fix: remove downscale from silero vad and use upstream processor

.github/workflows/db_migrations.yml

@@ -2,8 +2,6 @@ name: Test Database Migrations
 
 on:
   push:
-    branches:
-      - main
     paths:
       - "server/migrations/**"
       - "server/reflector/db/**"
@@ -19,9 +17,6 @@ on:
 jobs:
   test-migrations:
     runs-on: ubuntu-latest
-    concurrency:
-      group: db-ubuntu-latest-${{ github.ref }}
-      cancel-in-progress: true
     services:
       postgres:
         image: postgres:17

.github/workflows/deploy.yml

@@ -1,4 +1,4 @@
-name: Build container/push to container registry
+name: Deploy to Amazon ECS
 
 on: [workflow_dispatch]
 

.github/workflows/docker-frontend.yml

@@ -1,57 +0,0 @@
-name: Build and Push Frontend Docker Image
-
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - 'www/**'
-      - '.github/workflows/docker-frontend.yml'
-  workflow_dispatch:
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}-frontend
-
-jobs:
-  build-and-push:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - name: Log in to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=sha,prefix={{branch}}-
-            type=raw,value=latest,enable={{is_default_branch}}
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: ./www
-          file: ./www/Dockerfile
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          platforms: linux/amd64,linux/arm64

.github/workflows/test_next_server.yml

@@ -1,45 +0,0 @@
-name: Test Next Server
-
-on:
-  pull_request:
-    paths:
-      - "www/**"
-  push:
-    branches:
-      - main
-    paths:
-      - "www/**"
-
-jobs:
-  test-next-server:
-    runs-on: ubuntu-latest
-
-    defaults:
-      run:
-        working-directory: ./www
-
-    steps:
-    - uses: actions/checkout@v4
-
-    - name: Setup Node.js
-      uses: actions/setup-node@v4
-      with:
-        node-version: '20'
-
-    - name: Install pnpm
-      uses: pnpm/action-setup@v4
-      with:
-        version: 8
-
-    - name: Setup Node.js cache
-      uses: actions/setup-node@v4
-      with:
-        node-version: '20'
-        cache: 'pnpm'
-        cache-dependency-path: './www/pnpm-lock.yaml'
-
-    - name: Install dependencies
-      run: pnpm install
-
-    - name: Run tests
-      run: pnpm test

.github/workflows/test_server.yml

@@ -5,17 +5,12 @@ on:
     paths:
       - "server/**"
   push:
-    branches:
-      - main
     paths:
       - "server/**"
 
 jobs:
   pytest:
     runs-on: ubuntu-latest
-    concurrency:
-      group: pytest-${{ github.ref }}
-      cancel-in-progress: true
     services:
       redis:
         image: redis:6
@@ -35,9 +30,6 @@ jobs:
 
   docker-amd64:
     runs-on: linux-amd64
-    concurrency:
-      group: docker-amd64-${{ github.ref }}
-      cancel-in-progress: true
     steps:
       - uses: actions/checkout@v4
       - name: Set up Docker Buildx
@@ -53,9 +45,6 @@ jobs:
 
   docker-arm64:
     runs-on: linux-arm64
-    concurrency:
-      group: docker-arm64-${{ github.ref }}
-      cancel-in-progress: true
     steps:
       - uses: actions/checkout@v4
       - name: Set up Docker Buildx

.gitignore

@@ -14,7 +14,4 @@ data/
 www/REFACTOR.md
 www/reload-frontend
 server/test.sqlite
-CLAUDE.local.md
+CLAUDE.local.md
-www/.env.development
-www/.env.production
-.playwright-mcp

.gitleaksignore

@@ -1 +0,0 @@
-b9d891d3424f371642cb032ecfd0e2564470a72c:server/tests/test_transcripts_recording_deletion.py:generic-api-key:15

.pre-commit-config.yaml

@@ -27,8 +27,3 @@ repos:
         files: ^server/
       - id: ruff-format
         files: ^server/
-
-  - repo: https://github.com/gitleaks/gitleaks
-    rev: v8.28.0
-    hooks:
-      - id: gitleaks

CHANGELOG.md

@@ -1,202 +1,5 @@
 # Changelog
 
-## [0.20.0](https://github.com/Monadical-SAS/reflector/compare/v0.19.0...v0.20.0) (2025-11-25)
-
-
-### Features
-
-* link transcript participants ([#737](https://github.com/Monadical-SAS/reflector/issues/737)) ([9bec398](https://github.com/Monadical-SAS/reflector/commit/9bec39808fc6322612d8b87e922a6f7901fc01c1))
-* transcript restart script ([#742](https://github.com/Monadical-SAS/reflector/issues/742)) ([86d5e26](https://github.com/Monadical-SAS/reflector/commit/86d5e26224bb55a0f1cc785aeda52065bb92ee6f))
-
-## [0.19.0](https://github.com/Monadical-SAS/reflector/compare/v0.18.0...v0.19.0) (2025-11-25)
-
-
-### Features
-
-* dailyco api module ([#725](https://github.com/Monadical-SAS/reflector/issues/725)) ([4287f8b](https://github.com/Monadical-SAS/reflector/commit/4287f8b8aeee60e51db7539f4dcbda5f6e696bd8))
-* dailyco poll ([#730](https://github.com/Monadical-SAS/reflector/issues/730)) ([8e438ca](https://github.com/Monadical-SAS/reflector/commit/8e438ca285152bd48fdc42767e706fb448d3525c))
-* multitrack cli ([#735](https://github.com/Monadical-SAS/reflector/issues/735)) ([11731c9](https://github.com/Monadical-SAS/reflector/commit/11731c9d38439b04e93b1c3afbd7090bad11a11f))
-
-
-### Bug Fixes
-
-* default platform fix ([#736](https://github.com/Monadical-SAS/reflector/issues/736)) ([c442a62](https://github.com/Monadical-SAS/reflector/commit/c442a627873ca667656eeaefb63e54ab10b8d19e))
-* parakeet vad not getting the end timestamp ([#728](https://github.com/Monadical-SAS/reflector/issues/728)) ([18ed713](https://github.com/Monadical-SAS/reflector/commit/18ed7133693653ef4ddac6c659a8c14b320d1657))
-* start raw tracks recording ([#729](https://github.com/Monadical-SAS/reflector/issues/729)) ([3e47c2c](https://github.com/Monadical-SAS/reflector/commit/3e47c2c0573504858e0d2e1798b6ed31f16b4a5d))
-
-## [0.18.0](https://github.com/Monadical-SAS/reflector/compare/v0.17.0...v0.18.0) (2025-11-14)
-
-
-### Features
-
-* daily QOL: participants dictionary ([#721](https://github.com/Monadical-SAS/reflector/issues/721)) ([b20cad7](https://github.com/Monadical-SAS/reflector/commit/b20cad76e69fb6a76405af299a005f1ddcf60eae))
-
-
-### Bug Fixes
-
-* add proccessing page to file upload and reprocessing ([#650](https://github.com/Monadical-SAS/reflector/issues/650)) ([28a7258](https://github.com/Monadical-SAS/reflector/commit/28a7258e45317b78e60e6397be2bc503647eaace))
-* copy transcript ([#674](https://github.com/Monadical-SAS/reflector/issues/674)) ([a9a4f32](https://github.com/Monadical-SAS/reflector/commit/a9a4f32324f66c838e081eee42bb9502f38c1db1))
-
-## [0.17.0](https://github.com/Monadical-SAS/reflector/compare/v0.16.0...v0.17.0) (2025-11-13)
-
-
-### Features
-
-* add API key management UI ([#716](https://github.com/Monadical-SAS/reflector/issues/716)) ([372202b](https://github.com/Monadical-SAS/reflector/commit/372202b0e1a86823900b0aa77be1bfbc2893d8a1))
-* daily.co support as alternative to whereby ([#691](https://github.com/Monadical-SAS/reflector/issues/691)) ([1473fd8](https://github.com/Monadical-SAS/reflector/commit/1473fd82dc472c394cbaa2987212ad662a74bcac))
-
-## [0.16.0](https://github.com/Monadical-SAS/reflector/compare/v0.15.0...v0.16.0) (2025-10-24)
-
-
-### Features
-
-* search date filter ([#710](https://github.com/Monadical-SAS/reflector/issues/710)) ([962c40e](https://github.com/Monadical-SAS/reflector/commit/962c40e2b6428ac42fd10aea926782d7a6f3f902))
-
-## [0.15.0](https://github.com/Monadical-SAS/reflector/compare/v0.14.0...v0.15.0) (2025-10-20)
-
-
-### Features
-
-* api tokens  ([#705](https://github.com/Monadical-SAS/reflector/issues/705)) ([9a258ab](https://github.com/Monadical-SAS/reflector/commit/9a258abc0209b0ac3799532a507ea6a9125d703a))
-
-## [0.14.0](https://github.com/Monadical-SAS/reflector/compare/v0.13.1...v0.14.0) (2025-10-08)
-
-
-### Features
-
-* Add calendar event data to transcript webhook payload ([#689](https://github.com/Monadical-SAS/reflector/issues/689)) ([5f6910e](https://github.com/Monadical-SAS/reflector/commit/5f6910e5131b7f28f86c9ecdcc57fed8412ee3cd))
-* container build for www / github ([#672](https://github.com/Monadical-SAS/reflector/issues/672)) ([969bd84](https://github.com/Monadical-SAS/reflector/commit/969bd84fcc14851d1a101412a0ba115f1b7cde82))
-* docker-compose for production frontend ([#664](https://github.com/Monadical-SAS/reflector/issues/664)) ([5bf64b5](https://github.com/Monadical-SAS/reflector/commit/5bf64b5a41f64535e22849b4bb11734d4dbb4aae))
-
-
-### Bug Fixes
-
-* restore feature boolean logic ([#671](https://github.com/Monadical-SAS/reflector/issues/671)) ([3660884](https://github.com/Monadical-SAS/reflector/commit/36608849ec64e953e3be456172502762e3c33df9))
-* security review ([#656](https://github.com/Monadical-SAS/reflector/issues/656)) ([5d98754](https://github.com/Monadical-SAS/reflector/commit/5d98754305c6c540dd194dda268544f6d88bfaf8))
-* update transcript list on reprocess ([#676](https://github.com/Monadical-SAS/reflector/issues/676)) ([9a71af1](https://github.com/Monadical-SAS/reflector/commit/9a71af145ee9b833078c78d0c684590ab12e9f0e))
-* upgrade nemo toolkit ([#678](https://github.com/Monadical-SAS/reflector/issues/678)) ([eef6dc3](https://github.com/Monadical-SAS/reflector/commit/eef6dc39037329b65804297786d852dddb0557f9))
-
-## [0.13.1](https://github.com/Monadical-SAS/reflector/compare/v0.13.0...v0.13.1) (2025-09-22)
-
-
-### Bug Fixes
-
-* TypeError on not all arguments converted during string formatting in logger ([#667](https://github.com/Monadical-SAS/reflector/issues/667)) ([565a629](https://github.com/Monadical-SAS/reflector/commit/565a62900f5a02fc946b68f9269a42190ed70ab6))
-
-## [0.13.0](https://github.com/Monadical-SAS/reflector/compare/v0.12.1...v0.13.0) (2025-09-19)
-
-
-### Features
-
-* room form edit with enter ([#662](https://github.com/Monadical-SAS/reflector/issues/662)) ([47716f6](https://github.com/Monadical-SAS/reflector/commit/47716f6e5ddee952609d2fa0ffabdfa865286796))
-
-
-### Bug Fixes
-
-* invalid cleanup call ([#660](https://github.com/Monadical-SAS/reflector/issues/660)) ([0abcebf](https://github.com/Monadical-SAS/reflector/commit/0abcebfc9491f87f605f21faa3e53996fafedd9a))
-
-## [0.12.1](https://github.com/Monadical-SAS/reflector/compare/v0.12.0...v0.12.1) (2025-09-17)
-
-
-### Bug Fixes
-
-* production blocked because having existing meeting with room_id null ([#657](https://github.com/Monadical-SAS/reflector/issues/657)) ([870e860](https://github.com/Monadical-SAS/reflector/commit/870e8605171a27155a9cbee215eeccb9a8d6c0a2))
-
-## [0.12.0](https://github.com/Monadical-SAS/reflector/compare/v0.11.0...v0.12.0) (2025-09-17)
-
-
-### Features
-
-* calendar integration ([#608](https://github.com/Monadical-SAS/reflector/issues/608)) ([6f680b5](https://github.com/Monadical-SAS/reflector/commit/6f680b57954c688882c4ed49f40f161c52a00a24))
-* self-hosted gpu api ([#636](https://github.com/Monadical-SAS/reflector/issues/636)) ([ab859d6](https://github.com/Monadical-SAS/reflector/commit/ab859d65a6bded904133a163a081a651b3938d42))
-
-
-### Bug Fixes
-
-* ignore player hotkeys for text inputs ([#646](https://github.com/Monadical-SAS/reflector/issues/646)) ([fa049e8](https://github.com/Monadical-SAS/reflector/commit/fa049e8d068190ce7ea015fd9fcccb8543f54a3f))
-
-## [0.11.0](https://github.com/Monadical-SAS/reflector/compare/v0.10.0...v0.11.0) (2025-09-16)
-
-
-### Features
-
-* remove profanity filter that was there for conference ([#652](https://github.com/Monadical-SAS/reflector/issues/652)) ([b42f7cf](https://github.com/Monadical-SAS/reflector/commit/b42f7cfc606783afcee792590efcc78b507468ab))
-
-
-### Bug Fixes
-
-* zulip and consent handler on the file pipeline ([#645](https://github.com/Monadical-SAS/reflector/issues/645)) ([5f143fe](https://github.com/Monadical-SAS/reflector/commit/5f143fe3640875dcb56c26694254a93189281d17))
-* zulip stream and topic selection in share dialog ([#644](https://github.com/Monadical-SAS/reflector/issues/644)) ([c546e69](https://github.com/Monadical-SAS/reflector/commit/c546e69739e68bb74fbc877eb62609928e5b8de6))
-
-## [0.10.0](https://github.com/Monadical-SAS/reflector/compare/v0.9.0...v0.10.0) (2025-09-11)
-
-
-### Features
-
-* replace nextjs-config with environment variables ([#632](https://github.com/Monadical-SAS/reflector/issues/632)) ([369ecdf](https://github.com/Monadical-SAS/reflector/commit/369ecdff13f3862d926a9c0b87df52c9d94c4dde))
-
-
-### Bug Fixes
-
-* anonymous users transcript permissions ([#621](https://github.com/Monadical-SAS/reflector/issues/621)) ([f81fe99](https://github.com/Monadical-SAS/reflector/commit/f81fe9948a9237b3e0001b2d8ca84f54d76878f9))
-* auth post ([#624](https://github.com/Monadical-SAS/reflector/issues/624)) ([cde99ca](https://github.com/Monadical-SAS/reflector/commit/cde99ca2716f84ba26798f289047732f0448742e))
-* auth post ([#626](https://github.com/Monadical-SAS/reflector/issues/626)) ([3b85ff3](https://github.com/Monadical-SAS/reflector/commit/3b85ff3bdf4fb053b103070646811bc990c0e70a))
-* auth post ([#627](https://github.com/Monadical-SAS/reflector/issues/627)) ([962038e](https://github.com/Monadical-SAS/reflector/commit/962038ee3f2a555dc3c03856be0e4409456e0996))
-* missing follow_redirects=True on modal endpoint ([#630](https://github.com/Monadical-SAS/reflector/issues/630)) ([fc363bd](https://github.com/Monadical-SAS/reflector/commit/fc363bd49b17b075e64f9186e5e0185abc325ea7))
-* sync backend and frontend token refresh logic ([#614](https://github.com/Monadical-SAS/reflector/issues/614)) ([5a5b323](https://github.com/Monadical-SAS/reflector/commit/5a5b3233820df9536da75e87ce6184a983d4713a))
-
-## [0.9.0](https://github.com/Monadical-SAS/reflector/compare/v0.8.2...v0.9.0) (2025-09-06)
-
-
-### Features
-
-* frontend openapi react query ([#606](https://github.com/Monadical-SAS/reflector/issues/606)) ([c4d2825](https://github.com/Monadical-SAS/reflector/commit/c4d2825c81f81ad8835629fbf6ea8c7383f8c31b))
-
-
-### Bug Fixes
-
-* align whisper transcriber api with parakeet ([#602](https://github.com/Monadical-SAS/reflector/issues/602)) ([0663700](https://github.com/Monadical-SAS/reflector/commit/0663700a615a4af69a03c96c410f049e23ec9443))
-* kv use tls explicit ([#610](https://github.com/Monadical-SAS/reflector/issues/610)) ([08d88ec](https://github.com/Monadical-SAS/reflector/commit/08d88ec349f38b0d13e0fa4cb73486c8dfd31836))
-* source kind for file processing ([#601](https://github.com/Monadical-SAS/reflector/issues/601)) ([dc82f8b](https://github.com/Monadical-SAS/reflector/commit/dc82f8bb3bdf3ab3d4088e592a30fd63907319e1))
-* token refresh locking ([#613](https://github.com/Monadical-SAS/reflector/issues/613)) ([7f5a4c9](https://github.com/Monadical-SAS/reflector/commit/7f5a4c9ddc7fd098860c8bdda2ca3b57f63ded2f))
-
-## [0.8.2](https://github.com/Monadical-SAS/reflector/compare/v0.8.1...v0.8.2) (2025-08-29)
-
-
-### Bug Fixes
-
-* search-logspam ([#593](https://github.com/Monadical-SAS/reflector/issues/593)) ([695d1a9](https://github.com/Monadical-SAS/reflector/commit/695d1a957d4cd862753049f9beed88836cabd5ab))
-
-## [0.8.1](https://github.com/Monadical-SAS/reflector/compare/v0.8.0...v0.8.1) (2025-08-29)
-
-
-### Bug Fixes
-
-* make webhook secret/url allowing null ([#590](https://github.com/Monadical-SAS/reflector/issues/590)) ([84a3812](https://github.com/Monadical-SAS/reflector/commit/84a381220bc606231d08d6f71d4babc818fa3c75))
-
-## [0.8.0](https://github.com/Monadical-SAS/reflector/compare/v0.7.3...v0.8.0) (2025-08-29)
-
-
-### Features
-
-* **cleanup:** add automatic data retention for public instances ([#574](https://github.com/Monadical-SAS/reflector/issues/574)) ([6f0c7c1](https://github.com/Monadical-SAS/reflector/commit/6f0c7c1a5e751713366886c8e764c2009e12ba72))
-* **rooms:** add webhook for transcript completion ([#578](https://github.com/Monadical-SAS/reflector/issues/578)) ([88ed7cf](https://github.com/Monadical-SAS/reflector/commit/88ed7cfa7804794b9b54cad4c3facc8a98cf85fd))
-
-
-### Bug Fixes
-
-* file pipeline status reporting and websocket updates ([#589](https://github.com/Monadical-SAS/reflector/issues/589)) ([9dfd769](https://github.com/Monadical-SAS/reflector/commit/9dfd76996f851cc52be54feea078adbc0816dc57))
-* Igor/evaluation ([#575](https://github.com/Monadical-SAS/reflector/issues/575)) ([124ce03](https://github.com/Monadical-SAS/reflector/commit/124ce03bf86044c18313d27228a25da4bc20c9c5))
-* optimize parakeet transcription batching algorithm ([#577](https://github.com/Monadical-SAS/reflector/issues/577)) ([7030e0f](https://github.com/Monadical-SAS/reflector/commit/7030e0f23649a8cf6c1eb6d5889684a41ce849ec))
-
-## [0.7.3](https://github.com/Monadical-SAS/reflector/compare/v0.7.2...v0.7.3) (2025-08-22)
-
-
-### Bug Fixes
-
-* cleaned repo, and get git-leaks clean ([359280d](https://github.com/Monadical-SAS/reflector/commit/359280dd340433ba4402ed69034094884c825e67))
-* restore previous behavior on live pipeline + audio downscaler ([#561](https://github.com/Monadical-SAS/reflector/issues/561)) ([9265d20](https://github.com/Monadical-SAS/reflector/commit/9265d201b590d23c628c5f19251b70f473859043))
-
 ## [0.7.2](https://github.com/Monadical-SAS/reflector/compare/v0.7.1...v0.7.2) (2025-08-21)
 
 

CLAUDE.md

@@ -66,6 +66,7 @@ pnpm install
 
 # Copy configuration templates
 cp .env_template .env
+cp config-template.ts config.ts
 ```
 
 **Development:**
@@ -151,7 +152,7 @@ All endpoints prefixed `/v1/`:
 
 **Frontend** (`www/.env`):
 - `NEXTAUTH_URL`, `NEXTAUTH_SECRET` - Authentication configuration
-- `REFLECTOR_API_URL` - Backend API endpoint
+- `NEXT_PUBLIC_REFLECTOR_API_URL` - Backend API endpoint
 - `REFLECTOR_DOMAIN_CONFIG` - Feature flags and domain settings
 
 ## Testing Strategy

README.md

@@ -1,60 +1,43 @@
 <div align="center">
-<img width="100" alt="image" src="https://github.com/user-attachments/assets/66fb367b-2c89-4516-9912-f47ac59c6a7f"/>
 
 # Reflector
 
-Reflector is an AI-powered audio transcription and meeting analysis platform that provides real-time transcription, speaker diarization, translation and summarization for audio content and live meetings. It works 100% with local models (whisper/parakeet, pyannote, seamless-m4t, and your local llm like phi-4).
+Reflector Audio Management and Analysis is a cutting-edge web application under development by Monadical. It utilizes AI to record meetings, providing a permanent record with transcripts, translations, and automated summaries.
 
-[![Tests](https://github.com/monadical-sas/reflector/actions/workflows/test_server.yml/badge.svg?branch=main&event=push)](https://github.com/monadical-sas/reflector/actions/workflows/test_server.yml)
+[![Tests](https://github.com/monadical-sas/reflector/actions/workflows/pytests.yml/badge.svg?branch=main&event=push)](https://github.com/monadical-sas/reflector/actions/workflows/pytests.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](https://opensource.org/licenses/MIT)
 </div>
-</div>
+
+## Screenshots
 <table>
   <tr>
     <td>
-      <a href="https://github.com/user-attachments/assets/21f5597c-2930-4899-a154-f7bd61a59e97">
+      <a href="https://github.com/user-attachments/assets/3a976930-56c1-47ef-8c76-55d3864309e3">
-        <img width="700" alt="image" src="https://github.com/user-attachments/assets/21f5597c-2930-4899-a154-f7bd61a59e97" />
+        <img width="700" alt="image" src="https://github.com/user-attachments/assets/3a976930-56c1-47ef-8c76-55d3864309e3" />
       </a>
     </td>
     <td>
-      <a href="https://github.com/user-attachments/assets/f6b9399a-5e51-4bae-b807-59128d0a940c">
+      <a href="https://github.com/user-attachments/assets/bfe3bde3-08af-4426-a9a1-11ad5cd63b33">
-        <img width="700" alt="image" src="https://github.com/user-attachments/assets/f6b9399a-5e51-4bae-b807-59128d0a940c" />
+        <img width="700" alt="image" src="https://github.com/user-attachments/assets/bfe3bde3-08af-4426-a9a1-11ad5cd63b33" />
       </a>
     </td>
     <td>
-      <a href="https://github.com/user-attachments/assets/a42ce460-c1fd-4489-a995-270516193897">
+      <a href="https://github.com/user-attachments/assets/7b60c9d0-efe4-474f-a27b-ea13bd0fabdc">
-        <img width="700" alt="image" src="https://github.com/user-attachments/assets/a42ce460-c1fd-4489-a995-270516193897" />
+        <img width="700" alt="image" src="https://github.com/user-attachments/assets/7b60c9d0-efe4-474f-a27b-ea13bd0fabdc" />
-      </a>
-    </td>
-    <td>
-      <a href="https://github.com/user-attachments/assets/21929f6d-c309-42fe-9c11-f1299e50fbd4">
-        <img width="700" alt="image" src="https://github.com/user-attachments/assets/21929f6d-c309-42fe-9c11-f1299e50fbd4" />
       </a>
     </td>
   </tr>
 </table>
 
-## What is Reflector?
-
-Reflector is a web application that utilizes local models to process audio content, providing:
-
-- **Real-time Transcription**: Convert speech to text using [Whisper](https://github.com/openai/whisper) (multi-language) or [Parakeet](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2) (English) models
-- **Speaker Diarization**: Identify and label different speakers using [Pyannote](https://github.com/pyannote/pyannote-audio) 3.1
-- **Live Translation**: Translate audio content in real-time to many languages with [Facebook Seamless-M4T](https://github.com/facebookresearch/seamless_communication)
-- **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.
-
 ## Background
 
 The project architecture consists of three primary components:
 
-- **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.
+- **Back-End**: Python server that offers an API and data persistence, found in `server/`.
+- **GPU implementation**: Providing services such as speech-to-text transcription, topic generation, automated summaries, and translations. Most reliable option is Modal deployment
 
-It also uses authentik for authentication if activated.
+It also uses authentik for authentication if activated, and Vercel for deployment and configuration of the front-end.
 
 ## Contribution Guidelines
 
@@ -89,8 +72,6 @@ Note: We currently do not have instructions for Windows users.
 
 ## Installation
 
-*Note: we're working toward better installation, theses instructions are not accurate for now*
-
 ### Frontend
 
 Start with `cd www`.
@@ -99,10 +80,11 @@ Start with `cd www`.
 
