chore(main): release 0.38.0 (#897)

Bumps the npm_and_yarn group with 1 update in the /docs directory: [dompurify](https://github.com/cure53/DOMPurify).


Updates `dompurify` from 3.3.1 to 3.3.2
- [Release notes](https://github.com/cure53/DOMPurify/releases)
- [Commits](https://github.com/cure53/DOMPurify/compare/3.3.1...3.3.2)

---
updated-dependencies:
- dependency-name: dompurify
  dependency-version: 3.3.2
  dependency-type: indirect
  dependency-group: npm_and_yarn
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/selfhost-script.yml

@@ -0,0 +1,36 @@
+# Validates the self-hosted setup script: runs with --cpu and --garage,
+# brings up services, runs health checks, then tears down.
+name: Selfhost script (CPU + Garage)
+
+on:
+  workflow_dispatch: {}
+  push:
+    branches:
+      - main
+  pull_request: {}
+
+jobs:
+  selfhost-cpu-garage:
+    runs-on: ubuntu-latest
+    timeout-minutes: 25
+    concurrency:
+      group: selfhost-${{ github.ref }}
+      cancel-in-progress: true
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Run setup-selfhosted.sh (CPU + Garage)
+        run: |
+          ./scripts/setup-selfhosted.sh --cpu --garage
+
+      - name: Quick health checks
+        run: |
+          curl -sf http://localhost:1250/health && echo " Server OK"
+          curl -sf http://localhost:3000 > /dev/null && echo " Frontend OK"
+          curl -sf http://localhost:3903/metrics > /dev/null && echo " Garage admin OK"
+
+      - name: Teardown
+        if: always()
+        run: |
+          docker compose -f docker-compose.selfhosted.yml --profile cpu --profile garage down -v --remove-orphans 2>/dev/null || true

.github/workflows/test_server.yml

@@ -34,7 +34,7 @@ jobs:
           uv run -m pytest -v tests
 
   docker-amd64:
-    runs-on: linux-amd64
+    runs-on: [linux-amd64]
     concurrency:
       group: docker-amd64-${{ github.ref }}
       cancel-in-progress: true
@@ -52,12 +52,14 @@ jobs:
           github-token: ${{ secrets.GHA_CACHE_TOKEN }}
 
   docker-arm64:
-    runs-on: linux-arm64
+    runs-on: [linux-arm64]
     concurrency:
       group: docker-arm64-${{ github.ref }}
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v4
+      - name: Wait for Docker daemon
+        run: while ! docker version; do sleep 1; done
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
       - name: Build ARM64

.gitignore

@@ -1,7 +1,9 @@
 .DS_Store
 server/.env
+server/.env.production
 .env
 Caddyfile
+.env.hatchet
 server/exportdanswer
 .vercel
 .env*.local
@@ -19,6 +21,7 @@ CLAUDE.local.md
 www/.env.development
 www/.env.production
 .playwright-mcp
-docs/pnpm-lock.yaml
 .secrets
 opencode.json
+
+vibedocs/

.gitleaksignore

@@ -3,3 +3,5 @@ docs/docs/installation/auth-setup.md:curl-auth-header:250
 docs/docs/installation/daily-setup.md:curl-auth-header:277
 gpu/self_hosted/DEV_SETUP.md:curl-auth-header:74
 gpu/self_hosted/DEV_SETUP.md:curl-auth-header:83
+server/reflector/worker/process.py:generic-api-key:465
+server/reflector/worker/process.py:generic-api-key:594

.pre-commit-config.yaml

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

CHANGELOG.md

@@ -1,5 +1,120 @@
 # Changelog
 
+## [0.38.0](https://github.com/GreyhavenHQ/reflector/compare/v0.37.0...v0.38.0) (2026-03-06)
+
+
+### Features
+
+* 3-mode selfhosted refactoring (--gpu, --cpu, --hosted) + audio token auth fallback ([#896](https://github.com/GreyhavenHQ/reflector/issues/896)) ([a682846](https://github.com/GreyhavenHQ/reflector/commit/a6828466456407c808302e9eb8dc4b4f0614dd6f))
+
+
+### Bug Fixes
+
+* improve hatchet workflow reliability ([#900](https://github.com/GreyhavenHQ/reflector/issues/900)) ([c155f66](https://github.com/GreyhavenHQ/reflector/commit/c155f669825e8e2a6e929821a1ef0bd94237dc11))
+
+## [0.37.0](https://github.com/GreyhavenHQ/reflector/compare/v0.36.0...v0.37.0) (2026-03-03)
+
+
+### Features
+
+* enable daily co in selfhosted + only schedule tasks when necessary ([#883](https://github.com/GreyhavenHQ/reflector/issues/883)) ([045eae8](https://github.com/GreyhavenHQ/reflector/commit/045eae8ff2014a7b83061045e3c8cb25cce9d60a))
+
+
+### Bug Fixes
+
+* aws storage construction ([#895](https://github.com/GreyhavenHQ/reflector/issues/895)) ([f5ec2d2](https://github.com/GreyhavenHQ/reflector/commit/f5ec2d28cfa2de9b2b4aeec81966737b740689c2))
+* remaining dependabot security issues ([#890](https://github.com/GreyhavenHQ/reflector/issues/890)) ([0931095](https://github.com/GreyhavenHQ/reflector/commit/0931095f49e61216e651025ce92be460e6a9df9e))
+* test selfhosted script ([#892](https://github.com/GreyhavenHQ/reflector/issues/892)) ([4d915e2](https://github.com/GreyhavenHQ/reflector/commit/4d915e2a9fe9f05f31cbd0018d9c2580daf7854f))
+* upgrade to nextjs 16 ([#888](https://github.com/GreyhavenHQ/reflector/issues/888)) ([f6cc032](https://github.com/GreyhavenHQ/reflector/commit/f6cc03286baf3e3a115afd3b22ae993ad7a4b7e3))
+
+## [0.35.1](https://github.com/GreyhavenHQ/reflector/compare/v0.35.0...v0.35.1) (2026-02-25)
+
+
+### Bug Fixes
+
+* enable sentry on frontend ([#876](https://github.com/GreyhavenHQ/reflector/issues/876)) ([bc6bb63](https://github.com/GreyhavenHQ/reflector/commit/bc6bb63c32dc84be5d3b00388618d53f04f64e35))
+* switch structured output to tool-call with reflection retry ([#879](https://github.com/GreyhavenHQ/reflector/issues/879)) ([5d54758](https://github.com/GreyhavenHQ/reflector/commit/5d547586ef0f54514d1d65aacca8e57869013a82))
+
+## [0.35.0](https://github.com/Monadical-SAS/reflector/compare/v0.34.0...v0.35.0) (2026-02-23)
+
+
+### Features
+
+* Add Single User authentication to Selfhosted ([#870](https://github.com/Monadical-SAS/reflector/issues/870)) ([c8db373](https://github.com/Monadical-SAS/reflector/commit/c8db37362b6cfd8f772aee8857de2909f283c029))
+
+## [0.34.0](https://github.com/Monadical-SAS/reflector/compare/v0.33.0...v0.34.0) (2026-02-20)
+
+
+### Features
+
+* add Caddy reverse proxy with auto HTTPS for LAN access and auto-derive WebSocket URL ([#863](https://github.com/Monadical-SAS/reflector/issues/863)) ([7f2a401](https://github.com/Monadical-SAS/reflector/commit/7f2a4013cbb3d3ee3e76885f28d73331dcaf325c))
+* add change_seq to transcripts for ingestion support ([#868](https://github.com/Monadical-SAS/reflector/issues/868)) ([d4cc6be](https://github.com/Monadical-SAS/reflector/commit/d4cc6be1fed56ea7fba06acb8d50c9de43b26b07))
+* local llm support + standalone-script doc/draft ([#856](https://github.com/Monadical-SAS/reflector/issues/856)) ([b468427](https://github.com/Monadical-SAS/reflector/commit/b468427f1bb12634f5840990e9d64b2c145d7c1a))
+* remove network_mode host for standalone WebRTC ([#864](https://github.com/Monadical-SAS/reflector/issues/864)) ([9dbf155](https://github.com/Monadical-SAS/reflector/commit/9dbf155be4de7c059035a75f90c7bf0845344b74))
+* standalone frontend uses production build instead of dev server ([#862](https://github.com/Monadical-SAS/reflector/issues/862)) ([5bca925](https://github.com/Monadical-SAS/reflector/commit/5bca92510a5c33f8baeeaac2c346fb1978366ac8))
+
+
+### Bug Fixes
+
+* auto-rebuild standalone images and blank Hatchet vars ([3d13e5d](https://github.com/Monadical-SAS/reflector/commit/3d13e5d42fc53ce3c005841265ed1e8735a61518))
+* check compose version output, not just exit code ([e57c618](https://github.com/Monadical-SAS/reflector/commit/e57c6186f92d66e4525786e56b018c08cf792d2f))
+* check for Docker BuildKit (buildx) before building images ([14a8b58](https://github.com/Monadical-SAS/reflector/commit/14a8b5808e5aed860e55aaed35a0fdf8b2f4afa3))
+* check for Docker Compose plugin before running standalone setup ([36a8dae](https://github.com/Monadical-SAS/reflector/commit/36a8daee61c2b7a0937fd0914d51fb4ea8212ae7))
+* live flow real-time updates during processing ([#861](https://github.com/Monadical-SAS/reflector/issues/861)) ([972a52d](https://github.com/Monadical-SAS/reflector/commit/972a52d22f989f9e2c6f52362b3f1a4e17773663))
+* remove max_tokens cap to support thinking models (Kimi-K2.5) ([#869](https://github.com/Monadical-SAS/reflector/issues/869)) ([527a069](https://github.com/Monadical-SAS/reflector/commit/527a069ba9eff6717ccd4bb1e839674edebffceb))
+* standalone on ubuntu ([#865](https://github.com/Monadical-SAS/reflector/issues/865)) ([a8ad237](https://github.com/Monadical-SAS/reflector/commit/a8ad237d8571d5ef5c78fb4427c538592d6a7b43))
+* standalone server networking and setup diagnostics ([695f3c4](https://github.com/Monadical-SAS/reflector/commit/695f3c49285254869f6a6cbd5f860d1169fa4daa))
+
+## [0.33.0](https://github.com/Monadical-SAS/reflector/compare/v0.32.2...v0.33.0) (2026-02-05)
+
+
+### Features
+
+* Daily+hatchet default ([#846](https://github.com/Monadical-SAS/reflector/issues/846)) ([15ab2e3](https://github.com/Monadical-SAS/reflector/commit/15ab2e306eacf575494b4b5d2b2ad779d44a1c7f))
+
+
+### Bug Fixes
+
+* websocket tests ([#825](https://github.com/Monadical-SAS/reflector/issues/825)) ([1ce1c7a](https://github.com/Monadical-SAS/reflector/commit/1ce1c7a910b6c374115d2437b17f9d288ef094dc))
+
+## [0.32.2](https://github.com/Monadical-SAS/reflector/compare/v0.32.1...v0.32.2) (2026-02-03)
+
+
+### Bug Fixes
+
+* increase TIMEOUT_MEDIUM from 2m to 5m for LLM tasks ([#843](https://github.com/Monadical-SAS/reflector/issues/843)) ([4acde4b](https://github.com/Monadical-SAS/reflector/commit/4acde4b7fdef88cc02ca12cf38c9020b05ed96ac))
+* make caddy optional ([#841](https://github.com/Monadical-SAS/reflector/issues/841)) ([a2ed7d6](https://github.com/Monadical-SAS/reflector/commit/a2ed7d60d557b551a5b64e4dfd909b63a791d9fc))
+* use Daily API recording.duration as master source for transcript duration ([#844](https://github.com/Monadical-SAS/reflector/issues/844)) ([8707c66](https://github.com/Monadical-SAS/reflector/commit/8707c6694a80c939b6214bbc13331741f192e082))
+
+## [0.32.1](https://github.com/Monadical-SAS/reflector/compare/v0.32.0...v0.32.1) (2026-01-30)
+
+
+### Bug Fixes
+
+* daily multitrack pipeline finalze dependency fix ([23eb137](https://github.com/Monadical-SAS/reflector/commit/23eb1371cb9348c4b81eb12ad506b582f8a4799e))
+* match httpx pad with hatchet audio timeout ([c05d1f0](https://github.com/Monadical-SAS/reflector/commit/c05d1f03cd8369fc06efd455527e50246887efd0))
+
+## [0.32.0](https://github.com/Monadical-SAS/reflector/compare/v0.31.0...v0.32.0) (2026-01-30)
+
+
+### Features
+
+* modal padding ([#837](https://github.com/Monadical-SAS/reflector/issues/837)) ([7fde64e](https://github.com/Monadical-SAS/reflector/commit/7fde64e2529a1d37b0f7507c62d983a7bd0b5b89))
+
+## [0.31.0](https://github.com/Monadical-SAS/reflector/compare/v0.30.0...v0.31.0) (2026-01-23)
+
+
+### Features
+
+* mixdown optional ([#834](https://github.com/Monadical-SAS/reflector/issues/834)) ([fc3ef6c](https://github.com/Monadical-SAS/reflector/commit/fc3ef6c8933231c731fad84e7477a476a6220a5e))
+
+## [0.30.0](https://github.com/Monadical-SAS/reflector/compare/v0.29.0...v0.30.0) (2026-01-23)
+
+
+### Features
+
+* brady bunch ([#816](https://github.com/Monadical-SAS/reflector/issues/816)) ([6c175a1](https://github.com/Monadical-SAS/reflector/commit/6c175a11d8a3745095bfad06a4ad3ccdfd278433))
+
 ## [0.29.0](https://github.com/Monadical-SAS/reflector/compare/v0.28.1...v0.29.0) (2026-01-21)
 
 

CLAUDE.md

@@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 Reflector is an AI-powered audio transcription and meeting analysis platform with real-time processing capabilities. The system consists of:
 
-- **Frontend**: Next.js 14 React application (`www/`) with Chakra UI, real-time WebSocket integration
+- **Frontend**: Next.js 16 React application (`www/`) with Chakra UI, real-time WebSocket integration
 - **Backend**: Python FastAPI server (`server/`) with async database operations and background processing
 - **Processing**: GPU-accelerated ML pipeline for transcription, diarization, summarization via Modal.com
 - **Infrastructure**: Redis, PostgreSQL/SQLite, Celery workers, WebRTC streaming

Caddyfile.example

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

Caddyfile.selfhosted.example

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

Caddyfile.standalone.example

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

README.md

@@ -34,6 +34,8 @@ Reflector is an AI-powered audio transcription and meeting analysis platform tha
   </tr>
 </table>
 
+<p align="center" style="font-size: 1.5em; font-weight: bold;">By <a href="https://greyhaven.co">Greyhaven</a></p>
+
 ## What is Reflector?
 
 Reflector is a web application that utilizes local models to process audio content, providing:
@@ -44,22 +46,100 @@ Reflector is a web application that utilizes local models to process audio conte
 - **Topic Detection & Summarization**: Extract key topics and generate concise summaries using LLMs
 - **Meeting Recording**: Create permanent records of meetings with searchable transcripts
 
-Currently we provide [modal.com](https://modal.com/) gpu template to deploy.
+## Architecture
 
-## Background
+The project consists of three primary components:
 
-The project architecture consists of three primary components:
+- **Back-End**: Python FastAPI server with async database operations and background processing, found in `server/`.
+- **Front-End**: Next.js 14 React application with Chakra UI, located in `www/`.
+- **GPU Models**: Specialized ML models for transcription, diarization, translation, and summarization.
 
-- **Back-End**: Python server that offers an API and data persistence, found in `server/`.
-- **Front-End**: NextJS React project hosted on Vercel, located in `www/`.
-- **GPU implementation**: Providing services such as speech-to-text transcription, topic generation, automated summaries, and translations.
+Currently, Reflector supports two input methods:
+- **Screenshare capture**: Real-time audio capture from your browser via WebRTC
+- **Audio file upload**: Upload pre-recorded audio files for processing
 
-It also uses authentik for authentication if activated.
+## Installation
 
-## Contribution Guidelines
+For full deployment instructions, see the [Self-Hosted Production Guide](docsv2/selfhosted-production.md) and the [Architecture Reference](docsv2/selfhosted-architecture.md).
 
-All new contributions should be made in a separate branch, and goes through a Pull Request.
-[Conventional commits](https://www.conventionalcommits.org/en/v1.0.0/) must be used for the PR title and commits.
+### Self-Hosted Deployment
+
+The self-hosted setup script configures and launches everything on a single server:
+
+```bash
+# GPU with local Ollama LLM, local S3 storage, and Caddy reverse proxy
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# With a custom domain (enables Let's Encrypt auto-HTTPS)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --domain reflector.example.com
+
+# CPU-only mode (slower, no NVIDIA GPU required)
+./scripts/setup-selfhosted.sh --cpu --ollama-cpu --garage --caddy
+
+# With password authentication
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+```
+
+The script is idempotent and safe to re-run. See `./scripts/setup-selfhosted.sh --help` for all options.
+
+### Authentication
+
+Reflector supports three authentication modes:
+
+- **Password authentication (recommended for self-hosted / single-user)**: Use the `--password` flag in the setup script. This creates an `admin@localhost` user with the provided password. Users must log in to create, edit, or delete transcripts.
+
+  ```bash
+  ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+  ```
+
+- **Authentik OIDC**: For multi-user or enterprise deployments, Reflector supports [Authentik](https://goauthentik.io/) as an OAuth/OIDC provider. This enables SSO, LDAP/AD integration, and centralized user management. Requires configuring `AUTH_BACKEND=jwt` on the backend and `AUTH_PROVIDER=authentik` on the frontend. See the [Self-Hosted Production Guide](docsv2/selfhosted-production.md) for details.
+
+- **Public mode (default when no auth is configured)**: If neither password nor Authentik is set up, Reflector runs in public mode. In this mode, no login is required — anyone with access to the URL can use the application. Transcripts are created anonymously (not tied to any user account), which means they **cannot be edited or deleted** through the UI or API. Anonymous transcripts are automatically cleaned up after 7 days. This mode is suitable for demos or testing but not recommended for production use.
+
+### Development Setup
+
+```bash
+# Backend
+cd server
+uv sync
+docker compose up -d redis
+uv run alembic upgrade head
+uv run -m reflector.app --reload
+
+# In a separate terminal — start the worker
+cd server
+uv run celery -A reflector.worker.app worker --loglevel=info
+
+# Frontend
+cd www
+pnpm install
+cp .env_template .env
+pnpm dev
+```
+
+### Modal.com GPU (Optional)
+
+Reflector also supports deploying specialized models (transcription, diarization) to [Modal.com](https://modal.com/) for serverless GPU processing. This is **not integrated into the self-hosted setup script** and must be configured manually.
+
+See [Modal.com Setup Guide](docs/docs/installation/modal-setup.md) for deployment instructions.
+
+## Audio Processing Commands
+
+### Process a local audio file
+
+```bash
+cd server
+uv run python -m reflector.tools.process path/to/audio.wav
+```
+
+### Reprocess an existing transcription
+
+Re-run the processing pipeline on a previously uploaded transcription by its UUID:
+
+```bash
+cd server
+uv run -m reflector.tools.process_transcript <transcript-uuid> --sync
+```
 
 ## Usage
 
@@ -87,96 +167,9 @@ Note: We currently do not have instructions for Windows users.
 - Then goto `System Preferences -> Sound` and choose the devices created from the Output and Input tabs.
 - The input from your local microphone, the browser run meeting should be aggregated into one virtual stream to listen to and the output should be fed back to your specified output devices if everything is configured properly.
 
-## Installation
-
-*Note: we're working toward better installation, theses instructions are not accurate for now*
-
-### Frontend
-
-Start with `cd www`.
-
-**Installation**
-
-```bash
-pnpm install
-cp .env.example .env
-```
-
-Then, fill in the environment variables in `.env` as needed. If you are unsure on how to proceed, ask in Zulip.
-
-**Run in development mode**
-
-```bash
-pnpm dev
-```
-
-Then (after completing server setup and starting it) open [http://localhost:3000](http://localhost:3000) to view it in the browser.
-
-**OpenAPI Code Generation**
-
-To generate the TypeScript files from the openapi.json file, make sure the python server is running, then run:
-
-```bash
-pnpm openapi
-```
-
-### Backend
-
-Start with `cd server`.
-
-**Run in development mode**
-
-```bash
-docker compose up -d redis
-
-# on the first run, or if the schemas changed
-uv run alembic upgrade head
-
-# start the worker
-uv run celery -A reflector.worker.app worker --loglevel=info
-
-# start the app
-uv run -m reflector.app --reload
-```
-
-Then fill `.env` with the omitted values (ask in Zulip).
-
-**Crontab (optional)**
-
-For crontab (only healthcheck for now), start the celery beat (you don't need it on your local dev environment):
-
-```bash
-uv run celery -A reflector.worker.app beat
-```
-
-### GPU models
-
-Currently, reflector heavily use custom local models, deployed on modal. All the micro services are available in server/gpu/
-
-To deploy llm changes to modal, you need:
-- a modal account
-- set up the required secret in your modal account (REFLECTOR_GPU_APIKEY)
-- install the modal cli
-- connect your modal cli to your account if not done previously
-- `modal run path/to/required/llm`
-
-## Using local files
-
-You can manually process an audio file by calling the process tool:
-
-```bash
-uv run python -m reflector.tools.process path/to/audio.wav
-```
-
-## Reprocessing any transcription
-
-```bash
-uv run -m reflector.tools.process_transcript 81ec38d1-9dd7-43d2-b3f8-51f4d34a07cd --sync
-```
-
 ## Build-time env variables
 
-Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a ccustomizable prebuild docker container.
+Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a customizable prebuilt docker container.
 
 Instead, all the variables are runtime. Variables needed to the frontend are served to the frontend app at initial render.
 
@@ -211,3 +204,22 @@ FEATURE_BROWSE=false
 # Enable Zulip integration
 FEATURE_SEND_TO_ZULIP=true
 ```
+
+## Contribution Guidelines
+
+All new contributions should be made in a separate branch, and goes through a Pull Request.
+[Conventional commits](https://www.conventionalcommits.org/en/v1.0.0/) must be used for the PR title and commits.
+
+## Future Plans
+
+- **Multi-language support enhancement**: Default language selection per room/user, automatic language detection improvements, multi-language diarization, and RTL language UI support
+- **Jitsi integration**: Self-hosted video conferencing rooms with no external API keys, full control over video infrastructure, and enhanced privacy
+- **Calendar integration**: Google Calendar and Microsoft Outlook synchronization, automatic meeting room creation, and post-meeting transcript delivery
+- **Enhanced analytics**: Meeting insights dashboard, speaker participation metrics, topic trends over time, and team collaboration patterns
+- **Advanced AI features**: Real-time sentiment analysis, emotion detection, meeting quality scores, and automated coaching suggestions
+- **Integration ecosystem**: Slack/Teams notifications, CRM integration (Salesforce, HubSpot), project management tools (Jira, Asana), and knowledge bases (Notion, Confluence)
+- **Performance improvements**: WebAssembly for client-side processing, edge computing support, and network optimization
+
+## Legacy Documentation
+
+The `docs/` folder contains an older Docusaurus-based documentation site. These docs are **no longer actively maintained** and may be outdated. For current installation and deployment instructions, refer to the [`docsv2/`](docsv2/) folder instead.

docker-compose.prod.yml

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

docker-compose.selfhosted.yml

@@ -0,0 +1,398 @@
+# Self-hosted production Docker Compose — single file for everything.
+#
+# Usage: ./scripts/setup-selfhosted.sh <--gpu|--cpu|--hosted> [--ollama-gpu|--ollama-cpu] [--garage] [--caddy]
+#   or:  docker compose -f docker-compose.selfhosted.yml [--profile gpu] [--profile ollama-gpu] [--profile garage] [--profile caddy] up -d
+#
+# ML processing modes (pick ONE — required):
+#   --gpu                  NVIDIA GPU container for transcription/diarization/translation (profile: gpu)
+#   --cpu                  In-process CPU processing on server/worker (no ML container needed)
+#   --hosted               Remote GPU service URL (no ML container needed)
+#
+# Local LLM (optional — for summarization/topics):
+#   --profile ollama-gpu   Local Ollama with NVIDIA GPU
+#   --profile ollama-cpu   Local Ollama on CPU only
+#
+# Daily.co multitrack processing (auto-detected from server/.env):
+#   --profile dailyco      Hatchet workflow engine + CPU/LLM workers
+#
+# Other optional services:
+#   --profile garage       Local S3-compatible storage (Garage)
+#   --profile caddy        Reverse proxy with auto-SSL
+#
+# Prerequisites:
+#   1. Run ./scripts/setup-selfhosted.sh to generate env files and secrets
+#   2. Or manually create server/.env and www/.env from the .selfhosted.example templates
+
+services:
+  # ===========================================================
+  # Always-on core services (no profile required)
+  # ===========================================================
+
+  server:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:1250:1250"
+      - "51000-51100:51000-51100/udp"
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: server
+      # Docker-internal overrides (always correct inside compose network)
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      # ML backend config comes from env_file (server/.env), set per-mode by setup script
+      # HF_TOKEN needed for in-process pyannote diarization (--cpu mode)
+      HF_TOKEN: ${HF_TOKEN:-}
+      # WebRTC: fixed UDP port range for ICE candidates (mapped above)
+      WEBRTC_PORT_RANGE: "51000-51100"
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    volumes:
+      - server_data:/app/data
+
+  worker:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: worker
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      # ML backend config comes from env_file (server/.env), set per-mode by setup script
+      HF_TOKEN: ${HF_TOKEN:-}
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+    volumes:
+      - server_data:/app/data
+
+  beat:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: beat
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+    depends_on:
+      postgres:
+        condition: service_healthy
+      redis:
+        condition: service_started
+
+  web:
+    build:
+      context: ./www
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-frontend:latest
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:3000:3000"
+    env_file:
+      - ./www/.env
+    environment:
+      NODE_ENV: production
+      NODE_TLS_REJECT_UNAUTHORIZED: "0"
+      SERVER_API_URL: http://server:1250
+      KV_URL: redis://redis:6379
+      KV_USE_TLS: "false"
+      NEXTAUTH_URL_INTERNAL: http://localhost:3000
+    depends_on:
+      - redis
+
+  redis:
+    image: redis:7.2-alpine
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 30s
+      timeout: 3s
+      retries: 3
+    volumes:
+      - redis_data:/data
+
+  postgres:
+    image: postgres:17-alpine
+    restart: unless-stopped
+    command: ["postgres", "-c", "max_connections=200"]
+    environment:
+      POSTGRES_USER: reflector
+      POSTGRES_PASSWORD: reflector
+      POSTGRES_DB: reflector
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+      - ./server/docker/init-hatchet-db.sql:/docker-entrypoint-initdb.d/init-hatchet-db.sql:ro
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U reflector"]
+      interval: 30s
+      timeout: 3s
+      retries: 3
+
+  # ===========================================================
+  # Specialized model containers (transcription, diarization, translation)
+  # Only the gpu profile is activated by the setup script (--gpu mode).
+  # The cpu service definition is kept for manual/standalone use but is
+  # NOT activated by --cpu mode (which uses in-process local backends).
+  # Both services get alias "transcription" so server config never changes.
+  # ===========================================================
+
+  gpu:
+    build:
+      context: ./gpu/self_hosted
+      dockerfile: Dockerfile
+    profiles: [gpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:8000:8000"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-}
+    volumes:
+      - gpu_cache:/root/.cache
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+    networks:
+      default:
+        aliases:
+          - transcription
+
+  cpu:
+    build:
+      context: ./gpu/self_hosted
+      dockerfile: Dockerfile.cpu
+    profiles: [cpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:8000:8000"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-}
+    volumes:
+      - gpu_cache:/root/.cache
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
+      interval: 15s
+      timeout: 5s
+      retries: 10
+      start_period: 120s
+    networks:
+      default:
+        aliases:
+          - transcription
+
+  # ===========================================================
+  # Ollama — local LLM for summarization & topic detection
+  # Only started with --ollama-gpu or --ollama-cpu modes.
+  # ===========================================================
+
+  ollama:
+    image: ollama/ollama:latest
+    profiles: [ollama-gpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:11435:11435"
+    volumes:
+      - ollama_data:/root/.ollama
+    environment:
+      OLLAMA_HOST: "0.0.0.0:11435"
+      OLLAMA_KEEP_ALIVE: "24h"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  ollama-cpu:
+    image: ollama/ollama:latest
+    profiles: [ollama-cpu]
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:11435:11435"
+    volumes:
+      - ollama_data:/root/.ollama
+    environment:
+      OLLAMA_HOST: "0.0.0.0:11435"
+      OLLAMA_KEEP_ALIVE: "24h"         # keep model loaded to avoid reload delays
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:11435/api/tags"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+  # ===========================================================
+  # Garage — local S3-compatible object storage (optional)
+  # ===========================================================
+
+  garage:
+    image: dxflrs/garage:v1.1.0
+    profiles: [garage]
+    restart: unless-stopped
+    ports:
+      - "3900:3900"   # S3 API
+      - "3903:3903"   # Admin API
+    volumes:
+      - garage_data:/var/lib/garage/data
+      - garage_meta:/var/lib/garage/meta
+      - ./data/garage.toml:/etc/garage.toml:ro
+    healthcheck:
+      test: ["CMD", "/garage", "stats"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 5s
+
+  # ===========================================================
+  # Caddy — reverse proxy with automatic SSL (optional)
+  # Maps 80:80 and 443:443 — only exposed ports in the stack.
+  # ===========================================================
+
+  caddy:
+    image: caddy:2-alpine
+    profiles: [caddy]
+    restart: unless-stopped
+    ports:
+      - "80:80"
+      - "443:443"
+    volumes:
+      - ./Caddyfile:/etc/caddy/Caddyfile:ro
+      - caddy_data:/data
+      - caddy_config:/config
+    depends_on:
+      - web
+      - server
+
+  # ===========================================================
+  # Hatchet + Daily.co workers (optional — for Daily.co multitrack processing)
+  # Auto-enabled when DAILY_API_KEY is configured in server/r
+  # ===========================================================
+
+  hatchet:
+    image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
+    profiles: [dailyco]
+    restart: on-failure
+    depends_on:
+      postgres:
+        condition: service_healthy
+    ports:
+      - "8888:8888"
+      - "7078:7077"
+    env_file:
+      - ./.env.hatchet
+    environment:
+      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable&connect_timeout=30"
+      SERVER_AUTH_COOKIE_INSECURE: "t"
+      SERVER_GRPC_BIND_ADDRESS: "0.0.0.0"
+      SERVER_GRPC_INSECURE: "t"
+      SERVER_GRPC_BROADCAST_ADDRESS: hatchet:7077
+      SERVER_GRPC_PORT: "7077"
+      SERVER_AUTH_SET_EMAIL_VERIFIED: "t"
+      SERVER_INTERNAL_CLIENT_INTERNAL_GRPC_BROADCAST_ADDRESS: hatchet:7077
+    volumes:
+      - hatchet_config:/config
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8888/api/live"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 30s
+
+  hatchet-worker-cpu:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    profiles: [dailyco]
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: hatchet-worker-cpu
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
+    depends_on:
+      hatchet:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+  hatchet-worker-llm:
+    build:
+      context: ./server
+      dockerfile: Dockerfile
+    image: monadicalsas/reflector-backend:latest
+    profiles: [dailyco]
+    restart: unless-stopped
+    env_file:
+      - ./server/.env
+    environment:
+      ENTRYPOINT: hatchet-worker-llm
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+      REDIS_HOST: redis
+      CELERY_BROKER_URL: redis://redis:6379/1
+      CELERY_RESULT_BACKEND: redis://redis:6379/1
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
+    depends_on:
+      hatchet:
+        condition: service_healthy
+    volumes:
+      - server_data:/app/data
+
+volumes:
+  postgres_data:
+  redis_data:
+  server_data:
+  gpu_cache:
+  garage_data:
+  garage_meta:
+  ollama_data:
+  caddy_data:
+  caddy_config:
+  hatchet_config:
+
+networks:
+  default:
+    attachable: true

docker-compose.standalone.yml

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

docker-compose.yml

@@ -2,8 +2,7 @@ services:
   server:
     build:
       context: server
-    ports:
-      - 1250:1250
+    network_mode: host
     volumes:
       - ./server/:/app/
       - /app/.venv
@@ -11,6 +10,12 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: server
+      DATABASE_URL: postgresql+asyncpg://reflector:reflector@localhost:5432/reflector
+      REDIS_HOST: localhost
+      CELERY_BROKER_URL: redis://localhost:6379/1
+      CELERY_RESULT_BACKEND: redis://localhost:6379/1
+      HATCHET_CLIENT_SERVER_URL: http://localhost:8889
+      HATCHET_CLIENT_HOST_PORT: localhost:7078
 
   worker:
     build:
@@ -22,6 +27,11 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: worker
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
+    depends_on:
+      redis:
+        condition: service_started
 
   beat:
     build:
@@ -33,6 +43,9 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: beat
+    depends_on:
+      redis:
+        condition: service_started
 
   hatchet-worker-cpu:
     build:
@@ -44,6 +57,8 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: hatchet-worker-cpu
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
     depends_on:
       hatchet:
         condition: service_healthy
@@ -57,6 +72,8 @@ services:
       - ./server/.env
     environment:
       ENTRYPOINT: hatchet-worker-llm
+      HATCHET_CLIENT_SERVER_URL: http://hatchet:8888
+      HATCHET_CLIENT_HOST_PORT: hatchet:7077
     depends_on:
       hatchet:
         condition: service_healthy
@@ -66,19 +83,22 @@ services:
     ports:
       - 6379:6379
   web:
-    image: node:22-alpine
+    build:
+      context: ./www
+      dockerfile: Dockerfile
     ports:
       - "3000:3000"
-    command: sh -c "corepack enable && pnpm install && pnpm dev"
-    restart: unless-stopped
-    working_dir: /app
-    volumes:
-      - ./www:/app/
-      - /app/node_modules
     env_file:
       - ./www/.env.local
     environment:
-      - NODE_ENV=development
+      NODE_ENV: development
+      SERVER_API_URL: http://host.docker.internal:1250
+      KV_URL: redis://redis:6379
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    depends_on:
+      redis:
+        condition: service_started
 
   postgres:
     image: postgres:17
@@ -94,13 +114,14 @@ services:
       - ./server/docker/init-hatchet-db.sql:/docker-entrypoint-initdb.d/init-hatchet-db.sql:ro
     healthcheck:
       test: ["CMD-SHELL", "pg_isready -d reflector -U reflector"]
-      interval: 10s
-      timeout: 10s
-      retries: 5
-      start_period: 10s
+      interval: 5s
+      timeout: 5s
+      retries: 10
+      start_period: 15s
 
   hatchet:
     image: ghcr.io/hatchet-dev/hatchet/hatchet-lite:latest
+    restart: on-failure
     ports:
       - "8889:8888"
       - "7078:7077"
@@ -108,7 +129,7 @@ services:
       postgres:
         condition: service_healthy
     environment:
-      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable"
+      DATABASE_URL: "postgresql://reflector:reflector@postgres:5432/hatchet?sslmode=disable&connect_timeout=30"
       SERVER_AUTH_COOKIE_DOMAIN: localhost
       SERVER_AUTH_COOKIE_INSECURE: "t"
       SERVER_GRPC_BIND_ADDRESS: "0.0.0.0"
@@ -128,6 +149,5 @@ services:
       retries: 5
       start_period: 30s
 
-networks:
-  default:
-    attachable: true
+volumes:
+  next_cache:

docs/.dockerignore

@@ -0,0 +1,7 @@
+node_modules
+build
+.git
+.gitignore
+*.log
+.DS_Store
+.env*

docs/Dockerfile

@@ -1,14 +1,17 @@
-FROM node:18-alpine AS builder
+FROM node:20-alpine AS builder
 WORKDIR /app
 
 # Install curl for fetching OpenAPI spec
 RUN apk add --no-cache curl
 
-# Copy package files
-COPY package*.json ./
+# Enable pnpm
+RUN corepack enable && corepack prepare pnpm@latest --activate
+
+# Copy package files and lockfile
+COPY package.json pnpm-lock.yaml* ./
 
 # Install dependencies
-RUN npm ci
+RUN pnpm install --frozen-lockfile
 
 # Copy source
 COPY . .
@@ -21,7 +24,7 @@ RUN mkdir -p ./static && curl -sf "${OPENAPI_URL}" -o ./static/openapi.json || e
 RUN sed -i "s/onBrokenLinks: 'throw'/onBrokenLinks: 'warn'/g" docusaurus.config.ts
 
 # Build static site (skip prebuild hook by calling docusaurus directly)
-RUN npx docusaurus build
+RUN pnpm exec docusaurus build
 
 # Production image
 FROM nginx:alpine

docs/README.md

@@ -5,13 +5,13 @@ This website is built using [Docusaurus](https://docusaurus.io/), a modern stati
 ### Installation
 
 ```
-$ yarn
+$ pnpm install
 ```
 
 ### Local Development
 
 ```
-$ yarn start
+$ pnpm start
 ```
 
 This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
@@ -19,7 +19,7 @@ This command starts a local development server and opens up a browser window. Mo
 ### Build
 
 ```
-$ yarn build
+$ pnpm build
 ```
 
 This command generates static content into the `build` directory and can be served using any static contents hosting service.
@@ -29,13 +29,13 @@ This command generates static content into the `build` directory and can be serv
 Using SSH:
 
 ```
-$ USE_SSH=true yarn deploy
+$ USE_SSH=true pnpm deploy
 ```
 
 Not using SSH:
 
 ```
-$ GIT_USER=<Your GitHub username> yarn deploy
+$ GIT_USER=<Your GitHub username> pnpm deploy
 ```
 
 If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

docs/create-docs.sh

@@ -254,15 +254,15 @@ Reflector can run completely offline:
 Control where each step happens:
 
 ```yaml
-# All local processing
-TRANSCRIPT_BACKEND=local
-DIARIZATION_BACKEND=local
-TRANSLATION_BACKEND=local
+# All in-process processing
+TRANSCRIPT_BACKEND=whisper
+DIARIZATION_BACKEND=pyannote
+TRANSLATION_BACKEND=marian
 
 # Hybrid approach
-TRANSCRIPT_BACKEND=modal  # Fast GPU processing
-DIARIZATION_BACKEND=local # Sensitive speaker data
-TRANSLATION_BACKEND=modal  # Non-sensitive translation
+TRANSCRIPT_BACKEND=modal    # Fast GPU processing
+DIARIZATION_BACKEND=pyannote # Sensitive speaker data
+TRANSLATION_BACKEND=modal    # Non-sensitive translation
 ```
 
 ### Storage Options

docs/docs/concepts/overview.md

@@ -11,7 +11,7 @@ Reflector is built as a modern, scalable, microservices-based application design
 
 ### Frontend Application
 
-The user interface is built with **Next.js 15** using the App Router pattern, providing:
+The user interface is built with **Next.js 16** using the App Router pattern, providing:
 
