647a7634b004825a7335f8159d0d035ae89253b4abf6f3ea", size = 2769711 },
-    { url = "https://files.pythonhosted.org/packages/29/df/cd236ab32a8abfd11558f296e064424258db5edefd1279ffdbcfd4fd8b76/fonttools-4.59.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a10c1bd7644dc58f8862d8ba0cf9fb7fef0af01ea184ba6ce3f50ab7dfe74d5a", size = 2340225 },
-    { url = "https://files.pythonhosted.org/packages/98/12/b6f9f964fe6d4b4dd4406bcbd3328821c3de1f909ffc3ffa558fe72af48c/fonttools-4.59.2-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:738f31f23e0339785fd67652a94bc69ea49e413dfdb14dcb8c8ff383d249464e", size = 4912766 },
-    { url = "https://files.pythonhosted.org/packages/73/78/82bde2f2d2c306ef3909b927363170b83df96171f74e0ccb47ad344563cd/fonttools-4.59.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0ec99f9bdfee9cdb4a9172f9e8fd578cce5feb231f598909e0aecf5418da4f25", size = 4955178 },
-    { url = "https://files.pythonhosted.org/packages/92/77/7de766afe2d31dda8ee46d7e479f35c7d48747e558961489a2d6e3a02bd4/fonttools-4.59.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0476ea74161322e08c7a982f83558a2b81b491509984523a1a540baf8611cc31", size = 4897898 },
-    { url = "https://files.pythonhosted.org/packages/c5/77/ce0e0b905d62a06415fda9f2b2e109a24a5db54a59502b769e9e297d2242/fonttools-4.59.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:95922a922daa1f77cc72611747c156cfb38030ead72436a2c551d30ecef519b9", size = 5049144 },
-    { url = "https://files.pythonhosted.org/packages/d9/ea/870d93aefd23fff2e07cbeebdc332527868422a433c64062c09d4d5e7fe6/fonttools-4.59.2-cp312-cp312-win32.whl", hash = "sha256:39ad9612c6a622726a6a130e8ab15794558591f999673f1ee7d2f3d30f6a3e1c", size = 2206473 },
-    { url = "https://files.pythonhosted.org/packages/61/c4/e44bad000c4a4bb2e9ca11491d266e857df98ab6d7428441b173f0fe2517/fonttools-4.59.2-cp312-cp312-win_amd64.whl", hash = "sha256:980fd7388e461b19a881d35013fec32c713ffea1fc37aef2f77d11f332dfd7da", size = 2254706 },
-    { url = "https://files.pythonhosted.org/packages/65/a4/d2f7be3c86708912c02571db0b550121caab8cd88a3c0aacb9cfa15ea66e/fonttools-4.59.2-py3-none-any.whl", hash = "sha256:8bd0f759020e87bb5d323e6283914d9bf4ae35a7307dafb2cbd1e379e720ad37", size = 1132315 },
-]
-
 [[package]]
 name = "frozenlist"
 version = "1.7.0"
@@ -1111,11 +991,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2f/e0/014d5d9d7a4564cf1c40b5039bc882db69fd881111e03ab3657ac0b218e2/fsspec-2025.7.0-py3-none-any.whl", hash = "sha256:8b012e39f63c7d5f10474de957f3ab793b47b45ae7d39f2fb735f8bbe25c0e21", size = 199597 },
 ]
 
-[package.optional-dependencies]
-http = [
-    { name = "aiohttp" },
-]
-
 [[package]]
 name = "google-crc32c"
 version = "1.7.1"
@@ -1380,19 +1255,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f0/0f/310fb31e39e2d734ccaa2c0fb981ee41f7bd5056ce9bc29b2248bd569169/humanfriendly-10.0-py2.py3-none-any.whl", hash = "sha256:1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477", size = 86794 },
 ]
 
-[[package]]
-name = "hyperpyyaml"
-version = "1.2.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "pyyaml" },
-    { name = "ruamel-yaml" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/52/e3/3ac46d9a662b037f699a6948b39c8d03bfcff0b592335d5953ba0c55d453/HyperPyYAML-1.2.2.tar.gz", hash = "sha256:bdb734210d18770a262f500fe5755c7a44a5d3b91521b06e24f7a00a36ee0f87", size = 17085 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/33/c9/751b6401887f4b50f9307cc1e53d287b3dc77c375c126aeb6335aff73ccb/HyperPyYAML-1.2.2-py3-none-any.whl", hash = "sha256:3c5864bdc8864b2f0fbd7bc495e7e8fdf2dfd5dd80116f72da27ca96a128bdeb", size = 16118 },
-]
-
 [[package]]
 name = "icalendar"
 version = "6.3.1"
@@ -1535,55 +1397,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/01/0e/b27cdbaccf30b890c40ed1da9fd4a3593a5cf94dae54fb34f8a4b74fcd3f/jsonschema_specifications-2025.4.1-py3-none-any.whl", hash = "sha256:4653bffbd6584f7de83a67e0d620ef16900b390ddc7939d56684d6c81e33f1af", size = 18437 },
 ]
 