 ```bash
 pnpm install
-cp .env.example .env
+cp .env_template .env
+cp config-template.ts config.ts
 ```
 
-Then, fill in the environment variables in `.env` as needed. If you are unsure on how to proceed, ask in Zulip.
+Then, fill in the environment variables in `.env` and the configuration in `config.ts` as needed. If you are unsure on how to proceed, ask in Zulip.
 
 **Run in development mode**
 
@@ -167,41 +149,3 @@ You can manually process an audio file by calling the process tool:
 ```bash
 uv run python -m reflector.tools.process path/to/audio.wav
 ```
-
-## 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.
-
-Instead, all the variables are runtime. Variables needed to the frontend are served to the frontend app at initial render.
-
-It also means there's no static prebuild and no static files to serve for js/html.
-
-## Feature Flags
-
-Reflector uses environment variable-based feature flags to control application functionality. These flags allow you to enable or disable features without code changes.
-
-### Available Feature Flags
-
-| Feature Flag | Environment Variable |
-|-------------|---------------------|
-| `requireLogin` | `FEATURE_REQUIRE_LOGIN` |
-| `privacy` | `FEATURE_PRIVACY` |
-| `browse` | `FEATURE_BROWSE` |
-| `sendToZulip` | `FEATURE_SEND_TO_ZULIP` |
-| `rooms` | `FEATURE_ROOMS` |
-
-### Setting Feature Flags
-
-Feature flags are controlled via environment variables using the pattern `FEATURE_{FEATURE_NAME}` where `{FEATURE_NAME}` is the SCREAMING_SNAKE_CASE version of the feature name.
-
-**Examples:**
-```bash
-# Enable user authentication requirement
-FEATURE_REQUIRE_LOGIN=true
-
-# Disable browse functionality
-FEATURE_BROWSE=false
-
-# Enable Zulip integration
-FEATURE_SEND_TO_ZULIP=true
-```

compose.yml

@@ -6,7 +6,6 @@ services:
       - 1250:1250
     volumes:
       - ./server/:/app/
-      - /app/.venv
     env_file:
       - ./server/.env
     environment:
@@ -17,7 +16,6 @@ services:
       context: server
     volumes:
       - ./server/:/app/
-      - /app/.venv
     env_file:
       - ./server/.env
     environment:
@@ -28,7 +26,6 @@ services:
       context: server
     volumes:
       - ./server/:/app/
-      - /app/.venv
     env_file:
       - ./server/.env
     environment:
@@ -39,7 +36,7 @@ services:
     ports:
       - 6379:6379
   web:
-    image: node:22-alpine
+    image: node:18
     ports:
       - "3000:3000"
     command: sh -c "corepack enable && pnpm install && pnpm dev"
@@ -50,8 +47,6 @@ services:
       - /app/node_modules
     env_file:
       - ./www/.env.local
-    environment:
-      - NODE_ENV=development
 
   postgres:
     image: postgres:17

docker-compose.prod.yml

@@ -1,39 +0,0 @@
-# Production Docker Compose configuration for Frontend
-# Usage: docker compose -f docker-compose.prod.yml up -d
-
-services:
-  web:
-    build:
-      context: ./www
-      dockerfile: Dockerfile
-    image: reflector-frontend:latest
-    environment:
-      - KV_URL=${KV_URL:-redis://redis:6379}
-      - SITE_URL=${SITE_URL}
-      - API_URL=${API_URL}
-      - WEBSOCKET_URL=${WEBSOCKET_URL}
-      - NEXTAUTH_URL=${NEXTAUTH_URL:-http://localhost:3000}
-      - NEXTAUTH_SECRET=${NEXTAUTH_SECRET:-changeme-in-production}
-      - AUTHENTIK_ISSUER=${AUTHENTIK_ISSUER}
-      - AUTHENTIK_CLIENT_ID=${AUTHENTIK_CLIENT_ID}
-      - AUTHENTIK_CLIENT_SECRET=${AUTHENTIK_CLIENT_SECRET}
-      - AUTHENTIK_REFRESH_TOKEN_URL=${AUTHENTIK_REFRESH_TOKEN_URL}
-      - SENTRY_DSN=${SENTRY_DSN}
-      - SENTRY_IGNORE_API_RESOLUTION_ERROR=${SENTRY_IGNORE_API_RESOLUTION_ERROR:-1}
-    depends_on:
-      - redis
-    restart: unless-stopped
-
-  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
-
-volumes:
-  redis_data:

gpu/modal_deployments/.gitignore

@@ -1,33 +0,0 @@
-# OS / Editor
-.DS_Store
-.vscode/
-.idea/
-
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-
-# Logs
-*.log
-
-# Env and secrets
-.env
-.env.*
-*.env
-*.secret
-
-# Build / dist
-build/
-dist/
-.eggs/
-*.egg-info/
-
-# Coverage / test
-.pytest_cache/
-.coverage*
-htmlcov/
-
-# Modal local state (if any)
-modal_mounts/
-.modal_cache/

gpu/modal_deployments/reflector_transcriber.py

@@ -1,608 +0,0 @@
-import os
-import sys
-import threading
-import uuid
-from typing import Generator, Mapping, NamedTuple, NewType, TypedDict
-from urllib.parse import urlparse
-
-import modal
-
-MODEL_NAME = "large-v2"
-MODEL_COMPUTE_TYPE: str = "float16"
-MODEL_NUM_WORKERS: int = 1
-MINUTES = 60  # seconds
-SAMPLERATE = 16000
-UPLOADS_PATH = "/uploads"
-CACHE_PATH = "/models"
-SUPPORTED_FILE_EXTENSIONS = ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"]
-VAD_CONFIG = {
-    "batch_max_duration": 30.0,
-    "silence_padding": 0.5,
-    "window_size": 512,
-}
-
-
-WhisperUniqFilename = NewType("WhisperUniqFilename", str)
-AudioFileExtension = NewType("AudioFileExtension", str)
-
-app = modal.App("reflector-transcriber")
-
-model_cache = modal.Volume.from_name("models", create_if_missing=True)
-upload_volume = modal.Volume.from_name("whisper-uploads", create_if_missing=True)
-
-
-class TimeSegment(NamedTuple):
-    """Represents a time segment with start and end times."""
-
-    start: float
-    end: float
-
-
-class AudioSegment(NamedTuple):
-    """Represents an audio segment with timing and audio data."""
-
-    start: float
-    end: float
-    audio: any
-
-
-class TranscriptResult(NamedTuple):
-    """Represents a transcription result with text and word timings."""
-
-    text: str
-    words: list["WordTiming"]
-
-
-class WordTiming(TypedDict):
-    """Represents a word with its timing information."""
-
-    word: str
-    start: float
-    end: float
-
-
-def download_model():
-    from faster_whisper import download_model
-
-    model_cache.reload()
-
-    download_model(MODEL_NAME, cache_dir=CACHE_PATH)
-
-    model_cache.commit()
-
-
-image = (
-    modal.Image.debian_slim(python_version="3.12")
-    .env(
-        {
-            "HF_HUB_ENABLE_HF_TRANSFER": "1",
-            "LD_LIBRARY_PATH": (
-                "/usr/local/lib/python3.12/site-packages/nvidia/cudnn/lib/:"
-                "/opt/conda/lib/python3.12/site-packages/nvidia/cublas/lib/"
-            ),
-        }
-    )
-    .apt_install("ffmpeg")
-    .pip_install(
-        "huggingface_hub==0.27.1",
-        "hf-transfer==0.1.9",
-        "torch==2.5.1",
-        "faster-whisper==1.1.1",
-        "fastapi==0.115.12",
-        "requests",
-        "librosa==0.10.1",
-        "numpy<2",
-        "silero-vad==5.1.0",
-    )
-    .run_function(download_model, volumes={CACHE_PATH: model_cache})
-)
-
-
-def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
-    parsed_url = urlparse(url)
-    url_path = parsed_url.path
-
-    for ext in SUPPORTED_FILE_EXTENSIONS:
-        if url_path.lower().endswith(f".{ext}"):
-            return AudioFileExtension(ext)
-
-    content_type = headers.get("content-type", "").lower()
-    if "audio/mpeg" in content_type or "audio/mp3" in content_type:
-        return AudioFileExtension("mp3")
-    if "audio/wav" in content_type:
-        return AudioFileExtension("wav")
-    if "audio/mp4" in content_type:
-        return AudioFileExtension("mp4")
-
-    raise ValueError(
-        f"Unsupported audio format for URL: {url}. "
-        f"Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
-    )
-
-
-def download_audio_to_volume(
-    audio_file_url: str,
-) -> tuple[WhisperUniqFilename, AudioFileExtension]:
-    import requests
-    from fastapi import HTTPException
-
-    response = requests.head(audio_file_url, allow_redirects=True)
-    if response.status_code == 404:
-        raise HTTPException(status_code=404, detail="Audio file not found")
-
-    response = requests.get(audio_file_url, allow_redirects=True)
-    response.raise_for_status()
-
-    audio_suffix = detect_audio_format(audio_file_url, response.headers)
-    unique_filename = WhisperUniqFilename(f"{uuid.uuid4()}.{audio_suffix}")
-    file_path = f"{UPLOADS_PATH}/{unique_filename}"
-
-    with open(file_path, "wb") as f:
-        f.write(response.content)
-
-    upload_volume.commit()
-    return unique_filename, audio_suffix
-
-
-def pad_audio(audio_array, sample_rate: int = SAMPLERATE):
-    """Add 0.5s of silence if audio is shorter than the silence_padding window.
-
-    Whisper does not require this strictly, but aligning behavior with Parakeet
-    avoids edge-case crashes on extremely short inputs and makes comparisons easier.
-    """
-    import numpy as np
-
-    audio_duration = len(audio_array) / sample_rate
-    if audio_duration < VAD_CONFIG["silence_padding"]:
-        silence_samples = int(sample_rate * VAD_CONFIG["silence_padding"])
-        silence = np.zeros(silence_samples, dtype=np.float32)
-        return np.concatenate([audio_array, silence])
-    return audio_array
-
-
-@app.cls(
-    gpu="A10G",
-    timeout=5 * MINUTES,
-    scaledown_window=5 * MINUTES,
-    image=image,
-    volumes={CACHE_PATH: model_cache, UPLOADS_PATH: upload_volume},
-)
-@modal.concurrent(max_inputs=10)
-class TranscriberWhisperLive:
-    """Live transcriber class for small audio segments (A10G).
-
-    Mirrors the Parakeet live class API but uses Faster-Whisper under the hood.
-    """
-
-    @modal.enter()
-    def enter(self):
-        import faster_whisper
-        import torch
-
-        self.lock = threading.Lock()
-        self.use_gpu = torch.cuda.is_available()
-        self.device = "cuda" if self.use_gpu else "cpu"
-        self.model = faster_whisper.WhisperModel(
-            MODEL_NAME,
-            device=self.device,
-            compute_type=MODEL_COMPUTE_TYPE,
-            num_workers=MODEL_NUM_WORKERS,
-            download_root=CACHE_PATH,
-            local_files_only=True,
-        )
-        print(f"Model is on device: {self.device}")
-
-    @modal.method()
-    def transcribe_segment(
-        self,
-        filename: str,
-        language: str = "en",
-    ):
-        """Transcribe a single uploaded audio file by filename."""
-        upload_volume.reload()
-
-        file_path = f"{UPLOADS_PATH}/{filename}"
-        if not os.path.exists(file_path):
-            raise FileNotFoundError(f"File not found: {file_path}")
-
-        with self.lock:
-            with NoStdStreams():
-                segments, _ = self.model.transcribe(
-                    file_path,
-                    language=language,
-                    beam_size=5,
-                    word_timestamps=True,
-                    vad_filter=True,
-                    vad_parameters={"min_silence_duration_ms": 500},
-                )
-
-        segments = list(segments)
-        text = "".join(segment.text for segment in segments).strip()
-        words = [
-            {
-                "word": word.word,
-                "start": round(float(word.start), 2),
-                "end": round(float(word.end), 2),
-            }
-            for segment in segments
-            for word in segment.words
-        ]
-
-        return {"text": text, "words": words}
-
-    @modal.method()
-    def transcribe_batch(
-        self,
-        filenames: list[str],
-        language: str = "en",
-    ):
-        """Transcribe multiple uploaded audio files and return per-file results."""
-        upload_volume.reload()
-
-        results = []
-        for filename in filenames:
-            file_path = f"{UPLOADS_PATH}/{filename}"
-            if not os.path.exists(file_path):
-                raise FileNotFoundError(f"Batch file not found: {file_path}")
-
-            with self.lock:
-                with NoStdStreams():
-                    segments, _ = self.model.transcribe(
-                        file_path,
-                        language=language,
-                        beam_size=5,
-                        word_timestamps=True,
-                        vad_filter=True,
-                        vad_parameters={"min_silence_duration_ms": 500},
-                    )
-
-            segments = list(segments)
-            text = "".join(seg.text for seg in segments).strip()
-            words = [
-                {
-                    "word": w.word,
-                    "start": round(float(w.start), 2),
-                    "end": round(float(w.end), 2),
-                }
-                for seg in segments
-                for w in seg.words
-            ]
-
-            results.append(
-                {
-                    "filename": filename,
-                    "text": text,
-                    "words": words,
-                }
-            )
-
-        return results
-
-
-@app.cls(
-    gpu="L40S",
-    timeout=15 * MINUTES,
-    image=image,
-    volumes={CACHE_PATH: model_cache, UPLOADS_PATH: upload_volume},
-)
-class TranscriberWhisperFile:
-    """File transcriber for larger/longer audio, using VAD-driven batching (L40S)."""
-
-    @modal.enter()
-    def enter(self):
-        import faster_whisper
-        import torch
-        from silero_vad import load_silero_vad
-
-        self.lock = threading.Lock()
-        self.use_gpu = torch.cuda.is_available()
-        self.device = "cuda" if self.use_gpu else "cpu"
-        self.model = faster_whisper.WhisperModel(
-            MODEL_NAME,
-            device=self.device,
-            compute_type=MODEL_COMPUTE_TYPE,
-            num_workers=MODEL_NUM_WORKERS,
-            download_root=CACHE_PATH,
-            local_files_only=True,
-        )
-        self.vad_model = load_silero_vad(onnx=False)
-
-    @modal.method()
-    def transcribe_segment(
-        self, filename: str, timestamp_offset: float = 0.0, language: str = "en"
-    ):
-        import librosa
-        import numpy as np
-        from silero_vad import VADIterator
-
-        def vad_segments(
-            audio_array,
-            sample_rate: int = SAMPLERATE,
-            window_size: int = VAD_CONFIG["window_size"],
-        ) -> Generator[TimeSegment, None, None]:
-            """Generate speech segments as TimeSegment using Silero VAD."""
-            iterator = VADIterator(self.vad_model, sampling_rate=sample_rate)
-            start = None
-            for i in range(0, len(audio_array), window_size):
-                chunk = audio_array[i : i + window_size]
-                if len(chunk) < window_size:
-                    chunk = np.pad(
-                        chunk, (0, window_size - len(chunk)), mode="constant"
-                    )
-                speech = iterator(chunk)
-                if not speech:
-                    continue
-                if "start" in speech:
-                    start = speech["start"]
-                    continue
-                if "end" in speech and start is not None:
-                    end = speech["end"]
-                    yield TimeSegment(
-                        start / float(SAMPLERATE), end / float(SAMPLERATE)
-                    )
-                    start = None
-            iterator.reset_states()
-
-        upload_volume.reload()
-        file_path = f"{UPLOADS_PATH}/{filename}"
-        if not os.path.exists(file_path):
-            raise FileNotFoundError(f"File not found: {file_path}")
-
-        audio_array, _sr = librosa.load(file_path, sr=SAMPLERATE, mono=True)
-
-        # Batch segments up to ~30s windows by merging contiguous VAD segments
-        merged_batches: list[TimeSegment] = []
-        batch_start = None
-        batch_end = None
-        max_duration = VAD_CONFIG["batch_max_duration"]
-        for segment in vad_segments(audio_array):
-            seg_start, seg_end = segment.start, segment.end
-            if batch_start is None:
-                batch_start, batch_end = seg_start, seg_end
-                continue
-            if seg_end - batch_start <= max_duration:
-                batch_end = seg_end
-            else:
-                merged_batches.append(TimeSegment(batch_start, batch_end))
-                batch_start, batch_end = seg_start, seg_end
-        if batch_start is not None and batch_end is not None:
-            merged_batches.append(TimeSegment(batch_start, batch_end))
-
-        all_text = []
-        all_words = []
-
-        for segment in merged_batches:
-            start_time, end_time = segment.start, segment.end
-            s_idx = int(start_time * SAMPLERATE)
-            e_idx = int(end_time * SAMPLERATE)
-            segment = audio_array[s_idx:e_idx]
-            segment = pad_audio(segment, SAMPLERATE)
-
-            with self.lock:
-                segments, _ = self.model.transcribe(
-                    segment,
-                    language=language,
-                    beam_size=5,
-                    word_timestamps=True,
-                    vad_filter=True,
-                    vad_parameters={"min_silence_duration_ms": 500},
-                )
-
-            segments = list(segments)
-            text = "".join(seg.text for seg in segments).strip()
-            words = [
-                {
-                    "word": w.word,
-                    "start": round(float(w.start) + start_time + timestamp_offset, 2),
-                    "end": round(float(w.end) + start_time + timestamp_offset, 2),
-                }
-                for seg in segments
-                for w in seg.words
-            ]
-            if text:
-                all_text.append(text)
-            all_words.extend(words)
-
-        return {"text": " ".join(all_text), "words": all_words}
-
-
-def detect_audio_format(url: str, headers: dict) -> str:
-    from urllib.parse import urlparse
-
-    from fastapi import HTTPException
-
-    url_path = urlparse(url).path
-    for ext in SUPPORTED_FILE_EXTENSIONS:
-        if url_path.lower().endswith(f".{ext}"):
-            return ext
-
-    content_type = headers.get("content-type", "").lower()
-    if "audio/mpeg" in content_type or "audio/mp3" in content_type:
-        return "mp3"
-    if "audio/wav" in content_type:
-        return "wav"
-    if "audio/mp4" in content_type:
-        return "mp4"
-
-    raise HTTPException(
-        status_code=400,
-        detail=(
-            f"Unsupported audio format for URL. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
-        ),
-    )
-
-
-def download_audio_to_volume(audio_file_url: str) -> tuple[str, str]:
-    import requests
-    from fastapi import HTTPException
-
-    response = requests.head(audio_file_url, allow_redirects=True)
-    if response.status_code == 404:
-        raise HTTPException(status_code=404, detail="Audio file not found")
-
-    response = requests.get(audio_file_url, allow_redirects=True)
-    response.raise_for_status()
-
-    audio_suffix = detect_audio_format(audio_file_url, response.headers)
-    unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
-    file_path = f"{UPLOADS_PATH}/{unique_filename}"
-
-    with open(file_path, "wb") as f:
-        f.write(response.content)
-
-    upload_volume.commit()
-    return unique_filename, audio_suffix
-
-
-@app.function(
-    scaledown_window=60,
-    timeout=600,
-    secrets=[
-        modal.Secret.from_name("reflector-gpu"),
-    ],
-    volumes={CACHE_PATH: model_cache, UPLOADS_PATH: upload_volume},
-    image=image,
-)
-@modal.concurrent(max_inputs=40)
-@modal.asgi_app()
-def web():
-    from fastapi import (
-        Body,
-        Depends,
-        FastAPI,
-        Form,
-        HTTPException,
-        UploadFile,
-        status,
-    )
-    from fastapi.security import OAuth2PasswordBearer
-
-    transcriber_live = TranscriberWhisperLive()
-    transcriber_file = TranscriberWhisperFile()
-
-    app = FastAPI()
-
-    oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
-
-    def apikey_auth(apikey: str = Depends(oauth2_scheme)):
-        if apikey == os.environ["REFLECTOR_GPU_APIKEY"]:
-            return
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail="Invalid API key",
-            headers={"WWW-Authenticate": "Bearer"},
-        )
-
-    class TranscriptResponse(dict):
-        pass
-
-    @app.post("/v1/audio/transcriptions", dependencies=[Depends(apikey_auth)])
-    def transcribe(
-        file: UploadFile = None,
-        files: list[UploadFile] | None = None,
-        model: str = Form(MODEL_NAME),
-        language: str = Form("en"),
-        batch: bool = Form(False),
-    ):
-        if not file and not files:
-            raise HTTPException(
-                status_code=400, detail="Either 'file' or 'files' parameter is required"
-            )
-        if batch and not files:
-            raise HTTPException(
-                status_code=400, detail="Batch transcription requires 'files'"
-            )
-
-        upload_files = [file] if file else files
-
-        uploaded_filenames: list[str] = []
-        for upload_file in upload_files:
-            audio_suffix = upload_file.filename.split(".")[-1]
-            if audio_suffix not in SUPPORTED_FILE_EXTENSIONS:
-                raise HTTPException(
-                    status_code=400,
-                    detail=(
-                        f"Unsupported audio format. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
-                    ),
-                )
-
-            unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
-            file_path = f"{UPLOADS_PATH}/{unique_filename}"
-            with open(file_path, "wb") as f:
-                content = upload_file.file.read()
-                f.write(content)
-            uploaded_filenames.append(unique_filename)
-
-        upload_volume.commit()
-
-        try:
-            if batch and len(upload_files) > 1:
-                func = transcriber_live.transcribe_batch.spawn(
-                    filenames=uploaded_filenames,
-                    language=language,
-                )
-                results = func.get()
-                return {"results": results}
-
-            results = []
-            for filename in uploaded_filenames:
-                func = transcriber_live.transcribe_segment.spawn(
-                    filename=filename,
-                    language=language,
-                )
-                result = func.get()
-                result["filename"] = filename
-                results.append(result)
-
-            return {"results": results} if len(results) > 1 else results[0]
-        finally:
-            for filename in uploaded_filenames:
-                try:
-                    file_path = f"{UPLOADS_PATH}/{filename}"
-                    os.remove(file_path)
-                except Exception:
-                    pass
-            upload_volume.commit()
-
-    @app.post("/v1/audio/transcriptions-from-url", dependencies=[Depends(apikey_auth)])
-    def transcribe_from_url(
-        audio_file_url: str = Body(
-            ..., description="URL of the audio file to transcribe"
-        ),
-        model: str = Body(MODEL_NAME),
-        language: str = Body("en"),
-        timestamp_offset: float = Body(0.0),
-    ):
-        unique_filename, _audio_suffix = download_audio_to_volume(audio_file_url)
-        try:
-            func = transcriber_file.transcribe_segment.spawn(
-                filename=unique_filename,
-                timestamp_offset=timestamp_offset,
-                language=language,
-            )
-            result = func.get()
-            return result
-        finally:
-            try:
-                file_path = f"{UPLOADS_PATH}/{unique_filename}"
-                os.remove(file_path)
-                upload_volume.commit()
-            except Exception:
-                pass
-
-    return app
-
-
-class NoStdStreams:
-    def __init__(self):
-        self.devnull = open(os.devnull, "w")
-
-    def __enter__(self):
-        self._stdout, self._stderr = sys.stdout, sys.stderr
-        self._stdout.flush()
-        self._stderr.flush()
-        sys.stdout, sys.stderr = self.devnull, self.devnull
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        sys.stdout, sys.stderr = self._stdout, self._stderr
-        self.devnull.close()

gpu/self_hosted/.env.example

@@ -1,2 +0,0 @@
-REFLECTOR_GPU_APIKEY=
-HF_TOKEN=

gpu/self_hosted/.gitignore

@@ -1,38 +0,0 @@
-cache/
-
-# OS / Editor
-.DS_Store
-.vscode/
-.idea/
-
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-
-# Env and secrets
-.env
-*.env
-*.secret
-HF_TOKEN
-REFLECTOR_GPU_APIKEY
-
-# Virtual env / uv
-.venv/
-venv/
-ENV/
-uv/
-
-# Build / dist
-build/
-dist/
-.eggs/
-*.egg-info/
-
-# Coverage / test
-.pytest_cache/
-.coverage*
-htmlcov/
-
-# Logs
-*.log

gpu/self_hosted/Dockerfile

@@ -1,46 +0,0 @@
-FROM python:3.12-slim
-
-ENV PYTHONUNBUFFERED=1 \
-    UV_LINK_MODE=copy \
-    UV_NO_CACHE=1
-
-WORKDIR /tmp
-RUN apt-get update \
- && apt-get install -y \
-    ffmpeg \
-    curl \
-    ca-certificates \
-    gnupg \
-    wget \
- && apt-get clean
-# 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 \
- && 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/*
-ADD https://astral.sh/uv/install.sh /uv-installer.sh
-RUN sh /uv-installer.sh && rm /uv-installer.sh
-ENV PATH="/root/.local/bin/:$PATH"
-ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_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/
-
-EXPOSE 8000
-
-CMD ["sh", "/app/runserver.sh"]
-
-

gpu/self_hosted/README.md

@@ -1,73 +0,0 @@
-# Self-hosted Model API
-
-Run transcription, translation, and diarization services compatible with Reflector's GPU Model API. Works on CPU or GPU.
-
-Environment variables
-
-- REFLECTOR_GPU_APIKEY: Optional Bearer token. If unset, auth is disabled.
-- HF_TOKEN: Optional. Required for diarization to download pyannote pipelines
-
-Requirements
-
-- FFmpeg must be installed and on PATH (used for URL-based and segmented transcription)
-- Python 3.12+
-- NVIDIA GPU optional. If available, it will be used automatically
-
-Local run
-Set env vars in self_hosted/.env file
-uv sync
-
-uv run uvicorn main:app --host 0.0.0.0 --port 8000
-
-Authentication
-
-- If REFLECTOR_GPU_APIKEY is set, include header: Authorization: Bearer <key>
-
-Endpoints
-
-- POST /v1/audio/transcriptions
-
-  - multipart/form-data
-  - fields: file (single file) OR files[] (multiple files), language, batch (true/false)
-  - response: single { text, words, filename } or { results: [ ... ] }
-
-- POST /v1/audio/transcriptions-from-url
-
-  - application/json
-  - body: { audio_file_url, language, timestamp_offset }
-  - response: { text, words }
-
-- POST /translate
-
-  - text: query parameter
-  - body (application/json): { source_language, target_language }
-  - response: { text: { <src>: original, <tgt>: translated } }
-
-- POST /diarize
-  - query parameters: audio_file_url, timestamp (optional)
-  - requires HF_TOKEN to be set (for pyannote)
-  - response: { diarization: [ { start, end, speaker } ] }
-
-OpenAPI docs
-
-- Visit /docs when the server is running
-
-Docker
-
-- Not yet provided in this directory. A Dockerfile will be added later. For now, use Local run above
-
-Conformance tests
-
-# From this directory
-
-TRANSCRIPT_URL=http://localhost:8000 \
-TRANSCRIPT_API_KEY=dev-key \
-uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_transcript.py
-
-TRANSLATION_URL=http://localhost:8000 \
-TRANSLATION_API_KEY=dev-key \
-uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_translation.py
-
-DIARIZATION_URL=http://localhost:8000 \
-DIARIZATION_API_KEY=dev-key \
-uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_diarization.py

gpu/self_hosted/app/auth.py

@@ -1,19 +0,0 @@
-import os
-
-from fastapi import Depends, HTTPException, status
-from fastapi.security import OAuth2PasswordBearer
-
-oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
-
-
-def apikey_auth(apikey: str = Depends(oauth2_scheme)):
-    required_key = os.environ.get("REFLECTOR_GPU_APIKEY")
-    if not required_key:
-        return
-    if apikey == required_key:
-        return
-    raise HTTPException(
-        status_code=status.HTTP_401_UNAUTHORIZED,
-        detail="Invalid API key",
-        headers={"WWW-Authenticate": "Bearer"},
-    )

gpu/self_hosted/app/config.py

@@ -1,12 +0,0 @@
-from pathlib import Path
-
-SUPPORTED_FILE_EXTENSIONS = ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"]
-SAMPLE_RATE = 16000
-VAD_CONFIG = {
-    "batch_max_duration": 30.0,
-    "silence_padding": 0.5,
-    "window_size": 512,
-}
-
-# App-level paths
-UPLOADS_PATH = Path("/tmp/whisper-uploads")

gpu/self_hosted/app/factory.py

@@ -1,30 +0,0 @@
-from contextlib import asynccontextmanager
-
-from fastapi import FastAPI
-
-from .routers.diarization import router as diarization_router
-from .routers.transcription import router as transcription_router
-from .routers.translation import router as translation_router
-from .services.transcriber import WhisperService
-from .services.diarizer import PyannoteDiarizationService
-from .utils import ensure_dirs
-
-
-@asynccontextmanager
-async def lifespan(app: FastAPI):
-    ensure_dirs()
-    whisper_service = WhisperService()
-    whisper_service.load()
-    app.state.whisper = whisper_service
-    diarization_service = PyannoteDiarizationService()
-    diarization_service.load()
-    app.state.diarizer = diarization_service
-    yield
-
-
-def create_app() -> FastAPI:
-    app = FastAPI(lifespan=lifespan)
-    app.include_router(transcription_router)
-    app.include_router(translation_router)
-    app.include_router(diarization_router)
-    return app

gpu/self_hosted/app/routers/diarization.py

@@ -1,30 +0,0 @@
-from typing import List
-
-from fastapi import APIRouter, Depends, Request
-from pydantic import BaseModel
-
-from ..auth import apikey_auth
-from ..services.diarizer import PyannoteDiarizationService
-from ..utils import download_audio_file
-
-router = APIRouter(tags=["diarization"])
-
-
-class DiarizationSegment(BaseModel):
-    start: float
-    end: float
-    speaker: int
-
-
-class DiarizationResponse(BaseModel):
-    diarization: List[DiarizationSegment]
-
-
-@router.post(
-    "/diarize", dependencies=[Depends(apikey_auth)], response_model=DiarizationResponse
-)
-def diarize(request: Request, audio_file_url: str, timestamp: float = 0.0):
-    with download_audio_file(audio_file_url) as (file_path, _ext):
-        file_path = str(file_path)
-        diarizer: PyannoteDiarizationService = request.app.state.diarizer
-        return diarizer.diarize_file(file_path, timestamp=timestamp)

gpu/self_hosted/app/routers/transcription.py

@@ -1,109 +0,0 @@
-import uuid
-from typing import Optional, Union
-
-from fastapi import APIRouter, Body, Depends, Form, HTTPException, Request, UploadFile
-from pydantic import BaseModel
-from pathlib import Path
-from ..auth import apikey_auth
-from ..config import SUPPORTED_FILE_EXTENSIONS, UPLOADS_PATH
-from ..services.transcriber import MODEL_NAME
-from ..utils import cleanup_uploaded_files, download_audio_file
-
-router = APIRouter(prefix="/v1/audio", tags=["transcription"])
-
-
-class WordTiming(BaseModel):
-    word: str
-    start: float
-    end: float
-
-
-class TranscriptResult(BaseModel):
-    text: str
-    words: list[WordTiming]
-    filename: Optional[str] = None
-
-
-class TranscriptBatchResponse(BaseModel):
-    results: list[TranscriptResult]
-
-
-@router.post(
-    "/transcriptions",
-    dependencies=[Depends(apikey_auth)],
-    response_model=Union[TranscriptResult, TranscriptBatchResponse],
-)
-def transcribe(
-    request: Request,
-    file: UploadFile = None,
-    files: list[UploadFile] | None = None,
-    model: str = Form(MODEL_NAME),
-    language: str = Form("en"),
-    batch: bool = Form(False),
-):
-    service = request.app.state.whisper
-    if not file and not files:
-        raise HTTPException(
-            status_code=400, detail="Either 'file' or 'files' parameter is required"
-        )
-    if batch and not files:
-        raise HTTPException(
-            status_code=400, detail="Batch transcription requires 'files'"
-        )
-
-    upload_files = [file] if file else files
-
-    uploaded_paths: list[Path] = []
-    with cleanup_uploaded_files(uploaded_paths):
-        for upload_file in upload_files:
-            audio_suffix = upload_file.filename.split(".")[-1].lower()
-            if audio_suffix not in SUPPORTED_FILE_EXTENSIONS:
-                raise HTTPException(
-                    status_code=400,
-                    detail=(
-                        f"Unsupported audio format. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
-                    ),
-                )
-            unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
-            file_path = UPLOADS_PATH / unique_filename
-            with open(file_path, "wb") as f:
-                content = upload_file.file.read()
-                f.write(content)
-            uploaded_paths.append(file_path)
-
-        if batch and len(upload_files) > 1:
-            results = []
-            for path in uploaded_paths:
-                result = service.transcribe_file(str(path), language=language)
-                result["filename"] = path.name
-                results.append(result)
-            return {"results": results}
-
-        results = []
-        for path in uploaded_paths:
-            result = service.transcribe_file(str(path), language=language)
-            result["filename"] = path.name
-            results.append(result)
-
-        return {"results": results} if len(results) > 1 else results[0]
-
-
-@router.post(
-    "/transcriptions-from-url",
-    dependencies=[Depends(apikey_auth)],
-    response_model=TranscriptResult,
-)
-def transcribe_from_url(
-    request: Request,
-    audio_file_url: str = Body(..., description="URL of the audio file to transcribe"),
-    model: str = Body(MODEL_NAME),
-    language: str = Body("en"),
-    timestamp_offset: float = Body(0.0),
-):
-    service = request.app.state.whisper
-    with download_audio_file(audio_file_url) as (file_path, _ext):
-        file_path = str(file_path)
-        result = service.transcribe_vad_url_segment(
-            file_path=file_path, timestamp_offset=timestamp_offset, language=language
-        )
-        return result

gpu/self_hosted/app/routers/translation.py

@@ -1,28 +0,0 @@
-from typing import Dict
-
-from fastapi import APIRouter, Body, Depends
-from pydantic import BaseModel
-
-from ..auth import apikey_auth
-from ..services.translator import TextTranslatorService
-
-router = APIRouter(tags=["translation"])
-
-translator = TextTranslatorService()
-
-
-class TranslationResponse(BaseModel):
-    text: Dict[str, str]
-
-
-@router.post(
-    "/translate",
-    dependencies=[Depends(apikey_auth)],
-    response_model=TranslationResponse,
-)
-def translate(
-    text: str,
-    source_language: str = Body("en"),
-    target_language: str = Body("fr"),
-):
-    return translator.translate(text, source_language, target_language)

gpu/self_hosted/app/services/diarizer.py

@@ -1,42 +0,0 @@
-import os
-import threading
-
-import torch
-import torchaudio
-from pyannote.audio import Pipeline
-
-
-class PyannoteDiarizationService:
-    def __init__(self):
-        self._pipeline = None
-        self._device = "cpu"
-        self._lock = threading.Lock()
-
-    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"),
-        )
-        self._pipeline.to(torch.device(self._device))
-
-    def diarize_file(self, file_path: str, timestamp: float = 0.0) -> dict:
-        if self._pipeline is None:
-            self.load()
-        waveform, sample_rate = torchaudio.load(file_path)
-        with self._lock:
-            diarization = self._pipeline(
-                {"waveform": waveform, "sample_rate": sample_rate}
-            )
-        words = []
-        for diarization_segment, _, speaker in diarization.itertracks(yield_label=True):
-            words.append(
-                {
-                    "start": round(timestamp + diarization_segment.start, 3),
-                    "end": round(timestamp + diarization_segment.end, 3),
-                    "speaker": int(speaker[-2:])
-                    if speaker and speaker[-2:].isdigit()
-                    else 0,
-                }
-            )
-        return {"diarization": words}

gpu/self_hosted/app/services/transcriber.py

@@ -1,208 +0,0 @@
-import os
-import shutil
-import subprocess
-import threading
-from typing import Generator
-
-import faster_whisper
-import librosa
-import numpy as np
-import torch
-from fastapi import HTTPException
-from silero_vad import VADIterator, load_silero_vad
-
-from ..config import SAMPLE_RATE, VAD_CONFIG
-
-# Whisper configuration (service-local defaults)
-MODEL_NAME = "large-v2"
-# None delegates compute type to runtime: float16 on CUDA, int8 on CPU
-MODEL_COMPUTE_TYPE = None
-MODEL_NUM_WORKERS = 1
-CACHE_PATH = os.path.join(os.path.expanduser("~"), ".cache", "reflector-whisper")
-from ..utils import NoStdStreams
-
-
-class WhisperService:
-    def __init__(self):
-        self.model = None
-        self.device = "cpu"
-        self.lock = threading.Lock()
-
-    def load(self):
-        self.device = "cuda" if torch.cuda.is_available() else "cpu"
-        compute_type = MODEL_COMPUTE_TYPE or (
-            "float16" if self.device == "cuda" else "int8"
-        )
-        self.model = faster_whisper.WhisperModel(
-            MODEL_NAME,
-            device=self.device,
-            compute_type=compute_type,
-            num_workers=MODEL_NUM_WORKERS,
-            download_root=CACHE_PATH,
-        )
-
-    def pad_audio(self, audio_array, sample_rate: int = SAMPLE_RATE):
-        audio_duration = len(audio_array) / sample_rate
-        if audio_duration < VAD_CONFIG["silence_padding"]:
-            silence_samples = int(sample_rate * VAD_CONFIG["silence_padding"])
-            silence = np.zeros(silence_samples, dtype=np.float32)
-            return np.concatenate([audio_array, silence])
-        return audio_array
-
-    def enforce_word_timing_constraints(self, words: list[dict]) -> list[dict]:
-        if len(words) <= 1:
-            return words
-        enforced: list[dict] = []
-        for i, word in enumerate(words):
-            current = dict(word)
-            if i < len(words) - 1:
-                next_start = words[i + 1]["start"]
-                if current["end"] > next_start:
-                    current["end"] = next_start
-            enforced.append(current)
-        return enforced
-
-    def transcribe_file(self, file_path: str, language: str = "en") -> dict:
-        input_for_model: str | "object" = file_path
-        try:
-            audio_array, _sample_rate = librosa.load(
-                file_path, sr=SAMPLE_RATE, mono=True
-            )
-            if len(audio_array) / float(SAMPLE_RATE) < VAD_CONFIG["silence_padding"]:
-                input_for_model = self.pad_audio(audio_array, SAMPLE_RATE)
-        except Exception:
-            pass
-
-        with self.lock:
-            with NoStdStreams():
-                segments, _ = self.model.transcribe(
-                    input_for_model,
-                    language=language,
-                    beam_size=5,
-                    word_timestamps=True,
-                    vad_filter=True,
-                    vad_parameters={"min_silence_duration_ms": 500},
-                )
-
-        segments = list(segments)
-        text = "".join(segment.text for segment in segments).strip()
-        words = [
-            {
-                "word": word.word,
-                "start": round(float(word.start), 2),
-                "end": round(float(word.end), 2),
-            }
-            for segment in segments
-            for word in segment.words
-        ]
-        words = self.enforce_word_timing_constraints(words)
-        return {"text": text, "words": words}
-
-    def transcribe_vad_url_segment(
-        self, file_path: str, timestamp_offset: float = 0.0, language: str = "en"
-    ) -> dict:
-        def load_audio_via_ffmpeg(input_path: str, sample_rate: int) -> np.ndarray:
-            ffmpeg_bin = shutil.which("ffmpeg") or "ffmpeg"
-            cmd = [
-                ffmpeg_bin,
-                "-nostdin",
-                "-threads",
-                "1",
-                "-i",
-                input_path,
-                "-f",
-                "f32le",
-                "-acodec",
-                "pcm_f32le",
-                "-ac",
-                "1",
-                "-ar",
-                str(sample_rate),
-                "pipe:1",
-            ]
-            try:
-                proc = subprocess.run(
-                    cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=True
-                )
-            except Exception as e:
-                raise HTTPException(status_code=400, detail=f"ffmpeg failed: {e}")
-            audio = np.frombuffer(proc.stdout, dtype=np.float32)
-            return audio
-
-        def vad_segments(
-            audio_array,
-            sample_rate: int = SAMPLE_RATE,
-            window_size: int = VAD_CONFIG["window_size"],
-        ) -> Generator[tuple[float, float], None, None]:
-            vad_model = load_silero_vad(onnx=False)
-            iterator = VADIterator(vad_model, sampling_rate=sample_rate)
-            start = None
-            for i in range(0, len(audio_array), window_size):
-                chunk = audio_array[i : i + window_size]
-                if len(chunk) < window_size:
-                    chunk = np.pad(
-                        chunk, (0, window_size - len(chunk)), mode="constant"
-                    )
-                speech = iterator(chunk)
-                if not speech:
-                    continue
-                if "start" in speech:
-                    start = speech["start"]
-                    continue
-                if "end" in speech and start is not None:
-                    end = speech["end"]
-                    yield (start / float(SAMPLE_RATE), end / float(SAMPLE_RATE))
-                    start = None
-            iterator.reset_states()
-
-        audio_array = load_audio_via_ffmpeg(file_path, SAMPLE_RATE)
-
-        merged_batches: list[tuple[float, float]] = []
-        batch_start = None
-        batch_end = None
-        max_duration = VAD_CONFIG["batch_max_duration"]
-        for seg_start, seg_end in vad_segments(audio_array):
-            if batch_start is None:
-                batch_start, batch_end = seg_start, seg_end
-                continue
-            if seg_end - batch_start <= max_duration:
-                batch_end = seg_end
-            else:
-                merged_batches.append((batch_start, batch_end))
-                batch_start, batch_end = seg_start, seg_end
-        if batch_start is not None and batch_end is not None:
-            merged_batches.append((batch_start, batch_end))
-
-        all_text = []
-        all_words = []
-        for start_time, end_time in merged_batches:
-            s_idx = int(start_time * SAMPLE_RATE)
-            e_idx = int(end_time * SAMPLE_RATE)
-            segment = audio_array[s_idx:e_idx]
-            segment = self.pad_audio(segment, SAMPLE_RATE)
-            with self.lock:
-                segments, _ = self.model.transcribe(
-                    segment,
-                    language=language,
-                    beam_size=5,
-                    word_timestamps=True,
-                    vad_filter=True,
-                    vad_parameters={"min_silence_duration_ms": 500},
-                )
-            segments = list(segments)
-            text = "".join(seg.text for seg in segments).strip()
-            words = [
-                {
-                    "word": w.word,
-                    "start": round(float(w.start) + start_time + timestamp_offset, 2),
-                    "end": round(float(w.end) + start_time + timestamp_offset, 2),
-                }
-                for seg in segments
-                for w in seg.words
-            ]
-            if text:
-                all_text.append(text)
-            all_words.extend(words)
-
-        all_words = self.enforce_word_timing_constraints(all_words)
-        return {"text": " ".join(all_text), "words": all_words}

gpu/self_hosted/app/services/translator.py

@@ -1,44 +0,0 @@
-import threading
-
-from transformers import MarianMTModel, MarianTokenizer, pipeline
-
-
-class TextTranslatorService:
-    """Simple text-to-text translator using HuggingFace MarianMT models.
-
-    This mirrors the modal translator API shape but uses text translation only.
-    """
-
-    def __init__(self):
-        self._pipeline = None
-        self._lock = threading.Lock()
-
-    def load(self, source_language: str = "en", target_language: str = "fr"):
-        # Pick a default MarianMT model pair if available; fall back to Helsinki-NLP en->fr
-        model_name = self._resolve_model_name(source_language, target_language)
-        tokenizer = MarianTokenizer.from_pretrained(model_name)
-        model = MarianMTModel.from_pretrained(model_name)
-        self._pipeline = pipeline("translation", model=model, tokenizer=tokenizer)
-
-    def _resolve_model_name(self, src: str, tgt: str) -> str:
-        # Minimal mapping; extend as needed
-        pair = (src.lower(), tgt.lower())
-        mapping = {
-            ("en", "fr"): "Helsinki-NLP/opus-mt-en-fr",