 - Server-side rendering for optimal performance
 - Real-time WebSocket connections for live transcription

docs/docs/installation/docker-setup.md

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

docs/docs/installation/docs-deployment.md

@@ -36,14 +36,15 @@ This creates `docs/static/openapi.json` (should be ~70KB) which will be copied d
 The Dockerfile is already in `docs/Dockerfile`:
 
 ```dockerfile
-FROM node:18-alpine AS builder
+FROM node:20-alpine AS builder
 WORKDIR /app
 
-# Copy package files
-COPY package*.json ./
+# Enable pnpm and copy package files + lockfile
+RUN corepack enable && corepack prepare pnpm@latest --activate
+COPY package.json pnpm-lock.yaml* ./
 
-# Inshall dependencies
-RUN npm ci
+# Install dependencies
+RUN pnpm install --frozen-lockfile
 
 # Copy source (includes static/openapi.json if pre-fetched)
 COPY . .
@@ -52,7 +53,7 @@ COPY . .
 RUN sed -i "s/onBrokenLinks: 'throw'/onBrokenLinks: 'warn'/g" docusaurus.config.ts
 
 # Build static site
-RUN npx docusaurus build
+RUN pnpm exec docusaurus build
 
 FROM nginx:alpine
 COPY --from=builder /app/build /usr/share/nginx/html

docs/docs/installation/overview.md

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

docs/docs/installation/setup-standalone.md

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

docs/docs/intro.md

@@ -46,7 +46,7 @@ Reflector consists of three main components:
 
 Ready to deploy Reflector? Head over to our [Installation Guide](./installation/overview) to set up your own instance.
 
-For a quick overview of how Reflector processes audio, check out our [Pipeline Documentation](./pipelines/overview).
+For a quick overview of how Reflector processes audio, check out our [Pipeline Documentation](./concepts/pipeline).
 
 ## Open Source
 

docs/docusaurus.config.ts

@@ -124,11 +124,11 @@ const config: Config = {
           items: [
             {
               label: 'Architecture',
-              to: '/docs/reference/architecture/overview',
+              to: '/docs/concepts/overview',
             },
             {
               label: 'Pipelines',
-              to: '/docs/pipelines/overview',
+              to: '/docs/concepts/pipeline',
             },
             {
               label: 'Roadmap',

docs/package.json

@@ -14,26 +14,26 @@
     "write-heading-ids": "docusaurus write-heading-ids",
     "typecheck": "tsc",
     "fetch-openapi": "./scripts/fetch-openapi.sh",
-    "gen-api-docs": "npm run fetch-openapi && docusaurus gen-api-docs reflector",
-    "prebuild": "npm run fetch-openapi"
+    "gen-api-docs": "pnpm run fetch-openapi && docusaurus gen-api-docs reflector",
+    "prebuild": "pnpm run fetch-openapi"
   },
   "dependencies": {
-    "@docusaurus/core": "3.6.3",
-    "@docusaurus/preset-classic": "3.6.3",
-    "@mdx-js/react": "^3.0.0",
-    "clsx": "^2.0.0",
-    "docusaurus-plugin-openapi-docs": "^4.5.1",
-    "docusaurus-theme-openapi-docs": "^4.5.1",
-    "@docusaurus/theme-mermaid": "3.6.3",
-    "prism-react-renderer": "^2.3.0",
-    "react": "^18.0.0",
-    "react-dom": "^18.0.0"
+    "@docusaurus/core": "3.9.2",
+    "@docusaurus/preset-classic": "3.9.2",
+    "@docusaurus/theme-mermaid": "3.9.2",
+    "@mdx-js/react": "^3.1.1",
+    "clsx": "^2.1.1",
+    "docusaurus-plugin-openapi-docs": "^4.7.1",
+    "docusaurus-theme-openapi-docs": "^4.7.1",
+    "prism-react-renderer": "^2.4.1",
+    "react": "^19.2.4",
+    "react-dom": "^19.2.4"
   },
   "devDependencies": {
-    "@docusaurus/module-type-aliases": "3.6.3",
-    "@docusaurus/tsconfig": "3.6.3",
-    "@docusaurus/types": "3.6.3",
-    "typescript": "~5.6.2"
+    "@docusaurus/module-type-aliases": "3.9.2",
+    "@docusaurus/tsconfig": "3.9.2",
+    "@docusaurus/types": "3.9.2",
+    "typescript": "~5.9.3"
   },
   "browserslist": {
     "production": [
@@ -49,5 +49,16 @@
   },
   "engines": {
     "node": ">=18.0"
+  },
+  "pnpm": {
+    "overrides": {
+      "minimatch@<3.1.4": "3.1.5",
+      "minimatch@>=5.0.0 <5.1.8": "5.1.8",
+      "minimatch@>=9.0.0 <9.0.7": "9.0.7",
+      "lodash@<4.17.23": "4.17.23",
+      "js-yaml@<4.1.1": "4.1.1",
+      "gray-matter": "github:jonschlinkert/gray-matter#234163e",
+      "serialize-javascript": "7.0.4"
+    }
   }
 }

docsv2/selfhosted-architecture.md

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

docsv2/selfhosted-production.md

@@ -0,0 +1,638 @@
+# Self-Hosted Production Deployment
+
+Deploy Reflector on a single server with everything running in Docker. Transcription, diarization, and translation use specialized ML models (Whisper/Parakeet, Pyannote); only summarization and topic detection require an LLM.
+
+> For a detailed walkthrough of how the setup script and infrastructure work under the hood, see [How the Self-Hosted Setup Works](selfhosted-architecture.md).
+
+## Prerequisites
+
+### Hardware
+- **With GPU**: Linux server with NVIDIA GPU (8GB+ VRAM recommended), 16GB+ RAM, 50GB+ disk
+- **CPU-only**: 8+ cores, 32GB+ RAM (transcription is slower but works)
+- Disk space for ML models (~2GB on first run) + audio storage
+
+### Software
+- Docker Engine 24+ with Compose V2
+- NVIDIA drivers + `nvidia-container-toolkit` (GPU modes only)
+- `curl`, `openssl` (usually pre-installed)
+
+### Accounts & Credentials (depending on options)
+
+**Always recommended:**
+- **HuggingFace token** — For downloading pyannote speaker diarization models. Get one at https://huggingface.co/settings/tokens and accept the model licenses:
+  - https://huggingface.co/pyannote/speaker-diarization-3.1
+  - https://huggingface.co/pyannote/segmentation-3.0
+  - The setup script will prompt for this. If skipped, diarization falls back to a public model bundle (may be less reliable).
+
+**LLM for summarization & topic detection (pick one):**
+- **With `--ollama-gpu` or `--ollama-cpu`**: Nothing extra — Ollama runs locally and pulls the model automatically
+- **Without `--ollama-*`**: An OpenAI-compatible LLM API key and endpoint. Examples:
+  - OpenAI: `LLM_URL=https://api.openai.com/v1`, `LLM_API_KEY=sk-...`, `LLM_MODEL=gpt-4o-mini`
+  - Anthropic, Together, Groq, or any OpenAI-compatible API
+  - A self-managed vLLM or Ollama instance elsewhere on the network
+
+**Object storage (pick one):**
+- **With `--garage`**: Nothing extra — Garage (local S3-compatible storage) is auto-configured by the script
+- **Without `--garage`**: S3-compatible storage credentials. The script will prompt for these, or you can pre-fill `server/.env`. Options include:
+  - **AWS S3**: Access Key ID, Secret Access Key, bucket name, region
+  - **MinIO**: Same credentials + `TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://your-minio:9000`
+  - **Any S3-compatible provider** (Backblaze B2, Cloudflare R2, DigitalOcean Spaces, etc.): same fields + custom endpoint URL
+
+**Optional add-ons (configure after initial setup):**
+- **Authentik** (user authentication): Requires an Authentik instance with an OAuth2/OIDC application configured for Reflector. See [Enabling Authentication](#enabling-authentication-authentik) below.
+
+## Quick Start
+
+```bash
+git clone https://github.com/Monadical-SAS/reflector.git
+cd reflector
+
+# GPU + local Ollama LLM + local Garage storage + Caddy SSL (with domain):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --domain reflector.example.com
+
+# Same but without a domain (self-signed cert, access via IP):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# CPU-only (in-process ML, no GPU container):
+./scripts/setup-selfhosted.sh --cpu --ollama-cpu --garage --caddy
+
+# Remote GPU service (your own hosted GPU, no local ML container):
+./scripts/setup-selfhosted.sh --hosted --garage --caddy
+
+# With password authentication (single admin user):
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+
+# Build from source instead of pulling prebuilt images:
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --build
+```
+
+That's it. The script generates env files, secrets, starts all containers, waits for health checks, and prints the URL.
+
+## ML Processing Modes (Required)
+
+Pick `--gpu`, `--cpu`, or `--hosted`. This determines how **transcription, diarization, translation, and audio padding** run:
+
+| Flag | What it does | Requires |
+|------|-------------|----------|
+| `--gpu` | NVIDIA GPU container for ML models | NVIDIA GPU + drivers + `nvidia-container-toolkit` |
+| `--cpu` | In-process CPU processing on server/worker (no ML container) | 8+ cores, 16GB+ RAM (32GB recommended for large files) |
+| `--hosted` | Remote GPU service URL (no local ML container) | A running GPU service instance (e.g. `gpu/self_hosted/`) |
+
+## Local LLM (Optional)
+
+Optionally add `--ollama-gpu` or `--ollama-cpu` for a **local Ollama instance** that handles summarization and topic detection. If omitted, configure an external OpenAI-compatible LLM in `server/.env`.
+
+| Flag | What it does | Requires |
+|------|-------------|----------|
+| `--ollama-gpu` | Local Ollama with NVIDIA GPU acceleration | NVIDIA GPU |
+| `--ollama-cpu` | Local Ollama on CPU only | Nothing extra |
+| `--llm-model MODEL` | Choose which Ollama model to download (default: `qwen2.5:14b`) | `--ollama-gpu` or `--ollama-cpu` |
+| *(omitted)* | User configures external LLM (OpenAI, Anthropic, etc.) | LLM API key |
+
+### macOS / Apple Silicon
+
+`--ollama-gpu` requires an NVIDIA GPU and **does not work on macOS**. Docker on macOS cannot access Apple GPU acceleration, so the containerized Ollama will run on CPU only regardless of the flag used.
+
+For the best performance on Mac, we recommend running Ollama **natively outside Docker** (install from https://ollama.com) — this gives Ollama direct access to Apple Metal GPU acceleration. Then omit `--ollama-gpu`/`--ollama-cpu` from the setup script and point the backend to your local Ollama instance:
+
+```env
+# In server/.env
+LLM_URL=http://host.docker.internal:11434/v1
+LLM_MODEL=qwen2.5:14b
+LLM_API_KEY=not-needed
+```
+
+`--ollama-cpu` does work on macOS but will be significantly slower than a native Ollama install with Metal acceleration.
+
+### Choosing an Ollama model
+
+The default model is `qwen2.5:14b` (~9GB download, good multilingual support and summary quality). Override with `--llm-model`:
+
+```bash
+# Default (qwen2.5:14b)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+
+# Mistral — good balance of speed and quality (~4.1GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model mistral --garage --caddy
+
+# Phi-4 — smaller and faster (~9.1GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model phi4 --garage --caddy
+
+# Llama 3.3 70B — best quality, needs 48GB+ RAM or GPU VRAM (~43GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model llama3.3:70b --garage --caddy
+
+# Gemma 2 9B (~5.4GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model gemma2 --garage --caddy
+
+# DeepSeek R1 8B — reasoning model, verbose but thorough summaries (~4.9GB)
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model deepseek-r1:8b --garage --caddy
+```
+
+Browse all available models at https://ollama.com/library.
+
+### Recommended combinations
+
+- **`--gpu --ollama-gpu`**: Best for servers with NVIDIA GPU. Fully self-contained, no external API keys needed.
+- **`--cpu --ollama-cpu`**: No GPU available but want everything self-contained. Slower but works.
+- **`--hosted --ollama-cpu`**: Remote GPU for ML, local CPU for LLM. Great when you have a separate GPU server.
+- **`--gpu --ollama-cpu`**: GPU for transcription, CPU for LLM. Saves GPU VRAM for ML models.
+- **`--gpu`**: Have NVIDIA GPU but prefer a cloud LLM (faster/better summaries with GPT-4, Claude, etc.).
+- **`--cpu`**: No GPU, prefer cloud LLM. Slowest transcription but best summary quality.
+- **`--hosted`**: Remote GPU, cloud LLM. No local ML at all.
+
+## Other Optional Flags
+
+| Flag | What it does |
+|------|-------------|
+| `--garage` | Starts Garage (local S3-compatible storage). Auto-configures bucket, keys, and env vars. |
+| `--caddy` | Starts Caddy reverse proxy on ports 80/443 with self-signed cert. |
+| `--domain DOMAIN` | Use a real domain with Let's Encrypt auto-HTTPS (implies `--caddy`). Requires DNS A record pointing to this server and ports 80/443 open. |
+| `--password PASS` | Enable password authentication with an `admin@localhost` user. Sets `AUTH_BACKEND=password`, `PUBLIC_MODE=false`. See [Enabling Password Authentication](#enabling-password-authentication). |
+| `--build` | Build backend (server, worker, beat) and frontend (web) Docker images from source instead of pulling prebuilt images from the registry. Useful for development or when running a version with local changes. |
+
+Without `--garage`, you **must** provide S3-compatible credentials (the script will prompt interactively or you can pre-fill `server/.env`).
+
+Without `--caddy` or `--domain`, no ports are exposed. Point your own reverse proxy at `web:3000` (frontend) and `server:1250` (API).
+
+**Using a domain (recommended for production):** Point a DNS A record at your server's IP, then pass `--domain your.domain.com`. Caddy will automatically obtain and renew a Let's Encrypt certificate. Ports 80 and 443 must be open.
+
+**Without a domain:** `--caddy` alone uses a self-signed certificate. Browsers will show a security warning that must be accepted.
+
+## What the Script Does
+
+1. **Prerequisites check** — Docker, NVIDIA GPU (if needed), compose file exists
+2. **Generate secrets** — `SECRET_KEY`, `NEXTAUTH_SECRET` via `openssl rand`
+3. **Generate `server/.env`** — From template, sets infrastructure defaults, configures LLM based on mode, enables `PUBLIC_MODE`
+4. **Generate `www/.env`** — Auto-detects server IP, sets URLs
+5. **Storage setup** — Either initializes Garage (bucket, keys, permissions) or prompts for external S3 credentials
+6. **Caddyfile** — Generates domain-specific (Let's Encrypt) or IP-specific (self-signed) configuration
+7. **Build & start** — For `--gpu`, builds the GPU model image from source. For `--cpu` and `--hosted`, no ML container is built. With `--build`, also builds backend and frontend from source; otherwise pulls prebuilt images from the registry
+8. **Auto-detects video platforms** — If `DAILY_API_KEY` is found in `server/.env`, generates `.env.hatchet` (dashboard URL/cookie config), starts Hatchet workflow engine, and generates an API token. If any video platform is configured, enables the Rooms feature
+9. **Health checks** — Waits for each service, pulls Ollama model if needed, warns about missing LLM config
+
+> For a deeper dive into each step, see [How the Self-Hosted Setup Works](selfhosted-architecture.md).
+
+## Configuration Reference
+
+### Server Environment (`server/.env`)
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `DATABASE_URL` | PostgreSQL connection | Auto-set (Docker internal) |
+| `REDIS_HOST` | Redis hostname | Auto-set (`redis`) |
+| `SECRET_KEY` | App secret | Auto-generated |
+| `AUTH_BACKEND` | Authentication method (`none`, `password`, `jwt`) | `none` |
+| `PUBLIC_MODE` | Allow unauthenticated access | `true` |
+| `ADMIN_EMAIL` | Admin email for password auth | *(unset)* |
+| `ADMIN_PASSWORD_HASH` | PBKDF2 hash for password auth | *(unset)* |
+| `WEBRTC_HOST` | IP advertised in WebRTC ICE candidates | Auto-detected (server IP) |
+| `TRANSCRIPT_URL` | Specialized model endpoint | `http://transcription:8000` |
+| `PADDING_BACKEND` | Audio padding backend (`pyav` or `modal`) | `modal` (selfhosted), `pyav` (default) |
+| `PADDING_URL` | Audio padding endpoint (when `PADDING_BACKEND=modal`) | `http://transcription:8000` |
+| `LLM_URL` | OpenAI-compatible LLM endpoint | Auto-set for Ollama modes |
+| `LLM_API_KEY` | LLM API key | `not-needed` for Ollama |
+| `LLM_MODEL` | LLM model name | `qwen2.5:14b` for Ollama (override with `--llm-model`) |
+| `CELERY_BEAT_POLL_INTERVAL` | Override all worker polling intervals (seconds). `0` = use individual defaults | `300` (selfhosted), `0` (other) |
+| `TRANSCRIPT_STORAGE_BACKEND` | Storage backend | `aws` |
+| `TRANSCRIPT_STORAGE_AWS_*` | S3 credentials | Auto-set for Garage |
+| `DAILY_API_KEY` | Daily.co API key (enables live rooms) | *(unset)* |
+| `DAILY_SUBDOMAIN` | Daily.co subdomain | *(unset)* |
+| `DAILYCO_STORAGE_AWS_ACCESS_KEY_ID` | AWS access key for reading Daily's recording bucket | *(unset)* |
+| `DAILYCO_STORAGE_AWS_SECRET_ACCESS_KEY` | AWS secret key for reading Daily's recording bucket | *(unset)* |
+| `HATCHET_CLIENT_TOKEN` | Hatchet API token (auto-generated) | *(unset)* |
+| `HATCHET_CLIENT_SERVER_URL` | Hatchet server URL | Auto-set when Daily.co configured |
+| `HATCHET_CLIENT_HOST_PORT` | Hatchet gRPC address | Auto-set when Daily.co configured |
+| `TRANSCRIPT_FILE_TIMEOUT` | HTTP timeout (seconds) for file transcription requests | `600` (`3600` in CPU mode) |
+| `DIARIZATION_FILE_TIMEOUT` | HTTP timeout (seconds) for file diarization requests | `600` (`3600` in CPU mode) |
+
+### Frontend Environment (`www/.env`)
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `SITE_URL` | Public-facing URL | Auto-detected |
+| `API_URL` | API URL (browser-side) | Same as SITE_URL |
+| `SERVER_API_URL` | API URL (server-side) | `http://server:1250` |
+| `NEXTAUTH_SECRET` | Auth secret | Auto-generated |
+| `FEATURE_REQUIRE_LOGIN` | Require authentication | `false` |
+| `AUTH_PROVIDER` | Auth provider (`authentik` or `credentials`) | *(unset)* |
+| `FEATURE_ROOMS` | Enable meeting rooms UI | Auto-set when video platform configured |
+
+## Storage Options
+
+### Garage (Recommended for Self-Hosted)
+
+Use `--garage` flag. The script automatically:
+- Generates `data/garage.toml` with a random RPC secret
+- Starts the Garage container
+- Creates the `reflector-media` bucket
+- Creates an access key with read/write permissions
+- Writes all S3 credentials to `server/.env`
+
+### External S3 (AWS, MinIO, etc.)
+
+Don't use `--garage`. The script will prompt for:
+- Access Key ID
+- Secret Access Key
+- Bucket Name
+- Region
+- Endpoint URL (for non-AWS like MinIO)
+
+Or pre-fill in `server/.env`:
+```env
+TRANSCRIPT_STORAGE_BACKEND=aws
+TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID=your-key
+TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY=your-secret
+TRANSCRIPT_STORAGE_AWS_BUCKET_NAME=reflector-media
+TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
+# For non-AWS S3 (MinIO, etc.):
+TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://minio:9000
+```
+
+## What Authentication Enables
+
+By default, Reflector runs in **public mode** (`AUTH_BACKEND=none`, `PUBLIC_MODE=true`) — anyone can create and view transcripts without logging in. Transcripts are anonymous (not linked to any user) and cannot be edited or deleted after creation.
+
+Enabling authentication (either password or Authentik) unlocks:
+
+| Feature | Public mode (no auth) | With authentication |
+|---------|----------------------|---------------------|
+| Create transcripts (record/upload) | Yes (anonymous, unowned) | Yes (owned by user) |
+| View transcripts | All transcripts visible | Own transcripts + shared rooms |
+| Edit/delete transcripts | No | Yes (owner only) |
+| Privacy controls (private/semi-private/public) | No (everything public) | Yes (owner can set share mode) |
+| Speaker reassignment and merging | No | Yes (owner only) |
+| Participant management (add/edit/delete) | Read-only | Full CRUD (owner only) |
+| Create rooms | No | Yes |
+| Edit/delete rooms | No | Yes (owner only) |
+| Room calendar (ICS) sync | No | Yes (owner only) |
+| API key management | No | Yes |
+| Post to Zulip | No | Yes (owner only) |
+| Real-time WebSocket notifications | No (connection closed) | Yes (transcript create/delete events) |
+| Meeting host access (Daily.co token) | No | Yes (room owner) |
+
+In short: public mode is "demo-friendly" — great for trying Reflector out. Authentication adds **ownership, privacy, and management** of your data.
+
+## Authentication Options
+
+Reflector supports three authentication backends:
+
+| Backend | `AUTH_BACKEND` | Use case |
+|---------|---------------|----------|
+| `none` | `none` | Public/demo mode, no login required |
+| `password` | `password` | Single-user self-hosted, simple email/password login |
+| `jwt` | `jwt` | Multi-user via Authentik (OAuth2/OIDC) |
+
+## Enabling Password Authentication
+
+The simplest way to add authentication. Creates a single admin user with email/password login — no external identity provider needed.
+
+### Quick setup (recommended)
+
+Pass `--password` to the setup script:
+
+```bash
+./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --password mysecretpass
+```
+
+This automatically:
+- Sets `AUTH_BACKEND=password` and `PUBLIC_MODE=false` in `server/.env`
+- Creates an `admin@localhost` user with the given password
+- Sets `FEATURE_REQUIRE_LOGIN=true` and `AUTH_PROVIDER=credentials` in `www/.env`
+- Provisions the admin user in the database on container startup
+
+### Manual setup
+
+If you prefer to configure manually or want to change the admin email:
+
+1. Generate a password hash:
+   ```bash
+   cd server
+   uv run python -m reflector.tools.create_admin --hash-only --password yourpassword
+   ```
+
+2. Update `server/.env`:
+   ```env
+   AUTH_BACKEND=password
+   PUBLIC_MODE=false
+   ADMIN_EMAIL=admin@yourdomain.com
+   ADMIN_PASSWORD_HASH=pbkdf2:sha256:100000$<salt>$<hash>
+   ```
+
+3. Update `www/.env`:
+   ```env
+   FEATURE_REQUIRE_LOGIN=true
+   AUTH_PROVIDER=credentials
+   ```
+
+4. Restart:
+   ```bash
+   docker compose -f docker-compose.selfhosted.yml down
+   ./scripts/setup-selfhosted.sh <same-flags>
+   ```
+
+### How it works
+
+- The backend issues HS256 JWTs (signed with `SECRET_KEY`) on successful login via `POST /v1/auth/login`
+- Tokens expire after 24 hours; the user must log in again after expiry
+- The frontend shows a login page at `/login` with email and password fields
+- A rate limiter blocks IPs after 10 failed login attempts within 5 minutes
+- The admin user is provisioned automatically on container startup from `ADMIN_EMAIL` and `ADMIN_PASSWORD_HASH` environment variables
+- Passwords are hashed with PBKDF2-SHA256 (100,000 iterations) — no additional dependencies required
+
+### Changing the admin password
+
+```bash
+cd server
+uv run python -m reflector.tools.create_admin --email admin@localhost --password newpassword
+```
+
+Or update `ADMIN_PASSWORD_HASH` in `server/.env` and restart the containers.
+
+## Enabling Authentication (Authentik)
+
+For multi-user deployments with SSO. Requires an external Authentik instance.
+
+By default, authentication is disabled (`AUTH_BACKEND=none`, `FEATURE_REQUIRE_LOGIN=false`). To enable:
+
+1. Deploy an Authentik instance (see [Authentik docs](https://goauthentik.io/docs/installation))
+2. Create an OAuth2/OIDC application for Reflector
+3. Update `server/.env`:
+   ```env
+   AUTH_BACKEND=jwt
+   AUTH_JWT_AUDIENCE=your-client-id
+   ```
+4. Update `www/.env`:
+   ```env
+   FEATURE_REQUIRE_LOGIN=true
+   AUTH_PROVIDER=authentik
+   AUTHENTIK_ISSUER=https://authentik.example.com/application/o/reflector
+   AUTHENTIK_REFRESH_TOKEN_URL=https://authentik.example.com/application/o/token/
+   AUTHENTIK_CLIENT_ID=your-client-id
+   AUTHENTIK_CLIENT_SECRET=your-client-secret
+   ```
+5. Restart: `docker compose -f docker-compose.selfhosted.yml down && ./scripts/setup-selfhosted.sh <same-flags>`
+
+## Enabling Daily.co Live Rooms
+
+Daily.co enables real-time meeting rooms with automatic recording and per-participant
+audio tracks for improved diarization. When configured, the setup script automatically
+starts the Hatchet workflow engine for multitrack recording processing.
+
+### Prerequisites
+
+- **Daily.co account** — Sign up at https://www.daily.co/
+- **API key** — From Daily.co Dashboard → Developers → API Keys
+- **Subdomain** — The `yourname` part of `yourname.daily.co`
+- **AWS S3 bucket** — For Daily.co to store recordings. See [Daily.co recording storage docs](https://docs.daily.co/guides/products/live-streaming-recording/storing-recordings-in-a-custom-s3-bucket)
+- **IAM role ARN** — An AWS IAM role that Daily.co assumes to write recordings to your bucket
+
+### Setup
+
+1. Configure Daily.co env vars in `server/.env` **before** running the setup script:
+
+   ```env
+   DAILY_API_KEY=your-daily-api-key
+   DAILY_SUBDOMAIN=your-subdomain
+   DEFAULT_VIDEO_PLATFORM=daily
+   DAILYCO_STORAGE_AWS_BUCKET_NAME=your-recordings-bucket
+   DAILYCO_STORAGE_AWS_REGION=us-east-1
+   DAILYCO_STORAGE_AWS_ROLE_ARN=arn:aws:iam::123456789:role/DailyCoAccess
+   # Worker credentials for reading/deleting recordings from Daily's S3 bucket.
+   # Required when transcript storage is separate from Daily's bucket
+   # (e.g., selfhosted with Garage or a different S3 account).
+   DAILYCO_STORAGE_AWS_ACCESS_KEY_ID=your-aws-access-key
+   DAILYCO_STORAGE_AWS_SECRET_ACCESS_KEY=your-aws-secret-key
+   ```
+
+   > **Important:** The `DAILYCO_STORAGE_AWS_ACCESS_KEY_ID` and `SECRET_ACCESS_KEY` are AWS IAM
+   > credentials that allow the Hatchet workers to **read and delete** recording files from Daily's
+   > S3 bucket. These are separate from the `ROLE_ARN` (which Daily's API uses to *write* recordings).
+   > Without these keys, multitrack processing will fail with 404 errors when transcript storage
+   > (e.g., Garage) uses different credentials than the Daily recording bucket.
+
+2. Run the setup script as normal:
+
+   ```bash
+   ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
+   ```
+
+   The script detects `DAILY_API_KEY` and automatically:
+   - Starts the Hatchet workflow engine (`hatchet` container)
+   - Starts Hatchet CPU and LLM workers (`hatchet-worker-cpu`, `hatchet-worker-llm`)
+   - Generates a `HATCHET_CLIENT_TOKEN` and saves it to `server/.env`
+   - Sets `HATCHET_CLIENT_SERVER_URL` and `HATCHET_CLIENT_HOST_PORT`
+   - Enables `FEATURE_ROOMS=true` in `www/.env`
+   - Registers Daily.co beat tasks (recording polling, presence reconciliation)
+
+3. (Optional) For faster recording discovery, configure a Daily.co webhook:
+   - In the Daily.co dashboard, add a webhook pointing to `https://your-domain/v1/daily/webhook`
+   - Set `DAILY_WEBHOOK_SECRET` in `server/.env` (the signing secret from Daily.co)
+   - Without webhooks, the system polls the Daily.co API every 15 seconds
+
+### What Gets Started
+
+| Service | Purpose |
+|---------|---------|
+| `hatchet` | Workflow orchestration engine (manages multitrack processing pipelines) |
+| `hatchet-worker-cpu` | CPU-heavy audio tasks (track mixdown, waveform generation) |
+| `hatchet-worker-llm` | Transcription, LLM inference (summaries, topics, titles), orchestration |
+
+### Hatchet Dashboard
+
+The Hatchet workflow engine includes a web dashboard for monitoring workflow runs and debugging. The setup script auto-generates `.env.hatchet` at the project root with the dashboard URL and cookie domain configuration. This file is git-ignored.
+
+- **With Caddy**: Accessible at `https://your-domain:8888` (TLS via Caddy)
+- **Without Caddy**: Accessible at `http://your-ip:8888` (direct port mapping)
+
+### Conditional Beat Tasks
+
+Beat tasks are registered based on which services are configured:
+
+- **Whereby tasks** (only if `WHEREBY_API_KEY` or `AWS_PROCESS_RECORDING_QUEUE_URL`): `process_messages`, `reprocess_failed_recordings`
+- **Daily.co tasks** (only if `DAILY_API_KEY`): `poll_daily_recordings`, `trigger_daily_reconciliation`, `reprocess_failed_daily_recordings`
+- **Platform tasks** (if any video platform configured): `process_meetings`, `sync_all_ics_calendars`, `create_upcoming_meetings`
+- **Always registered**: `cleanup_old_public_data` (if `PUBLIC_MODE`), `healthcheck_ping` (if `HEALTHCHECK_URL`)
+
+## Enabling Real Domain with Let's Encrypt
+
+By default, Caddy uses self-signed certificates. For a real domain:
+
+1. Point your domain's DNS to your server's IP
+2. Ensure ports 80 and 443 are open
+3. Edit `Caddyfile`:
+   ```
+   reflector.example.com {
+       handle /v1/* {
+           reverse_proxy server:1250
+       }
+       handle /health {
+           reverse_proxy server:1250
+       }
+       handle {
+           reverse_proxy web:3000
+       }
+   }
+   ```
+4. Update `www/.env`:
+   ```env
+   SITE_URL=https://reflector.example.com
+   NEXTAUTH_URL=https://reflector.example.com
+   API_URL=https://reflector.example.com
+   ```
+5. Restart Caddy: `docker compose -f docker-compose.selfhosted.yml restart caddy web`
+
+## Worker Polling Frequency
+
+The selfhosted setup defaults all background worker polling intervals to **300 seconds (5 minutes)** to reduce CPU and memory usage. This controls how often the beat scheduler triggers tasks like recording discovery, meeting reconciliation, and calendar sync.
+
+To change the interval, edit `server/.env`:
+
+```env
+# Poll every 60 seconds (more responsive, uses more resources)
+CELERY_BEAT_POLL_INTERVAL=60
+
+# Poll every 5 minutes (default for selfhosted)
+CELERY_BEAT_POLL_INTERVAL=300
+
+# Use individual per-task defaults (production SaaS behavior)
+CELERY_BEAT_POLL_INTERVAL=0
+```
+
+After changing, restart the beat and worker containers:
+
+```bash
+docker compose -f docker-compose.selfhosted.yml restart beat worker
+```
+
+**Affected tasks when `CELERY_BEAT_POLL_INTERVAL` is set:**
+
+| Task | Default (no override) | With override |
+|------|-----------------------|---------------|
+| SQS message polling | 60s | Override value |
+| Daily.co recording discovery | 15s (no webhook) / 180s (webhook) | Override value |
+| Meeting reconciliation | 30s | Override value |
+| ICS calendar sync | 60s | Override value |
+| Upcoming meeting creation | 30s | Override value |
+
+> **Note:** Daily crontab tasks (failed recording reprocessing at 05:00 UTC, public data cleanup at 03:00 UTC) and healthcheck pings (10 min) are **not** affected by this setting.
+
+## Troubleshooting
+
+### Check service status
+```bash
+docker compose -f docker-compose.selfhosted.yml ps
+```
+
+### View logs for a specific service
+```bash
+docker compose -f docker-compose.selfhosted.yml logs server --tail 50
+docker compose -f docker-compose.selfhosted.yml logs gpu --tail 50
+docker compose -f docker-compose.selfhosted.yml logs web --tail 50
+```
+
+### GPU service taking too long
+First start downloads ~1-2GB of ML models. Check progress:
+```bash
+docker compose -f docker-compose.selfhosted.yml logs gpu -f
+```
+
+### Server exits immediately
+Usually a database migration issue. Check:
+```bash
+docker compose -f docker-compose.selfhosted.yml logs server --tail 50
+```
+
+### Caddy certificate issues
+For self-signed certs, your browser will warn. Click Advanced > Proceed.
+For Let's Encrypt, ensure ports 80/443 are open and DNS is pointed correctly.
+
+### File processing timeout on CPU
+CPU transcription and diarization are significantly slower than GPU. A 20-minute audio file can take 20-40 minutes to process on CPU. The setup script automatically sets `TRANSCRIPT_FILE_TIMEOUT=3600` and `DIARIZATION_FILE_TIMEOUT=3600` (1 hour) for `--cpu` mode. If you still hit timeouts with very long files, increase these values in `server/.env`:
+```bash
+# Increase to 2 hours for files over 1 hour
+TRANSCRIPT_FILE_TIMEOUT=7200
+DIARIZATION_FILE_TIMEOUT=7200
+```
+Then restart the worker: `docker compose -f docker-compose.selfhosted.yml restart worker`
+
+### Summaries/topics not generating
+Check LLM configuration:
+```bash
+grep LLM_ server/.env
+```
+If you didn't use `--ollama-gpu` or `--ollama-cpu`, you must set `LLM_URL`, `LLM_API_KEY`, and `LLM_MODEL`.
+
+### Health check from inside containers
+```bash
+docker compose -f docker-compose.selfhosted.yml exec server curl http://localhost:1250/health
+docker compose -f docker-compose.selfhosted.yml exec gpu curl http://localhost:8000/docs
+```
+
+## Updating
+
+```bash
+# Option A: Pull latest prebuilt images and restart
+docker compose -f docker-compose.selfhosted.yml down
+./scripts/setup-selfhosted.sh <same-flags-as-before>
+
+# Option B: Build from source (after git pull) and restart
+git pull
+docker compose -f docker-compose.selfhosted.yml down
+./scripts/setup-selfhosted.sh <same-flags-as-before> --build
+
+# Rebuild only the GPU/CPU model image (picks up model updates)
+docker compose -f docker-compose.selfhosted.yml build gpu  # or cpu
+```
+
+The setup script is idempotent — it won't overwrite existing secrets or env vars that are already set.
+
+## Architecture Overview
+
+```
+                    ┌─────────┐
+  Internet ────────>│  Caddy  │ :80/:443
+                    └────┬────┘
+                         │
+            ┌────────────┼────────────┐
+            │            │            │
+            v            v            │
+       ┌─────────┐  ┌─────────┐      │
+       │   web   │  │ server  │      │
+       │ :3000   │  │ :1250   │      │
+       └─────────┘  └────┬────┘      │
+                         │            │
+                    ┌────┴────┐       │
+                    │ worker  │       │
+                    │  beat   │       │
+                    └────┬────┘       │
+                         │            │
+          ┌──────────────┼────────────┤
+          │              │            │
+          v              v            v
+    ┌───────────┐  ┌─────────┐  ┌─────────┐
+    │ ML models │  │postgres │  │  redis  │
+    │ (varies)  │  │ :5432   │  │ :6379   │
+    └───────────┘  └─────────┘  └─────────┘
+          │
+    ┌─────┴─────┐     ┌─────────┐
+    │  ollama   │     │ garage  │
+    │ (optional)│     │(optional│
+    │ :11435    │     │ S3)     │
+    └───────────┘     └─────────┘
+
+    ┌───────────────────────────────────┐
+    │  Hatchet (optional — Daily.co)   │
+    │  ┌─────────┐  ┌───────────────┐  │
+    │  │ hatchet │  │ hatchet-worker│  │
+    │  │ :8888   │──│  -cpu / -llm  │  │
+    │  └─────────┘  └───────────────┘  │
+    └───────────────────────────────────┘
+
+ML models box varies by mode:
+  --gpu:    Local GPU container (transcription:8000)
+  --cpu:    In-process on server/worker (no container)
+  --hosted: Remote GPU service (user URL)
+```
+
+All services communicate over Docker's internal network. Only Caddy (if enabled) exposes ports to the internet. Hatchet services are only started when `DAILY_API_KEY` is configured.
+

gpu/modal_deployments/deploy-all.sh

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

gpu/modal_deployments/reflector_padding.py

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

gpu/self_hosted/Dockerfile

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

gpu/self_hosted/Dockerfile.cpu

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

gpu/self_hosted/app/auth.py

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

gpu/self_hosted/app/factory.py

@@ -3,6 +3,7 @@ from contextlib import asynccontextmanager
 from fastapi import FastAPI
 
 from .routers.diarization import router as diarization_router
+from .routers.padding import router as padding_router
 from .routers.transcription import router as transcription_router
 from .routers.translation import router as translation_router
 from .services.transcriber import WhisperService
@@ -27,4 +28,5 @@ def create_app() -> FastAPI:
     app.include_router(transcription_router)
     app.include_router(translation_router)
     app.include_router(diarization_router)
+    app.include_router(padding_router)
     return app

gpu/self_hosted/app/routers/padding.py

@@ -0,0 +1,199 @@
+"""
+Audio padding endpoint for selfhosted GPU service.
+
+CPU-intensive audio padding service for adding silence to audio tracks.
+Uses PyAV filter graph (adelay) for precise track synchronization.
+
+IMPORTANT: This padding logic is duplicated from server/reflector/utils/audio_padding.py
+for deployment isolation (self_hosted can't import from server/reflector/). If you modify
+the PyAV filter graph or padding algorithm, you MUST update both:
+  - gpu/self_hosted/app/routers/padding.py (this file)
+  - server/reflector/utils/audio_padding.py
+
+Constants duplicated from server/reflector/utils/audio_constants.py for same reason.
+"""
+
+import logging
+import math
+import os
+import tempfile
+from fractions import Fraction
+
+import av
+import requests
+from av.audio.resampler import AudioResampler
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+
+from ..auth import apikey_auth
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(tags=["padding"])
+
+# ref B0F71CE8-FC59-4AA5-8414-DAFB836DB711
+OPUS_STANDARD_SAMPLE_RATE = 48000
+OPUS_DEFAULT_BIT_RATE = 128000
+
+S3_TIMEOUT = 60
+
+
+class PaddingRequest(BaseModel):
+    track_url: str
+    output_url: str
+    start_time_seconds: float
+    track_index: int
+
+
+class PaddingResponse(BaseModel):
+    size: int
+    cancelled: bool = False
+
+
+@router.post("/pad", dependencies=[Depends(apikey_auth)], response_model=PaddingResponse)
+def pad_track(req: PaddingRequest):
+    """Pad audio track with silence using PyAV adelay filter graph."""
+    if not req.track_url:
+        raise HTTPException(status_code=400, detail="track_url cannot be empty")
+    if not req.output_url:
+        raise HTTPException(status_code=400, detail="output_url cannot be empty")
+    if req.start_time_seconds <= 0:
+        raise HTTPException(
+            status_code=400,
+            detail=f"start_time_seconds must be positive, got {req.start_time_seconds}",
+        )
+    if req.start_time_seconds > 18000:
+        raise HTTPException(
+            status_code=400,
+            detail="start_time_seconds exceeds maximum 18000s (5 hours)",
+        )
+
+    logger.info(
+        "Padding request: track %d, delay=%.3fs", req.track_index, req.start_time_seconds
+    )
+
+    temp_dir = tempfile.mkdtemp()
+    input_path = None
+    output_path = None
+
+    try:
+        # Download source audio
+        logger.info("Downloading track for padding")
+        response = requests.get(req.track_url, stream=True, timeout=S3_TIMEOUT)
+        response.raise_for_status()
+
+        input_path = os.path.join(temp_dir, "track.webm")
+        total_bytes = 0
+        with open(input_path, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+                    total_bytes += len(chunk)
+        logger.info("Track downloaded: %d bytes", total_bytes)
+
+        # Apply padding using PyAV
+        output_path = os.path.join(temp_dir, "padded.webm")
+        delay_ms = math.floor(req.start_time_seconds * 1000)
+        logger.info("Padding track %d with %dms delay using PyAV", req.track_index, delay_ms)
+
+        in_container = av.open(input_path)
+        in_stream = next((s for s in in_container.streams if s.type == "audio"), None)
+        if in_stream is None:
+            in_container.close()
+            raise HTTPException(status_code=400, detail="No audio stream in input")
+
+        with av.open(output_path, "w", format="webm") as out_container:
+            out_stream = out_container.add_stream("libopus", rate=OPUS_STANDARD_SAMPLE_RATE)
+            out_stream.bit_rate = OPUS_DEFAULT_BIT_RATE
+            graph = av.filter.Graph()
+
+            abuf_args = (
+                f"time_base=1/{OPUS_STANDARD_SAMPLE_RATE}:"
+                f"sample_rate={OPUS_STANDARD_SAMPLE_RATE}:"
+                f"sample_fmt=s16:"
+                f"channel_layout=stereo"
+            )
+            src = graph.add("abuffer", args=abuf_args, name="src")
+            aresample_f = graph.add("aresample", args="async=1", name="ares")
+            delays_arg = f"{delay_ms}|{delay_ms}"
+            adelay_f = graph.add(
+                "adelay", args=f"delays={delays_arg}:all=1", name="delay"
+            )
+            sink = graph.add("abuffersink", name="sink")
+
+            src.link_to(aresample_f)
+            aresample_f.link_to(adelay_f)
+            adelay_f.link_to(sink)
+            graph.configure()
+
+            resampler = AudioResampler(
+                format="s16", layout="stereo", rate=OPUS_STANDARD_SAMPLE_RATE
+            )
+
+            for frame in in_container.decode(in_stream):
+                out_frames = resampler.resample(frame) or []
+                for rframe in out_frames:
+                    rframe.sample_rate = OPUS_STANDARD_SAMPLE_RATE
+                    rframe.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
+                    src.push(rframe)
+
+                    while True:
+                        try:
+                            f_out = sink.pull()
+                        except Exception:
+                            break
+                        f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
+                        f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
+                        for packet in out_stream.encode(f_out):
+                            out_container.mux(packet)
+
+            # Flush filter graph
+            src.push(None)
+            while True:
+                try:
+                    f_out = sink.pull()
+                except Exception:
+                    break
+                f_out.sample_rate = OPUS_STANDARD_SAMPLE_RATE
+                f_out.time_base = Fraction(1, OPUS_STANDARD_SAMPLE_RATE)
+                for packet in out_stream.encode(f_out):
+                    out_container.mux(packet)
+
+            # Flush encoder
+            for packet in out_stream.encode(None):
+                out_container.mux(packet)
+
+        in_container.close()
+
+        file_size = os.path.getsize(output_path)
+        logger.info("Padding complete: %d bytes", file_size)
+
+        # Upload padded track
+        logger.info("Uploading padded track to S3")
+        with open(output_path, "rb") as f:
+            upload_response = requests.put(req.output_url, data=f, timeout=S3_TIMEOUT)
+        upload_response.raise_for_status()
+        logger.info("Upload complete: %d bytes", file_size)
+
+        return PaddingResponse(size=file_size)
+
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error("Padding failed for track %d: %s", req.track_index, e, exc_info=True)
+        raise HTTPException(status_code=500, detail=f"Padding failed: {e}") from e
+    finally:
+        if input_path and os.path.exists(input_path):
+            try:
+                os.unlink(input_path)
+            except Exception as e:
+                logger.warning("Failed to cleanup input file: %s", e)
+        if output_path and os.path.exists(output_path):
+            try:
+                os.unlink(output_path)
+            except Exception as e:
+                logger.warning("Failed to cleanup output file: %s", e)
+        try:
+            os.rmdir(temp_dir)
+        except Exception as e:
+            logger.warning("Failed to cleanup temp directory: %s", e)

gpu/self_hosted/app/services/diarizer.py

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

gpu/self_hosted/pyproject.toml

@@ -11,9 +11,11 @@ dependencies = [
     "faster-whisper>=1.1.0",
     "librosa==0.10.1",
     "numpy<2",
-    "silero-vad==5.1.0",
+    "silero-vad==5.1.2",
     "transformers>=4.35.0",
     "sentencepiece",
-    "pyannote.audio==3.1.0",
+    "pyannote.audio==3.4.0",
+    "pytorch-lightning<2.6",
     "torchaudio>=2.3.0",
+    "av>=13.1.0",
 ]

gpu/self_hosted/sequoia.config

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

gpu/self_hosted/uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 2
+revision = 3
 requires-python = ">=3.12"
 
 [[package]]
@@ -13,7 +13,7 @@ wheels = [
 
 [[package]]
 name = "aiohttp"
-version = "3.12.15"
+version = "3.13.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohappyeyeballs" },
@@ -24,42 +24,76 @@ dependencies = [
     { name = "propcache" },
     { name = "yarl" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/9b/e7/d92a237d8802ca88483906c388f7c201bbe96cd80a165ffd0ac2f6a8d59f/aiohttp-3.12.15.tar.gz", hash = "sha256:4fc61385e9c98d72fcdf47e6dd81833f47b2f77c114c29cd64a361be57a763a2", size = 7823716, upload-time = "2025-07-29T05:52:32.215Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/50/42/32cf8e7704ceb4481406eb87161349abb46a57fee3f008ba9cb610968646/aiohttp-3.13.3.tar.gz", hash = "sha256:a949eee43d3782f2daae4f4a2819b2cb9b0c5d3b7f7a927067cc84dafdbb9f88", size = 7844556, upload-time = "2026-01-03T17:33:05.204Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/63/97/77cb2450d9b35f517d6cf506256bf4f5bda3f93a66b4ad64ba7fc917899c/aiohttp-3.12.15-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:802d3868f5776e28f7bf69d349c26fc0efadb81676d0afa88ed00d98a26340b7", size = 702333, upload-time = "2025-07-29T05:50:46.507Z" },
-    { url = "https://files.pythonhosted.org/packages/83/6d/0544e6b08b748682c30b9f65640d006e51f90763b41d7c546693bc22900d/aiohttp-3.12.15-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f2800614cd560287be05e33a679638e586a2d7401f4ddf99e304d98878c29444", size = 476948, upload-time = "2025-07-29T05:50:48.067Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/1d/c8c40e611e5094330284b1aea8a4b02ca0858f8458614fa35754cab42b9c/aiohttp-3.12.15-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8466151554b593909d30a0a125d638b4e5f3836e5aecde85b66b80ded1cb5b0d", size = 469787, upload-time = "2025-07-29T05:50:49.669Z" },
-    { url = "https://files.pythonhosted.org/packages/38/7d/b76438e70319796bfff717f325d97ce2e9310f752a267bfdf5192ac6082b/aiohttp-3.12.15-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e5a495cb1be69dae4b08f35a6c4579c539e9b5706f606632102c0f855bcba7c", size = 1716590, upload-time = "2025-07-29T05:50:51.368Z" },
-    { url = "https://files.pythonhosted.org/packages/79/b1/60370d70cdf8b269ee1444b390cbd72ce514f0d1cd1a715821c784d272c9/aiohttp-3.12.15-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:6404dfc8cdde35c69aaa489bb3542fb86ef215fc70277c892be8af540e5e21c0", size = 1699241, upload-time = "2025-07-29T05:50:53.628Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/2b/4968a7b8792437ebc12186db31523f541943e99bda8f30335c482bea6879/aiohttp-3.12.15-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3ead1c00f8521a5c9070fcb88f02967b1d8a0544e6d85c253f6968b785e1a2ab", size = 1754335, upload-time = "2025-07-29T05:50:55.394Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/c1/49524ed553f9a0bec1a11fac09e790f49ff669bcd14164f9fab608831c4d/aiohttp-3.12.15-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6990ef617f14450bc6b34941dba4f12d5613cbf4e33805932f853fbd1cf18bfb", size = 1800491, upload-time = "2025-07-29T05:50:57.202Z" },
-    { url = "https://files.pythonhosted.org/packages/de/5e/3bf5acea47a96a28c121b167f5ef659cf71208b19e52a88cdfa5c37f1fcc/aiohttp-3.12.15-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd736ed420f4db2b8148b52b46b88ed038d0354255f9a73196b7bbce3ea97545", size = 1719929, upload-time = "2025-07-29T05:50:59.192Z" },
-    { url = "https://files.pythonhosted.org/packages/39/94/8ae30b806835bcd1cba799ba35347dee6961a11bd507db634516210e91d8/aiohttp-3.12.15-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c5092ce14361a73086b90c6efb3948ffa5be2f5b6fbcf52e8d8c8b8848bb97c", size = 1635733, upload-time = "2025-07-29T05:51:01.394Z" },
-    { url = "https://files.pythonhosted.org/packages/7a/46/06cdef71dd03acd9da7f51ab3a9107318aee12ad38d273f654e4f981583a/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:aaa2234bb60c4dbf82893e934d8ee8dea30446f0647e024074237a56a08c01bd", size = 1696790, upload-time = "2025-07-29T05:51:03.657Z" },
-    { url = "https://files.pythonhosted.org/packages/02/90/6b4cfaaf92ed98d0ec4d173e78b99b4b1a7551250be8937d9d67ecb356b4/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:6d86a2fbdd14192e2f234a92d3b494dd4457e683ba07e5905a0b3ee25389ac9f", size = 1718245, upload-time = "2025-07-29T05:51:05.911Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/e6/2593751670fa06f080a846f37f112cbe6f873ba510d070136a6ed46117c6/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a041e7e2612041a6ddf1c6a33b883be6a421247c7afd47e885969ee4cc58bd8d", size = 1658899, upload-time = "2025-07-29T05:51:07.753Z" },
-    { url = "https://files.pythonhosted.org/packages/8f/28/c15bacbdb8b8eb5bf39b10680d129ea7410b859e379b03190f02fa104ffd/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5015082477abeafad7203757ae44299a610e89ee82a1503e3d4184e6bafdd519", size = 1738459, upload-time = "2025-07-29T05:51:09.56Z" },
-    { url = "https://files.pythonhosted.org/packages/00/de/c269cbc4faa01fb10f143b1670633a8ddd5b2e1ffd0548f7aa49cb5c70e2/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:56822ff5ddfd1b745534e658faba944012346184fbfe732e0d6134b744516eea", size = 1766434, upload-time = "2025-07-29T05:51:11.423Z" },
-    { url = "https://files.pythonhosted.org/packages/52/b0/4ff3abd81aa7d929b27d2e1403722a65fc87b763e3a97b3a2a494bfc63bc/aiohttp-3.12.15-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b2acbbfff69019d9014508c4ba0401822e8bae5a5fdc3b6814285b71231b60f3", size = 1726045, upload-time = "2025-07-29T05:51:13.689Z" },
-    { url = "https://files.pythonhosted.org/packages/71/16/949225a6a2dd6efcbd855fbd90cf476052e648fb011aa538e3b15b89a57a/aiohttp-3.12.15-cp312-cp312-win32.whl", hash = "sha256:d849b0901b50f2185874b9a232f38e26b9b3d4810095a7572eacea939132d4e1", size = 423591, upload-time = "2025-07-29T05:51:15.452Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/d8/fa65d2a349fe938b76d309db1a56a75c4fb8cc7b17a398b698488a939903/aiohttp-3.12.15-cp312-cp312-win_amd64.whl", hash = "sha256:b390ef5f62bb508a9d67cb3bba9b8356e23b3996da7062f1a57ce1a79d2b3d34", size = 450266, upload-time = "2025-07-29T05:51:17.239Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/33/918091abcf102e39d15aba2476ad9e7bd35ddb190dcdd43a854000d3da0d/aiohttp-3.12.15-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:9f922ffd05034d439dde1c77a20461cf4a1b0831e6caa26151fe7aa8aaebc315", size = 696741, upload-time = "2025-07-29T05:51:19.021Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/2a/7495a81e39a998e400f3ecdd44a62107254803d1681d9189be5c2e4530cd/aiohttp-3.12.15-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:2ee8a8ac39ce45f3e55663891d4b1d15598c157b4d494a4613e704c8b43112cd", size = 474407, upload-time = "2025-07-29T05:51:21.165Z" },
-    { url = "https://files.pythonhosted.org/packages/49/fc/a9576ab4be2dcbd0f73ee8675d16c707cfc12d5ee80ccf4015ba543480c9/aiohttp-3.12.15-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3eae49032c29d356b94eee45a3f39fdf4b0814b397638c2f718e96cfadf4c4e4", size = 466703, upload-time = "2025-07-29T05:51:22.948Z" },
-    { url = "https://files.pythonhosted.org/packages/09/2f/d4bcc8448cf536b2b54eed48f19682031ad182faa3a3fee54ebe5b156387/aiohttp-3.12.15-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b97752ff12cc12f46a9b20327104448042fce5c33a624f88c18f66f9368091c7", size = 1705532, upload-time = "2025-07-29T05:51:25.211Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/f3/59406396083f8b489261e3c011aa8aee9df360a96ac8fa5c2e7e1b8f0466/aiohttp-3.12.15-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:894261472691d6fe76ebb7fcf2e5870a2ac284c7406ddc95823c8598a1390f0d", size = 1686794, upload-time = "2025-07-29T05:51:27.145Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/71/164d194993a8d114ee5656c3b7ae9c12ceee7040d076bf7b32fb98a8c5c6/aiohttp-3.12.15-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5fa5d9eb82ce98959fc1031c28198b431b4d9396894f385cb63f1e2f3f20ca6b", size = 1738865, upload-time = "2025-07-29T05:51:29.366Z" },
-    { url = "https://files.pythonhosted.org/packages/1c/00/d198461b699188a93ead39cb458554d9f0f69879b95078dce416d3209b54/aiohttp-3.12.15-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f0fa751efb11a541f57db59c1dd821bec09031e01452b2b6217319b3a1f34f3d", size = 1788238, upload-time = "2025-07-29T05:51:31.285Z" },
-    { url = "https://files.pythonhosted.org/packages/85/b8/9e7175e1fa0ac8e56baa83bf3c214823ce250d0028955dfb23f43d5e61fd/aiohttp-3.12.15-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5346b93e62ab51ee2a9d68e8f73c7cf96ffb73568a23e683f931e52450e4148d", size = 1710566, upload-time = "2025-07-29T05:51:33.219Z" },
-    { url = "https://files.pythonhosted.org/packages/59/e4/16a8eac9df39b48ae102ec030fa9f726d3570732e46ba0c592aeeb507b93/aiohttp-3.12.15-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:049ec0360f939cd164ecbfd2873eaa432613d5e77d6b04535e3d1fbae5a9e645", size = 1624270, upload-time = "2025-07-29T05:51:35.195Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/f8/cd84dee7b6ace0740908fd0af170f9fab50c2a41ccbc3806aabcb1050141/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:b52dcf013b57464b6d1e51b627adfd69a8053e84b7103a7cd49c030f9ca44461", size = 1677294, upload-time = "2025-07-29T05:51:37.215Z" },
-    { url = "https://files.pythonhosted.org/packages/ce/42/d0f1f85e50d401eccd12bf85c46ba84f947a84839c8a1c2c5f6e8ab1eb50/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:9b2af240143dd2765e0fb661fd0361a1b469cab235039ea57663cda087250ea9", size = 1708958, upload-time = "2025-07-29T05:51:39.328Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/6b/f6fa6c5790fb602538483aa5a1b86fcbad66244997e5230d88f9412ef24c/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:ac77f709a2cde2cc71257ab2d8c74dd157c67a0558a0d2799d5d571b4c63d44d", size = 1651553, upload-time = "2025-07-29T05:51:41.356Z" },
-    { url = "https://files.pythonhosted.org/packages/04/36/a6d36ad545fa12e61d11d1932eef273928b0495e6a576eb2af04297fdd3c/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:47f6b962246f0a774fbd3b6b7be25d59b06fdb2f164cf2513097998fc6a29693", size = 1727688, upload-time = "2025-07-29T05:51:43.452Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/c8/f195e5e06608a97a4e52c5d41c7927301bf757a8e8bb5bbf8cef6c314961/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:760fb7db442f284996e39cf9915a94492e1896baac44f06ae551974907922b64", size = 1761157, upload-time = "2025-07-29T05:51:45.643Z" },
-    { url = "https://files.pythonhosted.org/packages/05/6a/ea199e61b67f25ba688d3ce93f63b49b0a4e3b3d380f03971b4646412fc6/aiohttp-3.12.15-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ad702e57dc385cae679c39d318def49aef754455f237499d5b99bea4ef582e51", size = 1710050, upload-time = "2025-07-29T05:51:48.203Z" },
-    { url = "https://files.pythonhosted.org/packages/b4/2e/ffeb7f6256b33635c29dbed29a22a723ff2dd7401fff42ea60cf2060abfb/aiohttp-3.12.15-cp313-cp313-win32.whl", hash = "sha256:f813c3e9032331024de2eb2e32a88d86afb69291fbc37a3a3ae81cc9917fb3d0", size = 422647, upload-time = "2025-07-29T05:51:50.718Z" },
-    { url = "https://files.pythonhosted.org/packages/1b/8e/78ee35774201f38d5e1ba079c9958f7629b1fd079459aea9467441dbfbf5/aiohttp-3.12.15-cp313-cp313-win_amd64.whl", hash = "sha256:1a649001580bdb37c6fdb1bebbd7e3bc688e8ec2b5c6f52edbb664662b17dc84", size = 449067, upload-time = "2025-07-29T05:51:52.549Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/be/4fc11f202955a69e0db803a12a062b8379c970c7c84f4882b6da17337cc1/aiohttp-3.13.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:b903a4dfee7d347e2d87697d0713be59e0b87925be030c9178c5faa58ea58d5c", size = 739732, upload-time = "2026-01-03T17:30:14.23Z" },
+    { url = "https://files.pythonhosted.org/packages/97/2c/621d5b851f94fa0bb7430d6089b3aa970a9d9b75196bc93bb624b0db237a/aiohttp-3.13.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a45530014d7a1e09f4a55f4f43097ba0fd155089372e105e4bff4ca76cb1b168", size = 494293, upload-time = "2026-01-03T17:30:15.96Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/43/4be01406b78e1be8320bb8316dc9c42dbab553d281c40364e0f862d5661c/aiohttp-3.13.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:27234ef6d85c914f9efeb77ff616dbf4ad2380be0cda40b4db086ffc7ddd1b7d", size = 493533, upload-time = "2026-01-03T17:30:17.431Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/a8/5a35dc56a06a2c90d4742cbf35294396907027f80eea696637945a106f25/aiohttp-3.13.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d32764c6c9aafb7fb55366a224756387cd50bfa720f32b88e0e6fa45b27dcf29", size = 1737839, upload-time = "2026-01-03T17:30:19.422Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/62/4b9eeb331da56530bf2e198a297e5303e1c1ebdceeb00fe9b568a65c5a0c/aiohttp-3.13.3-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:b1a6102b4d3ebc07dad44fbf07b45bb600300f15b552ddf1851b5390202ea2e3", size = 1703932, upload-time = "2026-01-03T17:30:21.756Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/f6/af16887b5d419e6a367095994c0b1332d154f647e7dc2bd50e61876e8e3d/aiohttp-3.13.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c014c7ea7fb775dd015b2d3137378b7be0249a448a1612268b5a90c2d81de04d", size = 1771906, upload-time = "2026-01-03T17:30:23.932Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/83/397c634b1bcc24292fa1e0c7822800f9f6569e32934bdeef09dae7992dfb/aiohttp-3.13.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2b8d8ddba8f95ba17582226f80e2de99c7a7948e66490ef8d947e272a93e9463", size = 1871020, upload-time = "2026-01-03T17:30:26Z" },
+    { url = "https://files.pythonhosted.org/packages/86/f6/a62cbbf13f0ac80a70f71b1672feba90fdb21fd7abd8dbf25c0105fb6fa3/aiohttp-3.13.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9ae8dd55c8e6c4257eae3a20fd2c8f41edaea5992ed67156642493b8daf3cecc", size = 1755181, upload-time = "2026-01-03T17:30:27.554Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/87/20a35ad487efdd3fba93d5843efdfaa62d2f1479eaafa7453398a44faf13/aiohttp-3.13.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:01ad2529d4b5035578f5081606a465f3b814c542882804e2e8cda61adf5c71bf", size = 1561794, upload-time = "2026-01-03T17:30:29.254Z" },
+    { url = "https://files.pythonhosted.org/packages/de/95/8fd69a66682012f6716e1bc09ef8a1a2a91922c5725cb904689f112309c4/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:bb4f7475e359992b580559e008c598091c45b5088f28614e855e42d39c2f1033", size = 1697900, upload-time = "2026-01-03T17:30:31.033Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/66/7b94b3b5ba70e955ff597672dad1691333080e37f50280178967aff68657/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:c19b90316ad3b24c69cd78d5c9b4f3aa4497643685901185b65166293d36a00f", size = 1728239, upload-time = "2026-01-03T17:30:32.703Z" },
+    { url = "https://files.pythonhosted.org/packages/47/71/6f72f77f9f7d74719692ab65a2a0252584bf8d5f301e2ecb4c0da734530a/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:96d604498a7c782cb15a51c406acaea70d8c027ee6b90c569baa6e7b93073679", size = 1740527, upload-time = "2026-01-03T17:30:34.695Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/b4/75ec16cbbd5c01bdaf4a05b19e103e78d7ce1ef7c80867eb0ace42ff4488/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:084911a532763e9d3dd95adf78a78f4096cd5f58cdc18e6fdbc1b58417a45423", size = 1554489, upload-time = "2026-01-03T17:30:36.864Z" },
+    { url = "https://files.pythonhosted.org/packages/52/8f/bc518c0eea29f8406dcf7ed1f96c9b48e3bc3995a96159b3fc11f9e08321/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:7a4a94eb787e606d0a09404b9c38c113d3b099d508021faa615d70a0131907ce", size = 1767852, upload-time = "2026-01-03T17:30:39.433Z" },
+    { url = "https://files.pythonhosted.org/packages/9d/f2/a07a75173124f31f11ea6f863dc44e6f09afe2bca45dd4e64979490deab1/aiohttp-3.13.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:87797e645d9d8e222e04160ee32aa06bc5c163e8499f24db719e7852ec23093a", size = 1722379, upload-time = "2026-01-03T17:30:41.081Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/4a/1a3fee7c21350cac78e5c5cef711bac1b94feca07399f3d406972e2d8fcd/aiohttp-3.13.3-cp312-cp312-win32.whl", hash = "sha256:b04be762396457bef43f3597c991e192ee7da460a4953d7e647ee4b1c28e7046", size = 428253, upload-time = "2026-01-03T17:30:42.644Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/b7/76175c7cb4eb73d91ad63c34e29fc4f77c9386bba4a65b53ba8e05ee3c39/aiohttp-3.13.3-cp312-cp312-win_amd64.whl", hash = "sha256:e3531d63d3bdfa7e3ac5e9b27b2dd7ec9df3206a98e0b3445fa906f233264c57", size = 455407, upload-time = "2026-01-03T17:30:44.195Z" },
+    { url = "https://files.pythonhosted.org/packages/97/8a/12ca489246ca1faaf5432844adbfce7ff2cc4997733e0af120869345643a/aiohttp-3.13.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:5dff64413671b0d3e7d5918ea490bdccb97a4ad29b3f311ed423200b2203e01c", size = 734190, upload-time = "2026-01-03T17:30:45.832Z" },
+    { url = "https://files.pythonhosted.org/packages/32/08/de43984c74ed1fca5c014808963cc83cb00d7bb06af228f132d33862ca76/aiohttp-3.13.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:87b9aab6d6ed88235aa2970294f496ff1a1f9adcd724d800e9b952395a80ffd9", size = 491783, upload-time = "2026-01-03T17:30:47.466Z" },
+    { url = "https://files.pythonhosted.org/packages/17/f8/8dd2cf6112a5a76f81f81a5130c57ca829d101ad583ce57f889179accdda/aiohttp-3.13.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:425c126c0dc43861e22cb1c14ba4c8e45d09516d0a3ae0a3f7494b79f5f233a3", size = 490704, upload-time = "2026-01-03T17:30:49.373Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/40/a46b03ca03936f832bc7eaa47cfbb1ad012ba1be4790122ee4f4f8cba074/aiohttp-3.13.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7f9120f7093c2a32d9647abcaf21e6ad275b4fbec5b55969f978b1a97c7c86bf", size = 1720652, upload-time = "2026-01-03T17:30:50.974Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/7e/917fe18e3607af92657e4285498f500dca797ff8c918bd7d90b05abf6c2a/aiohttp-3.13.3-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:697753042d57f4bf7122cab985bf15d0cef23c770864580f5af4f52023a56bd6", size = 1692014, upload-time = "2026-01-03T17:30:52.729Z" },
+    { url = "https://files.pythonhosted.org/packages/71/b6/cefa4cbc00d315d68973b671cf105b21a609c12b82d52e5d0c9ae61d2a09/aiohttp-3.13.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6de499a1a44e7de70735d0b39f67c8f25eb3d91eb3103be99ca0fa882cdd987d", size = 1759777, upload-time = "2026-01-03T17:30:54.537Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/e3/e06ee07b45e59e6d81498b591fc589629be1553abb2a82ce33efe2a7b068/aiohttp-3.13.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:37239e9f9a7ea9ac5bf6b92b0260b01f8a22281996da609206a84df860bc1261", size = 1861276, upload-time = "2026-01-03T17:30:56.512Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/24/75d274228acf35ceeb2850b8ce04de9dd7355ff7a0b49d607ee60c29c518/aiohttp-3.13.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f76c1e3fe7d7c8afad7ed193f89a292e1999608170dcc9751a7462a87dfd5bc0", size = 1743131, upload-time = "2026-01-03T17:30:58.256Z" },
+    { url = "https://files.pythonhosted.org/packages/04/98/3d21dde21889b17ca2eea54fdcff21b27b93f45b7bb94ca029c31ab59dc3/aiohttp-3.13.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fc290605db2a917f6e81b0e1e0796469871f5af381ce15c604a3c5c7e51cb730", size = 1556863, upload-time = "2026-01-03T17:31:00.445Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/84/da0c3ab1192eaf64782b03971ab4055b475d0db07b17eff925e8c93b3aa5/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4021b51936308aeea0367b8f006dc999ca02bc118a0cc78c303f50a2ff6afb91", size = 1682793, upload-time = "2026-01-03T17:31:03.024Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/0f/5802ada182f575afa02cbd0ec5180d7e13a402afb7c2c03a9aa5e5d49060/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:49a03727c1bba9a97d3e93c9f93ca03a57300f484b6e935463099841261195d3", size = 1716676, upload-time = "2026-01-03T17:31:04.842Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/8c/714d53bd8b5a4560667f7bbbb06b20c2382f9c7847d198370ec6526af39c/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:3d9908a48eb7416dc1f4524e69f1d32e5d90e3981e4e37eb0aa1cd18f9cfa2a4", size = 1733217, upload-time = "2026-01-03T17:31:06.868Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/79/e2176f46d2e963facea939f5be2d26368ce543622be6f00a12844d3c991f/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:2712039939ec963c237286113c68dbad80a82a4281543f3abf766d9d73228998", size = 1552303, upload-time = "2026-01-03T17:31:08.958Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/6a/28ed4dea1759916090587d1fe57087b03e6c784a642b85ef48217b0277ae/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:7bfdc049127717581866fa4708791220970ce291c23e28ccf3922c700740fdc0", size = 1763673, upload-time = "2026-01-03T17:31:10.676Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/35/4a3daeb8b9fab49240d21c04d50732313295e4bd813a465d840236dd0ce1/aiohttp-3.13.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:8057c98e0c8472d8846b9c79f56766bcc57e3e8ac7bfd510482332366c56c591", size = 1721120, upload-time = "2026-01-03T17:31:12.575Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/9f/d643bb3c5fb99547323e635e251c609fbbc660d983144cfebec529e09264/aiohttp-3.13.3-cp313-cp313-win32.whl", hash = "sha256:1449ceddcdbcf2e0446957863af03ebaaa03f94c090f945411b61269e2cb5daf", size = 427383, upload-time = "2026-01-03T17:31:14.382Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/f1/ab0395f8a79933577cdd996dd2f9aa6014af9535f65dddcf88204682fe62/aiohttp-3.13.3-cp313-cp313-win_amd64.whl", hash = "sha256:693781c45a4033d31d4187d2436f5ac701e7bbfe5df40d917736108c1cc7436e", size = 453899, upload-time = "2026-01-03T17:31:15.958Z" },
+    { url = "https://files.pythonhosted.org/packages/99/36/5b6514a9f5d66f4e2597e40dea2e3db271e023eb7a5d22defe96ba560996/aiohttp-3.13.3-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:ea37047c6b367fd4bd632bff8077449b8fa034b69e812a18e0132a00fae6e808", size = 737238, upload-time = "2026-01-03T17:31:17.909Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/49/459327f0d5bcd8c6c9ca69e60fdeebc3622861e696490d8674a6d0cb90a6/aiohttp-3.13.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:6fc0e2337d1a4c3e6acafda6a78a39d4c14caea625124817420abceed36e2415", size = 492292, upload-time = "2026-01-03T17:31:19.919Z" },
+    { url = "https://files.pythonhosted.org/packages/e8/0b/b97660c5fd05d3495b4eb27f2d0ef18dc1dc4eff7511a9bf371397ff0264/aiohttp-3.13.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c685f2d80bb67ca8c3837823ad76196b3694b0159d232206d1e461d3d434666f", size = 493021, upload-time = "2026-01-03T17:31:21.636Z" },
+    { url = "https://files.pythonhosted.org/packages/54/d4/438efabdf74e30aeceb890c3290bbaa449780583b1270b00661126b8aae4/aiohttp-3.13.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:48e377758516d262bde50c2584fc6c578af272559c409eecbdd2bae1601184d6", size = 1717263, upload-time = "2026-01-03T17:31:23.296Z" },
+    { url = "https://files.pythonhosted.org/packages/71/f2/7bddc7fd612367d1459c5bcf598a9e8f7092d6580d98de0e057eb42697ad/aiohttp-3.13.3-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:34749271508078b261c4abb1767d42b8d0c0cc9449c73a4df494777dc55f0687", size = 1669107, upload-time = "2026-01-03T17:31:25.334Z" },
+    { url = "https://files.pythonhosted.org/packages/00/5a/1aeaecca40e22560f97610a329e0e5efef5e0b5afdf9f857f0d93839ab2e/aiohttp-3.13.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:82611aeec80eb144416956ec85b6ca45a64d76429c1ed46ae1b5f86c6e0c9a26", size = 1760196, upload-time = "2026-01-03T17:31:27.394Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/f8/0ff6992bea7bd560fc510ea1c815f87eedd745fe035589c71ce05612a19a/aiohttp-3.13.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2fff83cfc93f18f215896e3a190e8e5cb413ce01553901aca925176e7568963a", size = 1843591, upload-time = "2026-01-03T17:31:29.238Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/d1/e30e537a15f53485b61f5be525f2157da719819e8377298502aebac45536/aiohttp-3.13.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bbe7d4cecacb439e2e2a8a1a7b935c25b812af7a5fd26503a66dadf428e79ec1", size = 1720277, upload-time = "2026-01-03T17:31:31.053Z" },
+    { url = "https://files.pythonhosted.org/packages/84/45/23f4c451d8192f553d38d838831ebbc156907ea6e05557f39563101b7717/aiohttp-3.13.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b928f30fe49574253644b1ca44b1b8adbd903aa0da4b9054a6c20fc7f4092a25", size = 1548575, upload-time = "2026-01-03T17:31:32.87Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/ed/0a42b127a43712eda7807e7892c083eadfaf8429ca8fb619662a530a3aab/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7b5e8fe4de30df199155baaf64f2fcd604f4c678ed20910db8e2c66dc4b11603", size = 1679455, upload-time = "2026-01-03T17:31:34.76Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/b5/c05f0c2b4b4fe2c9d55e73b6d3ed4fd6c9dc2684b1d81cbdf77e7fad9adb/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:8542f41a62bcc58fc7f11cf7c90e0ec324ce44950003feb70640fc2a9092c32a", size = 1687417, upload-time = "2026-01-03T17:31:36.699Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/6b/915bc5dad66aef602b9e459b5a973529304d4e89ca86999d9d75d80cbd0b/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:5e1d8c8b8f1d91cd08d8f4a3c2b067bfca6ec043d3ff36de0f3a715feeedf926", size = 1729968, upload-time = "2026-01-03T17:31:38.622Z" },
+    { url = "https://files.pythonhosted.org/packages/11/3b/e84581290a9520024a08640b63d07673057aec5ca548177a82026187ba73/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:90455115e5da1c3c51ab619ac57f877da8fd6d73c05aacd125c5ae9819582aba", size = 1545690, upload-time = "2026-01-03T17:31:40.57Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/04/0c3655a566c43fd647c81b895dfe361b9f9ad6d58c19309d45cff52d6c3b/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:042e9e0bcb5fba81886c8b4fbb9a09d6b8a00245fd8d88e4d989c1f96c74164c", size = 1746390, upload-time = "2026-01-03T17:31:42.857Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/53/71165b26978f719c3419381514c9690bd5980e764a09440a10bb816ea4ab/aiohttp-3.13.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2eb752b102b12a76ca02dff751a801f028b4ffbbc478840b473597fc91a9ed43", size = 1702188, upload-time = "2026-01-03T17:31:44.984Z" },
+    { url = "https://files.pythonhosted.org/packages/29/a7/cbe6c9e8e136314fa1980da388a59d2f35f35395948a08b6747baebb6aa6/aiohttp-3.13.3-cp314-cp314-win32.whl", hash = "sha256:b556c85915d8efaed322bf1bdae9486aa0f3f764195a0fb6ee962e5c71ef5ce1", size = 433126, upload-time = "2026-01-03T17:31:47.463Z" },
+    { url = "https://files.pythonhosted.org/packages/de/56/982704adea7d3b16614fc5936014e9af85c0e34b58f9046655817f04306e/aiohttp-3.13.3-cp314-cp314-win_amd64.whl", hash = "sha256:9bf9f7a65e7aa20dd764151fb3d616c81088f91f8df39c3893a536e279b4b984", size = 459128, upload-time = "2026-01-03T17:31:49.2Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/2a/3c79b638a9c3d4658d345339d22070241ea341ed4e07b5ac60fb0f418003/aiohttp-3.13.3-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:05861afbbec40650d8a07ea324367cb93e9e8cc7762e04dd4405df99fa65159c", size = 769512, upload-time = "2026-01-03T17:31:51.134Z" },
+    { url = "https://files.pythonhosted.org/packages/29/b9/3e5014d46c0ab0db8707e0ac2711ed28c4da0218c358a4e7c17bae0d8722/aiohttp-3.13.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:2fc82186fadc4a8316768d61f3722c230e2c1dcab4200d52d2ebdf2482e47592", size = 506444, upload-time = "2026-01-03T17:31:52.85Z" },
+    { url = "https://files.pythonhosted.org/packages/90/03/c1d4ef9a054e151cd7839cdc497f2638f00b93cbe8043983986630d7a80c/aiohttp-3.13.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0add0900ff220d1d5c5ebbf99ed88b0c1bbf87aa7e4262300ed1376a6b13414f", size = 510798, upload-time = "2026-01-03T17:31:54.91Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/76/8c1e5abbfe8e127c893fe7ead569148a4d5a799f7cf958d8c09f3eedf097/aiohttp-3.13.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:568f416a4072fbfae453dcf9a99194bbb8bdeab718e08ee13dfa2ba0e4bebf29", size = 1868835, upload-time = "2026-01-03T17:31:56.733Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/ac/984c5a6f74c363b01ff97adc96a3976d9c98940b8969a1881575b279ac5d/aiohttp-3.13.3-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:add1da70de90a2569c5e15249ff76a631ccacfe198375eead4aadf3b8dc849dc", size = 1720486, upload-time = "2026-01-03T17:31:58.65Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/9a/b7039c5f099c4eb632138728828b33428585031a1e658d693d41d07d89d1/aiohttp-3.13.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:10b47b7ba335d2e9b1239fa571131a87e2d8ec96b333e68b2a305e7a98b0bae2", size = 1847951, upload-time = "2026-01-03T17:32:00.989Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/02/3bec2b9a1ba3c19ff89a43a19324202b8eb187ca1e928d8bdac9bbdddebd/aiohttp-3.13.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:3dd4dce1c718e38081c8f35f323209d4c1df7d4db4bab1b5c88a6b4d12b74587", size = 1941001, upload-time = "2026-01-03T17:32:03.122Z" },
+    { url = "https://files.pythonhosted.org/packages/37/df/d879401cedeef27ac4717f6426c8c36c3091c6e9f08a9178cc87549c537f/aiohttp-3.13.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:34bac00a67a812570d4a460447e1e9e06fae622946955f939051e7cc895cfab8", size = 1797246, upload-time = "2026-01-03T17:32:05.255Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/15/be122de1f67e6953add23335c8ece6d314ab67c8bebb3f181063010795a7/aiohttp-3.13.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a19884d2ee70b06d9204b2727a7b9f983d0c684c650254679e716b0b77920632", size = 1627131, upload-time = "2026-01-03T17:32:07.607Z" },
+    { url = "https://files.pythonhosted.org/packages/12/12/70eedcac9134cfa3219ab7af31ea56bc877395b1ac30d65b1bc4b27d0438/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:5f8ca7f2bb6ba8348a3614c7918cc4bb73268c5ac2a207576b7afea19d3d9f64", size = 1795196, upload-time = "2026-01-03T17:32:09.59Z" },
+    { url = "https://files.pythonhosted.org/packages/32/11/b30e1b1cd1f3054af86ebe60df96989c6a414dd87e27ad16950eee420bea/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:b0d95340658b9d2f11d9697f59b3814a9d3bb4b7a7c20b131df4bcef464037c0", size = 1782841, upload-time = "2026-01-03T17:32:11.445Z" },
+    { url = "https://files.pythonhosted.org/packages/88/0d/d98a9367b38912384a17e287850f5695c528cff0f14f791ce8ee2e4f7796/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a1e53262fd202e4b40b70c3aff944a8155059beedc8a89bba9dc1f9ef06a1b56", size = 1795193, upload-time = "2026-01-03T17:32:13.705Z" },
+    { url = "https://files.pythonhosted.org/packages/43/a5/a2dfd1f5ff5581632c7f6a30e1744deda03808974f94f6534241ef60c751/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:d60ac9663f44168038586cab2157e122e46bdef09e9368b37f2d82d354c23f72", size = 1621979, upload-time = "2026-01-03T17:32:15.965Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/f0/12973c382ae7c1cccbc4417e129c5bf54c374dfb85af70893646e1f0e749/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:90751b8eed69435bac9ff4e3d2f6b3af1f57e37ecb0fbeee59c0174c9e2d41df", size = 1822193, upload-time = "2026-01-03T17:32:18.219Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/5f/24155e30ba7f8c96918af1350eb0663e2430aad9e001c0489d89cd708ab1/aiohttp-3.13.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:fc353029f176fd2b3ec6cfc71be166aba1936fe5d73dd1992ce289ca6647a9aa", size = 1769801, upload-time = "2026-01-03T17:32:20.25Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/f8/7314031ff5c10e6ece114da79b338ec17eeff3a079e53151f7e9f43c4723/aiohttp-3.13.3-cp314-cp314t-win32.whl", hash = "sha256:2e41b18a58da1e474a057b3d35248d8320029f61d70a37629535b16a0c8f3767", size = 466523, upload-time = "2026-01-03T17:32:22.215Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/63/278a98c715ae467624eafe375542d8ba9b4383a016df8fdefe0ae28382a7/aiohttp-3.13.3-cp314-cp314t-win_amd64.whl", hash = "sha256:44531a36aa2264a1860089ffd4dce7baf875ee5a6079d5fb42e261c704ef7344", size = 499694, upload-time = "2026-01-03T17:32:24.546Z" },
 ]
 
 [[package]]
@@ -89,6 +123,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/39/4a/4c61d4c84cfd9befb6fa08a702535b27b21fff08c946bc2f6139decbf7f7/alembic-1.16.5-py3-none-any.whl", hash = "sha256:e845dfe090c5ffa7b92593ae6687c5cb1a101e91fa53868497dbd79847f9dbe3", size = 247355, upload-time = "2025-08-27T18:02:07.37Z" },
 ]
 
+[[package]]
+name = "annotated-doc"
+version = "0.0.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/57/ba/046ceea27344560984e26a590f90bc7f4a75b06701f653222458922b558c/annotated_doc-0.0.4.tar.gz", hash = "sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4", size = 7288, upload-time = "2025-11-10T22:07:42.062Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/d3/26bf1008eb3d2daa8ef4cacc7f3bfdc11818d111f7e2d0201bc6e3b49d45/annotated_doc-0.0.4-py3-none-any.whl", hash = "sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320", size = 5303, upload-time = "2025-11-10T22:07:40.673Z" },
+]
+
 [[package]]
 name = "annotated-types"
 version = "0.7.0"
@@ -460,16 +503,18 @@ wheels = [
 
 [[package]]
 name = "fastapi"
-version = "0.116.1"
+version = "0.133.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
+    { name = "annotated-doc" },
     { name = "pydantic" },
     { name = "starlette" },
     { name = "typing-extensions" },
+    { name = "typing-inspection" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/78/d7/6c8b3bfe33eeffa208183ec037fee0cce9f7f024089ab1c5d12ef04bd27c/fastapi-0.116.1.tar.gz", hash = "sha256:ed52cbf946abfd70c5a0dccb24673f0670deeb517a88b3544d03c2a6bf283143", size = 296485, upload-time = "2025-07-11T16:22:32.057Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/22/6f/0eafed8349eea1fa462238b54a624c8b408cd1ba2795c8e64aa6c34f8ab7/fastapi-0.133.1.tar.gz", hash = "sha256:ed152a45912f102592976fde6cbce7dae1a8a1053da94202e51dd35d184fadd6", size = 378741, upload-time = "2026-02-25T18:18:17.398Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/e5/47/d63c60f59a59467fda0f93f46335c9d18526d7071f025cb5b89d5353ea42/fastapi-0.116.1-py3-none-any.whl", hash = "sha256:c46ac7c312df840f0c9e220f7964bada936781bc4e2e6eb71f1c4d7553786565", size = 95631, upload-time = "2025-07-11T16:22:30.485Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/c9/a175a7779f3599dfa4adfc97a6ce0e157237b3d7941538604aadaf97bfb6/fastapi-0.133.1-py3-none-any.whl", hash = "sha256:658f34ba334605b1617a65adf2ea6461901bdb9af3a3080d63ff791ecf7dc2e2", size = 109029, upload-time = "2026-02-25T18:18:18.578Z" },
 ]
 
 [package.optional-dependencies]
@@ -478,6 +523,8 @@ standard = [
     { name = "fastapi-cli", extra = ["standard"] },
     { name = "httpx" },
     { name = "jinja2" },
+    { name = "pydantic-extra-types" },
+    { name = "pydantic-settings" },
     { name = "python-multipart" },
     { name = "uvicorn", extra = ["standard"] },
 ]
@@ -539,11 +586,11 @@ wheels = [
 
 [[package]]
 name = "filelock"
-version = "3.19.1"
+version = "3.20.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/40/bb/0ab3e58d22305b6f5440629d20683af28959bf793d98d11950e305c1c326/filelock-3.19.1.tar.gz", hash = "sha256:66eda1888b0171c998b35be2bcc0f6d75c388a7ce20c3f3f37aa8e96c2dddf58", size = 17687, upload-time = "2025-08-14T16:56:03.016Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1d/65/ce7f1b70157833bf3cb851b556a37d4547ceafc158aa9b34b36782f23696/filelock-3.20.3.tar.gz", hash = "sha256:18c57ee915c7ec61cff0ecf7f0f869936c7c30191bb0cf406f1341778d0834e1", size = 19485, upload-time = "2026-01-09T17:55:05.421Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/42/14/42b2651a2f46b022ccd948bca9f2d5af0fd8929c4eec235b8d6d844fbe67/filelock-3.19.1-py3-none-any.whl", hash = "sha256:d38e30481def20772f5baf097c122c3babc4fcdb7e14e57049eb9d88c6dc017d", size = 15988, upload-time = "2025-08-14T16:56:01.633Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/36/7fb70f04bf00bc646cd5bb45aa9eddb15e19437a28b8fb2b4a5249fac770/filelock-3.20.3-py3-none-any.whl", hash = "sha256:4b0dda527ee31078689fc205ec4f1c1bf7d56cf88b6dc9426c4f230e46c2dce1", size = 16701, upload-time = "2026-01-09T17:55:04.334Z" },
 ]
 
 [[package]]
@@ -557,43 +604,43 @@ wheels = [
 
 [[package]]
 name = "fonttools"
-version = "4.59.2"
+version = "4.60.2"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/0d/a5/fba25f9fbdab96e26dedcaeeba125e5f05a09043bf888e0305326e55685b/fonttools-4.59.2.tar.gz", hash = "sha256:e72c0749b06113f50bcb80332364c6be83a9582d6e3db3fe0b280f996dc2ef22", size = 3540889, upload-time = "2025-08-27T16:40:30.97Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/3e/c4/db6a7b5eb0656534c3aa2596c2c5e18830d74f1b9aa5aa8a7dff63a0b11d/fonttools-4.60.2.tar.gz", hash = "sha256:d29552e6b155ebfc685b0aecf8d429cb76c14ab734c22ef5d3dea6fdf800c92c", size = 3562254, upload-time = "2025-12-09T13:38:11.835Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ba/3d/1f45db2df51e7bfa55492e8f23f383d372200be3a0ded4bf56a92753dd1f/fonttools-4.59.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:82906d002c349cad647a7634b004825a7335f8159d0d035ae89253b4abf6f3ea", size = 2769711, upload-time = "2025-08-27T16:39:04.423Z" },
-    { url = "https://files.pythonhosted.org/packages/29/df/cd236ab32a8abfd11558f296e064424258db5edefd1279ffdbcfd4fd8b76/fonttools-4.59.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:a10c1bd7644dc58f8862d8ba0cf9fb7fef0af01ea184ba6ce3f50ab7dfe74d5a", size = 2340225, upload-time = "2025-08-27T16:39:06.143Z" },
-    { url = "https://files.pythonhosted.org/packages/98/12/b6f9f964fe6d4b4dd4406bcbd3328821c3de1f909ffc3ffa558fe72af48c/fonttools-4.59.2-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:738f31f23e0339785fd67652a94bc69ea49e413dfdb14dcb8c8ff383d249464e", size = 4912766, upload-time = "2025-08-27T16:39:08.138Z" },
-    { url = "https://files.pythonhosted.org/packages/73/78/82bde2f2d2c306ef3909b927363170b83df96171f74e0ccb47ad344563cd/fonttools-4.59.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0ec99f9bdfee9cdb4a9172f9e8fd578cce5feb231f598909e0aecf5418da4f25", size = 4955178, upload-time = "2025-08-27T16:39:10.094Z" },
-    { url = "https://files.pythonhosted.org/packages/92/77/7de766afe2d31dda8ee46d7e479f35c7d48747e558961489a2d6e3a02bd4/fonttools-4.59.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0476ea74161322e08c7a982f83558a2b81b491509984523a1a540baf8611cc31", size = 4897898, upload-time = "2025-08-27T16:39:12.087Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/77/ce0e0b905d62a06415fda9f2b2e109a24a5db54a59502b769e9e297d2242/fonttools-4.59.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:95922a922daa1f77cc72611747c156cfb38030ead72436a2c551d30ecef519b9", size = 5049144, upload-time = "2025-08-27T16:39:13.84Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/ea/870d93aefd23fff2e07cbeebdc332527868422a433c64062c09d4d5e7fe6/fonttools-4.59.2-cp312-cp312-win32.whl", hash = "sha256:39ad9612c6a622726a6a130e8ab15794558591f999673f1ee7d2f3d30f6a3e1c", size = 2206473, upload-time = "2025-08-27T16:39:15.854Z" },
-    { url = "https://files.pythonhosted.org/packages/61/c4/e44bad000c4a4bb2e9ca11491d266e857df98ab6d7428441b173f0fe2517/fonttools-4.59.2-cp312-cp312-win_amd64.whl", hash = "sha256:980fd7388e461b19a881d35013fec32c713ffea1fc37aef2f77d11f332dfd7da", size = 2254706, upload-time = "2025-08-27T16:39:17.893Z" },
-    { url = "https://files.pythonhosted.org/packages/13/7b/d0d3b9431642947b5805201fbbbe938a47b70c76685ef1f0cb5f5d7140d6/fonttools-4.59.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:381bde13216ba09489864467f6bc0c57997bd729abfbb1ce6f807ba42c06cceb", size = 2761563, upload-time = "2025-08-27T16:39:20.286Z" },
-    { url = "https://files.pythonhosted.org/packages/76/be/fc5fe58dd76af7127b769b68071dbc32d4b95adc8b58d1d28d42d93c90f2/fonttools-4.59.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f33839aa091f7eef4e9078f5b7ab1b8ea4b1d8a50aeaef9fdb3611bba80869ec", size = 2335671, upload-time = "2025-08-27T16:39:22.027Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/9f/bf231c2a3fac99d1d7f1d89c76594f158693f981a4aa02be406e9f036832/fonttools-4.59.2-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:6235fc06bcbdb40186f483ba9d5d68f888ea68aa3c8dac347e05a7c54346fbc8", size = 4893967, upload-time = "2025-08-27T16:39:23.664Z" },