-[[package]]
-name = "julius"
-version = "0.2.7"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/a1/19/c9e1596b5572c786b93428d0904280e964c930fae7e6c9368ed9e1b63922/julius-0.2.7.tar.gz", hash = "sha256:3c0f5f5306d7d6016fcc95196b274cae6f07e2c9596eed314e4e7641554fbb08", size = 59640 }
-
-[[package]]
-name = "kiwisolver"
-version = "1.4.9"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/5c/3c/85844f1b0feb11ee581ac23fe5fce65cd049a200c1446708cc1b7f922875/kiwisolver-1.4.9.tar.gz", hash = "sha256:c3b22c26c6fd6811b0ae8363b95ca8ce4ea3c202d3d0975b2914310ceb1bcc4d", size = 97564 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/6f/ab/c80b0d5a9d8a1a65f4f815f2afff9798b12c3b9f31f1d304dd233dd920e2/kiwisolver-1.4.9-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb14a5da6dc7642b0f3a18f13654847cd8b7a2550e2645a5bda677862b03ba16", size = 124167 },
-    { url = "https://files.pythonhosted.org/packages/a0/c0/27fe1a68a39cf62472a300e2879ffc13c0538546c359b86f149cc19f6ac3/kiwisolver-1.4.9-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:39a219e1c81ae3b103643d2aedb90f1ef22650deb266ff12a19e7773f3e5f089", size = 66579 },
-    { url = "https://files.pythonhosted.org/packages/31/a2/a12a503ac1fd4943c50f9822678e8015a790a13b5490354c68afb8489814/kiwisolver-1.4.9-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2405a7d98604b87f3fc28b1716783534b1b4b8510d8142adca34ee0bc3c87543", size = 65309 },
-    { url = "https://files.pythonhosted.org/packages/66/e1/e533435c0be77c3f64040d68d7a657771194a63c279f55573188161e81ca/kiwisolver-1.4.9-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:dc1ae486f9abcef254b5618dfb4113dd49f94c68e3e027d03cf0143f3f772b61", size = 1435596 },
-    { url = "https://files.pythonhosted.org/packages/67/1e/51b73c7347f9aabdc7215aa79e8b15299097dc2f8e67dee2b095faca9cb0/kiwisolver-1.4.9-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8a1f570ce4d62d718dce3f179ee78dac3b545ac16c0c04bb363b7607a949c0d1", size = 1246548 },
-    { url = "https://files.pythonhosted.org/packages/21/aa/72a1c5d1e430294f2d32adb9542719cfb441b5da368d09d268c7757af46c/kiwisolver-1.4.9-cp311-cp311-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:cb27e7b78d716c591e88e0a09a2139c6577865d7f2e152488c2cc6257f460872", size = 1263618 },
-    { url = "https://files.pythonhosted.org/packages/a3/af/db1509a9e79dbf4c260ce0cfa3903ea8945f6240e9e59d1e4deb731b1a40/kiwisolver-1.4.9-cp311-cp311-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:15163165efc2f627eb9687ea5f3a28137217d217ac4024893d753f46bce9de26", size = 1317437 },
-    { url = "https://files.pythonhosted.org/packages/e0/f2/3ea5ee5d52abacdd12013a94130436e19969fa183faa1e7c7fbc89e9a42f/kiwisolver-1.4.9-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:bdee92c56a71d2b24c33a7d4c2856bd6419d017e08caa7802d2963870e315028", size = 2195742 },
-    { url = "https://files.pythonhosted.org/packages/6f/9b/1efdd3013c2d9a2566aa6a337e9923a00590c516add9a1e89a768a3eb2fc/kiwisolver-1.4.9-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:412f287c55a6f54b0650bd9b6dce5aceddb95864a1a90c87af16979d37c89771", size = 2290810 },
-    { url = "https://files.pythonhosted.org/packages/fb/e5/cfdc36109ae4e67361f9bc5b41323648cb24a01b9ade18784657e022e65f/kiwisolver-1.4.9-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:2c93f00dcba2eea70af2be5f11a830a742fe6b579a1d4e00f47760ef13be247a", size = 2461579 },
-    { url = "https://files.pythonhosted.org/packages/62/86/b589e5e86c7610842213994cdea5add00960076bef4ae290c5fa68589cac/kiwisolver-1.4.9-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f117e1a089d9411663a3207ba874f31be9ac8eaa5b533787024dc07aeb74f464", size = 2268071 },
-    { url = "https://files.pythonhosted.org/packages/3b/c6/f8df8509fd1eee6c622febe54384a96cfaf4d43bf2ccec7a0cc17e4715c9/kiwisolver-1.4.9-cp311-cp311-win_amd64.whl", hash = "sha256:be6a04e6c79819c9a8c2373317d19a96048e5a3f90bec587787e86a1153883c2", size = 73840 },
-    { url = "https://files.pythonhosted.org/packages/e2/2d/16e0581daafd147bc11ac53f032a2b45eabac897f42a338d0a13c1e5c436/kiwisolver-1.4.9-cp311-cp311-win_arm64.whl", hash = "sha256:0ae37737256ba2de764ddc12aed4956460277f00c4996d51a197e72f62f5eec7", size = 65159 },
-    { url = "https://files.pythonhosted.org/packages/86/c9/13573a747838aeb1c76e3267620daa054f4152444d1f3d1a2324b78255b5/kiwisolver-1.4.9-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:ac5a486ac389dddcc5bef4f365b6ae3ffff2c433324fb38dd35e3fab7c957999", size = 123686 },
-    { url = "https://files.pythonhosted.org/packages/51/ea/2ecf727927f103ffd1739271ca19c424d0e65ea473fbaeea1c014aea93f6/kiwisolver-1.4.9-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f2ba92255faa7309d06fe44c3a4a97efe1c8d640c2a79a5ef728b685762a6fd2", size = 66460 },
-    { url = "https://files.pythonhosted.org/packages/5b/5a/51f5464373ce2aeb5194508298a508b6f21d3867f499556263c64c621914/kiwisolver-1.4.9-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4a2899935e724dd1074cb568ce7ac0dce28b2cd6ab539c8e001a8578eb106d14", size = 64952 },
-    { url = "https://files.pythonhosted.org/packages/70/90/6d240beb0f24b74371762873e9b7f499f1e02166a2d9c5801f4dbf8fa12e/kiwisolver-1.4.9-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f6008a4919fdbc0b0097089f67a1eb55d950ed7e90ce2cc3e640abadd2757a04", size = 1474756 },
-    { url = "https://files.pythonhosted.org/packages/12/42/f36816eaf465220f683fb711efdd1bbf7a7005a2473d0e4ed421389bd26c/kiwisolver-1.4.9-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:67bb8b474b4181770f926f7b7d2f8c0248cbcb78b660fdd41a47054b28d2a752", size = 1276404 },
-    { url = "https://files.pythonhosted.org/packages/2e/64/bc2de94800adc830c476dce44e9b40fd0809cddeef1fde9fcf0f73da301f/kiwisolver-1.4.9-cp312-cp312-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:2327a4a30d3ee07d2fbe2e7933e8a37c591663b96ce42a00bc67461a87d7df77", size = 1294410 },
-    { url = "https://files.pythonhosted.org/packages/5f/42/2dc82330a70aa8e55b6d395b11018045e58d0bb00834502bf11509f79091/kiwisolver-1.4.9-cp312-cp312-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:7a08b491ec91b1d5053ac177afe5290adacf1f0f6307d771ccac5de30592d198", size = 1343631 },
-    { url = "https://files.pythonhosted.org/packages/22/fd/f4c67a6ed1aab149ec5a8a401c323cee7a1cbe364381bb6c9c0d564e0e20/kiwisolver-1.4.9-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d8fc5c867c22b828001b6a38d2eaeb88160bf5783c6cb4a5e440efc981ce286d", size = 2224963 },
-    { url = "https://files.pythonhosted.org/packages/45/aa/76720bd4cb3713314677d9ec94dcc21ced3f1baf4830adde5bb9b2430a5f/kiwisolver-1.4.9-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:3b3115b2581ea35bb6d1f24a4c90af37e5d9b49dcff267eeed14c3893c5b86ab", size = 2321295 },
-    { url = "https://files.pythonhosted.org/packages/80/19/d3ec0d9ab711242f56ae0dc2fc5d70e298bb4a1f9dfab44c027668c673a1/kiwisolver-1.4.9-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:858e4c22fb075920b96a291928cb7dea5644e94c0ee4fcd5af7e865655e4ccf2", size = 2487987 },
-    { url = "https://files.pythonhosted.org/packages/39/e9/61e4813b2c97e86b6fdbd4dd824bf72d28bcd8d4849b8084a357bc0dd64d/kiwisolver-1.4.9-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:ed0fecd28cc62c54b262e3736f8bb2512d8dcfdc2bcf08be5f47f96bf405b145", size = 2291817 },
-    { url = "https://files.pythonhosted.org/packages/a0/41/85d82b0291db7504da3c2defe35c9a8a5c9803a730f297bd823d11d5fb77/kiwisolver-1.4.9-cp312-cp312-win_amd64.whl", hash = "sha256:f68208a520c3d86ea51acf688a3e3002615a7f0238002cccc17affecc86a8a54", size = 73895 },
-    { url = "https://files.pythonhosted.org/packages/e2/92/5f3068cf15ee5cb624a0c7596e67e2a0bb2adee33f71c379054a491d07da/kiwisolver-1.4.9-cp312-cp312-win_arm64.whl", hash = "sha256:2c1a4f57df73965f3f14df20b80ee29e6a7930a57d2d9e8491a25f676e197c60", size = 64992 },
-    { url = "https://files.pythonhosted.org/packages/a3/0f/36d89194b5a32c054ce93e586d4049b6c2c22887b0eb229c61c68afd3078/kiwisolver-1.4.9-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:720e05574713db64c356e86732c0f3c5252818d05f9df320f0ad8380641acea5", size = 60104 },
-    { url = "https://files.pythonhosted.org/packages/52/ba/4ed75f59e4658fd21fe7dde1fee0ac397c678ec3befba3fe6482d987af87/kiwisolver-1.4.9-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:17680d737d5335b552994a2008fab4c851bcd7de33094a82067ef3a576ff02fa", size = 58592 },
-    { url = "https://files.pythonhosted.org/packages/33/01/a8ea7c5ea32a9b45ceeaee051a04c8ed4320f5add3c51bfa20879b765b70/kiwisolver-1.4.9-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:85b5352f94e490c028926ea567fc569c52ec79ce131dadb968d3853e809518c2", size = 80281 },
-    { url = "https://files.pythonhosted.org/packages/da/e3/dbd2ecdce306f1d07a1aaf324817ee993aab7aee9db47ceac757deabafbe/kiwisolver-1.4.9-pp311-pypy311_pp73-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:464415881e4801295659462c49461a24fb107c140de781d55518c4b80cb6790f", size = 78009 },
-    { url = "https://files.pythonhosted.org/packages/da/e9/0d4add7873a73e462aeb45c036a2dead2562b825aa46ba326727b3f31016/kiwisolver-1.4.9-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:fb940820c63a9590d31d88b815e7a3aa5915cad3ce735ab45f0c730b39547de1", size = 73929 },
-]
-
 [[package]]
 name = "kombu"
 version = "5.5.4"
@@ -1646,41 +1459,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/dc/1e/408fd10217eac0e43aea0604be22b4851a09e03d761d44d4ea12089dd70e/levenshtein-0.27.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:7987ef006a3cf56a4532bd4c90c2d3b7b4ca9ad3bf8ae1ee5713c4a3bdfda913", size = 98045 },
 ]
 
-[[package]]
-name = "lightning"
-version = "2.5.5"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "fsspec", extra = ["http"] },
-    { name = "lightning-utilities" },
-    { name = "packaging" },
-    { name = "pytorch-lightning" },
-    { name = "pyyaml" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torchmetrics" },
-    { name = "tqdm" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/0f/dd/86bb3bebadcdbc6e6e5a63657f0a03f74cd065b5ea965896679f76fec0b4/lightning-2.5.5.tar.gz", hash = "sha256:4d3d66c5b1481364a7e6a1ce8ddde1777a04fa740a3145ec218a9941aed7dd30", size = 640770 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/2e/d0/4b4fbafc3b18df91207a6e46782d9fd1905f9f45cb2c3b8dfbb239aef781/lightning-2.5.5-py3-none-any.whl", hash = "sha256:69eb248beadd7b600bf48eff00a0ec8af171ec7a678d23787c4aedf12e225e8f", size = 828490 },
-]
-
-[[package]]
-name = "lightning-utilities"
-version = "0.15.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "packaging" },
-    { name = "setuptools" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/b8/39/6fc58ca81492db047149b4b8fd385aa1bfb8c28cd7cacb0c7eb0c44d842f/lightning_utilities-0.15.2.tar.gz", hash = "sha256:cdf12f530214a63dacefd713f180d1ecf5d165338101617b4742e8f22c032e24", size = 31090 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/de/73/3d757cb3fc16f0f9794dd289bcd0c4a031d9cf54d8137d6b984b2d02edf3/lightning_utilities-0.15.2-py3-none-any.whl", hash = "sha256:ad3ab1703775044bbf880dbf7ddaaac899396c96315f3aa1779cec9d618a9841", size = 29431 },
-]
-
 [[package]]
 name = "llama-cloud"
 version = "0.1.32"
@@ -2028,42 +1806,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/34/75/51952c7b2d3873b44a0028b1bd26a25078c18f92f256608e8d1dc61b39fd/marshmallow-3.26.1-py3-none-any.whl", hash = "sha256:3350409f20a70a7e4e11a27661187b77cdcaeb20abca41c1454fe33636bea09c", size = 50878 },
 ]
 
