mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2025-12-20 20:29:06 +00:00
Compare commits
27 Commits
igor/daili
...
mathieu/ji
| Author | SHA1 | Date | |
|---|---|---|---|
| e91979abbc | |||
| 95e8011975 | |||
| 293f7d4f1f | |||
| 41224a424c | |||
| dd0089906f | |||
| fa559b1970 | |||
| c26ce65083 | |||
| 52eff2acc0 | |||
| 7875ec3432 | |||
| 398be06fad | |||
| da700069d9 | |||
| 51229a1790 | |||
| 2d2c23f7cc | |||
| 0acb9cac79 | |||
| d861d92cc2 | |||
| 24ff83a2ec | |||
| 249234238c | |||
| 42a603d5c3 | |||
| 6d2092f950 | |||
| f2bb6aaecb | |||
| 2b136ac7b0 | |||
| 3f4fc26483 | |||
| 8e5ef5bca6 | |||
| d49fdcb38d | |||
| d42380abf1 | |||
| cf64e1a3d9 | |||
| ea53ca7000 |
57
.github/workflows/docker-frontend.yml
vendored
57
.github/workflows/docker-frontend.yml
vendored
@@ -1,57 +0,0 @@
|
||||
name: Build and Push Frontend Docker Image
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- 'www/**'
|
||||
- '.github/workflows/docker-frontend.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
REGISTRY: ghcr.io
|
||||
IMAGE_NAME: ${{ github.repository }}-frontend
|
||||
|
||||
jobs:
|
||||
build-and-push:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Log in to GitHub Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=sha,prefix={{branch}}-
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: ./www
|
||||
file: ./www/Dockerfile
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
platforms: linux/amd64,linux/arm64
|
||||
69
CHANGELOG.md
69
CHANGELOG.md
@@ -1,74 +1,5 @@
|
||||
# Changelog
|
||||
|
||||
## [0.14.0](https://github.com/Monadical-SAS/reflector/compare/v0.13.1...v0.14.0) (2025-10-08)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* Add calendar event data to transcript webhook payload ([#689](https://github.com/Monadical-SAS/reflector/issues/689)) ([5f6910e](https://github.com/Monadical-SAS/reflector/commit/5f6910e5131b7f28f86c9ecdcc57fed8412ee3cd))
|
||||
* container build for www / github ([#672](https://github.com/Monadical-SAS/reflector/issues/672)) ([969bd84](https://github.com/Monadical-SAS/reflector/commit/969bd84fcc14851d1a101412a0ba115f1b7cde82))
|
||||
* docker-compose for production frontend ([#664](https://github.com/Monadical-SAS/reflector/issues/664)) ([5bf64b5](https://github.com/Monadical-SAS/reflector/commit/5bf64b5a41f64535e22849b4bb11734d4dbb4aae))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* restore feature boolean logic ([#671](https://github.com/Monadical-SAS/reflector/issues/671)) ([3660884](https://github.com/Monadical-SAS/reflector/commit/36608849ec64e953e3be456172502762e3c33df9))
|
||||
* security review ([#656](https://github.com/Monadical-SAS/reflector/issues/656)) ([5d98754](https://github.com/Monadical-SAS/reflector/commit/5d98754305c6c540dd194dda268544f6d88bfaf8))
|
||||
* update transcript list on reprocess ([#676](https://github.com/Monadical-SAS/reflector/issues/676)) ([9a71af1](https://github.com/Monadical-SAS/reflector/commit/9a71af145ee9b833078c78d0c684590ab12e9f0e))
|
||||
* upgrade nemo toolkit ([#678](https://github.com/Monadical-SAS/reflector/issues/678)) ([eef6dc3](https://github.com/Monadical-SAS/reflector/commit/eef6dc39037329b65804297786d852dddb0557f9))
|
||||
|
||||
## [0.13.1](https://github.com/Monadical-SAS/reflector/compare/v0.13.0...v0.13.1) (2025-09-22)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* TypeError on not all arguments converted during string formatting in logger ([#667](https://github.com/Monadical-SAS/reflector/issues/667)) ([565a629](https://github.com/Monadical-SAS/reflector/commit/565a62900f5a02fc946b68f9269a42190ed70ab6))
|
||||
|
||||
## [0.13.0](https://github.com/Monadical-SAS/reflector/compare/v0.12.1...v0.13.0) (2025-09-19)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* room form edit with enter ([#662](https://github.com/Monadical-SAS/reflector/issues/662)) ([47716f6](https://github.com/Monadical-SAS/reflector/commit/47716f6e5ddee952609d2fa0ffabdfa865286796))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* invalid cleanup call ([#660](https://github.com/Monadical-SAS/reflector/issues/660)) ([0abcebf](https://github.com/Monadical-SAS/reflector/commit/0abcebfc9491f87f605f21faa3e53996fafedd9a))
|
||||
|
||||
## [0.12.1](https://github.com/Monadical-SAS/reflector/compare/v0.12.0...v0.12.1) (2025-09-17)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* production blocked because having existing meeting with room_id null ([#657](https://github.com/Monadical-SAS/reflector/issues/657)) ([870e860](https://github.com/Monadical-SAS/reflector/commit/870e8605171a27155a9cbee215eeccb9a8d6c0a2))
|
||||
|
||||
## [0.12.0](https://github.com/Monadical-SAS/reflector/compare/v0.11.0...v0.12.0) (2025-09-17)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* calendar integration ([#608](https://github.com/Monadical-SAS/reflector/issues/608)) ([6f680b5](https://github.com/Monadical-SAS/reflector/commit/6f680b57954c688882c4ed49f40f161c52a00a24))
|
||||
* self-hosted gpu api ([#636](https://github.com/Monadical-SAS/reflector/issues/636)) ([ab859d6](https://github.com/Monadical-SAS/reflector/commit/ab859d65a6bded904133a163a081a651b3938d42))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* ignore player hotkeys for text inputs ([#646](https://github.com/Monadical-SAS/reflector/issues/646)) ([fa049e8](https://github.com/Monadical-SAS/reflector/commit/fa049e8d068190ce7ea015fd9fcccb8543f54a3f))
|
||||
|
||||
## [0.11.0](https://github.com/Monadical-SAS/reflector/compare/v0.10.0...v0.11.0) (2025-09-16)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* remove profanity filter that was there for conference ([#652](https://github.com/Monadical-SAS/reflector/issues/652)) ([b42f7cf](https://github.com/Monadical-SAS/reflector/commit/b42f7cfc606783afcee792590efcc78b507468ab))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* zulip and consent handler on the file pipeline ([#645](https://github.com/Monadical-SAS/reflector/issues/645)) ([5f143fe](https://github.com/Monadical-SAS/reflector/commit/5f143fe3640875dcb56c26694254a93189281d17))
|
||||
* zulip stream and topic selection in share dialog ([#644](https://github.com/Monadical-SAS/reflector/issues/644)) ([c546e69](https://github.com/Monadical-SAS/reflector/commit/c546e69739e68bb74fbc877eb62609928e5b8de6))
|
||||
|
||||
## [0.10.0](https://github.com/Monadical-SAS/reflector/compare/v0.9.0...v0.10.0) (2025-09-11)
|
||||
|
||||
|
||||
|
||||
@@ -151,7 +151,7 @@ All endpoints prefixed `/v1/`:
|
||||
|
||||
**Frontend** (`www/.env`):
|
||||
- `NEXTAUTH_URL`, `NEXTAUTH_SECRET` - Authentication configuration
|
||||
- `REFLECTOR_API_URL` - Backend API endpoint
|
||||
- `NEXT_PUBLIC_REFLECTOR_API_URL` - Backend API endpoint
|
||||
- `REFLECTOR_DOMAIN_CONFIG` - Feature flags and domain settings
|
||||
|
||||
## Testing Strategy
|
||||
|
||||
@@ -1,345 +0,0 @@
|
||||
# Multi-Provider Video Platform Implementation - Coder Briefing
|
||||
|
||||
## Your Mission
|
||||
|
||||
Implement multi-provider video platform support in Reflector, allowing the system to work with both Whereby and Daily.co video conferencing providers. The goal is to abstract the current Whereby-only implementation and add Daily.co as a second provider, with the ability to switch between them via environment variables.
|
||||
|
||||
**Branch:** `igor/dailico-2` (you're already on it)
|
||||
|
||||
**Estimated Time:** 12-16 hours (senior engineer)
|
||||
|
||||
**Complexity:** Medium-High (requires careful integration with existing codebase)
|
||||
|
||||
---
|
||||
|
||||
## What You Have
|
||||
|
||||
### 1. **PLAN.md** - Your Technical Specification (2,452 lines)
|
||||
- Complete step-by-step implementation guide
|
||||
- All code examples you need
|
||||
- Architecture diagrams and design rationale
|
||||
- Testing strategy and success metrics
|
||||
- **Read this first** to understand the overall approach
|
||||
|
||||
### 2. **IMPLEMENTATION_GUIDE.md** - Your Practical Guide
|
||||
- What to copy vs. adapt vs. rewrite
|
||||
- Common pitfalls and how to avoid them
|
||||
- Verification checklists for each phase
|
||||
- Decision trees for implementation choices
|
||||
- **Use this as your day-to-day reference**
|
||||
|
||||
### 3. **Reference Implementation** - `./reflector-dailyco-reference/`
|
||||
- Working implementation from 2.5 months ago
|
||||
- Good architecture and patterns
|
||||
- **BUT:** 91 commits behind current main, DO NOT merge directly
|
||||
- Use for inspiration and code patterns only
|
||||
|
||||
---
|
||||
|
||||
## Critical Context: Why Not Just Merge?
|
||||
|
||||
The reference branch (`origin/igor/feat-dailyco`) was started on August 1, 2025 and is now severely diverged from main:
|
||||
|
||||
- **91 commits behind main**
|
||||
- Main has 12x more changes (45,840 insertions vs 3,689)
|
||||
- Main added: calendar integration, webhooks, full-text search, React Query migration, security fixes
|
||||
- Reference removed: features that main still has and needs
|
||||
|
||||
**Merging would be a disaster.** We're implementing fresh on current main, using the reference for validated patterns.
|
||||
|
||||
---
|
||||
|
||||
## High-Level Approach
|
||||
|
||||
### Phase 1: Analysis (2 hours)
|
||||
- Study current Whereby integration
|
||||
- Define abstraction requirements
|
||||
- Create standard data models
|
||||
|
||||
### Phase 2: Abstraction Layer (4-5 hours)
|
||||
- Build platform abstraction (base class, registry, factory)
|
||||
- Extract Whereby into the abstraction
|
||||
- Update database schema (add `platform` field)
|
||||
- Integrate into rooms.py **without breaking calendar/webhooks**
|
||||
|
||||
### Phase 3: Daily.co Implementation (4-5 hours)
|
||||
- Implement Daily.co client
|
||||
- Add webhook handler
|
||||
- Create frontend components (rewrite API calls for React Query)
|
||||
- Add recording processing
|
||||
|
||||
### Phase 4: Testing (2-3 hours)
|
||||
- Unit tests for platform abstraction
|
||||
- Integration tests for webhooks
|
||||
- Manual testing with both providers
|
||||
|
||||
---
|
||||
|
||||
## Key Files You'll Touch
|
||||
|
||||
### Backend (New)
|
||||
```
|
||||
server/reflector/video_platforms/
|
||||
├── __init__.py
|
||||
├── base.py ← Abstract base class
|
||||
├── models.py ← Platform, MeetingData, VideoPlatformConfig
|
||||
├── registry.py ← Platform registration system
|
||||
├── factory.py ← Client creation and config
|
||||
├── whereby.py ← Whereby client wrapper
|
||||
├── daily.py ← Daily.co client
|
||||
└── mock.py ← Mock client for testing
|
||||
|
||||
server/reflector/views/daily.py ← Daily.co webhooks
|
||||
server/tests/test_video_platforms.py ← Platform tests
|
||||
server/tests/test_daily_webhook.py ← Webhook tests
|
||||
```
|
||||
|
||||
### Backend (Modified - Careful!)
|
||||
```
|
||||
server/reflector/settings.py ← Add Daily.co settings
|
||||
server/reflector/db/rooms.py ← Add platform field, PRESERVE calendar fields
|
||||
server/reflector/db/meetings.py ← Add platform field
|
||||
server/reflector/views/rooms.py ← Integrate abstraction, PRESERVE calendar/webhooks
|
||||
server/reflector/worker/process.py ← Add process_recording_from_url task
|
||||
server/reflector/app.py ← Register daily router
|
||||
server/env.example ← Document new env vars
|
||||
```
|
||||
|
||||
### Frontend (New)
|
||||
```
|
||||
www/app/[roomName]/components/
|
||||
├── RoomContainer.tsx ← Platform router
|
||||
├── DailyRoom.tsx ← Daily.co component (rewrite API calls!)
|
||||
└── WherebyRoom.tsx ← Extract existing logic
|
||||
```
|
||||
|
||||
### Frontend (Modified)
|
||||
```
|
||||
www/app/[roomName]/page.tsx ← Use RoomContainer
|
||||
www/package.json ← Add @daily-co/daily-js
|
||||
```
|
||||
|
||||
### Database
|
||||
```
|
||||
server/migrations/versions/XXXXXX_add_platform_support.py ← Generate fresh migration
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Critical Warnings ⚠️
|
||||
|
||||
### 1. **DO NOT Copy Database Migrations**
|
||||
The reference migration has the wrong `down_revision` and is based on old schema.
|
||||
```bash
|
||||
# Instead:
|
||||
cd server
|
||||
uv run alembic revision -m "add_platform_support"
|
||||
# Then edit the generated file
|
||||
```
|
||||
|
||||
### 2. **DO NOT Remove Main's Features**
|
||||
Main has calendar integration, webhooks, ICS sync that reference doesn't have.
|
||||
When modifying `rooms.py`, only change meeting creation logic, preserve everything else.
|
||||
|
||||
### 3. **DO NOT Copy Frontend API Calls**
|
||||
Reference uses old OpenAPI client. Main uses React Query.
|
||||
Check how main currently makes API calls and replicate that pattern.
|
||||
|
||||
### 4. **DO NOT Copy package.json/migrations**
|
||||
These files are severely outdated in reference.
|
||||
|
||||
### 5. **Preserve Type Safety**
|
||||
Use `TYPE_CHECKING` imports to avoid circular dependencies:
|
||||
```python
|
||||
from typing import TYPE_CHECKING
|
||||
if TYPE_CHECKING:
|
||||
from reflector.db.rooms import Room
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## How to Start
|
||||
|
||||
### Day 1 Morning: Setup & Understanding (2-3 hours)
|
||||
```bash
|
||||
# 1. Verify you're on the right branch
|
||||
git branch
|
||||
# Should show: igor/dailico-2
|
||||
|
||||
# 2. Read the docs (in order)
|
||||
# - PLAN.md (skim to understand scope, read Phase 1 carefully)
|
||||
# - IMPLEMENTATION_GUIDE.md (read fully, bookmark it)
|
||||
|
||||
# 3. Study current Whereby integration
|
||||
cat server/reflector/views/rooms.py | grep -A 20 "whereby"
|
||||
cat www/app/[roomName]/page.tsx
|
||||
|
||||
# 4. Check reference implementation structure
|
||||
ls -la reflector-dailyco-reference/server/reflector/video_platforms/
|
||||
```
|
||||
|
||||
### Day 1 Afternoon: Phase 1 Execution (2-3 hours)
|
||||
```bash
|
||||
# 5. Copy video_platforms directory from reference
|
||||
cp -r reflector-dailyco-reference/server/reflector/video_platforms/ \
|
||||
server/reflector/
|
||||
|
||||
# 6. Review and fix imports
|
||||
cd server
|
||||
uv run ruff check reflector/video_platforms/
|
||||
|
||||
# 7. Add settings to settings.py (see PLAN.md Phase 2.7)
|
||||
|
||||
# 8. Test imports work
|
||||
uv run python -c "from reflector.video_platforms import create_platform_client; print('OK')"
|
||||
```
|
||||
|
||||
### Day 2: Phase 2 - Database & Integration (4-5 hours)
|
||||
```bash
|
||||
# 9. Generate migration
|
||||
uv run alembic revision -m "add_platform_support"
|
||||
# Edit the file following PLAN.md Phase 2.8
|
||||
|
||||
# 10. Update Room/Meeting models
|
||||
# Add platform field, PRESERVE all existing fields
|
||||
|
||||
# 11. Integrate into rooms.py
|
||||
# Carefully modify meeting creation, preserve calendar/webhooks
|
||||
|
||||
# 12. Add Daily.co webhook handler
|
||||
cp reflector-dailyco-reference/server/reflector/views/daily.py \
|
||||
server/reflector/views/
|
||||
# Register in app.py
|
||||
```
|
||||
|
||||
### Day 3: Phase 3 - Frontend & Testing (4-5 hours)
|
||||
```bash
|
||||
# 13. Create frontend components
|
||||
mkdir -p www/app/[roomName]/components
|
||||
|
||||
# 14. Add Daily.co dependency
|
||||
cd www
|
||||
pnpm add @daily-co/daily-js@^0.81.0
|
||||
|
||||
# 15. Create RoomContainer, DailyRoom, WherebyRoom
|
||||
# IMPORTANT: Rewrite API calls using React Query patterns
|
||||
|
||||
# 16. Regenerate types
|
||||
pnpm openapi
|
||||
|
||||
# 17. Copy and adapt tests
|
||||
cp reflector-dailyco-reference/server/tests/test_*.py server/tests/
|
||||
|
||||
# 18. Run tests
|
||||
cd server
|
||||
REDIS_HOST=localhost \
|
||||
CELERY_BROKER_URL=redis://localhost:6379/1 \
|
||||
uv run pytest tests/test_video_platforms.py -v
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
After implementation, all of these must pass:
|
||||
|
||||
**Backend:**
|
||||
- [ ] `cd server && uv run ruff check .` passes
|
||||
- [ ] `uv run alembic upgrade head` works cleanly
|
||||
- [ ] `uv run pytest tests/test_video_platforms.py` passes
|
||||
- [ ] Can import: `from reflector.video_platforms import create_platform_client`
|
||||
- [ ] Settings has all Daily.co variables
|
||||
|
||||
**Frontend:**
|
||||
- [ ] `cd www && pnpm lint` passes
|
||||
- [ ] No TypeScript errors
|
||||
- [ ] `pnpm openapi` generates platform field
|
||||
- [ ] No `@ts-ignore` for platform field
|
||||
|
||||
**Integration:**
|
||||
- [ ] Whereby meetings still work (existing flow unchanged)
|
||||
- [ ] Calendar/webhook features still work in rooms.py
|
||||
- [ ] env.example documents all new variables
|
||||
|
||||
---
|
||||
|
||||
## When You're Stuck
|
||||
|
||||
### Check These Resources:
|
||||
1. **PLAN.md** - Detailed code examples for your exact scenario
|
||||
2. **IMPLEMENTATION_GUIDE.md** - Common pitfalls section
|
||||
3. **Reference code** - See how it was solved before
|
||||
4. **Git diff** - Compare reference to your implementation
|
||||
|
||||
### Compare Files:
|
||||
```bash
|
||||
# See what reference did
|
||||
diff reflector-dailyco-reference/server/reflector/views/rooms.py \
|
||||
server/reflector/views/rooms.py
|
||||
|
||||
# See what changed in main since reference branch
|
||||
git log --oneline --since="2025-08-01" -- server/reflector/views/rooms.py
|
||||
```
|
||||
|
||||
### Common Issues:
|
||||
- **Circular imports:** Use `TYPE_CHECKING` pattern
|
||||
- **Tests fail with postgres error:** Use `REDIS_HOST=localhost` env vars
|
||||
- **Frontend API calls broken:** Check current React Query patterns in main
|
||||
- **Migrations fail:** Ensure you generated fresh, not copied
|
||||
|
||||
---
|
||||
|
||||
## Success Looks Like
|
||||
|
||||
When you're done:
|
||||
- ✅ All tests pass
|
||||
- ✅ Linting passes
|
||||
- ✅ Can create Whereby meetings (unchanged behavior)
|
||||
- ✅ Can create Daily.co meetings (with env vars)
|
||||
- ✅ Calendar/webhooks still work
|
||||
- ✅ Frontend has no TypeScript errors
|
||||
- ✅ Platform selection via environment variables works
|
||||
|
||||
---
|
||||
|
||||
## Communication
|
||||
|
||||
If you need clarification on requirements, have questions about architecture decisions, or find issues with the spec, document them clearly with:
|
||||
- What you expected
|
||||
- What you found
|
||||
- Your proposed solution
|
||||
|
||||
The PLAN.md document is comprehensive but you may find edge cases. Use your engineering judgment and document decisions.