-    { url = "https://files.pythonhosted.org/packages/26/a9/d46d2ad4fcb915198504d6727f83aa07f46764c64f425a861aa38756c9fd/fonttools-4.59.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:83ad6e5d06ef3a2884c4fa6384a20d6367b5cfe560e3b53b07c9dc65a7020e73", size = 4951986, upload-time = "2025-08-27T16:39:25.379Z" },
-    { url = "https://files.pythonhosted.org/packages/07/90/1cc8d7dd8f707dfeeca472b82b898d3add0ebe85b1f645690dcd128ee63f/fonttools-4.59.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:d029804c70fddf90be46ed5305c136cae15800a2300cb0f6bba96d48e770dde0", size = 4891630, upload-time = "2025-08-27T16:39:27.494Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/04/f0345b0d9fe67d65aa8d3f2d4cbf91d06f111bc7b8d802e65914eb06194d/fonttools-4.59.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:95807a3b5e78f2714acaa26a33bc2143005cc05c0217b322361a772e59f32b89", size = 5035116, upload-time = "2025-08-27T16:39:29.406Z" },
-    { url = "https://files.pythonhosted.org/packages/d7/7d/5ba5eefffd243182fbd067cdbfeb12addd4e5aec45011b724c98a344ea33/fonttools-4.59.2-cp313-cp313-win32.whl", hash = "sha256:b3ebda00c3bb8f32a740b72ec38537d54c7c09f383a4cfefb0b315860f825b08", size = 2204907, upload-time = "2025-08-27T16:39:31.42Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/a9/be7219fc64a6026cc0aded17fa3720f9277001c185434230bd351bf678e6/fonttools-4.59.2-cp313-cp313-win_amd64.whl", hash = "sha256:a72155928d7053bbde499d32a9c77d3f0f3d29ae72b5a121752481bcbd71e50f", size = 2253742, upload-time = "2025-08-27T16:39:33.079Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/c7/486580d00be6fa5d45e41682e5ffa5c809f3d25773c6f39628d60f333521/fonttools-4.59.2-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:d09e487d6bfbe21195801323ba95c91cb3523f0fcc34016454d4d9ae9eaa57fe", size = 2762444, upload-time = "2025-08-27T16:39:34.759Z" },
-    { url = "https://files.pythonhosted.org/packages/d3/9b/950ea9b7b764ceb8d18645c62191e14ce62124d8e05cb32a4dc5e65fde0b/fonttools-4.59.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:dec2f22486d7781087b173799567cffdcc75e9fb2f1c045f05f8317ccce76a3e", size = 2333256, upload-time = "2025-08-27T16:39:40.777Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/4d/8ee9d563126de9002eede950cde0051be86cc4e8c07c63eca0c9fc95734a/fonttools-4.59.2-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:1647201af10993090120da2e66e9526c4e20e88859f3e34aa05b8c24ded2a564", size = 4834846, upload-time = "2025-08-27T16:39:42.885Z" },
-    { url = "https://files.pythonhosted.org/packages/03/26/f26d947b0712dce3d118e92ce30ca88f98938b066498f60d0ee000a892ae/fonttools-4.59.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:47742c33fe65f41eabed36eec2d7313a8082704b7b808752406452f766c573fc", size = 4930871, upload-time = "2025-08-27T16:39:44.818Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/7f/ebe878061a5a5e6b6502f0548489e01100f7e6c0049846e6546ba19a3ab4/fonttools-4.59.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:92ac2d45794f95d1ad4cb43fa07e7e3776d86c83dc4b9918cf82831518165b4b", size = 4876971, upload-time = "2025-08-27T16:39:47.027Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/0d/0d22e3a20ac566836098d30718092351935487e3271fd57385db1adb2fde/fonttools-4.59.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:fa9ecaf2dcef8941fb5719e16322345d730f4c40599bbf47c9753de40eb03882", size = 4987478, upload-time = "2025-08-27T16:39:48.774Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/a3/960cc83182a408ffacc795e61b5f698c6f7b0cfccf23da4451c39973f3c8/fonttools-4.59.2-cp314-cp314-win32.whl", hash = "sha256:a8d40594982ed858780e18a7e4c80415af65af0f22efa7de26bdd30bf24e1e14", size = 2208640, upload-time = "2025-08-27T16:39:50.592Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/74/55e5c57c414fa3965fee5fc036ed23f26a5c4e9e10f7f078a54ff9c7dfb7/fonttools-4.59.2-cp314-cp314-win_amd64.whl", hash = "sha256:9cde8b6a6b05f68516573523f2013a3574cb2c75299d7d500f44de82ba947b80", size = 2258457, upload-time = "2025-08-27T16:39:52.611Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/dc/8e4261dc591c5cfee68fecff3ffee2a9b29e1edc4c4d9cbafdc5aefe74ee/fonttools-4.59.2-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:036cd87a2dbd7ef72f7b68df8314ced00b8d9973aee296f2464d06a836aeb9a9", size = 2829901, upload-time = "2025-08-27T16:39:55.014Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/05/331538dcf21fd6331579cd628268150e85210d0d2bdae20f7598c2b36c05/fonttools-4.59.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:14870930181493b1d740b6f25483e20185e5aea58aec7d266d16da7be822b4bb", size = 2362717, upload-time = "2025-08-27T16:39:56.843Z" },
-    { url = "https://files.pythonhosted.org/packages/60/ae/d26428ca9ede809c0a93f0af91f44c87433dc0251e2aec333da5ed00d38f/fonttools-4.59.2-cp314-cp314t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:7ff58ea1eb8fc7e05e9a949419f031890023f8785c925b44d6da17a6a7d6e85d", size = 4835120, upload-time = "2025-08-27T16:39:59.06Z" },
-    { url = "https://files.pythonhosted.org/packages/07/c4/0f6ac15895de509e07688cb1d45f1ae583adbaa0fa5a5699d73f3bd58ca0/fonttools-4.59.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6dee142b8b3096514c96ad9e2106bf039e2fe34a704c587585b569a36df08c3c", size = 5071115, upload-time = "2025-08-27T16:40:01.009Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/b6/147a711b7ecf7ea39f9da9422a55866f6dd5747c2f36b3b0a7a7e0c6820b/fonttools-4.59.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:8991bdbae39cf78bcc9cd3d81f6528df1f83f2e7c23ccf6f990fa1f0b6e19708", size = 4943905, upload-time = "2025-08-27T16:40:03.179Z" },
-    { url = "https://files.pythonhosted.org/packages/5b/4e/2ab19006646b753855e2b02200fa1cabb75faa4eeca4ef289f269a936974/fonttools-4.59.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:53c1a411b7690042535a4f0edf2120096a39a506adeb6c51484a232e59f2aa0c", size = 4960313, upload-time = "2025-08-27T16:40:05.45Z" },
-    { url = "https://files.pythonhosted.org/packages/98/3d/df77907e5be88adcca93cc2cee00646d039da220164be12bee028401e1cf/fonttools-4.59.2-cp314-cp314t-win32.whl", hash = "sha256:59d85088e29fa7a8f87d19e97a1beae2a35821ee48d8ef6d2c4f965f26cb9f8a", size = 2269719, upload-time = "2025-08-27T16:40:07.553Z" },
-    { url = "https://files.pythonhosted.org/packages/2d/a0/d4c4bc5b50275449a9a908283b567caa032a94505fe1976e17f994faa6be/fonttools-4.59.2-cp314-cp314t-win_amd64.whl", hash = "sha256:7ad5d8d8cc9e43cb438b3eb4a0094dd6d4088daa767b0a24d52529361fd4c199", size = 2333169, upload-time = "2025-08-27T16:40:09.656Z" },
-    { url = "https://files.pythonhosted.org/packages/65/a4/d2f7be3c86708912c02571db0b550121caab8cd88a3c0aacb9cfa15ea66e/fonttools-4.59.2-py3-none-any.whl", hash = "sha256:8bd0f759020e87bb5d323e6283914d9bf4ae35a7307dafb2cbd1e379e720ad37", size = 1132315, upload-time = "2025-08-27T16:40:28.984Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/30/530c9eddcd1c39219dc0aaede2b5a4c8ab80e0bb88d1b3ffc12944c4aac3/fonttools-4.60.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:e0164b7609d2b5c5dd4e044b8085b7bd7ca7363ef8c269a4ab5b5d4885a426b2", size = 2847196, upload-time = "2025-12-09T13:36:33.262Z" },
+    { url = "https://files.pythonhosted.org/packages/19/2f/4077a482836d5bbe3bc9dac1c004d02ee227cf04ed62b0a2dfc41d4f0dfd/fonttools-4.60.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:1dd3d9574fc595c1e97faccae0f264dc88784ddf7fbf54c939528378bacc0033", size = 2395842, upload-time = "2025-12-09T13:36:35.47Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/05/aae5bb99c5398f8ed4a8b784f023fd9dd3568f0bd5d5b21e35b282550f11/fonttools-4.60.2-cp312-cp312-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:98d0719f1b11c2817307d2da2e94296a3b2a3503f8d6252a101dca3ee663b917", size = 4949713, upload-time = "2025-12-09T13:36:37.874Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/37/49067349fc78ff0efbf09fadefe80ddf41473ca8f8a25400e3770da38328/fonttools-4.60.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9d3ea26957dd07209f207b4fff64c702efe5496de153a54d3b91007ec28904dd", size = 4999907, upload-time = "2025-12-09T13:36:39.853Z" },
+    { url = "https://files.pythonhosted.org/packages/16/31/d0f11c758bd0db36b664c92a0f9dfdcc2d7313749aa7d6629805c6946f21/fonttools-4.60.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1ee301273b0850f3a515299f212898f37421f42ff9adfc341702582ca5073c13", size = 4939717, upload-time = "2025-12-09T13:36:43.075Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/bc/1cff0d69522e561bf1b99bee7c3911c08c25e919584827c3454a64651ce9/fonttools-4.60.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:c6eb4694cc3b9c03b7c01d65a9cf35b577f21aa6abdbeeb08d3114b842a58153", size = 5089205, upload-time = "2025-12-09T13:36:45.468Z" },
+    { url = "https://files.pythonhosted.org/packages/05/e6/fb174f0069b7122e19828c551298bfd34fdf9480535d2a6ac2ed37afacd3/fonttools-4.60.2-cp312-cp312-win32.whl", hash = "sha256:57f07b616c69c244cc1a5a51072eeef07dddda5ebef9ca5c6e9cf6d59ae65b70", size = 2264674, upload-time = "2025-12-09T13:36:49.238Z" },
+    { url = "https://files.pythonhosted.org/packages/75/57/6552ffd6b582d3e6a9f01780c5275e6dfff1e70ca146101733aa1c12a129/fonttools-4.60.2-cp312-cp312-win_amd64.whl", hash = "sha256:310035802392f1fe5a7cf43d76f6ff4a24c919e4c72c0352e7b8176e2584b8a0", size = 2314701, upload-time = "2025-12-09T13:36:51.09Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/e4/8381d0ca6b6c6c484660b03517ec5b5b81feeefca3808726dece36c652a9/fonttools-4.60.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2bb5fd231e56ccd7403212636dcccffc96c5ae0d6f9e4721fa0a32cb2e3ca432", size = 2842063, upload-time = "2025-12-09T13:36:53.468Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/2c/4367117ee8ff4f4374787a1222da0bd413d80cf3522111f727a7b8f80d1d/fonttools-4.60.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:536b5fab7b6fec78ccf59b5c59489189d9d0a8b0d3a77ed1858be59afb096696", size = 2393792, upload-time = "2025-12-09T13:36:55.742Z" },
+    { url = "https://files.pythonhosted.org/packages/49/b7/a76b6dffa193869e54e32ca2f9abb0d0e66784bc8a24e6f86eb093015481/fonttools-4.60.2-cp313-cp313-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:6b9288fc38252ac86a9570f19313ecbc9ff678982e0f27c757a85f1f284d3400", size = 4924020, upload-time = "2025-12-09T13:36:58.229Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/4e/0078200e2259f0061c86a74075f507d64c43dd2ab38971956a5c0012d344/fonttools-4.60.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:93fcb420791d839ef592eada2b69997c445d0ce9c969b5190f2e16828ec10607", size = 4980070, upload-time = "2025-12-09T13:37:00.311Z" },
+    { url = "https://files.pythonhosted.org/packages/85/1f/d87c85a11cb84852c975251581862681e4a0c1c3bd456c648792203f311b/fonttools-4.60.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:7916a381b094db4052ac284255186aebf74c5440248b78860cb41e300036f598", size = 4921411, upload-time = "2025-12-09T13:37:02.345Z" },
+    { url = "https://files.pythonhosted.org/packages/75/c0/7efad650f5ed8e317c2633133ef3c64917e7adf2e4e2940c798f5d57ec6e/fonttools-4.60.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:58c8c393d5e16b15662cfc2d988491940458aa87894c662154f50c7b49440bef", size = 5063465, upload-time = "2025-12-09T13:37:04.836Z" },
+    { url = "https://files.pythonhosted.org/packages/18/a8/750518c4f8cdd79393b386bc81226047ade80239e58c6c9f5dbe1fdd8ea1/fonttools-4.60.2-cp313-cp313-win32.whl", hash = "sha256:19c6e0afd8b02008caa0aa08ab896dfce5d0bcb510c49b2c499541d5cb95a963", size = 2263443, upload-time = "2025-12-09T13:37:06.762Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/22/026c60376f165981f80a0e90bd98a79ae3334e9d89a3d046c4d2e265c724/fonttools-4.60.2-cp313-cp313-win_amd64.whl", hash = "sha256:6a500dc59e11b2338c2dba1f8cf11a4ae8be35ec24af8b2628b8759a61457b76", size = 2313800, upload-time = "2025-12-09T13:37:08.713Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/ab/7cf1f5204e1366ddf9dc5cdc2789b571feb9eebcee0e3463c3f457df5f52/fonttools-4.60.2-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9387c532acbe323bbf2a920f132bce3c408a609d5f9dcfc6532fbc7e37f8ccbb", size = 2841690, upload-time = "2025-12-09T13:37:10.696Z" },
+    { url = "https://files.pythonhosted.org/packages/00/3c/0bf83c6f863cc8b934952567fa2bf737cfcec8fc4ffb59b3f93820095f89/fonttools-4.60.2-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:e6f1c824185b5b8fb681297f315f26ae55abb0d560c2579242feea8236b1cfef", size = 2392191, upload-time = "2025-12-09T13:37:12.954Z" },
+    { url = "https://files.pythonhosted.org/packages/00/f0/40090d148b8907fbea12e9bdf1ff149f30cdf1769e3b2c3e0dbf5106b88d/fonttools-4.60.2-cp314-cp314-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:55a3129d1e4030b1a30260f1b32fe76781b585fb2111d04a988e141c09eb6403", size = 4873503, upload-time = "2025-12-09T13:37:15.142Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/e0/d8b13f99e58b8c293781288ba62fe634f1f0697c9c4c0ae104d3215f3a10/fonttools-4.60.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b196e63753abc33b3b97a6fd6de4b7c4fef5552c0a5ba5e562be214d1e9668e0", size = 4968493, upload-time = "2025-12-09T13:37:18.272Z" },
+    { url = "https://files.pythonhosted.org/packages/46/c5/960764d12c92bc225f02401d3067048cb7b282293d9e48e39fe2b0ec38a9/fonttools-4.60.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:de76c8d740fb55745f3b154f0470c56db92ae3be27af8ad6c2e88f1458260c9a", size = 4920015, upload-time = "2025-12-09T13:37:20.334Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/ab/839d8caf253d1eef3653ef4d34427d0326d17a53efaec9eb04056b670fff/fonttools-4.60.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:6ba6303225c95998c9fda2d410aa792c3d2c1390a09df58d194b03e17583fa25", size = 5031165, upload-time = "2025-12-09T13:37:23.57Z" },
+    { url = "https://files.pythonhosted.org/packages/de/bf/3bc862796a6841cbe0725bb5512d272239b809dba631a4b0301df885e62d/fonttools-4.60.2-cp314-cp314-win32.whl", hash = "sha256:0a89728ce10d7c816fedaa5380c06d2793e7a8a634d7ce16810e536c22047384", size = 2267526, upload-time = "2025-12-09T13:37:25.821Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/a1/c1909cacf00c76dc37b4743451561fbaaf7db4172c22a6d9394081d114c3/fonttools-4.60.2-cp314-cp314-win_amd64.whl", hash = "sha256:fa8446e6ab8bd778b82cb1077058a2addba86f30de27ab9cc18ed32b34bc8667", size = 2319096, upload-time = "2025-12-09T13:37:28.058Z" },
+    { url = "https://files.pythonhosted.org/packages/29/b3/f66e71433f08e3a931b2b31a665aeed17fcc5e6911fc73529c70a232e421/fonttools-4.60.2-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:4063bc81ac5a4137642865cb63dd270e37b3cd1f55a07c0d6e41d072699ccca2", size = 2925167, upload-time = "2025-12-09T13:37:30.348Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/13/eeb491ff743594bbd0bee6e49422c03a59fe9c49002d3cc60eeb77414285/fonttools-4.60.2-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:ebfdb66fa69732ed604ab8e2a0431e6deff35e933a11d73418cbc7823d03b8e1", size = 2430923, upload-time = "2025-12-09T13:37:32.817Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/e5/db609f785e460796e53c4dbc3874a5f4948477f27beceb5e2d24b2537666/fonttools-4.60.2-cp314-cp314t-manylinux1_x86_64.manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:50b10b3b1a72d1d54c61b0e59239e1a94c0958f4a06a1febf97ce75388dd91a4", size = 4877729, upload-time = "2025-12-09T13:37:35.858Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/d6/85e4484dd4bfb03fee7bd370d65888cccbd3dee2681ee48c869dd5ccb23f/fonttools-4.60.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:beae16891a13b4a2ddec9b39b4de76092a3025e4d1c82362e3042b62295d5e4d", size = 5096003, upload-time = "2025-12-09T13:37:37.862Z" },
+    { url = "https://files.pythonhosted.org/packages/30/49/1a98e44b71030b83d2046f981373b80571868259d98e6dae7bc20099dac6/fonttools-4.60.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:522f017fdb3766fd5d2d321774ef351cc6ce88ad4e6ac9efe643e4a2b9d528db", size = 4974410, upload-time = "2025-12-09T13:37:40.166Z" },
+    { url = "https://files.pythonhosted.org/packages/42/07/d6f775d950ee8a841012472c7303f8819423d8cc3b4530915de7265ebfa2/fonttools-4.60.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:82cceceaf9c09a965a75b84a4b240dd3768e596ffb65ef53852681606fe7c9ba", size = 5002036, upload-time = "2025-12-09T13:37:42.639Z" },
+    { url = "https://files.pythonhosted.org/packages/73/f6/ba6458f83ce1a9f8c3b17bd8f7b8a2205a126aac1055796b7e7cfebbd38f/fonttools-4.60.2-cp314-cp314t-win32.whl", hash = "sha256:bbfbc918a75437fe7e6d64d1b1e1f713237df1cf00f3a36dedae910b2ba01cee", size = 2330985, upload-time = "2025-12-09T13:37:45.157Z" },
+    { url = "https://files.pythonhosted.org/packages/91/24/fea0ba4d3a32d4ed1103a1098bfd99dc78b5fe3bb97202920744a37b73dc/fonttools-4.60.2-cp314-cp314t-win_amd64.whl", hash = "sha256:0e5cd9b0830f6550d58c84f3ab151a9892b50c4f9d538c5603c0ce6fff2eb3f1", size = 2396226, upload-time = "2025-12-09T13:37:47.355Z" },
+    { url = "https://files.pythonhosted.org/packages/79/6c/10280af05b44fafd1dff69422805061fa1af29270bc52dce031ac69540bf/fonttools-4.60.2-py3-none-any.whl", hash = "sha256:73cf92eeda67cf6ff10c8af56fc8f4f07c1647d989a979be9e388a49be26552a", size = 1144610, upload-time = "2025-12-09T13:38:09.5Z" },
 ]
 
 [[package]]
@@ -679,27 +726,30 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/44/69/9b804adb5fd0671f367781560eb5eb586c4d495277c93bde4307b9e28068/greenlet-3.2.4-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3b67ca49f54cede0186854a008109d6ee71f66bd57bb36abd6d0a0267b540cdd", size = 274079, upload-time = "2025-08-07T13:15:45.033Z" },
     { url = "https://files.pythonhosted.org/packages/46/e9/d2a80c99f19a153eff70bc451ab78615583b8dac0754cfb942223d2c1a0d/greenlet-3.2.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ddf9164e7a5b08e9d22511526865780a576f19ddd00d62f8a665949327fde8bb", size = 640997, upload-time = "2025-08-07T13:42:56.234Z" },
     { url = "https://files.pythonhosted.org/packages/3b/16/035dcfcc48715ccd345f3a93183267167cdd162ad123cd93067d86f27ce4/greenlet-3.2.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:f28588772bb5fb869a8eb331374ec06f24a83a9c25bfa1f38b6993afe9c1e968", size = 655185, upload-time = "2025-08-07T13:45:27.624Z" },
-    { url = "https://files.pythonhosted.org/packages/31/da/0386695eef69ffae1ad726881571dfe28b41970173947e7c558d9998de0f/greenlet-3.2.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:5c9320971821a7cb77cfab8d956fa8e39cd07ca44b6070db358ceb7f8797c8c9", size = 649926, upload-time = "2025-08-07T13:53:15.251Z" },
     { url = "https://files.pythonhosted.org/packages/68/88/69bf19fd4dc19981928ceacbc5fd4bb6bc2215d53199e367832e98d1d8fe/greenlet-3.2.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c60a6d84229b271d44b70fb6e5fa23781abb5d742af7b808ae3f6efd7c9c60f6", size = 651839, upload-time = "2025-08-07T13:18:30.281Z" },
     { url = "https://files.pythonhosted.org/packages/19/0d/6660d55f7373b2ff8152401a83e02084956da23ae58cddbfb0b330978fe9/greenlet-3.2.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b3812d8d0c9579967815af437d96623f45c0f2ae5f04e366de62a12d83a8fb0", size = 607586, upload-time = "2025-08-07T13:18:28.544Z" },
     { url = "https://files.pythonhosted.org/packages/8e/1a/c953fdedd22d81ee4629afbb38d2f9d71e37d23caace44775a3a969147d4/greenlet-3.2.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:abbf57b5a870d30c4675928c37278493044d7c14378350b3aa5d484fa65575f0", size = 1123281, upload-time = "2025-08-07T13:42:39.858Z" },
     { url = "https://files.pythonhosted.org/packages/3f/c7/12381b18e21aef2c6bd3a636da1088b888b97b7a0362fac2e4de92405f97/greenlet-3.2.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20fb936b4652b6e307b8f347665e2c615540d4b42b3b4c8a321d8286da7e520f", size = 1151142, upload-time = "2025-08-07T13:18:22.981Z" },
+    { url = "https://files.pythonhosted.org/packages/27/45/80935968b53cfd3f33cf99ea5f08227f2646e044568c9b1555b58ffd61c2/greenlet-3.2.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ee7a6ec486883397d70eec05059353b8e83eca9168b9f3f9a361971e77e0bcd0", size = 1564846, upload-time = "2025-11-04T12:42:15.191Z" },
+    { url = "https://files.pythonhosted.org/packages/69/02/b7c30e5e04752cb4db6202a3858b149c0710e5453b71a3b2aec5d78a1aab/greenlet-3.2.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:326d234cbf337c9c3def0676412eb7040a35a768efc92504b947b3e9cfc7543d", size = 1633814, upload-time = "2025-11-04T12:42:17.175Z" },
     { url = "https://files.pythonhosted.org/packages/e9/08/b0814846b79399e585f974bbeebf5580fbe59e258ea7be64d9dfb253c84f/greenlet-3.2.4-cp312-cp312-win_amd64.whl", hash = "sha256:a7d4e128405eea3814a12cc2605e0e6aedb4035bf32697f72deca74de4105e02", size = 299899, upload-time = "2025-08-07T13:38:53.448Z" },
     { url = "https://files.pythonhosted.org/packages/49/e8/58c7f85958bda41dafea50497cbd59738c5c43dbbea5ee83d651234398f4/greenlet-3.2.4-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:1a921e542453fe531144e91e1feedf12e07351b1cf6c9e8a3325ea600a715a31", size = 272814, upload-time = "2025-08-07T13:15:50.011Z" },
     { url = "https://files.pythonhosted.org/packages/62/dd/b9f59862e9e257a16e4e610480cfffd29e3fae018a68c2332090b53aac3d/greenlet-3.2.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd3c8e693bff0fff6ba55f140bf390fa92c994083f838fece0f63be121334945", size = 641073, upload-time = "2025-08-07T13:42:57.23Z" },
     { url = "https://files.pythonhosted.org/packages/f7/0b/bc13f787394920b23073ca3b6c4a7a21396301ed75a655bcb47196b50e6e/greenlet-3.2.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:710638eb93b1fa52823aa91bf75326f9ecdfd5e0466f00789246a5280f4ba0fc", size = 655191, upload-time = "2025-08-07T13:45:29.752Z" },
-    { url = "https://files.pythonhosted.org/packages/f2/d6/6adde57d1345a8d0f14d31e4ab9c23cfe8e2cd39c3baf7674b4b0338d266/greenlet-3.2.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:c5111ccdc9c88f423426df3fd1811bfc40ed66264d35aa373420a34377efc98a", size = 649516, upload-time = "2025-08-07T13:53:16.314Z" },
     { url = "https://files.pythonhosted.org/packages/7f/3b/3a3328a788d4a473889a2d403199932be55b1b0060f4ddd96ee7cdfcad10/greenlet-3.2.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d76383238584e9711e20ebe14db6c88ddcedc1829a9ad31a584389463b5aa504", size = 652169, upload-time = "2025-08-07T13:18:32.861Z" },
     { url = "https://files.pythonhosted.org/packages/ee/43/3cecdc0349359e1a527cbf2e3e28e5f8f06d3343aaf82ca13437a9aa290f/greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671", size = 610497, upload-time = "2025-08-07T13:18:31.636Z" },
     { url = "https://files.pythonhosted.org/packages/b8/19/06b6cf5d604e2c382a6f31cafafd6f33d5dea706f4db7bdab184bad2b21d/greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b", size = 1121662, upload-time = "2025-08-07T13:42:41.117Z" },
     { url = "https://files.pythonhosted.org/packages/a2/15/0d5e4e1a66fab130d98168fe984c509249c833c1a3c16806b90f253ce7b9/greenlet-3.2.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d25c5091190f2dc0eaa3f950252122edbbadbb682aa7b1ef2f8af0f8c0afefae", size = 1149210, upload-time = "2025-08-07T13:18:24.072Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/53/f9c440463b3057485b8594d7a638bed53ba531165ef0ca0e6c364b5cc807/greenlet-3.2.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6e343822feb58ac4d0a1211bd9399de2b3a04963ddeec21530fc426cc121f19b", size = 1564759, upload-time = "2025-11-04T12:42:19.395Z" },
+    { url = "https://files.pythonhosted.org/packages/47/e4/3bb4240abdd0a8d23f4f88adec746a3099f0d86bfedb623f063b2e3b4df0/greenlet-3.2.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ca7f6f1f2649b89ce02f6f229d7c19f680a6238af656f61e0115b24857917929", size = 1634288, upload-time = "2025-11-04T12:42:21.174Z" },
     { url = "https://files.pythonhosted.org/packages/0b/55/2321e43595e6801e105fcfdee02b34c0f996eb71e6ddffca6b10b7e1d771/greenlet-3.2.4-cp313-cp313-win_amd64.whl", hash = "sha256:554b03b6e73aaabec3745364d6239e9e012d64c68ccd0b8430c64ccc14939a8b", size = 299685, upload-time = "2025-08-07T13:24:38.824Z" },
     { url = "https://files.pythonhosted.org/packages/22/5c/85273fd7cc388285632b0498dbbab97596e04b154933dfe0f3e68156c68c/greenlet-3.2.4-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:49a30d5fda2507ae77be16479bdb62a660fa51b1eb4928b524975b3bde77b3c0", size = 273586, upload-time = "2025-08-07T13:16:08.004Z" },
     { url = "https://files.pythonhosted.org/packages/d1/75/10aeeaa3da9332c2e761e4c50d4c3556c21113ee3f0afa2cf5769946f7a3/greenlet-3.2.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:299fd615cd8fc86267b47597123e3f43ad79c9d8a22bebdce535e53550763e2f", size = 686346, upload-time = "2025-08-07T13:42:59.944Z" },
     { url = "https://files.pythonhosted.org/packages/c0/aa/687d6b12ffb505a4447567d1f3abea23bd20e73a5bed63871178e0831b7a/greenlet-3.2.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:c17b6b34111ea72fc5a4e4beec9711d2226285f0386ea83477cbb97c30a3f3a5", size = 699218, upload-time = "2025-08-07T13:45:30.969Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/8b/29aae55436521f1d6f8ff4e12fb676f3400de7fcf27fccd1d4d17fd8fecd/greenlet-3.2.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b4a1870c51720687af7fa3e7cda6d08d801dae660f75a76f3845b642b4da6ee1", size = 694659, upload-time = "2025-08-07T13:53:17.759Z" },
     { url = "https://files.pythonhosted.org/packages/92/2e/ea25914b1ebfde93b6fc4ff46d6864564fba59024e928bdc7de475affc25/greenlet-3.2.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:061dc4cf2c34852b052a8620d40f36324554bc192be474b9e9770e8c042fd735", size = 695355, upload-time = "2025-08-07T13:18:34.517Z" },
     { url = "https://files.pythonhosted.org/packages/72/60/fc56c62046ec17f6b0d3060564562c64c862948c9d4bc8aa807cf5bd74f4/greenlet-3.2.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44358b9bf66c8576a9f57a590d5f5d6e72fa4228b763d0e43fee6d3b06d3a337", size = 657512, upload-time = "2025-08-07T13:18:33.969Z" },
+    { url = "https://files.pythonhosted.org/packages/23/6e/74407aed965a4ab6ddd93a7ded3180b730d281c77b765788419484cdfeef/greenlet-3.2.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:2917bdf657f5859fbf3386b12d68ede4cf1f04c90c3a6bc1f013dd68a22e2269", size = 1612508, upload-time = "2025-11-04T12:42:23.427Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/da/343cd760ab2f92bac1845ca07ee3faea9fe52bee65f7bcb19f16ad7de08b/greenlet-3.2.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:015d48959d4add5d6c9f6c5210ee3803a830dce46356e3bc326d6776bde54681", size = 1680760, upload-time = "2025-11-04T12:42:25.341Z" },
     { url = "https://files.pythonhosted.org/packages/e3/a5/6ddab2b4c112be95601c13428db1d8b6608a8b6039816f2ba09c346c08fc/greenlet-3.2.4-cp314-cp314-win_amd64.whl", hash = "sha256:e37ab26028f12dbb0ff65f29a8d3d44a765c61e729647bf2ddfbbed621726f01", size = 303425, upload-time = "2025-08-07T13:32:27.59Z" },
 ]
 
@@ -1519,68 +1569,71 @@ wheels = [
 
 [[package]]
 name = "pillow"
-version = "11.3.0"
+version = "12.1.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/f3/0d/d0d6dea55cd152ce3d6767bb38a8fc10e33796ba4ba210cbab9354b6d238/pillow-11.3.0.tar.gz", hash = "sha256:3828ee7586cd0b2091b6209e5ad53e20d0649bbe87164a459d0676e035e8f523", size = 47113069, upload-time = "2025-07-01T09:16:30.666Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1f/42/5c74462b4fd957fcd7b13b04fb3205ff8349236ea74c7c375766d6c82288/pillow-12.1.1.tar.gz", hash = "sha256:9ad8fa5937ab05218e2b6a4cff30295ad35afd2f83ac592e68c0d871bb0fdbc4", size = 46980264, upload-time = "2026-02-11T04:23:07.146Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/40/fe/1bc9b3ee13f68487a99ac9529968035cca2f0a51ec36892060edcc51d06a/pillow-11.3.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fdae223722da47b024b867c1ea0be64e0df702c5e0a60e27daad39bf960dd1e4", size = 5278800, upload-time = "2025-07-01T09:14:17.648Z" },
-    { url = "https://files.pythonhosted.org/packages/2c/32/7e2ac19b5713657384cec55f89065fb306b06af008cfd87e572035b27119/pillow-11.3.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:921bd305b10e82b4d1f5e802b6850677f965d8394203d182f078873851dada69", size = 4686296, upload-time = "2025-07-01T09:14:19.828Z" },
-    { url = "https://files.pythonhosted.org/packages/8e/1e/b9e12bbe6e4c2220effebc09ea0923a07a6da1e1f1bfbc8d7d29a01ce32b/pillow-11.3.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:eb76541cba2f958032d79d143b98a3a6b3ea87f0959bbe256c0b5e416599fd5d", size = 5871726, upload-time = "2025-07-03T13:10:04.448Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/33/e9200d2bd7ba00dc3ddb78df1198a6e80d7669cce6c2bdbeb2530a74ec58/pillow-11.3.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:67172f2944ebba3d4a7b54f2e95c786a3a50c21b88456329314caaa28cda70f6", size = 7644652, upload-time = "2025-07-03T13:10:10.391Z" },
-    { url = "https://files.pythonhosted.org/packages/41/f1/6f2427a26fc683e00d985bc391bdd76d8dd4e92fac33d841127eb8fb2313/pillow-11.3.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:97f07ed9f56a3b9b5f49d3661dc9607484e85c67e27f3e8be2c7d28ca032fec7", size = 5977787, upload-time = "2025-07-01T09:14:21.63Z" },
-    { url = "https://files.pythonhosted.org/packages/e4/c9/06dd4a38974e24f932ff5f98ea3c546ce3f8c995d3f0985f8e5ba48bba19/pillow-11.3.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:676b2815362456b5b3216b4fd5bd89d362100dc6f4945154ff172e206a22c024", size = 6645236, upload-time = "2025-07-01T09:14:23.321Z" },
-    { url = "https://files.pythonhosted.org/packages/40/e7/848f69fb79843b3d91241bad658e9c14f39a32f71a301bcd1d139416d1be/pillow-11.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:3e184b2f26ff146363dd07bde8b711833d7b0202e27d13540bfe2e35a323a809", size = 6086950, upload-time = "2025-07-01T09:14:25.237Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/1a/7cff92e695a2a29ac1958c2a0fe4c0b2393b60aac13b04a4fe2735cad52d/pillow-11.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6be31e3fc9a621e071bc17bb7de63b85cbe0bfae91bb0363c893cbe67247780d", size = 6723358, upload-time = "2025-07-01T09:14:27.053Z" },
-    { url = "https://files.pythonhosted.org/packages/26/7d/73699ad77895f69edff76b0f332acc3d497f22f5d75e5360f78cbcaff248/pillow-11.3.0-cp312-cp312-win32.whl", hash = "sha256:7b161756381f0918e05e7cb8a371fff367e807770f8fe92ecb20d905d0e1c149", size = 6275079, upload-time = "2025-07-01T09:14:30.104Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/ce/e7dfc873bdd9828f3b6e5c2bbb74e47a98ec23cc5c74fc4e54462f0d9204/pillow-11.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:a6444696fce635783440b7f7a9fc24b3ad10a9ea3f0ab66c5905be1c19ccf17d", size = 6986324, upload-time = "2025-07-01T09:14:31.899Z" },
-    { url = "https://files.pythonhosted.org/packages/16/8f/b13447d1bf0b1f7467ce7d86f6e6edf66c0ad7cf44cf5c87a37f9bed9936/pillow-11.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:2aceea54f957dd4448264f9bf40875da0415c83eb85f55069d89c0ed436e3542", size = 2423067, upload-time = "2025-07-01T09:14:33.709Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/93/0952f2ed8db3a5a4c7a11f91965d6184ebc8cd7cbb7941a260d5f018cd2d/pillow-11.3.0-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:1c627742b539bba4309df89171356fcb3cc5a9178355b2727d1b74a6cf155fbd", size = 2128328, upload-time = "2025-07-01T09:14:35.276Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/e8/100c3d114b1a0bf4042f27e0f87d2f25e857e838034e98ca98fe7b8c0a9c/pillow-11.3.0-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:30b7c02f3899d10f13d7a48163c8969e4e653f8b43416d23d13d1bbfdc93b9f8", size = 2170652, upload-time = "2025-07-01T09:14:37.203Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/86/3f758a28a6e381758545f7cdb4942e1cb79abd271bea932998fc0db93cb6/pillow-11.3.0-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:7859a4cc7c9295f5838015d8cc0a9c215b77e43d07a25e460f35cf516df8626f", size = 2227443, upload-time = "2025-07-01T09:14:39.344Z" },
-    { url = "https://files.pythonhosted.org/packages/01/f4/91d5b3ffa718df2f53b0dc109877993e511f4fd055d7e9508682e8aba092/pillow-11.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:ec1ee50470b0d050984394423d96325b744d55c701a439d2bd66089bff963d3c", size = 5278474, upload-time = "2025-07-01T09:14:41.843Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/0e/37d7d3eca6c879fbd9dba21268427dffda1ab00d4eb05b32923d4fbe3b12/pillow-11.3.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7db51d222548ccfd274e4572fdbf3e810a5e66b00608862f947b163e613b67dd", size = 4686038, upload-time = "2025-07-01T09:14:44.008Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/b0/3426e5c7f6565e752d81221af9d3676fdbb4f352317ceafd42899aaf5d8a/pillow-11.3.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2d6fcc902a24ac74495df63faad1884282239265c6839a0a6416d33faedfae7e", size = 5864407, upload-time = "2025-07-03T13:10:15.628Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/c1/c6c423134229f2a221ee53f838d4be9d82bab86f7e2f8e75e47b6bf6cd77/pillow-11.3.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f0f5d8f4a08090c6d6d578351a2b91acf519a54986c055af27e7a93feae6d3f1", size = 7639094, upload-time = "2025-07-03T13:10:21.857Z" },
-    { url = "https://files.pythonhosted.org/packages/ba/c9/09e6746630fe6372c67c648ff9deae52a2bc20897d51fa293571977ceb5d/pillow-11.3.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c37d8ba9411d6003bba9e518db0db0c58a680ab9fe5179f040b0463644bc9805", size = 5973503, upload-time = "2025-07-01T09:14:45.698Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/1c/a2a29649c0b1983d3ef57ee87a66487fdeb45132df66ab30dd37f7dbe162/pillow-11.3.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:13f87d581e71d9189ab21fe0efb5a23e9f28552d5be6979e84001d3b8505abe8", size = 6642574, upload-time = "2025-07-01T09:14:47.415Z" },
-    { url = "https://files.pythonhosted.org/packages/36/de/d5cc31cc4b055b6c6fd990e3e7f0f8aaf36229a2698501bcb0cdf67c7146/pillow-11.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:023f6d2d11784a465f09fd09a34b150ea4672e85fb3d05931d89f373ab14abb2", size = 6084060, upload-time = "2025-07-01T09:14:49.636Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/ea/502d938cbaeec836ac28a9b730193716f0114c41325db428e6b280513f09/pillow-11.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:45dfc51ac5975b938e9809451c51734124e73b04d0f0ac621649821a63852e7b", size = 6721407, upload-time = "2025-07-01T09:14:51.962Z" },
-    { url = "https://files.pythonhosted.org/packages/45/9c/9c5e2a73f125f6cbc59cc7087c8f2d649a7ae453f83bd0362ff7c9e2aee2/pillow-11.3.0-cp313-cp313-win32.whl", hash = "sha256:a4d336baed65d50d37b88ca5b60c0fa9d81e3a87d4a7930d3880d1624d5b31f3", size = 6273841, upload-time = "2025-07-01T09:14:54.142Z" },
-    { url = "https://files.pythonhosted.org/packages/23/85/397c73524e0cd212067e0c969aa245b01d50183439550d24d9f55781b776/pillow-11.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:0bce5c4fd0921f99d2e858dc4d4d64193407e1b99478bc5cacecba2311abde51", size = 6978450, upload-time = "2025-07-01T09:14:56.436Z" },
-    { url = "https://files.pythonhosted.org/packages/17/d2/622f4547f69cd173955194b78e4d19ca4935a1b0f03a302d655c9f6aae65/pillow-11.3.0-cp313-cp313-win_arm64.whl", hash = "sha256:1904e1264881f682f02b7f8167935cce37bc97db457f8e7849dc3a6a52b99580", size = 2423055, upload-time = "2025-07-01T09:14:58.072Z" },
-    { url = "https://files.pythonhosted.org/packages/dd/80/a8a2ac21dda2e82480852978416cfacd439a4b490a501a288ecf4fe2532d/pillow-11.3.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:4c834a3921375c48ee6b9624061076bc0a32a60b5532b322cc0ea64e639dd50e", size = 5281110, upload-time = "2025-07-01T09:14:59.79Z" },
-    { url = "https://files.pythonhosted.org/packages/44/d6/b79754ca790f315918732e18f82a8146d33bcd7f4494380457ea89eb883d/pillow-11.3.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5e05688ccef30ea69b9317a9ead994b93975104a677a36a8ed8106be9260aa6d", size = 4689547, upload-time = "2025-07-01T09:15:01.648Z" },
-    { url = "https://files.pythonhosted.org/packages/49/20/716b8717d331150cb00f7fdd78169c01e8e0c219732a78b0e59b6bdb2fd6/pillow-11.3.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1019b04af07fc0163e2810167918cb5add8d74674b6267616021ab558dc98ced", size = 5901554, upload-time = "2025-07-03T13:10:27.018Z" },
-    { url = "https://files.pythonhosted.org/packages/74/cf/a9f3a2514a65bb071075063a96f0a5cf949c2f2fce683c15ccc83b1c1cab/pillow-11.3.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:f944255db153ebb2b19c51fe85dd99ef0ce494123f21b9db4877ffdfc5590c7c", size = 7669132, upload-time = "2025-07-03T13:10:33.01Z" },
-    { url = "https://files.pythonhosted.org/packages/98/3c/da78805cbdbee9cb43efe8261dd7cc0b4b93f2ac79b676c03159e9db2187/pillow-11.3.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1f85acb69adf2aaee8b7da124efebbdb959a104db34d3a2cb0f3793dbae422a8", size = 6005001, upload-time = "2025-07-01T09:15:03.365Z" },
-    { url = "https://files.pythonhosted.org/packages/6c/fa/ce044b91faecf30e635321351bba32bab5a7e034c60187fe9698191aef4f/pillow-11.3.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:05f6ecbeff5005399bb48d198f098a9b4b6bdf27b8487c7f38ca16eeb070cd59", size = 6668814, upload-time = "2025-07-01T09:15:05.655Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/51/90f9291406d09bf93686434f9183aba27b831c10c87746ff49f127ee80cb/pillow-11.3.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:a7bc6e6fd0395bc052f16b1a8670859964dbd7003bd0af2ff08342eb6e442cfe", size = 6113124, upload-time = "2025-07-01T09:15:07.358Z" },
-    { url = "https://files.pythonhosted.org/packages/cd/5a/6fec59b1dfb619234f7636d4157d11fb4e196caeee220232a8d2ec48488d/pillow-11.3.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:83e1b0161c9d148125083a35c1c5a89db5b7054834fd4387499e06552035236c", size = 6747186, upload-time = "2025-07-01T09:15:09.317Z" },
-    { url = "https://files.pythonhosted.org/packages/49/6b/00187a044f98255225f172de653941e61da37104a9ea60e4f6887717e2b5/pillow-11.3.0-cp313-cp313t-win32.whl", hash = "sha256:2a3117c06b8fb646639dce83694f2f9eac405472713fcb1ae887469c0d4f6788", size = 6277546, upload-time = "2025-07-01T09:15:11.311Z" },
-    { url = "https://files.pythonhosted.org/packages/e8/5c/6caaba7e261c0d75bab23be79f1d06b5ad2a2ae49f028ccec801b0e853d6/pillow-11.3.0-cp313-cp313t-win_amd64.whl", hash = "sha256:857844335c95bea93fb39e0fa2726b4d9d758850b34075a7e3ff4f4fa3aa3b31", size = 6985102, upload-time = "2025-07-01T09:15:13.164Z" },
-    { url = "https://files.pythonhosted.org/packages/f3/7e/b623008460c09a0cb38263c93b828c666493caee2eb34ff67f778b87e58c/pillow-11.3.0-cp313-cp313t-win_arm64.whl", hash = "sha256:8797edc41f3e8536ae4b10897ee2f637235c94f27404cac7297f7b607dd0716e", size = 2424803, upload-time = "2025-07-01T09:15:15.695Z" },
-    { url = "https://files.pythonhosted.org/packages/73/f4/04905af42837292ed86cb1b1dabe03dce1edc008ef14c473c5c7e1443c5d/pillow-11.3.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:d9da3df5f9ea2a89b81bb6087177fb1f4d1c7146d583a3fe5c672c0d94e55e12", size = 5278520, upload-time = "2025-07-01T09:15:17.429Z" },
-    { url = "https://files.pythonhosted.org/packages/41/b0/33d79e377a336247df6348a54e6d2a2b85d644ca202555e3faa0cf811ecc/pillow-11.3.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:0b275ff9b04df7b640c59ec5a3cb113eefd3795a8df80bac69646ef699c6981a", size = 4686116, upload-time = "2025-07-01T09:15:19.423Z" },
-    { url = "https://files.pythonhosted.org/packages/49/2d/ed8bc0ab219ae8768f529597d9509d184fe8a6c4741a6864fea334d25f3f/pillow-11.3.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0743841cabd3dba6a83f38a92672cccbd69af56e3e91777b0ee7f4dba4385632", size = 5864597, upload-time = "2025-07-03T13:10:38.404Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/3d/b932bb4225c80b58dfadaca9d42d08d0b7064d2d1791b6a237f87f661834/pillow-11.3.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2465a69cf967b8b49ee1b96d76718cd98c4e925414ead59fdf75cf0fd07df673", size = 7638246, upload-time = "2025-07-03T13:10:44.987Z" },
-    { url = "https://files.pythonhosted.org/packages/09/b5/0487044b7c096f1b48f0d7ad416472c02e0e4bf6919541b111efd3cae690/pillow-11.3.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:41742638139424703b4d01665b807c6468e23e699e8e90cffefe291c5832b027", size = 5973336, upload-time = "2025-07-01T09:15:21.237Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/2d/524f9318f6cbfcc79fbc004801ea6b607ec3f843977652fdee4857a7568b/pillow-11.3.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:93efb0b4de7e340d99057415c749175e24c8864302369e05914682ba642e5d77", size = 6642699, upload-time = "2025-07-01T09:15:23.186Z" },
-    { url = "https://files.pythonhosted.org/packages/6f/d2/a9a4f280c6aefedce1e8f615baaa5474e0701d86dd6f1dede66726462bbd/pillow-11.3.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:7966e38dcd0fa11ca390aed7c6f20454443581d758242023cf36fcb319b1a874", size = 6083789, upload-time = "2025-07-01T09:15:25.1Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/54/86b0cd9dbb683a9d5e960b66c7379e821a19be4ac5810e2e5a715c09a0c0/pillow-11.3.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:98a9afa7b9007c67ed84c57c9e0ad86a6000da96eaa638e4f8abe5b65ff83f0a", size = 6720386, upload-time = "2025-07-01T09:15:27.378Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/95/88efcaf384c3588e24259c4203b909cbe3e3c2d887af9e938c2022c9dd48/pillow-11.3.0-cp314-cp314-win32.whl", hash = "sha256:02a723e6bf909e7cea0dac1b0e0310be9d7650cd66222a5f1c571455c0a45214", size = 6370911, upload-time = "2025-07-01T09:15:29.294Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/cc/934e5820850ec5eb107e7b1a72dd278140731c669f396110ebc326f2a503/pillow-11.3.0-cp314-cp314-win_amd64.whl", hash = "sha256:a418486160228f64dd9e9efcd132679b7a02a5f22c982c78b6fc7dab3fefb635", size = 7117383, upload-time = "2025-07-01T09:15:31.128Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/e9/9c0a616a71da2a5d163aa37405e8aced9a906d574b4a214bede134e731bc/pillow-11.3.0-cp314-cp314-win_arm64.whl", hash = "sha256:155658efb5e044669c08896c0c44231c5e9abcaadbc5cd3648df2f7c0b96b9a6", size = 2511385, upload-time = "2025-07-01T09:15:33.328Z" },