-[[package]]
-name = "matplotlib"
-version = "3.10.6"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "contourpy" },
-    { name = "cycler" },
-    { name = "fonttools" },
-    { name = "kiwisolver" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "pillow" },
-    { name = "pyparsing" },
-    { name = "python-dateutil" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/a0/59/c3e6453a9676ffba145309a73c462bb407f4400de7de3f2b41af70720a3c/matplotlib-3.10.6.tar.gz", hash = "sha256:ec01b645840dd1996df21ee37f208cd8ba57644779fa20464010638013d3203c", size = 34804264 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/80/d6/5d3665aa44c49005aaacaa68ddea6fcb27345961cd538a98bb0177934ede/matplotlib-3.10.6-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:905b60d1cb0ee604ce65b297b61cf8be9f4e6cfecf95a3fe1c388b5266bc8f4f", size = 8257527 },
-    { url = "https://files.pythonhosted.org/packages/8c/af/30ddefe19ca67eebd70047dabf50f899eaff6f3c5e6a1a7edaecaf63f794/matplotlib-3.10.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7bac38d816637343e53d7185d0c66677ff30ffb131044a81898b5792c956ba76", size = 8119583 },
-    { url = "https://files.pythonhosted.org/packages/d3/29/4a8650a3dcae97fa4f375d46efcb25920d67b512186f8a6788b896062a81/matplotlib-3.10.6-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:942a8de2b5bfff1de31d95722f702e2966b8a7e31f4e68f7cd963c7cd8861cf6", size = 8692682 },
-    { url = "https://files.pythonhosted.org/packages/aa/d3/b793b9cb061cfd5d42ff0f69d1822f8d5dbc94e004618e48a97a8373179a/matplotlib-3.10.6-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a3276c85370bc0dfca051ec65c5817d1e0f8f5ce1b7787528ec8ed2d524bbc2f", size = 9521065 },
-    { url = "https://files.pythonhosted.org/packages/f7/c5/53de5629f223c1c66668d46ac2621961970d21916a4bc3862b174eb2a88f/matplotlib-3.10.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:9df5851b219225731f564e4b9e7f2ac1e13c9e6481f941b5631a0f8e2d9387ce", size = 9576888 },
-    { url = "https://files.pythonhosted.org/packages/fc/8e/0a18d6d7d2d0a2e66585032a760d13662e5250c784d53ad50434e9560991/matplotlib-3.10.6-cp311-cp311-win_amd64.whl", hash = "sha256:abb5d9478625dd9c9eb51a06d39aae71eda749ae9b3138afb23eb38824026c7e", size = 8115158 },
-    { url = "https://files.pythonhosted.org/packages/07/b3/1a5107bb66c261e23b9338070702597a2d374e5aa7004b7adfc754fbed02/matplotlib-3.10.6-cp311-cp311-win_arm64.whl", hash = "sha256:886f989ccfae63659183173bb3fced7fd65e9eb793c3cc21c273add368536951", size = 7992444 },
-    { url = "https://files.pythonhosted.org/packages/ea/1a/7042f7430055d567cc3257ac409fcf608599ab27459457f13772c2d9778b/matplotlib-3.10.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:31ca662df6a80bd426f871105fdd69db7543e28e73a9f2afe80de7e531eb2347", size = 8272404 },
-    { url = "https://files.pythonhosted.org/packages/a9/5d/1d5f33f5b43f4f9e69e6a5fe1fb9090936ae7bc8e2ff6158e7a76542633b/matplotlib-3.10.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1678bb61d897bb4ac4757b5ecfb02bfb3fddf7f808000fb81e09c510712fda75", size = 8128262 },
-    { url = "https://files.pythonhosted.org/packages/67/c3/135fdbbbf84e0979712df58e5e22b4f257b3f5e52a3c4aacf1b8abec0d09/matplotlib-3.10.6-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:56cd2d20842f58c03d2d6e6c1f1cf5548ad6f66b91e1e48f814e4fb5abd1cb95", size = 8697008 },
-    { url = "https://files.pythonhosted.org/packages/9c/be/c443ea428fb2488a3ea7608714b1bd85a82738c45da21b447dc49e2f8e5d/matplotlib-3.10.6-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:662df55604a2f9a45435566d6e2660e41efe83cd94f4288dfbf1e6d1eae4b0bb", size = 9530166 },
-    { url = "https://files.pythonhosted.org/packages/a9/35/48441422b044d74034aea2a3e0d1a49023f12150ebc58f16600132b9bbaf/matplotlib-3.10.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:08f141d55148cd1fc870c3387d70ca4df16dee10e909b3b038782bd4bda6ea07", size = 9593105 },
-    { url = "https://files.pythonhosted.org/packages/45/c3/994ef20eb4154ab84cc08d033834555319e4af970165e6c8894050af0b3c/matplotlib-3.10.6-cp312-cp312-win_amd64.whl", hash = "sha256:590f5925c2d650b5c9d813c5b3b5fc53f2929c3f8ef463e4ecfa7e052044fb2b", size = 8122784 },
-    { url = "https://files.pythonhosted.org/packages/57/b8/5c85d9ae0e40f04e71bedb053aada5d6bab1f9b5399a0937afb5d6b02d98/matplotlib-3.10.6-cp312-cp312-win_arm64.whl", hash = "sha256:f44c8d264a71609c79a78d50349e724f5d5fc3684ead7c2a473665ee63d868aa", size = 7992823 },
-    { url = "https://files.pythonhosted.org/packages/12/bb/02c35a51484aae5f49bd29f091286e7af5f3f677a9736c58a92b3c78baeb/matplotlib-3.10.6-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:f2d684c3204fa62421bbf770ddfebc6b50130f9cad65531eeba19236d73bb488", size = 8252296 },
-    { url = "https://files.pythonhosted.org/packages/7d/85/41701e3092005aee9a2445f5ee3904d9dbd4a7df7a45905ffef29b7ef098/matplotlib-3.10.6-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:6f4a69196e663a41d12a728fab8751177215357906436804217d6d9cf0d4d6cf", size = 8116749 },
-    { url = "https://files.pythonhosted.org/packages/16/53/8d8fa0ea32a8c8239e04d022f6c059ee5e1b77517769feccd50f1df43d6d/matplotlib-3.10.6-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4d6ca6ef03dfd269f4ead566ec6f3fb9becf8dab146fb999022ed85ee9f6b3eb", size = 8693933 },
-]
-
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -2205,19 +1947,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/48/6b/1c6b515a83d5564b1698a61efa245727c8feecf308f4091f565988519d20/numpy-2.3.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:e610832418a2bc09d974cc9fecebfa51e9532d6190223bc5ef6a7402ebf3b5cb", size = 12927246 },
 ]
 
-[[package]]
-name = "omegaconf"
-version = "2.3.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "antlr4-python3-runtime" },
-    { name = "pyyaml" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/09/48/6388f1bb9da707110532cb70ec4d2822858ddfb44f1cdf1233c20a80ea4b/omegaconf-2.3.0.tar.gz", hash = "sha256:d5d4b6d29955cc50ad50c46dc269bcd92c6e00f5f90d23ab5fee7bfca4ba4cc7", size = 3298120 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e3/94/1843518e420fa3ed6919835845df698c7e27e183cb997394e4a670973a65/omegaconf-2.3.0-py3-none-any.whl", hash = "sha256:7b4df175cdb08ba400f45cae3bdcae7ba8365db4d165fc65fd04b050ab63b46b", size = 79500 },
-]
-
 [[package]]
 name = "onnxruntime"
 version = "1.22.1"
@@ -2260,24 +1989,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8a/91/1f1cf577f745e956b276a8b1d3d76fa7a6ee0c2b05db3b001b900f2c71db/openai-1.97.0-py3-none-any.whl", hash = "sha256:a1c24d96f4609f3f7f51c9e1c2606d97cc6e334833438659cfd687e9c972c610", size = 764953 },
 ]
 