|
||||
|
||||
---
|
||||
|
||||
## Final Notes
|
||||
|
||||
**This is not a simple copy-paste job.** You're doing careful integration work where you need to:
|
||||
- Understand the abstraction pattern (PLAN.md)
|
||||
- Preserve all of main's features
|
||||
- Adapt reference code to current patterns
|
||||
- Think about edge cases and testing
|
||||
|
||||
Take your time with Phase 2 (rooms.py integration) - that's where most bugs will come from if you accidentally break calendar/webhook features.
|
||||
|
||||
**Good luck! You've got comprehensive specs, working reference code, and a clean starting point. You can do this.**
|
||||
|
||||
---
|
||||
|
||||
## Quick Reference
|
||||
|
||||
```bash
|
||||
# Your workspace
|
||||
├── PLAN.md ← Complete technical spec (read first)
|
||||
├── IMPLEMENTATION_GUIDE.md ← Practical guide (bookmark this)
|
||||
├── CODER_BRIEFING.md ← This file
|
||||
└── reflector-dailyco-reference/ ← Reference implementation (inspiration only)
|
||||
|
||||
# Key commands
|
||||
cd server && uv run ruff check . # Lint backend
|
||||
cd www && pnpm lint # Lint frontend
|
||||
cd server && uv run alembic revision -m "..." # Create migration
|
||||
cd www && pnpm openapi # Regenerate types
|
||||
cd server && uv run pytest -v # Run tests
|
||||
```
|
||||
@@ -1,489 +0,0 @@
|
||||
# Daily.co Implementation Guide
|
||||
|
||||
## Overview
|
||||
Implement multi-provider video platform support (Whereby + Daily.co) following PLAN.md.
|
||||
|
||||
## Reference Code Location
|
||||
- **Reference branch:** `origin/igor/feat-dailyco` (on remote)
|
||||
- **Worktree location:** `./reflector-dailyco-reference/`
|
||||
- **Status:** Reference only - DO NOT merge or copy directly
|
||||
|
||||
## What Exists in Reference Branch (For Inspiration)
|
||||
|
||||
### ✅ Can Use As Reference (Well-Implemented)
|
||||
```
|
||||
server/reflector/video_platforms/
|
||||
├── base.py ← Platform abstraction (good design, copy-safe)
|
||||
├── models.py ← Data models (copy-safe)
|
||||
├── registry.py ← Registry pattern (copy-safe)
|
||||
├── factory.py ← Factory pattern (needs settings updates)
|
||||
├── whereby.py ← Whereby client (needs adaptation)
|
||||
├── daily.py ← Daily.co client (needs adaptation)
|
||||
└── mock.py ← Mock client (copy-safe for tests)
|
||||
|
||||
server/reflector/views/daily.py ← Webhook handler (needs adaptation)
|
||||
server/tests/test_video_platforms.py ← Tests (good reference)
|
||||
server/tests/test_daily_webhook.py ← Tests (good reference)
|
||||
|
||||
www/app/[roomName]/components/
|
||||
├── RoomContainer.tsx ← Platform router (needs React Query)
|
||||
├── DailyRoom.tsx ← Daily component (needs React Query)
|
||||
└── WherebyRoom.tsx ← Whereby extraction (needs React Query)
|
||||
```
|
||||
|
||||
### ⚠️ Needs Significant Changes (Use Logic Only)
|
||||
- `server/reflector/db/rooms.py` - Reference removed calendar/webhook fields that main has
|
||||
- `server/reflector/db/meetings.py` - Same issue (missing user_id handling differences)
|
||||
- `server/reflector/views/rooms.py` - Main has calendar integration, webhooks, ICS sync
|
||||
- `server/reflector/worker/process.py` - Main has different recording flow
|
||||
- Migration files - Must regenerate against current main schema
|
||||
|
||||
### ❌ Do NOT Use (Outdated/Incompatible)
|
||||
- `package.json`/`pnpm-lock.yaml` - Main uses different dependency versions
|
||||
- Frontend API client calls - Main uses React Query (reference uses old OpenAPI client)
|
||||
- Database migrations - Must create new ones from scratch
|
||||
- Any files that delete features present in main (search, calendar, webhooks)
|
||||
|
||||
## Key Differences: Reference vs Current Main
|
||||
|
||||
| Aspect | Reference Branch | Current Main | Action Required |
|
||||
|--------|------------------|--------------|-----------------|
|
||||
| **API client** | Old OpenAPI generated | React Query hooks | Rewrite all API calls |
|
||||
| **Database schema** | Simplified (removed features) | Has calendar, webhooks, full-text search | Merge carefully, preserve main features |
|
||||
| **Settings** | Aug 2025 structure | Current structure | Adapt carefully |
|
||||
| **Migrations** | Branched from Aug 1 | Current main (91+ commits ahead) | Regenerate from scratch |
|
||||
| **Frontend deps** | `@daily-co/daily-js@0.81.0` | Check current versions | Update to compatible versions |
|
||||
| **Package manager** | yarn | pnpm (maybe both?) | Use what main uses |
|
||||
|
||||
## Branch Divergence Analysis
|
||||
|
||||
**The reference branch is 91 commits behind main and severely diverged:**
|
||||
- Reference: 8 commits, 3,689 insertions, 425 deletions
|
||||
- Main since divergence: 320 files changed, 45,840 insertions, 16,827 deletions
|
||||
- **Main has 12x more changes**
|
||||
|
||||
**Major features in main that reference lacks:**
|
||||
1. Calendar integration (ICS sync with rooms)
|
||||
2. Self-hosted GPU API infrastructure
|
||||
3. Frontend OpenAPI React Query migration
|
||||
4. Full-text search (backend + frontend)
|
||||
5. Webhook system for room events
|
||||
6. Environment variable migration
|
||||
7. Security fixes and auth improvements
|
||||
8. Docker production frontend
|
||||
9. Meeting user ID removal (schema change)
|
||||
10. NextJS version upgrades
|
||||
|
||||
**High conflict risk files:**
|
||||
- `server/reflector/views/rooms.py` - 12x more changes in main
|
||||
- `server/reflector/db/rooms.py` - Main added 7+ fields
|
||||
- `www/package.json` - NextJS major version bump
|
||||
- Database migrations - 20+ new migrations in main
|
||||
|
||||
## Implementation Approach
|
||||
|
||||
### Phase 1: Copy Clean Abstractions (1-2 hours)
|
||||
|
||||
**Files to copy directly from reference:**
|
||||
```bash
|
||||
# Core abstraction (review but mostly safe to copy)
|
||||
cp -r reflector-dailyco-reference/server/reflector/video_platforms/ \
|
||||
server/reflector/
|
||||
|
||||
# BUT review each file for:
|
||||
# - Import paths (make sure they match current main)
|
||||
# - Settings references (adapt to current settings.py)
|
||||
# - Type imports (ensure no circular dependencies)
|
||||
```
|
||||
|
||||
**After copying, immediately:**
|
||||
```bash
|
||||
cd server
|
||||
# Check for issues
|
||||
uv run ruff check reflector/video_platforms/
|
||||
# Fix any import errors or type issues
|
||||
```
|
||||
|
||||
### Phase 2: Adapt to Current Main (2-3 hours)
|
||||
|
||||
**2.1 Settings Integration**
|
||||
|
||||
File: `server/reflector/settings.py`
|
||||
|
||||
Add at the appropriate location (near existing Whereby settings):
|
||||
|
||||
```python
|
||||
# Daily.co API Integration (NEW)
|
||||
DAILY_API_KEY: str | None = None
|
||||
DAILY_WEBHOOK_SECRET: str | None = None
|
||||
DAILY_SUBDOMAIN: str | None = None
|
||||
AWS_DAILY_S3_BUCKET: str | None = None
|
||||
AWS_DAILY_S3_REGION: str = "us-west-2"
|
||||
AWS_DAILY_ROLE_ARN: str | None = None
|
||||
|
||||
# Platform Migration Feature Flags (NEW)
|
||||
DAILY_MIGRATION_ENABLED: bool = False # Conservative default
|
||||
DAILY_MIGRATION_ROOM_IDS: list[str] = []
|
||||
DEFAULT_VIDEO_PLATFORM: Literal["whereby", "daily"] = "whereby"
|
||||
```
|
||||
|
||||
**2.2 Database Migration**
|
||||
|
||||
⚠️ **CRITICAL: Do NOT copy migration from reference**
|
||||
|
||||
Generate new migration:
|
||||
```bash
|
||||
cd server
|
||||
uv run alembic revision -m "add_platform_support"
|
||||
```
|
||||
|
||||
Edit the generated migration file to add `platform` column:
|
||||
```python
|
||||
def upgrade():
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.add_column(
|
||||
sa.Column("platform", sa.String(), nullable=False, server_default="whereby")
|
||||
)
|
||||
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.add_column(
|
||||
sa.Column("platform", sa.String(), nullable=False, server_default="whereby")
|
||||
)
|
||||
```
|
||||
|
||||
**2.3 Update Database Models**
|
||||
|
||||
File: `server/reflector/db/rooms.py`
|
||||
|
||||
Add platform field (preserve all existing fields from main):
|
||||
```python
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from reflector.video_platforms.models import Platform
|
||||
|
||||
class Room:
|
||||
# ... ALL existing fields from main (calendar, webhooks, etc.) ...
|
||||
|
||||
# NEW: Platform field
|
||||
platform: "Platform" = sqlalchemy.Column(
|
||||
sqlalchemy.String,
|
||||
nullable=False,
|
||||
server_default="whereby",
|
||||
)
|
||||
```
|
||||
|
||||
File: `server/reflector/db/meetings.py`
|
||||
|
||||
Same approach - add platform field, preserve everything from main.
|
||||
|
||||
**2.4 Integrate Platform Abstraction into rooms.py**
|
||||
|
||||
⚠️ **This is the most delicate part - main has calendar/webhook features**
|
||||
|
||||
File: `server/reflector/views/rooms.py`
|
||||
|
||||
Strategy:
|
||||
1. Add imports at top
|
||||
2. Modify meeting creation logic only
|
||||
3. Preserve all calendar/webhook/ICS logic from main
|
||||
|
||||
```python
|
||||
# Add imports
|
||||
from reflector.video_platforms import (
|
||||
create_platform_client,
|
||||
get_platform_for_room,
|
||||
)
|
||||
|
||||
# In create_meeting endpoint:
|
||||
# OLD: Direct Whereby API calls
|
||||
# NEW: Platform abstraction
|
||||
|
||||
# Find the meeting creation section and replace:
|
||||
platform = get_platform_for_room(room.id)
|
||||
client = create_platform_client(platform)
|
||||
|
||||
meeting_data = await client.create_meeting(
|
||||
room_name_prefix=room.name,
|
||||
end_date=meeting_data.end_date,
|
||||
room=room,
|
||||
)
|
||||
|
||||
# Then create Meeting record with meeting_data.platform, meeting_data.meeting_id, etc.
|
||||
```
|
||||
|
||||
**2.5 Add Daily.co Webhook Handler**
|
||||
|
||||
Copy from reference, minimal changes needed:
|
||||
```bash
|
||||
cp reflector-dailyco-reference/server/reflector/views/daily.py \
|
||||
server/reflector/views/
|
||||
```
|
||||
|
||||
Register in `server/reflector/app.py`:
|
||||
```python
|
||||
from reflector.views import daily
|
||||
|
||||
app.include_router(daily.router, prefix="/v1/daily", tags=["daily"])
|
||||
```
|
||||
|
||||
**2.6 Add Recording Processing Task**
|
||||
|
||||
File: `server/reflector/worker/process.py`
|
||||
|
||||
Add the `process_recording_from_url` task from reference (copy the function).
|
||||
|
||||
### Phase 3: Frontend Adaptation (3-4 hours)
|
||||
|
||||
**3.1 Determine Current API Client Pattern**
|
||||
|
||||
First, check how main currently makes API calls:
|
||||
```bash
|
||||
cd www
|
||||
grep -r "api\." app/ | head -20
|
||||
# Look for patterns like: api.v1Something()
|
||||
```
|
||||
|
||||
**3.2 Create Components**
|
||||
|
||||
Copy component structure from reference but **rewrite all API calls**:
|
||||
|
||||
```bash
|
||||
mkdir -p www/app/[roomName]/components
|
||||
```
|
||||
|
||||
Files to create:
|
||||
- `RoomContainer.tsx` - Platform router (mostly copy-safe, just fix imports)
|
||||
- `DailyRoom.tsx` - Needs React Query API calls
|
||||
- `WherebyRoom.tsx` - Extract current room page logic
|
||||
|
||||
**Example React Query pattern** (adapt to your actual API):
|
||||
```typescript
|
||||
import { api } from '@/app/api/client'
|
||||
|
||||
// In DailyRoom.tsx
|
||||
const handleConsent = async () => {
|
||||
try {
|
||||
await api.v1MeetingAudioConsent({
|
||||
path: { meeting_id: meeting.id },
|
||||
body: { consent: true },
|
||||
})
|
||||
// ...
|
||||
} catch (error) {
|
||||
// ...
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**3.3 Add Daily.co Dependency**
|
||||
|
||||
Check current package manager:
|
||||
```bash
|
||||
cd www
|
||||
ls package-lock.json yarn.lock pnpm-lock.yaml
|
||||
```
|
||||
|
||||
Then install:
|
||||
```bash
|
||||
# If using pnpm
|
||||
pnpm add @daily-co/daily-js@^0.81.0
|
||||
|
||||
# If using yarn
|
||||
yarn add @daily-co/daily-js@^0.81.0
|
||||
```
|
||||
|
||||
**3.4 Update TypeScript Types**
|
||||
|
||||
After backend changes, regenerate types:
|
||||
```bash
|
||||
cd www
|
||||
pnpm openapi # or yarn openapi
|
||||
```
|
||||
|
||||
This should pick up the new `platform` field on Meeting type.
|
||||
|
||||
### Phase 4: Testing (2-3 hours)
|
||||
|
||||
**4.1 Copy Test Structure**
|
||||
|
||||
```bash
|
||||
cp reflector-dailyco-reference/server/tests/test_video_platforms.py \
|
||||
server/tests/
|
||||
|
||||
cp reflector-dailyco-reference/server/tests/test_daily_webhook.py \
|
||||
server/tests/
|
||||
```
|
||||
|
||||
**4.2 Fix Test Imports and Fixtures**
|
||||
|
||||
Update imports to match current test infrastructure:
|
||||
- Check `server/tests/conftest.py` for fixture patterns
|
||||
- Update database access patterns if changed
|
||||
- Fix any import errors
|
||||
|
||||
**4.3 Run Tests**
|
||||
|
||||
```bash
|
||||
cd server
|
||||
# Run with environment variables for Mac
|
||||
REDIS_HOST=localhost \
|
||||
CELERY_BROKER_URL=redis://localhost:6379/1 \
|
||||
CELERY_RESULT_BACKEND=redis://localhost:6379/1 \
|
||||
uv run pytest tests/test_video_platforms.py -v
|
||||
```
|
||||
|
||||
### Phase 5: Environment Configuration
|
||||
|
||||
**Update `server/env.example`:**
|
||||
|
||||
Add at the end:
|
||||
```bash
|
||||
# Daily.co API Integration
|
||||
DAILY_API_KEY=your-daily-api-key
|
||||
DAILY_WEBHOOK_SECRET=your-daily-webhook-secret
|
||||
DAILY_SUBDOMAIN=your-subdomain
|
||||
AWS_DAILY_S3_BUCKET=your-daily-bucket
|
||||
AWS_DAILY_S3_REGION=us-west-2
|
||||
AWS_DAILY_ROLE_ARN=arn:aws:iam::ACCOUNT:role/DailyRecording
|
||||
|
||||
# Platform Selection
|
||||
DAILY_MIGRATION_ENABLED=false # Master switch
|
||||
DAILY_MIGRATION_ROOM_IDS=[] # Specific room IDs
|
||||
DEFAULT_VIDEO_PLATFORM=whereby # Default platform
|
||||
```
|
||||
|
||||
## Decision Tree: Copy vs Adapt vs Rewrite
|
||||
|
||||
```
|
||||
┌─ Is it pure abstraction logic? (base.py, registry.py, models.py)
|
||||
│ YES → Copy directly, review imports
|
||||
│ NO → Continue ↓
|
||||
│
|
||||
├─ Does it touch database models?
|
||||
│ YES → Adapt carefully, preserve main's fields
|
||||
│ NO → Continue ↓
|
||||
│
|
||||
├─ Does it make API calls on frontend?
|
||||
│ YES → Rewrite using React Query
|
||||
│ NO → Continue ↓
|
||||
│
|
||||
├─ Is it a database migration?
|
||||
│ YES → Generate fresh from current schema
|
||||
│ NO → Continue ↓
|
||||
│
|
||||
└─ Does it touch rooms.py or core business logic?
|
||||
YES → Merge carefully, preserve calendar/webhooks
|
||||
NO → Safe to adapt from reference
|
||||
```
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
After each phase, verify:
|
||||
|
||||
**Phase 1 (Abstraction Layer):**
|
||||
- [ ] `uv run ruff check server/reflector/video_platforms/` passes
|
||||
- [ ] No circular import errors
|
||||
- [ ] Can import `from reflector.video_platforms import create_platform_client`
|
||||
|
||||
**Phase 2 (Backend Integration):**
|
||||
- [ ] `uv run ruff check server/` passes
|
||||
- [ ] Migration file generated (not copied)
|
||||
- [ ] Room and Meeting models have platform field
|
||||
- [ ] rooms.py still has calendar/webhook features
|
||||
|
||||
**Phase 3 (Frontend):**
|
||||
- [ ] `pnpm lint` passes
|
||||
- [ ] No TypeScript errors
|
||||
- [ ] No `@ts-ignore` for platform field
|
||||
- [ ] API calls use React Query patterns
|
||||
|
||||
**Phase 4 (Testing):**
|
||||
- [ ] Tests can be collected: `pytest tests/test_video_platforms.py --collect-only`
|
||||
- [ ] Database fixtures work
|
||||
- [ ] Mock platform works
|
||||
|
||||
**Phase 5 (Config):**
|
||||
- [ ] env.example has Daily.co variables
|
||||
- [ ] settings.py has all new variables
|
||||
- [ ] No duplicate variable definitions
|
||||
|
||||
## Common Pitfalls
|
||||
|
||||
### 1. Database Schema Conflicts
|
||||
**Problem:** Reference removed fields that main has (calendar, webhooks)
|
||||
**Solution:** Always preserve main's fields, only add platform field
|
||||
|
||||
### 2. Migration Conflicts
|
||||
**Problem:** Reference migration has wrong `down_revision`
|
||||
**Solution:** Always generate fresh migration from current main
|
||||
|
||||
### 3. Frontend API Calls
|
||||
**Problem:** Reference uses old API client patterns
|
||||
**Solution:** Check current main's API usage, replicate that pattern
|
||||
|
||||
### 4. Import Errors
|
||||
**Problem:** Circular imports with TYPE_CHECKING
|
||||
**Solution:** Use `if TYPE_CHECKING:` for Room/Meeting imports in video_platforms
|
||||
|
||||
### 5. Test Database Issues
|
||||
**Problem:** Tests fail with "could not translate host name 'postgres'"
|
||||
**Solution:** Use environment variables: `REDIS_HOST=localhost DATABASE_URL=...`
|
||||
|
||||
### 6. Preserved Features Broken
|
||||
**Problem:** Calendar/webhook features stop working
|
||||
**Solution:** Carefully review rooms.py diff, only change meeting creation, not calendar logic
|
||||
|
||||
## File Modification Summary
|
||||
|
||||
**New files (can copy):**
|
||||
- `server/reflector/video_platforms/*.py` (entire directory)
|
||||
- `server/reflector/views/daily.py`
|
||||
- `server/tests/test_video_platforms.py`
|
||||
- `server/tests/test_daily_webhook.py`
|
||||
- `www/app/[roomName]/components/RoomContainer.tsx`
|
||||
- `www/app/[roomName]/components/DailyRoom.tsx`
|
||||
- `www/app/[roomName]/components/WherebyRoom.tsx`
|
||||
|
||||
**Modified files (careful merging):**
|
||||
- `server/reflector/settings.py` - Add Daily.co settings
|
||||
- `server/reflector/db/rooms.py` - Add platform field
|
||||
- `server/reflector/db/meetings.py` - Add platform field
|
||||
- `server/reflector/views/rooms.py` - Integrate platform abstraction
|
||||
- `server/reflector/worker/process.py` - Add process_recording_from_url
|
||||
- `server/reflector/app.py` - Register daily router
|
||||
- `server/env.example` - Add Daily.co variables
|
||||
- `www/app/[roomName]/page.tsx` - Use RoomContainer
|
||||
- `www/package.json` - Add @daily-co/daily-js
|
||||
|
||||
**Generated files (do not copy):**
|
||||
- `server/migrations/versions/XXXXXX_add_platform_support.py` - Generate fresh
|
||||
|
||||
## Success Metrics
|
||||
|
||||
Implementation is complete when:
|
||||
- [ ] All tests pass (including new platform tests)
|
||||
- [ ] Linting passes (ruff, pnpm lint)
|
||||
- [ ] Migration applies cleanly: `uv run alembic upgrade head`
|
||||
- [ ] Can create Whereby meeting (existing flow unchanged)
|
||||
- [ ] Can create Daily.co meeting (with env vars set)
|
||||
- [ ] Frontend loads without TypeScript errors
|
||||
- [ ] No features from main were accidentally removed
|
||||
|
||||
## Getting Help
|
||||
|
||||
**Reference documentation locations:**
|
||||
- Implementation plan: `PLAN.md`
|
||||
- Reference implementation: `./reflector-dailyco-reference/`
|
||||
- Current main codebase: `./ ` (current directory)
|
||||
|
||||
**Compare implementations:**
|
||||
```bash
|
||||
# Compare specific files
|
||||
diff reflector-dailyco-reference/server/reflector/video_platforms/base.py \
|
||||
server/reflector/video_platforms/base.py
|
||||
|
||||
# See what changed in rooms.py between reference branch point and now
|
||||
git log --oneline --since="2025-08-01" -- server/reflector/views/rooms.py
|
||||
```
|
||||
|
||||
**Key insight:** The reference branch validates the approach and provides working code patterns, but you're implementing fresh against current main to avoid merge conflicts and preserve all new features.