-    { url = "https://files.pythonhosted.org/packages/1a/33/c88376898aff369658b225262cd4f2659b13e8178e7534df9e6e1fa289f6/pillow-11.3.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:59a03cdf019efbfeeed910bf79c7c93255c3d54bc45898ac2a4140071b02b4ae", size = 5281129, upload-time = "2025-07-01T09:15:35.194Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/70/d376247fb36f1844b42910911c83a02d5544ebd2a8bad9efcc0f707ea774/pillow-11.3.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:f8a5827f84d973d8636e9dc5764af4f0cf2318d26744b3d902931701b0d46653", size = 4689580, upload-time = "2025-07-01T09:15:37.114Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/1c/537e930496149fbac69efd2fc4329035bbe2e5475b4165439e3be9cb183b/pillow-11.3.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ee92f2fd10f4adc4b43d07ec5e779932b4eb3dbfbc34790ada5a6669bc095aa6", size = 5902860, upload-time = "2025-07-03T13:10:50.248Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/57/80f53264954dcefeebcf9dae6e3eb1daea1b488f0be8b8fef12f79a3eb10/pillow-11.3.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c96d333dcf42d01f47b37e0979b6bd73ec91eae18614864622d9b87bbd5bbf36", size = 7670694, upload-time = "2025-07-03T13:10:56.432Z" },
-    { url = "https://files.pythonhosted.org/packages/70/ff/4727d3b71a8578b4587d9c276e90efad2d6fe0335fd76742a6da08132e8c/pillow-11.3.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4c96f993ab8c98460cd0c001447bff6194403e8b1d7e149ade5f00594918128b", size = 6005888, upload-time = "2025-07-01T09:15:39.436Z" },
-    { url = "https://files.pythonhosted.org/packages/05/ae/716592277934f85d3be51d7256f3636672d7b1abfafdc42cf3f8cbd4b4c8/pillow-11.3.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:41342b64afeba938edb034d122b2dda5db2139b9a4af999729ba8818e0056477", size = 6670330, upload-time = "2025-07-01T09:15:41.269Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/bb/7fe6cddcc8827b01b1a9766f5fdeb7418680744f9082035bdbabecf1d57f/pillow-11.3.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:068d9c39a2d1b358eb9f245ce7ab1b5c3246c7c8c7d9ba58cfa5b43146c06e50", size = 6114089, upload-time = "2025-07-01T09:15:43.13Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/f5/06bfaa444c8e80f1a8e4bff98da9c83b37b5be3b1deaa43d27a0db37ef84/pillow-11.3.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:a1bc6ba083b145187f648b667e05a2534ecc4b9f2784c2cbe3089e44868f2b9b", size = 6748206, upload-time = "2025-07-01T09:15:44.937Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/77/bc6f92a3e8e6e46c0ca78abfffec0037845800ea38c73483760362804c41/pillow-11.3.0-cp314-cp314t-win32.whl", hash = "sha256:118ca10c0d60b06d006be10a501fd6bbdfef559251ed31b794668ed569c87e12", size = 6377370, upload-time = "2025-07-01T09:15:46.673Z" },
-    { url = "https://files.pythonhosted.org/packages/4a/82/3a721f7d69dca802befb8af08b7c79ebcab461007ce1c18bd91a5d5896f9/pillow-11.3.0-cp314-cp314t-win_amd64.whl", hash = "sha256:8924748b688aa210d79883357d102cd64690e56b923a186f35a82cbc10f997db", size = 7121500, upload-time = "2025-07-01T09:15:48.512Z" },
-    { url = "https://files.pythonhosted.org/packages/89/c7/5572fa4a3f45740eaab6ae86fcdf7195b55beac1371ac8c619d880cfe948/pillow-11.3.0-cp314-cp314t-win_arm64.whl", hash = "sha256:79ea0d14d3ebad43ec77ad5272e6ff9bba5b679ef73375ea760261207fa8e0aa", size = 2512835, upload-time = "2025-07-01T09:15:50.399Z" },
+    { url = "https://files.pythonhosted.org/packages/07/d3/8df65da0d4df36b094351dce696f2989bec731d4f10e743b1c5f4da4d3bf/pillow-12.1.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ab323b787d6e18b3d91a72fc99b1a2c28651e4358749842b8f8dfacd28ef2052", size = 5262803, upload-time = "2026-02-11T04:20:47.653Z" },
+    { url = "https://files.pythonhosted.org/packages/d6/71/5026395b290ff404b836e636f51d7297e6c83beceaa87c592718747e670f/pillow-12.1.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:adebb5bee0f0af4909c30db0d890c773d1a92ffe83da908e2e9e720f8edf3984", size = 4657601, upload-time = "2026-02-11T04:20:49.328Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/2e/1001613d941c67442f745aff0f7cc66dd8df9a9c084eb497e6a543ee6f7e/pillow-12.1.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:bb66b7cc26f50977108790e2456b7921e773f23db5630261102233eb355a3b79", size = 6234995, upload-time = "2026-02-11T04:20:51.032Z" },
+    { url = "https://files.pythonhosted.org/packages/07/26/246ab11455b2549b9233dbd44d358d033a2f780fa9007b61a913c5b2d24e/pillow-12.1.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:aee2810642b2898bb187ced9b349e95d2a7272930796e022efaf12e99dccd293", size = 8045012, upload-time = "2026-02-11T04:20:52.882Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/8b/07587069c27be7535ac1fe33874e32de118fbd34e2a73b7f83436a88368c/pillow-12.1.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a0b1cd6232e2b618adcc54d9882e4e662a089d5768cd188f7c245b4c8c44a397", size = 6349638, upload-time = "2026-02-11T04:20:54.444Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/79/6df7b2ee763d619cda2fb4fea498e5f79d984dae304d45a8999b80d6cf5c/pillow-12.1.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7aac39bcf8d4770d089588a2e1dd111cbaa42df5a94be3114222057d68336bd0", size = 7041540, upload-time = "2026-02-11T04:20:55.97Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/5e/2ba19e7e7236d7529f4d873bdaf317a318896bac289abebd4bb00ef247f0/pillow-12.1.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ab174cd7d29a62dd139c44bf74b698039328f45cb03b4596c43473a46656b2f3", size = 6462613, upload-time = "2026-02-11T04:20:57.542Z" },
+    { url = "https://files.pythonhosted.org/packages/03/03/31216ec124bb5c3dacd74ce8efff4cc7f52643653bad4825f8f08c697743/pillow-12.1.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:339ffdcb7cbeaa08221cd401d517d4b1fe7a9ed5d400e4a8039719238620ca35", size = 7166745, upload-time = "2026-02-11T04:20:59.196Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/e7/7c4552d80052337eb28653b617eafdef39adfb137c49dd7e831b8dc13bc5/pillow-12.1.1-cp312-cp312-win32.whl", hash = "sha256:5d1f9575a12bed9e9eedd9a4972834b08c97a352bd17955ccdebfeca5913fa0a", size = 6328823, upload-time = "2026-02-11T04:21:01.385Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/17/688626d192d7261bbbf98846fc98995726bddc2c945344b65bec3a29d731/pillow-12.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:21329ec8c96c6e979cd0dfd29406c40c1d52521a90544463057d2aaa937d66a6", size = 7033367, upload-time = "2026-02-11T04:21:03.536Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/fe/a0ef1f73f939b0eca03ee2c108d0043a87468664770612602c63266a43c4/pillow-12.1.1-cp312-cp312-win_arm64.whl", hash = "sha256:af9a332e572978f0218686636610555ae3defd1633597be015ed50289a03c523", size = 2453811, upload-time = "2026-02-11T04:21:05.116Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/11/6db24d4bd7685583caeae54b7009584e38da3c3d4488ed4cd25b439de486/pillow-12.1.1-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:d242e8ac078781f1de88bf823d70c1a9b3c7950a44cdf4b7c012e22ccbcd8e4e", size = 4062689, upload-time = "2026-02-11T04:21:06.804Z" },
+    { url = "https://files.pythonhosted.org/packages/33/c0/ce6d3b1fe190f0021203e0d9b5b99e57843e345f15f9ef22fcd43842fd21/pillow-12.1.1-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:02f84dfad02693676692746df05b89cf25597560db2857363a208e393429f5e9", size = 4138535, upload-time = "2026-02-11T04:21:08.452Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/c6/d5eb6a4fb32a3f9c21a8c7613ec706534ea1cf9f4b3663e99f0d83f6fca8/pillow-12.1.1-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:e65498daf4b583091ccbb2556c7000abf0f3349fcd57ef7adc9a84a394ed29f6", size = 3601364, upload-time = "2026-02-11T04:21:10.194Z" },
+    { url = "https://files.pythonhosted.org/packages/14/a1/16c4b823838ba4c9c52c0e6bbda903a3fe5a1bdbf1b8eb4fff7156f3e318/pillow-12.1.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6c6db3b84c87d48d0088943bf33440e0c42370b99b1c2a7989216f7b42eede60", size = 5262561, upload-time = "2026-02-11T04:21:11.742Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/ad/ad9dc98ff24f485008aa5cdedaf1a219876f6f6c42a4626c08bc4e80b120/pillow-12.1.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:8b7e5304e34942bf62e15184219a7b5ad4ff7f3bb5cca4d984f37df1a0e1aee2", size = 4657460, upload-time = "2026-02-11T04:21:13.786Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/1b/f1a4ea9a895b5732152789326202a82464d5254759fbacae4deea3069334/pillow-12.1.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:18e5bddd742a44b7e6b1e773ab5db102bd7a94c32555ba656e76d319d19c3850", size = 6232698, upload-time = "2026-02-11T04:21:15.949Z" },
+    { url = "https://files.pythonhosted.org/packages/95/f4/86f51b8745070daf21fd2e5b1fe0eb35d4db9ca26e6d58366562fb56a743/pillow-12.1.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:fc44ef1f3de4f45b50ccf9136999d71abb99dca7706bc75d222ed350b9fd2289", size = 8041706, upload-time = "2026-02-11T04:21:17.723Z" },
+    { url = "https://files.pythonhosted.org/packages/29/9b/d6ecd956bb1266dd1045e995cce9b8d77759e740953a1c9aad9502a0461e/pillow-12.1.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5a8eb7ed8d4198bccbd07058416eeec51686b498e784eda166395a23eb99138e", size = 6346621, upload-time = "2026-02-11T04:21:19.547Z" },
+    { url = "https://files.pythonhosted.org/packages/71/24/538bff45bde96535d7d998c6fed1a751c75ac7c53c37c90dc2601b243893/pillow-12.1.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:47b94983da0c642de92ced1702c5b6c292a84bd3a8e1d1702ff923f183594717", size = 7038069, upload-time = "2026-02-11T04:21:21.378Z" },
+    { url = "https://files.pythonhosted.org/packages/94/0e/58cb1a6bc48f746bc4cb3adb8cabff73e2742c92b3bf7a220b7cf69b9177/pillow-12.1.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:518a48c2aab7ce596d3bf79d0e275661b846e86e4d0e7dec34712c30fe07f02a", size = 6460040, upload-time = "2026-02-11T04:21:23.148Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/57/9045cb3ff11eeb6c1adce3b2d60d7d299d7b273a2e6c8381a524abfdc474/pillow-12.1.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a550ae29b95c6dc13cf69e2c9dc5747f814c54eeb2e32d683e5e93af56caa029", size = 7164523, upload-time = "2026-02-11T04:21:25.01Z" },
+    { url = "https://files.pythonhosted.org/packages/73/f2/9be9cb99f2175f0d4dbadd6616ce1bf068ee54a28277ea1bf1fbf729c250/pillow-12.1.1-cp313-cp313-win32.whl", hash = "sha256:a003d7422449f6d1e3a34e3dd4110c22148336918ddbfc6a32581cd54b2e0b2b", size = 6332552, upload-time = "2026-02-11T04:21:27.238Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/eb/b0834ad8b583d7d9d42b80becff092082a1c3c156bb582590fcc973f1c7c/pillow-12.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:344cf1e3dab3be4b1fa08e449323d98a2a3f819ad20f4b22e77a0ede31f0faa1", size = 7040108, upload-time = "2026-02-11T04:21:29.462Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/7d/fc09634e2aabdd0feabaff4a32f4a7d97789223e7c2042fd805ea4b4d2c2/pillow-12.1.1-cp313-cp313-win_arm64.whl", hash = "sha256:5c0dd1636633e7e6a0afe7bf6a51a14992b7f8e60de5789018ebbdfae55b040a", size = 2453712, upload-time = "2026-02-11T04:21:31.072Z" },
+    { url = "https://files.pythonhosted.org/packages/19/2a/b9d62794fc8a0dd14c1943df68347badbd5511103e0d04c035ffe5cf2255/pillow-12.1.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0330d233c1a0ead844fc097a7d16c0abff4c12e856c0b325f231820fee1f39da", size = 5264880, upload-time = "2026-02-11T04:21:32.865Z" },
+    { url = "https://files.pythonhosted.org/packages/26/9d/e03d857d1347fa5ed9247e123fcd2a97b6220e15e9cb73ca0a8d91702c6e/pillow-12.1.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5dae5f21afb91322f2ff791895ddd8889e5e947ff59f71b46041c8ce6db790bc", size = 4660616, upload-time = "2026-02-11T04:21:34.97Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/ec/8a6d22afd02570d30954e043f09c32772bfe143ba9285e2fdb11284952cd/pillow-12.1.1-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2e0c664be47252947d870ac0d327fea7e63985a08794758aa8af5b6cb6ec0c9c", size = 6269008, upload-time = "2026-02-11T04:21:36.623Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/1d/6d875422c9f28a4a361f495a5f68d9de4a66941dc2c619103ca335fa6446/pillow-12.1.1-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:691ab2ac363b8217f7d31b3497108fb1f50faab2f75dfb03284ec2f217e87bf8", size = 8073226, upload-time = "2026-02-11T04:21:38.585Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/cd/134b0b6ee5eda6dc09e25e24b40fdafe11a520bc725c1d0bbaa5e00bf95b/pillow-12.1.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e9e8064fb1cc019296958595f6db671fba95209e3ceb0c4734c9baf97de04b20", size = 6380136, upload-time = "2026-02-11T04:21:40.562Z" },
+    { url = "https://files.pythonhosted.org/packages/7a/a9/7628f013f18f001c1b98d8fffe3452f306a70dc6aba7d931019e0492f45e/pillow-12.1.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:472a8d7ded663e6162dafdf20015c486a7009483ca671cece7a9279b512fcb13", size = 7067129, upload-time = "2026-02-11T04:21:42.521Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/f8/66ab30a2193b277785601e82ee2d49f68ea575d9637e5e234faaa98efa4c/pillow-12.1.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:89b54027a766529136a06cfebeecb3a04900397a3590fd252160b888479517bf", size = 6491807, upload-time = "2026-02-11T04:21:44.22Z" },
+    { url = "https://files.pythonhosted.org/packages/da/0b/a877a6627dc8318fdb84e357c5e1a758c0941ab1ddffdafd231983788579/pillow-12.1.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:86172b0831b82ce4f7877f280055892b31179e1576aa00d0df3bb1bbf8c3e524", size = 7190954, upload-time = "2026-02-11T04:21:46.114Z" },
+    { url = "https://files.pythonhosted.org/packages/83/43/6f732ff85743cf746b1361b91665d9f5155e1483817f693f8d57ea93147f/pillow-12.1.1-cp313-cp313t-win32.whl", hash = "sha256:44ce27545b6efcf0fdbdceb31c9a5bdea9333e664cda58a7e674bb74608b3986", size = 6336441, upload-time = "2026-02-11T04:21:48.22Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/44/e865ef3986611bb75bfabdf94a590016ea327833f434558801122979cd0e/pillow-12.1.1-cp313-cp313t-win_amd64.whl", hash = "sha256:a285e3eb7a5a45a2ff504e31f4a8d1b12ef62e84e5411c6804a42197c1cf586c", size = 7045383, upload-time = "2026-02-11T04:21:50.015Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/c6/f4fb24268d0c6908b9f04143697ea18b0379490cb74ba9e8d41b898bd005/pillow-12.1.1-cp313-cp313t-win_arm64.whl", hash = "sha256:cc7d296b5ea4d29e6570dabeaed58d31c3fea35a633a69679fb03d7664f43fb3", size = 2456104, upload-time = "2026-02-11T04:21:51.633Z" },
+    { url = "https://files.pythonhosted.org/packages/03/d0/bebb3ffbf31c5a8e97241476c4cf8b9828954693ce6744b4a2326af3e16b/pillow-12.1.1-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:417423db963cb4be8bac3fc1204fe61610f6abeed1580a7a2cbb2fbda20f12af", size = 4062652, upload-time = "2026-02-11T04:21:53.19Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/c0/0e16fb0addda4851445c28f8350d8c512f09de27bbb0d6d0bbf8b6709605/pillow-12.1.1-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:b957b71c6b2387610f556a7eb0828afbe40b4a98036fc0d2acfa5a44a0c2036f", size = 4138823, upload-time = "2026-02-11T04:22:03.088Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/fb/6170ec655d6f6bb6630a013dd7cf7bc218423d7b5fa9071bf63dc32175ae/pillow-12.1.1-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:097690ba1f2efdeb165a20469d59d8bb03c55fb6621eb2041a060ae8ea3e9642", size = 3601143, upload-time = "2026-02-11T04:22:04.909Z" },
+    { url = "https://files.pythonhosted.org/packages/59/04/dc5c3f297510ba9a6837cbb318b87dd2b8f73eb41a43cc63767f65cb599c/pillow-12.1.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2815a87ab27848db0321fb78c7f0b2c8649dee134b7f2b80c6a45c6831d75ccd", size = 5266254, upload-time = "2026-02-11T04:22:07.656Z" },
+    { url = "https://files.pythonhosted.org/packages/05/30/5db1236b0d6313f03ebf97f5e17cda9ca060f524b2fcc875149a8360b21c/pillow-12.1.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:f7ed2c6543bad5a7d5530eb9e78c53132f93dfa44a28492db88b41cdab885202", size = 4657499, upload-time = "2026-02-11T04:22:09.613Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/18/008d2ca0eb612e81968e8be0bbae5051efba24d52debf930126d7eaacbba/pillow-12.1.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:652a2c9ccfb556235b2b501a3a7cf3742148cd22e04b5625c5fe057ea3e3191f", size = 6232137, upload-time = "2026-02-11T04:22:11.434Z" },
+    { url = "https://files.pythonhosted.org/packages/70/f1/f14d5b8eeb4b2cd62b9f9f847eb6605f103df89ef619ac68f92f748614ea/pillow-12.1.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d6e4571eedf43af33d0fc233a382a76e849badbccdf1ac438841308652a08e1f", size = 8042721, upload-time = "2026-02-11T04:22:13.321Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/d6/17824509146e4babbdabf04d8171491fa9d776f7061ff6e727522df9bd03/pillow-12.1.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b574c51cf7d5d62e9be37ba446224b59a2da26dc4c1bb2ecbe936a4fb1a7cb7f", size = 6347798, upload-time = "2026-02-11T04:22:15.449Z" },
+    { url = "https://files.pythonhosted.org/packages/d1/ee/c85a38a9ab92037a75615aba572c85ea51e605265036e00c5b67dfafbfe2/pillow-12.1.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a37691702ed687799de29a518d63d4682d9016932db66d4e90c345831b02fb4e", size = 7039315, upload-time = "2026-02-11T04:22:17.24Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/f3/bc8ccc6e08a148290d7523bde4d9a0d6c981db34631390dc6e6ec34cacf6/pillow-12.1.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:f95c00d5d6700b2b890479664a06e754974848afaae5e21beb4d83c106923fd0", size = 6462360, upload-time = "2026-02-11T04:22:19.111Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/ab/69a42656adb1d0665ab051eec58a41f169ad295cf81ad45406963105408f/pillow-12.1.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:559b38da23606e68681337ad74622c4dbba02254fc9cb4488a305dd5975c7eeb", size = 7165438, upload-time = "2026-02-11T04:22:21.041Z" },
+    { url = "https://files.pythonhosted.org/packages/02/46/81f7aa8941873f0f01d4b55cc543b0a3d03ec2ee30d617a0448bf6bd6dec/pillow-12.1.1-cp314-cp314-win32.whl", hash = "sha256:03edcc34d688572014ff223c125a3f77fb08091e4607e7745002fc214070b35f", size = 6431503, upload-time = "2026-02-11T04:22:22.833Z" },
+    { url = "https://files.pythonhosted.org/packages/40/72/4c245f7d1044b67affc7f134a09ea619d4895333d35322b775b928180044/pillow-12.1.1-cp314-cp314-win_amd64.whl", hash = "sha256:50480dcd74fa63b8e78235957d302d98d98d82ccbfac4c7e12108ba9ecbdba15", size = 7176748, upload-time = "2026-02-11T04:22:24.64Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/ad/8a87bdbe038c5c698736e3348af5c2194ffb872ea52f11894c95f9305435/pillow-12.1.1-cp314-cp314-win_arm64.whl", hash = "sha256:5cb1785d97b0c3d1d1a16bc1d710c4a0049daefc4935f3a8f31f827f4d3d2e7f", size = 2544314, upload-time = "2026-02-11T04:22:26.685Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/9d/efd18493f9de13b87ede7c47e69184b9e859e4427225ea962e32e56a49bc/pillow-12.1.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:1f90cff8aa76835cba5769f0b3121a22bd4eb9e6884cfe338216e557a9a548b8", size = 5268612, upload-time = "2026-02-11T04:22:29.884Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/f1/4f42eb2b388eb2ffc660dcb7f7b556c1015c53ebd5f7f754965ef997585b/pillow-12.1.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1f1be78ce9466a7ee64bfda57bdba0f7cc499d9794d518b854816c41bf0aa4e9", size = 4660567, upload-time = "2026-02-11T04:22:31.799Z" },
+    { url = "https://files.pythonhosted.org/packages/01/54/df6ef130fa43e4b82e32624a7b821a2be1c5653a5fdad8469687a7db4e00/pillow-12.1.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:42fc1f4677106188ad9a55562bbade416f8b55456f522430fadab3cef7cd4e60", size = 6269951, upload-time = "2026-02-11T04:22:33.921Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/48/618752d06cc44bb4aae8ce0cd4e6426871929ed7b46215638088270d9b34/pillow-12.1.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98edb152429ab62a1818039744d8fbb3ccab98a7c29fc3d5fcef158f3f1f68b7", size = 8074769, upload-time = "2026-02-11T04:22:35.877Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/bd/f1d71eb39a72fa088d938655afba3e00b38018d052752f435838961127d8/pillow-12.1.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d470ab1178551dd17fdba0fef463359c41aaa613cdcd7ff8373f54be629f9f8f", size = 6381358, upload-time = "2026-02-11T04:22:37.698Z" },
+    { url = "https://files.pythonhosted.org/packages/64/ef/c784e20b96674ed36a5af839305f55616f8b4f8aa8eeccf8531a6e312243/pillow-12.1.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6408a7b064595afcab0a49393a413732a35788f2a5092fdc6266952ed67de586", size = 7068558, upload-time = "2026-02-11T04:22:39.597Z" },
+    { url = "https://files.pythonhosted.org/packages/73/cb/8059688b74422ae61278202c4e1ad992e8a2e7375227be0a21c6b87ca8d5/pillow-12.1.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:5d8c41325b382c07799a3682c1c258469ea2ff97103c53717b7893862d0c98ce", size = 6493028, upload-time = "2026-02-11T04:22:42.73Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/da/e3c008ed7d2dd1f905b15949325934510b9d1931e5df999bb15972756818/pillow-12.1.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:c7697918b5be27424e9ce568193efd13d925c4481dd364e43f5dff72d33e10f8", size = 7191940, upload-time = "2026-02-11T04:22:44.543Z" },
+    { url = "https://files.pythonhosted.org/packages/01/4a/9202e8d11714c1fc5951f2e1ef362f2d7fbc595e1f6717971d5dd750e969/pillow-12.1.1-cp314-cp314t-win32.whl", hash = "sha256:d2912fd8114fc5545aa3a4b5576512f64c55a03f3ebcca4c10194d593d43ea36", size = 6438736, upload-time = "2026-02-11T04:22:46.347Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/ca/cbce2327eb9885476b3957b2e82eb12c866a8b16ad77392864ad601022ce/pillow-12.1.1-cp314-cp314t-win_amd64.whl", hash = "sha256:4ceb838d4bd9dab43e06c363cab2eebf63846d6a4aeaea283bbdfd8f1a8ed58b", size = 7182894, upload-time = "2026-02-11T04:22:48.114Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/d2/de599c95ba0a973b94410477f8bf0b6f0b5e67360eb89bcb1ad365258beb/pillow-12.1.1-cp314-cp314t-win_arm64.whl", hash = "sha256:7b03048319bfc6170e93bd60728a1af51d3dd7704935feb228c4d4faab35d334", size = 2546446, upload-time = "2026-02-11T04:22:50.342Z" },
 ]
 
 [[package]]
@@ -1674,21 +1727,22 @@ wheels = [
 
 [[package]]
 name = "protobuf"
-version = "6.32.0"
+version = "6.33.5"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/c0/df/fb4a8eeea482eca989b51cffd274aac2ee24e825f0bf3cbce5281fa1567b/protobuf-6.32.0.tar.gz", hash = "sha256:a81439049127067fc49ec1d36e25c6ee1d1a2b7be930675f919258d03c04e7d2", size = 440614, upload-time = "2025-08-14T21:21:25.015Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/25/7c72c307aafc96fa87062aa6291d9f7c94836e43214d43722e86037aac02/protobuf-6.33.5.tar.gz", hash = "sha256:6ddcac2a081f8b7b9642c09406bc6a4290128fce5f471cddd165960bb9119e5c", size = 444465, upload-time = "2026-01-29T21:51:33.494Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/33/18/df8c87da2e47f4f1dcc5153a81cd6bca4e429803f4069a299e236e4dd510/protobuf-6.32.0-cp310-abi3-win32.whl", hash = "sha256:84f9e3c1ff6fb0308dbacb0950d8aa90694b0d0ee68e75719cb044b7078fe741", size = 424409, upload-time = "2025-08-14T21:21:12.366Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/59/0a820b7310f8139bd8d5a9388e6a38e1786d179d6f33998448609296c229/protobuf-6.32.0-cp310-abi3-win_amd64.whl", hash = "sha256:a8bdbb2f009cfc22a36d031f22a625a38b615b5e19e558a7b756b3279723e68e", size = 435735, upload-time = "2025-08-14T21:21:15.046Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/5b/0d421533c59c789e9c9894683efac582c06246bf24bb26b753b149bd88e4/protobuf-6.32.0-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:d52691e5bee6c860fff9a1c86ad26a13afbeb4b168cd4445c922b7e2cf85aaf0", size = 426449, upload-time = "2025-08-14T21:21:16.687Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/7b/607764ebe6c7a23dcee06e054fd1de3d5841b7648a90fd6def9a3bb58c5e/protobuf-6.32.0-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:501fe6372fd1c8ea2a30b4d9be8f87955a64d6be9c88a973996cef5ef6f0abf1", size = 322869, upload-time = "2025-08-14T21:21:18.282Z" },
-    { url = "https://files.pythonhosted.org/packages/40/01/2e730bd1c25392fc32e3268e02446f0d77cb51a2c3a8486b1798e34d5805/protobuf-6.32.0-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:75a2aab2bd1aeb1f5dc7c5f33bcb11d82ea8c055c9becbb41c26a8c43fd7092c", size = 322009, upload-time = "2025-08-14T21:21:19.893Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/f2/80ffc4677aac1bc3519b26bc7f7f5de7fce0ee2f7e36e59e27d8beb32dd1/protobuf-6.32.0-py3-none-any.whl", hash = "sha256:ba377e5b67b908c8f3072a57b63e2c6a4cbd18aea4ed98d2584350dbf46f2783", size = 169287, upload-time = "2025-08-14T21:21:23.515Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/79/af92d0a8369732b027e6d6084251dd8e782c685c72da161bd4a2e00fbabb/protobuf-6.33.5-cp310-abi3-win32.whl", hash = "sha256:d71b040839446bac0f4d162e758bea99c8251161dae9d0983a3b88dee345153b", size = 425769, upload-time = "2026-01-29T21:51:21.751Z" },
+    { url = "https://files.pythonhosted.org/packages/55/75/bb9bc917d10e9ee13dee8607eb9ab963b7cf8be607c46e7862c748aa2af7/protobuf-6.33.5-cp310-abi3-win_amd64.whl", hash = "sha256:3093804752167bcab3998bec9f1048baae6e29505adaf1afd14a37bddede533c", size = 437118, upload-time = "2026-01-29T21:51:24.022Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/6b/e48dfc1191bc5b52950246275bf4089773e91cb5ba3592621723cdddca62/protobuf-6.33.5-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:a5cb85982d95d906df1e2210e58f8e4f1e3cdc088e52c921a041f9c9a0386de5", size = 427766, upload-time = "2026-01-29T21:51:25.413Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/b1/c79468184310de09d75095ed1314b839eb2f72df71097db9d1404a1b2717/protobuf-6.33.5-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:9b71e0281f36f179d00cbcb119cb19dec4d14a81393e5ea220f64b286173e190", size = 324638, upload-time = "2026-01-29T21:51:26.423Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/f5/65d838092fd01c44d16037953fd4c2cc851e783de9b8f02b27ec4ffd906f/protobuf-6.33.5-cp39-abi3-manylinux2014_s390x.whl", hash = "sha256:8afa18e1d6d20af15b417e728e9f60f3aa108ee76f23c3b2c07a2c3b546d3afd", size = 339411, upload-time = "2026-01-29T21:51:27.446Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/53/a9443aa3ca9ba8724fdfa02dd1887c1bcd8e89556b715cfbacca6b63dbec/protobuf-6.33.5-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:cbf16ba3350fb7b889fca858fb215967792dc125b35c7976ca4818bee3521cf0", size = 323465, upload-time = "2026-01-29T21:51:28.925Z" },
+    { url = "https://files.pythonhosted.org/packages/57/bf/2086963c69bdac3d7cff1cc7ff79b8ce5ea0bec6797a017e1be338a46248/protobuf-6.33.5-py3-none-any.whl", hash = "sha256:69915a973dd0f60f31a08b8318b73eab2bd6a392c79184b3612226b0a3f8ec02", size = 170687, upload-time = "2026-01-29T21:51:32.557Z" },
 ]
 
 [[package]]
 name = "pyannote-audio"
-version = "3.1.0"
+version = "3.4.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asteroid-filterbanks" },
@@ -1711,9 +1765,9 @@ dependencies = [
     { name = "torchaudio" },
     { name = "torchmetrics" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/ad/55/7253267c35e2aa9188b1d86cba121eb5bdd91ed12d3194488625a008cae7/pyannote.audio-3.1.0.tar.gz", hash = "sha256:da04705443d3b74607e034d3ca88f8b572c7e9672dd9a4199cab65a0dbc33fad", size = 14812058, upload-time = "2023-11-16T12:26:38.939Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/ec/1e/efe9619c38f1281ddf21640654d8ea9e3f67c459b76f78657b26d8557bbe/pyannote_audio-3.4.0.tar.gz", hash = "sha256:d523d883cb8d37cb6daf99f3ba83f9138bb193646ad71e6eae7deb89d8ddd642", size = 804850, upload-time = "2025-09-09T07:04:51.17Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a1/37/158859ce4c45b5ba2dca40b53b0c10d36f935b7f6d4e737298397167c8b1/pyannote.audio-3.1.0-py2.py3-none-any.whl", hash = "sha256:66ab485728c6e141760e80555cb7a083e7be824cd528cc79b9e6f7d6421a91ae", size = 208592, upload-time = "2023-11-16T12:26:36.726Z" },
+    { url = "https://files.pythonhosted.org/packages/79/13/620c6f711b723653092fd063bfee82a6af5ea3a4d3c42efc53ce623a7f4d/pyannote_audio-3.4.0-py2.py3-none-any.whl", hash = "sha256:36e38f058059f46da3478dda581cda53d9d85a21173a3e70bbdbc3ba93b5e1b7", size = 897789, upload-time = "2025-09-09T07:04:49.464Z" },
 ]
 
 [[package]]
@@ -1857,6 +1911,33 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/6f/9a/e73262f6c6656262b5fdd723ad90f518f579b7bc8622e43a942eec53c938/pydantic_core-2.33.2-cp313-cp313t-win_amd64.whl", hash = "sha256:c2fc0a768ef76c15ab9238afa6da7f69895bb5d1ee83aeea2e3509af4472d0b9", size = 1935777, upload-time = "2025-04-23T18:32:25.088Z" },
 ]
 
+[[package]]
+name = "pydantic-extra-types"
+version = "2.11.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pydantic" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/fd/35/2fee58b1316a73e025728583d3b1447218a97e621933fc776fb8c0f2ebdd/pydantic_extra_types-2.11.0.tar.gz", hash = "sha256:4e9991959d045b75feb775683437a97991d02c138e00b59176571db9ce634f0e", size = 157226, upload-time = "2025-12-31T16:18:27.944Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fe/17/fabd56da47096d240dd45ba627bead0333b0cf0ee8ada9bec579287dadf3/pydantic_extra_types-2.11.0-py3-none-any.whl", hash = "sha256:84b864d250a0fc62535b7ec591e36f2c5b4d1325fa0017eb8cda9aeb63b374a6", size = 74296, upload-time = "2025-12-31T16:18:26.38Z" },
+]
+
+[[package]]
+name = "pydantic-settings"
+version = "2.13.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pydantic" },
+    { name = "python-dotenv" },
+    { name = "typing-inspection" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/52/6d/fffca34caecc4a3f97bda81b2098da5e8ab7efc9a66e819074a11955d87e/pydantic_settings-2.13.1.tar.gz", hash = "sha256:b4c11847b15237fb0171e1462bf540e294affb9b86db4d9aa5c01730bdbe4025", size = 223826, upload-time = "2026-02-19T13:45:08.055Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/00/4b/ccc026168948fec4f7555b9164c724cf4125eac006e176541483d2c959be/pydantic_settings-2.13.1-py3-none-any.whl", hash = "sha256:d56fd801823dbeae7f0975e1f8c8e25c258eb75d278ea7abb5d9cebb01b56237", size = 58929, upload-time = "2026-02-19T13:45:06.034Z" },
+]
+
 [[package]]
 name = "pygments"
 version = "2.19.2"
@@ -1907,11 +1988,11 @@ wheels = [
 
 [[package]]
 name = "python-multipart"
-version = "0.0.20"
+version = "0.0.22"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/f3/87/f44d7c9f274c7ee665a29b885ec97089ec5dc034c7f3fafa03da9e39a09e/python_multipart-0.0.20.tar.gz", hash = "sha256:8dd0cab45b8e23064ae09147625994d090fa46f5b0d1e13af944c331a7fa9d13", size = 37158, upload-time = "2024-12-16T19:45:46.972Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/01/979e98d542a70714b0cb2b6728ed0b7c46792b695e3eaec3e20711271ca3/python_multipart-0.0.22.tar.gz", hash = "sha256:7340bef99a7e0032613f56dc36027b959fd3b30a787ed62d310e951f7c3a3a58", size = 37612, upload-time = "2026-01-25T10:15:56.219Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104", size = 24546, upload-time = "2024-12-16T19:45:44.423Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/d0/397f9626e711ff749a95d96b7af99b9c566a9bb5129b8e4c10fc4d100304/python_multipart-0.0.22-py3-none-any.whl", hash = "sha256:2b2cd894c83d21bf49d702499531c7bafd057d730c201782048f7945d82de155", size = 24579, upload-time = "2026-01-25T10:15:54.811Z" },
 ]
 
 [[package]]
@@ -1988,11 +2069,13 @@ name = "reflector-gpu"
 version = "0.1.0"
 source = { virtual = "." }
 dependencies = [
+    { name = "av" },
     { name = "fastapi", extra = ["standard"] },
     { name = "faster-whisper" },
     { name = "librosa" },
     { name = "numpy" },
     { name = "pyannote-audio" },
+    { name = "pytorch-lightning" },
     { name = "sentencepiece" },
     { name = "silero-vad" },
     { name = "torch" },
@@ -2003,13 +2086,15 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
+    { name = "av", specifier = ">=13.1.0" },
     { name = "fastapi", extras = ["standard"], specifier = ">=0.116.1" },
     { name = "faster-whisper", specifier = ">=1.1.0" },
     { name = "librosa", specifier = "==0.10.1" },
     { name = "numpy", specifier = "<2" },
-    { name = "pyannote-audio", specifier = "==3.1.0" },
+    { name = "pyannote-audio", specifier = "==3.4.0" },
+    { name = "pytorch-lightning", specifier = "<2.6" },
     { name = "sentencepiece" },
-    { name = "silero-vad", specifier = "==5.1.0" },
+    { name = "silero-vad", specifier = "==5.1.2" },
     { name = "torch", specifier = ">=2.3.0" },
     { name = "torchaudio", specifier = ">=2.3.0" },
     { name = "transformers", specifier = ">=4.35.0" },
@@ -2389,16 +2474,16 @@ wheels = [
 
 [[package]]
 name = "silero-vad"
-version = "5.1"
+version = "5.1.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "onnxruntime" },
     { name = "torch" },
     { name = "torchaudio" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/7c/5d/b912e45d21b8b61859a552554893222d2cdebfd0f9afa7e8ba69c7a3441a/silero_vad-5.1.tar.gz", hash = "sha256:c644275ba5df06cee596cc050ba0bd1e0f5237d1abfa44d58dd4618f6e77434d", size = 3996829, upload-time = "2024-07-09T13:19:24.181Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/b1/b4/d0311b2e6220a11f8f4699f4a278cb088131573286cdfe804c87c7eb5123/silero_vad-5.1.2.tar.gz", hash = "sha256:c442971160026d2d7aa0ad83f0c7ee86c89797a65289fe625c8ea59fc6fb828d", size = 5098526, upload-time = "2024-10-09T09:50:47.019Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0e/be/0fdbc72030b93d6f55107490d5d2185ddf0dbabdc921f589649d3e92ccd5/silero_vad-5.1-py3-none-any.whl", hash = "sha256:ecb50b484f538f7a962ce5cd3c07120d9db7b9d5a0c5861ccafe459856f22c8f", size = 3939986, upload-time = "2024-07-09T13:19:21.383Z" },
+    { url = "https://files.pythonhosted.org/packages/98/f7/5ae11d13fbb733cd3bfd7ff1c3a3902e6f55437df4b72307c1f168146268/silero_vad-5.1.2-py3-none-any.whl", hash = "sha256:93b41953d7774b165407fda6b533c119c5803864e367d5034dc626c82cfdf661", size = 5026737, upload-time = "2024-10-09T09:50:44.355Z" },
 ]
 
 [[package]]
@@ -2515,15 +2600,15 @@ wheels = [
 
 [[package]]
 name = "starlette"
-version = "0.47.3"
+version = "0.49.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio" },
     { name = "typing-extensions", marker = "python_full_version < '3.13'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/15/b9/cc3017f9a9c9b6e27c5106cc10cc7904653c3eec0729793aec10479dd669/starlette-0.47.3.tar.gz", hash = "sha256:6bc94f839cc176c4858894f1f8908f0ab79dfec1a6b8402f6da9be26ebea52e9", size = 2584144, upload-time = "2025-08-24T13:36:42.122Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1b/3f/507c21db33b66fb027a332f2cb3abbbe924cc3a79ced12f01ed8645955c9/starlette-0.49.1.tar.gz", hash = "sha256:481a43b71e24ed8c43b11ea02f5353d77840e01480881b8cb5a26b8cae64a8cb", size = 2654703, upload-time = "2025-10-28T17:34:10.928Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ce/fd/901cfa59aaa5b30a99e16876f11abe38b59a1a2c51ffb3d7142bb6089069/starlette-0.47.3-py3-none-any.whl", hash = "sha256:89c0778ca62a76b826101e7c709e70680a1699ca7da6b44d38eb0a7e61fe4b51", size = 72991, upload-time = "2025-08-24T13:36:40.887Z" },
+    { url = "https://files.pythonhosted.org/packages/51/da/545b75d420bb23b5d494b0517757b351963e974e79933f01e05c929f20a6/starlette-0.49.1-py3-none-any.whl", hash = "sha256:d92ce9f07e4a3caa3ac13a79523bd18e3bc0042bb8ff2d759a8e7dd0e1859875", size = 74175, upload-time = "2025-10-28T17:34:09.13Z" },
 ]
 
 [[package]]
@@ -2777,14 +2862,14 @@ wheels = [
 
 [[package]]
 name = "typing-inspection"
-version = "0.4.1"
+version = "0.4.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/f8/b1/0c11f5058406b3af7609f121aaa6b609744687f1d158b3c3a5bf4cc94238/typing_inspection-0.4.1.tar.gz", hash = "sha256:6ae134cc0203c33377d43188d4064e9b357dba58cff3185f22924610e70a9d28", size = 75726, upload-time = "2025-05-21T18:55:23.885Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/55/e3/70399cb7dd41c10ac53367ae42139cf4b1ca5f36bb3dc6c9d33acdb43655/typing_inspection-0.4.2.tar.gz", hash = "sha256:ba561c48a67c5958007083d386c3295464928b01faa735ab8547c5692e87f464", size = 75949, upload-time = "2025-10-01T02:14:41.687Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/17/69/cd203477f944c353c31bade965f880aa1061fd6bf05ded0726ca845b6ff7/typing_inspection-0.4.1-py3-none-any.whl", hash = "sha256:389055682238f53b04f7badcb49b989835495a96700ced5dab2d8feae4b26f51", size = 14552, upload-time = "2025-05-21T18:55:22.152Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/9b/47798a6c91d8bdb567fe2698fe81e0c6b7cb7ef4d13da4114b41d239f65d/typing_inspection-0.4.2-py3-none-any.whl", hash = "sha256:4ed1cacbdc298c220f1bd249ed5287caa16f34d44ef4e9c3d0cbad5b521545e7", size = 14611, upload-time = "2025-10-01T02:14:40.154Z" },
 ]
 
 [[package]]
@@ -2798,11 +2883,11 @@ wheels = [
 
 [[package]]
 name = "urllib3"
-version = "2.5.0"
+version = "2.6.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185, upload-time = "2025-06-18T14:07:41.644Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" },
+    { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" },
 ]
 
 [[package]]

node_modules/.yarn-integrity

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

scripts/garage.toml

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

scripts/install-docker-ubuntu.sh

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

scripts/setup-standalone.sh

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

server/.env.example

@@ -66,24 +66,43 @@ TRANSLATE_URL=https://monadical-sas--reflector-translator-web.modal.run
 ## LLM backend (Required)
 ##
 ## Responsible for generating titles, summaries, and topic detection
-## Requires OpenAI API key
+## Supports any OpenAI-compatible endpoint.
 ## =======================================================
 
-## OpenAI API key - get from https://platform.openai.com/account/api-keys
-LLM_API_KEY=sk-your-openai-api-key
-LLM_MODEL=gpt-4o-mini
+## --- Option A: Local LLM via Ollama (recommended for dev) ---
+## Setup: ./scripts/setup-standalone.sh
+## Mac: Ollama runs natively (Metal GPU). Containers reach it via host.docker.internal.
+## Linux: docker compose --profile ollama-gpu up -d (or ollama-cpu for no GPU)
+LLM_URL=http://host.docker.internal:11435/v1
+LLM_MODEL=qwen2.5:14b
+LLM_API_KEY=not-needed
+## Linux with containerized Ollama: LLM_URL=http://ollama:11435/v1
 
-## Optional: Custom endpoint (defaults to OpenAI)
-# LLM_URL=https://api.openai.com/v1
+## --- Option B: Remote/cloud LLM ---
+#LLM_API_KEY=sk-your-openai-api-key
+#LLM_MODEL=gpt-4o-mini
+## LLM_URL defaults to OpenAI when unset
 
 ## Context size for summary generation (tokens)
 LLM_CONTEXT_WINDOW=16000
 
+## =======================================================
+## Audio Padding
+##
+## backends: pyav (in-process PyAV), modal (HTTP API client)
+## Default is "pyav" — no external service needed.
+## Set to "modal" when using Modal.com or self-hosted gpu/self_hosted/ container.
+## =======================================================
+#PADDING_BACKEND=pyav
+#PADDING_BACKEND=modal
+#PADDING_URL=https://xxxxx--reflector-padding-web.modal.run
+#PADDING_MODAL_API_KEY=xxxxx
+
 ## =======================================================
 ## Diarization
 ##
-## Only available on modal
-## To allow diarization, you need to expose expose the files to be dowloded by the pipeline
+## backends: modal (HTTP API), pyannote (in-process pyannote.audio)
+## To allow diarization, you need to expose expose the files to be downloaded by the pipeline
 ## =======================================================
 DIARIZATION_ENABLED=false
 DIARIZATION_BACKEND=modal
@@ -130,6 +149,10 @@ TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
 #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
+# Worker credentials for reading/deleting from Daily's recording bucket
+# Required when transcript storage is separate from Daily's bucket (e.g., selfhosted with Garage)
+#DAILYCO_STORAGE_AWS_ACCESS_KEY_ID=your-aws-access-key
+#DAILYCO_STORAGE_AWS_SECRET_ACCESS_KEY=your-aws-secret-key
 
 ## Whereby (optional separate bucket)
 #WHEREBY_STORAGE_AWS_BUCKET_NAME=reflector-whereby

server/.env.selfhosted.example

@@ -0,0 +1,165 @@
+# =======================================================
+# Reflector Self-Hosted Production — Backend Configuration
+# Generated by: ./scripts/setup-selfhosted.sh
+# Reference: server/reflector/settings.py
+# =======================================================
+
+# =======================================================
+# Database & Infrastructure
+# Pre-filled for Docker internal networking (docker-compose.selfhosted.yml)
+# =======================================================
+DATABASE_URL=postgresql+asyncpg://reflector:reflector@postgres:5432/reflector
+REDIS_HOST=redis
+REDIS_PORT=6379
+CELERY_BROKER_URL=redis://redis:6379/1
+CELERY_RESULT_BACKEND=redis://redis:6379/1
+
+# Secret key — auto-generated by setup script
+# Generate manually with: openssl rand -hex 32
+SECRET_KEY=changeme-generate-a-secure-random-string
+
+# =======================================================
+# Authentication
+# Disabled by default. Enable Authentik for multi-user access.
+# See docsv2/selfhosted-production.md for setup instructions.
+# =======================================================
+AUTH_BACKEND=none
+# AUTH_BACKEND=jwt
+# AUTH_JWT_AUDIENCE=
+# AUTH_BACKEND=password
+# ADMIN_EMAIL=admin@localhost
+# ADMIN_PASSWORD_HASH=pbkdf2:sha256:100000$<salt>$<hash>
+
+# =======================================================
+# Specialized Models (Transcription, Diarization, Translation)
+# These do NOT use an LLM. Configured per mode by the setup script:
+#