-            ("fr", "en"): "Helsinki-NLP/opus-mt-fr-en",
-            ("en", "es"): "Helsinki-NLP/opus-mt-en-es",
-            ("es", "en"): "Helsinki-NLP/opus-mt-es-en",
-            ("en", "de"): "Helsinki-NLP/opus-mt-en-de",
-            ("de", "en"): "Helsinki-NLP/opus-mt-de-en",
-        }
-        return mapping.get(pair, "Helsinki-NLP/opus-mt-en-fr")
-
-    def translate(self, text: str, source_language: str, target_language: str) -> dict:
-        if self._pipeline is None:
-            self.load(source_language, target_language)
-        with self._lock:
-            results = self._pipeline(
-                text, src_lang=source_language, tgt_lang=target_language
-            )
-        translated = results[0]["translation_text"] if results else ""
-        return {"text": {source_language: text, target_language: translated}}

gpu/self_hosted/app/utils.py

@@ -1,107 +0,0 @@
-import logging
-import os
-import sys
-import uuid
-from contextlib import contextmanager
-from typing import Mapping
-from urllib.parse import urlparse
-from pathlib import Path
-
-import requests
-from fastapi import HTTPException
-
-from .config import SUPPORTED_FILE_EXTENSIONS, UPLOADS_PATH
-
-logger = logging.getLogger(__name__)
-
-
-class NoStdStreams:
-    def __init__(self):
-        self.devnull = open(os.devnull, "w")
-
-    def __enter__(self):
-        self._stdout, self._stderr = sys.stdout, sys.stderr
-        self._stdout.flush()
-        self._stderr.flush()
-        sys.stdout, sys.stderr = self.devnull, self.devnull
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        sys.stdout, sys.stderr = self._stdout, self._stderr
-        self.devnull.close()
-
-
-def ensure_dirs():
-    UPLOADS_PATH.mkdir(parents=True, exist_ok=True)
-
-
-def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
-    url_path = urlparse(url).path
-    for ext in SUPPORTED_FILE_EXTENSIONS:
-        if url_path.lower().endswith(f".{ext}"):
-            return ext
-
-    content_type = headers.get("content-type", "").lower()
-    if "audio/mpeg" in content_type or "audio/mp3" in content_type:
-        return "mp3"
-    if "audio/wav" in content_type:
-        return "wav"
-    if "audio/mp4" in content_type:
-        return "mp4"
-
-    raise HTTPException(
-        status_code=400,
-        detail=(
-            f"Unsupported audio format for URL. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
-        ),
-    )
-
-
-def download_audio_to_uploads(audio_file_url: str) -> tuple[Path, str]:
-    response = requests.head(audio_file_url, allow_redirects=True)
-    if response.status_code == 404:
-        raise HTTPException(status_code=404, detail="Audio file not found")
-
-    response = requests.get(audio_file_url, allow_redirects=True)
-    response.raise_for_status()
-
-    audio_suffix = detect_audio_format(audio_file_url, response.headers)
-    unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
-    file_path: Path = UPLOADS_PATH / unique_filename
-
-    with open(file_path, "wb") as f:
-        f.write(response.content)
-
-    return file_path, audio_suffix
-
-
-@contextmanager
-def download_audio_file(audio_file_url: str):
-    """Download an audio file to UPLOADS_PATH and remove it after use.
-
-    Yields (file_path: Path, audio_suffix: str).
-    """
-    file_path, audio_suffix = download_audio_to_uploads(audio_file_url)
-    try:
-        yield file_path, audio_suffix
-    finally:
-        try:
-            file_path.unlink(missing_ok=True)
-        except Exception as e:
-            logger.error("Error deleting temporary file %s: %s", file_path, e)
-
-
-@contextmanager
-def cleanup_uploaded_files(file_paths: list[Path]):
-    """Ensure provided file paths are removed after use.
-
-    The provided list can be populated inside the context; all present entries
-    at exit will be deleted.
-    """
-    try:
-        yield file_paths
-    finally:
-        for path in list(file_paths):
-            try:
-                path.unlink(missing_ok=True)
-            except Exception as e:
-                logger.error("Error deleting temporary file %s: %s", path, e)

gpu/self_hosted/compose.yml

@@ -1,10 +0,0 @@
-services:
-  reflector_gpu:
-    build:
-      context: .
-    ports:
-      - "8000:8000"
-    env_file:
-      - .env
-    volumes:
-      - ./cache:/root/.cache

gpu/self_hosted/main.py

@@ -1,3 +0,0 @@
-from app.factory import create_app
-
-app = create_app()

gpu/self_hosted/pyproject.toml

@@ -1,19 +0,0 @@
-[project]
-name = "reflector-gpu"
-version = "0.1.0"
-description = "Self-hosted GPU service for speech transcription, diarization, and translation via FastAPI."
-readme = "README.md"
-requires-python = ">=3.12"
-dependencies = [
-    "fastapi[standard]>=0.116.1",
-    "uvicorn[standard]>=0.30.0",
-    "torch>=2.3.0",
-    "faster-whisper>=1.1.0",
-    "librosa==0.10.1",
-    "numpy<2",
-    "silero-vad==5.1.0",
-    "transformers>=4.35.0",
-    "sentencepiece",
-    "pyannote.audio==3.1.0",
-    "torchaudio>=2.3.0",
-]

gpu/self_hosted/runserver.sh

@@ -1,17 +0,0 @@
-#!/bin/sh
-set -e
-
-export PATH="/root/.local/bin:$PATH"
-cd /app
-
-# Install Python dependencies at runtime (first run or when FORCE_SYNC=1)
-if [ ! -d "/app/.venv" ] || [ "$FORCE_SYNC" = "1" ]; then
-  echo "[startup] Installing Python dependencies with uv..."
-  uv sync --compile-bytecode --locked
-else
-  echo "[startup] Using existing virtual environment at /app/.venv"
-fi
-
-exec uv run uvicorn main:app --host 0.0.0.0 --port 8000
-
-

server/README.md

@@ -1,29 +1,3 @@
-## API Key Management
-
-### Finding Your User ID
-
-```bash
-# Get your OAuth sub (user ID) - requires authentication
-curl -H "Authorization: Bearer <your_jwt>" http://localhost:1250/v1/me
-# Returns: {"sub": "your-oauth-sub-here", "email": "...", ...}
-```
-
-### Creating API Keys
-
-```bash
-curl -X POST http://localhost:1250/v1/user/api-keys \
-  -H "Authorization: Bearer <your_jwt>" \
-  -H "Content-Type: application/json" \
-  -d '{"name": "My API Key"}'
-```
-
-### Using API Keys
-
-```bash
-# Use X-API-Key header instead of Authorization
-curl -H "X-API-Key: <your_api_key>" http://localhost:1250/v1/transcripts
-```
-
 ## AWS S3/SQS usage clarification
 
 Whereby.com uploads recordings directly to our S3 bucket when meetings end.

server/docs/data_retention.md

@@ -1,95 +0,0 @@
-# Data Retention and Cleanup
-
-## Overview
-
-For public instances of Reflector, a data retention policy is automatically enforced to delete anonymous user data after a configurable period (default: 7 days). This ensures compliance with privacy expectations and prevents unbounded storage growth.
-
-## Configuration
-
-### Environment Variables
-
-- `PUBLIC_MODE` (bool): Must be set to `true` to enable automatic cleanup
-- `PUBLIC_DATA_RETENTION_DAYS` (int): Number of days to retain anonymous data (default: 7)
-
-### What Gets Deleted
-
-When data reaches the retention period, the following items are automatically removed:
-
-1. **Transcripts** from anonymous users (where `user_id` is NULL):
-   - Database records
-   - Local files (audio.wav, audio.mp3, audio.json waveform)
-   - Storage files (cloud storage if configured)
-
-## Automatic Cleanup
-
-### Celery Beat Schedule
-
-When `PUBLIC_MODE=true`, a Celery beat task runs daily at 3 AM to clean up old data:
-
-```python
-# Automatically scheduled when PUBLIC_MODE=true
-"cleanup_old_public_data": {
-    "task": "reflector.worker.cleanup.cleanup_old_public_data",
-    "schedule": crontab(hour=3, minute=0),  # Daily at 3 AM
-}
-```
-
-### Running the Worker
-
-Ensure both Celery worker and beat scheduler are running:
-
-```bash
-# Start Celery worker
-uv run celery -A reflector.worker.app worker --loglevel=info
-
-# Start Celery beat scheduler (in another terminal)
-uv run celery -A reflector.worker.app beat
-```
-
-## Manual Cleanup
-
-For testing or manual intervention, use the cleanup tool:
-
-```bash
-# Delete data older than 7 days (default)
-uv run python -m reflector.tools.cleanup_old_data
-
-# Delete data older than 30 days
-uv run python -m reflector.tools.cleanup_old_data --days 30
-```
-
-Note: The manual tool uses the same implementation as the Celery worker task to ensure consistency.
-
-## Important Notes
-
-1. **User Data Deletion**: Only anonymous data (where `user_id` is NULL) is deleted. Authenticated user data is preserved.
-
-2. **Storage Cleanup**: The system properly cleans up both local files and cloud storage when configured.
-
-3. **Error Handling**: If individual deletions fail, the cleanup continues and logs errors. Failed deletions are reported in the task output.
-
-4. **Public Instance Only**: The automatic cleanup task only runs when `PUBLIC_MODE=true` to prevent accidental data loss in private deployments.
-
-## Testing
-
-Run the cleanup tests:
-
-```bash
-uv run pytest tests/test_cleanup.py -v
-```
-
-## Monitoring
-
-Check Celery logs for cleanup task execution:
-
-```bash
-# Look for cleanup task logs
-grep "cleanup_old_public_data" celery.log
-grep "Starting cleanup of old public data" celery.log
-```
-
-Task statistics are logged after each run:
-- Number of transcripts deleted
-- Number of meetings deleted
-- Number of orphaned recordings deleted
-- Any errors encountered

server/docs/gpu/api-transcription.md

@@ -1,194 +0,0 @@
-## Reflector GPU Transcription API (Specification)
-
-This document defines the Reflector GPU transcription API that all implementations must adhere to. Current implementations include NVIDIA Parakeet (NeMo) and Whisper (faster-whisper), both deployed on Modal.com. The API surface and response shapes are OpenAI/Whisper-compatible, so clients can switch implementations by changing only the base URL.
-
-### Base URL and Authentication
-
-- Example base URLs (Modal web endpoints):
-
-  - Parakeet: `https://<account>--reflector-transcriber-parakeet-web.modal.run`
-  - Whisper: `https://<account>--reflector-transcriber-web.modal.run`
-
-- All endpoints are served under `/v1` and require a Bearer token:
-
-```
-Authorization: Bearer <REFLECTOR_GPU_APIKEY>
-```
-
-Note: To switch implementations, deploy the desired variant and point `TRANSCRIPT_URL` to its base URL. The API is identical.
-
-### Supported file types
-
-`mp3, mp4, mpeg, mpga, m4a, wav, webm`
-
-### Models and languages
-
-- Parakeet (NVIDIA NeMo): default `nvidia/parakeet-tdt-0.6b-v2`
-  - Language support: only `en`. Other languages return HTTP 400.
-- Whisper (faster-whisper): default `large-v2` (or deployment-specific)
-  - Language support: multilingual (per Whisper model capabilities).
-
-Note: The `model` parameter is accepted by all implementations for interface parity. Some backends may treat it as informational.
-
-### Endpoints
-
-#### POST /v1/audio/transcriptions
-
-Transcribe one or more uploaded audio files.
-
-Request: multipart/form-data
-
-- `file` (File) — optional. Single file to transcribe.
-- `files` (File[]) — optional. One or more files to transcribe.
-- `model` (string) — optional. Defaults to the implementation-specific model (see above).
-- `language` (string) — optional, defaults to `en`.
-  - Parakeet: only `en` is accepted; other values return HTTP 400
-  - Whisper: model-dependent; typically multilingual
-- `batch` (boolean) — optional, defaults to `false`.
-
-Notes:
-
-- Provide either `file` or `files`, not both. If neither is provided, HTTP 400.
-- `batch` requires `files`; using `batch=true` without `files` returns HTTP 400.
-- Response shape for multiple files is the same regardless of `batch`.
-- Files sent to this endpoint are processed in a single pass (no VAD/chunking). This is intended for short clips (roughly ≤ 30s; depends on GPU memory/model). For longer audio, prefer `/v1/audio/transcriptions-from-url` which supports VAD-based chunking.
-
-Responses
-
-Single file response:
-
-```json
-{
-  "text": "transcribed text",
-  "words": [
-    { "word": "hello", "start": 0.0, "end": 0.5 },
-    { "word": "world", "start": 0.5, "end": 1.0 }
-  ],
-  "filename": "audio.mp3"
-}
-```
-
-Multiple files response:
-
-```json
-{
-  "results": [
-    {"filename": "a1.mp3", "text": "...", "words": [...]},
-    {"filename": "a2.mp3", "text": "...", "words": [...]}]
-}
-```
-
-Notes:
-
-- Word objects always include keys: `word`, `start`, `end`.
-- Some implementations may include a trailing space in `word` to match Whisper tokenization behavior; clients should trim if needed.
-
-Example curl (single file):
-
-```bash
-curl -X POST \
-  -H "Authorization: Bearer $REFLECTOR_GPU_APIKEY" \
-  -F "file=@/path/to/audio.mp3" \
-  -F "language=en" \
-  "$BASE_URL/v1/audio/transcriptions"
-```
-
-Example curl (multiple files, batch):
-
-```bash
-curl -X POST \
-  -H "Authorization: Bearer $REFLECTOR_GPU_APIKEY" \
-  -F "files=@/path/a1.mp3" -F "files=@/path/a2.mp3" \
-  -F "batch=true" -F "language=en" \
-  "$BASE_URL/v1/audio/transcriptions"
-```
-
-#### POST /v1/audio/transcriptions-from-url
-
-Transcribe a single remote audio file by URL.
-
-Request: application/json
-
-Body parameters:
-
-- `audio_file_url` (string) — required. URL of the audio file to transcribe.
-- `model` (string) — optional. Defaults to the implementation-specific model (see above).
-- `language` (string) — optional, defaults to `en`. Parakeet only accepts `en`.
-- `timestamp_offset` (number) — optional, defaults to `0.0`. Added to each word's `start`/`end` in the response.
-
-```json
-{
-  "audio_file_url": "https://example.com/audio.mp3",
-  "model": "nvidia/parakeet-tdt-0.6b-v2",
-  "language": "en",
-  "timestamp_offset": 0.0
-}
-```
-
-Response:
-
-```json
-{
-  "text": "transcribed text",
-  "words": [
-    { "word": "hello", "start": 10.0, "end": 10.5 },
-    { "word": "world", "start": 10.5, "end": 11.0 }
-  ]
-}
-```
-
-Notes:
-
-- `timestamp_offset` is added to each word’s `start`/`end` in the response.
-- Implementations may perform VAD-based chunking and batching for long-form audio; word timings are adjusted accordingly.
-
-Example curl:
-
-```bash
-curl -X POST \
-  -H "Authorization: Bearer $REFLECTOR_GPU_APIKEY" \
-  -H "Content-Type: application/json" \
-  -d '{
-        "audio_file_url": "https://example.com/audio.mp3",
-        "language": "en",
-        "timestamp_offset": 0
-      }' \
-  "$BASE_URL/v1/audio/transcriptions-from-url"
-```
-
-### Error handling
-
-- 400 Bad Request
-  - Parakeet: `language` other than `en`
-  - Missing required parameters (`file`/`files` for upload; `audio_file_url` for URL endpoint)
-  - Unsupported file extension
-- 401 Unauthorized
-  - Missing or invalid Bearer token
-- 404 Not Found
-  - `audio_file_url` does not exist
-
-### Implementation details
-
-- GPUs: A10G for small-file/live, L40S for large-file URL transcription (subject to deployment)
-- VAD chunking and segment batching; word timings adjusted and overlapping ends constrained
-- Pads very short segments (< 0.5s) to avoid model crashes on some backends
-
-### Server configuration (Reflector API)
-
-Set the Reflector server to use the Modal backend and point `TRANSCRIPT_URL` to your chosen deployment:
-
-```
-TRANSCRIPT_BACKEND=modal
-TRANSCRIPT_URL=https://<account>--reflector-transcriber-parakeet-web.modal.run
-TRANSCRIPT_MODAL_API_KEY=<REFLECTOR_GPU_APIKEY>
-```
-
-### Conformance tests
-
-Use the pytest-based conformance tests to validate any new implementation (including self-hosted) against this spec:
-
-```
-TRANSCRIPT_URL=https://<your-deployment-base> \
-TRANSCRIPT_MODAL_API_KEY=your-api-key \
-uv run -m pytest -m model_api --no-cov server/tests/test_model_api_transcript.py
-```

server/docs/video-platforms/README.md

@@ -1,236 +0,0 @@
-# Reflector Architecture: Whereby + Daily.co Recording Storage
-
-## System Overview
-
-```mermaid
-graph TB
-    subgraph "Actors"
-        APP[Our App<br/>Reflector]
-        WHEREBY[Whereby Service<br/>External]
-        DAILY[Daily.co Service<br/>External]
-    end
-
-    subgraph "AWS S3 Buckets"
-        TRANSCRIPT_BUCKET[Transcript Bucket<br/>reflector-transcripts<br/>Output: Processed MP3s]
-        WHEREBY_BUCKET[Whereby Bucket<br/>reflector-whereby-recordings<br/>Input: Raw MP4s]
-        DAILY_BUCKET[Daily.co Bucket<br/>reflector-dailyco-recordings<br/>Input: Raw WebM tracks]
-    end
-
-    subgraph "AWS Infrastructure"
-        SQS[SQS Queue<br/>Whereby notifications]
-    end
-
-    subgraph "Database"
-        DB[(PostgreSQL<br/>Recordings, Transcripts, Meetings)]
-    end
-
-    APP -->|Write processed| TRANSCRIPT_BUCKET
-    APP -->|Read/Delete| WHEREBY_BUCKET
-    APP -->|Read/Delete| DAILY_BUCKET
-    APP -->|Poll| SQS
-    APP -->|Store metadata| DB
-
-    WHEREBY -->|Write recordings| WHEREBY_BUCKET
-    WHEREBY_BUCKET -->|S3 Event| SQS
-    WHEREBY -->|Participant webhooks<br/>room.client.joined/left| APP
-
-    DAILY -->|Write recordings| DAILY_BUCKET
-    DAILY -->|Recording webhook<br/>recording.ready-to-download| APP
-```
-
-**Note on Webhook vs S3 Event for Recording Processing:**
-- **Whereby**: Uses S3 Events → SQS for recording availability (S3 as source of truth, no race conditions)
-- **Daily.co**: Uses webhooks for recording availability (more immediate, built-in reliability)
-- **Both**: Use webhooks for participant tracking (real-time updates)
-
-## Credentials & Permissions
-
-```mermaid
-graph LR
-    subgraph "Master Credentials"
-        MASTER[TRANSCRIPT_STORAGE_AWS_*<br/>Access Key ID + Secret]
-    end
-
-    subgraph "Whereby Upload Credentials"
-        WHEREBY_CREDS[AWS_WHEREBY_ACCESS_KEY_*<br/>Access Key ID + Secret]
-    end
-
-    subgraph "Daily.co Upload Role"
-        DAILY_ROLE[DAILY_STORAGE_AWS_ROLE_ARN<br/>IAM Role ARN]
-    end
-
-    subgraph "Our App Uses"
-        MASTER -->|Read/Write/Delete| TRANSCRIPT_BUCKET[Transcript Bucket]
-        MASTER -->|Read/Delete| WHEREBY_BUCKET[Whereby Bucket]
-        MASTER -->|Read/Delete| DAILY_BUCKET[Daily.co Bucket]
-        MASTER -->|Poll/Delete| SQS[SQS Queue]
-    end
-
-    subgraph "We Give To Services"
-        WHEREBY_CREDS -->|Passed in API call| WHEREBY_SERVICE[Whereby Service]
-        WHEREBY_SERVICE -->|Write Only| WHEREBY_BUCKET
-
-        DAILY_ROLE -->|Passed in API call| DAILY_SERVICE[Daily.co Service]
-        DAILY_SERVICE -->|Assume Role| DAILY_ROLE
-        DAILY_SERVICE -->|Write Only| DAILY_BUCKET
-    end
-```
-
-# Video Platform Recording Integration
-
-This document explains how Reflector receives and identifies multitrack audio recordings from different video platforms.
-
-## Platform Comparison
-
-| Platform | Delivery Method | Track Identification |
-|----------|----------------|---------------------|
-| **Daily.co** | Webhook | Explicit track list in payload |
-| **Whereby** | SQS (S3 notifications) | Single file per notification |
-
----
-
-## Daily.co
-
-**Note:** Primary discovery via polling (`poll_daily_recordings`), webhooks as backup.
-
-Daily.co uses **webhooks** to notify Reflector when recordings are ready.
-
-### How It Works
-
-1. **Daily.co sends webhook** when recording is ready
-   - Event type: `recording.ready-to-download`
-   - Endpoint: `/v1/daily/webhook` (`reflector/views/daily.py:46-102`)
-
-2. **Webhook payload explicitly includes track list**:
-```json
-{
-  "recording_id": "7443ee0a-dab1-40eb-b316-33d6c0d5ff88",
-  "room_name": "daily-20251020193458",
-  "tracks": [
-    {
-      "type": "audio",
-      "s3Key": "monadical/daily-20251020193458/1760988935484-52f7f48b-fbab-431f-9a50-87b9abfc8255-cam-audio-1760988935922",
-      "size": 831843
-    },
-    {
-      "type": "audio",
-      "s3Key": "monadical/daily-20251020193458/1760988935484-a37c35e3-6f8e-4274-a482-e9d0f102a732-cam-audio-1760988943823",
-      "size": 408438
-    },
-    {
-      "type": "video",
-      "s3Key": "monadical/daily-20251020193458/...-video.webm",
-      "size": 30000000
-    }
-  ]
-}
-```
-
-3. **System extracts audio tracks** (`daily.py:211`):
-```python
-track_keys = [t.s3Key for t in tracks if t.type == "audio"]
-```
-
-4. **Triggers multitrack processing** (`daily.py:213-218`):
-```python
-process_multitrack_recording.delay(
-    bucket_name=bucket_name,  # reflector-dailyco-local
-    room_name=room_name,      # daily-20251020193458
-    recording_id=recording_id, # 7443ee0a-dab1-40eb-b316-33d6c0d5ff88
-    track_keys=track_keys      # Only audio s3Keys
-)
-```
-
-### Key Advantage: No Ambiguity
-
-Even though multiple meetings may share the same S3 bucket/folder (`monadical/`), **there's no ambiguity** because:
-- Each webhook payload contains the exact `s3Key` list for that specific `recording_id`
-- No need to scan folders or guess which files belong together
-- Each track's s3Key includes the room timestamp subfolder (e.g., `daily-20251020193458/`)
-
-The room name includes timestamp (`daily-20251020193458`) to keep recordings organized, but **the webhook's explicit track list is what prevents mixing files from different meetings**.
-
-### Track Timeline Extraction
-
-Daily.co provides timing information in two places:
-
-**1. PyAV WebM Metadata (current approach)**:
-```python
-# Read from WebM container stream metadata
-stream.start_time = 8.130s  # Meeting-relative timing
-```
-
-**2. Filename Timestamps (alternative approach, commit 3bae9076)**:
-```
-Filename format: {recording_start_ts}-{uuid}-cam-audio-{track_start_ts}.webm
-Example: 1760988935484-52f7f48b-fbab-431f-9a50-87b9abfc8255-cam-audio-1760988935922.webm
-
-Parse timestamps:
-- recording_start_ts: 1760988935484 (Unix ms)
-- track_start_ts: 1760988935922 (Unix ms)
-- offset: (1760988935922 - 1760988935484) / 1000 = 0.438s
-```
-
-**Time Difference (PyAV vs Filename)**:
-```
-Track 0:
-  Filename offset: 438ms
-  PyAV metadata:   229ms
-  Difference:      209ms
-
-Track 1:
-  Filename offset: 8339ms
-  PyAV metadata:   8130ms
-  Difference:      209ms
-```
-
-**Consistent 209ms delta** suggests network/encoding delay between file upload initiation (filename) and actual audio stream start (metadata).
-
-**Current implementation uses PyAV metadata** because:
-- More accurate (represents when audio actually started)
-- Padding BEFORE transcription produces correct Whisper timestamps automatically
-- No manual offset adjustment needed during transcript merge
-
-### Why Re-encoding During Padding
-
-Padding coincidentally involves re-encoding, which is important for Daily.co + Whisper:
-
-**Problem:** Daily.co skips frames in recordings when microphone is muted or paused
-- WebM containers have gaps where audio frames should be
-- Whisper doesn't understand these gaps and produces incorrect timestamps
-- Example: 5s of audio with 2s muted → file has frames only for 3s, Whisper thinks duration is 3s
-
-**Solution:** Re-encoding via PyAV filter graph (`adelay` + `aresample`)
-- Restores missing frames as silence
-- Produces continuous audio stream without gaps
-- Whisper now sees correct duration and produces accurate timestamps
-
-**Why combined with padding:**
-- Already re-encoding for padding (adding initial silence)
-- More performant to do both operations in single PyAV pipeline
-- Padded values needed for mixdown anyway (creating final MP3)
-
-Implementation: `main_multitrack_pipeline.py:_apply_audio_padding_streaming()`
-
----
-
-## Whereby (SQS-based)
-
-Whereby uses **AWS SQS** (via S3 notifications) to notify Reflector when files are uploaded.
-
-### How It Works
-
-1. **Whereby uploads recording** to S3
-2. **S3 sends notification** to SQS queue (one notification per file)
-3. **Reflector polls SQS queue** (`worker/process.py:process_messages()`)
-4. **System processes single file** (`worker/process.py:process_recording()`)
-
-### Key Difference from Daily.co
-
-**Whereby (SQS):** System receives S3 notification "file X was created" - only knows about one file at a time, would need to scan folder to find related files
-
-**Daily.co (Webhook):** Daily explicitly tells system which files belong together in the webhook payload
-
----
-
-

server/docs/webhook.md

@@ -1,233 +0,0 @@
-# Reflector Webhook Documentation
-
-## Overview
-
-Reflector supports webhook notifications to notify external systems when transcript processing is completed. Webhooks can be configured per room and are triggered automatically after a transcript is successfully processed.
-
-## Configuration
-
-Webhooks are configured at the room level with two fields:
-- `webhook_url`: The HTTPS endpoint to receive webhook notifications
-- `webhook_secret`: Optional secret key for HMAC signature verification (auto-generated if not provided)
-
-## Events
-
-### `transcript.completed`
-
-Triggered when a transcript has been fully processed, including transcription, diarization, summarization, topic detection and calendar event integration.
-
-### `test`
-
-A test event that can be triggered manually to verify webhook configuration.
-
-## Webhook Request Format
-
-### Headers
-
-All webhook requests include the following headers:
-
-| Header | Description | Example |
-|--------|-------------|---------|
-| `Content-Type` | Always `application/json` | `application/json` |
-| `User-Agent` | Identifies Reflector as the source | `Reflector-Webhook/1.0` |
-| `X-Webhook-Event` | The event type | `transcript.completed` or `test` |
-| `X-Webhook-Retry` | Current retry attempt number | `0`, `1`, `2`... |
-| `X-Webhook-Signature` | HMAC signature (if secret configured) | `t=1735306800,v1=abc123...` |
-
-### Signature Verification
-
-If a webhook secret is configured, Reflector includes an HMAC-SHA256 signature in the `X-Webhook-Signature` header to verify the webhook authenticity.
-
-The signature format is: `t={timestamp},v1={signature}`
-
-To verify the signature:
-1. Extract the timestamp and signature from the header
-2. Create the signed payload: `{timestamp}.{request_body}`
-3. Compute HMAC-SHA256 of the signed payload using your webhook secret
-4. Compare the computed signature with the received signature
-
-Example verification (Python):
-```python
-import hmac
-import hashlib
-
-def verify_webhook_signature(payload: bytes, signature_header: str, secret: str) -> bool:
-    # Parse header: "t=1735306800,v1=abc123..."
-    parts = dict(part.split("=") for part in signature_header.split(","))
-    timestamp = parts["t"]
-    received_signature = parts["v1"]
-
-    # Create signed payload
-    signed_payload = f"{timestamp}.{payload.decode('utf-8')}"
-
-    # Compute expected signature
-    expected_signature = hmac.new(
-        secret.encode("utf-8"),
-        signed_payload.encode("utf-8"),
-        hashlib.sha256
-    ).hexdigest()
-
-    # Compare signatures
-    return hmac.compare_digest(expected_signature, received_signature)
-```
-
-## Event Payloads
-
-### `transcript.completed` Event
-
-This event includes a convenient URL for accessing the transcript:
-- `frontend_url`: Direct link to view the transcript in the web interface
-
-```json
-{
-  "event": "transcript.completed",
-  "event_id": "transcript.completed-abc-123-def-456",
-  "timestamp": "2025-08-27T12:34:56.789012Z",
-  "transcript": {
-    "id": "abc-123-def-456",
-    "room_id": "room-789",
-    "created_at": "2025-08-27T12:00:00Z",
-    "duration": 1800.5,
-    "title": "Q3 Product Planning Meeting",
-    "short_summary": "Team discussed Q3 product roadmap, prioritizing mobile app features and API improvements.",
-    "long_summary": "The product team met to finalize the Q3 roadmap. Key decisions included...",
-    "webvtt": "WEBVTT\n\n00:00:00.000 --> 00:00:05.000\n<v Speaker 1>Welcome everyone to today's meeting...",
-    "topics": [
-      {
-        "title": "Introduction and Agenda",
-        "summary": "Meeting kickoff with agenda review",
-        "timestamp": 0.0,
-        "duration": 120.0,
-        "webvtt": "WEBVTT\n\n00:00:00.000 --> 00:00:05.000\n<v Speaker 1>Welcome everyone..."
-      },
-      {
-        "title": "Mobile App Features Discussion",
-        "summary": "Team reviewed proposed mobile app features for Q3",
-        "timestamp": 120.0,
-        "duration": 600.0,
-        "webvtt": "WEBVTT\n\n00:02:00.000 --> 00:02:10.000\n<v Speaker 2>Let's talk about the mobile app..."
-      }
-    ],
-    "participants": [
-      {
-        "id": "participant-1",
-        "name": "John Doe",
-        "speaker": "Speaker 1"
-      },
-      {
-        "id": "participant-2",
-        "name": "Jane Smith",
-        "speaker": "Speaker 2"
-      }
-    ],
-    "source_language": "en",
-    "target_language": "en",
-    "status": "completed",
-    "frontend_url": "https://app.reflector.com/transcripts/abc-123-def-456"
-  },
-  "room": {
-    "id": "room-789",
-    "name": "Product Team Room"
-  },
-  "calendar_event": {
-    "id": "calendar-event-123",
-    "ics_uid": "event-123",
-    "title": "Q3 Product Planning Meeting",
-    "start_time": "2025-08-27T12:00:00Z",
-    "end_time": "2025-08-27T12:30:00Z",
-    "description": "Team discussed Q3 product roadmap, prioritizing mobile app features and API improvements.",
-    "location": "Conference Room 1",
-    "attendees": [
-      {
-        "id": "participant-1",
-        "name": "John Doe",
-        "speaker": "Speaker 1"
-      },
-      {
-        "id": "participant-2",
-        "name": "Jane Smith",
-        "speaker": "Speaker 2"
-      }
-    ]
-  }
-}
-```
-
-### `test` Event
-
-```json
-{
-  "event": "test",
-  "event_id": "test.2025-08-27T12:34:56.789012Z",
-  "timestamp": "2025-08-27T12:34:56.789012Z",
-  "message": "This is a test webhook from Reflector",
-  "room": {
-    "id": "room-789",
-    "name": "Product Team Room"
-  }
-}
-```
-
-## Retry Policy
-
-Webhooks are delivered with automatic retry logic to handle transient failures. When a webhook delivery fails due to server errors or network issues, Reflector will automatically retry the delivery multiple times over an extended period.
-
-### Retry Mechanism
-
-Reflector implements an exponential backoff strategy for webhook retries:
-
-- **Initial retry delay**: 60 seconds after the first failure
-- **Exponential backoff**: Each subsequent retry waits approximately twice as long as the previous one
-- **Maximum retry interval**: 1 hour (backoff is capped at this duration)
-- **Maximum retry attempts**: 30 attempts total
-- **Total retry duration**: Retries continue for approximately 24 hours
-
-### How Retries Work
-
-When a webhook fails, Reflector will:
-1. Wait 60 seconds, then retry (attempt #1)
-2. If it fails again, wait ~2 minutes, then retry (attempt #2)
-3. Continue doubling the wait time up to a maximum of 1 hour between attempts
-4. Keep retrying at 1-hour intervals until successful or 30 attempts are exhausted
-
-The `X-Webhook-Retry` header indicates the current retry attempt number (0 for the initial attempt, 1 for first retry, etc.), allowing your endpoint to track retry attempts.
-
-### Retry Behavior by HTTP Status Code
-
-| Status Code | Behavior |
-|-------------|----------|
-| 2xx (Success) | No retry, webhook marked as delivered |
-| 4xx (Client Error) | No retry, request is considered permanently failed |
-| 5xx (Server Error) | Automatic retry with exponential backoff |
-| Network/Timeout Error | Automatic retry with exponential backoff |
-
-**Important Notes:**
-- Webhooks timeout after 30 seconds. If your endpoint takes longer to respond, it will be considered a timeout error and retried.
-- During the retry period (~24 hours), you may receive the same webhook multiple times if your endpoint experiences intermittent failures.
-- There is no mechanism to manually retry failed webhooks after the retry period expires.
-
-## Testing Webhooks
-
-You can test your webhook configuration before processing transcripts:
-
-```http
-POST /v1/rooms/{room_id}/webhook/test
-```
-
-Response:
-```json
-{
-  "success": true,
-  "status_code": 200,
-  "message": "Webhook test successful",
-  "response_preview": "OK"
-}
-```
-
-Or in case of failure:
-```json
-{
-  "success": false,
-  "error": "Webhook request timed out (10 seconds)"
-}
-```

server/env.example

@@ -27,7 +27,7 @@ AUTH_JWT_AUDIENCE=
 #TRANSCRIPT_MODAL_API_KEY=xxxxx
 
 TRANSCRIPT_BACKEND=modal
-TRANSCRIPT_URL=https://monadical-sas--reflector-transcriber-parakeet-web.modal.run
+TRANSCRIPT_URL=https://monadical-sas--reflector-transcriber-web.modal.run
 TRANSCRIPT_MODAL_API_KEY=
 
 ## =======================================================
@@ -71,30 +71,3 @@ DIARIZATION_URL=https://monadical-sas--reflector-diarizer-web.modal.run
 
 ## Sentry DSN configuration
 #SENTRY_DSN=
-
-## =======================================================
-## Video Platform Configuration
-## =======================================================
-
-## Whereby
-#WHEREBY_API_KEY=your-whereby-api-key
-#WHEREBY_WEBHOOK_SECRET=your-whereby-webhook-secret
-#WHEREBY_STORAGE_AWS_ACCESS_KEY_ID=your-aws-key
-#WHEREBY_STORAGE_AWS_SECRET_ACCESS_KEY=your-aws-secret
-#AWS_PROCESS_RECORDING_QUEUE_URL=https://sqs.us-west-2.amazonaws.com/...
-
-## Daily.co
-#DAILY_API_KEY=your-daily-api-key
-#DAILY_WEBHOOK_SECRET=your-daily-webhook-secret
-#DAILY_SUBDOMAIN=your-subdomain
-#DAILY_WEBHOOK_UUID=  # Auto-populated by recreate_daily_webhook.py script
-#DAILYCO_STORAGE_AWS_ROLE_ARN=...  # IAM role ARN for Daily.co S3 access
-#DAILYCO_STORAGE_AWS_BUCKET_NAME=reflector-dailyco
-#DAILYCO_STORAGE_AWS_REGION=us-west-2
-
-## Whereby (optional separate bucket)
-#WHEREBY_STORAGE_AWS_BUCKET_NAME=reflector-whereby
-#WHEREBY_STORAGE_AWS_REGION=us-east-1
-
-## Platform Configuration
-#DEFAULT_VIDEO_PLATFORM=whereby          # Default platform for new rooms

server/gpu/modal_deployments/reflector_transcriber.py

@@ -0,0 +1,161 @@
+import os
+import tempfile
+import threading
+
+import modal
+from pydantic import BaseModel
+
+MODELS_DIR = "/models"
+
+MODEL_NAME = "large-v2"
+MODEL_COMPUTE_TYPE: str = "float16"
+MODEL_NUM_WORKERS: int = 1
+
+MINUTES = 60  # seconds
+
+volume = modal.Volume.from_name("models", create_if_missing=True)
+
+app = modal.App("reflector-transcriber")
+
+
+def download_model():
+    from faster_whisper import download_model
+
+    volume.reload()
+
+    download_model(MODEL_NAME, cache_dir=MODELS_DIR)
+
+    volume.commit()
+
+
+image = (
+    modal.Image.debian_slim(python_version="3.12")
+    .pip_install(
+        "huggingface_hub==0.27.1",
+        "hf-transfer==0.1.9",
+        "torch==2.5.1",
+        "faster-whisper==1.1.1",
+    )
+    .env(
+        {
+            "HF_HUB_ENABLE_HF_TRANSFER": "1",
+            "LD_LIBRARY_PATH": (
+                "/usr/local/lib/python3.12/site-packages/nvidia/cudnn/lib/:"
+                "/opt/conda/lib/python3.12/site-packages/nvidia/cublas/lib/"
+            ),
+        }
+    )
+    .run_function(download_model, volumes={MODELS_DIR: volume})
+)
+
+
+@app.cls(
+    gpu="A10G",
+    timeout=5 * MINUTES,
+    scaledown_window=5 * MINUTES,
+    allow_concurrent_inputs=6,
+    image=image,
+    volumes={MODELS_DIR: volume},
+)
+class Transcriber:
+    @modal.enter()
+    def enter(self):
+        import faster_whisper
+        import torch
+
+        self.lock = threading.Lock()
+        self.use_gpu = torch.cuda.is_available()
+        self.device = "cuda" if self.use_gpu else "cpu"
+        self.model = faster_whisper.WhisperModel(
+            MODEL_NAME,
+            device=self.device,
+            compute_type=MODEL_COMPUTE_TYPE,
+            num_workers=MODEL_NUM_WORKERS,
+            download_root=MODELS_DIR,
+            local_files_only=True,
+        )
+
+    @modal.method()
+    def transcribe_segment(
+        self,
+        audio_data: str,
+        audio_suffix: str,
+        language: str,
+    ):
+        with tempfile.NamedTemporaryFile("wb+", suffix=f".{audio_suffix}") as fp:
+            fp.write(audio_data)
+
+            with self.lock:
+                segments, _ = self.model.transcribe(
+                    fp.name,
+                    language=language,
+                    beam_size=5,
+                    word_timestamps=True,
+                    vad_filter=True,
+                    vad_parameters={"min_silence_duration_ms": 500},
+                )
+
+            segments = list(segments)
+            text = "".join(segment.text for segment in segments)
+            words = [
+                {"word": word.word, "start": word.start, "end": word.end}
+                for segment in segments
+                for word in segment.words
+            ]
+
+            return {"text": text, "words": words}
+
+
+@app.function(
+    scaledown_window=60,
+    timeout=60,
+    allow_concurrent_inputs=40,
+    secrets=[
+        modal.Secret.from_name("reflector-gpu"),
+    ],
+    volumes={MODELS_DIR: volume},
+)
+@modal.asgi_app()
+def web():
+    from fastapi import Body, Depends, FastAPI, HTTPException, UploadFile, status
+    from fastapi.security import OAuth2PasswordBearer
+    from typing_extensions import Annotated
+
+    transcriber = Transcriber()
+
+    app = FastAPI()
+
+    oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
+
+    supported_file_types = ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"]
+
+    def apikey_auth(apikey: str = Depends(oauth2_scheme)):
+        if apikey != os.environ["REFLECTOR_GPU_APIKEY"]:
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail="Invalid API key",
+                headers={"WWW-Authenticate": "Bearer"},
+            )
+
+    class TranscriptResponse(BaseModel):
+        result: dict
+
+    @app.post("/v1/audio/transcriptions", dependencies=[Depends(apikey_auth)])
+    def transcribe(
+        file: UploadFile,
+        model: str = "whisper-1",
+        language: Annotated[str, Body(...)] = "en",
+    ) -> TranscriptResponse:
+        audio_data = file.file.read()
+        audio_suffix = file.filename.split(".")[-1]
+        assert audio_suffix in supported_file_types
+
+        func = transcriber.transcribe_segment.spawn(
+            audio_data=audio_data,
+            audio_suffix=audio_suffix,
+            language=language,
+        )
+        result = func.get()
+        return result
+
+    return app

server/gpu/modal_deployments/reflector_transcriber_parakeet.py

@@ -3,7 +3,7 @@ import os
 import sys
 import threading
 import uuid
-from typing import Generator, Mapping, NamedTuple, NewType, TypedDict
+from typing import Mapping, NewType
 from urllib.parse import urlparse
 
 import modal
@@ -14,7 +14,10 @@ SAMPLERATE = 16000
 UPLOADS_PATH = "/uploads"
 CACHE_PATH = "/cache"
 VAD_CONFIG = {
-    "batch_max_duration": 30.0,
+    "max_segment_duration": 30.0,
+    "batch_max_files": 10,
+    "batch_max_duration": 5.0,
+    "min_segment_duration": 0.02,
     "silence_padding": 0.5,
     "window_size": 512,
 }
@@ -22,37 +25,6 @@ VAD_CONFIG = {
 ParakeetUniqFilename = NewType("ParakeetUniqFilename", str)
 AudioFileExtension = NewType("AudioFileExtension", str)
 
-
-class TimeSegment(NamedTuple):
-    """Represents a time segment with start and end times."""
-
-    start: float
-    end: float
-
-
-class AudioSegment(NamedTuple):
-    """Represents an audio segment with timing and audio data."""
-
-    start: float
-    end: float
-    audio: any
-
-
-class TranscriptResult(NamedTuple):
-    """Represents a transcription result with text and word timings."""
-
-    text: str
-    words: list["WordTiming"]
-
-
-class WordTiming(TypedDict):
-    """Represents a word with its timing information."""
-
-    word: str
-    start: float
-    end: float
-
-
 app = modal.App("reflector-transcriber-parakeet")
 
 # Volume for caching model weights
@@ -77,13 +49,13 @@ image = (
     .pip_install(
         "hf_transfer==0.1.9",
         "huggingface_hub[hf-xet]==0.31.2",
-        "nemo_toolkit[asr]==2.5.0",
+        "nemo_toolkit[asr]==2.3.0",
         "cuda-python==12.8.0",
         "fastapi==0.115.12",
         "numpy<2",
-        "librosa==0.11.0",
+        "librosa==0.10.1",
         "requests",
-        "silero-vad==6.2.0",
+        "silero-vad==5.1.0",
         "torch",
     )
     .entrypoint([])  # silence chatty logs by container on start
@@ -198,14 +170,12 @@ class TranscriberParakeetLive:
                 (output,) = self.model.transcribe([padded_audio], timestamps=True)
 
         text = output.text.strip()
-        words: list[WordTiming] = [
+        words = [
-            WordTiming(
+            {
-                # XXX the space added here is to match the output of whisper
+                "word": word_info["word"] + " ",
-                # whisper add space to each words, while parakeet don't
+                "start": round(word_info["start"], 2),
-                word=word_info["word"] + " ",
+                "end": round(word_info["end"], 2),
-                start=round(word_info["start"], 2),
+            }
-                end=round(word_info["end"], 2),
-            )
             for word_info in output.timestamp["word"]
         ]
 
@@ -241,12 +211,12 @@ class TranscriberParakeetLive:
         for i, (filename, output) in enumerate(zip(filenames, outputs)):
             text = output.text.strip()
 
-            words: list[WordTiming] = [
+            words = [
-                WordTiming(
+                {
-                    word=word_info["word"] + " ",
+                    "word": word_info["word"] + " ",
-                    start=round(word_info["start"], 2),
+                    "start": round(word_info["start"], 2),
-                    end=round(word_info["end"], 2),
+                    "end": round(word_info["end"], 2),
-                )
+                }
                 for word_info in output.timestamp["word"]
             ]
 
@@ -301,12 +271,9 @@ class TranscriberParakeetFile:
             audio_array, sample_rate = librosa.load(file_path, sr=SAMPLERATE, mono=True)
             return audio_array
 
-        def vad_segment_generator(
+        def vad_segment_generator(audio_array):
-            audio_array,
-        ) -> Generator[TimeSegment, None, None]:
             """Generate speech segments using VAD with start/end sample indices"""
             vad_iterator = VADIterator(self.vad_model, sampling_rate=SAMPLERATE)
-            audio_duration = len(audio_array) / float(SAMPLERATE)
             window_size = VAD_CONFIG["window_size"]
             start = None
 
@@ -330,125 +297,107 @@ class TranscriberParakeetFile:
                     start_time = start / float(SAMPLERATE)
                     end_time = end / float(SAMPLERATE)
 
-                    yield TimeSegment(start_time, end_time)
+                    # Extract the actual audio segment
-                    start = None
+                    audio_segment = audio_array[start:end]
 
-            if start is not None:
+                    yield (start_time, end_time, audio_segment)
-                start_time = start / float(SAMPLERATE)
+                    start = None
-                yield TimeSegment(start_time, audio_duration)
 
             vad_iterator.reset_states()
 
-        def batch_speech_segments(
+        def vad_segment_filter(segments):
-            segments: Generator[TimeSegment, None, None], max_duration: int
+            """Filter VAD segments by duration and chunk large segments"""
-        ) -> Generator[TimeSegment, None, None]:
+            min_dur = VAD_CONFIG["min_segment_duration"]
-            """
+            max_dur = VAD_CONFIG["max_segment_duration"]
-            Input segments:
-              [0-2] [3-5] [6-8] [10-11] [12-15] [17-19] [20-22]
 
-                                  ↓ (max_duration=10)
+            for start_time, end_time, audio_segment in segments:
+                segment_duration = end_time - start_time
 
-              Output batches:
+                # Skip very small segments
-              [0-8]           [10-19]          [20-22]
+                if segment_duration < min_dur:
-
-            Note: silences are kept for better transcription, previous implementation was
-            passing segments separatly, but the output was less accurate.
-            """
-            batch_start_time = None
-            batch_end_time = None
-
-            for segment in segments:
-                start_time, end_time = segment.start, segment.end
-                if batch_start_time is None or batch_end_time is None:
-                    batch_start_time = start_time
-                    batch_end_time = end_time
                     continue
 
-                total_duration = end_time - batch_start_time
+                # If segment is within max duration, yield as-is
-
+                if segment_duration <= max_dur:
-                if total_duration <= max_duration:
+                    yield (start_time, end_time, audio_segment)
-                    batch_end_time = end_time
                     continue
 
-                yield TimeSegment(batch_start_time, batch_end_time)
+                # Chunk large segments into smaller pieces
-                batch_start_time = start_time
+                chunk_samples = int(max_dur * SAMPLERATE)
-                batch_end_time = end_time
+                current_start = start_time
 
-            if batch_start_time is None or batch_end_time is None:
+                for chunk_offset in range(0, len(audio_segment), chunk_samples):
-                return