-[[package]]
-name = "optuna"
-version = "4.5.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "alembic" },
-    { name = "colorlog" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "pyyaml" },
-    { name = "sqlalchemy" },
-    { name = "tqdm" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/53/a3/bcd1e5500de6ec794c085a277e5b624e60b4fac1790681d7cdbde25b93a2/optuna-4.5.0.tar.gz", hash = "sha256:264844da16dad744dea295057d8bc218646129c47567d52c35a201d9f99942ba", size = 472338 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/7f/12/cba81286cbaf0f0c3f0473846cfd992cb240bdcea816bf2ef7de8ed0f744/optuna-4.5.0-py3-none-any.whl", hash = "sha256:5b8a783e84e448b0742501bc27195344a28d2c77bd2feef5b558544d954851b0", size = 400872 },
-]
-
 [[package]]
 name = "packaging"
 version = "25.0"
@@ -2379,15 +2090,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538 },
 ]
 
-[[package]]
-name = "primepy"
-version = "1.3"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/35/77/0cfa1b4697cfb5336f3a96e8bc73327f64610be3a64c97275f1801afb395/primePy-1.3.tar.gz", hash = "sha256:25fd7e25344b0789a5984c75d89f054fcf1f180bef20c998e4befbac92de4669", size = 3914 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/74/c1/bb7e334135859c3a92ec399bc89293ea73f28e815e35b43929c8db6af030/primePy-1.3-py3-none-any.whl", hash = "sha256:5ed443718765be9bf7e2ff4c56cdff71b42140a15b39d054f9d99f0009e2317a", size = 4040 },
-]
-
 [[package]]
 name = "prometheus-client"
 version = "0.22.1"
@@ -2524,109 +2226,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/92/29/06261ea000e2dc1e22907dbbc483a1093665509ea586b29b8986a0e56733/psycopg2_binary-2.9.10-cp312-cp312-win_amd64.whl", hash = "sha256:18c5ee682b9c6dd3696dad6e54cc7ff3a1a9020df6a5c0f861ef8bfd338c3ca0", size = 1164031 },
 ]
 
-[[package]]
-name = "pyannote-audio"
-version = "3.3.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "asteroid-filterbanks" },
-    { name = "einops" },
-    { name = "huggingface-hub" },
-    { name = "lightning" },
-    { name = "omegaconf" },
-    { name = "pyannote-core" },
-    { name = "pyannote-database" },
-    { name = "pyannote-metrics" },
-    { name = "pyannote-pipeline" },
-    { name = "pytorch-metric-learning" },
-    { name = "rich" },
-    { name = "semver" },
-    { name = "soundfile" },
-    { name = "speechbrain" },
-    { name = "tensorboardx" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torch-audiomentations" },
-    { name = "torchaudio", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or sys_platform == 'darwin'" },
-    { name = "torchaudio", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "torchmetrics" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/e9/00/3b96ca7ad0641e4f64cfaa2af153dc7da0998ff972280e1c1681b1fcc243/pyannote_audio-3.3.2.tar.gz", hash = "sha256:b2115e86b0db5faedb9f36ee1a150cebd07f7758e65e815accdac1a12ca9c777", size = 13664309 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/17/e6/76049470d90217f9a15a34abf3e92d782cabc3fb4ab27515c9baaa5495d1/pyannote.audio-3.3.2-py2.py3-none-any.whl", hash = "sha256:599c694acd5d193215147ff82d0bf638bb191204ed502bd9fde8ff582e20aa1c", size = 898707 },
-    { url = "https://files.pythonhosted.org/packages/b7/9a/98a8992727e762b031ed30451d5726ece46cf8bb7b872a9dba5cef011e5d/pyannote_audio-3.3.2-py2.py3-none-any.whl", hash = "sha256:23e0dcedda920cb2e154e146bcd9663289ee7942d0e012663dad76f2e571ebeb", size = 897827 },
-]
-
-[[package]]
-name = "pyannote-core"
-version = "5.0.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-    { name = "scipy" },
-    { name = "sortedcontainers" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/65/03/feaf7534206f02c75baf151ce4b8c322b402a6f477c2be82f69d9269cbe6/pyannote.core-5.0.0.tar.gz", hash = "sha256:1a55bcc8bd680ba6be5fa53efa3b6f3d2cdd67144c07b6b4d8d66d5cb0d2096f", size = 59247 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/84/c4/370bc8ba66815a5832ece753a1009388bb07ea353d21c83f2d5a1a436f2c/pyannote.core-5.0.0-py3-none-any.whl", hash = "sha256:04920a6754492242ce0dc6017545595ab643870fe69a994f20c1a5f2da0544d0", size = 58475 },
-]
-
-[[package]]
-name = "pyannote-database"
-version = "5.1.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "pandas" },
-    { name = "pyannote-core" },
-    { name = "pyyaml" },
-    { name = "typer" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/a9/ae/de36413d69a46be87cb612ebbcdc4eacbeebce3bc809124603e44a88fe26/pyannote.database-5.1.3.tar.gz", hash = "sha256:0eaf64c1cc506718de60d2d702f1359b1ae7ff252ee3e4799f1c5e378cd52c31", size = 49957 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/64/92d51a3a05615ba58be8ba62a43f9f9f952d9f3646f7e4fb7826e5a3a24e/pyannote.database-5.1.3-py3-none-any.whl", hash = "sha256:37887844c7dfbcc075cb591eddc00aff45fae1ed905344e1f43e0090e63bd40a", size = 48127 },
-]
-
-[[package]]
-name = "pyannote-metrics"
-version = "3.2.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "docopt" },
-    { name = "matplotlib" },
-    { name = "numpy" },
-    { name = "pandas" },
-    { name = "pyannote-core" },
-    { name = "pyannote-database" },
-    { name = "scikit-learn" },
-    { name = "scipy" },
-    { name = "sympy" },
-    { name = "tabulate" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/39/2b/6c5f01d3c49aa1c160765946e23782ca6436ae8b9bc514b56319ff5f16e7/pyannote.metrics-3.2.1.tar.gz", hash = "sha256:08024255a3550e96a8e9da4f5f4af326886548480de891414567c8900920ee5c", size = 49086 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/6c/7d/035b370ab834b30e849fe9cd092b7bd7f321fcc4a2c56b84e96476b7ede5/pyannote.metrics-3.2.1-py3-none-any.whl", hash = "sha256:46be797cdade26c82773e5018659ae610145260069c7c5bf3d3c8a029ade8e22", size = 51386 },
-]
-
-[[package]]
-name = "pyannote-pipeline"
-version = "3.0.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "docopt" },
-    { name = "filelock" },
-    { name = "optuna" },
-    { name = "pyannote-core" },
-    { name = "pyannote-database" },
-    { name = "pyyaml" },
-    { name = "scikit-learn" },
-    { name = "tqdm" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/35/04/4bcfe0dd588577a188328b806f3a7213d8cead0ce5fe5784d01fd57df93f/pyannote.pipeline-3.0.1.tar.gz", hash = "sha256:021794e26a2cf5d8fb5bb1835951e71f5fac33eb14e23dfb7468e16b1b805151", size = 34486 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/83/42/1bf7cbf061ed05c580bfb63bffdd3f3474cbd5c02bee4fac518eea9e9d9e/pyannote.pipeline-3.0.1-py3-none-any.whl", hash = "sha256:819bde4c4dd514f740f2373dfec794832b9fc8e346a35e43a7681625ee187393", size = 31517 },
-]
-
 [[package]]
 name = "pyasn1"
 version = "0.6.1"
@@ -2806,15 +2405,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/80/28/2659c02301b9500751f8d42f9a6632e1508aa5120de5e43042b8b30f8d5d/pyopenssl-25.1.0-py3-none-any.whl", hash = "sha256:2b11f239acc47ac2e5aca04fd7fa829800aeee22a2eb30d744572a157bd8a1ab", size = 56771 },
 ]
 
-[[package]]
-name = "pyparsing"
-version = "3.2.3"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/bb/22/f1129e69d94ffff626bdb5c835506b3a5b4f3d070f17ea295e12c2c6f60f/pyparsing-3.2.3.tar.gz", hash = "sha256:b9c13f1ab8b3b542f72e28f634bad4de758ab3ce4546e4301970ad6fa77c38be", size = 1088608 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/05/e7/df2285f3d08fee213f2d041540fa4fc9ca6c2d44cf36d3a035bf2a8d2bcc/pyparsing-3.2.3-py3-none-any.whl", hash = "sha256:a749938e02d6fd0b59b356ca504a24982314bb090c383e3cf201c95ef7e2bfcf", size = 111120 },
-]
-
 [[package]]
 name = "pypdf"
 version = "5.8.0"
@@ -3022,42 +2612,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104", size = 24546 },
 ]
 