+# --gpu mode:    modal backends → GPU container (http://transcription:8000)
+# --cpu mode:    whisper/pyannote/marian/pyav → in-process ML on server/worker
+# --hosted mode: modal backends → user-provided remote GPU service URL
+# =======================================================
+
+# --- --gpu mode (default) ---
+TRANSCRIPT_BACKEND=modal
+TRANSCRIPT_URL=http://transcription:8000
+TRANSCRIPT_MODAL_API_KEY=selfhosted
+DIARIZATION_ENABLED=true
+DIARIZATION_BACKEND=modal
+DIARIZATION_URL=http://transcription:8000
+TRANSLATION_BACKEND=modal
+TRANSLATE_URL=http://transcription:8000
+PADDING_BACKEND=modal
+PADDING_URL=http://transcription:8000
+
+# --- --cpu mode (set by setup script) ---
+# TRANSCRIPT_BACKEND=whisper
+# DIARIZATION_BACKEND=pyannote
+# TRANSLATION_BACKEND=marian
+# PADDING_BACKEND=pyav
+
+# --- --hosted mode (set by setup script) ---
+# TRANSCRIPT_BACKEND=modal
+# TRANSCRIPT_URL=https://your-gpu-service.example.com
+# DIARIZATION_BACKEND=modal
+# DIARIZATION_URL=https://your-gpu-service.example.com
+# ... (all URLs point to one remote service)
+
+# Whisper model sizes for local transcription (--cpu mode)
+# Options: "tiny", "base", "small", "medium", "large-v2"
+# WHISPER_CHUNK_MODEL=tiny
+# WHISPER_FILE_MODEL=tiny
+
+# HuggingFace token — for gated models (e.g. pyannote diarization).
+# Required for --gpu and --cpu modes; falls back to public S3 bundle if not set.
+# Not needed for --hosted mode (remote service handles its own auth).
+# HF_TOKEN=hf_xxxxx
+
+# =======================================================
+# LLM for Summarization & Topic Detection
+# Only summaries and topics use an LLM. Everything else
+# (transcription, diarization, translation) uses specialized models above.
+#
+# Supports any OpenAI-compatible endpoint.
+# Auto-configured by setup script if using --ollama-gpu or --ollama-cpu.
+# For --gpu or --cpu modes, you MUST configure an external LLM.
+# =======================================================
+
+# --- Option A: External OpenAI-compatible API ---
+# LLM_URL=https://api.openai.com/v1
+# LLM_API_KEY=sk-your-api-key
+# LLM_MODEL=gpt-4o-mini
+
+# --- Option B: Local Ollama (auto-set by --ollama-gpu/--ollama-cpu) ---
+# LLM_URL=http://ollama:11435/v1
+# LLM_API_KEY=not-needed
+# LLM_MODEL=llama3.1
+
+LLM_CONTEXT_WINDOW=16000
+
+# =======================================================
+# S3 Storage (REQUIRED)
+# Where to store audio files and transcripts.
+#
+# Option A: Use --garage flag (auto-configured by setup script)
+# Option B: Any S3-compatible endpoint (AWS, MinIO, etc.)
+#           Set TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL for non-AWS endpoints.
+# =======================================================
+TRANSCRIPT_STORAGE_BACKEND=aws
+TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID=
+TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY=
+TRANSCRIPT_STORAGE_AWS_BUCKET_NAME=reflector-media
+TRANSCRIPT_STORAGE_AWS_REGION=us-east-1
+
+# For non-AWS S3-compatible endpoints (Garage, MinIO, etc.):
+# TRANSCRIPT_STORAGE_AWS_ENDPOINT_URL=http://garage:3900
+
+# =======================================================
+# Daily.co Live Rooms (Optional)
+# Enable real-time meeting rooms with Daily.co integration.
+# Configure these BEFORE running setup-selfhosted.sh and the
+# script will auto-detect and start Hatchet workflow services.
+#
+# Prerequisites:
+#   1. Daily.co account: https://www.daily.co/
+#   2. API key: Dashboard → Developers → API Keys
+#   3. S3 bucket for recordings: https://docs.daily.co/guides/products/live-streaming-recording/storing-recordings-in-a-custom-s3-bucket
+#   4. IAM role ARN for Daily.co to write recordings to your bucket
+#
+# After configuring, run: ./scripts/setup-selfhosted.sh <your-flags>
+# The script will detect DAILY_API_KEY and automatically:
+#   - Start Hatchet workflow engine + CPU/LLM workers
+#   - Generate a Hatchet API token
+#   - Enable FEATURE_ROOMS in the frontend
+# =======================================================
+# DAILY_API_KEY=your-daily-api-key
+# DAILY_SUBDOMAIN=your-subdomain
+# DEFAULT_VIDEO_PLATFORM=daily
+# DAILYCO_STORAGE_AWS_BUCKET_NAME=reflector-dailyco
+# DAILYCO_STORAGE_AWS_REGION=us-east-1
+# DAILYCO_STORAGE_AWS_ROLE_ARN=arn:aws:iam::role/DailyCoAccess
+# Worker credentials for reading/deleting from Daily's recording bucket
+# Required when transcript storage is separate from Daily's bucket (e.g., selfhosted with Garage)
+# DAILYCO_STORAGE_AWS_ACCESS_KEY_ID=your-aws-access-key
+# DAILYCO_STORAGE_AWS_SECRET_ACCESS_KEY=your-aws-secret-key
+# DAILY_WEBHOOK_SECRET=your-daily-webhook-secret  # optional, for faster recording discovery
+
+# =======================================================
+# Hatchet Workflow Engine (Auto-configured for Daily.co)
+# Required for Daily.co multitrack recording processing.
+# The setup script generates HATCHET_CLIENT_TOKEN automatically.
+# Do not set these manually unless you know what you're doing.
+# =======================================================
+# HATCHET_CLIENT_TOKEN=<auto-generated-by-script>
+# HATCHET_CLIENT_SERVER_URL=http://hatchet:8888
+# HATCHET_CLIENT_HOST_PORT=hatchet:7077
+
+# =======================================================
+# Feature Flags
+# =======================================================
+PUBLIC_MODE=true
+# FEATURE_ROOMS=true
+
+# =======================================================
+# Sentry (Optional)
+# =======================================================
+# SENTRY_DSN=

server/Dockerfile

@@ -6,7 +6,7 @@ ENV PYTHONUNBUFFERED=1 \
 
 # builder install base dependencies
 WORKDIR /tmp
-RUN apt-get update && apt-get install -y curl && apt-get clean
+RUN apt-get update && apt-get install -y curl ffmpeg && apt-get clean
 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"
@@ -17,9 +17,6 @@ WORKDIR /app
 COPY pyproject.toml uv.lock README.md /app/
 RUN uv sync --compile-bytecode --locked
 
-# pre-download nltk packages
-RUN uv run python -c "import nltk; nltk.download('punkt_tab'); nltk.download('averaged_perceptron_tagger_eng')"
-
 # bootstrap
 COPY alembic.ini runserver.sh /app/
 COPY images /app/images

server/docs/DAILY_REFLECTOR_DATA_MODEL.md

@@ -0,0 +1,496 @@
+# Daily.co and Reflector Data Model
+
+This document explains the data model relationships between Daily.co's API concepts and Reflector's database schema, clarifying common sources of confusion.
+
+---
+
+## Table of Contents
+
+1. [Core Entities Overview](#core-entities-overview)
+2. [Daily.co vs Reflector Terminology](#dailyco-vs-reflector-terminology)
+3. [Entity Relationships](#entity-relationships)
+4. [Recording Multiplicity](#recording-multiplicity)
+5. [Session Identifiers Explained](#session-identifiers-explained)
+6. [Time-Based Matching](#time-based-matching)
+7. [Multitrack Recording Details](#multitrack-recording-details)
+8. [Verified Example](#verified-example)
+
+---
+
+## Core Entities Overview
+
+### Reflector's Four Primary Entities
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│ Room (Reflector)                                                │
+│ - Persistent meeting template                                   │
+│ - User-created configuration                                    │
+│ - Example: "team-standup"                                       │
+└────────────────────┬────────────────────────────────────────────┘
+                     │ 1:N
+                     ▼
+┌─────────────────────────────────────────────────────────────────┐
+│ Meeting (Reflector)                                             │
+│ - Single session instance                                       │
+│ - Creates NEW Daily.co room with timestamp                      │
+│ - Example: "team-standup-20260115120000"                        │
+└────────────────────┬────────────────────────────────────────────┘
+                     │ 1:N
+                     ▼
+┌─────────────────────────────────────────────────────────────────┐
+│ Recording (Reflector + Daily.co)                                │
+│ - One segment of audio/video                                    │
+│ - New recording created on stop/restart                         │
+│ - track_keys: JSON array of S3 file paths                       │
+└────────────────────┬────────────────────────────────────────────┘
+                     │ 1:1
+                     ▼
+┌─────────────────────────────────────────────────────────────────┐
+│ Transcript (Reflector)                                          │
+│ - Processed audio with transcription                            │
+│ - Diarization, summaries, topics                                │
+│ - One transcript per recording                                  │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Daily.co vs Reflector Terminology
+
+### Room
+
+| Aspect | Daily.co | Reflector |
+|--------|----------|-----------|
+| **Definition** | Virtual meeting space on Daily.co platform | User-created meeting template/configuration |
+| **Lifetime** | Configurable expiration | Persistent until user deletes |
+| **Creation** | API call for each meeting | Pre-created by user once |
+| **Reuse** | Can host multiple sessions | Generates new Daily.co room per meeting |
+| **Name Format** | `room-name` (reusable) | `room-name` (base identifier) |
+| **Timestamping** | Not required | Meeting adds timestamp: `{name}-YYYYMMDDHHMMSS` |
+
+**Example:**
+```
+Reflector Room: "daily-private-igor" (persistent config)
+    ↓ starts meeting
+Daily.co Room: "daily-private-igor-20260110042117"
+```
+
+### Meeting
+
+| Aspect | Daily.co | Reflector |
+|--------|----------|-----------|
+| **Definition** | Session that starts when first participant joins | Explicit database record of a session |
+| **Identifier** | `mtgSessionId` (generated by Daily.co) | `meeting.id` (UUID, generated by Reflector) |
+| **Creation** | Implicit (first participant join) | Explicit API call before participants join |
+| **Purpose** | Tracks active session state | Links recordings, transcripts, participants |
+| **Scope** | Per room instance | Per Reflector room + timestamp |
+
+**Critical Limitation:** Daily.co's recordings API often does NOT return `mtgSessionId`, requiring time-based matching (see [Time-Based Matching](#time-based-matching)).
+
+### Recording
+
+| Aspect | Daily.co | Reflector |
+|--------|----------|-----------|
+| **Definition** | Audio/video files on S3 | Metadata + processing status |
+| **Types** | `cloud` (composed video), `raw-tracks` (multitrack) | Stores references + `track_keys` array |
+| **Multiplicity** | One recording object per start/stop cycle | One DB row per Daily.co recording object |
+| **Identifier** | Daily.co `recording_id` | Same `recording_id` (stored in DB) |
+| **Multitrack** | Array of `.webm` files (one per participant) | `track_keys` JSON array with S3 paths |
+| **Linkage** | Via `room_name` + `start_ts` | FK `meeting_id` (set via time-based match) |
+
+**Critical Behavior:** Recording **stops/restarts** create **separate recording objects** with unique IDs.
+
+---
+
+## Entity Relationships
+
+### Database Schema Relationships
+
+```sql
+-- Simplified schema showing key relationships
+
+TABLE room (
+    id VARCHAR PRIMARY KEY,
+    name VARCHAR UNIQUE,
+    platform VARCHAR  -- 'whereby' | 'daily'
+)
+
+TABLE meeting (
+    id VARCHAR PRIMARY KEY,
+    room_id VARCHAR REFERENCES room(id) ON DELETE CASCADE,  -- nullable
+    room_name VARCHAR,  -- Daily.co room name (timestamped)
+    start_date TIMESTAMP,
+    platform VARCHAR
+)
+
+TABLE recording (
+    id VARCHAR PRIMARY KEY,  -- Daily.co recording_id
+    meeting_id VARCHAR,      -- FK to meeting (set via time-based match)
+    bucket_name VARCHAR,
+    object_key VARCHAR,      -- S3 prefix
+    track_keys JSON,         -- Array of S3 keys for multitrack
+    recorded_at TIMESTAMP
+)
+
+TABLE transcript (
+    id VARCHAR PRIMARY KEY,
+    recording_id VARCHAR,    -- nullable FK
+    meeting_id VARCHAR,      -- nullable FK
+    room_id VARCHAR,         -- nullable FK
+    participants JSON,       -- [{id, speaker, name, user_id}, ...]
+    title VARCHAR,
+    long_summary VARCHAR,
+    webvtt TEXT
+)
+```
+
+**Relationship Cardinalities:**
+```
+1 Room → N Meetings
+1 Meeting → N Recordings (common: 1-21 recordings per meeting)
+1 Recording → 1 Transcript
+1 Meeting → N Transcripts (via recordings)
+```
+
+---
+
+## Recording Multiplicity
+
+### Why Multiple Recordings Per Meeting?
+
+Daily.co creates a **new recording object** (new ID, new files) whenever recording stops and restarts. This happens due to:
+
+1. **Manual stop/start** - User clicks stop, then start recording again
+2. **Network reconnection** - Participant drops, reconnects → triggers restart
+3. **Participant rejoin** - Last participant leaves, new one joins → new session
+
+---
+
+## Session Identifiers Explained
+
+### The Hidden Entity: Daily.co Meeting Session
+
+Daily.co has an **implicit ephemeral entity** that sits between Room and Recording:
+
+```
+Daily.co Room: "daily-private-igor-20260110042117"
+    │
+    ├─ Daily.co Meeting Session #1 (mtgSessionId: c04334de...)
+    │   └─ Recording #3 (f4a50f94) - 4s, 1 track
+    │
+    └─ Daily.co Meeting Session #2 (mtgSessionId: 4cdae3c0...)
+        ├─ Recording #2 (b0fa94da) - 80s, 2 tracks  ← recording stopped
+        └─ Recording #1 (05edf519) - 62s, 1 track   ← then restarted
+```
+
+**Daily.co Meeting Session:**
+- **Lifecycle:** Starts when first participant joins, ends when last participant leaves
+- **Identifier:** `mtgSessionId` (generated by Daily.co)
+- **Persistence:** Ephemeral - new ID if everyone leaves and someone rejoins
+- **Relationship:** 1 Session → N Recordings (if recording stops/restarts during session)
+
+**Key Insight:** Multiple recordings can share the same `mtgSessionId` if recording was stopped and restarted while participants remained connected.
+
+### mtgSessionId (Meeting Session Identifier)
+
+`mtgSessionId` identifies a **Daily.co meeting session** (not individual participants, not a room).
+
+### session_id (Per-Participant)
+
+**Different concept:** Per-participant connection identifier from webhooks.
+
+**Reflector Tracking:** `daily_participant_session` table
+```sql
+TABLE daily_participant_session (
+    id VARCHAR PRIMARY KEY,        -- {meeting_id}:{user_id}:{joined_at_ms}
+    meeting_id VARCHAR,
+    session_id VARCHAR,            -- From webhook (per-participant)
+    user_id VARCHAR,
+    user_name VARCHAR,
+    joined_at TIMESTAMP,
+    left_at TIMESTAMP
+)
+```
+---
+
+## Time-Based Matching
+
+### Problem Statement
+
+Daily.co's recordings API does not reliably return `mtgSessionId`, making it impossible to directly link recordings to meetings via Daily.co's identifiers.
+
+**Example API response:**
+```json
+{
+  "id": "recording-uuid",
+  "room_name": "daily-private-igor-20260110042117",
+  "start_ts": 1768018896,
+  "mtgSessionId": null  ← Missing!
+}
+```
+
+### Solution: Time-Based Matching
+
+**Implementation:** `reflector/db/meetings.py:get_by_room_name_and_time()`
+
+
+---
+
+## Multitrack Recording Details
+
+### track_keys JSON Array
+
+**Schema:** `recording.track_keys` (JSON, nullable)
+```sql
+-- Example recording with 2 audio tracks
+{
+  "id": "b0fa94da-73b5-4f95-9239-5216a682a505",
+  "track_keys": [
+    "igormonadical/daily-private-igor-20260110042117/1768018896877-890c0eae-e186-4534-a7bd-7c794b7d6d7f-cam-audio-1768018914565",
+    "igormonadical/daily-private-igor-20260110042117/1768018896877-9660e8e9-4297-4f17-951d-0b2bf2401803-cam-audio-1768018899286"
+  ]
+}
+```
+
+**Semantics:**
+- `track_keys = null` → Not multitrack (cloud recording)
+- `track_keys = []` → Multitrack recording with no audio captured (silence/muted)
+- `track_keys = [...]` → Multitrack with N audio tracks
+
+**Property:** `recording.is_multitrack` (Python)
+```python
+@property
+def is_multitrack(self) -> bool:
+    return self.track_keys is not None and len(self.track_keys) > 0
+```
+
+### Track Filename Format
+
+Daily.co multitrack filenames encode timing and participant information:
+
+**Format:** `{recording_start_ts}-{participant_id}-cam-audio-{track_start_ts}`
+
+**Example:** `1768018896877-890c0eae-e186-4534-a7bd-7c794b7d6d7f-cam-audio-1768018914565`
+
+**Parsed Components:**
+```python
+# reflector/utils/daily.py:25-60
+class DailyRecordingFilename(NamedTuple):
+    recording_start_ts: int  # 1768018896877 (milliseconds)
+    participant_id: str      # 890c0eae-e186-4534-a7bd-7c794b7d6d7f
+    track_start_ts: int      # 1768018914565 (milliseconds)
+```
+
+**Note:** Browser downloads from S3 add `.webm` extension due to MIME headers, but S3 object keys have no extension.
+
+### Video Track Filtering
+
+Daily.co API returns both audio and video tracks, but Reflector only processes audio.
+
+**Filtering Logic:** `reflector/worker/process.py:660`
+```python
+track_keys = [t.s3Key for t in recording.tracks if t.type == "audio"]
+```
+
+**Example API Response:**
+```json
+{
+  "tracks": [
+    {"type": "audio", "s3Key": "...cam-audio-1768018914565"},
+    {"type": "audio", "s3Key": "...cam-audio-1768018899286"},
+    {"type": "video", "s3Key": "...cam-video-1768018897095"}  ← Filtered out
+  ]
+}
+```
+
+**Result:** Only 2 audio tracks stored in `recording.track_keys`, video track discarded.
+
+**Rationale:** Reflector is audio transcription system; video not needed for processing.
+
+### Track-to-Participant Mapping
+
+**Flow:**
+1. Daily.co webhook/polling provides `track_keys` array
+2. Each track filename contains `participant_id`
+3. Reflector queries Daily.co API: `GET /meetings/{mtgSessionId}/participants`
+4. Maps `participant_id` → `user_name`
+5. Stores in `transcript.participants` JSON:
+```json
+[
+  {
+    "id": "890c0eae-e186-4534-a7bd-7c794b7d6d7f",
+    "speaker": 0,
+    "name": "test2",
+    "user_id": "907f2cc1-eaab-435f-8ee2-09185f416b22"
+  },
+  {
+    "id": "9660e8e9-4297-4f17-951d-0b2bf2401803",
+    "speaker": 1,
+    "name": "test",
+    "user_id": "907f2cc1-eaab-435f-8ee2-09185f416b22"
+  }
+]
+```
+
+**Diarization:** Multitrack recordings don't need speaker diarization AI — speaker identity comes from separate audio tracks.
+
+---
+
+## Example
+
+### Meeting: daily-private-igor-20260110042117
+
+**Context:** User conducted test recording with start/stop cycles, producing 3 recordings.
+
+#### Database State
+
+```sql
+-- Meeting
+id: 034804b8-cee2-4fb4-94d7-122f6f068a61
+room_name: daily-private-igor-20260110042117
+start_date: 2026-01-10 04:21:17+00
+```
+
+#### Daily.co API Response
+
+```json
+[
+  {
+    "id": "f4a50f94-053c-4f9d-bda6-78ad051fbc36",
+    "room_name": "daily-private-igor-20260110042117",
+    "start_ts": 1768018885,
+    "duration": 4,
+    "status": "finished",
+    "mtgSessionId": "c04334de-42a0-4c2a-96be-a49b068dca85",
+    "tracks": [
+      {"type": "audio", "s3Key": "...62e8f3ae...cam-audio-1768018885417"}
+    ]
+  },
+  {
+    "id": "b0fa94da-73b5-4f95-9239-5216a682a505",
+    "room_name": "daily-private-igor-20260110042117",
+    "start_ts": 1768018896,
+    "duration": 80,
+    "status": "finished",
+    "mtgSessionId": "4cdae3c0-86cb-4578-8a6d-3a228bb48345",
+    "tracks": [
+      {"type": "audio", "s3Key": "...890c0eae...cam-audio-1768018914565"},
+      {"type": "audio", "s3Key": "...9660e8e9...cam-audio-1768018899286"},
+      {"type": "video", "s3Key": "...9660e8e9...cam-video-1768018897095"}
+    ]
+  },
+  {
+    "id": "05edf519-9048-4b49-9a75-73e9826fd950",
+    "room_name": "daily-private-igor-20260110042117",
+    "start_ts": 1768018914,
+    "duration": 62,
+    "status": "finished",
+    "mtgSessionId": "4cdae3c0-86cb-4578-8a6d-3a228bb48345",
+    "tracks": [
+      {"type": "audio", "s3Key": "...890c0eae...cam-audio-1768018914948"}
+    ]
+  }
+]
+```
+
+**Key Observations:**
+- 3 recording objects returned by Daily.co
+- 2 different `mtgSessionId` values (2 different meeting instances)
+- Recording #2 has 3 tracks (2 audio + 1 video)
+- Timestamps: 1768018885 → 1768018896 (+11s) → 1768018914 (+18s)
+
+#### Reflector Database
+
+**Recordings:**
+```
+┌──────────────────────────────────────┬──────────────┬────────────┬──────────────────────────────────────┐
+│ id                                   │ track_count  │ duration   │ mtgSessionId                         │
+├──────────────────────────────────────┼──────────────┼────────────┼──────────────────────────────────────┤
+│ f4a50f94-053c-4f9d-bda6-78ad051fbc36 │ 1            │ 4s         │ c04334de-42a0-4c2a-96be-a49b068dca85 │
+│ b0fa94da-73b5-4f95-9239-5216a682a505 │ 2 (video=0)  │ 80s        │ 4cdae3c0-86cb-4578-8a6d-3a228bb48345 │
+│ 05edf519-9048-4b49-9a75-73e9826fd950 │ 1            │ 62s        │ 4cdae3c0-86cb-4578-8a6d-3a228bb48345 │
+└──────────────────────────────────────┴──────────────┴────────────┴──────────────────────────────────────┘
+```
+**Note:** Recording #2 has 2 audio tracks (video filtered out), not 3.
+
+**Transcripts:**
+```
+┌──────────────────────────────────────┬──────────────────────────────────────┬──────────────┬──────────────────────────────────────────────┐
+│ id                                   │ recording_id                         │ participants │ title                                        │
+├──────────────────────────────────────┼──────────────────────────────────────┼──────────────┼──────────────────────────────────────────────┤
+│ 17149b1f-546c-4837-80a0-f8140bd16592 │ f4a50f94-053c-4f9d-bda6-78ad051fbc36 │ 1 (test)     │ (empty - no speech)                          │
+│ 49801332-3222-4c11-bdb2-375479fc87f2 │ b0fa94da-73b5-4f95-9239-5216a682a505 │ 2 (test,     │ "Examination and Validation Procedures       │
+│                                      │                                      │   test2)     │  Review"                                     │
+│ e5271e12-20fb-42d2-b5a8-21438abadef9 │ 05edf519-9048-4b49-9a75-73e9826fd950 │ 1 (test2)    │ "Technical Sound Check Procedure Review"     │
+└──────────────────────────────────────┴──────────────────────────────────────┴──────────────┴──────────────────────────────────────────────┘
+```
+
+**Transcript Content:**
+
+*Transcript #1* (17149b1f): Empty WebVTT (no audio captured)
+
+*Transcript #2* (49801332):
+```webvtt
+WEBVTT
+
+00:00:03.109 --> 00:00:05.589
+<v Speaker1>Test, test, test. Test, test, test, test, test.
+
+00:00:19.829 --> 00:00:22.710
+<v Speaker0>Test test test test test test test test test test test.
+```
+**AI-Generated Summary:**
+> "The meeting focused on the critical importance of rigorous testing for ensuring reliability and quality, with test and test2 emphasizing the need for a structured testing framework and meticulous documentation..."
+
+*Transcript #3* (e5271e12):
+```webvtt
+WEBVTT
+
+00:00:02.029 --> 00:00:04.910
+<v Speaker0>Test, test, test, test, test, test, test, test, test, test, test.
+```
+
+#### Validation: track_keys → participants
+
+**Recording #2 (b0fa94da) tracks:**
+```json
+[
+  ".../890c0eae-e186-4534-a7bd-7c794b7d6d7f-cam-audio-...",
+  ".../9660e8e9-4297-4f17-951d-0b2bf2401803-cam-audio-..."
+]
+```
+
+**Transcript #2 (49801332) participants:**
+```json
+[
+  {"id": "890c0eae-e186-4534-a7bd-7c794b7d6d7f", "speaker": 0, "name": "test2"},
+  {"id": "9660e8e9-4297-4f17-951d-0b2bf2401803", "speaker": 1, "name": "test"}
+]
+```
+
+### Data Flow
+
+```
+Daily.co API: 3 recordings
+    ↓
+Polling: _poll_raw_tracks_recordings()
+    ↓
+Worker: process_multitrack_recording.delay() × 3
+    ↓
+DB: 3 recording rows created
+    ↓
+Pipeline: Audio processing + transcription × 3
+    ↓
+DB: 3 transcript rows created (1:1 with recordings)
+    ↓
+UI: User sees 3 separate transcripts
+```
+
+**Result:** ✅ 1:1 Recording → Transcript relationship maintained.
+
+
+---
+**Document Version:** 1.0
+**Last Verified:** 2026-01-15
+**Data Source:** Production database + Daily.co API inspection

server/migrations/versions/1b1e6a6fc465_add_cloud_recording_support.py

@@ -0,0 +1,40 @@
+"""add cloud recording support
+
+Revision ID: 1b1e6a6fc465
+Revises: bd3a729bb379
+Create Date: 2026-01-09 17:17:33.535620
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "1b1e6a6fc465"
+down_revision: Union[str, None] = "bd3a729bb379"
+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.add_column(
+            sa.Column("daily_composed_video_s3_key", sa.String(), nullable=True)
+        )
+        batch_op.add_column(
+            sa.Column("daily_composed_video_duration", sa.Integer(), 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.drop_column("daily_composed_video_duration")
+        batch_op.drop_column("daily_composed_video_s3_key")
+
+    # ### end Alembic commands ###

server/migrations/versions/3aa20b96d963_drop_use_celery_column.py

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

server/migrations/versions/623af934249a_add_change_seq_to_transcript.py

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

server/migrations/versions/e1f093f7f124_add_password_hash_to_user.py

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

server/migrations/versions/e69f08ead8ea_merge_cloud_recording_and_celery_heads.py

@@ -0,0 +1,23 @@
+"""merge cloud recording and celery heads
+
+Revision ID: e69f08ead8ea
+Revises: 1b1e6a6fc465, 80beb1ea3269
+Create Date: 2026-01-21 21:39:10.326841
+
+"""
+
+from typing import Sequence, Union
+
+# revision identifiers, used by Alembic.
+revision: str = "e69f08ead8ea"
+down_revision: Union[str, None] = ("1b1e6a6fc465", "80beb1ea3269")
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    pass

server/pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 dependencies = [
     "aiohttp>=3.9.0",
     "aiohttp-cors>=0.7.0",
-    "av>=10.0.0",
+    "av>=15.0.0",
     "requests>=2.31.0",
     "aiortc>=1.5.0",
     "sortedcontainers>=2.4.0",
@@ -18,17 +18,16 @@ dependencies = [
     "fastapi[standard]>=0.100.1",
     "sentry-sdk[fastapi]>=1.29.2",
     "httpx>=0.24.1",
-    "fastapi-pagination>=0.12.6",
+    "fastapi-pagination>=0.14.2",
     "databases[aiosqlite, asyncpg]>=0.7.0",
     "sqlalchemy<1.5",
     "alembic>=1.11.3",
-    "nltk>=3.8.1",
     "prometheus-fastapi-instrumentator>=6.1.0",
     "sentencepiece>=0.1.99",
     "protobuf>=4.24.3",
     "celery>=5.3.4",
     "redis>=5.0.1",
-    "python-jose[cryptography]>=3.3.0",
+    "pyjwt[crypto]>=2.8.0",
     "python-multipart>=0.0.6",
     "transformers>=4.36.2",
     "jsonschema>=4.23.0",
@@ -40,6 +39,7 @@ dependencies = [
     "webvtt-py>=0.5.0",
     "icalendar>=6.0.0",
     "hatchet-sdk>=0.47.0",
+    "pydantic>=2.12.5",
 ]
 
 [dependency-groups]
@@ -68,13 +68,15 @@ evaluation = [
     "pydantic>=2.1.1",
 ]
 local = [
-    "pyannote-audio>=3.3.2",
     "faster-whisper>=0.10.0",
 ]
 silero-vad = [
-    "silero-vad>=5.1.2",
+    "silero-vad==5.1.2",
     "torch>=2.8.0",
     "torchaudio>=2.8.0",
+    "pyannote.audio==3.4.0",
+    "pytorch-lightning<2.6",
+    "librosa==0.10.1",
 ]
 
 [tool.uv]

server/reflector/_warnings_filter.py

@@ -0,0 +1,13 @@
+"""
+Suppress known dependency warnings. Import this before any reflector/hatchet_sdk
+imports that pull in pydantic (e.g. llama_index) to hide UnsupportedFieldAttributeWarning
+about validate_default.
+"""
+
+import warnings
+
+warnings.filterwarnings(
+    "ignore",
+    message=".*validate_default.*",
+    category=UserWarning,
+)

server/reflector/app.py

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

server/reflector/asynctask.py

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

server/reflector/auth/__init__.py

@@ -12,3 +12,9 @@ AccessTokenInfo = auth_module.AccessTokenInfo
 authenticated = auth_module.authenticated
 current_user = auth_module.current_user
 current_user_optional = auth_module.current_user_optional
+parse_ws_bearer_token = auth_module.parse_ws_bearer_token
+current_user_ws_optional = auth_module.current_user_ws_optional
+verify_raw_token = auth_module.verify_raw_token
+
+# Optional router (e.g. for /auth/login in password backend)
+router = getattr(auth_module, "router", None)

server/reflector/auth/auth_jwt.py

@@ -1,8 +1,11 @@
-from typing import Annotated, List, Optional
+from typing import TYPE_CHECKING, Annotated, List, Optional
 
 from fastapi import Depends, HTTPException
+
+if TYPE_CHECKING:
+    from fastapi import WebSocket
+import jwt
 from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
-from jose import JWTError, jwt
 from pydantic import BaseModel
 
 from reflector.db.user_api_keys import user_api_keys_controller
@@ -51,7 +54,7 @@ class JWTAuth:
                 audience=jwt_audience,
             )
             return payload
-        except JWTError as e:
+        except jwt.PyJWTError as e:
             logger.error(f"JWT error: {e}")
             raise
 
@@ -91,7 +94,7 @@ async def _authenticate_user(
                 )
 
             user_infos.append(UserInfo(sub=user.id, email=email))
-        except JWTError as e:
+        except jwt.PyJWTError as e:
             logger.error(f"JWT error: {e}")
             raise HTTPException(status_code=401, detail="Invalid authentication")
 
@@ -124,3 +127,25 @@ async def current_user_optional(
     jwtauth: JWTAuth = Depends(),
 ):
     return await _authenticate_user(jwt_token, api_key, jwtauth)
+
+
+def parse_ws_bearer_token(
+    websocket: "WebSocket",
+) -> tuple[Optional[str], Optional[str]]:
+    raw = websocket.headers.get("sec-websocket-protocol") or ""
+    parts = [p.strip() for p in raw.split(",") if p.strip()]
+    if len(parts) >= 2 and parts[0].lower() == "bearer":
+        return parts[1], "bearer"
+    return None, None
+
+
+async def current_user_ws_optional(websocket: "WebSocket") -> Optional[UserInfo]:
+    token, _ = parse_ws_bearer_token(websocket)
+    if not token:
+        return None
+    return await _authenticate_user(token, None, JWTAuth())
+
+
+async def verify_raw_token(token: str) -> Optional[UserInfo]:
+    """Verify a raw JWT token string (used for query-param auth fallback)."""
+    return await _authenticate_user(token, None, JWTAuth())

server/reflector/auth/auth_none.py

@@ -1,11 +1,5 @@
-from typing import Annotated
-
-from fastapi import Depends
-from fastapi.security import OAuth2PasswordBearer
 from pydantic import BaseModel
 
-oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token", auto_error=False)
-
 
 class UserInfo(BaseModel):
     sub: str
@@ -15,13 +9,26 @@ class AccessTokenInfo(BaseModel):
     pass
 
 
-def authenticated(token: Annotated[str, Depends(oauth2_scheme)]):
+def authenticated():
     return None
 
 
-def current_user(token: Annotated[str, Depends(oauth2_scheme)]):
+def current_user():
     return None
 
 
-def current_user_optional(token: Annotated[str, Depends(oauth2_scheme)]):
+def current_user_optional():
+    return None
+
+
+def parse_ws_bearer_token(websocket):
+    return None, None
+
+
+async def current_user_ws_optional(websocket):
+    return None
+
+
+async def verify_raw_token(token):
+    """Verify a raw JWT token string (used for query-param auth fallback)."""
     return None

server/reflector/auth/auth_password.py

@@ -0,0 +1,203 @@
+"""Password-based authentication backend for selfhosted deployments.
+
+Issues HS256 JWTs signed with settings.SECRET_KEY. Provides a POST /auth/login
+endpoint for email/password authentication.
+"""
+
+import time
+from collections import defaultdict
+from datetime import datetime, timedelta, timezone
+from typing import TYPE_CHECKING, Annotated, Optional
+
+import jwt
+from fastapi import APIRouter, Depends, HTTPException, Request
+from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
+from pydantic import BaseModel
+
+from reflector.auth.password_utils import verify_password
+from reflector.db.user_api_keys import user_api_keys_controller
+from reflector.db.users import user_controller
+from reflector.logger import logger
+from reflector.settings import settings
+
+if TYPE_CHECKING:
+    from fastapi import WebSocket
+
+# --- FastAPI security schemes (same pattern as auth_jwt.py) ---
+oauth2_scheme = OAuth2PasswordBearer(tokenUrl="/v1/auth/login", auto_error=False)
+api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
+
+# --- JWT configuration ---
+JWT_ALGORITHM = "HS256"
+ACCESS_TOKEN_EXPIRE_MINUTES = 60 * 24  # 24 hours
+
+# --- Rate limiting (in-memory) ---
+_login_attempts: dict[str, list[float]] = defaultdict(list)
+RATE_LIMIT_WINDOW = 300  # 5 minutes
+RATE_LIMIT_MAX = 10  # max attempts per window
+
+
+def _check_rate_limit(key: str) -> bool:
+    """Return True if request is allowed, False if rate-limited."""
+    now = time.monotonic()
+    attempts = _login_attempts[key]
+    _login_attempts[key] = [t for t in attempts if now - t < RATE_LIMIT_WINDOW]
+    if len(_login_attempts[key]) >= RATE_LIMIT_MAX:
+        return False
+    _login_attempts[key].append(now)
+    return True
+
+
+# --- Pydantic models ---
+class UserInfo(BaseModel):
+    sub: str
+    email: Optional[str] = None
+
+    def __getitem__(self, key):
+        return getattr(self, key)
+
+
+class AccessTokenInfo(BaseModel):
+    exp: Optional[int] = None
+    sub: Optional[str] = None
+
+
+class LoginRequest(BaseModel):
+    email: str
+    password: str
+
+
+class LoginResponse(BaseModel):
+    access_token: str
+    token_type: str = "bearer"
+    expires_in: int
+
+
+# --- JWT token creation and verification ---
+def _create_access_token(user_id: str, email: str) -> tuple[str, int]:
+    """Create an HS256 JWT. Returns (token, expires_in_seconds)."""
+    expires_delta = timedelta(minutes=ACCESS_TOKEN_EXPIRE_MINUTES)
+    expire = datetime.now(timezone.utc) + expires_delta
+    payload = {
+        "sub": user_id,
+        "email": email,
+        "exp": expire,
+    }
+    token = jwt.encode(payload, settings.SECRET_KEY, algorithm=JWT_ALGORITHM)
+    return token, int(expires_delta.total_seconds())
+
+
+def _verify_token(token: str) -> dict:
+    """Verify and decode an HS256 JWT."""
+    return jwt.decode(token, settings.SECRET_KEY, algorithms=[JWT_ALGORITHM])
+
+
+# --- Authentication logic (mirrors auth_jwt._authenticate_user) ---
+async def _authenticate_user(
+    jwt_token: Optional[str],
+    api_key: Optional[str],
+) -> UserInfo | None:
+    user_infos: list[UserInfo] = []
+
+    if api_key:
+        user_api_key = await user_api_keys_controller.verify_key(api_key)
+        if user_api_key:
+            user_infos.append(UserInfo(sub=user_api_key.user_id, email=None))
+
+    if jwt_token:
+        try:
+            payload = _verify_token(jwt_token)
+            user_id = payload["sub"]
+            email = payload.get("email")
+            user_infos.append(UserInfo(sub=user_id, email=email))
+        except jwt.PyJWTError as e:
+            logger.error(f"JWT error: {e}")
+            raise HTTPException(status_code=401, detail="Invalid authentication")
+
+    if len(user_infos) == 0:
+        return None
+
+    if len(set(x.sub for x in user_infos)) > 1:
+        raise HTTPException(
+            status_code=401,
+            detail="Invalid authentication: more than one user provided",
+        )
+
+    return user_infos[0]
+
+
+# --- FastAPI dependencies (exported, required by auth/__init__.py) ---
+def authenticated(token: Annotated[str, Depends(oauth2_scheme)]):
+    if token is None:
+        raise HTTPException(status_code=401, detail="Not authenticated")
+    return None
+
+
+async def current_user(
+    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
+    api_key: Annotated[Optional[str], Depends(api_key_header)],
+):
+    user = await _authenticate_user(jwt_token, api_key)
+    if user is None:
+        raise HTTPException(status_code=401, detail="Not authenticated")
+    return user
+
+
+async def current_user_optional(
+    jwt_token: Annotated[Optional[str], Depends(oauth2_scheme)],
+    api_key: Annotated[Optional[str], Depends(api_key_header)],
+):
+    return await _authenticate_user(jwt_token, api_key)
+
+
+# --- WebSocket auth (same pattern as auth_jwt.py) ---
+def parse_ws_bearer_token(
+    websocket: "WebSocket",
+) -> tuple[Optional[str], Optional[str]]:
+    raw = websocket.headers.get("sec-websocket-protocol") or ""
+    parts = [p.strip() for p in raw.split(",") if p.strip()]
+    if len(parts) >= 2 and parts[0].lower() == "bearer":
+        return parts[1], "bearer"
+    return None, None
+
+
+async def current_user_ws_optional(websocket: "WebSocket") -> Optional[UserInfo]:
+    token, _ = parse_ws_bearer_token(websocket)
+    if not token:
+        return None
+    return await _authenticate_user(token, None)
+
+
+async def verify_raw_token(token: str) -> Optional[UserInfo]:
+    """Verify a raw JWT token string (used for query-param auth fallback)."""
+    return await _authenticate_user(token, None)
+
+
+# --- Login router ---
+router = APIRouter(prefix="/auth", tags=["auth"])
+
+
+@router.post("/login", response_model=LoginResponse)
+async def login(request: Request, body: LoginRequest):
+    client_ip = request.client.host if request.client else "unknown"
+    if not _check_rate_limit(client_ip):
+        raise HTTPException(
+            status_code=429,
+            detail="Too many login attempts. Try again later.",
+        )
+
+    user = await user_controller.get_by_email(body.email)
+    if not user or not user.password_hash:
+        print("invalid email")
+        raise HTTPException(status_code=401, detail="Invalid email or password")
+
+    if not verify_password(body.password, user.password_hash):
+        print("invalid pass")
+        raise HTTPException(status_code=401, detail="Invalid email or password")
+
+    access_token, expires_in = _create_access_token(user.id, user.email)
+    return LoginResponse(
+        access_token=access_token,
+        token_type="bearer",
+        expires_in=expires_in,
+    )

server/reflector/auth/password_utils.py

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

server/reflector/dailyco_api/__init__.py

@@ -3,7 +3,7 @@ Daily.co API Module
 """
 
 # Client
-from .client import DailyApiClient, DailyApiError
+from .client import DailyApiClient, DailyApiError, RecordingType
 
 # Request models
 from .requests import (
@@ -64,6 +64,7 @@ __all__ = [
     # Client
     "DailyApiClient",
     "DailyApiError",
+    "RecordingType",
     # Requests
     "CreateRoomRequest",
     "RoomProperties",

server/reflector/dailyco_api/client.py

@@ -7,7 +7,8 @@ Reference: https://docs.daily.co/reference/rest-api
 """
 
 from http import HTTPStatus
-from typing import Any
+from typing import Any, Literal
+from uuid import UUID
 
 import httpx
 import structlog
@@ -32,6 +33,8 @@ from .responses import (
 
 logger = structlog.get_logger(__name__)
 
+RecordingType = Literal["cloud", "raw-tracks"]
+
 
 class DailyApiError(Exception):
     """Daily.co API error with full request/response context."""
@@ -143,6 +146,8 @@ class DailyApiClient:
             )
             raise DailyApiError(operation, response)
 
+        if not response.content:
+            return {}
         return response.json()
 
     # ============================================================================
@@ -395,6 +400,38 @@ class DailyApiClient:
 
         return [RecordingResponse(**r) for r in data["data"]]
 
+    async def start_recording(
+        self,
+        room_name: NonEmptyString,
+        recording_type: RecordingType,
+        instance_id: UUID,
+    ) -> dict[str, Any]:
+        """Start recording via REST API.
+
+        Reference: https://docs.daily.co/reference/rest-api/rooms/recordings/start
+
+        Args:
+            room_name: Daily.co room name
+            recording_type: Recording type
+            instance_id: UUID for this recording session
+
+        Returns:
+            Recording start confirmation from Daily.co API
+
+        Raises:
+            DailyApiError: If API request fails
+        """
+        client = await self._get_client()
+        response = await client.post(
+            f"{self.base_url}/rooms/{room_name}/recordings/start",
+            headers=self.headers,
+            json={
+                "type": recording_type,
+                "instanceId": str(instance_id),
+            },
+        )
+        return await self._handle_response(response, "start_recording")
+
     # ============================================================================
     # MEETING TOKENS
     # ============================================================================

server/reflector/dailyco_api/instance_id.py

@@ -0,0 +1,37 @@
+"""
+Daily.co recording instanceId generation utilities.
+
+Deterministic instance ID generation for cloud and raw-tracks recordings.
+MUST match frontend logic
+"""
+
+from uuid import UUID, uuid5
+
+from reflector.utils.string import NonEmptyString
+
+# Namespace UUID for UUIDv5 generation of raw-tracks instanceIds
+# DO NOT CHANGE: Breaks instanceId determinism across deployments and frontend/backend matching
+RAW_TRACKS_NAMESPACE = UUID("a1b2c3d4-e5f6-7890-abcd-ef1234567890")
+
+
+def generate_cloud_instance_id(meeting_id: NonEmptyString) -> UUID:
+    """
+    Generate instanceId for cloud recording.
+
+    Cloud recordings use meeting ID directly as instanceId.
+    This ensures each meeting has one unique cloud recording.
+    """
+    return UUID(meeting_id)
+
+
+def generate_raw_tracks_instance_id(meeting_id: NonEmptyString) -> UUID:
+    """
+    Generate instanceId for raw-tracks recording.
+
+    Raw-tracks recordings use UUIDv5(meeting_id, namespace) to ensure
+    different instanceId from cloud while remaining deterministic.
+
+    Daily.co requires cloud and raw-tracks to have different instanceIds
+    for concurrent recording.
+    """
+    return uuid5(RAW_TRACKS_NAMESPACE, meeting_id)

server/reflector/dailyco_api/requests.py