+                    chunk_audio = audio_segment[
+                        chunk_offset : chunk_offset + chunk_samples
+                    ]
+                    if len(chunk_audio) == 0:
+                        break
 
-            yield TimeSegment(batch_start_time, batch_end_time)
+                    chunk_duration = len(chunk_audio) / float(SAMPLERATE)
+                    chunk_end = current_start + chunk_duration
 
-        def batch_segment_to_audio_segment(
+                    # Only yield chunks that meet minimum duration
-            segments: Generator[TimeSegment, None, None],
+                    if chunk_duration >= min_dur:
-            audio_array,
+                        yield (current_start, chunk_end, chunk_audio)
-        ) -> Generator[AudioSegment, None, None]:
-            """Extract audio segments and apply padding for Parakeet compatibility.
 
-            Uses pad_audio to ensure segments are at least 0.5s long, preventing
+                    current_start = chunk_end
-            Parakeet crashes. This padding may cause slight timing overlaps between
-            segments, which are corrected by enforce_word_timing_constraints.
-            """
-            for segment in segments:
-                start_time, end_time = segment.start, segment.end
-                start_sample = int(start_time * SAMPLERATE)
-                end_sample = int(end_time * SAMPLERATE)
-                audio_segment = audio_array[start_sample:end_sample]
 
-                padded_segment = pad_audio(audio_segment, SAMPLERATE)
+        def batch_segments(segments, max_files=10, max_duration=5.0):
+            batch = []
+            batch_duration = 0.0
 
-                yield AudioSegment(start_time, end_time, padded_segment)
+            for start_time, end_time, audio_segment in segments:
+                segment_duration = end_time - start_time
 
-        def transcribe_batch(model, audio_segments: list) -> list:
+                if segment_duration < VAD_CONFIG["silence_padding"]:
+                    silence_samples = int(
+                        (VAD_CONFIG["silence_padding"] - segment_duration) * SAMPLERATE
+                    )
+                    padding = np.zeros(silence_samples, dtype=np.float32)
+                    audio_segment = np.concatenate([audio_segment, padding])
+                    segment_duration = VAD_CONFIG["silence_padding"]
+
+                batch.append((start_time, end_time, audio_segment))
+                batch_duration += segment_duration
+
+                if len(batch) >= max_files or batch_duration >= max_duration:
+                    yield batch
+                    batch = []
+                    batch_duration = 0.0
+
+            if batch:
+                yield batch
+
+        def transcribe_batch(model, audio_segments):
             with NoStdStreams():
                 outputs = model.transcribe(audio_segments, timestamps=True)
             return outputs
 
-        def enforce_word_timing_constraints(
-            words: list[WordTiming],
-        ) -> list[WordTiming]:
-            """Enforce that word end times don't exceed the start time of the next word.
-
-            Due to silence padding added in batch_segment_to_audio_segment for better
-            transcription accuracy, word timings from different segments may overlap.
-            This function ensures there are no overlaps by adjusting end times.
-            """
-            if len(words) <= 1:
-                return words
-
-            enforced_words = []
-            for i, word in enumerate(words):
-                enforced_word = word.copy()
-
-                if i < len(words) - 1:
-                    next_start = words[i + 1]["start"]
-                    if enforced_word["end"] > next_start:
-                        enforced_word["end"] = next_start
-
-                enforced_words.append(enforced_word)
-
-            return enforced_words
-
         def emit_results(
-            results: list,
+            results,
-            segments_info: list[AudioSegment],
+            segments_info,
-        ) -> Generator[TranscriptResult, None, None]:
+            batch_index,
+            total_batches,
+        ):
             """Yield transcribed text and word timings from model output, adjusting timestamps to absolute positions."""
-            for i, (output, segment) in enumerate(zip(results, segments_info)):
+            for i, (output, (start_time, end_time, _)) in enumerate(
-                start_time, end_time = segment.start, segment.end
+                zip(results, segments_info)
+            ):
                 text = output.text.strip()
-                words: list[WordTiming] = [
+                words = [
-                    WordTiming(
+                    {
-                        word=word_info["word"] + " ",
+                        "word": word_info["word"] + " ",
-                        start=round(
+                        "start": round(
                             word_info["start"] + start_time + timestamp_offset, 2
                         ),
-                        end=round(word_info["end"] + start_time + timestamp_offset, 2),
+                        "end": round(
-                    )
+                            word_info["end"] + start_time + timestamp_offset, 2
+                        ),
+                    }
                     for word_info in output.timestamp["word"]
                 ]
 
-                yield TranscriptResult(text, words)
+                yield text, words
 
         upload_volume.reload()
 
@@ -458,31 +407,41 @@ class TranscriberParakeetFile:
 
         audio_array = load_and_convert_audio(file_path)
         total_duration = len(audio_array) / float(SAMPLERATE)
+        processed_duration = 0.0
 
-        all_text_parts: list[str] = []
+        all_text_parts = []
-        all_words: list[WordTiming] = []
+        all_words = []
 
         raw_segments = vad_segment_generator(audio_array)
-        speech_segments = batch_speech_segments(
+        filtered_segments = vad_segment_filter(raw_segments)
-            raw_segments,
+        batches = batch_segments(
+            filtered_segments,
+            VAD_CONFIG["batch_max_files"],
             VAD_CONFIG["batch_max_duration"],
         )
-        audio_segments = batch_segment_to_audio_segment(speech_segments, audio_array)
 
-        for batch in audio_segments:
+        batch_index = 0
-            audio_segment = batch.audio
+        total_batches = max(
-            results = transcribe_batch(self.model, [audio_segment])
+            1, int(total_duration / VAD_CONFIG["batch_max_duration"]) + 1
+        )
 
-            for result in emit_results(
+        for batch in batches:
+            batch_index += 1
+            audio_segments = [seg[2] for seg in batch]
+            results = transcribe_batch(self.model, audio_segments)
+
+            for text, words in emit_results(
                 results,
-                [batch],
+                batch,
+                batch_index,
+                total_batches,
             ):
-                if not result.text:
+                if not text:
                     continue
-                all_text_parts.append(result.text)
+                all_text_parts.append(text)
-                all_words.extend(result.words)
+                all_words.extend(words)
 
-        all_words = enforce_word_timing_constraints(all_words)
+            processed_duration += sum(len(seg[2]) / float(SAMPLERATE) for seg in batch)
 
         combined_text = " ".join(all_text_parts)
         return {"text": combined_text, "words": all_words}

server/migrations/versions/0194f65cd6d3_add_webhook_fields_to_rooms.py

@@ -1,36 +0,0 @@
-"""Add webhook fields to rooms
-
-Revision ID: 0194f65cd6d3
-Revises: 5a8907fd1d78
-Create Date: 2025-08-27 09:03:19.610995
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "0194f65cd6d3"
-down_revision: Union[str, None] = "5a8907fd1d78"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.add_column(sa.Column("webhook_url", sa.String(), nullable=True))
-        batch_op.add_column(sa.Column("webhook_secret", sa.String(), nullable=True))
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.drop_column("webhook_secret")
-        batch_op.drop_column("webhook_url")
-
-    # ### end Alembic commands ###

server/migrations/versions/0ce521cda2ee_remove_user_id_from_meeting_table.py

@@ -1,36 +0,0 @@
-"""remove user_id from meeting table
-
-Revision ID: 0ce521cda2ee
-Revises: 6dec9fb5b46c
-Create Date: 2025-09-10 12:40:55.688899
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "0ce521cda2ee"
-down_revision: Union[str, None] = "6dec9fb5b46c"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.drop_column("user_id")
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.add_column(
-            sa.Column("user_id", sa.VARCHAR(), autoincrement=False, nullable=True)
-        )
-
-    # ### end Alembic commands ###

server/migrations/versions/1e49625677e4_add_platform_support.py

@@ -1,50 +0,0 @@
-"""add_platform_support
-
-Revision ID: 1e49625677e4
-Revises: 9e3f7b2a4c8e
-Create Date: 2025-10-08 13:17:29.943612
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "1e49625677e4"
-down_revision: Union[str, None] = "9e3f7b2a4c8e"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    """Add platform field with default 'whereby' for backward compatibility."""
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.add_column(
-            sa.Column(
-                "platform",
-                sa.String(),
-                nullable=True,
-                server_default=None,
-            )
-        )
-
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.add_column(
-            sa.Column(
-                "platform",
-                sa.String(),
-                nullable=False,
-                server_default="whereby",
-            )
-        )
-
-
-def downgrade() -> None:
-    """Remove platform field."""
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.drop_column("platform")
-
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.drop_column("platform")

server/migrations/versions/2ae3db106d4e_clean_up_orphaned_room_id_references_in_.py

@@ -1,32 +0,0 @@
-"""clean up orphaned room_id references in meeting table
-
-Revision ID: 2ae3db106d4e
-Revises: def1b5867d4c
-Create Date: 2025-09-11 10:35:15.759967
-
-"""
-
-from typing import Sequence, Union
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "2ae3db106d4e"
-down_revision: Union[str, None] = "def1b5867d4c"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Set room_id to NULL for meetings that reference non-existent rooms
-    op.execute("""
-        UPDATE meeting
-        SET room_id = NULL
-        WHERE room_id IS NOT NULL
-          AND room_id NOT IN (SELECT id FROM room WHERE id IS NOT NULL)
-    """)
-
-
-def downgrade() -> None:
-    # Cannot restore orphaned references - no operation needed
-    pass

server/migrations/versions/2b92a1b03caa_add_daily_participant_session_table_.py

@@ -1,79 +0,0 @@
-"""add daily participant session table with immutable left_at
-
-Revision ID: 2b92a1b03caa
-Revises: f8294b31f022
-Create Date: 2025-11-13 20:29:30.486577
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "2b92a1b03caa"
-down_revision: Union[str, None] = "f8294b31f022"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Create table
-    op.create_table(
-        "daily_participant_session",
-        sa.Column("id", sa.String(), nullable=False),
-        sa.Column("meeting_id", sa.String(), nullable=False),
-        sa.Column("room_id", sa.String(), nullable=False),
-        sa.Column("session_id", sa.String(), nullable=False),
-        sa.Column("user_id", sa.String(), nullable=True),
-        sa.Column("user_name", sa.String(), nullable=False),
-        sa.Column("joined_at", sa.DateTime(timezone=True), nullable=False),
-        sa.Column("left_at", sa.DateTime(timezone=True), nullable=True),
-        sa.ForeignKeyConstraint(["meeting_id"], ["meeting.id"], ondelete="CASCADE"),
-        sa.ForeignKeyConstraint(["room_id"], ["room.id"], ondelete="CASCADE"),
-        sa.PrimaryKeyConstraint("id"),
-    )
-    with op.batch_alter_table("daily_participant_session", schema=None) as batch_op:
-        batch_op.create_index(
-            "idx_daily_session_meeting_left", ["meeting_id", "left_at"], unique=False
-        )
-        batch_op.create_index("idx_daily_session_room", ["room_id"], unique=False)
-
-    # Create trigger function to prevent left_at from being updated once set
-    op.execute("""
-        CREATE OR REPLACE FUNCTION prevent_left_at_update()
-        RETURNS TRIGGER AS $$
-        BEGIN
-            IF OLD.left_at IS NOT NULL THEN
-                RAISE EXCEPTION 'left_at is immutable once set';
-            END IF;
-            RETURN NEW;
-        END;
-        $$ LANGUAGE plpgsql;
-    """)
-
-    # Create trigger
-    op.execute("""
-        CREATE TRIGGER prevent_left_at_update_trigger
-        BEFORE UPDATE ON daily_participant_session
-        FOR EACH ROW
-        EXECUTE FUNCTION prevent_left_at_update();
-    """)
-
-
-def downgrade() -> None:
-    # Drop trigger
-    op.execute(
-        "DROP TRIGGER IF EXISTS prevent_left_at_update_trigger ON daily_participant_session;"
-    )
-
-    # Drop trigger function
-    op.execute("DROP FUNCTION IF EXISTS prevent_left_at_update();")
-
-    # Drop indexes and table
-    with op.batch_alter_table("daily_participant_session", schema=None) as batch_op:
-        batch_op.drop_index("idx_daily_session_room")
-        batch_op.drop_index("idx_daily_session_meeting_left")
-
-    op.drop_table("daily_participant_session")

server/migrations/versions/5a8907fd1d78_add_cascade_delete_to_meeting_consent_.py

@@ -1,50 +0,0 @@
-"""add cascade delete to meeting consent foreign key
-
-Revision ID: 5a8907fd1d78
-Revises: 0ab2d7ffaa16
-Create Date: 2025-08-26 17:26:50.945491
-
-"""
-
-from typing import Sequence, Union
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "5a8907fd1d78"
-down_revision: Union[str, None] = "0ab2d7ffaa16"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting_consent", schema=None) as batch_op:
-        batch_op.drop_constraint(
-            batch_op.f("meeting_consent_meeting_id_fkey"), type_="foreignkey"
-        )
-        batch_op.create_foreign_key(
-            batch_op.f("meeting_consent_meeting_id_fkey"),
-            "meeting",
-            ["meeting_id"],
-            ["id"],
-            ondelete="CASCADE",
-        )
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting_consent", schema=None) as batch_op:
-        batch_op.drop_constraint(
-            batch_op.f("meeting_consent_meeting_id_fkey"), type_="foreignkey"
-        )
-        batch_op.create_foreign_key(
-            batch_op.f("meeting_consent_meeting_id_fkey"),
-            "meeting",
-            ["meeting_id"],
-            ["id"],
-        )
-
-    # ### end Alembic commands ###

server/migrations/versions/5d6b9df9b045_make_room_platform_non_nullable_with_.py

@@ -1,30 +0,0 @@
-"""Make room platform non-nullable with dynamic default
-
-Revision ID: 5d6b9df9b045
-Revises: 2b92a1b03caa
-Create Date: 2025-11-21 13:22:25.756584
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "5d6b9df9b045"
-down_revision: Union[str, None] = "2b92a1b03caa"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.execute("UPDATE room SET platform = 'whereby' WHERE platform IS NULL")
-
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.alter_column("platform", existing_type=sa.String(), nullable=False)
-
-
-def downgrade() -> None:
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.alter_column("platform", existing_type=sa.String(), nullable=True)

server/migrations/versions/6025e9b2bef2_remove_one_active_meeting_per_room_.py

@@ -1,53 +0,0 @@
-"""remove_one_active_meeting_per_room_constraint
-
-Revision ID: 6025e9b2bef2
-Revises: 2ae3db106d4e
-Create Date: 2025-08-18 18:45:44.418392
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "6025e9b2bef2"
-down_revision: Union[str, None] = "2ae3db106d4e"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Remove the unique constraint that prevents multiple active meetings per room
-    # This is needed to support calendar integration with overlapping meetings
-    # Check if index exists before trying to drop it
-    from alembic import context
-
-    if context.get_context().dialect.name == "postgresql":
-        conn = op.get_bind()
-        result = conn.execute(
-            sa.text(
-                "SELECT 1 FROM pg_indexes WHERE indexname = 'idx_one_active_meeting_per_room'"
-            )
-        )
-        if result.fetchone():
-            op.drop_index("idx_one_active_meeting_per_room", table_name="meeting")
-    else:
-        # For SQLite, just try to drop it
-        try:
-            op.drop_index("idx_one_active_meeting_per_room", table_name="meeting")
-        except:
-            pass
-
-
-def downgrade() -> None:
-    # Restore the unique constraint
-    op.create_index(
-        "idx_one_active_meeting_per_room",
-        "meeting",
-        ["room_id"],
-        unique=True,
-        postgresql_where=sa.text("is_active = true"),
-        sqlite_where=sa.text("is_active = 1"),
-    )

server/migrations/versions/61882a919591_webhook_url_and_secret_null_by_default.py

@@ -1,28 +0,0 @@
-"""webhook url and secret null by default
-
-
-Revision ID: 61882a919591
-Revises: 0194f65cd6d3
-Create Date: 2025-08-29 11:46:36.738091
-
-"""
-
-from typing import Sequence, Union
-
-# revision identifiers, used by Alembic.
-revision: str = "61882a919591"
-down_revision: Union[str, None] = "0194f65cd6d3"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    pass
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    pass
-    # ### end Alembic commands ###

server/migrations/versions/6dec9fb5b46c_make_meeting_room_id_required_and_add_.py

@@ -1,35 +0,0 @@
-"""make meeting room_id required and add foreign key
-
-Revision ID: 6dec9fb5b46c
-Revises: 61882a919591
-Create Date: 2025-09-10 10:47:06.006819
-
-"""
-
-from typing import Sequence, Union
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "6dec9fb5b46c"
-down_revision: Union[str, None] = "61882a919591"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.create_foreign_key(
-            None, "room", ["room_id"], ["id"], ondelete="CASCADE"
-        )
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.drop_constraint("meeting_room_id_fkey", type_="foreignkey")
-
-    # ### end Alembic commands ###

server/migrations/versions/9e3f7b2a4c8e_add_user_api_keys.py

@@ -1,38 +0,0 @@
-"""add user api keys
-
-Revision ID: 9e3f7b2a4c8e
-Revises: dc035ff72fd5
-Create Date: 2025-10-17 00:00:00.000000
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "9e3f7b2a4c8e"
-down_revision: Union[str, None] = "dc035ff72fd5"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "user_api_key",
-        sa.Column("id", sa.String(), nullable=False),
-        sa.Column("user_id", sa.String(), nullable=False),
-        sa.Column("key_hash", sa.String(), nullable=False),
-        sa.Column("name", sa.String(), nullable=True),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-    )
-
-    with op.batch_alter_table("user_api_key", schema=None) as batch_op:
-        batch_op.create_index("idx_user_api_key_hash", ["key_hash"], unique=True)
-        batch_op.create_index("idx_user_api_key_user_id", ["user_id"], unique=False)
-
-
-def downgrade() -> None:
-    op.drop_table("user_api_key")

server/migrations/versions/bbafedfa510c_add_user_table.py

@@ -1,38 +0,0 @@
-"""add user table
-
-Revision ID: bbafedfa510c
-Revises: 5d6b9df9b045
-Create Date: 2025-11-19 21:06:30.543262
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "bbafedfa510c"
-down_revision: Union[str, None] = "5d6b9df9b045"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "user",
-        sa.Column("id", sa.String(), nullable=False),
-        sa.Column("email", sa.String(), nullable=False),
-        sa.Column("authentik_uid", sa.String(), nullable=False),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
-        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-    )
-
-    with op.batch_alter_table("user", schema=None) as batch_op:
-        batch_op.create_index("idx_user_authentik_uid", ["authentik_uid"], unique=True)
-        batch_op.create_index("idx_user_email", ["email"], unique=False)
-
-
-def downgrade() -> None:
-    op.drop_table("user")

server/migrations/versions/d4a1c446458c_add_grace_period_fields_to_meeting.py

@@ -1,34 +0,0 @@
-"""add_grace_period_fields_to_meeting
-
-Revision ID: d4a1c446458c
-Revises: 6025e9b2bef2
-Create Date: 2025-08-18 18:50:37.768052
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "d4a1c446458c"
-down_revision: Union[str, None] = "6025e9b2bef2"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Add fields to track when participants left for grace period logic
-    op.add_column(
-        "meeting", sa.Column("last_participant_left_at", sa.DateTime(timezone=True))
-    )
-    op.add_column(
-        "meeting",
-        sa.Column("grace_period_minutes", sa.Integer, server_default=sa.text("15")),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("meeting", "grace_period_minutes")
-    op.drop_column("meeting", "last_participant_left_at")

server/migrations/versions/d8e204bbf615_add_calendar.py

@@ -1,129 +0,0 @@
-"""add calendar
-
-Revision ID: d8e204bbf615
-Revises: d4a1c446458c
-Create Date: 2025-09-10 19:56:22.295756
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision: str = "d8e204bbf615"
-down_revision: Union[str, None] = "d4a1c446458c"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table(
-        "calendar_event",
-        sa.Column("id", sa.String(), nullable=False),
-        sa.Column("room_id", sa.String(), nullable=False),
-        sa.Column("ics_uid", sa.Text(), nullable=False),
-        sa.Column("title", sa.Text(), nullable=True),
-        sa.Column("description", sa.Text(), nullable=True),
-        sa.Column("start_time", sa.DateTime(timezone=True), nullable=False),
-        sa.Column("end_time", sa.DateTime(timezone=True), nullable=False),
-        sa.Column("attendees", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
-        sa.Column("location", sa.Text(), nullable=True),
-        sa.Column("ics_raw_data", sa.Text(), nullable=True),
-        sa.Column("last_synced", sa.DateTime(timezone=True), nullable=False),
-        sa.Column(
-            "is_deleted", sa.Boolean(), server_default=sa.text("false"), nullable=False
-        ),
-        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
-        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["room_id"],
-            ["room.id"],
-            name="fk_calendar_event_room_id",
-            ondelete="CASCADE",
-        ),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("room_id", "ics_uid", name="uq_room_calendar_event"),
-    )
-    with op.batch_alter_table("calendar_event", schema=None) as batch_op:
-        batch_op.create_index(
-            "idx_calendar_event_deleted",
-            ["is_deleted"],
-            unique=False,
-            postgresql_where=sa.text("NOT is_deleted"),
-        )
-        batch_op.create_index(
-            "idx_calendar_event_room_start", ["room_id", "start_time"], unique=False
-        )
-
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.add_column(sa.Column("calendar_event_id", sa.String(), nullable=True))
-        batch_op.add_column(
-            sa.Column(
-                "calendar_metadata",
-                postgresql.JSONB(astext_type=sa.Text()),
-                nullable=True,
-            )
-        )
-        batch_op.create_index(
-            "idx_meeting_calendar_event", ["calendar_event_id"], unique=False
-        )
-        batch_op.create_foreign_key(
-            "fk_meeting_calendar_event_id",
-            "calendar_event",
-            ["calendar_event_id"],
-            ["id"],
-            ondelete="SET NULL",
-        )
-
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.add_column(sa.Column("ics_url", sa.Text(), nullable=True))
-        batch_op.add_column(
-            sa.Column(
-                "ics_fetch_interval", sa.Integer(), server_default="300", nullable=True
-            )
-        )
-        batch_op.add_column(
-            sa.Column(
-                "ics_enabled",
-                sa.Boolean(),
-                server_default=sa.text("false"),
-                nullable=False,
-            )
-        )
-        batch_op.add_column(
-            sa.Column("ics_last_sync", sa.DateTime(timezone=True), nullable=True)
-        )
-        batch_op.add_column(sa.Column("ics_last_etag", sa.Text(), nullable=True))
-        batch_op.create_index("idx_room_ics_enabled", ["ics_enabled"], unique=False)
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("room", schema=None) as batch_op:
-        batch_op.drop_index("idx_room_ics_enabled")
-        batch_op.drop_column("ics_last_etag")
-        batch_op.drop_column("ics_last_sync")
-        batch_op.drop_column("ics_enabled")
-        batch_op.drop_column("ics_fetch_interval")
-        batch_op.drop_column("ics_url")
-
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.drop_constraint("fk_meeting_calendar_event_id", type_="foreignkey")
-        batch_op.drop_index("idx_meeting_calendar_event")
-        batch_op.drop_column("calendar_metadata")
-        batch_op.drop_column("calendar_event_id")
-
-    with op.batch_alter_table("calendar_event", schema=None) as batch_op:
-        batch_op.drop_index("idx_calendar_event_room_start")
-        batch_op.drop_index(
-            "idx_calendar_event_deleted", postgresql_where=sa.text("NOT is_deleted")
-        )
-
-    op.drop_table("calendar_event")
-    # ### end Alembic commands ###

server/migrations/versions/dc035ff72fd5_remove_grace_period_fields.py

@@ -1,43 +0,0 @@
-"""remove_grace_period_fields
-
-Revision ID: dc035ff72fd5
-Revises: d8e204bbf615
-Create Date: 2025-09-11 10:36:45.197588
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "dc035ff72fd5"
-down_revision: Union[str, None] = "d8e204bbf615"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # Remove grace period columns from meeting table
-    op.drop_column("meeting", "last_participant_left_at")
-    op.drop_column("meeting", "grace_period_minutes")
-
-
-def downgrade() -> None:
-    # Add back grace period columns to meeting table
-    op.add_column(
-        "meeting",
-        sa.Column(
-            "last_participant_left_at", sa.DateTime(timezone=True), nullable=True
-        ),
-    )
-    op.add_column(
-        "meeting",
-        sa.Column(
-            "grace_period_minutes",
-            sa.Integer(),
-            server_default=sa.text("15"),
-            nullable=True,
-        ),
-    )

server/migrations/versions/def1b5867d4c_make_meeting_room_id_nullable_but_keep_.py

@@ -1,34 +0,0 @@
-"""make meeting room_id nullable but keep foreign key
-
-Revision ID: def1b5867d4c
-Revises: 0ce521cda2ee
-Create Date: 2025-09-11 09:42:18.697264
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "def1b5867d4c"
-down_revision: Union[str, None] = "0ce521cda2ee"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.alter_column("room_id", existing_type=sa.VARCHAR(), nullable=True)
-
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table("meeting", schema=None) as batch_op:
-        batch_op.alter_column("room_id", existing_type=sa.VARCHAR(), nullable=False)
-
-    # ### end Alembic commands ###

server/migrations/versions/f8294b31f022_add_track_keys.py

@@ -1,28 +0,0 @@
-"""add_track_keys
-
-Revision ID: f8294b31f022
-Revises: 1e49625677e4
-Create Date: 2025-10-27 18:52:17.589167
-
-"""
-
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "f8294b31f022"
-down_revision: Union[str, None] = "1e49625677e4"
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    with op.batch_alter_table("recording", schema=None) as batch_op:
-        batch_op.add_column(sa.Column("track_keys", sa.JSON(), nullable=True))
-
-
-def downgrade() -> None:
-    with op.batch_alter_table("recording", schema=None) as batch_op:
-        batch_op.drop_column("track_keys")

server/pyproject.toml

@@ -12,6 +12,7 @@ dependencies = [
     "requests>=2.31.0",
     "aiortc>=1.5.0",
     "sortedcontainers>=2.4.0",
+    "loguru>=0.7.0",
     "pydantic-settings>=2.0.2",
     "structlog>=23.1.0",
     "uvicorn[standard]>=0.23.1",
@@ -26,6 +27,7 @@ dependencies = [
     "prometheus-fastapi-instrumentator>=6.1.0",
     "sentencepiece>=0.1.99",
     "protobuf>=4.24.3",
+    "profanityfilter>=2.0.6",
     "celery>=5.3.4",
     "redis>=5.0.1",
     "python-jose[cryptography]>=3.3.0",
@@ -38,7 +40,6 @@ dependencies = [
     "llama-index-llms-openai-like>=0.4.0",
     "pytest-env>=1.1.5",
     "webvtt-py>=0.5.0",
-    "icalendar>=6.0.0",
 ]
 
 [dependency-groups]
@@ -112,14 +113,13 @@ source = ["reflector"]
 [tool.pytest_env]
 ENVIRONMENT = "pytest"
 DATABASE_URL = "postgresql://test_user:test_password@localhost:15432/reflector_test"
-AUTH_BACKEND = "jwt"
 
 [tool.pytest.ini_options]
 addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v"
 testpaths = ["tests"]
 asyncio_mode = "auto"
 markers = [
-    "model_api: tests for the unified model-serving HTTP API (backend- and hardware-agnostic)",
+    "gpu_modal: mark test to run only with GPU Modal endpoints (deselect with '-m \"not gpu_modal\"')",
 ]
 
 [tool.ruff.lint]
@@ -131,7 +131,7 @@ select = [
 
 [tool.ruff.lint.per-file-ignores]
 "reflector/processors/summary/summary_builder.py" = ["E501"]
-"gpu/modal_deployments/**.py" = ["PLC0415"]
+"gpu/**.py" = ["PLC0415"]
 "reflector/tools/**.py" = ["PLC0415"]
 "migrations/versions/**.py" = ["PLC0415"]
 "tests/**.py" = ["PLC0415"]

server/reflector/app.py

@@ -12,7 +12,6 @@ from reflector.events import subscribers_shutdown, subscribers_startup
 from reflector.logger import logger
 from reflector.metrics import metrics_init
 from reflector.settings import settings
-from reflector.views.daily import router as daily_router
 from reflector.views.meetings import router as meetings_router
 from reflector.views.rooms import router as rooms_router
 from reflector.views.rtc_offer import router as rtc_offer_router
@@ -27,8 +26,6 @@ from reflector.views.transcripts_upload import router as transcripts_upload_rout
 from reflector.views.transcripts_webrtc import router as transcripts_webrtc_router
 from reflector.views.transcripts_websocket import router as transcripts_websocket_router
 from reflector.views.user import router as user_router
-from reflector.views.user_api_keys import router as user_api_keys_router
-from reflector.views.user_websocket import router as user_ws_router
 from reflector.views.whereby import router as whereby_router
 from reflector.views.zulip import router as zulip_router
 
@@ -68,12 +65,6 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-
-@app.get("/health")
-async def health():
-    return {"status": "healthy"}
-
-
 # metrics
 instrumentator = Instrumentator(
     excluded_handlers=["/docs", "/metrics"],
@@ -93,11 +84,8 @@ app.include_router(transcripts_websocket_router, prefix="/v1")
 app.include_router(transcripts_webrtc_router, prefix="/v1")
 app.include_router(transcripts_process_router, prefix="/v1")
 app.include_router(user_router, prefix="/v1")
-app.include_router(user_api_keys_router, prefix="/v1")
-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")
 add_pagination(app)
 
 # prepare celery

server/reflector/asynctask.py

@@ -1,27 +0,0 @@
-import asyncio
-import functools
-
-from reflector.db import get_database
-
-
-def asynctask(f):
-    @functools.wraps(f)
-    def wrapper(*args, **kwargs):
-        async def run_with_db():
-            database = get_database()
-            await database.connect()
-            try:
-                return await f(*args, **kwargs)
-            finally:
-                await database.disconnect()
-
-        coro = run_with_db()
-        try:
-            loop = asyncio.get_running_loop()
-        except RuntimeError:
-            loop = None
-        if loop and loop.is_running():
-            return loop.run_until_complete(coro)
-        return asyncio.run(coro)
-
-    return wrapper

server/reflector/auth/auth_jwt.py

@@ -1,18 +1,14 @@
-from typing import Annotated, List, Optional
+from typing import Annotated, Optional
 
 from fastapi import Depends, HTTPException
-from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
+from fastapi.security import OAuth2PasswordBearer
 from jose import JWTError, jwt
 from pydantic import BaseModel
 
-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
-from reflector.utils import generate_uuid4
 
 oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token", auto_error=False)
-api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
 
 jwt_public_key = open(f"reflector/auth/jwt/keys/{settings.AUTH_JWT_PUBLIC_KEY}").read()
 jwt_algorithm = settings.AUTH_JWT_ALGORITHM
@@ -30,7 +26,7 @@ class JWTException(Exception):
 
 class UserInfo(BaseModel):
     sub: str
-    email: Optional[str] = None
+    email: str
 
     def __getitem__(self, key):
         return getattr(self, key)
@@ -62,65 +58,33 @@ def authenticated(token: Annotated[str, Depends(oauth2_scheme)]):
     return None
 
 
-async def _authenticate_user(
+def current_user(
-    jwt_token: Optional[str],
+    token: Annotated[Optional[str], Depends(oauth2_scheme)],
-    api_key: Optional[str],
-    jwtauth: JWTAuth,
-) -> 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 = jwtauth.verify_token(jwt_token)
-            authentik_uid = payload["sub"]
-            email = payload["email"]
-
-            user = await user_controller.get_by_authentik_uid(authentik_uid)
-            if not user:
-                logger.info(
-                    f"Creating new user on first login: {authentik_uid} ({email})"
-                )
-                user = await user_controller.create_or_update(
-                    id=generate_uuid4(),
-                    authentik_uid=authentik_uid,
-                    email=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 JWTException(
-            status_code=401,
-            detail="Invalid authentication: more than one user provided",
-        )
-
-    return user_infos[0]
-
-
-async def current_user(
-    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
-    api_key: Annotated[Optional[str], Depends(api_key_header)],
     jwtauth: JWTAuth = Depends(),
 ):
-    user = await _authenticate_user(jwt_token, api_key, jwtauth)
+    if token is None:
-    if user is None:
         raise HTTPException(status_code=401, detail="Not authenticated")
-    return user
+    try:
+        payload = jwtauth.verify_token(token)
+        sub = payload["sub"]
+        return UserInfo(sub=sub)
+    except JWTError as e:
+        logger.error(f"JWT error: {e}")
+        raise HTTPException(status_code=401, detail="Invalid authentication")
 
 
-async def current_user_optional(
+def current_user_optional(
-    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
+    token: Annotated[Optional[str], Depends(oauth2_scheme)],
-    api_key: Annotated[Optional[str], Depends(api_key_header)],
     jwtauth: JWTAuth = Depends(),
 ):
-    return await _authenticate_user(jwt_token, api_key, jwtauth)
+    # we accept no token, but if one is provided, it must be a valid one.
+    if token is None:
+        return None
+    try:
+        payload = jwtauth.verify_token(token)
+        sub = payload["sub"]
+        email = payload["email"]
+        return UserInfo(sub=sub, email=email)
+    except JWTError as e:
+        logger.error(f"JWT error: {e}")
+        raise HTTPException(status_code=401, detail="Invalid authentication")

server/reflector/dailyco_api/README.md

@@ -1,6 +0,0 @@
-anything about Daily.co api interaction
-
-- webhook event shapes
-- REST api client
-
-No REST api client existing found in the wild; the official lib is about working with videocall as a bot

server/reflector/dailyco_api/__init__.py

@@ -1,108 +0,0 @@
-"""
-Daily.co API Module
-"""
-
-# Client
-from .client import DailyApiClient, DailyApiError
-
-# Request models
-from .requests import (
-    CreateMeetingTokenRequest,
-    CreateRoomRequest,
-    CreateWebhookRequest,
-    MeetingTokenProperties,
-    RecordingsBucketConfig,
-    RoomProperties,
-    UpdateWebhookRequest,
-)
-
-# Response models
-from .responses import (
-    MeetingParticipant,
-    MeetingParticipantsResponse,
-    MeetingResponse,
-    MeetingTokenResponse,
-    RecordingResponse,
-    RecordingS3Info,
-    RoomPresenceParticipant,
-    RoomPresenceResponse,
-    RoomResponse,
-    WebhookResponse,
-)
-
-# Webhook utilities
-from .webhook_utils import (
-    extract_room_name,
-    parse_participant_joined,
-    parse_participant_left,
-    parse_recording_error,
-    parse_recording_ready,
-    parse_recording_started,
-    parse_webhook_payload,
-    verify_webhook_signature,
-)
-
-# Webhook models
-from .webhooks import (
-    DailyTrack,
-    DailyWebhookEvent,
-    DailyWebhookEventUnion,
-    ParticipantJoinedEvent,
-    ParticipantJoinedPayload,
-    ParticipantLeftEvent,
-    ParticipantLeftPayload,
-    RecordingErrorEvent,
-    RecordingErrorPayload,
-    RecordingReadyEvent,
-    RecordingReadyToDownloadPayload,
-    RecordingStartedEvent,
-    RecordingStartedPayload,
-)
-
-__all__ = [
-    # Client
-    "DailyApiClient",
-    "DailyApiError",
-    # Requests
-    "CreateRoomRequest",
-    "RoomProperties",
-    "RecordingsBucketConfig",
-    "CreateMeetingTokenRequest",
-    "MeetingTokenProperties",
-    "CreateWebhookRequest",
-    "UpdateWebhookRequest",
-    # Responses
-    "RoomResponse",
-    "RoomPresenceResponse",
-    "RoomPresenceParticipant",
-    "MeetingParticipantsResponse",
-    "MeetingParticipant",
-    "MeetingResponse",
-    "RecordingResponse",
-    "RecordingS3Info",
-    "MeetingTokenResponse",
-    "WebhookResponse",
-    # Webhooks
-    "DailyWebhookEvent",
-    "DailyWebhookEventUnion",
-    "DailyTrack",
-    "ParticipantJoinedEvent",
-    "ParticipantJoinedPayload",
-    "ParticipantLeftEvent",
-    "ParticipantLeftPayload",
-    "RecordingStartedEvent",
-    "RecordingStartedPayload",
-    "RecordingReadyEvent",
-    "RecordingReadyToDownloadPayload",
-    "RecordingErrorEvent",
-    "RecordingErrorPayload",
-    # Webhook utilities
-    "verify_webhook_signature",
-    "extract_room_name",
-    "parse_webhook_payload",
-    "parse_participant_joined",
-    "parse_participant_left",
-    "parse_recording_started",
-    "parse_recording_ready",
-    "parse_recording_error",
-]

server/reflector/dailyco_api/client.py

@@ -1,573 +0,0 @@
-"""
-Daily.co API Client
-
-Complete async client for Daily.co REST API with Pydantic models.
-
-Reference: https://docs.daily.co/reference/rest-api
-"""
-
-from http import HTTPStatus
-from typing import Any
-
-import httpx
-import structlog
-
-from reflector.utils.string import NonEmptyString
-
-from .requests import (
-    CreateMeetingTokenRequest,
-    CreateRoomRequest,
-    CreateWebhookRequest,
-    UpdateWebhookRequest,
-)
-from .responses import (
-    MeetingParticipantsResponse,
-    MeetingResponse,
-    MeetingTokenResponse,
-    RecordingResponse,
-    RoomPresenceResponse,
-    RoomResponse,
-    WebhookResponse,
-)
-
-logger = structlog.get_logger(__name__)
-
-
-class DailyApiError(Exception):
-    """Daily.co API error with full request/response context."""
-
-    def __init__(self, operation: str, response: httpx.Response):
-        self.operation = operation
-        self.response = response
-        self.status_code = response.status_code
-        self.response_body = response.text
-        self.url = str(response.url)
-        self.request_body = (
-            response.request.content.decode() if response.request.content else None
-        )
-
-        super().__init__(
-            f"Daily.co API error: {operation} failed with status {self.status_code}"
-        )
-
-
-class DailyApiClient:
-    """
-    Complete async client for Daily.co REST API.
-
-    Usage:
-        # Direct usage
-        client = DailyApiClient(api_key="your_api_key")
-        room = await client.create_room(CreateRoomRequest(name="my-room"))
-        await client.close()  # Clean up when done
-
-        # Context manager (recommended)
-        async with DailyApiClient(api_key="your_api_key") as client:
-            room = await client.create_room(CreateRoomRequest(name="my-room"))
-    """
-
-    BASE_URL = "https://api.daily.co/v1"
-    DEFAULT_TIMEOUT = 10.0
-
-    def __init__(
-        self,
-        api_key: NonEmptyString,
-        webhook_secret: NonEmptyString | None = None,
-        timeout: float = DEFAULT_TIMEOUT,
-        base_url: NonEmptyString | None = None,
-    ):
-        """
-        Initialize Daily.co API client.
-
-        Args:
-            api_key: Daily.co API key (Bearer token)
-            webhook_secret: Base64-encoded HMAC secret for webhook verification.
-                Must match the 'hmac' value provided when creating webhooks.
-                Generate with: base64.b64encode(os.urandom(32)).decode()
-            timeout: Default request timeout in seconds
-            base_url: Override base URL (for testing)
-        """
-        self.api_key = api_key
-        self.webhook_secret = webhook_secret
-        self.timeout = timeout
-        self.base_url = base_url or self.BASE_URL
-
-        self.headers = {
-            "Authorization": f"Bearer {api_key}",
-            "Content-Type": "application/json",
-        }
-
-        self._client: httpx.AsyncClient | None = None
-
-    async def __aenter__(self):
-        return self
-
-    async def __aexit__(self, exc_type, exc_val, exc_tb):
-        await self.close()
-
-    async def _get_client(self) -> httpx.AsyncClient:
-        if self._client is None:
-            self._client = httpx.AsyncClient(timeout=self.timeout)
-        return self._client
-
-    async def close(self):
-        if self._client is not None:
-            await self._client.aclose()
-            self._client = None
-
-    async def _handle_response(
-        self, response: httpx.Response, operation: str
-    ) -> dict[str, Any]:
-        """
-        Handle API response with error logging.
-
-        Args:
-            response: HTTP response
-            operation: Operation name for logging (e.g., "create_room")
-
-        Returns:
-            Parsed JSON response
-
-        Raises:
-            DailyApiError: If request failed with full context
-        """
-        if response.status_code >= 400:
-            logger.error(
-                f"Daily.co API error: {operation}",
-                status_code=response.status_code,
-                response_body=response.text,
-                request_body=response.request.content.decode()
-                if response.request.content
-                else None,
-                url=str(response.url),
-            )
-            raise DailyApiError(operation, response)
-
-        return response.json()
-
-    # ============================================================================
-    # ROOMS
-    # ============================================================================
-
-    async def create_room(self, request: CreateRoomRequest) -> RoomResponse:
-        """
-        Create a new Daily.co room.
-
-        Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
-
-        Args:
-            request: Room creation request with name, privacy, and properties
-
-        Returns:
-            Created room data including URL and ID
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.post(
-            f"{self.base_url}/rooms",
-            headers=self.headers,
-            json=request.model_dump(exclude_none=True),
-        )
-
-        data = await self._handle_response(response, "create_room")
-        return RoomResponse(**data)
-
-    async def get_room(self, room_name: NonEmptyString) -> RoomResponse:
-        """
-        Get room configuration.
-
-        Args:
-            room_name: Daily.co room name
-
-        Returns:
-            Room configuration data
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/rooms/{room_name}",
-            headers=self.headers,
-        )
-
-        data = await self._handle_response(response, "get_room")
-        return RoomResponse(**data)
-
-    async def get_room_presence(
-        self, room_name: NonEmptyString
-    ) -> RoomPresenceResponse:
-        """
-        Get current participants in a room (real-time presence).
-
-        Reference: https://docs.daily.co/reference/rest-api/rooms/get-room-presence
-
-        Args:
-            room_name: Daily.co room name
-
-        Returns:
-            List of currently present participants with join time and duration
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/rooms/{room_name}/presence",
-            headers=self.headers,
-        )
-
-        data = await self._handle_response(response, "get_room_presence")
-        return RoomPresenceResponse(**data)
-
-    async def delete_room(self, room_name: NonEmptyString) -> None:
-        """
-        Delete a room (idempotent - succeeds even if room doesn't exist).
-
-        Reference: https://docs.daily.co/reference/rest-api/rooms/delete-room
-
-        Args:
-            room_name: Daily.co room name
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails (except 404)
-        """
-        client = await self._get_client()
-        response = await client.delete(
-            f"{self.base_url}/rooms/{room_name}",
-            headers=self.headers,
-        )
-
-        # Idempotent delete - 404 means already deleted
-        if response.status_code == HTTPStatus.NOT_FOUND:
-            logger.debug("Room not found (already deleted)", room_name=room_name)
-            return
-
-        await self._handle_response(response, "delete_room")
-
-    # ============================================================================
-    # MEETINGS
-    # ============================================================================
-
-    async def get_meeting(self, meeting_id: NonEmptyString) -> MeetingResponse:
-        """
-        Get full meeting information including participants.
-
-        Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-information
-
-        Args:
-            meeting_id: Daily.co meeting/session ID
-
-        Returns:
-            Meeting metadata including room, duration, participants, and status
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/meetings/{meeting_id}",
-            headers=self.headers,
-        )
-
-        data = await self._handle_response(response, "get_meeting")
-        return MeetingResponse(**data)
-
-    async def get_meeting_participants(
-        self,
-        meeting_id: NonEmptyString,
-        limit: int | None = None,
-        joined_after: NonEmptyString | None = None,
-        joined_before: NonEmptyString | None = None,
-    ) -> MeetingParticipantsResponse:
-        """
-        Get historical participant data from a completed meeting (paginated).
-
-        Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
-
-        Args:
-            meeting_id: Daily.co meeting/session ID
-            limit: Maximum number of participant records to return
-            joined_after: Return participants who joined after this participant_id
-            joined_before: Return participants who joined before this participant_id
-
-        Returns:
-            List of participants with join times and duration
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails (404 when no more participants)
-
-        Note:
-            For pagination, use joined_after with the last participant_id from previous response.
-            Returns 404 when no more participants remain.
-        """
-        params = {}
-        if limit is not None:
-            params["limit"] = limit
-        if joined_after is not None:
-            params["joined_after"] = joined_after
-        if joined_before is not None:
-            params["joined_before"] = joined_before
-
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/meetings/{meeting_id}/participants",
-            headers=self.headers,
-            params=params,
-        )
-
-        data = await self._handle_response(response, "get_meeting_participants")
-        return MeetingParticipantsResponse(**data)
-
-    # ============================================================================
-    # RECORDINGS
-    # ============================================================================
-
-    async def get_recording(self, recording_id: NonEmptyString) -> RecordingResponse:
-        """
-        https://docs.daily.co/reference/rest-api/recordings/get-recording-information
-        Get recording metadata and status.
-        """
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/recordings/{recording_id}",
-            headers=self.headers,
-        )
-
-        data = await self._handle_response(response, "get_recording")
-        return RecordingResponse(**data)
-
-    async def list_recordings(
-        self,
-        room_name: NonEmptyString | None = None,
-        starting_after: str | None = None,
-        ending_before: str | None = None,
-        limit: int = 100,
-    ) -> list[RecordingResponse]:
-        """
-        List recordings with optional filters.
-
-        Reference: https://docs.daily.co/reference/rest-api/recordings
-
-        Args:
-            room_name: Filter by room name
-            starting_after: Pagination cursor - recording ID to start after
-            ending_before: Pagination cursor - recording ID to end before
-            limit: Max results per page (default 100, max 100)
-
-        Note: starting_after/ending_before are pagination cursors (recording IDs),
-        NOT time filters. API returns recordings in reverse chronological order.
-        """
-        client = await self._get_client()
-
-        params = {"limit": limit}
-        if room_name:
-            params["room_name"] = room_name
-        if starting_after:
-            params["starting_after"] = starting_after
-        if ending_before:
-            params["ending_before"] = ending_before
-
-        response = await client.get(
-            f"{self.base_url}/recordings",
-            headers=self.headers,
-            params=params,
-        )
-
-        data = await self._handle_response(response, "list_recordings")
-
-        if not isinstance(data, dict) or "data" not in data:
-            logger.error(
-                "Daily.co API returned unexpected format for list_recordings",
-                data_type=type(data).__name__,
-                data_keys=list(data.keys()) if isinstance(data, dict) else None,
-                data_sample=str(data)[:500],
-                room_name=room_name,
-                operation="list_recordings",
-            )
-            raise httpx.HTTPStatusError(
-                message=f"Unexpected response format from list_recordings: {type(data).__name__}",
-                request=response.request,
-                response=response,
-            )
-
-        return [RecordingResponse(**r) for r in data["data"]]
-
-    # ============================================================================
-    # MEETING TOKENS
-    # ============================================================================
-
-    async def create_meeting_token(
-        self, request: CreateMeetingTokenRequest
-    ) -> MeetingTokenResponse:
-        """
-        Create a meeting token for participant authentication.
-
-        Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
-
-        Args:
-            request: Token properties including room name, user_id, permissions
-
-        Returns:
-            JWT meeting token
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.post(
-            f"{self.base_url}/meeting-tokens",
-            headers=self.headers,
-            json=request.model_dump(exclude_none=True),
-        )
-
-        data = await self._handle_response(response, "create_meeting_token")
-        return MeetingTokenResponse(**data)
-
-    # ============================================================================
-    # WEBHOOKS
-    # ============================================================================
-
-    async def list_webhooks(self) -> list[WebhookResponse]:
-        """
-        List all configured webhooks for this account.
-
-        Reference: https://docs.daily.co/reference/rest-api/webhooks
-
-        Returns:
-            List of webhook configurations
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.get(
-            f"{self.base_url}/webhooks",
-            headers=self.headers,
-        )
-
-        data = await self._handle_response(response, "list_webhooks")
-
-        # Daily.co returns array directly (not paginated)
-        if isinstance(data, list):
-            return [WebhookResponse(**wh) for wh in data]
-
-        # Future-proof: handle potential pagination envelope
-        if isinstance(data, dict) and "data" in data:
-            return [WebhookResponse(**wh) for wh in data["data"]]
-
-        logger.warning("Unexpected webhook list response format", data=data)
-        return []
-
-    async def create_webhook(self, request: CreateWebhookRequest) -> WebhookResponse:
-        """
-        Create a new webhook subscription.
-
-        Reference: https://docs.daily.co/reference/rest-api/webhooks
-
-        Args:
-            request: Webhook configuration with URL, event types, and HMAC secret
-
-        Returns:
-            Created webhook with UUID and state
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.post(
-            f"{self.base_url}/webhooks",
-            headers=self.headers,
-            json=request.model_dump(exclude_none=True),
-        )
-
-        data = await self._handle_response(response, "create_webhook")
-        return WebhookResponse(**data)
-
-    async def update_webhook(
-        self, webhook_uuid: NonEmptyString, request: UpdateWebhookRequest
-    ) -> WebhookResponse:
-        """
-        Update webhook configuration.
-
-        Note: Daily.co may not support PATCH for all fields.
-        Common pattern is delete + recreate.
-
-        Reference: https://docs.daily.co/reference/rest-api/webhooks
-
-        Args:
-            webhook_uuid: Webhook UUID to update
-            request: Updated webhook configuration
-
-        Returns:
-            Updated webhook configuration
-
-        Raises:
-            httpx.HTTPStatusError: If API request fails
-        """
-        client = await self._get_client()
-        response = await client.patch(
-            f"{self.base_url}/webhooks/{webhook_uuid}",
-            headers=self.headers,
-            json=request.model_dump(exclude_none=True),
-        )
-
-        data = await self._handle_response(response, "update_webhook")
-        return WebhookResponse(**data)
-
-    async def delete_webhook(self, webhook_uuid: NonEmptyString) -> None:
-        """
-        Delete a webhook.
-
-        Reference: https://docs.daily.co/reference/rest-api/webhooks
-
-        Args:
-            webhook_uuid: Webhook UUID to delete
-
-        Raises:
-            httpx.HTTPStatusError: If webhook not found or deletion fails
-        """
-        client = await self._get_client()
-        response = await client.delete(
-            f"{self.base_url}/webhooks/{webhook_uuid}",
-            headers=self.headers,
-        )
-
-        await self._handle_response(response, "delete_webhook")
-
-    # ============================================================================
-    # HELPER METHODS
-    # ============================================================================
-
-    async def find_webhook_by_url(self, url: NonEmptyString) -> WebhookResponse | None:
-        """
-        Find a webhook by its URL.
-
-        Args:
-            url: Webhook endpoint URL to search for
-
-        Returns:
-            Webhook if found, None otherwise
-        """
-        webhooks = await self.list_webhooks()
-        for webhook in webhooks:
-            if webhook.url == url:
-                return webhook
-        return None
-
-    async def find_webhooks_by_pattern(
-        self, pattern: NonEmptyString
-    ) -> list[WebhookResponse]:
-        """
-        Find webhooks matching a URL pattern (e.g., 'ngrok').
-
-        Args:
-            pattern: String to match in webhook URLs
-
-        Returns:
-            List of matching webhooks
-        """
-        webhooks = await self.list_webhooks()
-        return [wh for wh in webhooks if pattern in wh.url]

server/reflector/dailyco_api/requests.py

@@ -1,158 +0,0 @@
-"""
-Daily.co API Request Models
-
-Reference: https://docs.daily.co/reference/rest-api
-"""
-
-from typing import List, Literal
-
-from pydantic import BaseModel, Field
-
-from reflector.utils.string import NonEmptyString
-
-
-class RecordingsBucketConfig(BaseModel):
-    """
-    S3 bucket configuration for raw-tracks recordings.
-
-    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
-    """
-
-    bucket_name: NonEmptyString = Field(description="S3 bucket name")
-    bucket_region: NonEmptyString = Field(description="AWS region (e.g., 'us-east-1')")
-    assume_role_arn: NonEmptyString = Field(
-        description="AWS IAM role ARN that Daily.co will assume to write recordings"
-    )
-    allow_api_access: bool = Field(
-        default=True,
-        description="Whether to allow API access to recording metadata",
-    )
-
-
-class RoomProperties(BaseModel):
-    """
-    Room configuration properties.
-    """
-
-    enable_recording: Literal["cloud", "local", "raw-tracks"] | None = Field(
-        default=None,
-        description="Recording mode: 'cloud' for mixed, 'local' for local recording, 'raw-tracks' for multitrack, None to disable",
-    )
-    enable_chat: bool = Field(default=True, description="Enable in-meeting chat")
-    enable_screenshare: bool = Field(default=True, description="Enable screen sharing")
-    start_video_off: bool = Field(
-        default=False, description="Start with video off for all participants"
-    )
-    start_audio_off: bool = Field(
-        default=False, description="Start with audio muted for all participants"
-    )
-    exp: int | None = Field(
-        None, description="Room expiration timestamp (Unix epoch seconds)"
-    )
-    recordings_bucket: RecordingsBucketConfig | None = Field(
-        None, description="S3 bucket configuration for raw-tracks recordings"
-    )
-
-
-class CreateRoomRequest(BaseModel):
-    """
-    Request to create a new Daily.co room.
-
-    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
-    """
-
-    name: NonEmptyString = Field(description="Room name (must be unique within domain)")
-    privacy: Literal["public", "private"] = Field(
-        default="public", description="Room privacy setting"
-    )
-    properties: RoomProperties = Field(
-        default_factory=RoomProperties, description="Room configuration properties"
-    )
-
-
-class MeetingTokenProperties(BaseModel):
-    """
-    Properties for meeting token creation.
-
-    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
-    """
-
-    room_name: NonEmptyString = Field(description="Room name this token is valid for")
-    user_id: NonEmptyString | None = Field(
-        None, description="User identifier to associate with token"
-    )
-    is_owner: bool = Field(
-        default=False, description="Grant owner privileges to token holder"
-    )
-    start_cloud_recording: bool = Field(
-        default=False, description="Automatically start cloud recording on join"
-    )
-    enable_recording_ui: bool = Field(
-        default=True, description="Show recording controls in UI"
-    )
-    eject_at_token_exp: bool = Field(
-        default=False, description="Eject participant when token expires"
-    )
-    nbf: int | None = Field(
-        None, description="Not-before timestamp (Unix epoch seconds)"
-    )
-    exp: int | None = Field(
-        None, description="Expiration timestamp (Unix epoch seconds)"
-    )
-
-
-class CreateMeetingTokenRequest(BaseModel):
-    """
-    Request to create a meeting token for participant authentication.
-
-    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
-    """
-
-    properties: MeetingTokenProperties = Field(description="Token properties")
-
-
-class CreateWebhookRequest(BaseModel):
-    """
-    Request to create a webhook subscription.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks
-    """
-
-    url: NonEmptyString = Field(description="Webhook endpoint URL (must be HTTPS)")
-    eventTypes: List[
-        Literal[
-            "participant.joined",
-            "participant.left",
-            "recording.started",
-            "recording.ready-to-download",
-            "recording.error",
-        ]
-    ] = Field(
-        description="Array of event types to subscribe to (only events we handle)"
-    )
-    hmac: NonEmptyString = Field(
-        description="Base64-encoded HMAC secret for webhook signature verification"
-    )
-    basicAuth: NonEmptyString | None = Field(
-        None, description="Optional basic auth credentials for webhook endpoint"
-    )
-
-
-class UpdateWebhookRequest(BaseModel):
-    """
-    Request to update an existing webhook.
-
-    Note: Daily.co API may not support PATCH for webhooks.
-    Common pattern is to delete and recreate.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks
-    """
-
-    url: NonEmptyString | None = Field(None, description="New webhook endpoint URL")
-    eventTypes: List[NonEmptyString] | None = Field(
-        None, description="New array of event types"
-    )
-    hmac: NonEmptyString | None = Field(None, description="New HMAC secret")
-    basicAuth: NonEmptyString | None = Field(
-        None, description="New basic auth credentials"
-    )

server/reflector/dailyco_api/responses.py

@@ -1,193 +0,0 @@
-"""
-Daily.co API Response Models
-"""
-
-from typing import Any, Dict, List, Literal
-
-from pydantic import BaseModel, Field
-
-from reflector.dailyco_api.webhooks import DailyTrack
-from reflector.utils.string import NonEmptyString
-
-# not documented in daily; we fill it according to observations
-RecordingStatus = Literal["in-progress", "finished"]
-
-
-class RoomResponse(BaseModel):
-    """
-    Response from room creation or retrieval.
-
-    Reference: https://docs.daily.co/reference/rest-api/rooms/create-room
-    """
-
-    id: NonEmptyString = Field(description="Unique room identifier (UUID)")
-    name: NonEmptyString = Field(description="Room name used in URLs")
-    api_created: bool = Field(description="Whether room was created via API")
-    privacy: Literal["public", "private"] = Field(description="Room privacy setting")
-    url: NonEmptyString = Field(description="Full room URL")
-    created_at: NonEmptyString = Field(description="ISO 8601 creation timestamp")
-    config: Dict[NonEmptyString, Any] = Field(
-        default_factory=dict, description="Room configuration properties"
-    )
-
-
-class RoomPresenceParticipant(BaseModel):
-    """
-    Participant presence information in a room.
-
-    Reference: https://docs.daily.co/reference/rest-api/rooms/get-room-presence
-    """
-
-    room: NonEmptyString = Field(description="Room name")
-    id: NonEmptyString = Field(description="Participant session ID")
-    userId: NonEmptyString | None = Field(None, description="User ID if provided")
-    userName: NonEmptyString | None = Field(None, description="User display name")
-    joinTime: NonEmptyString = Field(description="ISO 8601 join timestamp")
-    duration: int = Field(description="Duration in room (seconds)")
-
-
-class RoomPresenceResponse(BaseModel):
-    """
-    Response from room presence endpoint.
-
-    Reference: https://docs.daily.co/reference/rest-api/rooms/get-room-presence
-    """
-
-    total_count: int = Field(
-        description="Total number of participants currently in room"
-    )
-    data: List[RoomPresenceParticipant] = Field(
-        default_factory=list, description="Array of participant presence data"
-    )
-
-
-class MeetingParticipant(BaseModel):
-    """
-    Historical participant data from a meeting.
-
-    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
-    """
-
-    user_id: NonEmptyString = Field(description="User identifier")
-    participant_id: NonEmptyString = Field(description="Participant session identifier")
-    user_name: NonEmptyString | None = Field(None, description="User display name")
-    join_time: int = Field(description="Join timestamp (Unix epoch seconds)")
-    duration: int = Field(description="Duration in meeting (seconds)")
-
-
-class MeetingParticipantsResponse(BaseModel):
-    """
-    Response from meeting participants endpoint.
-
-    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
-    """
-
-    data: List[MeetingParticipant] = Field(
-        default_factory=list, description="Array of participant data"
-    )
-
-
-class MeetingResponse(BaseModel):
-    """
-    Response from meeting information endpoint.
-
-    Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-information
-    """
-
-    id: NonEmptyString = Field(description="Meeting session identifier (UUID)")
-    room: NonEmptyString = Field(description="Room name where meeting occurred")
-    start_time: int = Field(
-        description="Meeting start Unix timestamp (~15s granularity)"
-    )
-    duration: int = Field(description="Total meeting duration in seconds")
-    ongoing: bool = Field(description="Whether meeting is currently active")
-    max_participants: int = Field(description="Peak concurrent participant count")
-    participants: List[MeetingParticipant] = Field(
-        default_factory=list, description="Array of participant session data"
-    )
-
-
-class RecordingS3Info(BaseModel):
-    """
-    S3 bucket information for a recording.
-
-    Reference: https://docs.daily.co/reference/rest-api/recordings
-    """
-
-    bucket_name: NonEmptyString
-    bucket_region: NonEmptyString
-    endpoint: NonEmptyString | None = None
-
-
-class RecordingResponse(BaseModel):
-    """
-    Response from recording retrieval endpoint.
-
-    Reference: https://docs.daily.co/reference/rest-api/recordings
-    """
-
-    id: NonEmptyString = Field(description="Recording identifier")
-    room_name: NonEmptyString = Field(description="Room where recording occurred")
-    start_ts: int = Field(description="Recording start timestamp (Unix epoch seconds)")
-    status: RecordingStatus = Field(
-        description="Recording status ('in-progress' or 'finished')"
-    )
-    max_participants: int | None = Field(
-        None, description="Maximum participants during recording (may be missing)"
-    )
-    duration: int = Field(description="Recording duration in seconds")
-    share_token: NonEmptyString | None = Field(
-        None, description="Token for sharing recording"
-    )
-    s3: RecordingS3Info | None = Field(None, description="S3 bucket information")
-    tracks: list[DailyTrack] = Field(
-        default_factory=list,
-        description="Track list for raw-tracks recordings (always array, never null)",
-    )
-    # this is not a mistake but a deliberate Daily.co naming decision
-    mtgSessionId: NonEmptyString | None = Field(
-        None, description="Meeting session identifier (may be missing)"
-    )
-
-
-class MeetingTokenResponse(BaseModel):
-    """
-    Response from meeting token creation.
-
-    Reference: https://docs.daily.co/reference/rest-api/meeting-tokens/create-meeting-token
-    """
-
-    token: NonEmptyString = Field(
-        description="JWT meeting token for participant authentication"
-    )
-
-
-class WebhookResponse(BaseModel):
-    """
-    Response from webhook creation or retrieval.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks
-    """
-
-    uuid: NonEmptyString = Field(description="Unique webhook identifier")
-    url: NonEmptyString = Field(description="Webhook endpoint URL")
-    hmac: NonEmptyString | None = Field(
-        None, description="Base64-encoded HMAC secret for signature verification"
-    )
-    basicAuth: NonEmptyString | None = Field(
-        None, description="Basic auth credentials if configured"
-    )
-    eventTypes: List[NonEmptyString] = Field(
-        default_factory=list,
-        description="Array of event types (e.g., ['recording.started', 'participant.joined'])",
-    )
-    state: Literal["ACTIVE", "FAILED"] = Field(
-        description="Webhook state - FAILED after 3+ consecutive failures"
-    )
-    failedCount: int = Field(default=0, description="Number of consecutive failures")
-    lastMomentPushed: NonEmptyString | None = Field(
-        None, description="ISO 8601 timestamp of last successful push"
-    )
-    domainId: NonEmptyString = Field(description="Daily.co domain/account identifier")
-    createdAt: NonEmptyString = Field(description="ISO 8601 creation timestamp")
-    updatedAt: NonEmptyString = Field(description="ISO 8601 last update timestamp")

server/reflector/dailyco_api/webhook_utils.py

@@ -1,228 +0,0 @@
-"""
-Daily.co Webhook Utilities
-
-Utilities for verifying and parsing Daily.co webhook events.
-
-Reference: https://docs.daily.co/reference/rest-api/webhooks
-"""
-
-import base64
-import hmac
-from hashlib import sha256
-
-import structlog
-
-from .webhooks import (
-    DailyWebhookEvent,
-    ParticipantJoinedPayload,
-    ParticipantLeftPayload,
-    RecordingErrorPayload,
-    RecordingReadyToDownloadPayload,
-    RecordingStartedPayload,
-)
-
-logger = structlog.get_logger(__name__)
-
-
-def verify_webhook_signature(
-    body: bytes,
-    signature: str,
-    timestamp: str,
-    webhook_secret: str,
-) -> bool:
-    """
-    Verify Daily.co webhook signature using HMAC-SHA256.
-
-    Daily.co signature verification:
-    1. Base64-decode the webhook secret
-    2. Create signed content: timestamp + '.' + body
-    3. Compute HMAC-SHA256(secret, signed_content)
-    4. Base64-encode the result
-    5. Compare with provided signature using constant-time comparison
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks
-
-    Args:
-        body: Raw request body bytes
-        signature: X-Webhook-Signature header value
-        timestamp: X-Webhook-Timestamp header value
-        webhook_secret: Base64-encoded HMAC secret
-
-    Returns:
-        True if signature is valid, False otherwise
-
-    Example:
-        >>> body = b'{"version":"1.0.0","type":"participant.joined",...}'
-        >>> signature = "abc123..."
-        >>> timestamp = "1234567890"
-        >>> secret = "your-base64-secret"
-        >>> is_valid = verify_webhook_signature(body, signature, timestamp, secret)
-    """
-    if not signature or not timestamp or not webhook_secret:
-        logger.warning(
-            "Missing required data for webhook verification",
-            has_signature=bool(signature),
-            has_timestamp=bool(timestamp),
-            has_secret=bool(webhook_secret),
-        )
-        return False
-
-    try:
-        secret_bytes = base64.b64decode(webhook_secret)
-        signed_content = timestamp.encode() + b"." + body
-        expected = hmac.new(secret_bytes, signed_content, sha256).digest()
-        expected_b64 = base64.b64encode(expected).decode()
-
-        # Constant-time comparison to prevent timing attacks
-        return hmac.compare_digest(expected_b64, signature)
-
-    except (base64.binascii.Error, ValueError, TypeError, UnicodeDecodeError) as e:
-        logger.error(
-            "Webhook signature verification failed",
-            error=str(e),
-            error_type=type(e).__name__,
-        )
-        return False
-
-
-def extract_room_name(event: DailyWebhookEvent) -> str | None:
-    """
-    Extract room name from Daily.co webhook event payload.
-
-    Args:
-        event: Parsed webhook event
-
-    Returns:
-        Room name if present and is a string, None otherwise
-
-    Example:
-        >>> event = DailyWebhookEvent(**webhook_payload)
-        >>> room_name = extract_room_name(event)
-    """
-    room = event.payload.get("room_name")
-    # Ensure we return a string, not any falsy value that might be in payload
-    return room if isinstance(room, str) else None
-
-
-def parse_participant_joined(event: DailyWebhookEvent) -> ParticipantJoinedPayload:
-    """
-    Parse participant.joined webhook event payload.
-
-    Args:
-        event: Webhook event with type "participant.joined"
-
-    Returns:
-        Parsed participant joined payload
-
-    Raises:
-        pydantic.ValidationError: If payload doesn't match expected schema
-    """
-    return ParticipantJoinedPayload(**event.payload)
-
-
-def parse_participant_left(event: DailyWebhookEvent) -> ParticipantLeftPayload:
-    """
-    Parse participant.left webhook event payload.
-
-    Args:
-        event: Webhook event with type "participant.left"
-
-    Returns:
-        Parsed participant left payload
-
-    Raises:
-        pydantic.ValidationError: If payload doesn't match expected schema
-    """
-    return ParticipantLeftPayload(**event.payload)
-
-
-def parse_recording_started(event: DailyWebhookEvent) -> RecordingStartedPayload:
-    """
-    Parse recording.started webhook event payload.
-
-    Args:
-        event: Webhook event with type "recording.started"
-
-    Returns:
-        Parsed recording started payload
-
-    Raises:
-        pydantic.ValidationError: If payload doesn't match expected schema
-    """
-    return RecordingStartedPayload(**event.payload)
-
-
-def parse_recording_ready(
-    event: DailyWebhookEvent,
-) -> RecordingReadyToDownloadPayload:
-    """
-    Parse recording.ready-to-download webhook event payload.
-
-    This event is sent when raw-tracks recordings are complete and uploaded to S3.
-    The payload includes a 'tracks' array with individual audio/video files.
-
-    Args:
-        event: Webhook event with type "recording.ready-to-download"
-
-    Returns:
-        Parsed recording ready payload with tracks array
-
-    Raises:
-        pydantic.ValidationError: If payload doesn't match expected schema
-
-    Example:
-        >>> event = DailyWebhookEvent(**webhook_payload)
-        >>> if event.type == "recording.ready-to-download":
-        ...     payload = parse_recording_ready(event)
-        ...     audio_tracks = [t for t in payload.tracks if t.type == "audio"]
-    """
-    return RecordingReadyToDownloadPayload(**event.payload)
-
-
-def parse_recording_error(event: DailyWebhookEvent) -> RecordingErrorPayload:
-    """
-    Parse recording.error webhook event payload.
-
-    Args:
-        event: Webhook event with type "recording.error"
-
-    Returns:
-        Parsed recording error payload
-
-    Raises:
-        pydantic.ValidationError: If payload doesn't match expected schema
-    """
-    return RecordingErrorPayload(**event.payload)
-
-
-WEBHOOK_PARSERS = {
-    "participant.joined": parse_participant_joined,
-    "participant.left": parse_participant_left,
-    "recording.started": parse_recording_started,
-    "recording.ready-to-download": parse_recording_ready,
-    "recording.error": parse_recording_error,
-}
-
-
-def parse_webhook_payload(event: DailyWebhookEvent):
-    """
-    Parse webhook event payload based on event type.
-
-    Args:
-        event: Webhook event
-
-    Returns:
-        Typed payload model based on event type, or raw dict if unknown
-
-    Example:
-        >>> event = DailyWebhookEvent(**webhook_payload)
-        >>> payload = parse_webhook_payload(event)
-        >>> if isinstance(payload, ParticipantJoinedPayload):
-        ...     print(f"User {payload.user_name} joined")
-    """
-    parser = WEBHOOK_PARSERS.get(event.type)
-    if parser:
-        return parser(event)
-    else:
-        logger.warning("Unknown webhook event type", event_type=event.type)
-        return event.payload

server/reflector/dailyco_api/webhooks.py

@@ -1,271 +0,0 @@
-"""
-Daily.co Webhook Event Models
-
-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 reflector.utils.string import NonEmptyString
-
-
-def normalize_timestamp_to_int(v):
-    """
-    Normalize float timestamps to int by truncating decimal part.
-
-    Daily.co sometimes sends timestamps as floats (e.g., 1708972279.96).
-    Pydantic expects int for fields typed as `int`.
-    """
-    if v is None:
-        return v
-    if isinstance(v, float):
-        return int(v)
-    return v
-
-
-WebhookEventType = Literal[
-    "participant.joined",
-    "participant.left",
-    "recording.started",
-    "recording.ready-to-download",
-    "recording.error",
-]
-
-
-class DailyTrack(BaseModel):
-    """
-    Individual audio or video track from a multitrack recording.
-
-    Reference: https://docs.daily.co/reference/rest-api/recordings
-    """
-
-    type: Literal["audio", "video"]
-    s3Key: NonEmptyString = Field(description="S3 object key for the track file")
-    size: int = Field(description="File size in bytes")
-
-
-class DailyWebhookEvent(BaseModel):
-    """
-    Base structure for all Daily.co webhook events.
-    All events share five common fields documented below.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks
-    """
-
-    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"
-    )
-    type: WebhookEventType = Field(
-        description="Represents the type of the event described in the payload"
-    )
-    id: NonEmptyString = Field(
-        description="An identifier representing this specific event"
-    )
-    payload: Dict[NonEmptyString, Any] = Field(
-        description="An object representing the event, whose fields are described in the corresponding payload class"
-    )
-    event_ts: int = Field(
-        description="Documenting when the webhook itself was sent. This timestamp is different than the time of the event the webhook describes. For example, a recording.started event will contain a start_ts timestamp of when the actual recording started, and a slightly later event_ts timestamp indicating when the webhook event was sent"
-    )
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class ParticipantJoinedPayload(BaseModel):
-    """
-    Payload for participant.joined webhook event.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks/events/participant-joined
-    """
-
-    room_name: NonEmptyString | None = Field(None, description="Daily.co room name")
-    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")
-    joined_at: int = Field(description="Join timestamp in Unix epoch seconds")
-
-    _normalize_joined_at = field_validator("joined_at", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class ParticipantLeftPayload(BaseModel):
-    """
-    Payload for participant.left webhook event.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks/events/participant-left
-    """
-
-    room_name: NonEmptyString | None = Field(None, description="Daily.co room name")
-    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")
-    joined_at: int = Field(description="Join timestamp in Unix epoch seconds")
-    duration: int | None = Field(
-        None, description="Duration of participation in seconds"
-    )
-
-    _normalize_joined_at = field_validator("joined_at", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingStartedPayload(BaseModel):
-    """
-    Payload for recording.started webhook event.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-started
-    """
-
-    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")
-
-    _normalize_start_ts = field_validator("start_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingReadyToDownloadPayload(BaseModel):
-    """
-    Payload for recording.ready-to-download webhook event.
-    This is sent when raw-tracks recordings are complete and uploaded to S3.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-ready-to-download
-    """
-
-    type: Literal["cloud", "raw-tracks"] = Field(
-        description="The type of recording that was generated"
-    )
-    recording_id: NonEmptyString = Field(
-        description="An ID identifying the recording that was generated"
-    )
-    room_name: NonEmptyString = Field(
-        description="The name of the room where the recording was made"
-    )
-    start_ts: int = Field(
-        description="The Unix epoch time in seconds representing when the recording started"
-    )
-    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"
-    )
-    duration: int = Field(description="The duration in seconds of the call")
-    s3_key: NonEmptyString = Field(
-        description="The location of the recording in the provided S3 bucket"
-    )
-    share_token: NonEmptyString | None = Field(
-        None, description="undocumented documented secret field"
-    )
-    tracks: list[DailyTrack] | None = Field(
-        None,
-        description="If the recording is a raw-tracks recording, a tracks field will be provided. If role permissions have been removed, the tracks field may be null",
-    )
-
-    _normalize_start_ts = field_validator("start_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingErrorPayload(BaseModel):
-    """
-    Payload for recording.error webhook event.
-
-    Reference: https://docs.daily.co/reference/rest-api/webhooks/events/recording-error
-    """
-
-    action: Literal["clourd-recording-err", "cloud-recording-error"] = Field(
-        description="A string describing the event that was emitted (both variants are documented)"
-    )
-    error_msg: NonEmptyString = Field(description="The error message returned")
-    instance_id: NonEmptyString = Field(
-        description="The recording instance ID that was passed into the start recording command"
-    )
-    room_name: NonEmptyString = Field(
-        description="The name of the room where the recording was made"
-    )
-    timestamp: int = Field(
-        description="The Unix epoch time in seconds representing when the error was emitted"
-    )
-
-    _normalize_timestamp = field_validator("timestamp", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class ParticipantJoinedEvent(BaseModel):
-    version: NonEmptyString
-    type: Literal["participant.joined"]
-    id: NonEmptyString
-    payload: ParticipantJoinedPayload
-    event_ts: int
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class ParticipantLeftEvent(BaseModel):
-    version: NonEmptyString
-    type: Literal["participant.left"]
-    id: NonEmptyString
-    payload: ParticipantLeftPayload
-    event_ts: int
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingStartedEvent(BaseModel):
-    version: NonEmptyString
-    type: Literal["recording.started"]
-    id: NonEmptyString
-    payload: RecordingStartedPayload
-    event_ts: int
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingReadyEvent(BaseModel):
-    version: NonEmptyString
-    type: Literal["recording.ready-to-download"]
-    id: NonEmptyString
-    payload: RecordingReadyToDownloadPayload
-    event_ts: int
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-class RecordingErrorEvent(BaseModel):
-    version: NonEmptyString
-    type: Literal["recording.error"]
-    id: NonEmptyString
-    payload: RecordingErrorPayload
-    event_ts: int
-
-    _normalize_event_ts = field_validator("event_ts", mode="before")(
-        normalize_timestamp_to_int
-    )
-
-
-DailyWebhookEventUnion = Annotated[
-    Union[
-        ParticipantJoinedEvent,
-        ParticipantLeftEvent,
-        RecordingStartedEvent,
-        RecordingReadyEvent,
-        RecordingErrorEvent,
-    ],
-    Field(discriminator="type"),
-]

server/reflector/db/__init__.py

@@ -24,14 +24,10 @@ def get_database() -> databases.Database:
 
 
 # import models
-import reflector.db.calendar_events  # noqa
-import reflector.db.daily_participant_sessions  # noqa
 import reflector.db.meetings  # noqa
 import reflector.db.recordings  # noqa
 import reflector.db.rooms  # noqa
 import reflector.db.transcripts  # noqa
-import reflector.db.user_api_keys  # noqa
-import reflector.db.users  # noqa
 
 kwargs = {}
 if "postgres" not in settings.DATABASE_URL:

server/reflector/db/calendar_events.py

@@ -1,187 +0,0 @@
-from datetime import datetime, timedelta, timezone
-from typing import Any
-
-import sqlalchemy as sa
-from pydantic import BaseModel, Field
-from sqlalchemy.dialects.postgresql import JSONB
-
-from reflector.db import get_database, metadata
-from reflector.utils import generate_uuid4
-
-calendar_events = sa.Table(
-    "calendar_event",
-    metadata,
-    sa.Column("id", sa.String, primary_key=True),
-    sa.Column(
-        "room_id",
-        sa.String,
-        sa.ForeignKey("room.id", ondelete="CASCADE", name="fk_calendar_event_room_id"),
-        nullable=False,
-    ),
-    sa.Column("ics_uid", sa.Text, nullable=False),
-    sa.Column("title", sa.Text),
-    sa.Column("description", sa.Text),
-    sa.Column("start_time", sa.DateTime(timezone=True), nullable=False),
-    sa.Column("end_time", sa.DateTime(timezone=True), nullable=False),
-    sa.Column("attendees", JSONB),
-    sa.Column("location", sa.Text),
-    sa.Column("ics_raw_data", sa.Text),
-    sa.Column("last_synced", sa.DateTime(timezone=True), nullable=False),
-    sa.Column("is_deleted", sa.Boolean, nullable=False, server_default=sa.false()),
-    sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
-    sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
-    sa.UniqueConstraint("room_id", "ics_uid", name="uq_room_calendar_event"),
-    sa.Index("idx_calendar_event_room_start", "room_id", "start_time"),
-    sa.Index(
-        "idx_calendar_event_deleted",
-        "is_deleted",
-        postgresql_where=sa.text("NOT is_deleted"),
-    ),
-)
-
-
-class CalendarEvent(BaseModel):
-    id: str = Field(default_factory=generate_uuid4)
-    room_id: str
-    ics_uid: str
-    title: str | None = None
-    description: str | None = None
-    start_time: datetime
-    end_time: datetime
-    attendees: list[dict[str, Any]] | None = None
-    location: str | None = None
-    ics_raw_data: str | None = None
-    last_synced: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-    is_deleted: bool = False
-    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-
-
-class CalendarEventController:
-    async def get_by_room(
-        self,
-        room_id: str,
-        include_deleted: bool = False,
-        start_after: datetime | None = None,
-        end_before: datetime | None = None,
-    ) -> list[CalendarEvent]:
-        query = calendar_events.select().where(calendar_events.c.room_id == room_id)
-
-        if not include_deleted:
-            query = query.where(calendar_events.c.is_deleted == False)
-
-        if start_after:
-            query = query.where(calendar_events.c.start_time >= start_after)
-
-        if end_before:
-            query = query.where(calendar_events.c.end_time <= end_before)
-
-        query = query.order_by(calendar_events.c.start_time.asc())
-
-        results = await get_database().fetch_all(query)
-        return [CalendarEvent(**result) for result in results]
-
-    async def get_upcoming(
-        self, room_id: str, minutes_ahead: int = 120
-    ) -> list[CalendarEvent]:
-        """Get upcoming events for a room within the specified minutes, including currently happening events."""
-        now = datetime.now(timezone.utc)
-        future_time = now + timedelta(minutes=minutes_ahead)
-
-        query = (
-            calendar_events.select()
-            .where(
-                sa.and_(
-                    calendar_events.c.room_id == room_id,
-                    calendar_events.c.is_deleted == False,
-                    calendar_events.c.start_time <= future_time,
-                    calendar_events.c.end_time >= now,
-                )
-            )
-            .order_by(calendar_events.c.start_time.asc())
-        )
-
-        results = await get_database().fetch_all(query)
-        return [CalendarEvent(**result) for result in results]
-
-    async def get_by_id(self, event_id: str) -> CalendarEvent | None:
-        query = calendar_events.select().where(calendar_events.c.id == event_id)
-        result = await get_database().fetch_one(query)
-        return CalendarEvent(**result) if result else None
-
-    async def get_by_ics_uid(self, room_id: str, ics_uid: str) -> CalendarEvent | None:
-        query = calendar_events.select().where(
-            sa.and_(
-                calendar_events.c.room_id == room_id,
-                calendar_events.c.ics_uid == ics_uid,
-            )
-        )
-        result = await get_database().fetch_one(query)
-        return CalendarEvent(**result) if result else None
-
-    async def upsert(self, event: CalendarEvent) -> CalendarEvent:
-        existing = await self.get_by_ics_uid(event.room_id, event.ics_uid)
-
-        if existing:
-            event.id = existing.id
-            event.created_at = existing.created_at
-            event.updated_at = datetime.now(timezone.utc)
-
-            query = (
-                calendar_events.update()
-                .where(calendar_events.c.id == existing.id)
-                .values(**event.model_dump())
-            )
-        else:
-            query = calendar_events.insert().values(**event.model_dump())
-
-        await get_database().execute(query)
-        return event
-
-    async def soft_delete_missing(
-        self, room_id: str, current_ics_uids: list[str]
-    ) -> int:
-        """Soft delete future events that are no longer in the calendar."""
-        now = datetime.now(timezone.utc)
-
-        select_query = calendar_events.select().where(
-            sa.and_(
-                calendar_events.c.room_id == room_id,
-                calendar_events.c.start_time > now,
-                calendar_events.c.is_deleted == False,
-                calendar_events.c.ics_uid.notin_(current_ics_uids)
-                if current_ics_uids
-                else True,
-            )
-        )
-
-        to_delete = await get_database().fetch_all(select_query)
-        delete_count = len(to_delete)
-