-[[package]]
-name = "pytorch-lightning"
-version = "2.5.5"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "fsspec", extra = ["http"] },
-    { name = "lightning-utilities" },
-    { name = "packaging" },
-    { name = "pyyaml" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torchmetrics" },
-    { name = "tqdm" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/16/78/bce84aab9a5b3b2e9d087d4f1a6be9b481adbfaac4903bc9daaaf09d49a3/pytorch_lightning-2.5.5.tar.gz", hash = "sha256:d6fc8173d1d6e49abfd16855ea05d2eb2415e68593f33d43e59028ecb4e64087", size = 643703 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/04/f6/99a5c66478f469598dee25b0e29b302b5bddd4e03ed0da79608ac964056e/pytorch_lightning-2.5.5-py3-none-any.whl", hash = "sha256:0b533991df2353c0c6ea9ca10a7d0728b73631fd61f5a15511b19bee2aef8af0", size = 832431 },
-]
-
-[[package]]
-name = "pytorch-metric-learning"
-version = "2.9.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-    { name = "scikit-learn" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "tqdm" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/9b/80/6e61b1a91debf4c1b47d441f9a9d7fe2aabcdd9575ed70b2811474eb95c3/pytorch-metric-learning-2.9.0.tar.gz", hash = "sha256:27a626caf5e2876a0fd666605a78cb67ef7597e25d7a68c18053dd503830701f", size = 84530 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/46/7d/73ef5052f57b7720cad00e16598db3592a5ef4826745ffca67a2f085d4dc/pytorch_metric_learning-2.9.0-py3-none-any.whl", hash = "sha256:d51646006dc87168f00cf954785db133a4c5aac81253877248737aa42ef6432a", size = 127801 },
-]
-
 [[package]]
 name = "pytz"
 version = "2025.2"
@@ -3234,7 +2788,6 @@ evaluation = [
 ]
 local = [
     { name = "faster-whisper" },
-    { name = "pyannote-audio" },
 ]
 silero-vad = [
     { name = "silero-vad" },
@@ -3307,10 +2860,7 @@ evaluation = [
     { name = "pydantic", specifier = ">=2.1.1" },
     { name = "tqdm", specifier = ">=4.66.0" },
 ]
-local = [
-    { name = "faster-whisper", specifier = ">=0.10.0" },
-    { name = "pyannote-audio", specifier = ">=3.3.2" },
-]
+local = [{ name = "faster-whisper", specifier = ">=0.10.0" }]
 silero-vad = [
     { name = "silero-vad", specifier = ">=5.1.2" },
     { name = "torch", specifier = ">=2.8.0", index = "https://download.pytorch.org/whl/cpu" },
@@ -3514,44 +3064,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/64/8d/0133e4eb4beed9e425d9a98ed6e081a55d195481b7632472be1af08d2f6b/rsa-4.9.1-py3-none-any.whl", hash = "sha256:68635866661c6836b8d39430f97a996acbd61bfa49406748ea243539fe239762", size = 34696 },
 ]
 
-[[package]]
-name = "ruamel-yaml"
-version = "0.18.15"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "ruamel-yaml-clib", marker = "platform_python_implementation == 'CPython'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/3e/db/f3950f5e5031b618aae9f423a39bf81a55c148aecd15a34527898e752cf4/ruamel.yaml-0.18.15.tar.gz", hash = "sha256:dbfca74b018c4c3fba0b9cc9ee33e53c371194a9000e694995e620490fd40700", size = 146865 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d1/e5/f2a0621f1781b76a38194acae72f01e37b1941470407345b6e8653ad7640/ruamel.yaml-0.18.15-py3-none-any.whl", hash = "sha256:148f6488d698b7a5eded5ea793a025308b25eca97208181b6a026037f391f701", size = 119702 },
-]
-
-[[package]]
-name = "ruamel-yaml-clib"
-version = "0.2.12"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/20/84/80203abff8ea4993a87d823a5f632e4d92831ef75d404c9fc78d0176d2b5/ruamel.yaml.clib-0.2.12.tar.gz", hash = "sha256:6c8fbb13ec503f99a91901ab46e0b07ae7941cd527393187039aec586fdfd36f", size = 225315 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/fb/8f/683c6ad562f558cbc4f7c029abcd9599148c51c54b5ef0f24f2638da9fbb/ruamel.yaml.clib-0.2.12-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:4a6679521a58256a90b0d89e03992c15144c5f3858f40d7c18886023d7943db6", size = 132224 },
-    { url = "https://files.pythonhosted.org/packages/3c/d2/b79b7d695e2f21da020bd44c782490578f300dd44f0a4c57a92575758a76/ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:d84318609196d6bd6da0edfa25cedfbabd8dbde5140a0a23af29ad4b8f91fb1e", size = 641480 },
-    { url = "https://files.pythonhosted.org/packages/68/6e/264c50ce2a31473a9fdbf4fa66ca9b2b17c7455b31ef585462343818bd6c/ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bb43a269eb827806502c7c8efb7ae7e9e9d0573257a46e8e952f4d4caba4f31e", size = 739068 },
-    { url = "https://files.pythonhosted.org/packages/86/29/88c2567bc893c84d88b4c48027367c3562ae69121d568e8a3f3a8d363f4d/ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:811ea1594b8a0fb466172c384267a4e5e367298af6b228931f273b111f17ef52", size = 703012 },
-    { url = "https://files.pythonhosted.org/packages/11/46/879763c619b5470820f0cd6ca97d134771e502776bc2b844d2adb6e37753/ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cf12567a7b565cbf65d438dec6cfbe2917d3c1bdddfce84a9930b7d35ea59642", size = 704352 },
-    { url = "https://files.pythonhosted.org/packages/02/80/ece7e6034256a4186bbe50dee28cd032d816974941a6abf6a9d65e4228a7/ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7dd5adc8b930b12c8fc5b99e2d535a09889941aa0d0bd06f4749e9a9397c71d2", size = 737344 },
-    { url = "https://files.pythonhosted.org/packages/f0/ca/e4106ac7e80efbabdf4bf91d3d32fc424e41418458251712f5672eada9ce/ruamel.yaml.clib-0.2.12-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1492a6051dab8d912fc2adeef0e8c72216b24d57bd896ea607cb90bb0c4981d3", size = 714498 },
-    { url = "https://files.pythonhosted.org/packages/67/58/b1f60a1d591b771298ffa0428237afb092c7f29ae23bad93420b1eb10703/ruamel.yaml.clib-0.2.12-cp311-cp311-win32.whl", hash = "sha256:bd0a08f0bab19093c54e18a14a10b4322e1eacc5217056f3c063bd2f59853ce4", size = 100205 },
-    { url = "https://files.pythonhosted.org/packages/b4/4f/b52f634c9548a9291a70dfce26ca7ebce388235c93588a1068028ea23fcc/ruamel.yaml.clib-0.2.12-cp311-cp311-win_amd64.whl", hash = "sha256:a274fb2cb086c7a3dea4322ec27f4cb5cc4b6298adb583ab0e211a4682f241eb", size = 118185 },
-    { url = "https://files.pythonhosted.org/packages/48/41/e7a405afbdc26af961678474a55373e1b323605a4f5e2ddd4a80ea80f628/ruamel.yaml.clib-0.2.12-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:20b0f8dc160ba83b6dcc0e256846e1a02d044e13f7ea74a3d1d56ede4e48c632", size = 133433 },
-    { url = "https://files.pythonhosted.org/packages/ec/b0/b850385604334c2ce90e3ee1013bd911aedf058a934905863a6ea95e9eb4/ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:943f32bc9dedb3abff9879edc134901df92cfce2c3d5c9348f172f62eb2d771d", size = 647362 },
-    { url = "https://files.pythonhosted.org/packages/44/d0/3f68a86e006448fb6c005aee66565b9eb89014a70c491d70c08de597f8e4/ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95c3829bb364fdb8e0332c9931ecf57d9be3519241323c5274bd82f709cebc0c", size = 754118 },
-    { url = "https://files.pythonhosted.org/packages/52/a9/d39f3c5ada0a3bb2870d7db41901125dbe2434fa4f12ca8c5b83a42d7c53/ruamel.yaml.clib-0.2.12-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:749c16fcc4a2b09f28843cda5a193e0283e47454b63ec4b81eaa2242f50e4ccd", size = 706497 },
-    { url = "https://files.pythonhosted.org/packages/b0/fa/097e38135dadd9ac25aecf2a54be17ddf6e4c23e43d538492a90ab3d71c6/ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bf165fef1f223beae7333275156ab2022cffe255dcc51c27f066b4370da81e31", size = 698042 },
-    { url = "https://files.pythonhosted.org/packages/ec/d5/a659ca6f503b9379b930f13bc6b130c9f176469b73b9834296822a83a132/ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:32621c177bbf782ca5a18ba4d7af0f1082a3f6e517ac2a18b3974d4edf349680", size = 745831 },
-    { url = "https://files.pythonhosted.org/packages/db/5d/36619b61ffa2429eeaefaab4f3374666adf36ad8ac6330d855848d7d36fd/ruamel.yaml.clib-0.2.12-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:b82a7c94a498853aa0b272fd5bc67f29008da798d4f93a2f9f289feb8426a58d", size = 715692 },
-    { url = "https://files.pythonhosted.org/packages/b1/82/85cb92f15a4231c89b95dfe08b09eb6adca929ef7df7e17ab59902b6f589/ruamel.yaml.clib-0.2.12-cp312-cp312-win32.whl", hash = "sha256:e8c4ebfcfd57177b572e2040777b8abc537cdef58a2120e830124946aa9b42c5", size = 98777 },
-    { url = "https://files.pythonhosted.org/packages/d7/8f/c3654f6f1ddb75daf3922c3d8fc6005b1ab56671ad56ffb874d908bfa668/ruamel.yaml.clib-0.2.12-cp312-cp312-win_amd64.whl", hash = "sha256:0467c5965282c62203273b838ae77c0d29d7638c8a4e3a1c8bdd3602c10904e4", size = 115523 },
-]
-
 [[package]]
 name = "s3transfer"
 version = "0.13.0"
@@ -3586,68 +3098,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/69/e2/b011c38e5394c4c18fb5500778a55ec43ad6106126e74723ffaee246f56e/safetensors-0.5.3-cp38-abi3-win_amd64.whl", hash = "sha256:836cbbc320b47e80acd40e44c8682db0e8ad7123209f69b093def21ec7cafd11", size = 308878 },
 ]
 