|
||||
25
README.md
25
README.md
@@ -168,13 +168,6 @@ You can manually process an audio file by calling the process tool:
|
||||
uv run python -m reflector.tools.process path/to/audio.wav
|
||||
```
|
||||
|
||||
## Build-time env variables
|
||||
|
||||
Next.js projects are more used to NEXT_PUBLIC_ prefixed buildtime vars. We don't have those for the reason we need to serve a ccustomizable prebuild docker container.
|
||||
|
||||
Instead, all the variables are runtime. Variables needed to the frontend are served to the frontend app at initial render.
|
||||
|
||||
It also means there's no static prebuild and no static files to serve for js/html.
|
||||
|
||||
## Feature Flags
|
||||
|
||||
@@ -184,24 +177,24 @@ Reflector uses environment variable-based feature flags to control application f
|
||||
|
||||
| Feature Flag | Environment Variable |
|
||||
|-------------|---------------------|
|
||||
| `requireLogin` | `FEATURE_REQUIRE_LOGIN` |
|
||||
| `privacy` | `FEATURE_PRIVACY` |
|
||||
| `browse` | `FEATURE_BROWSE` |
|
||||
| `sendToZulip` | `FEATURE_SEND_TO_ZULIP` |
|
||||
| `rooms` | `FEATURE_ROOMS` |
|
||||
| `requireLogin` | `NEXT_PUBLIC_FEATURE_REQUIRE_LOGIN` |
|
||||
| `privacy` | `NEXT_PUBLIC_FEATURE_PRIVACY` |
|
||||
| `browse` | `NEXT_PUBLIC_FEATURE_BROWSE` |
|
||||
| `sendToZulip` | `NEXT_PUBLIC_FEATURE_SEND_TO_ZULIP` |
|
||||
| `rooms` | `NEXT_PUBLIC_FEATURE_ROOMS` |
|
||||
|
||||
### Setting Feature Flags
|
||||
|
||||
Feature flags are controlled via environment variables using the pattern `FEATURE_{FEATURE_NAME}` where `{FEATURE_NAME}` is the SCREAMING_SNAKE_CASE version of the feature name.
|
||||
Feature flags are controlled via environment variables using the pattern `NEXT_PUBLIC_FEATURE_{FEATURE_NAME}` where `{FEATURE_NAME}` is the SCREAMING_SNAKE_CASE version of the feature name.
|
||||
|
||||
**Examples:**
|
||||
```bash
|
||||
# Enable user authentication requirement
|
||||
FEATURE_REQUIRE_LOGIN=true
|
||||
NEXT_PUBLIC_FEATURE_REQUIRE_LOGIN=true
|
||||
|
||||
# Disable browse functionality
|
||||
FEATURE_BROWSE=false
|
||||
NEXT_PUBLIC_FEATURE_BROWSE=false
|
||||
|
||||
# Enable Zulip integration
|
||||
FEATURE_SEND_TO_ZULIP=true
|
||||
NEXT_PUBLIC_FEATURE_SEND_TO_ZULIP=true
|
||||
```
|
||||
|
||||
@@ -39,7 +39,7 @@ services:
|
||||
ports:
|
||||
- 6379:6379
|
||||
web:
|
||||
image: node:22-alpine
|
||||
image: node:18
|
||||
ports:
|
||||
- "3000:3000"
|
||||
command: sh -c "corepack enable && pnpm install && pnpm dev"
|
||||
@@ -50,8 +50,6 @@ services:
|
||||
- /app/node_modules
|
||||
env_file:
|
||||
- ./www/.env.local
|
||||
environment:
|
||||
- NODE_ENV=development
|
||||
|
||||
postgres:
|
||||
image: postgres:17
|
||||
@@ -1,39 +0,0 @@
|
||||
# Production Docker Compose configuration for Frontend
|
||||
# Usage: docker compose -f docker-compose.prod.yml up -d
|
||||
|
||||
services:
|
||||
web:
|
||||
build:
|
||||
context: ./www
|
||||
dockerfile: Dockerfile
|
||||
image: reflector-frontend:latest
|
||||
environment:
|
||||
- KV_URL=${KV_URL:-redis://redis:6379}
|
||||
- SITE_URL=${SITE_URL}
|
||||
- API_URL=${API_URL}
|
||||
- WEBSOCKET_URL=${WEBSOCKET_URL}
|
||||
- NEXTAUTH_URL=${NEXTAUTH_URL:-http://localhost:3000}
|
||||
- NEXTAUTH_SECRET=${NEXTAUTH_SECRET:-changeme-in-production}
|
||||
- AUTHENTIK_ISSUER=${AUTHENTIK_ISSUER}
|
||||
- AUTHENTIK_CLIENT_ID=${AUTHENTIK_CLIENT_ID}
|
||||
- AUTHENTIK_CLIENT_SECRET=${AUTHENTIK_CLIENT_SECRET}
|
||||
- AUTHENTIK_REFRESH_TOKEN_URL=${AUTHENTIK_REFRESH_TOKEN_URL}
|
||||
- SENTRY_DSN=${SENTRY_DSN}
|
||||
- SENTRY_IGNORE_API_RESOLUTION_ERROR=${SENTRY_IGNORE_API_RESOLUTION_ERROR:-1}
|
||||
depends_on:
|
||||
- redis
|
||||
restart: unless-stopped
|
||||
|
||||
redis:
|
||||
image: redis:7.2-alpine
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "redis-cli", "ping"]
|
||||
interval: 30s
|
||||
timeout: 3s
|
||||
retries: 3
|
||||
volumes:
|
||||
- redis_data:/data
|
||||
|
||||
volumes:
|
||||
redis_data:
|
||||
369
docs/jitsi.md
Normal file
369
docs/jitsi.md
Normal file
@@ -0,0 +1,369 @@
|
||||
# Jitsi Integration for Reflector
|
||||
|
||||
This document contains research and planning notes for integrating Jitsi Meet as a replacement for Whereby in Reflector.
|
||||
|
||||
## Overview
|
||||
|
||||
Jitsi Meet is an open-source video conferencing solution that can replace Whereby in Reflector, providing:
|
||||
- Cost reduction (no per-minute charges)
|
||||
- Direct recording access via Jibri
|
||||
- Real-time event webhooks
|
||||
- Full customization and control
|
||||
|
||||
## Current Whereby Integration Analysis
|
||||
|
||||
### Architecture
|
||||
1. **Room Creation**: User creates a "room" template in Reflector DB with settings
|
||||
2. **Meeting Creation**: `/rooms/{room_name}/meeting` endpoint calls Whereby API to create meeting
|
||||
3. **Recording**: Whereby handles recording automatically to S3 bucket
|
||||
4. **Webhooks**: Whereby sends events for participant tracking
|
||||
|
||||
### Database Structure
|
||||
```python
|
||||
# Room = Template/Configuration
|
||||
class Room:
|
||||
id, name, user_id
|
||||
recording_type, recording_trigger # cloud, automatic-2nd-participant
|
||||
webhook_url, webhook_secret
|
||||
|
||||
# Meeting = Actual Whereby Meeting Instance
|
||||
class Meeting:
|
||||
id # Whereby meetingId
|
||||
room_name # Generated by Whereby
|
||||
room_url, host_room_url # Whereby URLs
|
||||
num_clients # Updated via webhooks
|
||||
```
|
||||
|
||||
## Jitsi Components
|
||||
|
||||
### Core Architecture
|
||||
- **Jitsi Meet**: Web frontend (Next.js + React)
|
||||
- **Prosody**: XMPP server for messaging/rooms
|
||||
- **Jicofo**: Conference focus (orchestration)
|
||||
- **JVB**: Videobridge (media routing)
|
||||
- **Jibri**: Recording service
|
||||
- **Jigasi**: SIP gateway (optional, for phone dial-in)
|
||||
|
||||
### Exposure Requirements
|
||||
- **Web service**: 443/80 (frontend)
|
||||
- **JVB**: 10000/UDP (media streams) - **MUST EXPOSE**
|
||||
- **Prosody**: 5280 (BOSH/WebSocket) - can proxy via web
|
||||
- **Jicofo, Jibri, Jigasi**: Internal only
|
||||
|
||||
## Recording with Jibri
|
||||
|
||||
### How Jibri Works
|
||||
- Each Jibri instance handles **one recording at a time**
|
||||
- Records mixed audio/video to MP4 format
|
||||
- Uses Chrome headless + ffmpeg for capture
|
||||
- Supports finalize scripts for post-processing
|
||||
|
||||
### Jibri Pool for Scaling
|
||||
- Multiple Jibri instances join "jibribrewery" MUC
|
||||
- Jicofo distributes recording requests to available instances
|
||||
- Automatic load balancing and failover
|
||||
|
||||
```yaml
|
||||
# Multiple Jibri instances
|
||||
jibri1:
|
||||
environment:
|
||||
- JIBRI_INSTANCE_ID=jibri1
|
||||
- JIBRI_BREWERY_MUC=jibribrewery
|
||||
|
||||
jibri2:
|
||||
environment:
|
||||
- JIBRI_INSTANCE_ID=jibri2
|
||||
- JIBRI_BREWERY_MUC=jibribrewery
|
||||
```
|
||||
|
||||
### Recording Automation Options
|
||||
1. **Environment Variables**: `ENABLE_RECORDING=1`, `AUTO_RECORDING=1`
|
||||
2. **URL Parameters**: `?config.autoRecord=true`
|
||||
3. **JWT Token**: Include recording permissions in JWT
|
||||
4. **API Control**: `api.executeCommand('startRecording')`
|
||||
|
||||
### Post-Processing Integration
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# finalize.sh - runs after recording completion
|
||||
RECORDING_FILE=$1
|
||||
MEETING_METADATA=$2
|
||||
ROOM_NAME=$3
|
||||
|
||||
# Copy to Reflector-accessible location
|
||||
cp "$RECORDING_FILE" /shared/reflector-uploads/
|
||||
|
||||
# Trigger Reflector processing
|
||||
curl -X POST "http://reflector-api:8000/v1/transcripts/process" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{
|
||||
\"file_path\": \"/shared/reflector-uploads/$(basename $RECORDING_FILE)\",
|
||||
\"room_name\": \"$ROOM_NAME\",
|
||||
\"source\": \"jitsi\"
|
||||
}"
|
||||
```
|
||||
|
||||
## React Integration
|
||||
|
||||
### Official React SDK
|
||||
```bash
|
||||
npm i @jitsi/react-sdk
|
||||
```
|
||||
|
||||
```jsx
|
||||
import { JitsiMeeting } from '@jitsi/react-sdk'
|
||||
|
||||
<JitsiMeeting
|
||||
room="meeting-room"
|
||||
serverURL="https://your-jitsi.domain"
|
||||
jwt="your-jwt-token"
|
||||
config={{
|
||||
startWithAudioMuted: true,
|
||||
fileRecordingsEnabled: true,
|
||||
autoRecord: true
|
||||
}}
|
||||
onParticipantJoined={(participant) => {
|
||||
// Track participant events
|
||||
}}
|
||||
onRecordingStatusChanged={(status) => {
|
||||
// Handle recording events
|
||||
}}
|
||||
/>
|
||||
```
|
||||
|
||||
## Authentication & Room Control
|
||||
|
||||
### JWT-Based Access Control
|
||||
```python
|
||||
def generate_jitsi_jwt(payload):
|
||||
return jwt.encode({
|
||||
"aud": "jitsi",
|
||||
"iss": "reflector",
|
||||
"sub": "reflector-user",
|
||||
"room": payload["room"],
|
||||
"exp": int(payload["exp"].timestamp()),
|
||||
"context": {
|
||||
"user": {
|
||||
"name": payload["user_name"],
|
||||
"moderator": payload.get("moderator", False)
|
||||
},
|
||||
"features": {
|
||||
"recording": payload.get("recording", True)
|
||||
}
|
||||
}
|
||||
}, JITSI_JWT_SECRET)
|
||||
```
|
||||
|
||||
### Prevent Anonymous Room Creation
|
||||
```bash
|
||||
# Environment configuration
|
||||
ENABLE_AUTH=1
|
||||
ENABLE_GUESTS=0
|
||||
AUTH_TYPE=jwt
|
||||
JWT_APP_ID=reflector
|
||||
JWT_APP_SECRET=your-secret-key
|
||||
```
|
||||
|
||||
## Webhook Integration
|
||||
|
||||
### Real-time Events via Prosody
|
||||
Custom event-sync module can send webhooks for:
|
||||
- Participant join/leave
|
||||
- Recording start/stop
|
||||
- Room creation/destruction
|
||||
- Mute/unmute events
|
||||
|
||||
```lua
|
||||
-- mod_event_sync.lua
|
||||
module:hook("muc-occupant-joined", function(event)
|
||||
send_event({
|
||||
type = "participant_joined",
|
||||
room = event.room.jid,
|
||||
participant = {
|
||||
nick = event.occupant.nick,
|
||||
jid = event.occupant.jid,
|
||||
},
|
||||
timestamp = os.time(),
|
||||
});
|
||||
end);
|
||||
```
|
||||
|
||||
### Jibri Recording Webhooks
|
||||
```bash
|
||||
# Environment variable
|
||||
JIBRI_WEBHOOK_SUBSCRIBERS=https://your-reflector.com/webhooks/jibri
|
||||
```
|
||||
|
||||
## Proposed Reflector Integration
|
||||
|
||||
### Modified Database Schema
|
||||
```python
|
||||
class Meeting(BaseModel):
|
||||
id: str # Our generated meeting ID
|
||||
room_name: str # Generated: reflector-{room.name}-{timestamp}
|
||||
room_url: str # https://jitsi.domain/room_name?jwt=token
|
||||
host_room_url: str # Same but with moderator JWT
|
||||
# Add Jitsi-specific fields
|
||||
jitsi_jwt: str # JWT token
|
||||
jitsi_room_id: str # Internal room identifier
|
||||
recording_status: str # pending, recording, completed
|
||||
recording_file_path: Optional[str]
|
||||
```
|
||||
|
||||
### API Replacement
|
||||
```python
|
||||
# Replace whereby.py with jitsi.py
|
||||
async def create_meeting(room_name_prefix: str, end_date: datetime, room: Room):
|
||||
# Generate unique room name
|
||||
jitsi_room = f"reflector-{room.name}-{int(time.time())}"
|
||||
|
||||
# Generate JWT tokens
|
||||
user_jwt = generate_jwt(room=jitsi_room, moderator=False, exp=end_date)
|
||||
host_jwt = generate_jwt(room=jitsi_room, moderator=True, exp=end_date)
|
||||
|
||||
return {
|
||||
"meetingId": generate_uuid4(), # Our ID
|
||||
"roomName": jitsi_room,
|
||||
"roomUrl": f"https://jitsi.domain/{jitsi_room}?jwt={user_jwt}",
|
||||
"hostRoomUrl": f"https://jitsi.domain/{jitsi_room}?jwt={host_jwt}",
|
||||
"startDate": datetime.now().isoformat(),
|
||||
"endDate": end_date.isoformat(),
|
||||
}
|
||||
```
|
||||
|
||||
### Webhook Endpoints
|
||||
```python
|
||||
# Replace whereby webhook with jitsi webhooks
|
||||
@router.post("/jitsi/events")
|
||||
async def jitsi_events_webhook(event_data: dict):
|
||||
event_type = event_data.get("event")
|
||||
room_name = event_data.get("room", "").split("@")[0]
|
||||
|
||||
meeting = await Meeting.get_by_room(room_name)
|
||||
|
||||
if event_type == "muc-occupant-joined":
|
||||
# Update participant count
|
||||
meeting.num_clients += 1
|
||||
|
||||
elif event_type == "jibri-recording-on":
|
||||
meeting.recording_status = "recording"
|
||||
|
||||
elif event_type == "jibri-recording-off":
|
||||
meeting.recording_status = "processing"
|
||||
await process_meeting_recording.delay(meeting.id)
|
||||
|
||||
@router.post("/jibri/recording-complete")
|
||||
async def recording_complete(data: dict):
|
||||
# Handle finalize script webhook
|
||||
room_name = data.get("room_name")
|
||||
file_path = data.get("file_path")
|
||||
|
||||
meeting = await Meeting.get_by_room(room_name)
|
||||
meeting.recording_file_path = file_path
|
||||
meeting.recording_status = "completed"
|
||||
|
||||
# Start Reflector processing
|
||||
await process_recording_for_transcription(meeting.id, file_path)
|
||||
```
|
||||
|
||||
## Deployment with Docker
|
||||
|
||||
### Official docker-jitsi-meet
|
||||
```bash
|
||||
# Download official release
|
||||
wget $(wget -q -O - https://api.github.com/repos/jitsi/docker-jitsi-meet/releases/latest | grep zip | cut -d\" -f4)
|
||||
|
||||
# Setup
|
||||
mkdir -p ~/.jitsi-meet-cfg/{web,transcripts,prosody/config,prosody/prosody-plugins-custom,jicofo,jvb,jigasi,jibri}
|
||||
./gen-passwords.sh # Generate secure passwords
|
||||
docker compose up -d
|
||||
```
|
||||
|
||||
### Coolify Integration
|
||||
```yaml
|
||||
services:
|
||||
web:
|
||||
ports: ["80:80", "443:443"]
|
||||
jvb:
|
||||
ports: ["10000:10000/udp"] # Must expose for media
|
||||
jibri1:
|
||||
environment:
|
||||
- JIBRI_INSTANCE_ID=jibri1
|
||||
- JIBRI_FINALIZE_RECORDING_SCRIPT_PATH=/config/finalize.sh
|
||||
jibri2:
|
||||
environment:
|
||||
- JIBRI_INSTANCE_ID=jibri2
|
||||
```
|
||||
|
||||
## Benefits vs Whereby
|
||||
|
||||
### Cost & Control
|
||||
✅ **No per-minute charges** - significant cost savings
|
||||
✅ **Full recording control** - direct file access
|
||||
✅ **Custom branding** - complete UI control
|
||||
✅ **Self-hosted** - no vendor lock-in
|
||||
|
||||
### Technical Advantages
|
||||
✅ **Real-time events** - immediate webhook notifications
|
||||
✅ **Rich participant metadata** - detailed tracking
|
||||
✅ **JWT security** - token-based access with expiration
|
||||
✅ **Multiple recording formats** - audio-only options
|
||||
✅ **Scalable architecture** - horizontal Jibri scaling
|
||||
|
||||
### Integration Benefits
|
||||
✅ **Same API surface** - minimal changes to existing code
|
||||
✅ **React SDK** - better frontend integration
|
||||
✅ **Direct processing** - no S3 download delays
|
||||
✅ **Event-driven architecture** - better real-time capabilities
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
1. **Deploy Jitsi Stack** - Set up docker-jitsi-meet with multiple Jibri instances
|
||||
2. **Create jitsi.py** - Replace whereby.py with Jitsi API functions
|
||||
3. **Update Database** - Add Jitsi-specific fields to Meeting model
|
||||
4. **Webhook Integration** - Replace Whereby webhooks with Jitsi events
|
||||
5. **Frontend Updates** - Replace Whereby embed with Jitsi React SDK
|
||||
6. **Testing & Migration** - Gradual rollout with fallback to Whereby
|
||||
|
||||
## Recording Limitations & Considerations
|
||||
|
||||
### Current Limitations
|
||||
- **Mixed audio only** - Jibri doesn't separate participant tracks natively
|
||||
- **One recording per Jibri** - requires multiple instances for concurrent recordings
|
||||
- **Chrome dependency** - Jibri uses headless Chrome for recording
|
||||
|
||||
### Metadata Capabilities
|
||||
✅ **Participant join/leave timestamps** - via webhooks
|
||||
✅ **Speaking time tracking** - via audio level events
|
||||
✅ **Meeting duration** - precise timing
|
||||
✅ **Room-specific data** - custom metadata in JWT
|
||||
|
||||
### Alternative Recording Methods
|
||||
- **Local recording** - browser-based, per-participant
|
||||
- **Custom recording** - lib-jitsi-meet for individual streams
|
||||
- **Third-party solutions** - Recall.ai, Otter.ai integrations
|
||||
|
||||
## Security Considerations
|
||||
|
||||
### JWT Configuration
|
||||
- **Room-specific tokens** - limit access to specific rooms
|
||||
- **Time-based expiration** - automatic cleanup
|
||||
- **Feature permissions** - control recording, moderation rights
|
||||
- **User identification** - embed user metadata in tokens
|
||||
|
||||
### Access Control
|
||||
- **No anonymous rooms** - all rooms require valid JWT
|
||||
- **API-only creation** - prevent direct room access
|
||||
- **Webhook verification** - HMAC signature validation
|
||||
|
||||
## Next Steps
|
||||
|
||||
1. **Deploy test Jitsi instance** - validate recording pipeline
|
||||
2. **Prototype jitsi.py** - create equivalent API functions
|
||||
3. **Test webhook integration** - ensure event delivery works
|
||||
4. **Performance testing** - validate multiple concurrent recordings
|
||||
5. **Migration strategy** - plan gradual transition from Whereby
|
||||
|
||||
---
|
||||
|
||||
*This document serves as the comprehensive planning and research notes for Jitsi integration in Reflector. It should be updated as implementation progresses and new insights are discovered.*
|
||||
720
docs/video-jitsi.md
Normal file
720
docs/video-jitsi.md
Normal file
@@ -0,0 +1,720 @@
|
||||
# Jitsi Meet Integration Configuration Guide
|
||||
|
||||
This guide explains how to configure Reflector to use your self-hosted Jitsi Meet installation for video meetings, recording, and participant tracking.