-        if delete_count > 0:
-            update_query = (
-                calendar_events.update()
-                .where(
-                    sa.and_(
-                        calendar_events.c.room_id == room_id,
-                        calendar_events.c.start_time > now,
-                        calendar_events.c.is_deleted == False,
-                        calendar_events.c.ics_uid.notin_(current_ics_uids)
-                        if current_ics_uids
-                        else True,
-                    )
-                )
-                .values(is_deleted=True, updated_at=now)
-            )
-
-            await get_database().execute(update_query)
-
-        return delete_count
-
-    async def delete_by_room(self, room_id: str) -> int:
-        query = calendar_events.delete().where(calendar_events.c.room_id == room_id)
-        result = await get_database().execute(query)
-        return result.rowcount
-
-
-calendar_events_controller = CalendarEventController()

server/reflector/db/daily_participant_sessions.py

@@ -1,229 +0,0 @@
-"""Daily.co participant session tracking.
-
-Stores webhook data for participant.joined and participant.left events to provide
-historical session information (Daily.co API only returns current participants).
-"""
-
-from datetime import datetime
-
-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_participant_sessions = sa.Table(
-    "daily_participant_session",
-    metadata,
-    sa.Column("id", sa.String, primary_key=True),
-    sa.Column(
-        "meeting_id",
-        sa.String,
-        sa.ForeignKey("meeting.id", ondelete="CASCADE"),
-        nullable=False,
-    ),
-    sa.Column(
-        "room_id",
-        sa.String,
-        sa.ForeignKey("room.id", ondelete="CASCADE"),
-        nullable=False,
-    ),
-    sa.Column("session_id", sa.String, nullable=False),
-    sa.Column("user_id", sa.String, nullable=True),
-    sa.Column("user_name", sa.String, nullable=False),
-    sa.Column("joined_at", sa.DateTime(timezone=True), nullable=False),
-    sa.Column("left_at", sa.DateTime(timezone=True), nullable=True),
-    sa.Index("idx_daily_session_meeting_left", "meeting_id", "left_at"),
-    sa.Index("idx_daily_session_room", "room_id"),
-)
-
-
-class DailyParticipantSession(BaseModel):
-    """Daily.co participant session record.
-
-    Tracks when a participant joined and left a meeting. Populated from webhooks:
-    - participant.joined: Creates record with left_at=None
-    - participant.left: Updates record with left_at
-
-    ID format: {meeting_id}:{user_id}:{joined_at_ms}
-    - Ensures idempotency (duplicate webhooks don't create duplicates)
-    - Allows same user to rejoin (different joined_at = different session)
-
-    Duration is calculated as: left_at - joined_at (not stored)
-    """
-
-    id: NonEmptyString
-    meeting_id: NonEmptyString
-    room_id: NonEmptyString
-    session_id: NonEmptyString  # Daily.co's session_id (identifies room session)
-    user_id: NonEmptyString | None = None
-    user_name: str
-    joined_at: datetime
-    left_at: datetime | None = None
-
-
-class DailyParticipantSessionController:
-    """Controller for Daily.co participant session persistence."""
-
-    async def get_by_id(self, id: str) -> DailyParticipantSession | None:
-        """Get a session by its ID."""
-        query = daily_participant_sessions.select().where(
-            daily_participant_sessions.c.id == id
-        )
-        result = await get_database().fetch_one(query)
-        return DailyParticipantSession(**result) if result else None
-
-    async def get_open_session(
-        self, meeting_id: NonEmptyString, session_id: NonEmptyString
-    ) -> DailyParticipantSession | None:
-        """Get the open (not left) session for a user in a meeting."""
-        query = daily_participant_sessions.select().where(
-            sa.and_(
-                daily_participant_sessions.c.meeting_id == meeting_id,
-                daily_participant_sessions.c.session_id == session_id,
-                daily_participant_sessions.c.left_at.is_(None),
-            )
-        )
-        results = await get_database().fetch_all(query)
-
-        if len(results) > 1:
-            raise ValueError(
-                f"Multiple open sessions for daily session {session_id} in meeting {meeting_id}: "
-                f"found {len(results)} sessions"
-            )
-
-        return DailyParticipantSession(**results[0]) if results else None
-
-    async def upsert_joined(self, session: DailyParticipantSession) -> None:
-        """Insert or update when participant.joined webhook arrives.
-
-        Idempotent: Duplicate webhooks with same ID are safely ignored.
-        Out-of-order: If left webhook arrived first, preserves left_at.
-        """
-        query = insert(daily_participant_sessions).values(**session.model_dump())
-        query = query.on_conflict_do_update(
-            index_elements=["id"],
-            set_={"user_name": session.user_name},
-        )
-        await get_database().execute(query)
-
-    async def upsert_left(self, session: DailyParticipantSession) -> None:
-        """Update session when participant.left webhook arrives.
-
-        Finds the open session for this user in this meeting and updates left_at.
-        Works around Daily.co webhook timestamp inconsistency (joined_at differs by ~4ms between webhooks).
-
-        Handles three cases:
-        1. Normal flow: open session exists → updates left_at
-        2. Out-of-order: left arrives first → creates new record with left data
-        3. Duplicate: left arrives again → idempotent (DB trigger prevents left_at modification)
-        """
-        if session.left_at is None:
-            raise ValueError("left_at is required for upsert_left")
-
-        if session.left_at <= session.joined_at:
-            raise ValueError(
-                f"left_at ({session.left_at}) must be after joined_at ({session.joined_at})"
-            )
-
-        # Find existing open session (works around timestamp mismatch in webhooks)
-        existing = await self.get_open_session(session.meeting_id, session.session_id)
-
-        if existing:
-            # Update existing open session
-            query = (
-                daily_participant_sessions.update()
-                .where(daily_participant_sessions.c.id == existing.id)
-                .values(left_at=session.left_at)
-            )
-            await get_database().execute(query)
-        else:
-            # Out-of-order or first webhook: insert new record
-            query = insert(daily_participant_sessions).values(**session.model_dump())
-            query = query.on_conflict_do_nothing(index_elements=["id"])
-            await get_database().execute(query)
-
-    async def get_by_meeting(self, meeting_id: str) -> list[DailyParticipantSession]:
-        """Get all participant sessions for a meeting (active and ended)."""
-        query = daily_participant_sessions.select().where(
-            daily_participant_sessions.c.meeting_id == meeting_id
-        )
-        results = await get_database().fetch_all(query)
-        return [DailyParticipantSession(**result) for result in results]
-
-    async def get_active_by_meeting(
-        self, meeting_id: str
-    ) -> list[DailyParticipantSession]:
-        """Get only active (not left) participant sessions for a meeting."""
-        query = daily_participant_sessions.select().where(
-            sa.and_(
-                daily_participant_sessions.c.meeting_id == meeting_id,
-                daily_participant_sessions.c.left_at.is_(None),
-            )
-        )
-        results = await get_database().fetch_all(query)
-        return [DailyParticipantSession(**result) for result in results]
-
-    async def get_all_sessions_for_meeting(
-        self, meeting_id: NonEmptyString
-    ) -> dict[NonEmptyString, DailyParticipantSession]:
-        query = daily_participant_sessions.select().where(
-            daily_participant_sessions.c.meeting_id == meeting_id
-        )
-        results = await get_database().fetch_all(query)
-        # TODO DailySessionId custom type
-        return {row["session_id"]: DailyParticipantSession(**row) for row in results}
-
-    async def batch_upsert_sessions(
-        self, sessions: list[DailyParticipantSession]
-    ) -> None:
-        """Upsert multiple sessions in single query.
-
-        Uses ON CONFLICT for idempotency. Updates user_name on conflict since they may change it during a meeting.
-
-        """
-        if not sessions:
-            return
-
-        values = [session.model_dump() for session in sessions]
-        query = insert(daily_participant_sessions).values(values)
-        query = query.on_conflict_do_update(
-            index_elements=["id"],
-            set_={
-                # Preserve existing left_at to prevent race conditions
-                "left_at": sa.func.coalesce(
-                    daily_participant_sessions.c.left_at,
-                    query.excluded.left_at,
-                ),
-                "user_name": query.excluded.user_name,
-            },
-        )
-        await get_database().execute(query)
-
-    async def batch_close_sessions(
-        self, session_ids: list[NonEmptyString], left_at: datetime
-    ) -> None:
-        """Mark multiple sessions as left in single query.
-
-        Only updates sessions where left_at is NULL (protects already-closed sessions).
-
-        Left_at mismatch for existing sessions is ignored, assumed to be not important issue if ever happens.
-        """
-        if not session_ids:
-            return
-
-        query = (
-            daily_participant_sessions.update()
-            .where(
-                sa.and_(
-                    daily_participant_sessions.c.id.in_(session_ids),
-                    daily_participant_sessions.c.left_at.is_(None),
-                )
-            )
-            .values(left_at=left_at)
-        )
-        await get_database().execute(query)
-
-
-daily_participant_sessions_controller = DailyParticipantSessionController()

server/reflector/db/meetings.py

@@ -1,15 +1,13 @@
 from datetime import datetime
-from typing import Any, Literal
+from typing import Literal
 
 import sqlalchemy as sa
+from fastapi import HTTPException
 from pydantic import BaseModel, Field
-from sqlalchemy.dialects.postgresql import JSONB
 
 from reflector.db import get_database, metadata
 from reflector.db.rooms import Room
-from reflector.schemas.platform import WHEREBY_PLATFORM, Platform
 from reflector.utils import generate_uuid4
-from reflector.utils.string import assert_equal
 
 meetings = sa.Table(
     "meeting",
@@ -20,12 +18,8 @@ meetings = sa.Table(
     sa.Column("host_room_url", sa.String),
     sa.Column("start_date", sa.DateTime(timezone=True)),
     sa.Column("end_date", sa.DateTime(timezone=True)),
-    sa.Column(
+    sa.Column("user_id", sa.String),
-        "room_id",
+    sa.Column("room_id", sa.String),
-        sa.String,
-        sa.ForeignKey("room.id", ondelete="CASCADE"),
-        nullable=True,
-    ),
     sa.Column("is_locked", sa.Boolean, nullable=False, server_default=sa.false()),
     sa.Column("room_mode", sa.String, nullable=False, server_default="normal"),
     sa.Column("recording_type", sa.String, nullable=False, server_default="cloud"),
@@ -47,36 +41,20 @@ meetings = sa.Table(
         nullable=False,
         server_default=sa.true(),
     ),
-    sa.Column(
-        "calendar_event_id",
-        sa.String,
-        sa.ForeignKey(
-            "calendar_event.id",
-            ondelete="SET NULL",
-            name="fk_meeting_calendar_event_id",
-        ),
-    ),
-    sa.Column("calendar_metadata", JSONB),
-    sa.Column(
-        "platform",
-        sa.String,
-        nullable=False,
-        server_default=assert_equal(WHEREBY_PLATFORM, "whereby"),
-    ),
     sa.Index("idx_meeting_room_id", "room_id"),
-    sa.Index("idx_meeting_calendar_event", "calendar_event_id"),
+    sa.Index(
+        "idx_one_active_meeting_per_room",
+        "room_id",
+        unique=True,
+        postgresql_where=sa.text("is_active = true"),
+    ),
 )
 
 meeting_consent = sa.Table(
     "meeting_consent",
     metadata,
     sa.Column("id", sa.String, primary_key=True),
-    sa.Column(
+    sa.Column("meeting_id", sa.String, sa.ForeignKey("meeting.id"), nullable=False),
-        "meeting_id",
-        sa.String,
-        sa.ForeignKey("meeting.id", ondelete="CASCADE"),
-        nullable=False,
-    ),
     sa.Column("user_id", sa.String),
     sa.Column("consent_given", sa.Boolean, nullable=False),
     sa.Column("consent_timestamp", sa.DateTime(timezone=True), nullable=False),
@@ -98,18 +76,15 @@ class Meeting(BaseModel):
     host_room_url: str
     start_date: datetime
     end_date: datetime
-    room_id: str | None
+    user_id: str | None = None
+    room_id: str | None = None
     is_locked: bool = False
     room_mode: Literal["normal", "group"] = "normal"
     recording_type: Literal["none", "local", "cloud"] = "cloud"
-    recording_trigger: Literal[  # whereby-specific
+    recording_trigger: Literal[
         "none", "prompt", "automatic", "automatic-2nd-participant"
     ] = "automatic-2nd-participant"
     num_clients: int = 0
-    is_active: bool = True
-    calendar_event_id: str | None = None
-    calendar_metadata: dict[str, Any] | None = None
-    platform: Platform = WHEREBY_PLATFORM
 
 
 class MeetingController:
@@ -121,10 +96,12 @@ class MeetingController:
         host_room_url: str,
         start_date: datetime,
         end_date: datetime,
+        user_id: str,
         room: Room,
-        calendar_event_id: str | None = None,
-        calendar_metadata: dict[str, Any] | None = None,
     ):
+        """
+        Create a new meeting
+        """
         meeting = Meeting(
             id=id,
             room_name=room_name,
@@ -132,49 +109,41 @@ class MeetingController:
             host_room_url=host_room_url,
             start_date=start_date,
             end_date=end_date,
+            user_id=user_id,
             room_id=room.id,
             is_locked=room.is_locked,
             room_mode=room.room_mode,
             recording_type=room.recording_type,
             recording_trigger=room.recording_trigger,
-            calendar_event_id=calendar_event_id,
-            calendar_metadata=calendar_metadata,
-            platform=room.platform,
         )
         query = meetings.insert().values(**meeting.model_dump())
         await get_database().execute(query)
         return meeting
 
-    async def get_all_active(self, platform: str | None = None) -> list[Meeting]:
+    async def get_all_active(self) -> list[Meeting]:
-        conditions = [meetings.c.is_active]
+        """
-        if platform is not None:
+        Get active meetings.
-            conditions.append(meetings.c.platform == platform)
+        """
-        query = meetings.select().where(sa.and_(*conditions))
+        query = meetings.select().where(meetings.c.is_active)
-        results = await get_database().fetch_all(query)
+        return await get_database().fetch_all(query)
-        return [Meeting(**result) for result in results]
 
     async def get_by_room_name(
         self,
         room_name: str,
-    ) -> Meeting | None:
+    ) -> Meeting:
         """
         Get a meeting by room name.
-        For backward compatibility, returns the most recent meeting.
         """
-        query = (
+        query = meetings.select().where(meetings.c.room_name == room_name)
-            meetings.select()
-            .where(meetings.c.room_name == room_name)
-            .order_by(meetings.c.end_date.desc())
-        )
         result = await get_database().fetch_one(query)
         if not result:
             return None
+
         return Meeting(**result)
 
-    async def get_active(self, room: Room, current_time: datetime) -> Meeting | None:
+    async def get_active(self, room: Room, current_time: datetime) -> Meeting:
         """
         Get latest active meeting for a room.
-        For backward compatibility, returns the most recent active meeting.
         """
         end_date = getattr(meetings.c, "end_date")
         query = (
@@ -191,97 +160,40 @@ class MeetingController:
         result = await get_database().fetch_one(query)
         if not result:
             return None
+
         return Meeting(**result)
 
-    async def get_all_active_for_room(
+    async def get_by_id(self, meeting_id: str, **kwargs) -> Meeting | None:
-        self, room: Room, current_time: datetime
-    ) -> list[Meeting]:
-        end_date = getattr(meetings.c, "end_date")
-        query = (
-            meetings.select()
-            .where(
-                sa.and_(
-                    meetings.c.room_id == room.id,
-                    meetings.c.end_date > current_time,
-                    meetings.c.is_active,
-                )
-            )
-            .order_by(end_date.desc())
-        )
-        results = await get_database().fetch_all(query)
-        return [Meeting(**result) for result in results]
-
-    async def get_active_by_calendar_event(
-        self, room: Room, calendar_event_id: str, current_time: datetime
-    ) -> Meeting | None:
         """
-        Get active meeting for a specific calendar event.
+        Get a meeting by id
         """
-        query = meetings.select().where(
-            sa.and_(
-                meetings.c.room_id == room.id,
-                meetings.c.calendar_event_id == calendar_event_id,
-                meetings.c.end_date > current_time,
-                meetings.c.is_active,
-            )
-        )
-        result = await get_database().fetch_one(query)
-        if not result:
-            return None
-        return Meeting(**result)
-
-    async def get_by_id(
-        self, meeting_id: str, room: Room | None = None
-    ) -> Meeting | None:
         query = meetings.select().where(meetings.c.id == meeting_id)
-
-        if room:
-            query = query.where(meetings.c.room_id == room.id)
-
         result = await get_database().fetch_one(query)
         if not result:
             return None
         return Meeting(**result)
 
-    async def get_by_calendar_event(
+    async def get_by_id_for_http(self, meeting_id: str, user_id: str | None) -> Meeting:
-        self, calendar_event_id: str, room: Room
+        """
-    ) -> Meeting | None:
+        Get a meeting by ID for HTTP request.
-        query = meetings.select().where(
+
-            meetings.c.calendar_event_id == calendar_event_id
+        If not found, it will raise a 404 error.
-        )
+        """
-        if room:
+        query = meetings.select().where(meetings.c.id == meeting_id)
-            query = query.where(meetings.c.room_id == room.id)
         result = await get_database().fetch_one(query)
         if not result:
-            return None
+            raise HTTPException(status_code=404, detail="Meeting not found")
-        return Meeting(**result)
+
+        meeting = Meeting(**result)
+        if result["user_id"] != user_id:
+            meeting.host_room_url = ""
+
+        return meeting
 
     async def update_meeting(self, meeting_id: str, **kwargs):
         query = meetings.update().where(meetings.c.id == meeting_id).values(**kwargs)
         await get_database().execute(query)
 
-    async def increment_num_clients(self, meeting_id: str) -> None:
-        """Atomically increment participant count."""
-        query = (
-            meetings.update()
-            .where(meetings.c.id == meeting_id)
-            .values(num_clients=meetings.c.num_clients + 1)
-        )
-        await get_database().execute(query)
-
-    async def decrement_num_clients(self, meeting_id: str) -> None:
-        """Atomically decrement participant count (min 0)."""
-        query = (
-            meetings.update()
-            .where(meetings.c.id == meeting_id)
-            .values(
-                num_clients=sa.case(
-                    (meetings.c.num_clients > 0, meetings.c.num_clients - 1), else_=0
-                )
-            )
-        )
-        await get_database().execute(query)
-
 
 class MeetingConsentController:
     async def get_by_meeting_id(self, meeting_id: str) -> list[MeetingConsent]:
@@ -302,9 +214,10 @@ class MeetingConsentController:
         result = await get_database().fetch_one(query)
         if result is None:
             return None
-        return MeetingConsent(**result)
+        return MeetingConsent(**result) if result else None
 
     async def upsert(self, consent: MeetingConsent) -> MeetingConsent:
+        """Create new consent or update existing one for authenticated users"""
         if consent.user_id:
             # For authenticated users, check if consent already exists
             # not transactional but we're ok with that; the consents ain't deleted anyways

server/reflector/db/recordings.py

@@ -21,7 +21,6 @@ recordings = sa.Table(
         server_default="pending",
     ),
     sa.Column("meeting_id", sa.String),
-    sa.Column("track_keys", sa.JSON, nullable=True),
     sa.Index("idx_recording_meeting_id", "meeting_id"),
 )
 
@@ -29,13 +28,10 @@ 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"] = "pending"
     meeting_id: str | None = None
-    # for multitrack reprocessing
-    track_keys: list[str] | None = None
 
 
 class RecordingController:
@@ -44,14 +40,12 @@ class RecordingController:
         await get_database().execute(query)
         return recording
 
-    async def get_by_id(self, id: str) -> Recording | None:
+    async def get_by_id(self, id: str) -> Recording:
         query = recordings.select().where(recordings.c.id == id)
         result = await get_database().fetch_one(query)
         return Recording(**result) if result else None
 
-    async def get_by_object_key(
+    async def get_by_object_key(self, bucket_name: str, object_key: str) -> Recording:
-        self, bucket_name: str, object_key: str
-    ) -> Recording | None:
         query = recordings.select().where(
             recordings.c.bucket_name == bucket_name,
             recordings.c.object_key == object_key,
@@ -63,14 +57,5 @@ class RecordingController:
         query = recordings.delete().where(recordings.c.id == 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 []
-
-        query = recordings.select().where(recordings.c.id.in_(recording_ids))
-        results = await get_database().fetch_all(query)
-        return [Recording(**row) for row in results]
-
 
 recordings_controller = RecordingController()

server/reflector/db/rooms.py

@@ -1,4 +1,3 @@
-import secrets
 from datetime import datetime, timezone
 from sqlite3 import IntegrityError
 from typing import Literal
@@ -9,8 +8,6 @@ from pydantic import BaseModel, Field
 from sqlalchemy.sql import false, or_
 
 from reflector.db import get_database, metadata
-from reflector.schemas.platform import Platform
-from reflector.settings import settings
 from reflector.utils import generate_uuid4
 
 rooms = sqlalchemy.Table(
@@ -43,22 +40,7 @@ rooms = sqlalchemy.Table(
     sqlalchemy.Column(
         "is_shared", sqlalchemy.Boolean, nullable=False, server_default=false()
     ),
-    sqlalchemy.Column("webhook_url", sqlalchemy.String, nullable=True),
-    sqlalchemy.Column("webhook_secret", sqlalchemy.String, nullable=True),
-    sqlalchemy.Column("ics_url", sqlalchemy.Text),
-    sqlalchemy.Column("ics_fetch_interval", sqlalchemy.Integer, server_default="300"),
-    sqlalchemy.Column(
-        "ics_enabled", sqlalchemy.Boolean, nullable=False, server_default=false()
-    ),
-    sqlalchemy.Column("ics_last_sync", sqlalchemy.DateTime(timezone=True)),
-    sqlalchemy.Column("ics_last_etag", sqlalchemy.Text),
-    sqlalchemy.Column(
-        "platform",
-        sqlalchemy.String,
-        nullable=False,
-    ),
     sqlalchemy.Index("idx_room_is_shared", "is_shared"),
-    sqlalchemy.Index("idx_room_ics_enabled", "ics_enabled"),
 )
 
 
@@ -73,18 +55,10 @@ class Room(BaseModel):
     is_locked: bool = False
     room_mode: Literal["normal", "group"] = "normal"
     recording_type: Literal["none", "local", "cloud"] = "cloud"
-    recording_trigger: Literal[  # whereby-specific
+    recording_trigger: Literal[
         "none", "prompt", "automatic", "automatic-2nd-participant"
     ] = "automatic-2nd-participant"
     is_shared: bool = False
-    webhook_url: str | None = None
-    webhook_secret: str | None = None
-    ics_url: str | None = None
-    ics_fetch_interval: int = 300
-    ics_enabled: bool = False
-    ics_last_sync: datetime | None = None
-    ics_last_etag: str | None = None
-    platform: Platform = Field(default_factory=lambda: settings.DEFAULT_VIDEO_PLATFORM)
 
 
 class RoomController:
@@ -133,39 +107,22 @@ class RoomController:
         recording_type: str,
         recording_trigger: str,
         is_shared: bool,
-        webhook_url: str = "",
-        webhook_secret: str = "",
-        ics_url: str | None = None,
-        ics_fetch_interval: int = 300,
-        ics_enabled: bool = False,
-        platform: Platform = settings.DEFAULT_VIDEO_PLATFORM,
     ):
         """
         Add a new room
         """
-        if webhook_url and not webhook_secret:
+        room = Room(
-            webhook_secret = secrets.token_urlsafe(32)
+            name=name,
-
+            user_id=user_id,
-        room_data = {
+            zulip_auto_post=zulip_auto_post,
-            "name": name,
+            zulip_stream=zulip_stream,
-            "user_id": user_id,
+            zulip_topic=zulip_topic,
-            "zulip_auto_post": zulip_auto_post,
+            is_locked=is_locked,
-            "zulip_stream": zulip_stream,
+            room_mode=room_mode,
-            "zulip_topic": zulip_topic,
+            recording_type=recording_type,
-            "is_locked": is_locked,
+            recording_trigger=recording_trigger,
-            "room_mode": room_mode,
+            is_shared=is_shared,
-            "recording_type": recording_type,
+        )
-            "recording_trigger": recording_trigger,
-            "is_shared": is_shared,
-            "webhook_url": webhook_url,
-            "webhook_secret": webhook_secret,
-            "ics_url": ics_url,
-            "ics_fetch_interval": ics_fetch_interval,
-            "ics_enabled": ics_enabled,
-            "platform": platform,
-        }
-
-        room = Room(**room_data)
         query = rooms.insert().values(**room.model_dump())
         try:
             await get_database().execute(query)
@@ -177,9 +134,6 @@ class RoomController:
         """
         Update a room fields with key/values in values
         """
-        if values.get("webhook_url") and not values.get("webhook_secret"):
-            values["webhook_secret"] = secrets.token_urlsafe(32)
-
         query = rooms.update().where(rooms.c.id == room.id).values(**values)
         try:
             await get_database().execute(query)
@@ -229,13 +183,6 @@ class RoomController:
 
         return room
 
-    async def get_ics_enabled(self) -> list[Room]:
-        query = rooms.select().where(
-            rooms.c.ics_enabled == True, rooms.c.ics_url != None
-        )
-        results = await get_database().fetch_all(query)
-        return [Room(**result) for result in results]
-
     async def remove_by_id(
         self,
         room_id: str,

server/reflector/db/search.py

@@ -8,14 +8,12 @@ from typing import Annotated, Any, Dict, Iterator
 
 import sqlalchemy
 import webvtt
-from databases.interfaces import Record as DbRecord
 from fastapi import HTTPException
 from pydantic import (
     BaseModel,
     Field,
     NonNegativeFloat,
     NonNegativeInt,
-    TypeAdapter,
     ValidationError,
     constr,
     field_serializer,
@@ -23,10 +21,9 @@ from pydantic import (
 
 from reflector.db import get_database
 from reflector.db.rooms import rooms
-from reflector.db.transcripts import SourceKind, TranscriptStatus, transcripts
+from reflector.db.transcripts import SourceKind, transcripts
 from reflector.db.utils import is_postgresql
 from reflector.logger import logger
-from reflector.utils.string import NonEmptyString, try_parse_non_empty_string
 
 DEFAULT_SEARCH_LIMIT = 20
 SNIPPET_CONTEXT_LENGTH = 50  # Characters before/after match to include
@@ -34,13 +31,12 @@ DEFAULT_SNIPPET_MAX_LENGTH = NonNegativeInt(150)
 DEFAULT_MAX_SNIPPETS = NonNegativeInt(3)
 LONG_SUMMARY_MAX_SNIPPETS = 2
 
-SearchQueryBase = constr(min_length=1, strip_whitespace=True)
+SearchQueryBase = constr(min_length=0, strip_whitespace=True)
 SearchLimitBase = Annotated[int, Field(ge=1, le=100)]
 SearchOffsetBase = Annotated[int, Field(ge=0)]
 SearchTotalBase = Annotated[int, Field(ge=0)]
 
 SearchQuery = Annotated[SearchQueryBase, Field(description="Search query text")]
-search_query_adapter = TypeAdapter(SearchQuery)
 SearchLimit = Annotated[SearchLimitBase, Field(description="Results per page")]
 SearchOffset = Annotated[
     SearchOffsetBase, Field(description="Number of results to skip")
@@ -92,7 +88,7 @@ class WebVTTProcessor:
     @staticmethod
     def generate_snippets(
         webvtt_content: WebVTTContent,
-        query: SearchQuery,
+        query: str,
         max_snippets: NonNegativeInt = DEFAULT_MAX_SNIPPETS,
     ) -> list[str]:
         """Generate snippets from WebVTT content."""
@@ -129,14 +125,12 @@ class SnippetCandidate:
 class SearchParameters(BaseModel):
     """Validated search parameters for full-text search."""
 
-    query_text: SearchQuery | None = None
+    query_text: SearchQuery
     limit: SearchLimit = DEFAULT_SEARCH_LIMIT
     offset: SearchOffset = 0
     user_id: str | None = None
     room_id: str | None = None
     source_kind: SourceKind | None = None
-    from_datetime: datetime | None = None
-    to_datetime: datetime | None = None
 
 
 class SearchResultDB(BaseModel):
@@ -163,7 +157,7 @@ class SearchResult(BaseModel):
     room_name: str | None = None
     source_kind: SourceKind
     created_at: datetime
-    status: TranscriptStatus = Field(..., min_length=1)
+    status: str = Field(..., min_length=1)
     rank: float = Field(..., ge=0, le=1)
     duration: NonNegativeFloat | None = Field(..., description="Duration in seconds")
     search_snippets: list[str] = Field(
@@ -205,13 +199,15 @@ class SnippetGenerator:
             prev_start = start
 
     @staticmethod
-    def count_matches(text: str, query: SearchQuery) -> NonNegativeInt:
+    def count_matches(text: str, query: str) -> NonNegativeInt:
         """Count total number of matches for a query in text."""
         ZERO = NonNegativeInt(0)
         if not text:
             logger.warning("Empty text for search query in count_matches")
             return ZERO
-        assert query is not None
+        if not query:
+            logger.warning("Empty query for search text in count_matches")
+            return ZERO
         return NonNegativeInt(
             sum(1 for _ in SnippetGenerator.find_all_matches(text, query))
         )
@@ -247,14 +243,13 @@ class SnippetGenerator:
     @staticmethod
     def generate(
         text: str,
-        query: SearchQuery,
+        query: str,
         max_length: NonNegativeInt = DEFAULT_SNIPPET_MAX_LENGTH,
         max_snippets: NonNegativeInt = DEFAULT_MAX_SNIPPETS,
     ) -> list[str]:
         """Generate snippets from text."""
-        assert query is not None
+        if not text or not query:
-        if not text:
+            logger.warning("Empty text or query for generate_snippets")
-            logger.warning("Empty text for generate_snippets")
             return []
 
         candidates = (
@@ -275,7 +270,7 @@ class SnippetGenerator:
     @staticmethod
     def from_summary(
         summary: str,
-        query: SearchQuery,
+        query: str,
         max_snippets: NonNegativeInt = LONG_SUMMARY_MAX_SNIPPETS,
     ) -> list[str]:
         """Generate snippets from summary text."""
@@ -283,9 +278,9 @@ class SnippetGenerator:
 
     @staticmethod
     def combine_sources(
-        summary: NonEmptyString | None,
+        summary: str | None,
         webvtt: WebVTTContent | None,
-        query: SearchQuery,
+        query: str,
         max_total: NonNegativeInt = DEFAULT_MAX_SNIPPETS,
     ) -> tuple[list[str], NonNegativeInt]:
         """Combine snippets from multiple sources and return total match count.
@@ -294,11 +289,6 @@ class SnippetGenerator:
 
         snippets can be empty for real in case of e.g. title match
         """
-
-        assert (
-            summary is not None or webvtt is not None
-        ), "At least one source must be present"
-
         webvtt_matches = 0
         summary_matches = 0
 
@@ -365,8 +355,8 @@ class SearchController:
                 else_=rooms.c.name,
             ).label("room_name"),
         ]
-        search_query = None
+
-        if params.query_text is not None:
+        if params.query_text:
             search_query = sqlalchemy.func.websearch_to_tsquery(
                 "english", params.query_text
             )
@@ -383,9 +373,7 @@ class SearchController:
             transcripts.join(rooms, transcripts.c.room_id == rooms.c.id, isouter=True)
         )
 
-        if params.query_text is not None:
+        if params.query_text:
-            # because already initialized based on params.query_text presence above
-            assert search_query is not None
             base_query = base_query.where(
                 transcripts.c.search_vector_en.op("@@")(search_query)
             )
@@ -404,16 +392,8 @@ class SearchController:
             base_query = base_query.where(
                 transcripts.c.source_kind == params.source_kind
             )
-        if params.from_datetime:
-            base_query = base_query.where(
-                transcripts.c.created_at >= params.from_datetime
-            )
-        if params.to_datetime:
-            base_query = base_query.where(
-                transcripts.c.created_at <= params.to_datetime
-            )
 
-        if params.query_text is not None:
+        if params.query_text:
             order_by = sqlalchemy.desc(sqlalchemy.text("rank"))
         else:
             order_by = sqlalchemy.desc(transcripts.c.created_at)
@@ -427,29 +407,19 @@ class SearchController:
         )
         total = await get_database().fetch_val(count_query)
 
-        def _process_result(r: DbRecord) -> SearchResult:
+        def _process_result(r) -> SearchResult:
             r_dict: Dict[str, Any] = dict(r)
-
             webvtt_raw: str | None = r_dict.pop("webvtt", None)
-            webvtt: WebVTTContent | None
             if webvtt_raw:
                 webvtt = WebVTTProcessor.parse(webvtt_raw)
             else:
                 webvtt = None
-
+            long_summary: str | None = r_dict.pop("long_summary", None)
-            long_summary_r: str | None = r_dict.pop("long_summary", None)
-            long_summary: NonEmptyString = try_parse_non_empty_string(long_summary_r)
             room_name: str | None = r_dict.pop("room_name", None)
             db_result = SearchResultDB.model_validate(r_dict)
 
-            at_least_one_source = webvtt is not None or long_summary is not None
+            snippets, total_match_count = SnippetGenerator.combine_sources(
-            has_query = params.query_text is not None
+                long_summary, webvtt, params.query_text, DEFAULT_MAX_SNIPPETS
-            snippets, total_match_count = (
-                SnippetGenerator.combine_sources(
-                    long_summary, webvtt, params.query_text, DEFAULT_MAX_SNIPPETS
-                )
-                if has_query and at_least_one_source
-                else ([], 0)
             )
 
             return SearchResult(

server/reflector/db/transcripts.py

@@ -21,7 +21,7 @@ from reflector.db.utils import is_postgresql
 from reflector.logger import logger
 from reflector.processors.types import Word as ProcessorWord
 from reflector.settings import settings
-from reflector.storage import get_transcripts_storage
+from reflector.storage import get_recordings_storage, get_transcripts_storage
 from reflector.utils import generate_uuid4
 from reflector.utils.webvtt import topics_to_webvtt
 
@@ -122,15 +122,6 @@ def generate_transcript_name() -> str:
     return f"Transcript {now.strftime('%Y-%m-%d %H:%M:%S')}"
 
 
-TranscriptStatus = Literal[
-    "idle", "uploaded", "recording", "processing", "error", "ended"
-]
-
-
-class StrValue(BaseModel):
-    value: str
-
-
 class AudioWaveform(BaseModel):
     data: list[float]
 
@@ -186,7 +177,6 @@ class TranscriptParticipant(BaseModel):
     id: str = Field(default_factory=generate_uuid4)
     speaker: int | None
     name: str
-    user_id: str | None = None
 
 
 class Transcript(BaseModel):
@@ -195,7 +185,7 @@ class Transcript(BaseModel):
     id: str = Field(default_factory=generate_uuid4)
     user_id: str | None = None
     name: str = Field(default_factory=generate_transcript_name)
-    status: TranscriptStatus = "idle"
+    status: str = "idle"
     duration: float = 0
     created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
     title: str | None = None
@@ -624,9 +614,7 @@ class TranscriptController:
                 )
                 if recording:
                     try:
-                        await get_transcripts_storage().delete_file(
+                        await get_recordings_storage().delete_file(recording.object_key)
-                            recording.object_key, bucket=recording.bucket_name
-                        )
                     except Exception as e:
                         logger.warning(
                             "Failed to delete recording object from S3",
@@ -650,19 +638,6 @@ class TranscriptController:
         query = transcripts.delete().where(transcripts.c.recording_id == recording_id)
         await get_database().execute(query)
 
-    @staticmethod
-    def user_can_mutate(transcript: Transcript, user_id: str | None) -> bool:
-        """
-        Returns True if the given user is allowed to modify the transcript.
-
-        Policy:
-        - Anonymous transcripts (user_id is None) cannot be modified via API
-        - Only the owner (matching user_id) can modify their transcript
-        """
-        if transcript.user_id is None:
-            return False
-        return user_id and transcript.user_id == user_id
-
     @asynccontextmanager
     async def transaction(self):
         """
@@ -728,13 +703,11 @@ class TranscriptController:
         """
         Download audio from storage
         """
-        storage = get_transcripts_storage()
+        transcript.audio_mp3_filename.write_bytes(
-        try:
+            await get_transcripts_storage().get_file(
-            with open(transcript.audio_mp3_filename, "wb") as f:
+                transcript.storage_audio_path,
-                await storage.stream_to_fileobj(transcript.storage_audio_path, f)
+            )
-        except Exception:
+        )
-            transcript.audio_mp3_filename.unlink(missing_ok=True)
-            raise
 
     async def upsert_participant(
         self,
@@ -759,27 +732,5 @@ class TranscriptController:
         transcript.delete_participant(participant_id)
         await self.update(transcript, {"participants": transcript.participants_dump()})
 
-    async def set_status(
-        self, transcript_id: str, status: TranscriptStatus
-    ) -> TranscriptEvent | None:
-        """
-        Update the status of a transcript
-
-        Will add an event STATUS + update the status field of transcript
-        """
-        async with self.transaction():
-            transcript = await self.get_by_id(transcript_id)
-            if not transcript:
-                raise Exception(f"Transcript {transcript_id} not found")
-            if transcript.status == status:
-                return
-            resp = await self.append_event(
-                transcript=transcript,
-                event="STATUS",
-                data=StrValue(value=status),
-            )
-            await self.update(transcript, {"status": status})
-        return resp
-
 
 transcripts_controller = TranscriptController()

server/reflector/db/user_api_keys.py

@@ -1,91 +0,0 @@
-import hmac
-import secrets
-from datetime import datetime, timezone
-from hashlib import sha256
-
-import sqlalchemy
-from pydantic import BaseModel, Field
-
-from reflector.db import get_database, metadata
-from reflector.settings import settings
-from reflector.utils import generate_uuid4
-from reflector.utils.string import NonEmptyString
-
-user_api_keys = sqlalchemy.Table(
-    "user_api_key",
-    metadata,
-    sqlalchemy.Column("id", sqlalchemy.String, primary_key=True),
-    sqlalchemy.Column("user_id", sqlalchemy.String, nullable=False),
-    sqlalchemy.Column("key_hash", sqlalchemy.String, nullable=False),
-    sqlalchemy.Column("name", sqlalchemy.String, nullable=True),
-    sqlalchemy.Column("created_at", sqlalchemy.DateTime(timezone=True), nullable=False),
-    sqlalchemy.Index("idx_user_api_key_hash", "key_hash", unique=True),
-    sqlalchemy.Index("idx_user_api_key_user_id", "user_id"),
-)
-
-
-class UserApiKey(BaseModel):
-    id: NonEmptyString = Field(default_factory=generate_uuid4)
-    user_id: NonEmptyString
-    key_hash: NonEmptyString
-    name: NonEmptyString | None = None
-    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-
-
-class UserApiKeyController:
-    @staticmethod
-    def generate_key() -> NonEmptyString:
-        return secrets.token_urlsafe(48)
-
-    @staticmethod
-    def hash_key(key: NonEmptyString) -> str:
-        return hmac.new(
-            settings.SECRET_KEY.encode(), key.encode(), digestmod=sha256
-        ).hexdigest()
-
-    @classmethod
-    async def create_key(
-        cls,
-        user_id: NonEmptyString,
-        name: NonEmptyString | None = None,
-    ) -> tuple[UserApiKey, NonEmptyString]:
-        plaintext = cls.generate_key()
-        api_key = UserApiKey(
-            user_id=user_id,
-            key_hash=cls.hash_key(plaintext),
-            name=name,
-        )
-        query = user_api_keys.insert().values(**api_key.model_dump())
-        await get_database().execute(query)
-        return api_key, plaintext
-
-    @classmethod
-    async def verify_key(cls, plaintext_key: NonEmptyString) -> UserApiKey | None:
-        key_hash = cls.hash_key(plaintext_key)
-        query = user_api_keys.select().where(
-            user_api_keys.c.key_hash == key_hash,
-        )
-        result = await get_database().fetch_one(query)
-        return UserApiKey(**result) if result else None
-
-    @staticmethod
-    async def list_by_user_id(user_id: NonEmptyString) -> list[UserApiKey]:
-        query = (
-            user_api_keys.select()
-            .where(user_api_keys.c.user_id == user_id)
-            .order_by(user_api_keys.c.created_at.desc())
-        )
-        results = await get_database().fetch_all(query)
-        return [UserApiKey(**r) for r in results]
-
-    @staticmethod
-    async def delete_key(key_id: NonEmptyString, user_id: NonEmptyString) -> bool:
-        query = user_api_keys.delete().where(
-            (user_api_keys.c.id == key_id) & (user_api_keys.c.user_id == user_id)
-        )
-        result = await get_database().execute(query)
-        # asyncpg returns None for DELETE, consider it success if no exception
-        return result is None or result > 0
-
-
-user_api_keys_controller = UserApiKeyController()

server/reflector/db/users.py

@@ -1,92 +0,0 @@
-"""User table for storing Authentik user information."""
-
-from datetime import datetime, timezone
-
-import sqlalchemy
-from pydantic import BaseModel, Field
-
-from reflector.db import get_database, metadata
-from reflector.utils import generate_uuid4
-from reflector.utils.string import NonEmptyString
-
-users = sqlalchemy.Table(
-    "user",
-    metadata,
-    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("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),
-    sqlalchemy.Index("idx_user_email", "email", unique=False),
-)
-
-
-class User(BaseModel):
-    id: NonEmptyString = Field(default_factory=generate_uuid4)
-    email: NonEmptyString
-    authentik_uid: NonEmptyString
-    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
-
-
-class UserController:
-    @staticmethod
-    async def get_by_id(user_id: NonEmptyString) -> User | None:
-        query = users.select().where(users.c.id == user_id)
-        result = await get_database().fetch_one(query)
-        return User(**result) if result else None
-
-    @staticmethod
-    async def get_by_authentik_uid(authentik_uid: NonEmptyString) -> User | None:
-        query = users.select().where(users.c.authentik_uid == authentik_uid)
-        result = await get_database().fetch_one(query)
-        return User(**result) if result else None
-
-    @staticmethod
-    async def get_by_email(email: NonEmptyString) -> User | None:
-        query = users.select().where(users.c.email == email)
-        result = await get_database().fetch_one(query)
-        return User(**result) if result else None