-[[package]]
-name = "scikit-learn"
-version = "1.7.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "joblib" },
-    { name = "numpy" },
-    { name = "scipy" },
-    { name = "threadpoolctl" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/41/84/5f4af978fff619706b8961accac84780a6d298d82a8873446f72edb4ead0/scikit_learn-1.7.1.tar.gz", hash = "sha256:24b3f1e976a4665aa74ee0fcaac2b8fccc6ae77c8e07ab25da3ba6d3292b9802", size = 7190445 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/b4/bd/a23177930abd81b96daffa30ef9c54ddbf544d3226b8788ce4c3ef1067b4/scikit_learn-1.7.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:90c8494ea23e24c0fb371afc474618c1019dc152ce4a10e4607e62196113851b", size = 9334838 },
-    { url = "https://files.pythonhosted.org/packages/8d/a1/d3a7628630a711e2ac0d1a482910da174b629f44e7dd8cfcd6924a4ef81a/scikit_learn-1.7.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:bb870c0daf3bf3be145ec51df8ac84720d9972170786601039f024bf6d61a518", size = 8651241 },
-    { url = "https://files.pythonhosted.org/packages/26/92/85ec172418f39474c1cd0221d611345d4f433fc4ee2fc68e01f524ccc4e4/scikit_learn-1.7.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:40daccd1b5623f39e8943ab39735cadf0bdce80e67cdca2adcb5426e987320a8", size = 9718677 },
-    { url = "https://files.pythonhosted.org/packages/df/ce/abdb1dcbb1d2b66168ec43b23ee0cee356b4cc4100ddee3943934ebf1480/scikit_learn-1.7.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:30d1f413cfc0aa5a99132a554f1d80517563c34a9d3e7c118fde2d273c6fe0f7", size = 9511189 },
-    { url = "https://files.pythonhosted.org/packages/b2/3b/47b5eaee01ef2b5a80ba3f7f6ecf79587cb458690857d4777bfd77371c6f/scikit_learn-1.7.1-cp311-cp311-win_amd64.whl", hash = "sha256:c711d652829a1805a95d7fe96654604a8f16eab5a9e9ad87b3e60173415cb650", size = 8914794 },
-    { url = "https://files.pythonhosted.org/packages/cb/16/57f176585b35ed865f51b04117947fe20f130f78940c6477b6d66279c9c2/scikit_learn-1.7.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:3cee419b49b5bbae8796ecd690f97aa412ef1674410c23fc3257c6b8b85b8087", size = 9260431 },
-    { url = "https://files.pythonhosted.org/packages/67/4e/899317092f5efcab0e9bc929e3391341cec8fb0e816c4789686770024580/scikit_learn-1.7.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:2fd8b8d35817b0d9ebf0b576f7d5ffbbabdb55536b0655a8aaae629d7ffd2e1f", size = 8637191 },
-    { url = "https://files.pythonhosted.org/packages/f3/1b/998312db6d361ded1dd56b457ada371a8d8d77ca2195a7d18fd8a1736f21/scikit_learn-1.7.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:588410fa19a96a69763202f1d6b7b91d5d7a5d73be36e189bc6396bfb355bd87", size = 9486346 },
-    { url = "https://files.pythonhosted.org/packages/ad/09/a2aa0b4e644e5c4ede7006748f24e72863ba2ae71897fecfd832afea01b4/scikit_learn-1.7.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e3142f0abe1ad1d1c31a2ae987621e41f6b578144a911ff4ac94781a583adad7", size = 9290988 },
-    { url = "https://files.pythonhosted.org/packages/15/fa/c61a787e35f05f17fc10523f567677ec4eeee5f95aa4798dbbbcd9625617/scikit_learn-1.7.1-cp312-cp312-win_amd64.whl", hash = "sha256:3ddd9092c1bd469acab337d87930067c87eac6bd544f8d5027430983f1e1ae88", size = 8735568 },
-]
-
-[[package]]
-name = "scipy"
-version = "1.16.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/f5/4a/b927028464795439faec8eaf0b03b011005c487bb2d07409f28bf30879c4/scipy-1.16.1.tar.gz", hash = "sha256:44c76f9e8b6e8e488a586190ab38016e4ed2f8a038af7cd3defa903c0a2238b3", size = 30580861 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/da/91/812adc6f74409b461e3a5fa97f4f74c769016919203138a3bf6fc24ba4c5/scipy-1.16.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:c033fa32bab91dc98ca59d0cf23bb876454e2bb02cbe592d5023138778f70030", size = 36552519 },
-    { url = "https://files.pythonhosted.org/packages/47/18/8e355edcf3b71418d9e9f9acd2708cc3a6c27e8f98fde0ac34b8a0b45407/scipy-1.16.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:6e5c2f74e5df33479b5cd4e97a9104c511518fbd979aa9b8f6aec18b2e9ecae7", size = 28638010 },
-    { url = "https://files.pythonhosted.org/packages/d9/eb/e931853058607bdfbc11b86df19ae7a08686121c203483f62f1ecae5989c/scipy-1.16.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:0a55ffe0ba0f59666e90951971a884d1ff6f4ec3275a48f472cfb64175570f77", size = 20909790 },
-    { url = "https://files.pythonhosted.org/packages/45/0c/be83a271d6e96750cd0be2e000f35ff18880a46f05ce8b5d3465dc0f7a2a/scipy-1.16.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:f8a5d6cd147acecc2603fbd382fed6c46f474cccfcf69ea32582e033fb54dcfe", size = 23513352 },
-    { url = "https://files.pythonhosted.org/packages/7c/bf/fe6eb47e74f762f933cca962db7f2c7183acfdc4483bd1c3813cfe83e538/scipy-1.16.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cb18899127278058bcc09e7b9966d41a5a43740b5bb8dcba401bd983f82e885b", size = 33534643 },
-    { url = "https://files.pythonhosted.org/packages/bb/ba/63f402e74875486b87ec6506a4f93f6d8a0d94d10467280f3d9d7837ce3a/scipy-1.16.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:adccd93a2fa937a27aae826d33e3bfa5edf9aa672376a4852d23a7cd67a2e5b7", size = 35376776 },
-    { url = "https://files.pythonhosted.org/packages/c3/b4/04eb9d39ec26a1b939689102da23d505ea16cdae3dbb18ffc53d1f831044/scipy-1.16.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:18aca1646a29ee9a0625a1be5637fa798d4d81fdf426481f06d69af828f16958", size = 35698906 },
-    { url = "https://files.pythonhosted.org/packages/04/d6/bb5468da53321baeb001f6e4e0d9049eadd175a4a497709939128556e3ec/scipy-1.16.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:d85495cef541729a70cdddbbf3e6b903421bc1af3e8e3a9a72a06751f33b7c39", size = 38129275 },
-    { url = "https://files.pythonhosted.org/packages/c4/94/994369978509f227cba7dfb9e623254d0d5559506fe994aef4bea3ed469c/scipy-1.16.1-cp311-cp311-win_amd64.whl", hash = "sha256:226652fca853008119c03a8ce71ffe1b3f6d2844cc1686e8f9806edafae68596", size = 38644572 },
-    { url = "https://files.pythonhosted.org/packages/f8/d9/ec4864f5896232133f51382b54a08de91a9d1af7a76dfa372894026dfee2/scipy-1.16.1-cp312-cp312-macosx_10_14_x86_64.whl", hash = "sha256:81b433bbeaf35728dad619afc002db9b189e45eebe2cd676effe1fb93fef2b9c", size = 36575194 },
-    { url = "https://files.pythonhosted.org/packages/5c/6d/40e81ecfb688e9d25d34a847dca361982a6addf8e31f0957b1a54fbfa994/scipy-1.16.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:886cc81fdb4c6903a3bb0464047c25a6d1016fef77bb97949817d0c0d79f9e04", size = 28594590 },
-    { url = "https://files.pythonhosted.org/packages/0e/37/9f65178edfcc629377ce9a64fc09baebea18c80a9e57ae09a52edf84880b/scipy-1.16.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:15240c3aac087a522b4eaedb09f0ad061753c5eebf1ea430859e5bf8640d5919", size = 20866458 },
-    { url = "https://files.pythonhosted.org/packages/2c/7b/749a66766871ea4cb1d1ea10f27004db63023074c22abed51f22f09770e0/scipy-1.16.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:65f81a25805f3659b48126b5053d9e823d3215e4a63730b5e1671852a1705921", size = 23539318 },
-    { url = "https://files.pythonhosted.org/packages/c4/db/8d4afec60eb833a666434d4541a3151eedbf2494ea6d4d468cbe877f00cd/scipy-1.16.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6c62eea7f607f122069b9bad3f99489ddca1a5173bef8a0c75555d7488b6f725", size = 33292899 },
-    { url = "https://files.pythonhosted.org/packages/51/1e/79023ca3bbb13a015d7d2757ecca3b81293c663694c35d6541b4dca53e98/scipy-1.16.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f965bbf3235b01c776115ab18f092a95aa74c271a52577bcb0563e85738fd618", size = 35162637 },
-    { url = "https://files.pythonhosted.org/packages/b6/49/0648665f9c29fdaca4c679182eb972935b3b4f5ace41d323c32352f29816/scipy-1.16.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f006e323874ffd0b0b816d8c6a8e7f9a73d55ab3b8c3f72b752b226d0e3ac83d", size = 35490507 },
-    { url = "https://files.pythonhosted.org/packages/62/8f/66cbb9d6bbb18d8c658f774904f42a92078707a7c71e5347e8bf2f52bb89/scipy-1.16.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e8fd15fc5085ab4cca74cb91fe0a4263b1f32e4420761ddae531ad60934c2119", size = 37923998 },
-    { url = "https://files.pythonhosted.org/packages/14/c3/61f273ae550fbf1667675701112e380881905e28448c080b23b5a181df7c/scipy-1.16.1-cp312-cp312-win_amd64.whl", hash = "sha256:f7b8013c6c066609577d910d1a2a077021727af07b6fab0ee22c2f901f22352a", size = 38508060 },
-]
-
-[[package]]
-name = "semver"
-version = "3.0.4"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/72/d1/d3159231aec234a59dd7d601e9dd9fe96f3afff15efd33c1070019b26132/semver-3.0.4.tar.gz", hash = "sha256:afc7d8c584a5ed0a11033af086e8af226a9c0b206f313e0301f8dd7b6b589602", size = 269730 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a6/24/4d91e05817e92e3a61c8a21e08fd0f390f5301f1c448b137c57c4bc6e543/semver-3.0.4-py3-none-any.whl", hash = "sha256:9c824d87ba7f7ab4a1890799cec8596f15c1241cb473404ea1cb0c55e4b04746", size = 17912 },
-]
-
 [[package]]
 name = "sentencepiece"
 version = "0.2.0"
@@ -3751,25 +3201,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/32/46/9cb0e58b2deb7f82b84065f37f3bffeb12413f947f9388e4cac22c4621ce/sortedcontainers-2.4.0-py2.py3-none-any.whl", hash = "sha256:a163dcaede0f1c021485e957a39245190e74249897e2ae4b2aa38595db237ee0", size = 29575 },
 ]
 