@@ -88,13 +88,6 @@ class MeetingTokenProperties(BaseModel):
     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"
-    )
-    start_cloud_recording_opts: dict | None = Field(
-        default=None,
-        description="Options for startRecording when start_cloud_recording is true (e.g., maxDuration)",
-    )
     enable_recording_ui: bool = Field(
         default=True, description="Show recording controls in UI"
     )

server/reflector/dailyco_api/responses.py

@@ -116,6 +116,7 @@ class RecordingS3Info(BaseModel):
 
     bucket_name: NonEmptyString
     bucket_region: NonEmptyString
+    key: NonEmptyString | None = None
     endpoint: NonEmptyString | None = None
 
 
@@ -132,6 +133,9 @@ class RecordingResponse(BaseModel):
     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)")
+    type: Literal["cloud", "raw-tracks"] | None = Field(
+        None, description="Recording type (may be missing from API)"
+    )
     status: RecordingStatus = Field(
         description="Recording status ('in-progress' or 'finished')"
     )
@@ -145,6 +149,9 @@ class RecordingResponse(BaseModel):
         None, description="Token for sharing recording"
     )
     s3: RecordingS3Info | None = Field(None, description="S3 bucket information")
+    s3key: NonEmptyString | None = Field(
+        None, description="S3 key for cloud recordings (top-level field)"
+    )
     tracks: list[DailyTrack] = Field(
         default_factory=list,
         description="Track list for raw-tracks recordings (always array, never null)",

server/reflector/dailyco_api/webhook_utils.py

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

server/reflector/dailyco_api/webhooks.py

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

server/reflector/db/meetings.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timedelta
 from typing import Any, Literal
 
 import sqlalchemy as sa
@@ -9,7 +9,7 @@ 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
+from reflector.utils.string import NonEmptyString, assert_equal
 
 meetings = sa.Table(
     "meeting",
@@ -63,6 +63,9 @@ meetings = sa.Table(
         nullable=False,
         server_default=assert_equal(WHEREBY_PLATFORM, "whereby"),
     ),
+    # Daily.co composed video (Brady Bunch grid layout) - Daily.co only, not Whereby
+    sa.Column("daily_composed_video_s3_key", sa.String, nullable=True),
+    sa.Column("daily_composed_video_duration", sa.Integer, nullable=True),
     sa.Index("idx_meeting_room_id", "room_id"),
     sa.Index("idx_meeting_calendar_event", "calendar_event_id"),
 )
@@ -110,6 +113,9 @@ class Meeting(BaseModel):
     calendar_event_id: str | None = None
     calendar_metadata: dict[str, Any] | None = None
     platform: Platform = WHEREBY_PLATFORM
+    # Daily.co composed video (Brady Bunch grid) - Daily.co only
+    daily_composed_video_s3_key: str | None = None
+    daily_composed_video_duration: int | None = None
 
 
 class MeetingController:
@@ -171,6 +177,90 @@ class MeetingController:
             return None
         return Meeting(**result)
 
+    async def get_by_room_name_all(self, room_name: str) -> list[Meeting]:
+        """Get all meetings for a room name (not just most recent)."""
+        query = meetings.select().where(meetings.c.room_name == room_name)
+        results = await get_database().fetch_all(query)
+        return [Meeting(**r) for r in results]
+
+    async def get_by_room_name_and_time(
+        self,
+        room_name: NonEmptyString,
+        recording_start: datetime,
+        time_window_hours: int = 168,
+    ) -> Meeting | None:
+        """
+        Get meeting by room name closest to recording timestamp.
+
+        HACK ALERT: Daily.co doesn't return instanceId in recordings API response,
+        and mtgSessionId is separate from our instanceId. Time-based matching is
+        the least-bad workaround.
+
+        This handles edge case of duplicate room_name values in DB (race conditions,
+        double-clicks, etc.) by matching based on temporal proximity.
+
+        Algorithm:
+        1. Find meetings within time_window_hours of recording_start
+        2. Return meeting with start_date closest to recording_start
+        3. If tie, return first by meeting.id (deterministic)
+
+        Args:
+            room_name: Daily.co room name from recording
+            recording_start: Timezone-aware datetime from recording.start_ts
+            time_window_hours: Search window (default 168 = 1 week)
+
+        Returns:
+            Meeting closest to recording timestamp, or None if no matches
+
+        Failure modes:
+        - Multiple meetings in same room within ~5 minutes: picks closest
+        - All meetings outside time window: returns None
+        - Clock skew between Daily.co and DB: 1-week window tolerates this
+
+        Why 1 week window:
+        - Handles webhook failures (recording discovered days later)
+        - Tolerates clock skew
+        - Rejects unrelated meetings from weeks ago
+
+        """
+        # Validate timezone-aware datetime
+        if recording_start.tzinfo is None:
+            raise ValueError(
+                f"recording_start must be timezone-aware, got naive datetime: {recording_start}"
+            )
+
+        window_start = recording_start - timedelta(hours=time_window_hours)
+        window_end = recording_start + timedelta(hours=time_window_hours)
+
+        query = (
+            meetings.select()
+            .where(
+                sa.and_(
+                    meetings.c.room_name == room_name,
+                    meetings.c.start_date >= window_start,
+                    meetings.c.start_date <= window_end,
+                )
+            )
+            .order_by(meetings.c.start_date)
+        )
+
+        results = await get_database().fetch_all(query)
+        if not results:
+            return None
+
+        candidates = [Meeting(**r) for r in results]
+
+        # Find meeting with start_date closest to recording_start
+        closest = min(
+            candidates,
+            key=lambda m: (
+                abs((m.start_date - recording_start).total_seconds()),
+                m.id,  # Tie-breaker: deterministic by UUID
+            ),
+        )
+
+        return closest
+
     async def get_active(self, room: Room, current_time: datetime) -> Meeting | None:
         """
         Get latest active meeting for a room.
@@ -260,6 +350,44 @@ class MeetingController:
         query = meetings.update().where(meetings.c.id == meeting_id).values(**kwargs)
         await get_database().execute(query)
 
+    async def set_cloud_recording_if_missing(
+        self,
+        meeting_id: NonEmptyString,
+        s3_key: NonEmptyString,
+        duration: int,
+    ) -> bool:
+        """
+        Set cloud recording only if not already set.
+
+        Returns True if updated, False if already set.
+        Prevents webhook/polling race condition via atomic WHERE clause.
+        """
+        # Check current value before update to detect actual change
+        meeting_before = await self.get_by_id(meeting_id)
+        if not meeting_before:
+            return False
+
+        was_null = meeting_before.daily_composed_video_s3_key is None
+
+        query = (
+            meetings.update()
+            .where(
+                sa.and_(
+                    meetings.c.id == meeting_id,
+                    meetings.c.daily_composed_video_s3_key.is_(None),
+                )
+            )
+            .values(
+                daily_composed_video_s3_key=s3_key,
+                daily_composed_video_duration=duration,
+            )
+        )
+        await get_database().execute(query)
+
+        # Return True only if value was NULL before (actual update occurred)
+        # If was_null=False, the WHERE clause prevented the update
+        return was_null
+
     async def increment_num_clients(self, meeting_id: str) -> None:
         """Atomically increment participant count."""
         query = (

server/reflector/db/recordings.py

@@ -7,6 +7,7 @@ from sqlalchemy import or_
 
 from reflector.db import get_database, metadata
 from reflector.utils import generate_uuid4
+from reflector.utils.string import NonEmptyString
 
 recordings = sa.Table(
     "recording",
@@ -71,6 +72,19 @@ class RecordingController:
         query = recordings.delete().where(recordings.c.id == id)
         await get_database().execute(query)
 
+    async def set_meeting_id(
+        self,
+        recording_id: NonEmptyString,
+        meeting_id: NonEmptyString,
+    ) -> None:
+        """Link recording to meeting."""
+        query = (
+            recordings.update()
+            .where(recordings.c.id == recording_id)
+            .values(meeting_id=meeting_id)
+        )
+        await get_database().execute(query)
+
     # no check for existence
     async def get_by_ids(self, recording_ids: list[str]) -> list[Recording]:
         if not recording_ids:

server/reflector/db/rooms.py

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

server/reflector/db/search.py

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

server/reflector/db/transcripts.py

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

server/reflector/db/users.py

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

server/reflector/hatchet/broadcast.py

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

server/reflector/hatchet/client.py

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

server/reflector/hatchet/constants.py

@@ -35,7 +35,16 @@ LLM_RATE_LIMIT_PER_SECOND = 10
 
 # Task execution timeouts (seconds)
 TIMEOUT_SHORT = 60  # Quick operations: API calls, DB updates
-TIMEOUT_MEDIUM = 120  # Single LLM calls, waveform generation
+TIMEOUT_MEDIUM = (
+    300  # Single LLM calls, waveform generation (5m for slow LLM responses)
+)
 TIMEOUT_LONG = 180  # Action items (larger context LLM)
-TIMEOUT_AUDIO = 300  # Audio processing: padding, mixdown
-TIMEOUT_HEAVY = 600  # Transcription, fan-out LLM tasks
+TIMEOUT_TITLE = 300  # generate_title (single LLM call; doc: reduce from 600s)
+TIMEOUT_AUDIO = 720  # Audio processing: padding, mixdown (Hatchet execution_timeout)
+TIMEOUT_AUDIO_HTTP = (
+    660  # httpx timeout for pad_track — below 720 so Hatchet doesn't race
+)
+TIMEOUT_HEAVY = 600  # Transcription, fan-out LLM tasks (Hatchet execution_timeout)
+TIMEOUT_HEAVY_HTTP = (
+    540  # httpx timeout for transcribe_track — below 600 so Hatchet doesn't race
+)

server/reflector/hatchet/error_classification.py

@@ -0,0 +1,74 @@
+"""Classify exceptions as non-retryable for Hatchet workflows.
+
+When a task raises NonRetryableException (or an exception classified as
+non-retryable and re-raised as such), Hatchet stops immediately — no further
+retries. Used by with_error_handling to avoid wasting retries on config errors,
+auth failures, corrupt data, etc.
+"""
+
+# Optional dependencies: only classify if the exception type is available.
+# This avoids hard dependency on openai/av/botocore for code paths that don't use them.
+try:
+    import openai
+except ImportError:
+    openai = None  # type: ignore[assignment]
+
+try:
+    import av
+except ImportError:
+    av = None  # type: ignore[assignment]
+
+try:
+    from botocore.exceptions import ClientError as BotoClientError
+except ImportError:
+    BotoClientError = None  # type: ignore[misc, assignment]
+
+from hatchet_sdk import NonRetryableException
+from httpx import HTTPStatusError
+
+from reflector.llm import LLMParseError
+
+# HTTP status codes that won't change on retry (auth, not found, payment, payload)
+NON_RETRYABLE_HTTP_STATUSES = {401, 402, 403, 404, 413}
+NON_RETRYABLE_S3_CODES = {"AccessDenied", "NoSuchBucket", "NoSuchKey"}
+
+
+def is_non_retryable(e: BaseException) -> bool:
+    """Return True if the exception should stop Hatchet retries immediately.
+
+    Hard failures (config, auth, missing resource, corrupt data) return True.
+    Transient errors (timeouts, 5xx, 429, connection) return False.
+    """
+    if isinstance(e, NonRetryableException):
+        return True
+
+    # Config/input errors
+    if isinstance(e, (ValueError, TypeError)):
+        return True
+
+    # HTTP status codes that won't change on retry
+    if isinstance(e, HTTPStatusError):
+        return e.response.status_code in NON_RETRYABLE_HTTP_STATUSES
+
+    # OpenAI auth errors
+    if openai is not None and isinstance(e, openai.AuthenticationError):
+        return True
+
+    # LLM parse failures (already retried internally)
+    if isinstance(e, LLMParseError):
+        return True
+
+    # S3 permission/existence errors
+    if BotoClientError is not None and isinstance(e, BotoClientError):
+        code = e.response.get("Error", {}).get("Code", "")
+        return code in NON_RETRYABLE_S3_CODES
+
+    # Corrupt audio (PyAV) — AVError in some versions; fallback to InvalidDataError
+    if av is not None:
+        av_error = getattr(av, "AVError", None) or getattr(
+            getattr(av, "error", None), "InvalidDataError", None
+        )
+        if av_error is not None and isinstance(e, av_error):
+            return True
+
+    return False

server/reflector/hatchet/run_workers_cpu.py

@@ -7,6 +7,7 @@ Configuration:
 - Worker affinity: pool=cpu-heavy
 """
 
+import reflector._warnings_filter  # noqa: F401 -- side effect: suppress pydantic validate_default warning
 from reflector.hatchet.client import HatchetClientManager
 from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     daily_multitrack_pipeline,

server/reflector/hatchet/run_workers_llm.py

@@ -3,6 +3,9 @@ LLM/I/O worker pool for all non-CPU tasks.
 Handles: all tasks except mixdown_tracks (transcription, LLM inference, orchestration)
 """
 
+import asyncio
+
+import reflector._warnings_filter  # noqa: F401 -- side effect: suppress pydantic validate_default warning
 from reflector.hatchet.client import HatchetClientManager
 from reflector.hatchet.workflows.daily_multitrack_pipeline import (
     daily_multitrack_pipeline,
@@ -20,6 +23,15 @@ POOL = "llm-io"
 def main():
     hatchet = HatchetClientManager.get_client()
 
+    try:
+        asyncio.run(HatchetClientManager.ensure_rate_limit())
+    except Exception as e:
+        logger.warning(
+            "[Hatchet] Rate limit initialization failed, but continuing. "
+            "If workflows fail to register, rate limits may need to be created manually.",
+            error=str(e),
+        )
+
     logger.info(
         "Starting Hatchet LLM worker pool (all tasks except mixdown)",
         worker_name=WORKER_NAME,

server/reflector/hatchet/workflows/daily_multitrack_pipeline.py

@@ -27,6 +27,7 @@ from hatchet_sdk import (
     ConcurrencyExpression,
     ConcurrencyLimitStrategy,
     Context,
+    NonRetryableException,
 )
 from hatchet_sdk.labels import DesiredWorkerLabel
 from pydantic import BaseModel
@@ -43,8 +44,10 @@ from reflector.hatchet.constants import (
     TIMEOUT_LONG,
     TIMEOUT_MEDIUM,
     TIMEOUT_SHORT,
+    TIMEOUT_TITLE,
     TaskName,
 )
+from reflector.hatchet.error_classification import is_non_retryable
 from reflector.hatchet.workflows.models import (
     ActionItemsResult,
     ConsentResult,
@@ -90,7 +93,6 @@ from reflector.processors.summary.summary_builder import SummaryBuilder
 from reflector.processors.types import TitleSummary, Word
 from reflector.processors.types import Transcript as TranscriptType
 from reflector.settings import settings
-from reflector.storage.storage_aws import AwsStorage
 from reflector.utils.audio_constants import (
     PRESIGNED_URL_EXPIRATION_SECONDS,
     WAVEFORM_SEGMENTS,
@@ -117,6 +119,7 @@ class PipelineInput(BaseModel):
     bucket_name: NonEmptyString
     transcript_id: NonEmptyString
     room_id: NonEmptyString | None = None
+    source_platform: str = "daily"
 
 
 hatchet = HatchetClientManager.get_client()
@@ -170,13 +173,10 @@ async def set_workflow_error_status(transcript_id: NonEmptyString) -> bool:
 
 
 def _spawn_storage():
-    """Create fresh storage instance."""
-    return AwsStorage(
-        aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
-        aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
-        aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
-        aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
-    )
+    """Create fresh storage instance for writing to our transcript bucket."""
+    from reflector.storage import get_transcripts_storage  # noqa: PLC0415
+
+    return get_transcripts_storage()
 
 
 class Loggable(Protocol):
@@ -219,6 +219,13 @@ def make_audio_progress_logger(
 R = TypeVar("R")
 
 
+def _successful_run_results(
+    results: list[dict[str, Any] | BaseException],
+) -> list[dict[str, Any]]:
+    """Return only successful (non-exception) results from aio_run_many(return_exceptions=True)."""
+    return [r for r in results if not isinstance(r, BaseException)]
+
+
 def with_error_handling(
     step_name: TaskName, set_error_status: bool = True
 ) -> Callable[
@@ -246,8 +253,12 @@ def with_error_handling(
                     error=str(e),
                     exc_info=True,
                 )
-                if set_error_status:
-                    await set_workflow_error_status(input.transcript_id)
+                if is_non_retryable(e):
+                    # Hard fail: stop retries, set error status, fail workflow
+                    if set_error_status:
+                        await set_workflow_error_status(input.transcript_id)
+                    raise NonRetryableException(str(e)) from e
+                # Transient: do not set error status — Hatchet will retry
                 raise
 
         return wrapper  # type: ignore[return-value]
@@ -256,7 +267,10 @@ def with_error_handling(
 
 
 @daily_multitrack_pipeline.task(
-    execution_timeout=timedelta(seconds=TIMEOUT_SHORT), retries=3
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
 )
 @with_error_handling(TaskName.GET_RECORDING)
 async def get_recording(input: PipelineInput, ctx: Context) -> RecordingResult:
@@ -312,6 +326,8 @@ async def get_recording(input: PipelineInput, ctx: Context) -> RecordingResult:
     parents=[get_recording],
     execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
 )
 @with_error_handling(TaskName.GET_PARTICIPANTS)
 async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsResult:
@@ -322,6 +338,7 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
     mtg_session_id = recording.mtg_session_id
     async with fresh_db_connection():
         from reflector.db.transcripts import (  # noqa: PLC0415
+            TranscriptDuration,
             TranscriptParticipant,
             transcripts_controller,
         )
@@ -330,15 +347,26 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
         if not transcript:
             raise ValueError(f"Transcript {input.transcript_id} not found")
         # Note: title NOT cleared - preserves existing titles
+        # Duration from Daily API (seconds -> milliseconds) - master source
+        duration_ms = recording.duration * 1000 if recording.duration else 0
         await transcripts_controller.update(
             transcript,
             {
                 "events": [],
                 "topics": [],
                 "participants": [],
+                "duration": duration_ms,
             },
         )
 
+        await append_event_and_broadcast(
+            input.transcript_id,
+            transcript,
+            "DURATION",
+            TranscriptDuration(duration=duration_ms),
+            logger=logger,
+        )
+
         mtg_session_id = assert_non_none_and_non_empty(
             mtg_session_id, "mtg_session_id is required"
         )
@@ -403,6 +431,8 @@ async def get_participants(input: PipelineInput, ctx: Context) -> ParticipantsRe
     parents=[get_participants],
     execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
 )
 @with_error_handling(TaskName.PROCESS_TRACKS)
 async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksResult:
@@ -420,12 +450,13 @@ async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksRes
                 bucket_name=input.bucket_name,
                 transcript_id=input.transcript_id,
                 language=source_language,
+                source_platform=input.source_platform,
             )
         )
         for i, track in enumerate(input.tracks)
     ]
 
-    results = await track_workflow.aio_run_many(bulk_runs)
+    results = await track_workflow.aio_run_many(bulk_runs, return_exceptions=True)
 
     target_language = participants_result.target_language
 
@@ -433,7 +464,18 @@ async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksRes
     padded_tracks = []
     created_padded_files = set()
 
-    for result in results:
+    for i, result in enumerate(results):
+        if isinstance(result, BaseException):
+            logger.error(
+                "[Hatchet] process_tracks: track workflow failed, failing step",
+                transcript_id=input.transcript_id,
+                track_index=i,
+                error=str(result),
+            )
+            ctx.log(f"process_tracks: track {i} failed ({result}), failing step")
+            raise ValueError(
+                f"Track {i} workflow failed after retries: {result!s}"
+            ) from result
         transcribe_result = TranscribeTrackResult(**result[TaskName.TRANSCRIBE_TRACK])
         track_words.append(transcribe_result.words)
 
@@ -471,7 +513,9 @@ async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksRes
 @daily_multitrack_pipeline.task(
     parents=[process_tracks],
     execution_timeout=timedelta(seconds=TIMEOUT_AUDIO),
-    retries=3,
+    retries=2,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
     desired_worker_labels={
         "pool": DesiredWorkerLabel(
             value="cpu-heavy",
@@ -583,6 +627,8 @@ async def mixdown_tracks(input: PipelineInput, ctx: Context) -> MixdownResult:
     parents=[mixdown_tracks],
     execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
 )
 @with_error_handling(TaskName.GENERATE_WAVEFORM)
 async def generate_waveform(input: PipelineInput, ctx: Context) -> WaveformResult:
@@ -651,6 +697,8 @@ async def generate_waveform(input: PipelineInput, ctx: Context) -> WaveformResul
     parents=[process_tracks],
     execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
 )
 @with_error_handling(TaskName.DETECT_TOPICS)
 async def detect_topics(input: PipelineInput, ctx: Context) -> TopicsResult:
@@ -712,11 +760,22 @@ async def detect_topics(input: PipelineInput, ctx: Context) -> TopicsResult:
         for chunk in chunks
     ]
 
-    results = await topic_chunk_workflow.aio_run_many(bulk_runs)
+    results = await topic_chunk_workflow.aio_run_many(bulk_runs, return_exceptions=True)
 
-    topic_chunks = [
-        TopicChunkResult(**result[TaskName.DETECT_CHUNK_TOPIC]) for result in results
-    ]
+    topic_chunks: list[TopicChunkResult] = []
+    for i, result in enumerate(results):
+        if isinstance(result, BaseException):
+            logger.error(
+                "[Hatchet] detect_topics: chunk workflow failed, failing step",
+                transcript_id=input.transcript_id,
+                chunk_index=i,
+                error=str(result),
+            )
+            ctx.log(f"detect_topics: chunk {i} failed ({result}), failing step")
+            raise ValueError(
+                f"Topic chunk {i} workflow failed after retries: {result!s}"
+            ) from result
+        topic_chunks.append(TopicChunkResult(**result[TaskName.DETECT_CHUNK_TOPIC]))
 
     async with fresh_db_connection():
         transcript = await transcripts_controller.get_by_id(input.transcript_id)
@@ -754,8 +813,10 @@ async def detect_topics(input: PipelineInput, ctx: Context) -> TopicsResult:
 
 @daily_multitrack_pipeline.task(
     parents=[detect_topics],
-    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    execution_timeout=timedelta(seconds=TIMEOUT_TITLE),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
 )
 @with_error_handling(TaskName.GENERATE_TITLE)
 async def generate_title(input: PipelineInput, ctx: Context) -> TitleResult:
@@ -820,7 +881,9 @@ async def generate_title(input: PipelineInput, ctx: Context) -> TitleResult:
 @daily_multitrack_pipeline.task(
     parents=[detect_topics],
     execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
-    retries=3,
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
 )
 @with_error_handling(TaskName.EXTRACT_SUBJECTS)
 async def extract_subjects(input: PipelineInput, ctx: Context) -> SubjectsResult:
@@ -899,6 +962,8 @@ async def extract_subjects(input: PipelineInput, ctx: Context) -> SubjectsResult
     parents=[extract_subjects],
     execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
 )
 @with_error_handling(TaskName.PROCESS_SUBJECTS)
 async def process_subjects(input: PipelineInput, ctx: Context) -> ProcessSubjectsResult:
@@ -925,12 +990,24 @@ async def process_subjects(input: PipelineInput, ctx: Context) -> ProcessSubject
         for i, subject in enumerate(subjects)
     ]
 
-    results = await subject_workflow.aio_run_many(bulk_runs)
+    results = await subject_workflow.aio_run_many(bulk_runs, return_exceptions=True)
 
-    subject_summaries = [
-        SubjectSummaryResult(**result[TaskName.GENERATE_DETAILED_SUMMARY])
-        for result in results
-    ]
+    subject_summaries: list[SubjectSummaryResult] = []
+    for i, result in enumerate(results):
+        if isinstance(result, BaseException):
+            logger.error(
+                "[Hatchet] process_subjects: subject workflow failed, failing step",
+                transcript_id=input.transcript_id,
+                subject_index=i,
+                error=str(result),
+            )
+            ctx.log(f"process_subjects: subject {i} failed ({result}), failing step")
+            raise ValueError(
+                f"Subject {i} workflow failed after retries: {result!s}"
+            ) from result
+        subject_summaries.append(
+            SubjectSummaryResult(**result[TaskName.GENERATE_DETAILED_SUMMARY])
+        )
 
     ctx.log(f"process_subjects complete: {len(subject_summaries)} summaries")
 
@@ -941,6 +1018,8 @@ async def process_subjects(input: PipelineInput, ctx: Context) -> ProcessSubject
     parents=[process_subjects],
     execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
 )
 @with_error_handling(TaskName.GENERATE_RECAP)
 async def generate_recap(input: PipelineInput, ctx: Context) -> RecapResult:
@@ -1030,6 +1109,8 @@ async def generate_recap(input: PipelineInput, ctx: Context) -> RecapResult:
     parents=[extract_subjects],
     execution_timeout=timedelta(seconds=TIMEOUT_LONG),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
 )
 @with_error_handling(TaskName.IDENTIFY_ACTION_ITEMS)
 async def identify_action_items(
@@ -1095,9 +1176,11 @@ async def identify_action_items(
 
 
 @daily_multitrack_pipeline.task(
-    parents=[generate_waveform, generate_title, generate_recap, identify_action_items],
+    parents=[process_tracks, generate_title, generate_recap, identify_action_items],
     execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
     retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=5,
 )
 @with_error_handling(TaskName.FINALIZE)
 async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
@@ -1108,12 +1191,8 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
     """
     ctx.log("finalize: saving transcript and setting status to 'ended'")
 
-    mixdown_result = ctx.task_output(mixdown_tracks)
     track_result = ctx.task_output(process_tracks)
 
-    duration = mixdown_result.duration
-    all_words = track_result.all_words
-
     # Cleanup temporary padded S3 files (deferred until finalize for semantic parity with Celery)
     created_padded_files = track_result.created_padded_files
     if created_padded_files:
@@ -1133,7 +1212,6 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
 
     async with fresh_db_connection():
         from reflector.db.transcripts import (  # noqa: PLC0415
-            TranscriptDuration,
             TranscriptText,
             transcripts_controller,
         )
@@ -1142,34 +1220,26 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
         if transcript is None:
             raise ValueError(f"Transcript {input.transcript_id} not found in database")
 
-        merged_transcript = TranscriptType(words=all_words, translation=None)
-
         await append_event_and_broadcast(
             input.transcript_id,
             transcript,
             "TRANSCRIPT",
             TranscriptText(
-                text=merged_transcript.text,
-                translation=merged_transcript.translation,
+                text="",
+                translation=None,
             ),
             logger=logger,
         )
 
-        # Save duration and clear workflow_run_id (workflow completed successfully)
-        # Note: title/long_summary/short_summary already saved by their callbacks
+        # Clear workflow_run_id (workflow completed successfully)
+        # Note: title/long_summary/short_summary/duration already saved by their callbacks
         await transcripts_controller.update(
             transcript,
             {
-                "duration": duration,
                 "workflow_run_id": None,  # Clear on success - no need to resume
             },
         )
 
-        duration_data = TranscriptDuration(duration=duration)
-        await append_event_and_broadcast(
-            input.transcript_id, transcript, "DURATION", duration_data, logger=logger
-        )
-
         await set_status_and_broadcast(input.transcript_id, "ended", logger=logger)
 
         ctx.log(
@@ -1180,7 +1250,11 @@ async def finalize(input: PipelineInput, ctx: Context) -> FinalizeResult:
 
 
 @daily_multitrack_pipeline.task(
-    parents=[finalize], execution_timeout=timedelta(seconds=TIMEOUT_SHORT), retries=3
+    parents=[finalize],
+    execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=10,
 )
 @with_error_handling(TaskName.CLEANUP_CONSENT, set_error_status=False)
 async def cleanup_consent(input: PipelineInput, ctx: Context) -> ConsentResult:
@@ -1194,7 +1268,10 @@ async def cleanup_consent(input: PipelineInput, ctx: Context) -> ConsentResult:
         )
         from reflector.db.recordings import recordings_controller  # noqa: PLC0415
         from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
-        from reflector.storage import get_transcripts_storage  # noqa: PLC0415
+        from reflector.storage import (  # noqa: PLC0415
+            get_source_storage,
+            get_transcripts_storage,
+        )
 
         transcript = await transcripts_controller.get_by_id(input.transcript_id)
         if not transcript:
@@ -1244,7 +1321,7 @@ async def cleanup_consent(input: PipelineInput, ctx: Context) -> ConsentResult:
         deletion_errors = []
 
         if input_track_keys and input.bucket_name:
-            master_storage = get_transcripts_storage()
+            master_storage = get_source_storage(input.source_platform)
             for key in input_track_keys:
                 try:
                     await master_storage.delete_file(key, bucket=input.bucket_name)
@@ -1283,6 +1360,8 @@ async def cleanup_consent(input: PipelineInput, ctx: Context) -> ConsentResult:
     parents=[cleanup_consent],
     execution_timeout=timedelta(seconds=TIMEOUT_SHORT),
     retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
 )
 @with_error_handling(TaskName.POST_ZULIP, set_error_status=False)
 async def post_zulip(input: PipelineInput, ctx: Context) -> ZulipResult:
@@ -1310,6 +1389,8 @@ async def post_zulip(input: PipelineInput, ctx: Context) -> ZulipResult:
     parents=[cleanup_consent],
     execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
     retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=15,
 )
 @with_error_handling(TaskName.SEND_WEBHOOK, set_error_status=False)
 async def send_webhook(input: PipelineInput, ctx: Context) -> WebhookResult:
@@ -1347,14 +1428,63 @@ async def send_webhook(input: PipelineInput, ctx: Context) -> WebhookResult:
             f"participants={len(payload.transcript.participants)})"
         )
 
-        response = await send_webhook_request(
-            url=room.webhook_url,
-            payload=payload,
-            event_type="transcript.completed",
-            webhook_secret=room.webhook_secret,
-            timeout=30.0,
-        )
+        try:
+            response = await send_webhook_request(
+                url=room.webhook_url,
+                payload=payload,
+                event_type="transcript.completed",
+                webhook_secret=room.webhook_secret,
+                timeout=30.0,
+            )
 
-        ctx.log(f"send_webhook complete: status_code={response.status_code}")
+            ctx.log(f"send_webhook complete: status_code={response.status_code}")
+            return WebhookResult(webhook_sent=True, response_code=response.status_code)
 
-        return WebhookResult(webhook_sent=True, response_code=response.status_code)
+        except httpx.HTTPStatusError as e:
+            ctx.log(
+                f"send_webhook failed (HTTP {e.response.status_code}), continuing anyway"
+            )
+            return WebhookResult(
+                webhook_sent=False, response_code=e.response.status_code
+            )
+
+        except httpx.ConnectError as e:
+            ctx.log(f"send_webhook failed (connection error), continuing anyway: {e}")
+            return WebhookResult(webhook_sent=False)
+
+        except httpx.TimeoutException as e:
+            ctx.log(f"send_webhook failed (timeout), continuing anyway: {e}")
+            return WebhookResult(webhook_sent=False)
+
+        except Exception as e:
+            ctx.log(f"send_webhook unexpected error, continuing anyway: {e}")
+            return WebhookResult(webhook_sent=False)
+
+
+async def on_workflow_failure(input: PipelineInput, ctx: Context) -> None:
+    """Run when the workflow is truly dead (all retries exhausted).
+
+    Sets transcript status to 'error' only if it is not already 'ended'.
+    Post-finalize tasks (cleanup_consent, post_zulip, send_webhook) use
+    set_error_status=False; if one of them fails, we must not overwrite
+    the 'ended' status that finalize already set.
+    """
+    async with fresh_db_connection():
+        from reflector.db.transcripts import transcripts_controller  # noqa: PLC0415
+
+        transcript = await transcripts_controller.get_by_id(input.transcript_id)
+        if transcript and transcript.status == "ended":
+            logger.info(
+                "[Hatchet] on_workflow_failure: transcript already ended, skipping error status (failure was post-finalize)",
+                transcript_id=input.transcript_id,
+            )
+            ctx.log(
+                "on_workflow_failure: transcript already ended, skipping error status"
+            )
+            return
+    await set_workflow_error_status(input.transcript_id)
+
+
+@daily_multitrack_pipeline.on_failure_task()
+async def _register_on_workflow_failure(input: PipelineInput, ctx: Context) -> None:
+    await on_workflow_failure(input, ctx)

server/reflector/hatchet/workflows/padding_workflow.py

@@ -0,0 +1,143 @@
+"""
+Hatchet child workflow: PaddingWorkflow
+Handles individual audio track padding via Modal.com backend.
+"""
+
+from datetime import timedelta
+
+import av
+from hatchet_sdk import Context
+from pydantic import BaseModel
+
+from reflector.hatchet.client import HatchetClientManager
+from reflector.hatchet.constants import TIMEOUT_AUDIO
+from reflector.hatchet.workflows.models import PadTrackResult
+from reflector.logger import logger
+from reflector.utils.audio_constants import PRESIGNED_URL_EXPIRATION_SECONDS
+from reflector.utils.audio_padding import extract_stream_start_time_from_container
+
+
+class PaddingInput(BaseModel):
+    """Input for individual track padding."""
+
+    track_index: int
+    s3_key: str
+    bucket_name: str
+    transcript_id: str
+    source_platform: str = "daily"
+
+
+hatchet = HatchetClientManager.get_client()
+
+padding_workflow = hatchet.workflow(
+    name="PaddingWorkflow", input_validator=PaddingInput
+)
+
+
+@padding_workflow.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_AUDIO),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
+async def pad_track(input: PaddingInput, ctx: Context) -> PadTrackResult:
+    """Pad audio track with silence based on WebM container start_time."""
+    ctx.log(f"pad_track: track {input.track_index}, s3_key={input.s3_key}")
+    logger.info(
+        "[Hatchet] pad_track",
+        track_index=input.track_index,
+        s3_key=input.s3_key,
+        transcript_id=input.transcript_id,
+    )
+
+    try:
+        from reflector.storage import (  # noqa: PLC0415
+            get_source_storage,
+            get_transcripts_storage,
+        )
+
+        # Source reads: use platform-specific credentials
+        source_storage = get_source_storage(input.source_platform)
+        source_url = await source_storage.get_file_url(
+            input.s3_key,
+            operation="get_object",
+            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
+            bucket=input.bucket_name,
+        )
+
+        # Extract start_time to determine if padding needed
+        with av.open(source_url) as in_container:
+            if in_container.duration:
+                try:
+                    duration = timedelta(seconds=in_container.duration // 1_000_000)
+                    ctx.log(
+                        f"pad_track: track {input.track_index}, duration={duration}"
+                    )
+                except (ValueError, TypeError, OverflowError) as e:
+                    ctx.log(
+                        f"pad_track: track {input.track_index}, duration error: {str(e)}"
+                    )
+
+            start_time_seconds = extract_stream_start_time_from_container(
+                in_container, input.track_index, logger=logger
+            )
+
+        if start_time_seconds <= 0:
+            logger.info(
+                f"Track {input.track_index} requires no padding",
+                track_index=input.track_index,
+            )
+            return PadTrackResult(
+                padded_key=input.s3_key,
+                bucket_name=input.bucket_name,
+                size=0,
+                track_index=input.track_index,
+            )
+
+        storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
+
+        # Output writes: use transcript storage (our own bucket)
+        output_storage = get_transcripts_storage()
+        output_url = await output_storage.get_file_url(
+            storage_path,
+            operation="put_object",
+            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
+        )
+
+        from reflector.processors.audio_padding_auto import (  # noqa: PLC0415
+            AudioPaddingAutoProcessor,
+        )
+
+        processor = AudioPaddingAutoProcessor()
+        result = await processor.pad_track(
+            track_url=source_url,
+            output_url=output_url,
+            start_time_seconds=start_time_seconds,
+            track_index=input.track_index,
+        )
+        file_size = result.size
+
+        ctx.log(f"pad_track: padding returned size={file_size}")
+
+        logger.info(
+            "[Hatchet] pad_track complete",
+            track_index=input.track_index,
+            padded_key=storage_path,
+        )
+
+        return PadTrackResult(
+            padded_key=storage_path,
+            bucket_name=None,  # None = use default transcript storage bucket
+            size=file_size,
+            track_index=input.track_index,
+        )
+
+    except Exception as e:
+        logger.error(
+            "[Hatchet] pad_track failed",
+            transcript_id=input.transcript_id,
+            track_index=input.track_index,
+            error=str(e),
+            exc_info=True,
+        )
+        raise

server/reflector/hatchet/workflows/subject_processing.py

@@ -13,7 +13,7 @@ from hatchet_sdk.rate_limit import RateLimit
 from pydantic import BaseModel
 
 from reflector.hatchet.client import HatchetClientManager
-from reflector.hatchet.constants import LLM_RATE_LIMIT_KEY, TIMEOUT_MEDIUM
+from reflector.hatchet.constants import LLM_RATE_LIMIT_KEY, TIMEOUT_HEAVY
 from reflector.hatchet.workflows.models import SubjectSummaryResult
 from reflector.logger import logger
 from reflector.processors.summary.prompts import (
@@ -41,8 +41,10 @@ subject_workflow = hatchet.workflow(
 
 
 @subject_workflow.task(
-    execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
-    retries=3,
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=60,
     rate_limits=[RateLimit(static_key=LLM_RATE_LIMIT_KEY, units=2)],
 )
 async def generate_detailed_summary(

server/reflector/hatchet/workflows/topic_chunk_processing.py

@@ -50,7 +50,9 @@ topic_chunk_workflow = hatchet.workflow(
 
 @topic_chunk_workflow.task(
     execution_timeout=timedelta(seconds=TIMEOUT_MEDIUM),
-    retries=3,
+    retries=5,
+    backoff_factor=2.0,
+    backoff_max_seconds=60,
     rate_limits=[RateLimit(static_key=LLM_RATE_LIMIT_KEY, units=1)],
 )
 async def detect_chunk_topic(input: TopicChunkInput, ctx: Context) -> TopicChunkResult:
@@ -71,7 +73,7 @@ async def detect_chunk_topic(input: TopicChunkInput, ctx: Context) -> TopicChunk
     from reflector.settings import settings  # noqa: PLC0415
     from reflector.utils.text import clean_title  # noqa: PLC0415
 
-    llm = LLM(settings=settings, temperature=0.9, max_tokens=500)
+    llm = LLM(settings=settings, temperature=0.9)
 