|
||||
|
||||
## Overview
|
||||
|
||||
Jitsi Meet is an open-source video conferencing platform that can be self-hosted. Reflector integrates with Jitsi Meet to:
|
||||
|
||||
- Create secure meeting rooms with JWT authentication
|
||||
- Track participant join/leave events via Prosody webhooks
|
||||
- Record meetings using Jibri recording service
|
||||
- Process recordings for transcription and analysis
|
||||
|
||||
## Requirements
|
||||
|
||||
### Self-Hosted Jitsi Meet
|
||||
|
||||
You need a complete Jitsi Meet installation including:
|
||||
|
||||
1. **Jitsi Meet Web Interface** - The main meeting interface
|
||||
2. **Prosody XMPP Server** - Handles room management and authentication
|
||||
3. **Jicofo (JItsi COnference FOcus)** - Manages media sessions
|
||||
4. **Jitsi Videobridge (JVB)** - Handles WebRTC media routing
|
||||
5. **Jibri Recording Service** - Records meetings (optional but recommended)
|
||||
|
||||
### System Requirements
|
||||
|
||||
- **Domain with SSL Certificate** - Required for WebRTC functionality
|
||||
- **Prosody mod_event_sync** - For webhook event handling
|
||||
- **JWT Authentication** - For secure room access control
|
||||
- **Storage Solution** - For recording files (local or cloud)
|
||||
|
||||
## Configuration Variables
|
||||
|
||||
Add the following environment variables to your Reflector `.env` file:
|
||||
|
||||
### Required Variables
|
||||
|
||||
```bash
|
||||
# Jitsi Meet Domain (without https://)
|
||||
JITSI_DOMAIN=meet.example.com
|
||||
|
||||
# JWT Secret for room authentication (generate with: openssl rand -hex 32)
|
||||
JITSI_JWT_SECRET=your-64-character-hex-secret-here
|
||||
|
||||
# Webhook secret for event handling (generate with: openssl rand -hex 16)
|
||||
JITSI_WEBHOOK_SECRET=your-32-character-hex-secret-here
|
||||
```
|
||||
|
||||
### Optional Variables
|
||||
|
||||
```bash
|
||||
# Application identifier (should match Jitsi configuration)
|
||||
JITSI_APP_ID=reflector
|
||||
|
||||
# JWT issuer and audience (should match Jitsi configuration)
|
||||
JITSI_JWT_ISSUER=reflector
|
||||
JITSI_JWT_AUDIENCE=jitsi
|
||||
```
|
||||
|
||||
## Installation Steps
|
||||
|
||||
### 1. Jitsi Meet Server Installation
|
||||
|
||||
#### Quick Installation (Ubuntu/Debian)
|
||||
|
||||
```bash
|
||||
# Add Jitsi repository
|
||||
curl -fsSL https://download.jitsi.org/jitsi-key.gpg.key | sudo gpg --dearmor -o /usr/share/keyrings/jitsi-keyring.gpg
|
||||
echo "deb [signed-by=/usr/share/keyrings/jitsi-keyring.gpg] https://download.jitsi.org stable/" | sudo tee /etc/apt/sources.list.d/jitsi-stable.list
|
||||
|
||||
# Install Jitsi Meet
|
||||
sudo apt update
|
||||
sudo apt install jitsi-meet
|
||||
|
||||
# Configure SSL certificate
|
||||
sudo /usr/share/jitsi-meet/scripts/install-letsencrypt-cert.sh
|
||||
```
|
||||
|
||||
#### Docker Installation
|
||||
|
||||
```bash
|
||||
# Clone Jitsi Docker repository
|
||||
git clone https://github.com/jitsi/docker-jitsi-meet
|
||||
cd docker-jitsi-meet
|
||||
|
||||
# Copy environment template
|
||||
cp env.example .env
|
||||
|
||||
# Edit configuration
|
||||
nano .env
|
||||
|
||||
# Start services
|
||||
docker-compose up -d
|
||||
```
|
||||
|
||||
### 2. JWT Authentication Setup
|
||||
|
||||
#### Update Prosody Configuration
|
||||
|
||||
Edit `/etc/prosody/conf.d/your-domain.cfg.lua`:
|
||||
|
||||
```lua
|
||||
VirtualHost "meet.example.com"
|
||||
authentication = "token"
|
||||
app_id = "reflector"
|
||||
app_secret = "your-jwt-secret-here"
|
||||
|
||||
-- Allow anonymous access for guests
|
||||
c2s_require_encryption = false
|
||||
admins = { "focusUser@auth.meet.example.com" }
|
||||
|
||||
modules_enabled = {
|
||||
"bosh";
|
||||
"pubsub";
|
||||
"ping";
|
||||
"roster";
|
||||
"saslauth";
|
||||
"tls";
|
||||
"dialback";
|
||||
"disco";
|
||||
"carbons";
|
||||
"pep";
|
||||
"private";
|
||||
"blocklist";
|
||||
"vcard";
|
||||
"version";
|
||||
"uptime";
|
||||
"time";
|
||||
"ping";
|
||||
"register";
|
||||
"admin_adhoc";
|
||||
"token_verification";
|
||||
"event_sync"; -- Required for webhooks
|
||||
}
|
||||
```
|
||||
|
||||
#### Configure Jitsi Meet Interface
|
||||
|
||||
Edit `/etc/jitsi/meet/your-domain-config.js`:
|
||||
|
||||
```javascript
|
||||
var config = {
|
||||
hosts: {
|
||||
domain: 'meet.example.com',
|
||||
muc: 'conference.meet.example.com'
|
||||
},
|
||||
|
||||
// Enable JWT authentication
|
||||
enableUserRolesBasedOnToken: true,
|
||||
|
||||
// Recording configuration
|
||||
fileRecordingsEnabled: true,
|
||||
liveStreamingEnabled: false,
|
||||
|
||||
// Reflector integration settings
|
||||
prejoinPageEnabled: true,
|
||||
requireDisplayName: true
|
||||
};
|
||||
```
|
||||
|
||||
### 3. Webhook Event Configuration
|
||||
|
||||
#### Install Event Sync Module
|
||||
|
||||
```bash
|
||||
# Download the module
|
||||
cd /usr/share/jitsi-meet/prosody-plugins/
|
||||
wget https://raw.githubusercontent.com/jitsi-contrib/prosody-plugins/main/mod_event_sync.lua
|
||||
```
|
||||
|
||||
#### Configure Event Sync
|
||||
|
||||
Add to your Prosody configuration:
|
||||
|
||||
```lua
|
||||
Component "conference.meet.example.com" "muc"
|
||||
storage = "memory"
|
||||
modules_enabled = {
|
||||
"muc_meeting_id";
|
||||
"muc_domain_mapper";
|
||||
"polls";
|
||||
"event_sync"; -- Enable event sync
|
||||
}
|
||||
|
||||
-- Event sync webhook configuration
|
||||
event_sync_url = "https://your-reflector-domain.com/v1/jitsi/events"
|
||||
event_sync_secret = "your-webhook-secret-here"
|
||||
|
||||
-- Events to track
|
||||
event_sync_events = {
|
||||
"muc-occupant-joined",
|
||||
"muc-occupant-left",
|
||||
"jibri-recording-on",
|
||||
"jibri-recording-off"
|
||||
}
|
||||
|
||||
#### Webhook Event Payload Examples
|
||||
|
||||
**Participant Joined Event:**
|
||||
```json
|
||||
{
|
||||
"event": "muc-occupant-joined",
|
||||
"room": "reflector-my-room-uuid123",
|
||||
"timestamp": "2025-01-15T10:30:00.000Z",
|
||||
"data": {
|
||||
"occupant_id": "participant-456",
|
||||
"nick": "John Doe",
|
||||
"role": "participant",
|
||||
"affiliation": "none"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Recording Started Event:**
|
||||
```json
|
||||
{
|
||||
"event": "jibri-recording-on",
|
||||
"room": "reflector-my-room-uuid123",
|
||||
"timestamp": "2025-01-15T10:32:00.000Z",
|
||||
"data": {
|
||||
"recording_id": "rec-789",
|
||||
"initiator": "moderator-123"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Recording Completed Event:**
|
||||
```json
|
||||
{
|
||||
"room_name": "reflector-my-room-uuid123",
|
||||
"recording_file": "/var/recordings/rec-789.mp4",
|
||||
"recording_status": "completed",
|
||||
"timestamp": "2025-01-15T11:15:00.000Z"
|
||||
}
|
||||
```
|
||||
|
||||
### 4. Jibri Recording Setup (Optional)
|
||||
|
||||
#### Install Jibri
|
||||
|
||||
```bash
|
||||
# Install Jibri package
|
||||
sudo apt install jibri
|
||||
|
||||
# Create recording directory
|
||||
sudo mkdir -p /var/recordings
|
||||
sudo chown jibri:jibri /var/recordings
|
||||
```
|
||||
|
||||
#### Configure Jibri
|
||||
|
||||
Edit `/etc/jitsi/jibri/jibri.conf`:
|
||||
|
||||
```hocon
|
||||
jibri {
|
||||
recording {
|
||||
recordings-directory = "/var/recordings"
|
||||
finalize-script = "/opt/jitsi/jibri/finalize.sh"
|
||||
}
|
||||
|
||||
api {
|
||||
xmpp {
|
||||
environments = [{
|
||||
name = "prod environment"
|
||||
xmpp-server-hosts = ["meet.example.com"]
|
||||
xmpp-domain = "meet.example.com"
|
||||
|
||||
control-muc {
|
||||
domain = "internal.auth.meet.example.com"
|
||||
room-name = "JibriBrewery"
|
||||
nickname = "jibri-nickname"
|
||||
}
|
||||
|
||||
control-login {
|
||||
domain = "auth.meet.example.com"
|
||||
username = "jibri"
|
||||
password = "jibri-password"
|
||||
}
|
||||
}]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### Create Finalize Script
|
||||
|
||||
Create `/opt/jitsi/jibri/finalize.sh`:
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# Jibri finalize script for Reflector integration
|
||||
|
||||
RECORDING_FILE="$1"
|
||||
ROOM_NAME="$2"
|
||||
REFLECTOR_API_URL="${REFLECTOR_API_URL:-http://localhost:1250}"
|
||||
|
||||
# Prepare webhook payload
|
||||
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)
|
||||
PAYLOAD=$(cat <<EOF
|
||||
{
|
||||
"room_name": "$ROOM_NAME",
|
||||
"recording_file": "$RECORDING_FILE",
|
||||
"recording_status": "completed",
|
||||
"timestamp": "$TIMESTAMP"
|
||||
}
|
||||
EOF
|
||||
)
|
||||
|
||||
# Generate signature
|
||||
SIGNATURE=$(echo -n "$PAYLOAD" | openssl dgst -sha256 -hmac "$JITSI_WEBHOOK_SECRET" | cut -d' ' -f2)
|
||||
|
||||
# Send webhook to Reflector
|
||||
curl -X POST "$REFLECTOR_API_URL/v1/jibri/recording-complete" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: $SIGNATURE" \
|
||||
-d "$PAYLOAD"
|
||||
|
||||
echo "Recording finalization webhook sent for room: $ROOM_NAME"
|
||||
```
|
||||
|
||||
Make executable:
|
||||
```bash
|
||||
sudo chmod +x /opt/jitsi/jibri/finalize.sh
|
||||
```
|
||||
|
||||
### 5. Restart Services
|
||||
|
||||
After configuration changes:
|
||||
|
||||
```bash
|
||||
sudo systemctl restart prosody
|
||||
sudo systemctl restart jicofo
|
||||
sudo systemctl restart jitsi-videobridge2
|
||||
sudo systemctl restart jibri
|
||||
sudo systemctl restart nginx
|
||||
```
|
||||
|
||||
## Room Configuration
|
||||
|
||||
### Creating Jitsi Rooms
|
||||
|
||||
Create rooms with Jitsi platform in Reflector:
|
||||
|
||||
```bash
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN" \
|
||||
-d '{
|
||||
"name": "my-jitsi-room",
|
||||
"platform": "jitsi",
|
||||
"recording_type": "cloud",
|
||||
"recording_trigger": "automatic-2nd-participant",
|
||||
"is_locked": false,
|
||||
"room_mode": "normal"
|
||||
}'
|
||||
```
|
||||
|
||||
### Meeting Creation
|
||||
|
||||
Meetings automatically use JWT authentication:
|
||||
|
||||
```bash
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms/my-jitsi-room/meeting" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN"
|
||||
```
|
||||
|
||||
Response includes JWT-authenticated URLs:
|
||||
```json
|
||||
{
|
||||
"id": "meeting-uuid",
|
||||
"room_name": "reflector-my-jitsi-room-123456",
|
||||
"room_url": "https://meet.example.com/room?jwt=user-token",
|
||||
"host_room_url": "https://meet.example.com/room?jwt=moderator-token"
|
||||
}
|
||||
```
|
||||
|
||||
## Features and Capabilities
|
||||
|
||||
### JWT Authentication
|
||||
|
||||
Reflector automatically generates JWT tokens with:
|
||||
- **Room Access Control** - Secure room entry
|
||||
- **User Roles** - Moderator vs participant permissions
|
||||
- **Expiration** - Configurable token lifetime (default 8 hours)
|
||||
- **Custom Claims** - Room-specific metadata
|
||||
|
||||
### Recording Options
|
||||
|
||||
**Recording Types:**
|
||||
- `"none"` - No recording
|
||||
- `"local"` - Local Jibri recording
|
||||
- `"cloud"` - Cloud recording (requires external storage)
|
||||
|
||||
**Recording Triggers:**
|
||||
- `"none"` - Manual recording only
|
||||
- `"prompt"` - Prompt users to start
|
||||
- `"automatic"` - Start immediately
|
||||
- `"automatic-2nd-participant"` - Start when 2nd person joins
|
||||
|
||||
### Event Tracking and Storage
|
||||
|
||||
Reflector automatically stores all webhook events in the `meetings` table for comprehensive meeting analytics:
|
||||
|
||||
**Supported Event Types:**
|
||||
- `muc-occupant-joined` - Participant joined the meeting
|
||||
- `muc-occupant-left` - Participant left the meeting
|
||||
- `jibri-recording-on` - Recording started
|
||||
- `jibri-recording-off` - Recording stopped
|
||||
- `recording_completed` - Recording file ready for processing
|
||||
|
||||
**Event Storage Structure:**
|
||||
Each webhook event is stored as a JSON object in the `meetings.events` column:
|
||||
```json
|
||||
{
|
||||
"type": "muc-occupant-joined",
|
||||
"timestamp": "2025-01-15T10:30:00.123456Z",
|
||||
"data": {
|
||||
"timestamp": "2025-01-15T10:30:00Z",
|
||||
"user_id": "participant-123",
|
||||
"display_name": "John Doe"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Querying Stored Events:**
|
||||
```sql
|
||||
-- Get all events for a meeting
|
||||
SELECT events FROM meeting WHERE id = 'meeting-uuid';
|
||||
|
||||
-- Count participant joins
|
||||
SELECT json_array_length(
|
||||
json_extract(events, '$[*] ? (@.type == "muc-occupant-joined")')
|
||||
) as total_joins FROM meeting WHERE id = 'meeting-uuid';
|
||||
```
|
||||
|
||||
## Testing and Verification
|
||||
|
||||
### Health Check
|
||||
|
||||
Test Jitsi webhook integration:
|
||||
|
||||
```bash
|
||||
curl "https://your-reflector-domain.com/v1/jitsi/health"
|
||||
```
|
||||
|
||||
Expected response:
|
||||
```json
|
||||
{
|
||||
"status": "ok",
|
||||
"service": "jitsi-webhooks",
|
||||
"timestamp": "2025-01-15T10:30:00.000Z",
|
||||
"webhook_secret_configured": true
|
||||
}
|
||||
```
|
||||
|
||||
### JWT Token Testing
|
||||
|
||||
Verify JWT generation works:
|
||||
```bash
|
||||
# Create a test meeting
|
||||
MEETING=$(curl -X POST "https://your-reflector-domain.com/v1/rooms/test-room/meeting" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN" | jq -r '.room_url')
|
||||
|
||||
echo "Test meeting URL: $MEETING"
|
||||
```
|
||||
|
||||
### Webhook Testing
|
||||
|
||||
#### Manual Webhook Event Testing
|
||||
|
||||
Test participant join event:
|
||||
```bash
|
||||
# Generate proper signature
|
||||
PAYLOAD='{"event":"muc-occupant-joined","room":"reflector-test-room-uuid","timestamp":"2025-01-15T10:30:00.000Z","data":{"user_id":"test-user","display_name":"Test User"}}'
|
||||
SIGNATURE=$(echo -n "$PAYLOAD" | openssl dgst -sha256 -hmac "$JITSI_WEBHOOK_SECRET" | cut -d' ' -f2)
|
||||
|
||||
curl -X POST "https://your-reflector-domain.com/v1/jitsi/events" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: $SIGNATURE" \
|
||||
-d "$PAYLOAD"
|
||||
```
|
||||
|
||||
Expected response:
|
||||
```json
|
||||
{
|
||||
"status": "ok",
|
||||
"event": "muc-occupant-joined",
|
||||
"room": "reflector-test-room-uuid"
|
||||
}
|
||||
```
|
||||
|
||||
#### Recording Webhook Testing
|
||||
|
||||
Test recording completion event:
|
||||
```bash
|
||||
PAYLOAD='{"room_name":"reflector-test-room-uuid","recording_file":"/recordings/test.mp4","recording_status":"completed","timestamp":"2025-01-15T10:30:00.000Z"}'
|
||||
SIGNATURE=$(echo -n "$PAYLOAD" | openssl dgst -sha256 -hmac "$JITSI_WEBHOOK_SECRET" | cut -d' ' -f2)
|
||||
|
||||
curl -X POST "https://your-reflector-domain.com/v1/jibri/recording-complete" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: $SIGNATURE" \
|
||||
-d "$PAYLOAD"
|
||||
```
|
||||
|
||||
#### Event Storage Verification
|
||||
|
||||
Verify events were stored:
|
||||
```bash
|
||||
# Check meeting events via API (requires authentication)
|
||||
curl -H "Authorization: Bearer $AUTH_TOKEN" \
|
||||
"https://your-reflector-domain.com/v1/meetings/{meeting-id}"
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
#### JWT Authentication Failures
|
||||
|
||||
**Symptoms**: Users cannot join rooms, "Authentication failed" errors
|
||||
|
||||
**Solutions**:
|
||||
1. Verify `JITSI_JWT_SECRET` matches Prosody configuration
|
||||
2. Check JWT token hasn't expired (default 8 hours)
|
||||
3. Ensure system clocks are synchronized between servers
|
||||
4. Validate JWT issuer/audience configuration matches
|
||||
|
||||
**Debug JWT tokens**:
|
||||
```bash
|
||||
# Decode JWT payload
|
||||
echo "JWT_TOKEN_HERE" | cut -d'.' -f2 | base64 -d | jq
|
||||
```
|
||||
|
||||
#### Webhook Events Not Received
|
||||
|
||||
**Symptoms**: Participant counts not updating, no recording events
|
||||
|
||||
**Solutions**:
|
||||
1. Verify `mod_event_sync` is loaded in Prosody
|
||||
2. Check webhook URL is accessible from Jitsi server
|
||||
3. Validate webhook signature generation
|
||||
4. Review Prosody and Reflector logs
|
||||
|
||||
**Debug webhook connectivity**:
|
||||
```bash
|
||||
# Test from Jitsi server
|
||||
curl -v "https://your-reflector-domain.com/v1/jitsi/health"
|
||||
|
||||
# Check Prosody logs
|
||||
sudo tail -f /var/log/prosody/prosody.log
|
||||
```
|
||||
|
||||
#### Webhook Signature Verification Issues
|
||||
|
||||
**Symptoms**: HTTP 401 "Invalid webhook signature" errors
|
||||
|
||||
**Solutions**:
|
||||