-[[package]]
-name = "soundfile"
-version = "0.13.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "cffi" },
-    { name = "numpy" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/e1/41/9b873a8c055582859b239be17902a85339bec6a30ad162f98c9b0288a2cc/soundfile-0.13.1.tar.gz", hash = "sha256:b2c68dab1e30297317080a5b43df57e302584c49e2942defdde0acccc53f0e5b", size = 46156 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/64/28/e2a36573ccbcf3d57c00626a21fe51989380636e821b341d36ccca0c1c3a/soundfile-0.13.1-py2.py3-none-any.whl", hash = "sha256:a23c717560da2cf4c7b5ae1142514e0fd82d6bbd9dfc93a50423447142f2c445", size = 25751 },
-    { url = "https://files.pythonhosted.org/packages/ea/ab/73e97a5b3cc46bba7ff8650a1504348fa1863a6f9d57d7001c6b67c5f20e/soundfile-0.13.1-py2.py3-none-macosx_10_9_x86_64.whl", hash = "sha256:82dc664d19831933fe59adad199bf3945ad06d84bc111a5b4c0d3089a5b9ec33", size = 1142250 },
-    { url = "https://files.pythonhosted.org/packages/a0/e5/58fd1a8d7b26fc113af244f966ee3aecf03cb9293cb935daaddc1e455e18/soundfile-0.13.1-py2.py3-none-macosx_11_0_arm64.whl", hash = "sha256:743f12c12c4054921e15736c6be09ac26b3b3d603aef6fd69f9dde68748f2593", size = 1101406 },
-    { url = "https://files.pythonhosted.org/packages/58/ae/c0e4a53d77cf6e9a04179535766b3321b0b9ced5f70522e4caf9329f0046/soundfile-0.13.1-py2.py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:9c9e855f5a4d06ce4213f31918653ab7de0c5a8d8107cd2427e44b42df547deb", size = 1235729 },
-    { url = "https://files.pythonhosted.org/packages/57/5e/70bdd9579b35003a489fc850b5047beeda26328053ebadc1fb60f320f7db/soundfile-0.13.1-py2.py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:03267c4e493315294834a0870f31dbb3b28a95561b80b134f0bd3cf2d5f0e618", size = 1313646 },
-    { url = "https://files.pythonhosted.org/packages/fe/df/8c11dc4dfceda14e3003bb81a0d0edcaaf0796dd7b4f826ea3e532146bba/soundfile-0.13.1-py2.py3-none-win32.whl", hash = "sha256:c734564fab7c5ddf8e9be5bf70bab68042cd17e9c214c06e365e20d64f9a69d5", size = 899881 },
-    { url = "https://files.pythonhosted.org/packages/14/e9/6b761de83277f2f02ded7e7ea6f07828ec78e4b229b80e4ca55dd205b9dc/soundfile-0.13.1-py2.py3-none-win_amd64.whl", hash = "sha256:1e70a05a0626524a69e9f0f4dd2ec174b4e9567f4d8b6c11d38b5c289be36ee9", size = 1019162 },
-]
-
 [[package]]
 name = "soupsieve"
 version = "2.7"
@@ -3779,29 +3210,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677 },
 ]
 
-[[package]]
-name = "speechbrain"
-version = "1.0.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "huggingface-hub" },
-    { name = "hyperpyyaml" },
-    { name = "joblib" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "scipy" },
-    { name = "sentencepiece" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torchaudio", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or sys_platform == 'darwin'" },
-    { name = "torchaudio", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-    { name = "tqdm" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/ab/10/87e666544a4e0cec7cbdc09f26948994831ae0f8bbc58de3bf53b68285ff/speechbrain-1.0.3.tar.gz", hash = "sha256:fcab3c6e90012cecb1eed40ea235733b550137e73da6bfa2340ba191ec714052", size = 747735 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/58/13/e61f1085aebee17d5fc2df19fcc5177c10379be52578afbecdd615a831c9/speechbrain-1.0.3-py3-none-any.whl", hash = "sha256:9859d4c1b1fb3af3b85523c0c89f52e45a04f305622ed55f31aa32dd2fba19e9", size = 864091 },
-]
-
 [[package]]
 name = "sqlalchemy"
 version = "1.4.54"
@@ -3883,15 +3291,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a2/09/77d55d46fd61b4a135c444fc97158ef34a095e5681d0a6c10b75bf356191/sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5", size = 6299353 },
 ]
 
-[[package]]
-name = "tabulate"
-version = "0.9.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/ec/fe/802052aecb21e3797b8f7902564ab6ea0d60ff8ca23952079064155d1ae1/tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c", size = 81090 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f", size = 35252 },
-]
-
 [[package]]
 name = "tenacity"
 version = "9.1.2"
@@ -3901,29 +3300,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e5/30/643397144bfbfec6f6ef821f36f33e57d35946c44a2352d3c9f0ae847619/tenacity-9.1.2-py3-none-any.whl", hash = "sha256:f77bf36710d8b73a50b2dd155c97b870017ad21afe6ab300326b0371b3b05138", size = 28248 },
 ]
 