-
-    @staticmethod
-    async def create_or_update(
-        id: NonEmptyString, authentik_uid: NonEmptyString, email: NonEmptyString
-    ) -> User:
-        existing = await UserController.get_by_authentik_uid(authentik_uid)
-        now = datetime.now(timezone.utc)
-
-        if existing:
-            query = (
-                users.update()
-                .where(users.c.authentik_uid == authentik_uid)
-                .values(email=email, updated_at=now)
-            )
-            await get_database().execute(query)
-            return User(
-                id=existing.id,
-                authentik_uid=authentik_uid,
-                email=email,
-                created_at=existing.created_at,
-                updated_at=now,
-            )
-        else:
-            user = User(
-                id=id,
-                authentik_uid=authentik_uid,
-                email=email,
-                created_at=now,
-                updated_at=now,
-            )
-            query = users.insert().values(**user.model_dump())
-            await get_database().execute(query)
-            return user
-
-    @staticmethod
-    async def list_all() -> list[User]:
-        query = users.select().order_by(users.c.created_at.desc())
-        results = await get_database().fetch_all(query)
-        return [User(**r) for r in results]
-
-
-user_controller = UserController()

server/reflector/llm.py

@@ -1,4 +1,3 @@
-import logging
 from typing import Type, TypeVar
 
 from llama_index.core import Settings
@@ -6,7 +5,7 @@ from llama_index.core.output_parsers import PydanticOutputParser
 from llama_index.core.program import LLMTextCompletionProgram
 from llama_index.core.response_synthesizers import TreeSummarize
 from llama_index.llms.openai_like import OpenAILike
-from pydantic import BaseModel, ValidationError
+from pydantic import BaseModel
 
 T = TypeVar("T", bound=BaseModel)
 
@@ -62,8 +61,6 @@ class LLM:
         tone_name: str | None = None,
     ) -> T:
         """Get structured output from LLM for non-function-calling models"""
-        logger = logging.getLogger(__name__)
-
         summarizer = TreeSummarize(verbose=True)
         response = await summarizer.aget_response(prompt, texts, tone_name=tone_name)
 
@@ -79,25 +76,8 @@ class LLM:
             "Please structure the above information in the following JSON format:"
         )
 
-        try:
+        output = await program.acall(
-            output = await program.acall(
+            analysis=str(response), format_instructions=format_instructions
-                analysis=str(response), format_instructions=format_instructions
+        )
-            )
-        except ValidationError as e:
-            # Extract the raw JSON from the error details
-            errors = e.errors()
-            if errors and "input" in errors[0]:
-                raw_json = errors[0]["input"]
-                logger.error(
-                    f"JSON validation failed for {output_cls.__name__}. "
-                    f"Full raw JSON output:\n{raw_json}\n"
-                    f"Validation errors: {errors}"
-                )
-            else:
-                logger.error(
-                    f"JSON validation failed for {output_cls.__name__}. "
-                    f"Validation errors: {errors}"
-                )
-            raise
 
         return output

server/reflector/pipelines/__init__.py

@@ -1 +0,0 @@
-"""Pipeline modules for audio processing."""

server/reflector/pipelines/main_file_pipeline.py

@@ -7,34 +7,29 @@ Uses parallel processing for transcription, diarization, and waveform generation
 """
 
 import asyncio
-import uuid
 from pathlib import Path
 
 import av
 import structlog
-from celery import chain, shared_task
+from celery import shared_task
 
-from reflector.asynctask import asynctask
-from reflector.db.rooms import rooms_controller
 from reflector.db.transcripts import (
-    SourceKind,
     Transcript,
-    TranscriptStatus,
     transcripts_controller,
 )
 from reflector.logger import logger
-from reflector.pipelines import topic_processing
+from reflector.pipelines.main_live_pipeline import PipelineMainBase, asynctask
-from reflector.pipelines.main_live_pipeline import (
+from reflector.processors import (
-    PipelineMainBase,
+    AudioFileWriterProcessor,
-    broadcast_to_sockets,
+    TranscriptFinalSummaryProcessor,
-    task_cleanup_consent,
+    TranscriptFinalTitleProcessor,
-    task_pipeline_post_to_zulip,
+    TranscriptTopicDetectorProcessor,
 )
-from reflector.pipelines.transcription_helpers import transcribe_file_with_processor
-from reflector.processors import AudioFileWriterProcessor
 from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
 from reflector.processors.file_diarization import FileDiarizationInput
 from reflector.processors.file_diarization_auto import FileDiarizationAutoProcessor
+from reflector.processors.file_transcript import FileTranscriptInput
+from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
 from reflector.processors.transcript_diarization_assembler import (
     TranscriptDiarizationAssemblerInput,
     TranscriptDiarizationAssemblerProcessor,
@@ -48,7 +43,19 @@ from reflector.processors.types import (
 )
 from reflector.settings import settings
 from reflector.storage import get_transcripts_storage
-from reflector.worker.webhook import send_transcript_webhook
+
+
+class EmptyPipeline:
+    """Empty pipeline for processors that need a pipeline reference"""
+
+    def __init__(self, logger: structlog.BoundLogger):
+        self.logger = logger
+
+    def get_pref(self, k, d=None):
+        return d
+
+    async def emit(self, event):
+        pass
 
 
 class PipelineMainFile(PipelineMainBase):
@@ -63,7 +70,7 @@ class PipelineMainFile(PipelineMainBase):
     def __init__(self, transcript_id: str):
         super().__init__(transcript_id=transcript_id)
         self.logger = logger.bind(transcript_id=self.transcript_id)
-        self.empty_pipeline = topic_processing.EmptyPipeline(logger=self.logger)
+        self.empty_pipeline = EmptyPipeline(logger=self.logger)
 
     def _handle_gather_exceptions(self, results: list, operation: str) -> None:
         """Handle exceptions from asyncio.gather with return_exceptions=True"""
@@ -76,27 +83,12 @@ class PipelineMainFile(PipelineMainBase):
                 exc_info=result,
             )
 
-    @broadcast_to_sockets
-    async def set_status(self, transcript_id: str, status: TranscriptStatus):
-        async with self.lock_transaction():
-            return await transcripts_controller.set_status(transcript_id, status)
-
     async def process(self, file_path: Path):
         """Main entry point for file processing"""
         self.logger.info(f"Starting file pipeline for {file_path}")
 
         transcript = await self.get_transcript()
 
-        # Clear transcript as we're going to regenerate everything
-        async with self.transaction():
-            await transcripts_controller.update(
-                transcript,
-                {
-                    "events": [],
-                    "topics": [],
-                },
-            )
-
         # Extract audio and write to transcript location
         audio_path = await self.extract_and_write_audio(file_path, transcript)
 
@@ -113,8 +105,6 @@ class PipelineMainFile(PipelineMainBase):
 
         self.logger.info("File pipeline complete")
 
-        await self.set_status(transcript.id, "ended")
-
     async def extract_and_write_audio(
         self, file_path: Path, transcript: Transcript
     ) -> Path:
@@ -244,7 +234,24 @@ class PipelineMainFile(PipelineMainBase):
 
     async def transcribe_file(self, audio_url: str, language: str) -> TranscriptType:
         """Transcribe complete file"""
-        return await transcribe_file_with_processor(audio_url, language)
+        processor = FileTranscriptAutoProcessor()
+        input_data = FileTranscriptInput(audio_url=audio_url, language=language)
+
+        # Store result for retrieval
+        result: TranscriptType | None = None
+
+        async def capture_result(transcript):
+            nonlocal result
+            result = transcript
+
+        processor.on(capture_result)
+        await processor.push(input_data)
+        await processor.flush()
+
+        if not result:
+            raise ValueError("No transcript captured")
+
+        return result
 
     async def diarize_file(self, audio_url: str) -> list[DiarizationSegment] | None:
         """Get diarization for file"""
@@ -287,53 +294,63 @@ class PipelineMainFile(PipelineMainBase):
     async def detect_topics(
         self, transcript: TranscriptType, target_language: str
     ) -> list[TitleSummary]:
-        return await topic_processing.detect_topics(
+        """Detect topics from complete transcript"""
-            transcript,
+        chunk_size = 300
-            target_language,
+        topics: list[TitleSummary] = []
-            on_topic_callback=self.on_topic,
+
-            empty_pipeline=self.empty_pipeline,
+        async def on_topic(topic: TitleSummary):
-        )
+            topics.append(topic)
+            return await self.on_topic(topic)
+
+        topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
+        topic_detector.set_pipeline(self.empty_pipeline)
+
+        for i in range(0, len(transcript.words), chunk_size):
+            chunk_words = transcript.words[i : i + chunk_size]
+            if not chunk_words:
+                continue
+
+            chunk_transcript = TranscriptType(
+                words=chunk_words, translation=transcript.translation
+            )
+
+            await topic_detector.push(chunk_transcript)
+
+        await topic_detector.flush()
+        return topics
 
     async def generate_title(self, topics: list[TitleSummary]):
-        return await topic_processing.generate_title(
+        """Generate title from topics"""
-            topics,
+        if not topics:
-            on_title_callback=self.on_title,
+            self.logger.warning("No topics for title generation")
-            empty_pipeline=self.empty_pipeline,
+            return
-            logger=self.logger,
+
-        )
+        processor = TranscriptFinalTitleProcessor(callback=self.on_title)
+        processor.set_pipeline(self.empty_pipeline)
+
+        for topic in topics:
+            await processor.push(topic)
+
+        await processor.flush()
 
     async def generate_summaries(self, topics: list[TitleSummary]):
+        """Generate long and short summaries from topics"""
+        if not topics:
+            self.logger.warning("No topics for summary generation")
+            return
+
         transcript = await self.get_transcript()
-        return await topic_processing.generate_summaries(
+        processor = TranscriptFinalSummaryProcessor(
-            topics,
+            transcript=transcript,
-            transcript,
+            callback=self.on_long_summary,
-            on_long_summary_callback=self.on_long_summary,
+            on_short_summary=self.on_short_summary,
-            on_short_summary_callback=self.on_short_summary,
-            empty_pipeline=self.empty_pipeline,
-            logger=self.logger,
         )
+        processor.set_pipeline(self.empty_pipeline)
 
+        for topic in topics:
+            await processor.push(topic)
 
-@shared_task
+        await processor.flush()
-@asynctask
-async def task_send_webhook_if_needed(*, transcript_id: str):
-    """Send webhook if this is a room recording with webhook configured"""
-    transcript = await transcripts_controller.get_by_id(transcript_id)
-    if not transcript:
-        return
-
-    if transcript.source_kind == SourceKind.ROOM and transcript.room_id:
-        room = await rooms_controller.get_by_id(transcript.room_id)
-        if room and room.webhook_url:
-            logger.info(
-                "Dispatching webhook",
-                transcript_id=transcript_id,
-                room_id=room.id,
-                webhook_url=room.webhook_url,
-            )
-            send_transcript_webhook.delay(
-                transcript_id, room.id, event_id=uuid.uuid4().hex
-            )
 
 
 @shared_task
@@ -345,33 +362,14 @@ async def task_pipeline_file_process(*, transcript_id: str):
     if not transcript:
         raise Exception(f"Transcript {transcript_id} not found")
 
+    # Find the file to process
+    audio_file = next(transcript.data_path.glob("upload.*"), None)
+    if not audio_file:
+        audio_file = next(transcript.data_path.glob("audio.*"), None)
+
+    if not audio_file:
+        raise Exception("No audio file found to process")
+
+    # Run file pipeline
     pipeline = PipelineMainFile(transcript_id=transcript_id)
-    try:
+    await pipeline.process(audio_file)
-        await pipeline.set_status(transcript_id, "processing")
-
-        # Find the file to process
-        audio_file = next(transcript.data_path.glob("upload.*"), None)
-        if not audio_file:
-            audio_file = next(transcript.data_path.glob("audio.*"), None)
-
-        if not audio_file:
-            raise Exception("No audio file found to process")
-
-        await pipeline.process(audio_file)
-
-    except Exception as e:
-        logger.error(
-            f"File pipeline failed for transcript {transcript_id}: {type(e).__name__}: {str(e)}",
-            exc_info=True,
-            transcript_id=transcript_id,
-        )
-        await pipeline.set_status(transcript_id, "error")
-        raise
-
-    # Run post-processing chain: consent cleanup -> zulip -> webhook
-    post_chain = chain(
-        task_cleanup_consent.si(transcript_id=transcript_id),
-        task_pipeline_post_to_zulip.si(transcript_id=transcript_id),
-        task_send_webhook_if_needed.si(transcript_id=transcript_id),
-    )
-    post_chain.delay()

server/reflector/pipelines/main_live_pipeline.py

@@ -17,11 +17,12 @@ from contextlib import asynccontextmanager
 from typing import Generic
 
 import av
+import boto3
 from celery import chord, current_task, group, shared_task
 from pydantic import BaseModel
 from structlog import BoundLogger as Logger
 
-from reflector.asynctask import asynctask
+from reflector.db import get_database
 from reflector.db.meetings import meeting_consent_controller, meetings_controller
 from reflector.db.recordings import recordings_controller
 from reflector.db.rooms import rooms_controller
@@ -31,7 +32,6 @@ from reflector.db.transcripts import (
     TranscriptFinalLongSummary,
     TranscriptFinalShortSummary,
     TranscriptFinalTitle,
-    TranscriptStatus,
     TranscriptText,
     TranscriptTopic,
     TranscriptWaveform,
@@ -69,6 +69,29 @@ from reflector.zulip import (
 )
 
 
+def asynctask(f):
+    @functools.wraps(f)
+    def wrapper(*args, **kwargs):
+        async def run_with_db():
+            database = get_database()
+            await database.connect()
+            try:
+                return await f(*args, **kwargs)
+            finally:
+                await database.disconnect()
+
+        coro = run_with_db()
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            loop = None
+        if loop and loop.is_running():
+            return loop.run_until_complete(coro)
+        return asyncio.run(coro)
+
+    return wrapper
+
+
 def broadcast_to_sockets(func):
     """
     Decorator to broadcast transcript event to websockets
@@ -84,20 +107,6 @@ def broadcast_to_sockets(func):
             message=resp.model_dump(mode="json"),
         )
 
-        transcript = await transcripts_controller.get_by_id(self.transcript_id)
-        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"}
-            if resp.event in allowed_user_events:
-                await self.ws_manager.send_json(
-                    room_id=f"user:{transcript.user_id}",
-                    message={
-                        "event": f"TRANSCRIPT_{resp.event}",
-                        "data": {"id": self.transcript_id, **resp.data},
-                    },
-                )
-
     return wrapper
 
 
@@ -178,16 +187,9 @@ class PipelineMainBase(PipelineRunner[PipelineMessage], Generic[PipelineMessage]
             for topic in topics
         ]
 
-    @asynccontextmanager
-    async def lock_transaction(self):
-        # This lock is to prevent multiple processor starting adding
-        # into event array at the same time
-        async with self._lock:
-            yield
-
     @asynccontextmanager
     async def transaction(self):
-        async with self.lock_transaction():
+        async with self._lock:
             async with transcripts_controller.transaction():
                 yield
 
@@ -196,14 +198,14 @@ class PipelineMainBase(PipelineRunner[PipelineMessage], Generic[PipelineMessage]
         # if it's the first part, update the status of the transcript
         # but do not set the ended status yet.
         if isinstance(self, PipelineMainLive):
-            status_mapping: dict[str, TranscriptStatus] = {
+            status_mapping = {
                 "started": "recording",
                 "push": "recording",
                 "flush": "processing",
                 "error": "error",
             }
         elif isinstance(self, PipelineMainFinalSummaries):
-            status_mapping: dict[str, TranscriptStatus] = {
+            status_mapping = {
                 "push": "processing",
                 "flush": "processing",
                 "error": "error",
@@ -219,8 +221,22 @@ class PipelineMainBase(PipelineRunner[PipelineMessage], Generic[PipelineMessage]
             return
 
         # when the status of the pipeline changes, update the transcript
-        async with self._lock:
+        async with self.transaction():
-            return await transcripts_controller.set_status(self.transcript_id, status)
+            transcript = await self.get_transcript()
+            if status == transcript.status:
+                return
+            resp = await transcripts_controller.append_event(
+                transcript=transcript,
+                event="STATUS",
+                data=StrValue(value=status),
+            )
+            await transcripts_controller.update(
+                transcript,
+                {
+                    "status": status,
+                },
+            )
+            return resp
 
     @broadcast_to_sockets
     async def on_transcript(self, data):
@@ -583,7 +599,6 @@ async def cleanup_consent(transcript: Transcript, logger: Logger):
 
     consent_denied = False
     recording = None
-    meeting = None
     try:
         if transcript.recording_id:
             recording = await recordings_controller.get_by_id(transcript.recording_id)
@@ -594,8 +609,8 @@ async def cleanup_consent(transcript: Transcript, logger: Logger):
                         meeting.id
                     )
     except Exception as e:
-        logger.error(f"Failed to fetch consent: {e}", exc_info=e)
+        logger.error(f"Failed to get fetch consent: {e}", exc_info=e)
-        raise
+        consent_denied = True
 
     if not consent_denied:
         logger.info("Consent approved, keeping all files")
@@ -603,24 +618,25 @@ async def cleanup_consent(transcript: Transcript, logger: Logger):
 
     logger.info("Consent denied, cleaning up all related audio files")
 
-    deletion_errors = []
+    if recording and recording.bucket_name and recording.object_key:
-    if recording and recording.bucket_name:
+        s3_whereby = boto3.client(
-        keys_to_delete = []
+            "s3",
-        if recording.track_keys:
+            aws_access_key_id=settings.AWS_WHEREBY_ACCESS_KEY_ID,
-            keys_to_delete = recording.track_keys
+            aws_secret_access_key=settings.AWS_WHEREBY_ACCESS_KEY_SECRET,
-        elif recording.object_key:
+        )
-            keys_to_delete = [recording.object_key]
+        try:
-
+            s3_whereby.delete_object(
-        master_storage = get_transcripts_storage()
+                Bucket=recording.bucket_name, Key=recording.object_key
-        for key in keys_to_delete:
+            )
-            try:
+            logger.info(
-                await master_storage.delete_file(key, bucket=recording.bucket_name)
+                f"Deleted original Whereby recording: {recording.bucket_name}/{recording.object_key}"
-                logger.info(f"Deleted recording file: {recording.bucket_name}/{key}")
+            )
-            except Exception as e:
+        except Exception as e:
-                error_msg = f"Failed to delete {key}: {e}"
+            logger.error(f"Failed to delete Whereby recording: {e}", exc_info=e)
-                logger.error(error_msg, exc_info=e)
-                deletion_errors.append(error_msg)
 
+    # non-transactional, files marked for deletion not actually deleted is possible
+    await transcripts_controller.update(transcript, {"audio_deleted": True})
+    # 2. Delete processed audio from transcript storage S3 bucket
     if transcript.audio_location == "storage":
         storage = get_transcripts_storage()
         try:
@@ -629,28 +645,18 @@ async def cleanup_consent(transcript: Transcript, logger: Logger):
                 f"Deleted processed audio from storage: {transcript.storage_audio_path}"
             )
         except Exception as e:
-            error_msg = f"Failed to delete processed audio: {e}"
+            logger.error(f"Failed to delete processed audio: {e}", exc_info=e)
-            logger.error(error_msg, exc_info=e)
-            deletion_errors.append(error_msg)
 
+    # 3. Delete local audio files
     try:
         if hasattr(transcript, "audio_mp3_filename") and transcript.audio_mp3_filename:
             transcript.audio_mp3_filename.unlink(missing_ok=True)
         if hasattr(transcript, "audio_wav_filename") and transcript.audio_wav_filename:
             transcript.audio_wav_filename.unlink(missing_ok=True)
     except Exception as e:
-        error_msg = f"Failed to delete local audio files: {e}"
+        logger.error(f"Failed to delete local audio files: {e}", exc_info=e)
-        logger.error(error_msg, exc_info=e)
-        deletion_errors.append(error_msg)
 
-    if deletion_errors:
+    logger.info("Consent cleanup done")
-        logger.warning(
-            f"Consent cleanup completed with {len(deletion_errors)} errors",
-            errors=deletion_errors,
-        )
-    else:
-        await transcripts_controller.update(transcript, {"audio_deleted": True})
-        logger.info("Consent cleanup done - all audio deleted")
 
 
 @get_transcript
@@ -788,7 +794,7 @@ def pipeline_post(*, transcript_id: str):
         chain_final_summaries,
     ) | task_pipeline_post_to_zulip.si(transcript_id=transcript_id)
 
-    return chain.delay()
+    chain.delay()
 
 
 @get_transcript

server/reflector/pipelines/main_multitrack_pipeline.py

@@ -1,695 +0,0 @@
-import asyncio
-import math
-import tempfile
-from fractions import Fraction
-from pathlib import Path
-
-import av
-from av.audio.resampler import AudioResampler
-from celery import chain, shared_task
-
-from reflector.asynctask import asynctask
-from reflector.db.transcripts import (
-    TranscriptStatus,
-    TranscriptWaveform,
-    transcripts_controller,
-)
-from reflector.logger import logger
-from reflector.pipelines import topic_processing
-from reflector.pipelines.main_file_pipeline import task_send_webhook_if_needed
-from reflector.pipelines.main_live_pipeline import (
-    PipelineMainBase,
-    broadcast_to_sockets,
-    task_cleanup_consent,
-    task_pipeline_post_to_zulip,
-)
-from reflector.pipelines.transcription_helpers import transcribe_file_with_processor
-from reflector.processors import AudioFileWriterProcessor
-from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
-from reflector.processors.types import TitleSummary
-from reflector.processors.types import Transcript as TranscriptType
-from reflector.storage import Storage, get_transcripts_storage
-from reflector.utils.string import NonEmptyString
-
-# Audio encoding constants
-OPUS_STANDARD_SAMPLE_RATE = 48000
-OPUS_DEFAULT_BIT_RATE = 128000
-
-# Storage operation constants
-PRESIGNED_URL_EXPIRATION_SECONDS = 7200  # 2 hours
-
-
-class PipelineMainMultitrack(PipelineMainBase):
-    def __init__(self, transcript_id: str):
-        super().__init__(transcript_id=transcript_id)
-        self.logger = logger.bind(transcript_id=self.transcript_id)
-        self.empty_pipeline = topic_processing.EmptyPipeline(logger=self.logger)
-
-    async def pad_track_for_transcription(
-        self,
-        track_url: NonEmptyString,
-        track_idx: int,
-        storage: Storage,
-    ) -> NonEmptyString:
-        """
-        Pad a single track with silence based on stream metadata start_time.
-        Downloads from S3 presigned URL, processes via PyAV using tempfile, uploads to S3.
-        Returns presigned URL of padded track (or original URL if no padding needed).
-
-        Memory usage:
-        - Pattern: fixed_overhead(2-5MB) for PyAV codec/filters
-        - PyAV streams input efficiently (no full download, verified)
-        - Output written to tempfile (disk-based, not memory)
-        - Upload streams from file handle (boto3 chunks, typically 5-10MB)
-
-        Daily.co raw-tracks timing - Two approaches:
-
-            CURRENT APPROACH (PyAV metadata):
-            The WebM stream.start_time field encodes MEETING-RELATIVE timing:
-            - t=0: When Daily.co recording started (first participant joined)
-            - start_time=8.13s: This participant's track began 8.13s after recording started
-            - Purpose: Enables track alignment without external manifest files
-
-            This is NOT:
-            - Stream-internal offset (first packet timestamp relative to stream start)
-            - Absolute/wall-clock time
-            - Recording duration
-
-            ALTERNATIVE APPROACH (filename parsing):
-            Daily.co filenames contain Unix timestamps (milliseconds):
-            Format: {recording_start_ts}-{participant_id}-cam-audio-{track_start_ts}.webm
-            Example: 1760988935484-52f7f48b-fbab-431f-9a50-87b9abfc8255-cam-audio-1760988935922.webm
-
-            Can calculate offset: (track_start_ts - recording_start_ts) / 1000
-            - Track 0: (1760988935922 - 1760988935484) / 1000 = 0.438s
-            - Track 1: (1760988943823 - 1760988935484) / 1000 = 8.339s
-
-            TIME DIFFERENCE: PyAV metadata vs filename timestamps differ by ~209ms:
-            - Track 0: filename=438ms, metadata=229ms (diff: 209ms)
-            - Track 1: filename=8339ms, metadata=8130ms (diff: 209ms)
-
-            Consistent delta suggests network/encoding delay. PyAV metadata is ground truth
-            (represents when audio stream actually started vs when file upload initiated).
-
-            Example with 2 participants:
-                Track A: start_time=0.2s → Joined 200ms after recording began
-                Track B: start_time=8.1s → Joined 8.1 seconds later
-
-                After padding:
-                    Track A: [0.2s silence] + [speech...]
-                    Track B: [8.1s silence] + [speech...]
-
-                Whisper transcription timestamps are now synchronized:
-                    Track A word at 5.0s → happened at meeting t=5.0s
-                    Track B word at 10.0s → happened at meeting t=10.0s
-
-                Merging just sorts by timestamp - no offset calculation needed.
-
-        Padding coincidentally involves re-encoding. It's important when we work with Daily.co + Whisper.
-        This is because Daily.co returns recordings with skipped frames e.g. when microphone muted.
-        Daily.co doesn't understand those frames and ignores them, causing timestamp issues in transcription.
-        Re-encoding restores those frames. We do padding and re-encoding together just because it's convenient and more performant:
-        we need padded values for mix mp3 anyways
-        """
-
-        transcript = await self.get_transcript()
-
-        try:
-            # PyAV streams input from S3 URL efficiently (2-5MB fixed overhead for codec/filters)
-            with av.open(track_url) as in_container:
-                start_time_seconds = self._extract_stream_start_time_from_container(
-                    in_container, track_idx
-                )
-
-                if start_time_seconds <= 0:
-                    self.logger.info(
-                        f"Track {track_idx} requires no padding (start_time={start_time_seconds}s)",
-                        track_idx=track_idx,
-                    )
-                    return track_url
-
-                # Use tempfile instead of BytesIO for better memory efficiency
-                # Reduces peak memory usage during encoding/upload
-                with tempfile.NamedTemporaryFile(
-                    suffix=".webm", delete=False
-                ) as temp_file:
-                    temp_path = temp_file.name
-
-                try:
-                    self._apply_audio_padding_to_file(
-                        in_container, temp_path, start_time_seconds, track_idx
-                    )
-
-                    storage_path = (
-                        f"file_pipeline/{transcript.id}/tracks/padded_{track_idx}.webm"
-                    )
-
-                    # Upload using file handle for streaming
-                    with open(temp_path, "rb") as padded_file:
-                        await storage.put_file(storage_path, padded_file)
-                finally:
-                    # Clean up temp file
-                    Path(temp_path).unlink(missing_ok=True)
-
-                padded_url = await storage.get_file_url(
-                    storage_path,
-                    operation="get_object",
-                    expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-                )
-
-                self.logger.info(
-                    f"Successfully padded track {track_idx}",
-                    track_idx=track_idx,
-                    start_time_seconds=start_time_seconds,
-                    padded_url=padded_url,
-                )
-
-                return padded_url
-
-        except Exception as e:
-            self.logger.error(
-                f"Failed to process track {track_idx}",
-                track_idx=track_idx,
-                url=track_url,
-                error=str(e),
-                exc_info=True,
-            )
-            raise Exception(
-                f"Track {track_idx} padding failed - transcript would have incorrect timestamps"
-            ) from e
-
-    def _extract_stream_start_time_from_container(
-        self, container, track_idx: int
-    ) -> float:
-        """
-        Extract meeting-relative start time from WebM stream metadata.
-        Uses PyAV to read stream.start_time from WebM container.
-        More accurate than filename timestamps by ~209ms due to network/encoding delays.
-        """
-        start_time_seconds = 0.0
-        try:
-            audio_streams = [s for s in container.streams if s.type == "audio"]
-            stream = audio_streams[0] if audio_streams else container.streams[0]
-
-            # 1) Try stream-level start_time (most reliable for Daily.co tracks)
-            if stream.start_time is not None and stream.time_base is not None:
-                start_time_seconds = float(stream.start_time * stream.time_base)
-
-            # 2) Fallback to container-level start_time (in av.time_base units)
-            if (start_time_seconds <= 0) and (container.start_time is not None):
-                start_time_seconds = float(container.start_time * av.time_base)
-
-            # 3) Fallback to first packet DTS in stream.time_base
-            if start_time_seconds <= 0:
-                for packet in container.demux(stream):
-                    if packet.dts is not None:
-                        start_time_seconds = float(packet.dts * stream.time_base)
-                        break
-        except Exception as e:
-            self.logger.warning(
-                "PyAV metadata read failed; assuming 0 start_time",
-                track_idx=track_idx,
-                error=str(e),
-            )
-            start_time_seconds = 0.0
-
-        self.logger.info(
-            f"Track {track_idx} stream metadata: start_time={start_time_seconds:.3f}s",
-            track_idx=track_idx,
-        )
-        return start_time_seconds
-
-    def _apply_audio_padding_to_file(
-        self,
-        in_container,
-        output_path: str,
-        start_time_seconds: float,
-        track_idx: int,
-    ) -> None:
-        """Apply silence padding to audio track using PyAV filter graph, writing to file"""
-        delay_ms = math.floor(start_time_seconds * 1000)
-
-        self.logger.info(
-            f"Padding track {track_idx} with {delay_ms}ms delay using PyAV",
-            track_idx=track_idx,
-            delay_ms=delay_ms,
-        )
-
-        try:
-            with av.open(output_path, "w", format="webm") as out_container:
-                in_stream = next(
-                    (s for s in in_container.streams if s.type == "audio"), None
-                )
-                if in_stream is None:
-                    raise Exception("No audio stream in input")
-
-                out_stream = out_container.add_stream(
-                    "libopus", rate=OPUS_STANDARD_SAMPLE_RATE
-                )
-                out_stream.bit_rate = OPUS_DEFAULT_BIT_RATE
-                graph = av.filter.Graph()
-
-                abuf_args = (
-                    f"time_base=1/{OPUS_STANDARD_SAMPLE_RATE}:"
-                    f"sample_rate={OPUS_STANDARD_SAMPLE_RATE}:"
-                    f"sample_fmt=s16:"
-                    f"channel_layout=stereo"
-                )
-                src = graph.add("abuffer", args=abuf_args, name="src")
-                aresample_f = graph.add("aresample", args="async=1", name="ares")
-                # adelay requires one delay value per channel separated by '|'
-                delays_arg = f"{delay_ms}|{delay_ms}"
-                adelay_f = graph.add(
-                    "adelay", args=f"delays={delays_arg}:all=1", name="delay"
-                )
-                sink = graph.add("abuffersink", name="sink")
-
-                src.link_to(aresample_f)
-                aresample_f.link_to(adelay_f)
-                adelay_f.link_to(sink)
-                graph.configure()
-
-                resampler = AudioResampler(
-                    format="s16", layout="stereo", rate=OPUS_STANDARD_SAMPLE_RATE
-                )
-                # Decode -> resample -> push through graph -> encode Opus
-                for frame in in_container.decode(in_stream):
-                    out_frames = resampler.resample(frame) or []
-                    for rframe in out_frames:
-                        rframe.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                        rframe.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                        src.push(rframe)
-
-                        while True:
-                            try:
-                                f_out = sink.pull()
-                            except Exception:
-                                break
-                            f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                            f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                            for packet in out_stream.encode(f_out):
-                                out_container.mux(packet)
-
-                src.push(None)
-                while True:
-                    try:
-                        f_out = sink.pull()
-                    except Exception:
-                        break
-                    f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
-                    f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
-                    for packet in out_stream.encode(f_out):
-                        out_container.mux(packet)
-
-                for packet in out_stream.encode(None):
-                    out_container.mux(packet)
-        except Exception as e:
-            self.logger.error(
-                "PyAV padding failed for track",
-                track_idx=track_idx,
-                delay_ms=delay_ms,
-                error=str(e),
-                exc_info=True,
-            )
-            raise
-
-    async def mixdown_tracks(
-        self,
-        track_urls: list[str],
-        writer: AudioFileWriterProcessor,
-        offsets_seconds: list[float] | None = None,
-    ) -> None:
-        """Multi-track mixdown using PyAV filter graph (amix), reading from S3 presigned URLs"""
-
-        target_sample_rate: int | None = None
-        for url in track_urls:
-            if not url:
-                continue
-            container = None
-            try:
-                container = av.open(url)
-                for frame in container.decode(audio=0):
-                    target_sample_rate = frame.sample_rate
-                    break
-            except Exception:
-                continue
-            finally:
-                if container is not None:
-                    container.close()
-            if target_sample_rate:
-                break
-
-        if not target_sample_rate:
-            self.logger.error("Mixdown failed - no decodable audio frames found")
-            raise Exception("Mixdown failed: No decodable audio frames in any track")
-        # Build PyAV filter graph:
-        # N abuffer (s32/stereo)
-        #   -> optional adelay per input (for alignment)
-        #   -> amix (s32)
-        #   -> aformat(s16)
-        #   -> sink
-        graph = av.filter.Graph()
-        inputs = []
-        valid_track_urls = [url for url in track_urls if url]
-        input_offsets_seconds = None
-        if offsets_seconds is not None:
-            input_offsets_seconds = [
-                offsets_seconds[i] for i, url in enumerate(track_urls) if url
-            ]
-        for idx, url in enumerate(valid_track_urls):
-            args = (
-                f"time_base=1/{target_sample_rate}:"
-                f"sample_rate={target_sample_rate}:"
-                f"sample_fmt=s32:"
-                f"channel_layout=stereo"
-            )
-            in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
-            inputs.append(in_ctx)
-
-        if not inputs:
-            self.logger.error("Mixdown failed - no valid inputs for graph")
-            raise Exception("Mixdown failed: No valid inputs for filter graph")
-
-        mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
-
-        fmt = graph.add(
-            "aformat",
-            args=(
-                f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}"
-            ),
-            name="fmt",
-        )
-
-        sink = graph.add("abuffersink", name="out")
-
-        # Optional per-input delay before mixing
-        delays_ms: list[int] = []
-        if input_offsets_seconds is not None:
-            base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
-            delays_ms = [
-                max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds
-            ]
-        else:
-            delays_ms = [0 for _ in inputs]
-
-        for idx, in_ctx in enumerate(inputs):
-            delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
-            if delay_ms > 0:
-                # adelay requires one value per channel; use same for stereo
-                adelay = graph.add(
-                    "adelay",
-                    args=f"delays={delay_ms}|{delay_ms}:all=1",
-                    name=f"delay{idx}",
-                )
-                in_ctx.link_to(adelay)
-                adelay.link_to(mixer, 0, idx)
-            else:
-                in_ctx.link_to(mixer, 0, idx)
-        mixer.link_to(fmt)
-        fmt.link_to(sink)
-        graph.configure()
-
-        containers = []
-        try:
-            # Open all containers with cleanup guaranteed
-            for i, url in enumerate(valid_track_urls):
-                try:
-                    c = av.open(url)
-                    containers.append(c)
-                except Exception as e:
-                    self.logger.warning(
-                        "Mixdown: failed to open container from URL",
-                        input=i,
-                        url=url,
-                        error=str(e),
-                    )
-
-            if not containers:
-                self.logger.error("Mixdown failed - no valid containers opened")
-                raise Exception("Mixdown failed: Could not open any track containers")
-
-            decoders = [c.decode(audio=0) for c in containers]
-            active = [True] * len(decoders)
-            resamplers = [
-                AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
-                for _ in decoders
-            ]
-
-            while any(active):
-                for i, (dec, is_active) in enumerate(zip(decoders, active)):
-                    if not is_active:
-                        continue
-                    try:
-                        frame = next(dec)
-                    except StopIteration:
-                        active[i] = False
-                        continue
-
-                    if frame.sample_rate != target_sample_rate:
-                        continue
-                    out_frames = resamplers[i].resample(frame) or []
-                    for rf in out_frames:
-                        rf.sample_rate = target_sample_rate
-                        rf.time_base = Fraction(1, target_sample_rate)
-                        inputs[i].push(rf)
-
-                    while True:
-                        try:
-                            mixed = sink.pull()
-                        except Exception:
-                            break
-                        mixed.sample_rate = target_sample_rate
-                        mixed.time_base = Fraction(1, target_sample_rate)
-                        await writer.push(mixed)
-
-            for in_ctx in inputs:
-                in_ctx.push(None)
-            while True:
-                try:
-                    mixed = sink.pull()
-                except Exception:
-                    break
-                mixed.sample_rate = target_sample_rate
-                mixed.time_base = Fraction(1, target_sample_rate)
-                await writer.push(mixed)
-        finally:
-            # Cleanup all containers, even if processing failed
-            for c in containers:
-                if c is not None:
-                    try:
-                        c.close()
-                    except Exception:
-                        pass  # Best effort cleanup
-
-    @broadcast_to_sockets
-    async def set_status(self, transcript_id: str, status: TranscriptStatus):
-        async with self.lock_transaction():
-            return await transcripts_controller.set_status(transcript_id, status)
-
-    async def on_waveform(self, data):
-        async with self.transaction():
-            waveform = TranscriptWaveform(waveform=data)
-            transcript = await self.get_transcript()
-            return await transcripts_controller.append_event(
-                transcript=transcript, event="WAVEFORM", data=waveform
-            )
-
-    async def process(self, bucket_name: str, track_keys: list[str]):
-        transcript = await self.get_transcript()
-        async with self.transaction():
-            await transcripts_controller.update(
-                transcript,
-                {
-                    "events": [],
-                    "topics": [],
-                },
-            )
-
-        source_storage = get_transcripts_storage()
-        transcript_storage = source_storage
-
-        track_urls: list[str] = []
-        for key in track_keys:
-            url = await source_storage.get_file_url(
-                key,
-                operation="get_object",
-                expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
-                bucket=bucket_name,
-            )
-            track_urls.append(url)
-            self.logger.info(
-                f"Generated presigned URL for track from {bucket_name}",
-                key=key,
-            )
-
-        created_padded_files = set()
-        padded_track_urls: list[str] = []
-        for idx, url in enumerate(track_urls):
-            padded_url = await self.pad_track_for_transcription(
-                url, idx, transcript_storage
-            )
-            padded_track_urls.append(padded_url)
-            if padded_url != url:
-                storage_path = f"file_pipeline/{transcript.id}/tracks/padded_{idx}.webm"
-                created_padded_files.add(storage_path)
-            self.logger.info(f"Track {idx} processed, padded URL: {padded_url}")
-
-        transcript.data_path.mkdir(parents=True, exist_ok=True)
-
-        mp3_writer = AudioFileWriterProcessor(
-            path=str(transcript.audio_mp3_filename),
-            on_duration=self.on_duration,