1. Verify webhook secret matches between Jitsi and Reflector
|
||||
2. Check payload encoding (no extra whitespace)
|
||||
3. Ensure proper HMAC-SHA256 signature generation
|
||||
|
||||
**Debug signature generation**:
|
||||
```bash
|
||||
# Test signature manually
|
||||
PAYLOAD='{"event":"test","room":"test","timestamp":"2025-01-15T10:30:00.000Z","data":{}}'
|
||||
SECRET="your-webhook-secret-here"
|
||||
|
||||
# Generate signature (should match X-Jitsi-Signature header)
|
||||
echo -n "$PAYLOAD" | openssl dgst -sha256 -hmac "$SECRET" | cut -d' ' -f2
|
||||
|
||||
# Test with curl
|
||||
curl -X POST "https://your-reflector-domain.com/v1/jitsi/events" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: $(echo -n "$PAYLOAD" | openssl dgst -sha256 -hmac "$SECRET" | cut -d' ' -f2)" \
|
||||
-d "$PAYLOAD" -v
|
||||
```
|
||||
|
||||
#### Event Storage Problems
|
||||
|
||||
**Symptoms**: Events received but not stored in database
|
||||
|
||||
**Solutions**:
|
||||
1. Check database connectivity and permissions
|
||||
2. Verify meeting exists before event processing
|
||||
3. Review Reflector application logs
|
||||
4. Ensure JSON column support in database
|
||||
|
||||
**Debug event storage**:
|
||||
```bash
|
||||
# Check meeting exists
|
||||
curl -H "Authorization: Bearer $TOKEN" \
|
||||
"https://your-reflector-domain.com/v1/meetings/{meeting-id}"
|
||||
|
||||
# Monitor database queries (if using PostgreSQL)
|
||||
sudo -u postgres psql -c "SELECT * FROM pg_stat_activity WHERE query LIKE '%meeting%';"
|
||||
|
||||
# Check Reflector logs for event processing
|
||||
sudo journalctl -u reflector -f | grep -E "(event|webhook|jitsi)"
|
||||
```
|
||||
|
||||
#### Recording Issues
|
||||
|
||||
**Symptoms**: Recordings not starting, finalize script errors
|
||||
|
||||
**Solutions**:
|
||||
1. Verify Jibri service status: `sudo systemctl status jibri`
|
||||
2. Check recording directory permissions: `/var/recordings`
|
||||
3. Validate finalize script execution permissions
|
||||
4. Monitor Jibri logs: `sudo journalctl -u jibri -f`
|
||||
|
||||
**Test finalize script**:
|
||||
```bash
|
||||
sudo -u jibri /opt/jitsi/jibri/finalize.sh "/test/recording.mp4" "test-room"
|
||||
```
|
||||
|
||||
#### Meeting Creation Failures
|
||||
|
||||
**Symptoms**: HTTP 500 errors when creating meetings
|
||||
|
||||
**Solutions**:
|
||||
1. Check Reflector logs for JWT generation errors
|
||||
2. Verify all required environment variables are set
|
||||
3. Ensure Jitsi domain is accessible from Reflector
|
||||
4. Test JWT secret configuration
|
||||
|
||||
### Debug Commands
|
||||
|
||||
```bash
|
||||
# Verify Prosody configuration
|
||||
sudo prosodyctl check config
|
||||
|
||||
# Check Jitsi services status
|
||||
sudo systemctl status prosody jicofo jitsi-videobridge2
|
||||
|
||||
# Test JWT generation
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms/test/meeting" \
|
||||
-H "Authorization: Bearer $TOKEN" -v
|
||||
|
||||
# Monitor webhook events
|
||||
sudo tail -f /var/log/reflector/app.log | grep jitsi
|
||||
|
||||
# Check SSL certificates
|
||||
sudo certbot certificates
|
||||
```
|
||||
|
||||
### Performance Optimization
|
||||
|
||||
#### Scaling Considerations
|
||||
|
||||
**Single Server Limits:**
|
||||
- ~50 concurrent participants per JVB instance
|
||||
- ~10 concurrent Jibri recordings
|
||||
- CPU and bandwidth become bottlenecks
|
||||
|
||||
**Multi-Server Setup:**
|
||||
- Multiple JVB instances for scaling
|
||||
- Dedicated Jibri recording servers
|
||||
- Load balancing for high availability
|
||||
|
||||
#### Resource Monitoring
|
||||
|
||||
```bash
|
||||
# Monitor JVB performance
|
||||
sudo systemctl status jitsi-videobridge2
|
||||
sudo journalctl -u jitsi-videobridge2 -f
|
||||
|
||||
# Check Prosody connections
|
||||
sudo prosodyctl mod_admin_telnet
|
||||
> c2s:show()
|
||||
> muc:rooms()
|
||||
```
|
||||
|
||||
## Security Best Practices
|
||||
|
||||
### JWT Security
|
||||
- Use strong, unique secrets (32+ characters)
|
||||
- Rotate JWT secrets regularly
|
||||
- Implement proper token expiration
|
||||
- Never log or expose JWT tokens
|
||||
|
||||
### Network Security
|
||||
- Use HTTPS/WSS for all communications
|
||||
- Implement proper firewall rules
|
||||
- Consider VPN for server-to-server communication
|
||||
- Monitor for unauthorized access attempts
|
||||
|
||||
### Recording Security
|
||||
- Encrypt recordings at rest
|
||||
- Implement access controls for recording files
|
||||
- Regular security audits of file permissions
|
||||
- Comply with data protection regulations
|
||||
|
||||
## Migration from Whereby
|
||||
|
||||
If migrating from Whereby to Jitsi:
|
||||
|
||||
1. **Parallel Setup** - Configure Jitsi alongside existing Whereby
|
||||
2. **Room Migration** - Update room platform field to "jitsi"
|
||||
3. **Test Integration** - Verify meeting creation and webhooks
|
||||
4. **User Training** - Different UI and feature set
|
||||
5. **Monitor Performance** - Watch for issues during transition
|
||||
6. **Cleanup** - Remove Whereby configuration when stable
|
||||
|
||||
## Support and Resources
|
||||
|
||||
### Jitsi Community Resources
|
||||
- **Documentation**: [jitsi.github.io/handbook](https://jitsi.github.io/handbook/)
|
||||
- **Community Forum**: [community.jitsi.org](https://community.jitsi.org/)
|
||||
- **GitHub Issues**: [github.com/jitsi/jitsi-meet](https://github.com/jitsi/jitsi-meet)
|
||||
|
||||
### Professional Support
|
||||
- **8x8 Commercial Support** - Professional Jitsi hosting and support
|
||||
- **Community Consulting** - Third-party Jitsi implementation services
|
||||
|
||||
### Monitoring and Maintenance
|
||||
- Monitor system resources (CPU, memory, bandwidth)
|
||||
- Regular security updates for all components
|
||||
- Backup configuration files and certificates
|
||||
- Test disaster recovery procedures
|
||||
276
docs/video-whereby.md
Normal file
276
docs/video-whereby.md
Normal file
@@ -0,0 +1,276 @@
|
||||
# Whereby Integration Configuration Guide
|
||||
|
||||
This guide explains how to configure Reflector to use Whereby as your video meeting platform for room creation, recording, and participant tracking.
|
||||
|
||||
## Overview
|
||||
|
||||
Whereby is a browser-based video meeting platform that provides hosted meeting rooms with recording capabilities. Reflector integrates with Whereby's API to:
|
||||
|
||||
- Create secure meeting rooms with custom branding
|
||||
- Handle participant join/leave events via webhooks
|
||||
- Automatically record meetings to AWS S3 storage
|
||||
- Track meeting sessions and participant counts
|
||||
|
||||
## Requirements
|
||||
|
||||
### Whereby Account Setup
|
||||
|
||||
1. **Whereby Account**: Sign up for a Whereby business account at [whereby.com](https://whereby.com/business)
|
||||
2. **API Access**: Request API access from Whereby support (required for programmatic room creation)
|
||||
3. **Webhook Configuration**: Configure webhooks in your Whereby dashboard to point to your Reflector instance
|
||||
|
||||
### AWS S3 Storage
|
||||
|
||||
Whereby requires AWS S3 for recording storage. You need:
|
||||
- AWS account with S3 access
|
||||
- Dedicated S3 bucket for Whereby recordings
|
||||
- AWS IAM credentials with S3 write permissions
|
||||
|
||||
## Configuration Variables
|
||||
|
||||
Add the following environment variables to your Reflector `.env` file:
|
||||
|
||||
### Required Variables
|
||||
|
||||
```bash
|
||||
# Whereby API Configuration
|
||||
WHEREBY_API_KEY=your-whereby-jwt-api-key
|
||||
WHEREBY_WEBHOOK_SECRET=your-webhook-secret-from-whereby
|
||||
|
||||
# AWS S3 Storage for Recordings
|
||||
AWS_WHEREBY_ACCESS_KEY_ID=your-aws-access-key
|
||||
AWS_WHEREBY_ACCESS_KEY_SECRET=your-aws-secret-key
|
||||
RECORDING_STORAGE_AWS_BUCKET_NAME=your-s3-bucket-name
|
||||
```
|
||||
|
||||
### Optional Variables
|
||||
|
||||
```bash
|
||||
# Whereby API URL (defaults to production)
|
||||
WHEREBY_API_URL=https://api.whereby.dev/v1
|
||||
|
||||
# SQS Configuration (for recording processing)
|
||||
AWS_PROCESS_RECORDING_QUEUE_URL=https://sqs.region.amazonaws.com/account/queue
|
||||
SQS_POLLING_TIMEOUT_SECONDS=60
|
||||
```
|
||||
|
||||
## Configuration Steps
|
||||
|
||||
### 1. Whereby API Key Setup
|
||||
|
||||
1. **Contact Whereby Support** to request API access for your account
|
||||
2. **Generate JWT Token** in your Whereby dashboard under API settings
|
||||
3. **Copy the JWT token** and set it as `WHEREBY_API_KEY` in your environment
|
||||
|
||||
The API key is a JWT token that looks like:
|
||||
```
|
||||
eyJ[...truncated JWT token...]
|
||||
```
|
||||
|
||||
### 2. Webhook Configuration
|
||||
|
||||
1. **Access Whereby Dashboard** and navigate to webhook settings
|
||||
2. **Set Webhook URL** to your Reflector instance:
|
||||
```
|
||||
https://your-reflector-domain.com/v1/whereby
|
||||
```
|
||||
3. **Configure Events** to send the following event types:
|
||||
- `room.client.joined` - When participants join
|
||||
- `room.client.left` - When participants leave
|
||||
4. **Generate Webhook Secret** and set it as `WHEREBY_WEBHOOK_SECRET`
|
||||
5. **Save Configuration** in your Whereby dashboard
|
||||
|
||||
### 3. AWS S3 Storage Setup
|
||||
|
||||
1. **Create S3 Bucket** dedicated for Whereby recordings
|
||||
2. **Create IAM User** with programmatic access
|
||||
3. **Attach S3 Policy** with the following permissions:
|
||||
```json
|
||||
{
|
||||
"Version": "2012-10-17",
|
||||
"Statement": [
|
||||
{
|
||||
"Effect": "Allow",
|
||||
"Action": [
|
||||
"s3:PutObject",
|
||||
"s3:PutObjectAcl",
|
||||
"s3:GetObject"
|
||||
],
|
||||
"Resource": "arn:aws:s3:::your-bucket-name/*"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
4. **Configure Environment Variables** with the IAM credentials
|
||||
|
||||
### 4. Room Configuration
|
||||
|
||||
When creating rooms in Reflector, set the platform to use Whereby:
|
||||
|
||||
```bash
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN" \
|
||||
-d '{
|
||||
"name": "my-whereby-room",
|
||||
"platform": "whereby",
|
||||
"recording_type": "cloud",
|
||||
"recording_trigger": "automatic-2nd-participant",
|
||||
"is_locked": false,
|
||||
"room_mode": "normal"
|
||||
}'
|
||||
```
|
||||
|
||||
## Meeting Features
|
||||
|
||||
### Recording Options
|
||||
|
||||
Whereby supports three recording types:
|
||||
- **`none`**: No recording
|
||||
- **`local`**: Local recording (not recommended for production)
|
||||
- **`cloud`**: Cloud recording to S3 (recommended)
|
||||
|
||||
### Recording Triggers
|
||||
|
||||
Control when recordings start:
|
||||
- **`none`**: No automatic recording
|
||||
- **`prompt`**: Prompt users to start recording
|
||||
- **`automatic`**: Start immediately when meeting begins
|
||||
- **`automatic-2nd-participant`**: Start when second participant joins
|
||||
|
||||
### Room Modes
|
||||
|
||||
- **`normal`**: Standard meeting room
|
||||
- **`group`**: Group meeting with advanced features
|
||||
|
||||
## Webhook Event Handling
|
||||
|
||||
Reflector automatically handles these Whereby webhook events:
|
||||
|
||||
### Participant Tracking
|
||||
```json
|
||||
{
|
||||
"type": "room.client.joined",
|
||||
"data": {
|
||||
"meetingId": "room-uuid",
|
||||
"numClients": 2
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Recording Events
|
||||
Whereby sends recording completion events that trigger Reflector's processing pipeline:
|
||||
- Audio transcription
|
||||
- Speaker diarization
|
||||
- Summary generation
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
#### API Authentication Errors
|
||||
**Symptoms**: 401 Unauthorized errors when creating meetings
|
||||
|
||||
**Solutions**:
|
||||
1. Verify your `WHEREBY_API_KEY` is correct and not expired
|
||||
2. Ensure you have API access enabled on your Whereby account
|
||||
3. Contact Whereby support if API access is not available
|
||||
|
||||
#### Webhook Signature Validation Failed
|
||||
**Symptoms**: Webhook events rejected with 401 errors
|
||||
|
||||
**Solutions**:
|
||||
1. Verify `WHEREBY_WEBHOOK_SECRET` matches your Whereby dashboard configuration
|
||||
2. Check webhook URL is correctly configured in Whereby dashboard
|
||||
3. Ensure webhook endpoint is accessible from Whereby servers
|
||||
|
||||
#### Recording Upload Failures
|
||||
**Symptoms**: Recordings not appearing in S3 bucket
|
||||
|
||||
**Solutions**:
|
||||
1. Verify AWS credentials have S3 write permissions
|
||||
2. Check S3 bucket name is correct and accessible
|
||||
3. Ensure AWS region settings match your bucket location
|
||||
4. Review AWS CloudTrail logs for permission issues
|
||||
|
||||
#### Participant Count Not Updating
|
||||
**Symptoms**: Meeting participant counts remain at 0
|
||||
|
||||
**Solutions**:
|
||||
1. Verify webhook events are being received at `/v1/whereby`
|
||||
2. Check webhook signature validation is passing
|
||||
3. Ensure meeting IDs match between Whereby and Reflector database
|
||||
|
||||
### Debug Commands
|
||||
|
||||
```bash
|
||||
# Test Whereby API connectivity
|
||||
curl -H "Authorization: Bearer $WHEREBY_API_KEY" \
|
||||
https://api.whereby.dev/v1/meetings
|
||||
|
||||
# Check webhook endpoint health
|
||||
curl https://your-reflector-domain.com/v1/whereby/health
|
||||
|
||||
# Verify S3 bucket access
|
||||
aws s3 ls s3://your-bucket-name --profile whereby-user
|
||||
```
|
||||
|
||||
## Security Considerations
|
||||
|
||||
### API Key Security
|
||||
- Store API keys securely using environment variables
|
||||
- Rotate API keys regularly
|
||||
- Never commit API keys to version control
|
||||
- Use separate keys for development and production
|
||||
|
||||
### Webhook Security
|
||||
- Always validate webhook signatures using HMAC-SHA256
|
||||
- Use HTTPS for all webhook endpoints
|
||||
- Implement rate limiting on webhook endpoints
|
||||
- Monitor webhook events for suspicious activity
|
||||
|
||||
### Recording Privacy
|
||||
- Ensure S3 bucket access is restricted to authorized users
|
||||
- Consider encryption at rest for sensitive recordings
|
||||
- Implement retention policies for recorded content
|
||||
- Comply with data protection regulations (GDPR, etc.)
|
||||
|
||||
## Performance Optimization
|
||||
|
||||
### Meeting Scaling
|
||||
- Monitor concurrent meeting limits on your Whereby plan
|
||||
- Implement meeting cleanup for expired sessions
|
||||
- Use appropriate room modes for different use cases
|
||||
|
||||
### Recording Processing
|
||||
- Configure SQS for asynchronous recording processing
|
||||
- Monitor S3 storage usage and costs
|
||||
- Implement automatic cleanup of processed recordings
|
||||
|
||||
### Webhook Reliability
|
||||
- Implement webhook retry mechanisms
|
||||
- Monitor webhook delivery success rates
|
||||
- Log webhook events for debugging and auditing
|
||||
|
||||
## Migration from Other Platforms
|
||||
|
||||
If migrating from another video platform:
|
||||
|
||||
1. **Update Room Configuration**: Change existing rooms to use `"platform": "whereby"`
|
||||
2. **Configure Webhooks**: Set up Whereby webhook endpoints
|
||||
3. **Test Integration**: Verify meeting creation and event handling
|
||||
4. **Monitor Performance**: Watch for any issues during transition
|
||||
5. **Update Documentation**: Inform users of any workflow changes
|
||||
|
||||
## Support
|
||||
|
||||
For Whereby-specific issues:
|
||||
- **Whereby Support**: [whereby.com/support](https://whereby.com/support)
|
||||
- **API Documentation**: [whereby.dev](https://whereby.dev)
|
||||
- **Status Page**: [status.whereby.com](https://status.whereby.com)
|
||||
|
||||
For Reflector integration issues:
|
||||
- Check application logs for error details
|
||||
- Verify environment variable configuration
|
||||
- Test webhook connectivity and authentication
|
||||
- Review AWS permissions and S3 access
|
||||
474
docs/video_platforms.md
Normal file
474
docs/video_platforms.md
Normal file
@@ -0,0 +1,474 @@
|
||||
# Video Platforms Architecture (PR #529 Analysis)
|
||||
|
||||
This document analyzes the video platforms refactoring implemented in PR #529 for daily.co integration, providing a blueprint for extending support to Jitsi and other video conferencing platforms.