     prompt = TOPIC_PROMPT.format(text=input.chunk_text)
     response = await llm.get_structured_response(

server/reflector/hatchet/workflows/track_processing.py

@@ -14,9 +14,7 @@ Hatchet workers run in forked processes; fresh imports per task ensure
 storage/DB connections are not shared across forks.
 """
 
-import tempfile
 from datetime import timedelta
-from pathlib import Path
 
 import av
 from hatchet_sdk import Context
@@ -27,10 +25,7 @@ from reflector.hatchet.constants import TIMEOUT_AUDIO, TIMEOUT_HEAVY
 from reflector.hatchet.workflows.models import PadTrackResult, TranscribeTrackResult
 from reflector.logger import logger
 from reflector.utils.audio_constants import PRESIGNED_URL_EXPIRATION_SECONDS
-from reflector.utils.audio_padding import (
-    apply_audio_padding_to_file,
-    extract_stream_start_time_from_container,
-)
+from reflector.utils.audio_padding import extract_stream_start_time_from_container
 
 
 class TrackInput(BaseModel):
@@ -41,6 +36,7 @@ class TrackInput(BaseModel):
     bucket_name: str
     transcript_id: str
     language: str = "en"
+    source_platform: str = "daily"
 
 
 hatchet = HatchetClientManager.get_client()
@@ -48,7 +44,12 @@ hatchet = HatchetClientManager.get_client()
 track_workflow = hatchet.workflow(name="TrackProcessing", input_validator=TrackInput)
 
 
-@track_workflow.task(execution_timeout=timedelta(seconds=TIMEOUT_AUDIO), retries=3)
+@track_workflow.task(
+    execution_timeout=timedelta(seconds=TIMEOUT_AUDIO),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
+)
 async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
     """Pad single audio track with silence for alignment.
 
@@ -64,18 +65,14 @@ async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
     )
 
     try:
-        # Create fresh storage instance to avoid aioboto3 fork issues
-        from reflector.settings import settings  # noqa: PLC0415
-        from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
-
-        storage = AwsStorage(
-            aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
-            aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
-            aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
-            aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
+        from reflector.storage import (  # noqa: PLC0415
+            get_source_storage,
+            get_transcripts_storage,
         )
 
-        source_url = await storage.get_file_url(
+        # Source reads: use platform-specific credentials
+        source_storage = get_source_storage(input.source_platform)
+        source_url = await source_storage.get_file_url(
             input.s3_key,
             operation="get_object",
             expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
@@ -83,63 +80,45 @@ async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
         )
 
         with av.open(source_url) as in_container:
-            if in_container.duration:
-                try:
-                    duration = timedelta(seconds=in_container.duration // 1_000_000)
-                    ctx.log(
-                        f"pad_track: track {input.track_index}, duration={duration}"
-                    )
-                except Exception:
-                    ctx.log(f"pad_track: track {input.track_index}, duration=ERROR")
-
             start_time_seconds = extract_stream_start_time_from_container(
                 in_container, input.track_index, logger=logger
             )
 
-            # If no padding needed, return original S3 key
-            if start_time_seconds <= 0:
-                logger.info(
-                    f"Track {input.track_index} requires no padding",
-                    track_index=input.track_index,
-                )
-                return PadTrackResult(
-                    padded_key=input.s3_key,
-                    bucket_name=input.bucket_name,
-                    size=0,
-                    track_index=input.track_index,
-                )
+        # If no padding needed, return original S3 key
+        if start_time_seconds <= 0:
+            logger.info(
+                f"Track {input.track_index} requires no padding",
+                track_index=input.track_index,
+            )
+            return PadTrackResult(
+                padded_key=input.s3_key,
+                bucket_name=input.bucket_name,
+                size=0,
+                track_index=input.track_index,
+            )
 
-            with tempfile.NamedTemporaryFile(suffix=".webm", delete=False) as temp_file:
-                temp_path = temp_file.name
+        storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
 
-            try:
-                apply_audio_padding_to_file(
-                    in_container,
-                    temp_path,
-                    start_time_seconds,
-                    input.track_index,
-                    logger=logger,
-                )
+        # Output writes: use transcript storage (our own bucket)
+        output_storage = get_transcripts_storage()
+        output_url = await output_storage.get_file_url(
+            storage_path,
+            operation="put_object",
+            expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
+        )
 
-                file_size = Path(temp_path).stat().st_size
-                storage_path = f"file_pipeline_hatchet/{input.transcript_id}/tracks/padded_{input.track_index}.webm"
+        from reflector.processors.audio_padding_auto import (  # noqa: PLC0415
+            AudioPaddingAutoProcessor,
+        )
 
-                logger.info(
-                    f"About to upload padded track",
-                    key=storage_path,
-                    size=file_size,
-                )
-
-                with open(temp_path, "rb") as padded_file:
-                    await storage.put_file(storage_path, padded_file)
-
-                logger.info(
-                    f"Uploaded padded track to S3",
-                    key=storage_path,
-                    size=file_size,
-                )
-            finally:
-                Path(temp_path).unlink(missing_ok=True)
+        processor = AudioPaddingAutoProcessor()
+        result = await processor.pad_track(
+            track_url=source_url,
+            output_url=output_url,
+            start_time_seconds=start_time_seconds,
+            track_index=input.track_index,
+        )
+        file_size = result.size
 
         ctx.log(f"pad_track complete: track {input.track_index} -> {storage_path}")
         logger.info(
@@ -163,7 +142,11 @@ async def pad_track(input: TrackInput, ctx: Context) -> PadTrackResult:
 
 
 @track_workflow.task(
-    parents=[pad_track], execution_timeout=timedelta(seconds=TIMEOUT_HEAVY), retries=3
+    parents=[pad_track],
+    execution_timeout=timedelta(seconds=TIMEOUT_HEAVY),
+    retries=3,
+    backoff_factor=2.0,
+    backoff_max_seconds=30,
 )
 async def transcribe_track(input: TrackInput, ctx: Context) -> TranscribeTrackResult:
     """Transcribe audio track using GPU (Modal.com) or local Whisper."""
@@ -183,16 +166,18 @@ async def transcribe_track(input: TrackInput, ctx: Context) -> TranscribeTrackRe
             raise ValueError("Missing padded_key from pad_track")
 
         # Presign URL on demand (avoids stale URLs on workflow replay)
-        from reflector.settings import settings  # noqa: PLC0415
-        from reflector.storage.storage_aws import AwsStorage  # noqa: PLC0415
-
-        storage = AwsStorage(
-            aws_bucket_name=settings.TRANSCRIPT_STORAGE_AWS_BUCKET_NAME,
-            aws_region=settings.TRANSCRIPT_STORAGE_AWS_REGION,
-            aws_access_key_id=settings.TRANSCRIPT_STORAGE_AWS_ACCESS_KEY_ID,
-            aws_secret_access_key=settings.TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY,
+        from reflector.storage import (  # noqa: PLC0415
+            get_source_storage,
+            get_transcripts_storage,
         )
 
+        # If bucket_name is set, file is still in the platform's source bucket (no padding applied).
+        # If bucket_name is None, padded file was written to our transcript storage.
+        if bucket_name:
+            storage = get_source_storage(input.source_platform)
+        else:
+            storage = get_transcripts_storage()
+
         audio_url = await storage.get_file_url(
             padded_key,
             operation="get_object",

server/reflector/llm.py

@@ -1,42 +1,23 @@
 import logging
 from contextvars import ContextVar
-from typing import Generic, Type, TypeVar
+from typing import Type, TypeVar
 from uuid import uuid4
 
 from llama_index.core import Settings
-from llama_index.core.output_parsers import PydanticOutputParser
+from llama_index.core.prompts import PromptTemplate
 from llama_index.core.response_synthesizers import TreeSummarize
-from llama_index.core.workflow import (
-    Context,
-    Event,
-    StartEvent,
-    StopEvent,
-    Workflow,
-    step,
-)
 from llama_index.llms.openai_like import OpenAILike
 from pydantic import BaseModel, ValidationError
-from workflows.errors import WorkflowTimeoutError
 
 from reflector.utils.retry import retry
 
 T = TypeVar("T", bound=BaseModel)
-OutputT = TypeVar("OutputT", bound=BaseModel)
 
 # Session ID for LiteLLM request grouping - set per processing run
 llm_session_id: ContextVar[str | None] = ContextVar("llm_session_id", default=None)
 
 logger = logging.getLogger(__name__)
 
-STRUCTURED_RESPONSE_PROMPT_TEMPLATE = """
-Based on the following analysis, provide the information in the requested JSON format:
-
-Analysis:
-{analysis}
-
-{format_instructions}
-"""
-
 
 class LLMParseError(Exception):
     """Raised when LLM output cannot be parsed after retries."""
@@ -50,148 +31,10 @@ class LLMParseError(Exception):
         )
 
 
-class ExtractionDone(Event):
-    """Event emitted when LLM JSON formatting completes."""
-
-    output: str
-
-
-class ValidationErrorEvent(Event):
-    """Event emitted when validation fails."""
-
-    error: str
-    wrong_output: str
-
-
-class StructuredOutputWorkflow(Workflow, Generic[OutputT]):
-    """Workflow for structured output extraction with validation retry.
-
-    This workflow handles parse/validation retries only. Network error retries
-    are handled internally by Settings.llm (OpenAILike max_retries=3).
-    The caller should NOT wrap this workflow in additional retry logic.
-    """
-
-    def __init__(
-        self,
-        output_cls: Type[OutputT],
-        max_retries: int = 3,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.output_cls: Type[OutputT] = output_cls
-        self.max_retries = max_retries
-        self.output_parser = PydanticOutputParser(output_cls)
-
-    @step
-    async def extract(
-        self, ctx: Context, ev: StartEvent | ValidationErrorEvent
-    ) -> StopEvent | ExtractionDone:
-        """Extract structured data from text using two-step LLM process.
-
-        Step 1 (first call only): TreeSummarize generates text analysis
-        Step 2 (every call): Settings.llm.acomplete formats analysis as JSON
-        """
-        current_retries = await ctx.store.get("retries", default=0)
-        await ctx.store.set("retries", current_retries + 1)
-
-        if current_retries >= self.max_retries:
-            last_error = await ctx.store.get("last_error", default=None)
-            logger.error(
-                f"Max retries ({self.max_retries}) reached for {self.output_cls.__name__}"
-            )
-            return StopEvent(result={"error": last_error, "attempts": current_retries})
-
-        if isinstance(ev, StartEvent):
-            # First call: run TreeSummarize to get analysis, store in context
-            prompt = ev.get("prompt")
-            texts = ev.get("texts")
-            tone_name = ev.get("tone_name")
-            if not prompt or not isinstance(texts, list):
-                raise ValueError(
-                    "StartEvent must contain 'prompt' (str) and 'texts' (list)"
-                )
-
-            summarizer = TreeSummarize(verbose=False)
-            analysis = await summarizer.aget_response(
-                prompt, texts, tone_name=tone_name
-            )
-            await ctx.store.set("analysis", str(analysis))
-            reflection = ""
-        else:
-            # Retry: reuse analysis from context
-            analysis = await ctx.store.get("analysis")
-            if not analysis:
-                raise RuntimeError("Internal error: analysis not found in context")
-
-            wrong_output = ev.wrong_output
-            if len(wrong_output) > 2000:
-                wrong_output = wrong_output[:2000] + "... [truncated]"
-            reflection = (
-                f"\n\nYour previous response could not be parsed:\n{wrong_output}\n\n"
-                f"Error:\n{ev.error}\n\n"
-                "Please try again. Return ONLY valid JSON matching the schema above, "
-                "with no markdown formatting or extra text."
-            )
-
-        # Step 2: Format analysis as JSON using LLM completion
-        format_instructions = self.output_parser.format(
-            "Please structure the above information in the following JSON format:"
-        )
-
-        json_prompt = STRUCTURED_RESPONSE_PROMPT_TEMPLATE.format(
-            analysis=analysis,
-            format_instructions=format_instructions + reflection,
-        )
-
-        # Network retries handled by OpenAILike (max_retries=3)
-        response = await Settings.llm.acomplete(json_prompt)
-        return ExtractionDone(output=response.text)
-
-    @step
-    async def validate(
-        self, ctx: Context, ev: ExtractionDone
-    ) -> StopEvent | ValidationErrorEvent:
-        """Validate extracted output against Pydantic schema."""
-        raw_output = ev.output
-        retries = await ctx.store.get("retries", default=0)
-
-        try:
-            parsed = self.output_parser.parse(raw_output)
-            if retries > 1:
-                logger.info(
-                    f"LLM parse succeeded on attempt {retries}/{self.max_retries} "
-                    f"for {self.output_cls.__name__}"
-                )
-            return StopEvent(result={"success": parsed})
-
-        except (ValidationError, ValueError) as e:
-            error_msg = self._format_error(e, raw_output)
-            await ctx.store.set("last_error", error_msg)
-
-            logger.error(
-                f"LLM parse error (attempt {retries}/{self.max_retries}): "
-                f"{type(e).__name__}: {e}\nRaw response: {raw_output[:500]}"
-            )
-
-            return ValidationErrorEvent(
-                error=error_msg,
-                wrong_output=raw_output,
-            )
-
-    def _format_error(self, error: Exception, raw_output: str) -> str:
-        """Format error for LLM feedback."""
-        if isinstance(error, ValidationError):
-            error_messages = []
-            for err in error.errors():
-                field = ".".join(str(loc) for loc in err["loc"])
-                error_messages.append(f"- {err['msg']} in field '{field}'")
-            return "Schema validation errors:\n" + "\n".join(error_messages)
-        else:
-            return f"Parse error: {str(error)}"
-
-
 class LLM:
-    def __init__(self, settings, temperature: float = 0.4, max_tokens: int = 2048):
+    def __init__(
+        self, settings, temperature: float = 0.4, max_tokens: int | None = None
+    ):
         self.settings_obj = settings
         self.model_name = settings.LLM_MODEL
         self.url = settings.LLM_URL
@@ -212,19 +55,35 @@ class LLM:
             api_key=self.api_key,
             context_window=self.context_window,
             is_chat_model=True,
-            is_function_calling_model=False,
+            is_function_calling_model=True,
             temperature=self.temperature,
             max_tokens=self.max_tokens,
+            timeout=self.settings_obj.LLM_REQUEST_TIMEOUT,
             additional_kwargs={"extra_body": {"litellm_session_id": session_id}},
         )
 
     async def get_response(
         self, prompt: str, texts: list[str], tone_name: str | None = None
     ) -> str:
-        """Get a text response using TreeSummarize for non-function-calling models"""
-        summarizer = TreeSummarize(verbose=False)
-        response = await summarizer.aget_response(prompt, texts, tone_name=tone_name)
-        return str(response).strip()
+        """Get a text response using TreeSummarize for non-function-calling models.
+
+        Uses the same retry() wrapper as get_structured_response for transient
+        network errors (connection, timeout, OSError) with exponential backoff.
+        """
+
+        async def _call():
+            summarizer = TreeSummarize(verbose=False)
+            response = await summarizer.aget_response(
+                prompt, texts, tone_name=tone_name
+            )
+            return str(response).strip()
+
+        return await retry(_call)(
+            retry_attempts=3,
+            retry_backoff_interval=1.0,
+            retry_backoff_max=30.0,
+            retry_ignore_exc_types=(ConnectionError, TimeoutError, OSError),
+        )
 
     async def get_structured_response(
         self,
@@ -234,36 +93,91 @@ class LLM:
         tone_name: str | None = None,
         timeout: int | None = None,
     ) -> T:
-        """Get structured output from LLM with validation retry via Workflow."""
-        if timeout is None:
-            timeout = self.settings_obj.LLM_STRUCTURED_RESPONSE_TIMEOUT
+        """Get structured output from LLM using tool-call with reflection retry.
 
-        async def run_workflow():
-            workflow = StructuredOutputWorkflow(
+        Uses astructured_predict (function-calling / tool-call mode) for the
+        first attempt.  On ValidationError or parse failure the wrong output
+        and error are fed back as a reflection prompt and the call is retried
+        up to LLM_PARSE_MAX_RETRIES times.
+
+        The outer retry() wrapper handles transient network errors with
+        exponential back-off.
+        """
+        max_retries = self.settings_obj.LLM_PARSE_MAX_RETRIES
+
+        async def _call_with_reflection():
+            # Build full prompt: instruction + source texts
+            if texts:
+                texts_block = "\n\n".join(texts)
+                full_prompt = f"{prompt}\n\n{texts_block}"
+            else:
+                full_prompt = prompt
+
+            prompt_tmpl = PromptTemplate("{user_prompt}")
+            last_error: str | None = None
+
+            for attempt in range(1, max_retries + 2):  # +2: first try + retries
+                try:
+                    if attempt == 1:
+                        result = await Settings.llm.astructured_predict(
+                            output_cls, prompt_tmpl, user_prompt=full_prompt
+                        )
+                    else:
+                        reflection_tmpl = PromptTemplate(
+                            "{user_prompt}\n\n{reflection}"
+                        )
+                        result = await Settings.llm.astructured_predict(
+                            output_cls,
+                            reflection_tmpl,
+                            user_prompt=full_prompt,
+                            reflection=reflection,
+                        )
+
+                    if attempt > 1:
+                        logger.info(
+                            f"LLM structured_predict succeeded on attempt "
+                            f"{attempt}/{max_retries + 1} for {output_cls.__name__}"
+                        )
+                    return result
+
+                except (ValidationError, ValueError) as e:
+                    wrong_output = str(e)
+                    if len(wrong_output) > 2000:
+                        wrong_output = wrong_output[:2000] + "... [truncated]"
+
+                    last_error = self._format_validation_error(e)
+                    reflection = (
+                        f"Your previous response could not be parsed.\n\n"
+                        f"Error:\n{last_error}\n\n"
+                        "Please try again and return valid data matching the schema."
+                    )
+
+                    logger.error(
+                        f"LLM parse error (attempt {attempt}/{max_retries + 1}): "
+                        f"{type(e).__name__}: {e}\n"
+                        f"Raw response: {wrong_output[:500]}"
+                    )
+
+            raise LLMParseError(
                 output_cls=output_cls,
-                max_retries=self.settings_obj.LLM_PARSE_MAX_RETRIES + 1,
-                timeout=timeout,
+                error_msg=last_error or "Max retries exceeded",
+                attempts=max_retries + 1,
             )
 
-            result = await workflow.run(
-                prompt=prompt,
-                texts=texts,
-                tone_name=tone_name,
-            )
-
-            if "error" in result:
-                error_msg = result["error"] or "Max retries exceeded"
-                raise LLMParseError(
-                    output_cls=output_cls,
-                    error_msg=error_msg,
-                    attempts=result.get("attempts", 0),
-                )
-
-            return result["success"]
-
-        return await retry(run_workflow)(
+        return await retry(_call_with_reflection)(
             retry_attempts=3,
             retry_backoff_interval=1.0,
             retry_backoff_max=30.0,
-            retry_ignore_exc_types=(WorkflowTimeoutError,),
+            retry_ignore_exc_types=(ConnectionError, TimeoutError, OSError),
         )
+
+    @staticmethod
+    def _format_validation_error(error: Exception) -> str:
+        """Format a validation/parse error for LLM reflection feedback."""
+        if isinstance(error, ValidationError):
+            error_messages = []
+            for err in error.errors():
+                field = ".".join(str(loc) for loc in err["loc"])
+                error_messages.append(f"- {err['msg']} in field '{field}'")
+            return "Schema validation errors:\n" + "\n".join(error_messages)
+        return f"Parse error: {str(error)}"

server/reflector/pipelines/main_live_pipeline.py

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

server/reflector/processors/__init__.py

@@ -4,6 +4,8 @@ from .audio_diarization_auto import AudioDiarizationAutoProcessor  # noqa: F401
 from .audio_downscale import AudioDownscaleProcessor  # noqa: F401
 from .audio_file_writer import AudioFileWriterProcessor  # noqa: F401
 from .audio_merge import AudioMergeProcessor  # noqa: F401
+from .audio_padding import AudioPaddingProcessor  # noqa: F401
+from .audio_padding_auto import AudioPaddingAutoProcessor  # noqa: F401
 from .audio_transcript import AudioTranscriptProcessor  # noqa: F401
 from .audio_transcript_auto import AudioTranscriptAutoProcessor  # noqa: F401
 from .base import (  # noqa: F401

server/reflector/processors/_audio_download.py

@@ -0,0 +1,86 @@
+"""
+Shared audio download utility for local processors.
+
+Downloads audio from a URL to a temporary file for in-process ML inference.
+"""
+
+import asyncio
+import os
+import tempfile
+from pathlib import Path
+
+import requests
+
+from reflector.logger import logger
+
+S3_TIMEOUT = 60
+
+
+async def download_audio_to_temp(url: str) -> Path:
+    """Download audio from URL to a temporary file.
+
+    The caller is responsible for deleting the temp file after use.
+
+    Args:
+        url: Presigned URL or public URL to download audio from.
+
+    Returns:
+        Path to the downloaded temporary file.
+    """
+    loop = asyncio.get_event_loop()
+    return await loop.run_in_executor(None, _download_blocking, url)
+
+
+def _download_blocking(url: str) -> Path:
+    """Blocking download implementation."""
+    log = logger.bind(url=url[:80])
+    log.info("Downloading audio to temp file")
+
+    response = requests.get(url, stream=True, timeout=S3_TIMEOUT)
+    response.raise_for_status()
+
+    # Determine extension from content-type or URL
+    ext = _detect_extension(url, response.headers.get("content-type", ""))
+
+    fd, tmp_path = tempfile.mkstemp(suffix=ext)
+    try:
+        total_bytes = 0
+        with os.fdopen(fd, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+                    total_bytes += len(chunk)
+        log.info("Audio downloaded", bytes=total_bytes, path=tmp_path)
+        return Path(tmp_path)
+    except Exception:
+        # Clean up on failure
+        try:
+            os.unlink(tmp_path)
+        except OSError:
+            pass
+        raise
+
+
+def _detect_extension(url: str, content_type: str) -> str:
+    """Detect audio file extension from URL or content-type."""
+    # Try URL path first
+    path = url.split("?")[0]  # Strip query params
+    for ext in (".wav", ".mp3", ".mp4", ".m4a", ".webm", ".ogg", ".flac"):
+        if path.lower().endswith(ext):
+            return ext
+
+    # Try content-type
+    ct_map = {
+        "audio/wav": ".wav",
+        "audio/x-wav": ".wav",
+        "audio/mpeg": ".mp3",
+        "audio/mp4": ".m4a",
+        "audio/webm": ".webm",
+        "audio/ogg": ".ogg",
+        "audio/flac": ".flac",
+    }
+    for ct, ext in ct_map.items():
+        if ct in content_type.lower():
+            return ext
+
+    return ".audio"

server/reflector/processors/_marian_translator_service.py

@@ -0,0 +1,76 @@
+"""
+MarianMT translation service.
+
+Singleton service that loads HuggingFace MarianMT translation models
+and reuses them across all MarianMT translator processor instances.
+
+Ported from gpu/self_hosted/app/services/translator.py for in-process use.
+"""
+
+import logging
+import threading
+
+from transformers import MarianMTModel, MarianTokenizer, pipeline
+
+logger = logging.getLogger(__name__)
+
+
+class MarianTranslatorService:
+    """MarianMT text translation service for in-process use."""
+
+    def __init__(self):
+        self._pipeline = None
+        self._current_pair = None
+        self._lock = threading.Lock()
+
+    def load(self, source_language: str = "en", target_language: str = "fr"):
+        """Load the translation model for a specific language pair."""
+        model_name = self._resolve_model_name(source_language, target_language)
+        logger.info(
+            "Loading MarianMT model: %s (%s -> %s)",
+            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)
+        self._current_pair = (source_language.lower(), target_language.lower())
+
+    def _resolve_model_name(self, src: str, tgt: str) -> str:
+        """Resolve language pair to MarianMT model name."""
+        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:
+        """Translate text between languages.
+
+        Args:
+            text: Text to translate.
+            source_language: Source language code (e.g. "en").
+            target_language: Target language code (e.g. "fr").
+
+        Returns:
+            dict with "text" key containing {source_language: original, target_language: translated}.
+        """
+        pair = (source_language.lower(), target_language.lower())
+        if self._pipeline is None or self._current_pair != pair:
+            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}}
+
+
+# Module-level singleton — shared across all MarianMT translator processors
+translator_service = MarianTranslatorService()

server/reflector/processors/_pyannote_diarization_service.py

@@ -0,0 +1,133 @@
+"""
+Pyannote diarization service using pyannote.audio.
+
+Singleton service that loads the pyannote speaker diarization model once
+and reuses it across all pyannote diarization processor instances.
+
+Ported from gpu/self_hosted/app/services/diarizer.py for in-process use.
+"""
+
+import logging
+import tarfile
+import threading
+from pathlib import Path
+from urllib.request import urlopen
+
+import torch
+import torchaudio
+import yaml
+from pyannote.audio import Pipeline
+
+from reflector.settings import settings
+
+logger = logging.getLogger(__name__)
+
+S3_BUNDLE_URL = "https://reflector-public.s3.us-east-1.amazonaws.com/pyannote-speaker-diarization-3.1.tar.gz"
+BUNDLE_CACHE_DIR = Path.home() / ".cache" / "pyannote-bundle"
+
+
+def _ensure_model(cache_dir: Path) -> str:
+    """Download and extract S3 model bundle if not cached."""
+    model_dir = cache_dir / "pyannote-speaker-diarization-3.1"
+    config_path = model_dir / "config.yaml"
+
+    if config_path.exists():
+        logger.info("Using cached model bundle at %s", model_dir)
+        return str(model_dir)
+
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    tarball_path = cache_dir / "model.tar.gz"
+
+    logger.info("Downloading model bundle from %s", S3_BUNDLE_URL)
+    with urlopen(S3_BUNDLE_URL) as response, open(tarball_path, "wb") as f:
+        while chunk := response.read(8192):
+            f.write(chunk)
+
+    logger.info("Extracting model bundle")
+    with tarfile.open(tarball_path, "r:gz") as tar:
+        tar.extractall(path=cache_dir, filter="data")
+    tarball_path.unlink()
+
+    _patch_config(model_dir, cache_dir)
+    return str(model_dir)
+
+
+def _patch_config(model_dir: Path, cache_dir: Path) -> None:
+    """Rewrite config.yaml to reference local pytorch_model.bin paths."""
+    config_path = model_dir / "config.yaml"
+    with open(config_path) as f:
+        config = yaml.safe_load(f)
+
+    config["pipeline"]["params"]["segmentation"] = str(
+        cache_dir / "pyannote-segmentation-3.0" / "pytorch_model.bin"
+    )
+    config["pipeline"]["params"]["embedding"] = str(
+        cache_dir / "pyannote-wespeaker-voxceleb-resnet34-LM" / "pytorch_model.bin"
+    )
+
+    with open(config_path, "w") as f:
+        yaml.dump(config, f)
+
+    logger.info("Patched config.yaml with local model paths")
+
+
+class PyannoteDiarizationService:
+    """Pyannote speaker diarization service for in-process use."""
+
+    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"
+        hf_token = settings.HF_TOKEN
+
+        if hf_token:
+            logger.info("Loading pyannote model from HuggingFace (HF_TOKEN set)")
+            self._pipeline = Pipeline.from_pretrained(
+                "pyannote/speaker-diarization-3.1",
+                use_auth_token=hf_token,
+            )
+        else:
+            logger.info("HF_TOKEN not set — loading model from S3 bundle")
+            model_path = _ensure_model(BUNDLE_CACHE_DIR)
+            config_path = Path(model_path) / "config.yaml"
+            self._pipeline = Pipeline.from_pretrained(str(config_path))
+
+        self._pipeline.to(torch.device(self._device))
+
+    def diarize_file(self, file_path: str, timestamp: float = 0.0) -> dict:
+        """Run speaker diarization on an audio file.
+
+        Args:
+            file_path: Path to the audio file.
+            timestamp: Offset to add to all segment timestamps.
+
+        Returns:
+            dict with "diarization" key containing list of
+            {"start": float, "end": float, "speaker": int} segments.
+        """
+        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}
+            )
+        segments = []
+        for diarization_segment, _, speaker in diarization.itertracks(yield_label=True):
+            segments.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": segments}
+
+
+# Module-level singleton — shared across all pyannote diarization processors
+diarization_service = PyannoteDiarizationService()

server/reflector/processors/audio_diarization_pyannote.py

@@ -1,74 +1,37 @@
+"""
+Pyannote audio diarization processor using pyannote.audio in-process.
+
+Downloads audio from URL, runs pyannote diarization locally,
+and returns speaker segments. No HTTP backend needed.
+"""
+
+import asyncio
 import os
 
-import torch
-import torchaudio
-from pyannote.audio import Pipeline
-
+from reflector.processors._audio_download import download_audio_to_temp
+from reflector.processors._pyannote_diarization_service import diarization_service
 from reflector.processors.audio_diarization import AudioDiarizationProcessor
 from reflector.processors.audio_diarization_auto import AudioDiarizationAutoProcessor
-from reflector.processors.types import AudioDiarizationInput, DiarizationSegment
+from reflector.processors.types import AudioDiarizationInput
 
 
 class AudioDiarizationPyannoteProcessor(AudioDiarizationProcessor):
-    """Local diarization processor using pyannote.audio library"""
+    INPUT_TYPE = AudioDiarizationInput
 
-    def __init__(
-        self,
-        model_name: str = "pyannote/speaker-diarization-3.1",
-        pyannote_auth_token: str | None = None,
-        device: str | None = None,
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.model_name = model_name
-        self.auth_token = pyannote_auth_token or os.environ.get("HF_TOKEN")
-        self.device = device
-
-        if device is None:
-            self.device = "cuda" if torch.cuda.is_available() else "cpu"
-
-        self.logger.info(f"Loading pyannote diarization model: {self.model_name}")
-        self.diarization_pipeline = Pipeline.from_pretrained(
-            self.model_name, use_auth_token=self.auth_token
-        )
-        self.diarization_pipeline.to(torch.device(self.device))
-        self.logger.info(f"Diarization model loaded on device: {self.device}")
-
-    async def _diarize(self, data: AudioDiarizationInput) -> list[DiarizationSegment]:
+    async def _diarize(self, data: AudioDiarizationInput):
+        """Run pyannote diarization on audio from URL."""
+        tmp_path = await download_audio_to_temp(data.audio_url)
         try:
-            # Load audio file (audio_url is assumed to be a local file path)
-            self.logger.info(f"Loading local audio file: {data.audio_url}")
-            waveform, sample_rate = torchaudio.load(data.audio_url)
-            audio_input = {"waveform": waveform, "sample_rate": sample_rate}
-            self.logger.info("Running speaker diarization")
-            diarization = self.diarization_pipeline(audio_input)
-
-            # Convert pyannote diarization output to our format
-            segments = []
-            for segment, _, speaker in diarization.itertracks(yield_label=True):
-                # Extract speaker number from label (e.g., "SPEAKER_00" -> 0)
-                speaker_id = 0
-                if speaker.startswith("SPEAKER_"):
-                    try:
-                        speaker_id = int(speaker.split("_")[-1])
-                    except (ValueError, IndexError):
-                        # Fallback to hash-based ID if parsing fails
-                        speaker_id = hash(speaker) % 1000
-
-                segments.append(
-                    {
-                        "start": round(segment.start, 3),
-                        "end": round(segment.end, 3),
-                        "speaker": speaker_id,
-                    }
-                )
-
-            self.logger.info(f"Diarization completed with {len(segments)} segments")
-            return segments
-
-        except Exception as e:
-            self.logger.exception(f"Diarization failed: {e}")
-            raise
+            loop = asyncio.get_event_loop()
+            result = await loop.run_in_executor(
+                None, diarization_service.diarize_file, str(tmp_path)
+            )
+            return result["diarization"]
+        finally:
+            try:
+                os.unlink(tmp_path)
+            except OSError:
+                pass
 
 
 AudioDiarizationAutoProcessor.register("pyannote", AudioDiarizationPyannoteProcessor)

server/reflector/processors/audio_padding.py

@@ -0,0 +1,23 @@
+"""
+Base class for audio padding processors.
+"""
+
+from pydantic import BaseModel
+
+
+class PaddingResponse(BaseModel):
+    size: int
+    cancelled: bool = False
+
+
+class AudioPaddingProcessor:
+    """Base class for audio padding processors."""
+
+    async def pad_track(
+        self,
+        track_url: str,
+        output_url: str,
+        start_time_seconds: float,
+        track_index: int,
+    ) -> PaddingResponse:
+        raise NotImplementedError

server/reflector/processors/audio_padding_auto.py

@@ -0,0 +1,32 @@
+import importlib
+
+from reflector.processors.audio_padding import AudioPaddingProcessor
+from reflector.settings import settings
+
+
+class AudioPaddingAutoProcessor(AudioPaddingProcessor):
+    _registry = {}
+
+    @classmethod
+    def register(cls, name, kclass):
+        cls._registry[name] = kclass
+
+    def __new__(cls, name: str | None = None, **kwargs):
+        if name is None:
+            name = settings.PADDING_BACKEND
+        if name not in cls._registry:
+            module_name = f"reflector.processors.audio_padding_{name}"
+            importlib.import_module(module_name)
+
+        # gather specific configuration for the processor
+        # search `PADDING_XXX_YYY`, push to constructor as `xxx_yyy`
+        config = {}
+        name_upper = name.upper()
+        settings_prefix = "PADDING_"
+        config_prefix = f"{settings_prefix}{name_upper}_"
+        for key, value in settings:
+            if key.startswith(config_prefix):
+                config_name = key[len(settings_prefix) :].lower()
+                config[config_name] = value
+
+        return cls._registry[name](**config | kwargs)

server/reflector/processors/audio_padding_modal.py

@@ -0,0 +1,112 @@
+"""
+Modal.com backend for audio padding.
+"""
+
+import asyncio
+import os
+
+import httpx
+
+from reflector.hatchet.constants import TIMEOUT_AUDIO_HTTP
+from reflector.logger import logger
+from reflector.processors.audio_padding import AudioPaddingProcessor, PaddingResponse
+from reflector.processors.audio_padding_auto import AudioPaddingAutoProcessor
+
+
+class AudioPaddingModalProcessor(AudioPaddingProcessor):
+    """Audio padding processor using Modal.com CPU backend via HTTP."""
+
+    def __init__(
+        self, padding_url: str | None = None, modal_api_key: str | None = None
+    ):
+        self.padding_url = padding_url or os.getenv("PADDING_URL")
+        if not self.padding_url:
+            raise ValueError(
+                "PADDING_URL required to use AudioPaddingModalProcessor. "
+                "Set PADDING_URL environment variable or pass padding_url parameter."
+            )
+
+        self.modal_api_key = modal_api_key or os.getenv("MODAL_API_KEY")
+
+    async def pad_track(
+        self,
+        track_url: str,
+        output_url: str,
+        start_time_seconds: float,
+        track_index: int,
+    ) -> PaddingResponse:
+        """Pad audio track with silence via Modal backend.
+
+        Args:
+            track_url: Presigned GET URL for source audio track
+            output_url: Presigned PUT URL for output WebM
+            start_time_seconds: Amount of silence to prepend
+            track_index: Track index for logging
+        """
+        if not track_url:
+            raise ValueError("track_url cannot be empty")
+        if start_time_seconds <= 0:
+            raise ValueError(
+                f"start_time_seconds must be positive, got {start_time_seconds}"
+            )
+
+        log = logger.bind(track_index=track_index, padding_seconds=start_time_seconds)
+        log.info("Sending Modal padding HTTP request")
+
+        url = f"{self.padding_url}/pad"
+
+        headers = {}
+        if self.modal_api_key:
+            headers["Authorization"] = f"Bearer {self.modal_api_key}"
+
+        try:
+            async with httpx.AsyncClient(timeout=TIMEOUT_AUDIO_HTTP) as client:
+                response = await client.post(
+                    url,
+                    headers=headers,
+                    json={
+                        "track_url": track_url,
+                        "output_url": output_url,
+                        "start_time_seconds": start_time_seconds,
+                        "track_index": track_index,
+                    },
+                    follow_redirects=True,
+                )
+
+                if response.status_code != 200:
+                    error_body = response.text
+                    log.error(
+                        "Modal padding API error",
+                        status_code=response.status_code,
+                        error_body=error_body,
+                    )
+
+                response.raise_for_status()
+                result = response.json()
+
+            # Check if work was cancelled
+            if result.get("cancelled"):
+                log.warning("Modal padding was cancelled by disconnect detection")
+                raise asyncio.CancelledError(
+                    "Padding cancelled due to client disconnect"
+                )
+
+            log.info("Modal padding complete", size=result["size"])
+            return PaddingResponse(**result)
+        except asyncio.CancelledError:
+            log.warning(
+                "Modal padding cancelled (Hatchet timeout, disconnect detected on Modal side)"
+            )
+            raise
+        except httpx.TimeoutException as e:
+            log.error("Modal padding timeout", error=str(e), exc_info=True)
+            raise Exception(f"Modal padding timeout: {e}") from e
+        except httpx.HTTPStatusError as e:
+            log.error("Modal padding HTTP error", error=str(e), exc_info=True)
+            raise Exception(f"Modal padding HTTP error: {e}") from e
+        except Exception as e:
+            log.error("Modal padding unexpected error", error=str(e), exc_info=True)
+            raise
+
+
+AudioPaddingAutoProcessor.register("modal", AudioPaddingModalProcessor)