-        )
-        await self.mixdown_tracks(padded_track_urls, mp3_writer, offsets_seconds=None)
-        await mp3_writer.flush()
-
-        if not transcript.audio_mp3_filename.exists():
-            raise Exception(
-                "Mixdown failed - no MP3 file generated. Cannot proceed without playable audio."
-            )
-
-        storage_path = f"{transcript.id}/audio.mp3"
-        # Use file handle streaming to avoid loading entire MP3 into memory
-        mp3_size = transcript.audio_mp3_filename.stat().st_size
-        with open(transcript.audio_mp3_filename, "rb") as mp3_file:
-            await transcript_storage.put_file(storage_path, mp3_file)
-        mp3_url = await transcript_storage.get_file_url(storage_path)
-
-        await transcripts_controller.update(transcript, {"audio_location": "storage"})
-
-        self.logger.info(
-            f"Uploaded mixed audio to storage",
-            storage_path=storage_path,
-            size=mp3_size,
-            url=mp3_url,
-        )
-
-        self.logger.info("Generating waveform from mixed audio")
-        waveform_processor = AudioWaveformProcessor(
-            audio_path=transcript.audio_mp3_filename,
-            waveform_path=transcript.audio_waveform_filename,
-            on_waveform=self.on_waveform,
-        )
-        waveform_processor.set_pipeline(self.empty_pipeline)
-        await waveform_processor.flush()
-        self.logger.info("Waveform generated successfully")
-
-        speaker_transcripts: list[TranscriptType] = []
-        for idx, padded_url in enumerate(padded_track_urls):
-            if not padded_url:
-                continue
-
-            t = await self.transcribe_file(padded_url, transcript.source_language)
-
-            if not t.words:
-                self.logger.debug(f"no words in track {idx}")
-                # not skipping, it may be silence or indistinguishable mumbling
-
-            for w in t.words:
-                w.speaker = idx
-
-            speaker_transcripts.append(t)
-            self.logger.info(
-                f"Track {idx} transcribed successfully with {len(t.words)} words",
-                track_idx=idx,
-            )
-
-        valid_track_count = len([url for url in padded_track_urls if url])
-        if valid_track_count > 0 and len(speaker_transcripts) != valid_track_count:
-            raise Exception(
-                f"Only {len(speaker_transcripts)}/{valid_track_count} tracks transcribed successfully. "
-                f"All tracks must succeed to avoid incomplete transcripts."
-            )
-
-        if not speaker_transcripts:
-            raise Exception("No valid track transcriptions")
-
-        self.logger.info(f"Cleaning up {len(created_padded_files)} temporary S3 files")
-        cleanup_tasks = []
-        for storage_path in created_padded_files:
-            cleanup_tasks.append(transcript_storage.delete_file(storage_path))
-
-        if cleanup_tasks:
-            cleanup_results = await asyncio.gather(
-                *cleanup_tasks, return_exceptions=True
-            )
-            for storage_path, result in zip(created_padded_files, cleanup_results):
-                if isinstance(result, Exception):
-                    self.logger.warning(
-                        "Failed to cleanup temporary padded track",
-                        storage_path=storage_path,
-                        error=str(result),
-                    )
-
-        merged_words = []
-        for t in speaker_transcripts:
-            merged_words.extend(t.words)
-        merged_words.sort(
-            key=lambda w: w.start if hasattr(w, "start") and w.start is not None else 0
-        )
-
-        merged_transcript = TranscriptType(words=merged_words, translation=None)
-
-        await self.on_transcript(merged_transcript)
-
-        topics = await self.detect_topics(merged_transcript, transcript.target_language)
-        await asyncio.gather(
-            self.generate_title(topics),
-            self.generate_summaries(topics),
-            return_exceptions=False,
-        )
-
-        await self.set_status(transcript.id, "ended")
-
-    async def transcribe_file(self, audio_url: str, language: str) -> TranscriptType:
-        return await transcribe_file_with_processor(audio_url, language)
-
-    async def detect_topics(
-        self, transcript: TranscriptType, target_language: str
-    ) -> list[TitleSummary]:
-        return await topic_processing.detect_topics(
-            transcript,
-            target_language,
-            on_topic_callback=self.on_topic,
-            empty_pipeline=self.empty_pipeline,
-        )
-
-    async def generate_title(self, topics: list[TitleSummary]):
-        return await topic_processing.generate_title(
-            topics,
-            on_title_callback=self.on_title,
-            empty_pipeline=self.empty_pipeline,
-            logger=self.logger,
-        )
-
-    async def generate_summaries(self, topics: list[TitleSummary]):
-        transcript = await self.get_transcript()
-        return await topic_processing.generate_summaries(
-            topics,
-            transcript,
-            on_long_summary_callback=self.on_long_summary,
-            on_short_summary_callback=self.on_short_summary,
-            empty_pipeline=self.empty_pipeline,
-            logger=self.logger,
-        )
-
-
-@shared_task
-@asynctask
-async def task_pipeline_multitrack_process(
-    *, transcript_id: str, bucket_name: str, track_keys: list[str]
-):
-    pipeline = PipelineMainMultitrack(transcript_id=transcript_id)
-    try:
-        await pipeline.set_status(transcript_id, "processing")
-        await pipeline.process(bucket_name, track_keys)
-    except Exception:
-        await pipeline.set_status(transcript_id, "error")
-        raise
-
-    post_chain = chain(
-        task_cleanup_consent.si(transcript_id=transcript_id),
-        task_pipeline_post_to_zulip.si(transcript_id=transcript_id),
-        task_send_webhook_if_needed.si(transcript_id=transcript_id),
-    )
-    post_chain.delay()

server/reflector/pipelines/topic_processing.py

@@ -1,109 +0,0 @@
-"""
-Topic processing utilities
-==========================
-
-Shared topic detection, title generation, and summarization logic
-used across file and multitrack pipelines.
-"""
-
-from typing import Callable
-
-import structlog
-
-from reflector.db.transcripts import Transcript
-from reflector.processors import (
-    TranscriptFinalSummaryProcessor,
-    TranscriptFinalTitleProcessor,
-    TranscriptTopicDetectorProcessor,
-)
-from reflector.processors.types import TitleSummary
-from reflector.processors.types import Transcript as TranscriptType
-
-
-class EmptyPipeline:
-    def __init__(self, logger: structlog.BoundLogger):
-        self.logger = logger
-
-    def get_pref(self, k, d=None):
-        return d
-
-    async def emit(self, event):
-        pass
-
-
-async def detect_topics(
-    transcript: TranscriptType,
-    target_language: str,
-    *,
-    on_topic_callback: Callable,
-    empty_pipeline: EmptyPipeline,
-) -> list[TitleSummary]:
-    chunk_size = 300
-    topics: list[TitleSummary] = []
-
-    async def on_topic(topic: TitleSummary):
-        topics.append(topic)
-        return await on_topic_callback(topic)
-
-    topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
-    topic_detector.set_pipeline(empty_pipeline)
-
-    for i in range(0, len(transcript.words), chunk_size):
-        chunk_words = transcript.words[i : i + chunk_size]
-        if not chunk_words:
-            continue
-
-        chunk_transcript = TranscriptType(
-            words=chunk_words, translation=transcript.translation
-        )
-
-        await topic_detector.push(chunk_transcript)
-
-    await topic_detector.flush()
-    return topics
-
-
-async def generate_title(
-    topics: list[TitleSummary],
-    *,
-    on_title_callback: Callable,
-    empty_pipeline: EmptyPipeline,
-    logger: structlog.BoundLogger,
-):
-    if not topics:
-        logger.warning("No topics for title generation")
-        return
-
-    processor = TranscriptFinalTitleProcessor(callback=on_title_callback)
-    processor.set_pipeline(empty_pipeline)
-
-    for topic in topics:
-        await processor.push(topic)
-
-    await processor.flush()
-
-
-async def generate_summaries(
-    topics: list[TitleSummary],
-    transcript: Transcript,
-    *,
-    on_long_summary_callback: Callable,
-    on_short_summary_callback: Callable,
-    empty_pipeline: EmptyPipeline,
-    logger: structlog.BoundLogger,
-):
-    if not topics:
-        logger.warning("No topics for summary generation")
-        return
-
-    processor = TranscriptFinalSummaryProcessor(
-        transcript=transcript,
-        callback=on_long_summary_callback,
-        on_short_summary=on_short_summary_callback,
-    )
-    processor.set_pipeline(empty_pipeline)
-
-    for topic in topics:
-        await processor.push(topic)
-
-    await processor.flush()

server/reflector/pipelines/transcription_helpers.py

@@ -1,34 +0,0 @@
-from reflector.processors.file_transcript import FileTranscriptInput
-from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
-from reflector.processors.types import Transcript as TranscriptType
-
-
-async def transcribe_file_with_processor(
-    audio_url: str,
-    language: str,
-    processor_name: str | None = None,
-) -> TranscriptType:
-    processor = (
-        FileTranscriptAutoProcessor(name=processor_name)
-        if processor_name
-        else FileTranscriptAutoProcessor()
-    )
-    input_data = FileTranscriptInput(audio_url=audio_url, language=language)
-
-    result: TranscriptType | None = None
-
-    async def capture_result(transcript):
-        nonlocal result
-        result = transcript
-
-    processor.on(capture_result)
-    await processor.push(input_data)
-    await processor.flush()
-
-    if not result:
-        processor_label = processor_name or "default"
-        raise ValueError(
-            f"No transcript captured from {processor_label} processor for audio: {audio_url}"
-        )
-
-    return result

server/reflector/processors/audio_chunker_silero.py

@@ -11,7 +11,10 @@ from reflector.processors.audio_chunker_auto import AudioChunkerAutoProcessor
 
 class AudioChunkerSileroProcessor(AudioChunkerProcessor):
     """
-    Assemble audio frames into chunks with VAD-based speech detection using Silero VAD
+    Assemble audio frames into chunks with VAD-based speech detection using Silero VAD.
+
+    Expects input audio to be already downscaled to 16kHz mono s16 format
+    (handled by AudioDownscaleProcessor in the pipeline).
     """
 
     def __init__(
@@ -31,12 +34,13 @@ class AudioChunkerSileroProcessor(AudioChunkerProcessor):
         self._init_vad(use_onnx)
 
     def _init_vad(self, use_onnx=False):
-        """Initialize Silero VAD model"""
+        """Initialize Silero VAD model for 16kHz audio"""
         try:
             torch.set_num_threads(1)
             self.vad_model = load_silero_vad(onnx=use_onnx)
+            # VAD expects 16kHz audio (guaranteed by AudioDownscaleProcessor)
             self.vad_iterator = VADIterator(self.vad_model, sampling_rate=16000)
-            self.logger.info("Silero VAD initialized successfully")
+            self.logger.info("Silero VAD initialized for 16kHz audio")
 
         except Exception as e:
             self.logger.error(f"Failed to initialize Silero VAD: {e}")
@@ -75,7 +79,7 @@ class AudioChunkerSileroProcessor(AudioChunkerProcessor):
             return None
 
         # Processing block with current buffer size
-        print(f"Processing block: {len(self.frames)} frames in buffer")
+        # print(f"Processing block: {len(self.frames)} frames in buffer")
 
         try:
             # Convert frames to numpy array for VAD
@@ -189,38 +193,29 @@ class AudioChunkerSileroProcessor(AudioChunkerProcessor):
         return None
 
     def _frames_to_numpy(self, frames: list[av.AudioFrame]) -> Optional[np.ndarray]:
-        """Convert av.AudioFrame list to numpy array for VAD processing"""
+        """Convert av.AudioFrame list to numpy array for VAD processing
+
+        Input frames are already 16kHz mono s16 format from AudioDownscaleProcessor.
+        Only need to convert s16 to float32 for Silero VAD.
+        """
         if not frames:
             return None
 
         try:
-            audio_data = []
+            # Concatenate all frame arrays
-            for frame in frames:
+            audio_arrays = [frame.to_ndarray().flatten() for frame in frames]
-                frame_array = frame.to_ndarray()
+            if not audio_arrays:
-
-                if len(frame_array.shape) == 2:
-                    frame_array = frame_array.flatten()
-
-                audio_data.append(frame_array)
-
-            if not audio_data:
                 return None
 
-            combined_audio = np.concatenate(audio_data)
+            combined_audio = np.concatenate(audio_arrays)
 
-            # Ensure float32 format
+            # Convert s16 to float32 (Silero VAD requires float32 in range [-1.0, 1.0])
-            if combined_audio.dtype == np.int16:
+            # Input is guaranteed to be s16 from AudioDownscaleProcessor
-                # Normalize int16 audio to float32 in range [-1.0, 1.0]
+            return combined_audio.astype(np.float32) / 32768.0
-                combined_audio = combined_audio.astype(np.float32) / 32768.0
-            elif combined_audio.dtype != np.float32:
-                combined_audio = combined_audio.astype(np.float32)
-
-            return combined_audio
 
         except Exception as e:
             self.logger.error(f"Error converting frames to numpy: {e}")
-
+            return None
-        return None
 
     def _find_speech_segment_end(self, audio_array: np.ndarray) -> Optional[int]:
         """Find complete speech segments and return frame index at segment end"""

server/reflector/processors/file_diarization_modal.py

@@ -47,7 +47,6 @@ class FileDiarizationModalProcessor(FileDiarizationProcessor):
                     "audio_file_url": data.audio_url,
                     "timestamp": 0,
                 },
-                follow_redirects=True,
             )
             response.raise_for_status()
             diarization_data = response.json()["diarization"]

server/reflector/processors/file_transcript_modal.py

@@ -54,18 +54,7 @@ class FileTranscriptModalProcessor(FileTranscriptProcessor):
                     "language": data.language,
                     "batch": True,
                 },
-                follow_redirects=True,
             )
-
-            if response.status_code != 200:
-                error_body = response.text
-                self.logger.error(
-                    "Modal API error",
-                    audio_url=data.audio_url,
-                    status_code=response.status_code,
-                    error_body=error_body,
-                )
-
             response.raise_for_status()
             result = response.json()
 
@@ -78,9 +67,6 @@ class FileTranscriptModalProcessor(FileTranscriptProcessor):
             for word_info in result.get("words", [])
         ]
 
-        # words come not in order
-        words.sort(key=lambda w: w.start)
-
         return Transcript(words=words)
 
 

server/reflector/processors/summary/summary_builder.py

@@ -165,7 +165,6 @@ class SummaryBuilder:
         self.llm: LLM = llm
         self.model_name: str = llm.model_name
         self.logger = logger or structlog.get_logger()
-        self.participant_instructions: str | None = None
         if filename:
             self.read_transcript_from_file(filename)
 
@@ -192,61 +191,14 @@ class SummaryBuilder:
         self, prompt: str, output_cls: Type[T], tone_name: str | None = None
     ) -> T:
         """Generic function to get structured output from LLM for non-function-calling models."""
-        # Add participant instructions to the prompt if available
-        enhanced_prompt = self._enhance_prompt_with_participants(prompt)
         return await self.llm.get_structured_response(
-            enhanced_prompt, [self.transcript], output_cls, tone_name=tone_name
+            prompt, [self.transcript], output_cls, tone_name=tone_name
         )
 
-    async def _get_response(
-        self, prompt: str, texts: list[str], tone_name: str | None = None
-    ) -> str:
-        """Get text response with automatic participant instructions injection."""
-        enhanced_prompt = self._enhance_prompt_with_participants(prompt)
-        return await self.llm.get_response(enhanced_prompt, texts, tone_name=tone_name)
-
-    def _enhance_prompt_with_participants(self, prompt: str) -> str:
-        """Add participant instructions to any prompt if participants are known."""
-        if self.participant_instructions:
-            self.logger.debug("Adding participant instructions to prompt")
-            return f"{prompt}\n\n{self.participant_instructions}"
-        return prompt
-
     # ----------------------------------------------------------------------------
     # Participants
     # ----------------------------------------------------------------------------
 
-    def set_known_participants(self, participants: list[str]) -> None:
-        """
-        Set known participants directly without LLM identification.
-        This is used when participants are already identified and stored.
-        They are appended at the end of the transcript, providing more context for the assistant.
-        """
-        if not participants:
-            self.logger.warning("No participants provided")
-            return
-
-        self.logger.info(
-            "Using known participants",
-            participants=participants,
-        )
-
-        participants_md = self.format_list_md(participants)
-        self.transcript += f"\n\n# Participants\n\n{participants_md}"
-
-        # Set instructions that will be automatically added to all prompts
-        participants_list = ", ".join(participants)
-        self.participant_instructions = dedent(
-            f"""
-            # IMPORTANT: Participant Names
-            The following participants are identified in this conversation: {participants_list}
-
-            You MUST use these specific participant names when referring to people in your response.
-            Do NOT use generic terms like "a participant", "someone", "attendee", "Speaker 1", "Speaker 2", etc.
-            Always refer to people by their actual names (e.g., "John suggested..." not "A participant suggested...").
-            """
-        ).strip()
-
     async def identify_participants(self) -> None:
         """
         From a transcript, try to identify the participants using TreeSummarize with structured output.
@@ -280,19 +232,6 @@ class SummaryBuilder:
             if unique_participants:
                 participants_md = self.format_list_md(unique_participants)
                 self.transcript += f"\n\n# Participants\n\n{participants_md}"
-
-                # Set instructions that will be automatically added to all prompts
-                participants_list = ", ".join(unique_participants)
-                self.participant_instructions = dedent(
-                    f"""
-                    # IMPORTANT: Participant Names
-                    The following participants are identified in this conversation: {participants_list}
-
-                    You MUST use these specific participant names when referring to people in your response.
-                    Do NOT use generic terms like "a participant", "someone", "attendee", "Speaker 1", "Speaker 2", etc.
-                    Always refer to people by their actual names (e.g., "John suggested..." not "A participant suggested...").
-                    """
-                ).strip()
             else:
                 self.logger.warning("No participants identified in the transcript")
 
@@ -379,13 +318,13 @@ class SummaryBuilder:
         for subject in self.subjects:
             detailed_prompt = DETAILED_SUBJECT_PROMPT_TEMPLATE.format(subject=subject)
 
-            detailed_response = await self._get_response(
+            detailed_response = await self.llm.get_response(
                 detailed_prompt, [self.transcript], tone_name="Topic assistant"
             )
 
             paragraph_prompt = PARAGRAPH_SUMMARY_PROMPT
 
-            paragraph_response = await self._get_response(
+            paragraph_response = await self.llm.get_response(
                 paragraph_prompt, [str(detailed_response)], tone_name="Topic summarizer"
             )
 
@@ -406,7 +345,7 @@ class SummaryBuilder:
 
         recap_prompt = RECAP_PROMPT
 
-        recap_response = await self._get_response(
+        recap_response = await self.llm.get_response(
             recap_prompt, [summaries_text], tone_name="Recap summarizer"
         )
 

server/reflector/processors/transcript_final_summary.py

@@ -26,25 +26,7 @@ class TranscriptFinalSummaryProcessor(Processor):
     async def get_summary_builder(self, text) -> SummaryBuilder:
         builder = SummaryBuilder(self.llm, logger=self.logger)
         builder.set_transcript(text)
-
+        await builder.identify_participants()
-        # Use known participants if available, otherwise identify them
-        if self.transcript and self.transcript.participants:
-            # Extract participant names from the stored participants
-            participant_names = [p.name for p in self.transcript.participants if p.name]
-            if participant_names:
-                self.logger.info(
-                    f"Using {len(participant_names)} known participants from transcript"
-                )
-                builder.set_known_participants(participant_names)
-            else:
-                self.logger.info(
-                    "Participants field exists but is empty, identifying participants"
-                )
-                await builder.identify_participants()
-        else:
-            self.logger.info("No participants stored, identifying participants")
-            await builder.identify_participants()
-
         await builder.generate_summary()
         return builder
 
@@ -67,30 +49,18 @@ class TranscriptFinalSummaryProcessor(Processor):
         speakermap = {}
         if self.transcript:
             speakermap = {
-                p.speaker: p.name
+                participant["speaker"]: participant["name"]
-                for p in (self.transcript.participants or [])
+                for participant in self.transcript.participants
-                if p.speaker is not None and p.name
             }
-            self.logger.info(
-                f"Built speaker map with {len(speakermap)} participants",
-                speakermap=speakermap,
-            )
 
         # build the transcript as a single string
-        # Replace speaker IDs with actual participant names if available
+        # XXX: unsure if the participants name as replaced directly in speaker ?
         text_transcript = []
-        unique_speakers = set()
         for topic in self.chunks:
             for segment in topic.transcript.as_segments():
                 name = speakermap.get(segment.speaker, f"Speaker {segment.speaker}")
-                unique_speakers.add((segment.speaker, name))
                 text_transcript.append(f"{name}: {segment.text}")
 
-        self.logger.info(
-            f"Built transcript with {len(unique_speakers)} unique speakers",
-            speakers=list(unique_speakers),
-        )
-
         text_transcript = "\n".join(text_transcript)
 
         last_chunk = self.chunks[-1]

server/reflector/processors/transcript_topic_detector.py

@@ -1,6 +1,6 @@
 from textwrap import dedent
 
-from pydantic import AliasChoices, BaseModel, Field
+from pydantic import BaseModel, Field
 
 from reflector.llm import LLM
 from reflector.processors.base import Processor
@@ -34,14 +34,8 @@ TOPIC_PROMPT = dedent(
 class TopicResponse(BaseModel):
     """Structured response for topic detection"""
 
-    title: str = Field(
+    title: str = Field(description="A descriptive title for the topic being discussed")
-        description="A descriptive title for the topic being discussed",
+    summary: str = Field(description="A concise 1-2 sentence summary of the discussion")
-        validation_alias=AliasChoices("title", "Title"),
-    )
-    summary: str = Field(
-        description="A concise 1-2 sentence summary of the discussion",
-        validation_alias=AliasChoices("summary", "Summary"),
-    )
 
 
 class TranscriptTopicDetectorProcessor(Processor):

server/reflector/processors/types.py

@@ -4,8 +4,11 @@ import tempfile
 from pathlib import Path
 from typing import Annotated, TypedDict
 
+from profanityfilter import ProfanityFilter
 from pydantic import BaseModel, Field, PrivateAttr
 
+from reflector.redis_cache import redis_cache
+
 
 class DiarizationSegment(TypedDict):
     """Type definition for diarization segment containing speaker information"""
@@ -17,6 +20,9 @@ class DiarizationSegment(TypedDict):
 
 PUNC_RE = re.compile(r"[.;:?!…]")
 
+profanity_filter = ProfanityFilter()
+profanity_filter.set_censor("*")
+
 
 class AudioFile(BaseModel):
     name: str
@@ -118,11 +124,21 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
 
 class Transcript(BaseModel):
     translation: str | None = None
-    words: list[Word] = []
+    words: list[Word] = None
+
+    @property
+    def raw_text(self):
+        # Uncensored text
+        return "".join([word.text for word in self.words])
+
+    @redis_cache(prefix="profanity", duration=3600 * 24 * 7)
+    def _get_censored_text(self, text: str):
+        return profanity_filter.censor(text).strip()
 
     @property
     def text(self):
-        return "".join([word.text for word in self.words])
+        # Censored text
+        return self._get_censored_text(self.raw_text)
 
     @property
     def human_timestamp(self):
@@ -154,6 +170,12 @@ class Transcript(BaseModel):
             word.start += offset
             word.end += offset
 
+    def clone(self):
+        words = [
+            Word(text=word.text, start=word.start, end=word.end) for word in self.words
+        ]
+        return Transcript(text=self.text, translation=self.translation, words=words)
+
     def as_segments(self) -> list[TranscriptSegment]:
         return words_to_segments(self.words)
 

server/reflector/redis_cache.py

@@ -1,17 +1,10 @@
-import asyncio
 import functools
 import json
-from typing import Optional
 
 import redis
-import redis.asyncio as redis_async
-import structlog
-from redis.exceptions import LockError
 
 from reflector.settings import settings
 
-logger = structlog.get_logger(__name__)
-
 redis_clients = {}
 
 
@@ -28,12 +21,6 @@ def get_redis_client(db=0):
     return redis_clients[db]
 
 
-async def get_async_redis_client(db: int = 0):
-    return await redis_async.from_url(
-        f"redis://{settings.REDIS_HOST}:{settings.REDIS_PORT}/{db}"
-    )
-
-
 def redis_cache(prefix="cache", duration=3600, db=settings.REDIS_CACHE_DB, argidx=1):
     """
     Cache the result of a function in Redis.
@@ -62,87 +49,3 @@ def redis_cache(prefix="cache", duration=3600, db=settings.REDIS_CACHE_DB, argid
         return wrapper
 
     return decorator
-
-
-class RedisAsyncLock:
-    def __init__(
-        self,
-        key: str,
-        timeout: int = 120,
-        extend_interval: int = 30,
-        skip_if_locked: bool = False,
-        blocking: bool = True,
-        blocking_timeout: Optional[float] = None,
-    ):
-        self.key = f"async_lock:{key}"
-        self.timeout = timeout
-        self.extend_interval = extend_interval
-        self.skip_if_locked = skip_if_locked
-        self.blocking = blocking
-        self.blocking_timeout = blocking_timeout
-        self._lock = None
-        self._redis = None
-        self._extend_task = None
-        self._acquired = False
-
-    async def _extend_lock_periodically(self):
-        while True:
-            try:
-                await asyncio.sleep(self.extend_interval)
-                if self._lock:
-                    await self._lock.extend(self.timeout, replace_ttl=True)
-                    logger.debug("Extended lock", key=self.key)
-            except LockError:
-                logger.warning("Failed to extend lock", key=self.key)
-                break
-            except asyncio.CancelledError:
-                break
-            except Exception as e:
-                logger.error("Error extending lock", key=self.key, error=str(e))
-                break
-
-    async def __aenter__(self):
-        self._redis = await get_async_redis_client()
-        self._lock = self._redis.lock(
-            self.key,
-            timeout=self.timeout,
-            blocking=self.blocking,
-            blocking_timeout=self.blocking_timeout,
-        )
-
-        self._acquired = await self._lock.acquire()
-
-        if not self._acquired:
-            if self.skip_if_locked:
-                logger.warning(
-                    "Lock already acquired by another process, skipping", key=self.key
-                )
-                return self
-            else:
-                raise LockError(f"Failed to acquire lock: {self.key}")
-
-        self._extend_task = asyncio.create_task(self._extend_lock_periodically())
-        logger.info("Acquired lock", key=self.key)
-        return self
-
-    async def __aexit__(self, exc_type, exc_val, exc_tb):
-        if self._extend_task:
-            self._extend_task.cancel()
-            try:
-                await self._extend_task
-            except asyncio.CancelledError:
-                pass
-
-        if self._acquired and self._lock:
-            try:
-                await self._lock.release()
-                logger.info("Released lock", key=self.key)
-            except LockError:
-                logger.debug("Lock already released or expired", key=self.key)
-
-        if self._redis:
-            await self._redis.aclose()
-
-    @property
-    def acquired(self) -> bool:
-        return self._acquired

server/reflector/schemas/platform.py

@@ -1,5 +0,0 @@
-from typing import Literal
-
-Platform = Literal["whereby", "daily"]
-WHEREBY_PLATFORM: Platform = "whereby"
-DAILY_PLATFORM: Platform = "daily"

server/reflector/services/ics_sync.py

@@ -1,408 +0,0 @@
-"""
-ICS Calendar Synchronization Service
-
-This module provides services for fetching, parsing, and synchronizing ICS (iCalendar)
-calendar feeds with room booking data in the database.
-
-Key Components:
-- ICSFetchService: Handles HTTP fetching and parsing of ICS calendar data
-- ICSSyncService: Manages the synchronization process between ICS feeds and database
-
-Example Usage:
-    # Sync a room's calendar
-    room = Room(id="room1", name="conference-room", ics_url="https://cal.example.com/room.ics")
-    result = await ics_sync_service.sync_room_calendar(room)
-
-    # Result structure:
-    {
-        "status": "success",  # success|unchanged|error|skipped
-        "hash": "abc123...",  # MD5 hash of ICS content
-        "events_found": 5,    # Events matching this room
-        "total_events": 12,   # Total events in calendar within time window
-        "events_created": 2,  # New events added to database
-        "events_updated": 3,  # Existing events modified
-        "events_deleted": 1   # Events soft-deleted (no longer in calendar)
-    }
-
-Event Matching:
-    Events are matched to rooms by checking if the room's full URL appears in the
-    event's LOCATION or DESCRIPTION fields. Only events within a 25-hour window
-    (1 hour ago to 24 hours from now) are processed.
-
-Input: ICS calendar URL (e.g., "https://calendar.google.com/calendar/ical/...")
-Output: EventData objects with structured calendar information:
-    {
-        "ics_uid": "event123@google.com",
-        "title": "Team Meeting",
-        "description": "Weekly sync meeting",
-        "location": "https://meet.company.com/conference-room",
-        "start_time": datetime(2024, 1, 15, 14, 0, tzinfo=UTC),
-        "end_time": datetime(2024, 1, 15, 15, 0, tzinfo=UTC),
-        "attendees": [
-            {"email": "user@company.com", "name": "John Doe", "role": "ORGANIZER"},
-            {"email": "attendee@company.com", "name": "Jane Smith", "status": "ACCEPTED"}
-        ],
-        "ics_raw_data": "BEGIN:VEVENT\nUID:event123@google.com\n..."
-    }
-"""
-
-import hashlib
-from datetime import date, datetime, timedelta, timezone
-from enum import Enum
-from typing import TypedDict
-
-import httpx
-import pytz
-import structlog
-from icalendar import Calendar, Event
-
-from reflector.db.calendar_events import CalendarEvent, calendar_events_controller
-from reflector.db.rooms import Room, rooms_controller
-from reflector.redis_cache import RedisAsyncLock
-from reflector.settings import settings
-
-logger = structlog.get_logger()
-
-EVENT_WINDOW_DELTA_START = timedelta(hours=-1)
-EVENT_WINDOW_DELTA_END = timedelta(hours=24)
-
-
-class SyncStatus(str, Enum):
-    SUCCESS = "success"
-    UNCHANGED = "unchanged"
-    ERROR = "error"
-    SKIPPED = "skipped"
-
-
-class AttendeeData(TypedDict, total=False):
-    email: str | None
-    name: str | None
-    status: str | None
-    role: str | None
-
-
-class EventData(TypedDict):
-    ics_uid: str
-    title: str | None
-    description: str | None
-    location: str | None
-    start_time: datetime
-    end_time: datetime
-    attendees: list[AttendeeData]
-    ics_raw_data: str
-
-
-class SyncStats(TypedDict):
-    events_created: int
-    events_updated: int
-    events_deleted: int
-
-
-class SyncResultBase(TypedDict):
-    status: SyncStatus
-
-
-class SyncResult(SyncResultBase, total=False):
-    hash: str | None
-    events_found: int
-    total_events: int
-    events_created: int
-    events_updated: int
-    events_deleted: int
-    error: str | None
-    reason: str | None
-
-
-class ICSFetchService:
-    def __init__(self):
-        self.client = httpx.AsyncClient(
-            timeout=30.0, headers={"User-Agent": "Reflector/1.0"}
-        )
-
-    async def fetch_ics(self, url: str) -> str:
-        response = await self.client.get(url)
-        response.raise_for_status()
-
-        return response.text
-
-    def parse_ics(self, ics_content: str) -> Calendar:
-        return Calendar.from_ical(ics_content)
-
-    def extract_room_events(
-        self, calendar: Calendar, room_name: str, room_url: str
-    ) -> tuple[list[EventData], int]:
-        events = []
-        total_events = 0
-        now = datetime.now(timezone.utc)
-        window_start = now + EVENT_WINDOW_DELTA_START
-        window_end = now + EVENT_WINDOW_DELTA_END
-
-        for component in calendar.walk():
-            if component.name != "VEVENT":
-                continue
-
-            status = component.get("STATUS", "").upper()
-            if status == "CANCELLED":
-                continue
-
-            # Count total non-cancelled events in the time window
-            event_data = self._parse_event(component)
-            if event_data and window_start <= event_data["start_time"] <= window_end:
-                total_events += 1
-
-                # Check if event matches this room
-                if self._event_matches_room(component, room_name, room_url):
-                    events.append(event_data)
-
-        return events, total_events
-
-    def _event_matches_room(self, event: Event, room_name: str, room_url: str) -> bool:
-        location = str(event.get("LOCATION", ""))
-        description = str(event.get("DESCRIPTION", ""))
-
-        # Only match full room URL
-        # XXX leaved here as a patterns, to later be extended with tinyurl or such too
-        patterns = [
-            room_url,
-        ]
-
-        # Check location and description for patterns
-        text_to_check = f"{location} {description}".lower()
-        for pattern in patterns:
-            if pattern.lower() in text_to_check:
-                return True
-
-        return False
-
-    def _parse_event(self, event: Event) -> EventData | None:
-        uid = str(event.get("UID", ""))
-        summary = str(event.get("SUMMARY", ""))
-        description = str(event.get("DESCRIPTION", ""))
-        location = str(event.get("LOCATION", ""))
-        dtstart = event.get("DTSTART")
-        dtend = event.get("DTEND")
-
-        if not dtstart:
-            return None
-
-        # Convert fields
-        start_time = self._normalize_datetime(
-            dtstart.dt if hasattr(dtstart, "dt") else dtstart
-        )
-        end_time = (
-            self._normalize_datetime(dtend.dt if hasattr(dtend, "dt") else dtend)
-            if dtend
-            else start_time + timedelta(hours=1)
-        )
-        attendees = self._parse_attendees(event)
-
-        # Get raw event data for storage
-        raw_data = event.to_ical().decode("utf-8")
-
-        return {
-            "ics_uid": uid,
-            "title": summary,
-            "description": description,
-            "location": location,
-            "start_time": start_time,
-            "end_time": end_time,
-            "attendees": attendees,
-            "ics_raw_data": raw_data,
-        }
-
-    def _normalize_datetime(self, dt) -> datetime:
-        # Ensure datetime is with timezone, if not, assume UTC
-        if isinstance(dt, date) and not isinstance(dt, datetime):
-            dt = datetime.combine(dt, datetime.min.time())
-            dt = pytz.UTC.localize(dt)
-        elif isinstance(dt, datetime):
-            if dt.tzinfo is None:
-                dt = pytz.UTC.localize(dt)
-            else:
-                dt = dt.astimezone(pytz.UTC)
-
-        return dt
-
-    def _parse_attendees(self, event: Event) -> list[AttendeeData]:
-        # Extracts attendee information from both ATTENDEE and ORGANIZER properties.
-        # Handles malformed comma-separated email addresses in single ATTENDEE fields
-        # by splitting them into separate attendee entries. Returns a list of attendee
-        # data including email, name, status, and role information.
-        final_attendees = []
-
-        attendees = event.get("ATTENDEE", [])
-        if not isinstance(attendees, list):
-            attendees = [attendees]
-        for att in attendees:
-            email_str = str(att).replace("mailto:", "") if att else None
-
-            # Handle malformed comma-separated email addresses in a single ATTENDEE field
-            if email_str and "," in email_str:
-                # Split comma-separated emails and create separate attendee entries
-                email_parts = [email.strip() for email in email_str.split(",")]
-                for email in email_parts:
-                    if email and "@" in email:
-                        clean_email = email.replace("MAILTO:", "").replace(
-                            "mailto:", ""
-                        )
-                        att_data: AttendeeData = {
-                            "email": clean_email,
-                            "name": att.params.get("CN")
-                            if hasattr(att, "params") and email == email_parts[0]
-                            else None,
-                            "status": att.params.get("PARTSTAT")
-                            if hasattr(att, "params") and email == email_parts[0]
-                            else None,
-                            "role": att.params.get("ROLE")
-                            if hasattr(att, "params") and email == email_parts[0]
-                            else None,
-                        }
-                        final_attendees.append(att_data)
-            else:
-                # Normal single attendee
-                att_data: AttendeeData = {
-                    "email": email_str,
-                    "name": att.params.get("CN") if hasattr(att, "params") else None,
-                    "status": att.params.get("PARTSTAT")
-                    if hasattr(att, "params")
-                    else None,
-                    "role": att.params.get("ROLE") if hasattr(att, "params") else None,
-                }
-                final_attendees.append(att_data)
-
-        # Add organizer
-        organizer = event.get("ORGANIZER")
-        if organizer:
-            org_email = (
-                str(organizer).replace("mailto:", "").replace("MAILTO:", "")
-                if organizer
-                else None
-            )
-            org_data: AttendeeData = {
-                "email": org_email,
-                "name": organizer.params.get("CN")
-                if hasattr(organizer, "params")
-                else None,
-                "role": "ORGANIZER",
-            }
-            final_attendees.append(org_data)
-
-        return final_attendees
-
-
-class ICSSyncService:
-    def __init__(self):
-        self.fetch_service = ICSFetchService()
-
-    async def sync_room_calendar(self, room: Room) -> SyncResult:
-        async with RedisAsyncLock(
-            f"ics_sync_room:{room.id}", skip_if_locked=True
-        ) as lock:
-            if not lock.acquired:
-                logger.warning("ICS sync already in progress for room", room_id=room.id)
-                return {
-                    "status": SyncStatus.SKIPPED,
-                    "reason": "Sync already in progress",
-                }
-
-            return await self._sync_room_calendar(room)
-
-    async def _sync_room_calendar(self, room: Room) -> SyncResult:
-        if not room.ics_enabled or not room.ics_url:
-            return {"status": SyncStatus.SKIPPED, "reason": "ICS not configured"}
-
-        try:
-            if not self._should_sync(room):
-                return {"status": SyncStatus.SKIPPED, "reason": "Not time to sync yet"}
-
-            ics_content = await self.fetch_service.fetch_ics(room.ics_url)
-            calendar = self.fetch_service.parse_ics(ics_content)
-
-            content_hash = hashlib.md5(ics_content.encode()).hexdigest()
-            if room.ics_last_etag == content_hash:
-                logger.info("No changes in ICS for room", room_id=room.id)
-                room_url = f"{settings.UI_BASE_URL}/{room.name}"
-                events, total_events = self.fetch_service.extract_room_events(
-                    calendar, room.name, room_url
-                )
-                return {
-                    "status": SyncStatus.UNCHANGED,
-                    "hash": content_hash,
-                    "events_found": len(events),
-                    "total_events": total_events,
-                    "events_created": 0,
-                    "events_updated": 0,
-                    "events_deleted": 0,
-                }
-
-            # Extract matching events
-            room_url = f"{settings.UI_BASE_URL}/{room.name}"
-            events, total_events = self.fetch_service.extract_room_events(
-                calendar, room.name, room_url
-            )
-            sync_result = await self._sync_events_to_database(room.id, events)
-
-            # Update room sync metadata
-            await rooms_controller.update(
-                room,
-                {
-                    "ics_last_sync": datetime.now(timezone.utc),
-                    "ics_last_etag": content_hash,
-                },
-                mutate=False,
-            )
-
-            return {
-                "status": SyncStatus.SUCCESS,
-                "hash": content_hash,
-                "events_found": len(events),
-                "total_events": total_events,
-                **sync_result,
-            }
-
-        except Exception as e:
-            logger.error("Failed to sync ICS for room", room_id=room.id, error=str(e))
-            return {"status": SyncStatus.ERROR, "error": str(e)}
-
-    def _should_sync(self, room: Room) -> bool:
-        if not room.ics_last_sync:
-            return True
-
-        time_since_sync = datetime.now(timezone.utc) - room.ics_last_sync
-        return time_since_sync.total_seconds() >= room.ics_fetch_interval
-
-    async def _sync_events_to_database(
-        self, room_id: str, events: list[EventData]
-    ) -> SyncStats:
-        created = 0
-        updated = 0
-
-        current_ics_uids = []
-
-        for event_data in events:
-            calendar_event = CalendarEvent(room_id=room_id, **event_data)
-            existing = await calendar_events_controller.get_by_ics_uid(
-                room_id, event_data["ics_uid"]
-            )
-
-            if existing:
-                updated += 1
-            else:
-                created += 1
-
-            await calendar_events_controller.upsert(calendar_event)
-            current_ics_uids.append(event_data["ics_uid"])
-
-        # Soft delete events that are no longer in calendar
-        deleted = await calendar_events_controller.soft_delete_missing(
-            room_id, current_ics_uids
-        )
-
-        return {
-            "events_created": created,
-            "events_updated": updated,
-            "events_deleted": deleted,
-        }
-
-
-ics_sync_service = ICSSyncService()