|
||||
|
||||
## Overview
|
||||
|
||||
The video platforms refactoring introduces a clean abstraction layer that allows Reflector to support multiple video conferencing providers (Whereby, Daily.co, etc.) without changing core application logic. This architecture enables:
|
||||
|
||||
- Seamless switching between video platforms
|
||||
- Platform-specific feature support
|
||||
- Isolated platform code organization
|
||||
- Consistent API surface across platforms
|
||||
- Feature flags for gradual migration
|
||||
|
||||
## Architecture Components
|
||||
|
||||
### 1. **Directory Structure**
|
||||
|
||||
```
|
||||
server/reflector/video_platforms/
|
||||
├── __init__.py # Public API exports
|
||||
├── base.py # Abstract base classes
|
||||
├── factory.py # Platform client factory
|
||||
├── registry.py # Platform registration system
|
||||
├── whereby.py # Whereby implementation
|
||||
├── daily.py # Daily.co implementation
|
||||
└── mock.py # Testing implementation
|
||||
```
|
||||
|
||||
### 2. **Core Abstract Classes**
|
||||
|
||||
#### `VideoPlatformClient` (base.py)
|
||||
Abstract base class defining the interface all platforms must implement:
|
||||
|
||||
```python
|
||||
class VideoPlatformClient(ABC):
|
||||
PLATFORM_NAME: str = ""
|
||||
|
||||
@abstractmethod
|
||||
async def create_meeting(self, room_name_prefix: str, end_date: datetime, room: Room) -> MeetingData
|
||||
|
||||
@abstractmethod
|
||||
async def get_room_sessions(self, room_name: str) -> Dict[str, Any]
|
||||
|
||||
@abstractmethod
|
||||
async def delete_room(self, room_name: str) -> bool
|
||||
|
||||
@abstractmethod
|
||||
async def upload_logo(self, room_name: str, logo_path: str) -> bool
|
||||
|
||||
@abstractmethod
|
||||
def verify_webhook_signature(self, body: bytes, signature: str, timestamp: Optional[str] = None) -> bool
|
||||
```
|
||||
|
||||
#### `MeetingData` (base.py)
|
||||
Standardized meeting data structure returned by all platforms:
|
||||
|
||||
```python
|
||||
class MeetingData(BaseModel):
|
||||
meeting_id: str
|
||||
room_name: str
|
||||
room_url: str
|
||||
host_room_url: str
|
||||
platform: str
|
||||
extra_data: Dict[str, Any] = {} # Platform-specific data
|
||||
```
|
||||
|
||||
#### `VideoPlatformConfig` (base.py)
|
||||
Unified configuration structure for all platforms:
|
||||
|
||||
```python
|
||||
class VideoPlatformConfig(BaseModel):
|
||||
api_key: str
|
||||
webhook_secret: str
|
||||
api_url: Optional[str] = None
|
||||
subdomain: Optional[str] = None
|
||||
s3_bucket: Optional[str] = None
|
||||
s3_region: Optional[str] = None
|
||||
aws_role_arn: Optional[str] = None
|
||||
aws_access_key_id: Optional[str] = None
|
||||
aws_access_key_secret: Optional[str] = None
|
||||
```
|
||||
|
||||
### 3. **Platform Registration System**
|
||||
|
||||
#### Registry Pattern (registry.py)
|
||||
- Automatic registration of built-in platforms
|
||||
- Runtime platform discovery
|
||||
- Type-safe client instantiation
|
||||
|
||||
```python
|
||||
# Auto-registration of platforms
|
||||
_PLATFORMS: Dict[str, Type[VideoPlatformClient]] = {}
|
||||
|
||||
def register_platform(name: str, client_class: Type[VideoPlatformClient])
|
||||
def get_platform_client(platform: str, config: VideoPlatformConfig) -> VideoPlatformClient
|
||||
```
|
||||
|
||||
#### Factory System (factory.py)
|
||||
- Configuration management per platform
|
||||
- Platform selection logic
|
||||
- Feature flag integration
|
||||
|
||||
```python
|
||||
def get_platform_for_room(room_id: Optional[str] = None) -> str:
|
||||
"""Determine which platform to use based on feature flags."""
|
||||
if not settings.DAILY_MIGRATION_ENABLED:
|
||||
return "whereby"
|
||||
|
||||
if room_id and room_id in settings.DAILY_MIGRATION_ROOM_IDS:
|
||||
return "daily"
|
||||
|
||||
return settings.DEFAULT_VIDEO_PLATFORM
|
||||
```
|
||||
|
||||
### 4. **Database Schema Changes**
|
||||
|
||||
#### Room Model Updates
|
||||
Added `platform` field to track which video platform each room uses:
|
||||
|
||||
```python
|
||||
# Database Schema
|
||||
platform_column = sqlalchemy.Column(
|
||||
"platform",
|
||||
sqlalchemy.String,
|
||||
nullable=False,
|
||||
server_default="whereby"
|
||||
)
|
||||
|
||||
# Pydantic Model
|
||||
class Room(BaseModel):
|
||||
platform: Literal["whereby", "daily"] = "whereby"
|
||||
```
|
||||
|
||||
#### Meeting Model Updates
|
||||
Added `platform` field to meetings for tracking and debugging:
|
||||
|
||||
```python
|
||||
# Database Schema
|
||||
platform_column = sqlalchemy.Column(
|
||||
"platform",
|
||||
sqlalchemy.String,
|
||||
nullable=False,
|
||||
server_default="whereby"
|
||||
)
|
||||
|
||||
# Pydantic Model
|
||||
class Meeting(BaseModel):
|
||||
platform: Literal["whereby", "daily"] = "whereby"
|
||||
```
|
||||
|
||||
**Key Decision**: No platform-specific fields were added to models. Instead, the `extra_data` field in `MeetingData` handles platform-specific information, following the user's rule of using generic `provider_data` as JSON if needed.
|
||||
|
||||
### 5. **Settings Configuration**
|
||||
|
||||
#### Feature Flags
|
||||
```python
|
||||
# Migration control
|
||||
DAILY_MIGRATION_ENABLED: bool = True
|
||||
DAILY_MIGRATION_ROOM_IDS: list[str] = []
|
||||
DEFAULT_VIDEO_PLATFORM: str = "daily"
|
||||
|
||||
# Daily.co specific settings
|
||||
DAILY_API_KEY: str | None = None
|
||||
DAILY_WEBHOOK_SECRET: str | None = None
|
||||
DAILY_SUBDOMAIN: str | None = None
|
||||
AWS_DAILY_S3_BUCKET: str | None = None
|
||||
AWS_DAILY_S3_REGION: str = "us-west-2"
|
||||
AWS_DAILY_ROLE_ARN: str | None = None
|
||||
```
|
||||
|
||||
#### Configuration Pattern
|
||||
Each platform gets its own configuration namespace while sharing common patterns:
|
||||
|
||||
```python
|
||||
def get_platform_config(platform: str) -> VideoPlatformConfig:
|
||||
if platform == "whereby":
|
||||
return VideoPlatformConfig(
|
||||
api_key=settings.WHEREBY_API_KEY or "",
|
||||
webhook_secret=settings.WHEREBY_WEBHOOK_SECRET or "",
|
||||
# ... whereby-specific config
|
||||
)
|
||||
elif platform == "daily":
|
||||
return VideoPlatformConfig(
|
||||
api_key=settings.DAILY_API_KEY or "",
|
||||
webhook_secret=settings.DAILY_WEBHOOK_SECRET or "",
|
||||
# ... daily-specific config
|
||||
)
|
||||
```
|
||||
|
||||
### 6. **API Integration Updates**
|
||||
|
||||
#### Room Creation (views/rooms.py)
|
||||
Updated to use platform factory instead of direct Whereby calls:
|
||||
|
||||
```python
|
||||
@router.post("/rooms/{room_name}/meeting")
|
||||
async def rooms_create_meeting(room_name: str, user: UserInfo):
|
||||
# OLD: Direct Whereby integration
|
||||
# whereby_meeting = await create_meeting("", end_date=end_date, room=room)
|
||||
|
||||
# NEW: Platform abstraction
|
||||
platform = get_platform_for_room(room.id)
|
||||
client = create_platform_client(platform)
|
||||
|
||||
meeting_data = await client.create_meeting(
|
||||
room_name_prefix=room.name, end_date=end_date, room=room
|
||||
)
|
||||
|
||||
await client.upload_logo(meeting_data.room_name, "./images/logo.png")
|
||||
```
|
||||
|
||||
### 7. **Webhook Handling**
|
||||
|
||||
#### Separate Webhook Endpoints
|
||||
Each platform gets its own webhook endpoint with platform-specific signature verification:
|
||||
|
||||
```python
|
||||
# views/daily.py
|
||||
@router.post("/daily_webhook")
|
||||
async def daily_webhook(event: DailyWebhookEvent, request: Request):
|
||||
# Verify Daily.co signature
|
||||
body = await request.body()
|
||||
signature = request.headers.get("X-Daily-Signature", "")
|
||||
|
||||
if not verify_daily_webhook_signature(body, signature):
|
||||
raise HTTPException(status_code=401)
|
||||
|
||||
# Handle platform-specific events
|
||||
if event.type == "participant.joined":
|
||||
await _handle_participant_joined(event)
|
||||
```
|
||||
|
||||
#### Consistent Event Handling
|
||||
Despite different event formats, the core business logic remains the same:
|
||||
|
||||
```python
|
||||
async def _handle_participant_joined(event):
|
||||
room_name = event.data.get("room", {}).get("name") # Daily.co format
|
||||
meeting = await meetings_controller.get_by_room_name(room_name)
|
||||
if meeting:
|
||||
current_count = getattr(meeting, "num_clients", 0)
|
||||
await meetings_controller.update_meeting(
|
||||
meeting.id, num_clients=current_count + 1
|
||||
)
|
||||
```
|
||||
|
||||
### 8. **Worker Task Integration**
|
||||
|
||||
#### New Task for Daily.co Recording Processing
|
||||
Added platform-specific recording processing while maintaining the same pipeline:
|
||||
|
||||
```python
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def process_recording_from_url(recording_url: str, meeting_id: str, recording_id: str):
|
||||
"""Process recording from Direct URL (Daily.co webhook)."""
|
||||
logger.info("Processing recording from URL for meeting: %s", meeting_id)
|
||||
# Uses same processing pipeline as Whereby S3 recordings
|
||||
```
|
||||
|
||||
**Key Decision**: Worker tasks remain in main worker module but could be moved to platform-specific folders as suggested by the user.
|
||||
|
||||
### 9. **Testing Infrastructure**
|
||||
|
||||
#### Comprehensive Test Suite
|
||||
- Unit tests for each platform client
|
||||
- Integration tests for platform switching
|
||||
- Mock platform for testing without external dependencies
|
||||
- Webhook signature verification tests
|
||||
|
||||
```python
|
||||
class TestPlatformIntegration:
|
||||
"""Integration tests for platform switching."""
|
||||
|
||||
async def test_platform_switching_preserves_interface(self):
|
||||
"""Test that different platforms provide consistent interface."""
|
||||
# Test both Mock and Daily platforms return MeetingData objects
|
||||
# with consistent fields
|
||||
```
|
||||
|
||||
## Implementation Patterns for Jitsi Integration
|
||||
|
||||
Based on the daily.co implementation, here's how Jitsi should be integrated:
|
||||
|
||||
### 1. **Jitsi Client Implementation**
|
||||
|
||||
```python
|
||||
# video_platforms/jitsi.py
|
||||
class JitsiClient(VideoPlatformClient):
|
||||
PLATFORM_NAME = "jitsi"
|
||||
|
||||
async def create_meeting(self, room_name_prefix: str, end_date: datetime, room: Room) -> MeetingData:
|
||||
# Generate unique room name
|
||||
jitsi_room = f"reflector-{room.name}-{int(time.time())}"
|
||||
|
||||
# Generate JWT tokens
|
||||
user_jwt = self._generate_jwt(room=jitsi_room, moderator=False, exp=end_date)
|
||||
host_jwt = self._generate_jwt(room=jitsi_room, moderator=True, exp=end_date)
|
||||
|
||||
return MeetingData(
|
||||
meeting_id=generate_uuid4(),
|
||||
room_name=jitsi_room,
|
||||
room_url=f"https://jitsi.domain/{jitsi_room}?jwt={user_jwt}",
|
||||
host_room_url=f"https://jitsi.domain/{jitsi_room}?jwt={host_jwt}",
|
||||
platform=self.PLATFORM_NAME,
|
||||
extra_data={"user_jwt": user_jwt, "host_jwt": host_jwt}
|
||||
)
|
||||
```
|
||||
|
||||
### 2. **Settings Integration**
|
||||
|
||||
```python
|
||||
# settings.py
|
||||
JITSI_DOMAIN: str = "meet.jit.si"
|
||||
JITSI_JWT_SECRET: str | None = None
|
||||
JITSI_WEBHOOK_SECRET: str | None = None
|
||||
JITSI_API_URL: str | None = None # If using Jitsi API
|
||||
```
|
||||
|
||||
### 3. **Factory Registration**
|
||||
|
||||
```python
|
||||
# registry.py
|
||||
def _register_builtin_platforms():
|
||||
from .jitsi import JitsiClient
|
||||
register_platform("jitsi", JitsiClient)
|
||||
|
||||
# factory.py
|
||||
def get_platform_config(platform: str) -> VideoPlatformConfig:
|
||||
elif platform == "jitsi":
|
||||
return VideoPlatformConfig(
|
||||
api_key="", # Jitsi may not need API key
|
||||
webhook_secret=settings.JITSI_WEBHOOK_SECRET or "",
|
||||
api_url=settings.JITSI_API_URL,
|
||||
)
|
||||
```
|
||||
|
||||
### 4. **Webhook Integration**
|
||||
|
||||
```python
|
||||
# views/jitsi.py
|
||||
@router.post("/jitsi/events")
|
||||
async def jitsi_events_webhook(event_data: dict):
|
||||
# Handle Prosody event-sync webhook format
|
||||
event_type = event_data.get("event")
|
||||
room_name = event_data.get("room", "").split("@")[0]
|
||||
|
||||
if event_type == "muc-occupant-joined":
|
||||
# Same participant handling logic as other platforms
|
||||
```
|
||||
|
||||
## Key Benefits of This Architecture
|
||||
|
||||
### 1. **Isolation and Organization**
|
||||
- Platform-specific code contained in separate modules
|
||||
- No platform logic leaking into core application
|
||||
- Easy to add/remove platforms without affecting others
|
||||
|
||||
### 2. **Consistent Interface**
|
||||
- All platforms implement the same abstract methods
|
||||
- Standardized `MeetingData` structure
|
||||
- Uniform error handling and logging
|
||||
|
||||
### 3. **Gradual Migration Support**
|
||||
- Feature flags for controlled rollouts
|
||||
- Room-specific platform selection
|
||||
- Fallback mechanisms for platform failures
|
||||
|
||||
### 4. **Configuration Management**
|
||||
- Centralized settings per platform
|
||||
- Consistent naming patterns
|
||||
- Environment-based configuration
|
||||
|
||||
### 5. **Testing and Quality**
|
||||
- Mock platform for testing
|
||||
- Comprehensive test coverage
|
||||
- Platform-specific test utilities
|
||||
|
||||
## Migration Strategy Applied
|
||||
|
||||
The daily.co implementation demonstrates a careful migration approach:
|
||||
|
||||
### 1. **Backward Compatibility**
|
||||
- Default platform remains "whereby"
|
||||
- Existing rooms continue using Whereby unless explicitly migrated
|
||||
- Same API endpoints and response formats
|
||||
|
||||
### 2. **Feature Flag Control**
|
||||
```python
|
||||
# Gradual rollout control
|
||||
DAILY_MIGRATION_ENABLED: bool = True
|
||||
DAILY_MIGRATION_ROOM_IDS: list[str] = [] # Specific rooms to migrate
|
||||
DEFAULT_VIDEO_PLATFORM: str = "daily" # New rooms default
|
||||
```
|
||||
|
||||
### 3. **Data Integrity**
|
||||
- Platform field tracks which service each room/meeting uses
|
||||
- No data loss during migration
|
||||
- Platform-specific data preserved in `extra_data`
|
||||
|
||||
### 4. **Monitoring and Rollback**
|
||||
- Comprehensive logging of platform selection
|
||||
- Easy rollback by changing feature flags
|
||||
- Platform-specific error tracking
|
||||
|
||||
## Recommendations for Jitsi Integration
|
||||
|
||||
Based on this analysis and the user's requirements:
|
||||
|
||||
### 1. **Follow the Pattern**
|
||||
- Create `video_platforms/jitsi/` directory with:
|
||||
- `client.py` - Main JitsiClient implementation
|
||||
- `tasks.py` - Jitsi-specific worker tasks
|
||||
- `__init__.py` - Module exports
|
||||
|
||||
### 2. **Settings Organization**
|
||||
- Use `JITSI_*` prefix for all Jitsi settings
|
||||
- Follow the same configuration pattern as Daily.co
|
||||
- Support both environment variables and config files
|
||||
|
||||
### 3. **Generic Database Fields**
|
||||
- Avoid platform-specific columns in database
|
||||
- Use `provider_data` JSON field if platform-specific data needed
|
||||
- Keep `platform` field as simple string identifier
|
||||
|
||||
### 4. **Worker Task Migration**
|
||||
According to user requirements, migrate platform-specific tasks:
|
||||
```
|
||||
video_platforms/
|
||||
├── whereby/
|
||||
│ ├── client.py (moved from whereby.py)
|
||||
│ └── tasks.py (moved from worker/whereby_tasks.py)
|
||||
├── daily/
|
||||
│ ├── client.py (moved from daily.py)
|
||||
│ └── tasks.py (moved from worker/daily_tasks.py)
|
||||
└── jitsi/
|
||||
├── client.py (new JitsiClient)
|
||||
└── tasks.py (new Jitsi recording tasks)
|
||||
```
|
||||
|
||||
### 5. **Webhook Architecture**
|
||||
- Create `views/jitsi.py` for Jitsi-specific webhooks
|
||||
- Follow the same signature verification pattern
|
||||
- Reuse existing participant tracking logic
|
||||
|
||||
## Implementation Checklist for Jitsi
|
||||
|
||||
- [ ] Create `video_platforms/jitsi/` directory structure
|
||||
- [ ] Implement `JitsiClient` following the abstract interface
|
||||
- [ ] Add Jitsi settings to configuration
|
||||
- [ ] Register Jitsi platform in factory/registry
|
||||
- [ ] Create Jitsi webhook endpoint
|
||||
- [ ] Implement JWT token generation for room access
|
||||
- [ ] Add Jitsi recording processing tasks
|
||||
- [ ] Create comprehensive test suite
|
||||
- [ ] Update database migrations for platform field
|
||||
- [ ] Document Jitsi-specific configuration
|
||||
|
||||
## Conclusion
|
||||
|
||||
The video platforms refactoring in PR #529 provides an excellent foundation for adding Jitsi support. The architecture is well-designed with clear separation of concerns, consistent interfaces, and excellent extensibility. The daily.co implementation demonstrates how to add a new platform while maintaining backward compatibility and providing gradual migration capabilities.