-[[package]]
-name = "tensorboardx"
-version = "2.6.4"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "protobuf" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/2b/c5/d4cc6e293fb837aaf9f76dd7745476aeba8ef7ef5146c3b3f9ee375fe7a5/tensorboardx-2.6.4.tar.gz", hash = "sha256:b163ccb7798b31100b9f5fa4d6bc22dad362d7065c2f24b51e50731adde86828", size = 4769801 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e0/1d/b5d63f1a6b824282b57f7b581810d20b7a28ca951f2d5b59f1eb0782c12b/tensorboardx-2.6.4-py3-none-any.whl", hash = "sha256:5970cf3a1f0a6a6e8b180ccf46f3fe832b8a25a70b86e5a237048a7c0beb18e2", size = 87201 },
-]
-
-[[package]]
-name = "threadpoolctl"
-version = "3.6.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/b7/4d/08c89e34946fce2aec4fbb45c9016efd5f4d7f24af8e5d93296e935631d8/threadpoolctl-3.6.0.tar.gz", hash = "sha256:8ab8b4aa3491d812b623328249fab5302a68d2d71745c8a4c719a2fcaba9f44e", size = 21274 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/32/d5/f9a850d79b0851d1d4ef6456097579a9005b31fea68726a4ae5f2d82ddd9/threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb", size = 18638 },
-]
-
 [[package]]
 name = "tiktoken"
 version = "0.9.0"
@@ -4064,40 +3440,6 @@ wheels = [
     { url = "https://download.pytorch.org/whl/cpu/torch-2.8.0%2Bcpu-cp312-cp312-win_arm64.whl", hash = "sha256:99fc421a5d234580e45957a7b02effbf3e1c884a5dd077afc85352c77bf41434" },
 ]
 
-[[package]]
-name = "torch-audiomentations"
-version = "0.12.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "julius" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torch-pitch-shift" },
-    { name = "torchaudio", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or sys_platform == 'darwin'" },
-    { name = "torchaudio", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/31/8d/2f8fd7e34c75f5ee8de4310c3bd3f22270acd44d1f809e2fe7c12fbf35f8/torch_audiomentations-0.12.0.tar.gz", hash = "sha256:b02d4c5eb86376986a53eb405cca5e34f370ea9284411237508e720c529f7888", size = 52094 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/21/9d/1ee04f49c15d2d632f6f7102061d7c07652858e6d91b58a091531034e84f/torch_audiomentations-0.12.0-py3-none-any.whl", hash = "sha256:1b80b91d2016ccf83979622cac8f702072a79b7dcc4c2bee40f00b26433a786b", size = 48506 },
-]
-
-[[package]]
-name = "torch-pitch-shift"
-version = "1.2.5"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "packaging" },
-    { name = "primepy" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-    { name = "torchaudio", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or sys_platform == 'darwin'" },
-    { name = "torchaudio", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/79/a6/722a832bca75d5079f6731e005b3d0c2eec7c6c6863d030620952d143d57/torch_pitch_shift-1.2.5.tar.gz", hash = "sha256:6e1c7531f08d0f407a4c55e5ff8385a41355c5c5d27ab7fa08632e51defbd0ed", size = 4725 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/27/4c/96ac2a09efb56cc3c41fb3ce9b6f4d8c0604499f7481d4a13a7b03e21382/torch_pitch_shift-1.2.5-py3-none-any.whl", hash = "sha256:6f8500cbc13f1c98b11cde1805ce5084f82cdd195c285f34287541f168a7c6a7", size = 5005 },
-]
-
 [[package]]
 name = "torchaudio"
 version = "2.8.0"
@@ -4145,22 +3487,6 @@ wheels = [
     { url = "https://download.pytorch.org/whl/cpu/torchaudio-2.8.0%2Bcpu-cp312-cp312-win_amd64.whl", hash = "sha256:9b302192b570657c1cc787a4d487ae4bbb7f2aab1c01b1fcc46757e7f86f391e" },
 ]
 
-[[package]]
-name = "torchmetrics"
-version = "1.8.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "lightning-utilities" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "torch", version = "2.8.0", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'darwin'" },
-    { name = "torch", version = "2.8.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform != 'darwin'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/85/2e/48a887a59ecc4a10ce9e8b35b3e3c5cef29d902c4eac143378526e7485cb/torchmetrics-1.8.2.tar.gz", hash = "sha256:cf64a901036bf107f17a524009eea7781c9c5315d130713aeca5747a686fe7a5", size = 580679 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/02/21/aa0f434434c48490f91b65962b1ce863fdcce63febc166ca9fe9d706c2b6/torchmetrics-1.8.2-py3-none-any.whl", hash = "sha256:08382fd96b923e39e904c4d570f3d49e2cc71ccabd2a94e0f895d1f0dac86242", size = 983161 },
-]
-
 [[package]]
 name = "tqdm"
 version = "4.67.1"

www/.env.selfhosted.example

@@ -0,0 +1,53 @@
+# =======================================================
+# Reflector Self-Hosted Production — Frontend Configuration
+# Generated by: ./scripts/setup-selfhosted.sh
+# =======================================================
+
+# Site URL — set to your domain or server IP
+# The setup script auto-detects this on Linux.
+SITE_URL=https://localhost
+NEXTAUTH_URL=https://localhost
+NEXTAUTH_SECRET=changeme-generate-a-secure-random-string
+
+# API URLs
+# Public-facing (what the browser uses):
+API_URL=https://localhost
+WEBSOCKET_URL=auto
+
+# Internal Docker network (server-side rendering):
+SERVER_API_URL=http://server:1250
+KV_URL=redis://redis:6379
+
+# Authentication
+# Set to true when Authentik or password auth is configured
+FEATURE_REQUIRE_LOGIN=false
+
+# Auth provider: "authentik" or "credentials"
+# Set to "credentials" when using password auth backend
+# AUTH_PROVIDER=credentials
+
+# Nullify auth vars when not using Authentik
+AUTHENTIK_ISSUER=
+AUTHENTIK_REFRESH_TOKEN_URL=
+
+# =======================================================
+# Authentik OAuth/OIDC (Optional)
+# Uncomment and configure when enabling authentication.
+# See docsv2/selfhosted-production.md for setup instructions.
+# =======================================================
+# FEATURE_REQUIRE_LOGIN=true
+# AUTHENTIK_ISSUER=https://authentik.example.com/application/o/reflector
+# AUTHENTIK_REFRESH_TOKEN_URL=https://authentik.example.com/application/o/token/
+# AUTHENTIK_CLIENT_ID=your-client-id
+# AUTHENTIK_CLIENT_SECRET=your-client-secret
+
+# =======================================================
+# Feature Flags
+# =======================================================
+# FEATURE_ROOMS=true
+# FEATURE_BROWSE=true
+
+# =======================================================
+# Sentry (Optional)
+# =======================================================
+# SENTRY_DSN=

www/app/(app)/transcripts/[transcriptId]/processing/page.tsx

@@ -11,6 +11,7 @@ import {
 import { useRouter } from "next/navigation";
 import { useTranscriptGet } from "../../../../lib/apiHooks";
 import { parseNonEmptyString } from "../../../../lib/utils";
+import { useWebSockets } from "../../useWebSockets";
 
 type TranscriptProcessing = {
   params: Promise<{
@@ -24,6 +25,7 @@ export default function TranscriptProcessing(details: TranscriptProcessing) {
   const router = useRouter();
 
   const transcript = useTranscriptGet(transcriptId);
+  useWebSockets(transcriptId);
 
   useEffect(() => {
     const status = transcript.data?.status;

www/app/(app)/transcripts/useMp3.ts

@@ -78,7 +78,10 @@ const useMp3 = (transcriptId: string, waiting?: boolean): Mp3Response => {
 
     // Audio is not deleted, proceed to load it
     audioElement = document.createElement("audio");
-    audioElement.src = `${API_URL}/v1/transcripts/${transcriptId}/audio/mp3`;
+    const audioUrl = `${API_URL}/v1/transcripts/${transcriptId}/audio/mp3`;
+    audioElement.src = accessTokenInfo
+      ? `${audioUrl}?token=${encodeURIComponent(accessTokenInfo)}`
+      : audioUrl;
     audioElement.crossOrigin = "anonymous";
     audioElement.preload = "auto";
 

www/app/(app)/transcripts/useWebRTC.ts

@@ -23,7 +23,16 @@ const useWebRTC = (
     let p: Peer;
 
     try {
-      p = new Peer({ initiator: true, stream: stream });
+      p = new Peer({
+        initiator: true,
+        stream: stream,
+        // Disable trickle ICE: single SDP exchange (offer + answer) with all candidates.
+        // Required for HTTP-based signaling; trickle needs WebSocket for candidate exchange.
+        trickle: false,
+        config: {
+          iceServers: [{ urls: "stun:stun.l.google.com:19302" }],
+        },
+      });
     } catch (error) {
       setError(error as Error, "Error creating WebRTC");
       return;