|
||||
|
||||
The pattern should be directly applicable to Jitsi integration, with the main differences being:
|
||||
- JWT-based authentication instead of API keys
|
||||
- Different webhook event formats
|
||||
- Jibri recording pipeline integration
|
||||
- Self-hosted deployment considerations
|
||||
|
||||
This architecture successfully achieves the user's goals of:
|
||||
1. Settings-based configuration
|
||||
2. Generic database fields (no provider-specific columns)
|
||||
3. Platform isolation in separate directories
|
||||
4. Worker task organization within platform folders
|
||||
33
gpu/modal_deployments/.gitignore
vendored
33
gpu/modal_deployments/.gitignore
vendored
@@ -1,33 +0,0 @@
|
||||
# OS / Editor
|
||||
.DS_Store
|
||||
.vscode/
|
||||
.idea/
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
|
||||
# Env and secrets
|
||||
.env
|
||||
.env.*
|
||||
*.env
|
||||
*.secret
|
||||
|
||||
# Build / dist
|
||||
build/
|
||||
dist/
|
||||
.eggs/
|
||||
*.egg-info/
|
||||
|
||||
# Coverage / test
|
||||
.pytest_cache/
|
||||
.coverage*
|
||||
htmlcov/
|
||||
|
||||
# Modal local state (if any)
|
||||
modal_mounts/
|
||||
.modal_cache/
|
||||
@@ -1,2 +0,0 @@
|
||||
REFLECTOR_GPU_APIKEY=
|
||||
HF_TOKEN=
|
||||
38
gpu/self_hosted/.gitignore
vendored
38
gpu/self_hosted/.gitignore
vendored
@@ -1,38 +0,0 @@
|
||||
cache/
|
||||
|
||||
# OS / Editor
|
||||
.DS_Store
|
||||
.vscode/
|
||||
.idea/
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# Env and secrets
|
||||
.env
|
||||
*.env
|
||||
*.secret
|
||||
HF_TOKEN
|
||||
REFLECTOR_GPU_APIKEY
|
||||
|
||||
# Virtual env / uv
|
||||
.venv/
|
||||
venv/
|
||||
ENV/
|
||||
uv/
|
||||
|
||||
# Build / dist
|
||||
build/
|
||||
dist/
|
||||
.eggs/
|
||||
*.egg-info/
|
||||
|
||||
# Coverage / test
|
||||
.pytest_cache/
|
||||
.coverage*
|
||||
htmlcov/
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
@@ -1,46 +0,0 @@
|
||||
FROM python:3.12-slim
|
||||
|
||||
ENV PYTHONUNBUFFERED=1 \
|
||||
UV_LINK_MODE=copy \
|
||||
UV_NO_CACHE=1
|
||||
|
||||
WORKDIR /tmp
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y \
|
||||
ffmpeg \
|
||||
curl \
|
||||
ca-certificates \
|
||||
gnupg \
|
||||
wget \
|
||||
&& apt-get clean
|
||||
# Add NVIDIA CUDA repo for Debian 12 (bookworm) and install cuDNN 9 for CUDA 12
|
||||
ADD https://developer.download.nvidia.com/compute/cuda/repos/debian12/x86_64/cuda-keyring_1.1-1_all.deb /cuda-keyring.deb
|
||||
RUN dpkg -i /cuda-keyring.deb \
|
||||
&& rm /cuda-keyring.deb \
|
||||
&& apt-get update \
|
||||
&& apt-get install -y --no-install-recommends \
|
||||
cuda-cudart-12-6 \
|
||||
libcublas-12-6 \
|
||||
libcudnn9-cuda-12 \
|
||||
libcudnn9-dev-cuda-12 \
|
||||
&& apt-get clean \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
ADD https://astral.sh/uv/install.sh /uv-installer.sh
|
||||
RUN sh /uv-installer.sh && rm /uv-installer.sh
|
||||
ENV PATH="/root/.local/bin/:$PATH"
|
||||
ENV LD_LIBRARY_PATH="/usr/local/cuda/lib64:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
|
||||
|
||||
RUN mkdir -p /app
|
||||
WORKDIR /app
|
||||
COPY pyproject.toml uv.lock /app/
|
||||
|
||||
|
||||
COPY ./app /app/app
|
||||
COPY ./main.py /app/
|
||||
COPY ./runserver.sh /app/
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
CMD ["sh", "/app/runserver.sh"]
|
||||
|
||||
|
||||
@@ -1,73 +0,0 @@
|
||||
# Self-hosted Model API
|
||||
|
||||
Run transcription, translation, and diarization services compatible with Reflector's GPU Model API. Works on CPU or GPU.
|
||||
|
||||
Environment variables
|
||||
|
||||
- REFLECTOR_GPU_APIKEY: Optional Bearer token. If unset, auth is disabled.
|
||||
- HF_TOKEN: Optional. Required for diarization to download pyannote pipelines
|
||||
|
||||
Requirements
|
||||
|
||||
- FFmpeg must be installed and on PATH (used for URL-based and segmented transcription)
|
||||
- Python 3.12+
|
||||
- NVIDIA GPU optional. If available, it will be used automatically
|
||||
|
||||
Local run
|
||||
Set env vars in self_hosted/.env file
|
||||
uv sync
|
||||
|
||||
uv run uvicorn main:app --host 0.0.0.0 --port 8000
|
||||
|
||||
Authentication
|
||||
|
||||
- If REFLECTOR_GPU_APIKEY is set, include header: Authorization: Bearer <key>
|
||||
|
||||
Endpoints
|
||||
|
||||
- POST /v1/audio/transcriptions
|
||||
|
||||
- multipart/form-data
|
||||
- fields: file (single file) OR files[] (multiple files), language, batch (true/false)
|
||||
- response: single { text, words, filename } or { results: [ ... ] }
|
||||
|
||||
- POST /v1/audio/transcriptions-from-url
|
||||
|
||||
- application/json
|
||||
- body: { audio_file_url, language, timestamp_offset }
|
||||
- response: { text, words }
|
||||
|
||||
- POST /translate
|
||||
|
||||
- text: query parameter
|
||||
- body (application/json): { source_language, target_language }
|
||||
- response: { text: { <src>: original, <tgt>: translated } }
|
||||
|
||||
- POST /diarize
|
||||
- query parameters: audio_file_url, timestamp (optional)
|
||||
- requires HF_TOKEN to be set (for pyannote)
|
||||
- response: { diarization: [ { start, end, speaker } ] }
|
||||
|
||||
OpenAPI docs
|
||||
|
||||
- Visit /docs when the server is running
|
||||
|
||||
Docker
|
||||
|
||||
- Not yet provided in this directory. A Dockerfile will be added later. For now, use Local run above
|
||||
|
||||
Conformance tests
|
||||
|
||||
# From this directory
|
||||
|
||||
TRANSCRIPT_URL=http://localhost:8000 \
|
||||
TRANSCRIPT_API_KEY=dev-key \
|
||||
uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_transcript.py
|
||||
|
||||
TRANSLATION_URL=http://localhost:8000 \
|
||||
TRANSLATION_API_KEY=dev-key \
|
||||
uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_translation.py
|
||||
|
||||
DIARIZATION_URL=http://localhost:8000 \
|
||||
DIARIZATION_API_KEY=dev-key \
|
||||
uv run -m pytest -m model_api --no-cov ../../server/tests/test_model_api_diarization.py
|
||||
@@ -1,19 +0,0 @@
|
||||
import os
|
||||
|
||||
from fastapi import Depends, HTTPException, status
|
||||
from fastapi.security import OAuth2PasswordBearer
|
||||
|
||||
oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
|
||||
|
||||
|
||||
def apikey_auth(apikey: str = Depends(oauth2_scheme)):
|
||||
required_key = os.environ.get("REFLECTOR_GPU_APIKEY")
|
||||
if not required_key:
|
||||
return
|
||||
if apikey == required_key:
|
||||
return
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
detail="Invalid API key",
|
||||
headers={"WWW-Authenticate": "Bearer"},
|
||||
)
|
||||
@@ -1,12 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
SUPPORTED_FILE_EXTENSIONS = ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"]
|
||||
SAMPLE_RATE = 16000
|
||||
VAD_CONFIG = {
|
||||
"batch_max_duration": 30.0,
|
||||
"silence_padding": 0.5,
|
||||
"window_size": 512,
|
||||
}
|
||||
|
||||
# App-level paths
|
||||
UPLOADS_PATH = Path("/tmp/whisper-uploads")
|
||||
@@ -1,30 +0,0 @@
|
||||
from contextlib import asynccontextmanager
|
||||
|
||||
from fastapi import FastAPI
|
||||
|
||||
from .routers.diarization import router as diarization_router
|
||||
from .routers.transcription import router as transcription_router
|
||||
from .routers.translation import router as translation_router
|
||||
from .services.transcriber import WhisperService
|
||||
from .services.diarizer import PyannoteDiarizationService
|
||||
from .utils import ensure_dirs
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
ensure_dirs()
|
||||
whisper_service = WhisperService()
|
||||
whisper_service.load()
|
||||
app.state.whisper = whisper_service
|
||||
diarization_service = PyannoteDiarizationService()
|
||||
diarization_service.load()
|
||||
app.state.diarizer = diarization_service
|
||||
yield
|
||||
|
||||
|
||||
def create_app() -> FastAPI:
|
||||
app = FastAPI(lifespan=lifespan)
|
||||
app.include_router(transcription_router)
|
||||
app.include_router(translation_router)
|
||||
app.include_router(diarization_router)
|
||||
return app
|
||||
@@ -1,30 +0,0 @@
|
||||
from typing import List
|
||||
|
||||
from fastapi import APIRouter, Depends, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from ..auth import apikey_auth
|
||||
from ..services.diarizer import PyannoteDiarizationService
|
||||
from ..utils import download_audio_file
|
||||
|
||||
router = APIRouter(tags=["diarization"])
|
||||
|
||||
|
||||
class DiarizationSegment(BaseModel):
|
||||
start: float
|
||||
end: float
|
||||
speaker: int
|
||||
|
||||
|
||||
class DiarizationResponse(BaseModel):
|
||||
diarization: List[DiarizationSegment]
|
||||
|
||||
|
||||
@router.post(
|
||||
"/diarize", dependencies=[Depends(apikey_auth)], response_model=DiarizationResponse
|
||||
)
|
||||
def diarize(request: Request, audio_file_url: str, timestamp: float = 0.0):
|
||||
with download_audio_file(audio_file_url) as (file_path, _ext):
|
||||
file_path = str(file_path)
|
||||
diarizer: PyannoteDiarizationService = request.app.state.diarizer
|
||||
return diarizer.diarize_file(file_path, timestamp=timestamp)
|
||||
@@ -1,109 +0,0 @@
|
||||
import uuid
|
||||
from typing import Optional, Union
|
||||
|
||||
from fastapi import APIRouter, Body, Depends, Form, HTTPException, Request, UploadFile
|
||||
from pydantic import BaseModel
|
||||
from pathlib import Path
|
||||
from ..auth import apikey_auth
|
||||
from ..config import SUPPORTED_FILE_EXTENSIONS, UPLOADS_PATH
|
||||
from ..services.transcriber import MODEL_NAME
|
||||
from ..utils import cleanup_uploaded_files, download_audio_file
|
||||
|
||||
router = APIRouter(prefix="/v1/audio", tags=["transcription"])
|
||||
|
||||
|
||||
class WordTiming(BaseModel):
|
||||
word: str
|
||||
start: float
|
||||
end: float
|
||||
|
||||
|
||||
class TranscriptResult(BaseModel):
|
||||
text: str
|
||||
words: list[WordTiming]
|
||||
filename: Optional[str] = None
|
||||
|
||||
|
||||
class TranscriptBatchResponse(BaseModel):
|
||||
results: list[TranscriptResult]
|
||||
|
||||
|
||||
@router.post(
|
||||
"/transcriptions",
|
||||
dependencies=[Depends(apikey_auth)],
|
||||
response_model=Union[TranscriptResult, TranscriptBatchResponse],
|
||||
)
|
||||
def transcribe(
|
||||
request: Request,
|
||||
file: UploadFile = None,
|
||||
files: list[UploadFile] | None = None,
|
||||
model: str = Form(MODEL_NAME),
|
||||
language: str = Form("en"),
|
||||
batch: bool = Form(False),
|
||||
):
|
||||
service = request.app.state.whisper
|
||||
if not file and not files:
|
||||
raise HTTPException(
|
||||
status_code=400, detail="Either 'file' or 'files' parameter is required"
|
||||
)
|
||||
if batch and not files:
|
||||
raise HTTPException(
|
||||
status_code=400, detail="Batch transcription requires 'files'"
|
||||
)
|
||||
|
||||
upload_files = [file] if file else files
|
||||
|
||||
uploaded_paths: list[Path] = []
|
||||
with cleanup_uploaded_files(uploaded_paths):
|
||||
for upload_file in upload_files:
|
||||
audio_suffix = upload_file.filename.split(".")[-1].lower()
|
||||
if audio_suffix not in SUPPORTED_FILE_EXTENSIONS:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=(
|
||||
f"Unsupported audio format. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
|
||||
),
|
||||
)
|
||||
unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
|
||||
file_path = UPLOADS_PATH / unique_filename
|
||||
with open(file_path, "wb") as f:
|
||||
content = upload_file.file.read()
|
||||
f.write(content)
|
||||
uploaded_paths.append(file_path)
|
||||
|
||||
if batch and len(upload_files) > 1:
|
||||
results = []
|
||||
for path in uploaded_paths:
|
||||
result = service.transcribe_file(str(path), language=language)
|
||||
result["filename"] = path.name
|
||||
results.append(result)
|
||||
return {"results": results}
|
||||
|
||||
results = []
|
||||
for path in uploaded_paths:
|
||||
result = service.transcribe_file(str(path), language=language)
|
||||
result["filename"] = path.name
|
||||
results.append(result)
|
||||
|
||||
return {"results": results} if len(results) > 1 else results[0]
|
||||
|
||||
|
||||
@router.post(
|
||||
"/transcriptions-from-url",
|
||||
dependencies=[Depends(apikey_auth)],
|
||||
response_model=TranscriptResult,
|
||||
)
|
||||
def transcribe_from_url(
|
||||
request: Request,
|
||||
audio_file_url: str = Body(..., description="URL of the audio file to transcribe"),
|
||||
model: str = Body(MODEL_NAME),
|
||||
language: str = Body("en"),
|
||||
timestamp_offset: float = Body(0.0),
|
||||
):
|
||||
service = request.app.state.whisper
|
||||
with download_audio_file(audio_file_url) as (file_path, _ext):
|
||||
file_path = str(file_path)
|
||||
result = service.transcribe_vad_url_segment(
|
||||
file_path=file_path, timestamp_offset=timestamp_offset, language=language
|
||||
)
|
||||
return result
|
||||
@@ -1,28 +0,0 @@
|
||||
from typing import Dict
|
||||
|
||||
from fastapi import APIRouter, Body, Depends
|
||||
from pydantic import BaseModel
|
||||
|
||||
from ..auth import apikey_auth
|
||||
from ..services.translator import TextTranslatorService
|
||||
|
||||
router = APIRouter(tags=["translation"])
|
||||
|
||||
translator = TextTranslatorService()
|
||||
|
||||
|
||||
class TranslationResponse(BaseModel):
|
||||
text: Dict[str, str]
|
||||
|
||||
|
||||
@router.post(
|
||||
"/translate",
|
||||
dependencies=[Depends(apikey_auth)],
|
||||
response_model=TranslationResponse,
|
||||
)
|
||||
def translate(
|
||||
text: str,
|
||||
source_language: str = Body("en"),
|
||||
target_language: str = Body("fr"),
|
||||
):
|
||||
return translator.translate(text, source_language, target_language)
|
||||
@@ -1,42 +0,0 @@
|
||||
import os
|
||||
import threading
|
||||
|
||||
import torch
|
||||
import torchaudio
|
||||
from pyannote.audio import Pipeline
|
||||
|
||||
|
||||
class PyannoteDiarizationService:
|
||||
def __init__(self):
|
||||
self._pipeline = None
|
||||
self._device = "cpu"
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def load(self):
|
||||
self._device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
self._pipeline = Pipeline.from_pretrained(
|
||||
"pyannote/speaker-diarization-3.1",
|
||||
use_auth_token=os.environ.get("HF_TOKEN"),
|
||||
)
|
||||
self._pipeline.to(torch.device(self._device))
|
||||
|
||||
def diarize_file(self, file_path: str, timestamp: float = 0.0) -> dict:
|
||||
if self._pipeline is None:
|
||||
self.load()
|
||||
waveform, sample_rate = torchaudio.load(file_path)
|
||||
with self._lock:
|
||||
diarization = self._pipeline(
|
||||
{"waveform": waveform, "sample_rate": sample_rate}
|
||||
)
|
||||
words = []
|
||||
for diarization_segment, _, speaker in diarization.itertracks(yield_label=True):
|
||||
words.append(
|
||||
{
|
||||
"start": round(timestamp + diarization_segment.start, 3),
|
||||
"end": round(timestamp + diarization_segment.end, 3),
|
||||
"speaker": int(speaker[-2:])
|
||||
if speaker and speaker[-2:].isdigit()
|
||||
else 0,
|
||||
}
|
||||
)
|
||||
return {"diarization": words}
|
||||
@@ -1,208 +0,0 @@
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import threading
|
||||
from typing import Generator
|
||||
|
||||
import faster_whisper
|
||||
import librosa
|
||||
import numpy as np
|
||||
import torch
|
||||
from fastapi import HTTPException
|
||||
from silero_vad import VADIterator, load_silero_vad
|
||||
|
||||
from ..config import SAMPLE_RATE, VAD_CONFIG
|
||||
|
||||
# Whisper configuration (service-local defaults)
|
||||
MODEL_NAME = "large-v2"
|
||||
# None delegates compute type to runtime: float16 on CUDA, int8 on CPU
|
||||
MODEL_COMPUTE_TYPE = None
|
||||
MODEL_NUM_WORKERS = 1
|
||||
CACHE_PATH = os.path.join(os.path.expanduser("~"), ".cache", "reflector-whisper")
|
||||
from ..utils import NoStdStreams
|
||||
|
||||
|
||||
class WhisperService:
|
||||
def __init__(self):
|
||||
self.model = None
|
||||
self.device = "cpu"
|
||||
self.lock = threading.Lock()
|
||||
|
||||
def load(self):
|
||||
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||
compute_type = MODEL_COMPUTE_TYPE or (
|
||||
"float16" if self.device == "cuda" else "int8"
|
||||
)
|
||||
self.model = faster_whisper.WhisperModel(
|
||||
MODEL_NAME,
|
||||
device=self.device,
|
||||
compute_type=compute_type,
|
||||
num_workers=MODEL_NUM_WORKERS,
|
||||
download_root=CACHE_PATH,
|
||||
)
|
||||
|
||||
def pad_audio(self, audio_array, sample_rate: int = SAMPLE_RATE):
|
||||
audio_duration = len(audio_array) / sample_rate
|
||||
if audio_duration < VAD_CONFIG["silence_padding"]:
|
||||
silence_samples = int(sample_rate * VAD_CONFIG["silence_padding"])
|
||||
silence = np.zeros(silence_samples, dtype=np.float32)
|
||||
return np.concatenate([audio_array, silence])
|
||||
return audio_array
|
||||
|
||||
def enforce_word_timing_constraints(self, words: list[dict]) -> list[dict]:
|
||||
if len(words) <= 1:
|
||||
return words
|
||||
enforced: list[dict] = []
|
||||
for i, word in enumerate(words):
|
||||
current = dict(word)
|
||||
if i < len(words) - 1:
|
||||
next_start = words[i + 1]["start"]
|
||||
if current["end"] > next_start:
|
||||
current["end"] = next_start
|
||||
enforced.append(current)
|
||||
return enforced
|
||||
|
||||
def transcribe_file(self, file_path: str, language: str = "en") -> dict:
|
||||
input_for_model: str | "object" = file_path
|
||||
try:
|
||||
audio_array, _sample_rate = librosa.load(
|
||||
file_path, sr=SAMPLE_RATE, mono=True
|
||||
)
|
||||
if len(audio_array) / float(SAMPLE_RATE) < VAD_CONFIG["silence_padding"]:
|
||||
input_for_model = self.pad_audio(audio_array, SAMPLE_RATE)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
with self.lock:
|
||||
with NoStdStreams():
|
||||
segments, _ = self.model.transcribe(
|
||||
input_for_model,
|
||||
language=language,
|
||||
beam_size=5,
|
||||
word_timestamps=True,
|
||||
vad_filter=True,
|
||||
vad_parameters={"min_silence_duration_ms": 500},
|
||||
)
|
||||
|
||||
segments = list(segments)
|
||||
text = "".join(segment.text for segment in segments).strip()
|
||||
words = [
|
||||
{
|
||||
"word": word.word,
|
||||
"start": round(float(word.start), 2),
|
||||
"end": round(float(word.end), 2),
|
||||
}
|
||||
for segment in segments
|
||||
for word in segment.words
|
||||
]
|
||||
words = self.enforce_word_timing_constraints(words)
|
||||
return {"text": text, "words": words}
|
||||
|
||||
def transcribe_vad_url_segment(
|
||||
self, file_path: str, timestamp_offset: float = 0.0, language: str = "en"
|
||||
) -> dict:
|
||||
def load_audio_via_ffmpeg(input_path: str, sample_rate: int) -> np.ndarray:
|
||||
ffmpeg_bin = shutil.which("ffmpeg") or "ffmpeg"
|
||||
cmd = [
|
||||
ffmpeg_bin,
|
||||
"-nostdin",
|
||||
"-threads",
|
||||
"1",
|
||||
"-i",
|
||||
input_path,
|
||||
"-f",
|
||||
"f32le",
|
||||
"-acodec",
|
||||
"pcm_f32le",
|
||||
"-ac",
|
||||
"1",
|
||||
"-ar",
|
||||
str(sample_rate),
|
||||
"pipe:1",
|
||||
]
|
||||
try:
|
||||
proc = subprocess.run(
|
||||
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, check=True
|
||||
)
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=400, detail=f"ffmpeg failed: {e}")
|
||||
audio = np.frombuffer(proc.stdout, dtype=np.float32)
|
||||
return audio
|
||||
|
||||
def vad_segments(
|
||||
audio_array,
|
||||
sample_rate: int = SAMPLE_RATE,
|
||||
window_size: int = VAD_CONFIG["window_size"],
|
||||
) -> Generator[tuple[float, float], None, None]:
|
||||
vad_model = load_silero_vad(onnx=False)
|
||||
iterator = VADIterator(vad_model, sampling_rate=sample_rate)
|
||||
start = None
|
||||
for i in range(0, len(audio_array), window_size):
|
||||
chunk = audio_array[i : i + window_size]
|
||||
if len(chunk) < window_size:
|
||||
chunk = np.pad(
|
||||
chunk, (0, window_size - len(chunk)), mode="constant"
|
||||
)
|
||||
speech = iterator(chunk)
|
||||
if not speech:
|
||||
continue
|
||||
if "start" in speech:
|
||||
start = speech["start"]
|
||||
continue
|
||||
if "end" in speech and start is not None:
|
||||
end = speech["end"]
|
||||
yield (start / float(SAMPLE_RATE), end / float(SAMPLE_RATE))
|
||||
start = None
|
||||
iterator.reset_states()
|
||||
|
||||
audio_array = load_audio_via_ffmpeg(file_path, SAMPLE_RATE)
|
||||
|
||||
merged_batches: list[tuple[float, float]] = []
|
||||
batch_start = None
|
||||
batch_end = None
|
||||
max_duration = VAD_CONFIG["batch_max_duration"]
|
||||
for seg_start, seg_end in vad_segments(audio_array):
|
||||
if batch_start is None:
|
||||
batch_start, batch_end = seg_start, seg_end
|
||||
continue
|
||||
if seg_end - batch_start <= max_duration:
|
||||
batch_end = seg_end
|
||||
else:
|
||||
merged_batches.append((batch_start, batch_end))
|
||||
batch_start, batch_end = seg_start, seg_end
|
||||
if batch_start is not None and batch_end is not None:
|
||||
merged_batches.append((batch_start, batch_end))
|
||||
|
||||
all_text = []
|
||||
all_words = []
|
||||
for start_time, end_time in merged_batches:
|
||||
s_idx = int(start_time * SAMPLE_RATE)
|
||||
e_idx = int(end_time * SAMPLE_RATE)
|
||||
segment = audio_array[s_idx:e_idx]
|
||||
segment = self.pad_audio(segment, SAMPLE_RATE)
|
||||
with self.lock:
|
||||
segments, _ = self.model.transcribe(
|
||||
segment,
|
||||
language=language,
|
||||
beam_size=5,
|
||||
word_timestamps=True,
|
||||
vad_filter=True,
|
||||
vad_parameters={"min_silence_duration_ms": 500},
|
||||
)
|
||||
segments = list(segments)
|
||||
text = "".join(seg.text for seg in segments).strip()
|
||||
words = [
|
||||
{
|
||||
"word": w.word,
|
||||
"start": round(float(w.start) + start_time + timestamp_offset, 2),
|
||||
"end": round(float(w.end) + start_time + timestamp_offset, 2),
|
||||
}
|
||||
for seg in segments
|
||||
for w in seg.words
|
||||
]
|
||||
if text:
|
||||
all_text.append(text)
|
||||
all_words.extend(words)
|
||||
|
||||
all_words = self.enforce_word_timing_constraints(all_words)
|
||||
return {"text": " ".join(all_text), "words": all_words}
|
||||
@@ -1,44 +0,0 @@
|
||||
import threading
|
||||
|
||||
from transformers import MarianMTModel, MarianTokenizer, pipeline
|
||||
|
||||
|
||||
class TextTranslatorService:
|
||||
"""Simple text-to-text translator using HuggingFace MarianMT models.
|
||||
|
||||
This mirrors the modal translator API shape but uses text translation only.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self._pipeline = None
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def load(self, source_language: str = "en", target_language: str = "fr"):
|
||||
# Pick a default MarianMT model pair if available; fall back to Helsinki-NLP en->fr
|
||||
model_name = self._resolve_model_name(source_language, target_language)
|
||||
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
||||
model = MarianMTModel.from_pretrained(model_name)
|
||||
self._pipeline = pipeline("translation", model=model, tokenizer=tokenizer)
|
||||
|
||||
def _resolve_model_name(self, src: str, tgt: str) -> str:
|
||||
# Minimal mapping; extend as needed
|
||||
pair = (src.lower(), tgt.lower())
|
||||
mapping = {
|
||||
("en", "fr"): "Helsinki-NLP/opus-mt-en-fr",
|
||||
("fr", "en"): "Helsinki-NLP/opus-mt-fr-en",
|
||||
("en", "es"): "Helsinki-NLP/opus-mt-en-es",
|
||||
("es", "en"): "Helsinki-NLP/opus-mt-es-en",
|
||||
("en", "de"): "Helsinki-NLP/opus-mt-en-de",
|
||||
("de", "en"): "Helsinki-NLP/opus-mt-de-en",
|
||||
}
|
||||
return mapping.get(pair, "Helsinki-NLP/opus-mt-en-fr")
|
||||
|
||||
def translate(self, text: str, source_language: str, target_language: str) -> dict:
|
||||
if self._pipeline is None:
|
||||
self.load(source_language, target_language)
|
||||
with self._lock:
|
||||
results = self._pipeline(
|
||||
text, src_lang=source_language, tgt_lang=target_language
|
||||
)
|
||||
translated = results[0]["translation_text"] if results else ""
|
||||
return {"text": {source_language: text, target_language: translated}}
|
||||
@@ -1,107 +0,0 @@
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import uuid
|
||||
from contextlib import contextmanager
|
||||
from typing import Mapping
|
||||
from urllib.parse import urlparse
|
||||
from pathlib import Path
|
||||
|
||||
import requests
|
||||
from fastapi import HTTPException
|
||||
|
||||
from .config import SUPPORTED_FILE_EXTENSIONS, UPLOADS_PATH
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class NoStdStreams:
|
||||
def __init__(self):
|
||||
self.devnull = open(os.devnull, "w")
|
||||
|
||||
def __enter__(self):
|
||||
self._stdout, self._stderr = sys.stdout, sys.stderr
|
||||
self._stdout.flush()
|
||||
self._stderr.flush()
|
||||
sys.stdout, sys.stderr = self.devnull, self.devnull
|
||||
|
||||
def __exit__(self, exc_type, exc_value, traceback):
|
||||
sys.stdout, sys.stderr = self._stdout, self._stderr
|
||||
self.devnull.close()
|
||||
|
||||
|
||||
def ensure_dirs():
|
||||
UPLOADS_PATH.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
||||
def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
|
||||
url_path = urlparse(url).path
|
||||
for ext in SUPPORTED_FILE_EXTENSIONS:
|
||||
if url_path.lower().endswith(f".{ext}"):
|
||||
return ext
|
||||
|
||||
content_type = headers.get("content-type", "").lower()
|
||||
if "audio/mpeg" in content_type or "audio/mp3" in content_type:
|
||||
return "mp3"
|
||||
if "audio/wav" in content_type:
|
||||
return "wav"
|
||||
if "audio/mp4" in content_type:
|
||||
return "mp4"
|
||||
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=(
|
||||
f"Unsupported audio format for URL. Supported extensions: {', '.join(SUPPORTED_FILE_EXTENSIONS)}"
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def download_audio_to_uploads(audio_file_url: str) -> tuple[Path, str]:
|
||||
response = requests.head(audio_file_url, allow_redirects=True)
|
||||
if response.status_code == 404:
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
response = requests.get(audio_file_url, allow_redirects=True)
|
||||
response.raise_for_status()
|
||||
|
||||
audio_suffix = detect_audio_format(audio_file_url, response.headers)
|
||||
unique_filename = f"{uuid.uuid4()}.{audio_suffix}"
|
||||
file_path: Path = UPLOADS_PATH / unique_filename
|
||||
|
||||
with open(file_path, "wb") as f:
|
||||
f.write(response.content)
|
||||
|
||||
return file_path, audio_suffix
|
||||
|
||||
|
||||
@contextmanager
|
||||
def download_audio_file(audio_file_url: str):
|
||||
"""Download an audio file to UPLOADS_PATH and remove it after use.
|
||||
|
||||
Yields (file_path: Path, audio_suffix: str).
|
||||
"""
|
||||
file_path, audio_suffix = download_audio_to_uploads(audio_file_url)
|
||||
try:
|
||||
yield file_path, audio_suffix
|
||||
finally:
|
||||
try:
|
||||
file_path.unlink(missing_ok=True)
|
||||
except Exception as e:
|
||||
logger.error("Error deleting temporary file %s: %s", file_path, e)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def cleanup_uploaded_files(file_paths: list[Path]):
|
||||
"""Ensure provided file paths are removed after use.
|
||||
|
||||
The provided list can be populated inside the context; all present entries
|
||||
at exit will be deleted.
|
||||
"""
|
||||
try:
|
||||
yield file_paths
|
||||
finally:
|
||||
for path in list(file_paths):
|
||||
try:
|
||||
path.unlink(missing_ok=True)
|
||||
except Exception as e:
|
||||
logger.error("Error deleting temporary file %s: %s", path, e)
|
||||
@@ -1,10 +0,0 @@
|
||||
services:
|
||||
reflector_gpu:
|
||||
build:
|
||||
context: .
|
||||
ports:
|
||||
- "8000:8000"
|
||||
env_file:
|
||||
- .env
|
||||
volumes:
|
||||
- ./cache:/root/.cache
|
||||
@@ -1,3 +0,0 @@
|
||||
from app.factory import create_app
|
||||
|
||||
app = create_app()
|
||||
@@ -1,19 +0,0 @@
|
||||
[project]
|
||||
name = "reflector-gpu"
|
||||
version = "0.1.0"
|
||||
description = "Self-hosted GPU service for speech transcription, diarization, and translation via FastAPI."
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.12"
|
||||
dependencies = [
|
||||
"fastapi[standard]>=0.116.1",
|
||||
"uvicorn[standard]>=0.30.0",
|
||||
"torch>=2.3.0",
|
||||
"faster-whisper>=1.1.0",
|
||||
"librosa==0.10.1",
|
||||
"numpy<2",
|
||||
"silero-vad==5.1.0",
|
||||
"transformers>=4.35.0",
|
||||
"sentencepiece",
|
||||
"pyannote.audio==3.1.0",
|
||||
"torchaudio>=2.3.0",
|
||||
]
|
||||
@@ -1,17 +0,0 @@
|
||||
#!/bin/sh
|
||||
set -e
|
||||
|
||||
export PATH="/root/.local/bin:$PATH"
|
||||
cd /app
|
||||
|
||||
# Install Python dependencies at runtime (first run or when FORCE_SYNC=1)
|
||||
if [ ! -d "/app/.venv" ] || [ "$FORCE_SYNC" = "1" ]; then
|
||||
echo "[startup] Installing Python dependencies with uv..."
|
||||
uv sync --compile-bytecode --locked
|
||||
else
|
||||
echo "[startup] Using existing virtual environment at /app/.venv"
|
||||
fi
|
||||
|
||||
exec uv run uvicorn main:app --host 0.0.0.0 --port 8000
|
||||
|
||||
|
||||
3013
gpu/self_hosted/uv.lock
generated
3013
gpu/self_hosted/uv.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -1,613 +0,0 @@
|
||||
# Daily.co Integration Test Plan
|
||||
|
||||
## ✅ IMPLEMENTATION STATUS: Real Transcription Active
|
||||
|
||||
**This test validates Daily.co multitrack recording integration with REAL transcription/diarization.**
|
||||
|
||||
The implementation includes complete audio processing pipeline:
|
||||
- **Multitrack recordings** from Daily.co S3 (separate audio stream per participant)
|
||||
- **PyAV-based audio mixdown** with PTS-based track alignment
|
||||
- **Real transcription** via Modal GPU backend (Whisper)
|
||||
- **Real diarization** via Modal GPU backend (speaker identification)
|
||||
- **Per-track transcription** with timestamp synchronization
|
||||
- **Complete database entities** (recording, transcript, topics, participants, words)
|
||||
|
||||
**Processing pipeline** (`PipelineMainMultitrack`):
|
||||
1. Download all audio tracks from Daily.co S3
|
||||
2. Align tracks by PTS (presentation timestamp) to handle late joiners
|
||||
3. Mix tracks into single audio file for unified playback
|
||||
4. Transcribe each track individually with proper offset handling
|
||||
5. Perform diarization on mixed audio
|
||||
6. Generate topics, summaries, and word-level timestamps
|
||||
7. Convert audio to MP3 and generate waveform visualization
|
||||
|
||||
**Note:** A stub processor (`process_daily_recording`) exists for testing webhook flow without GPU costs, but the production code path uses `process_multitrack_recording` with full ML pipeline.
|
||||
|
||||
---
|
||||
|
||||
## Prerequisites
|
||||
|
||||
**1. Environment Variables** (check in `.env.development.local`):
|
||||
```bash
|
||||
# Daily.co API Configuration
|
||||
DAILY_API_KEY=<key>
|
||||
DAILY_SUBDOMAIN=monadical
|
||||
DAILY_WEBHOOK_SECRET=<base64-encoded-secret>
|
||||
AWS_DAILY_S3_BUCKET=reflector-dailyco-local
|
||||
AWS_DAILY_S3_REGION=us-east-1
|
||||
AWS_DAILY_ROLE_ARN=arn:aws:iam::950402358378:role/DailyCo
|
||||
DAILY_MIGRATION_ENABLED=true
|
||||
DAILY_MIGRATION_ROOM_IDS=["552640fd-16f2-4162-9526-8cf40cd2357e"]
|
||||
|
||||
# Transcription/Diarization Backend (Required for real processing)
|
||||
DIARIZATION_BACKEND=modal
|
||||
DIARIZATION_MODAL_API_KEY=<modal-api-key>
|
||||
# TRANSCRIPTION_BACKEND is not explicitly set (uses default/modal)
|
||||
```
|
||||
|
||||
**2. Services Running:**
|
||||
```bash
|
||||
docker compose ps # server, postgres, redis, worker, beat should be UP
|
||||
```
|
||||
|
||||
**IMPORTANT:** Worker and beat services MUST be running for transcription processing:
|
||||
```bash
|
||||
docker compose up -d worker beat
|
||||
```
|
||||
|
||||
**3. ngrok Tunnel for Webhooks:**
|
||||
```bash
|
||||
# Start ngrok (if not already running)
|
||||
ngrok http 1250 --log=stdout > /tmp/ngrok.log 2>&1 &
|
||||
|
||||
# Get public URL
|
||||
curl -s http://localhost:4040/api/tunnels | python3 -c "import sys, json; data=json.load(sys.stdin); print(data['tunnels'][0]['public_url'])"
|
||||
```
|
||||
|
||||
**Current ngrok URL:** `https://0503947384a3.ngrok-free.app` (as of last registration)
|
||||
|
||||
**4. Webhook Created:**
|
||||
```bash
|
||||
cd server
|
||||
uv run python scripts/recreate_daily_webhook.py https://0503947384a3.ngrok-free.app/v1/daily/webhook
|
||||
# Verify: "Created webhook <uuid> (state: ACTIVE)"
|
||||
```
|
||||
|
||||
**Current webhook status:** ✅ ACTIVE (webhook ID: dad5ad16-ceca-488e-8fc5-dae8650b51d0)
|
||||
|
||||
---
|
||||
|
||||
## Test 1: Database Configuration
|
||||
|
||||
**Check room platform:**
|
||||
```bash
|
||||
docker-compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT id, name, platform, recording_type FROM room WHERE name = 'test2';"
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```
|
||||
id: 552640fd-16f2-4162-9526-8cf40cd2357e
|
||||
name: test2
|
||||
platform: whereby # DB value (overridden by env var DAILY_MIGRATION_ROOM_IDS)
|
||||
recording_type: cloud
|
||||
```
|
||||
|
||||
**Clear old meetings:**
|
||||
```bash
|
||||
docker-compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"UPDATE meeting SET is_active = false WHERE room_id = '552640fd-16f2-4162-9526-8cf40cd2357e';"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Test 2: Meeting Creation with Auto-Recording
|
||||
|
||||
**Create meeting:**
|
||||
```bash
|
||||
curl -s -X POST http://localhost:1250/v1/rooms/test2/meeting \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"allow_duplicated":false}' | python3 -m json.tool
|
||||
```
|
||||
|
||||
**Expected Response:**
|
||||
```json
|
||||
{
|
||||
"room_name": "test2-YYYYMMDDHHMMSS", // Includes "test2" prefix!
|
||||
"room_url": "https://monadical.daily.co/test2-...?t=<JWT_TOKEN>", // Has token!
|
||||
"platform": "daily",
|
||||
"recording_type": "cloud" // DB value (Whereby-specific)
|
||||
}
|
||||
```
|
||||
|
||||
**Decode token to verify auto-recording:**
|
||||
```bash
|
||||
# Extract token from room_url, decode JWT payload
|
||||
echo "<token>" | python3 -c "
|
||||
import sys, json, base64
|
||||
token = sys.stdin.read().strip()
|
||||
payload = token.split('.')[1] + '=' * (4 - len(token.split('.')[1]) % 4)
|
||||
print(json.dumps(json.loads(base64.b64decode(payload)), indent=2))
|
||||
"
|
||||
```
|
||||
|
||||
**Expected token payload:**
|
||||
```json
|
||||
{
|
||||
"r": "test2-YYYYMMDDHHMMSS", // Room name
|
||||
"sr": true, // start_recording: true ✅
|
||||
"d": "...", // Domain ID
|
||||
"iat": 1234567890
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Test 3: Daily.co API Verification
|
||||
|
||||
**Check room configuration:**
|
||||
```bash
|
||||
ROOM_NAME="<from previous step>"
|
||||
curl -s -X GET "https://api.daily.co/v1/rooms/$ROOM_NAME" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -m json.tool
|
||||
```
|
||||
|
||||
**Expected config:**
|
||||
```json
|
||||
{
|
||||
"config": {
|
||||
"enable_recording": "raw-tracks", // ✅
|
||||
"recordings_bucket": {
|
||||
"bucket_name": "reflector-dailyco-local",
|
||||
"bucket_region": "us-east-1",
|
||||
"assume_role_arn": "arn:aws:iam::950402358378:role/DailyCo"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Test 4: Browser UI Test (Playwright MCP)
|
||||
|
||||
**Using Claude Code MCP tools:**
|
||||
|
||||
**Load room:**
|
||||
```
|
||||
Use: mcp__playwright__browser_navigate
|
||||
Input: {"url": "http://localhost:3000/test2"}
|
||||
|
||||
Then wait 12 seconds for iframe to load
|
||||
```
|
||||
|
||||
**Verify Daily.co iframe loaded:**
|
||||
```
|
||||
Use: mcp__playwright__browser_snapshot
|
||||
|
||||
Expected in snapshot:
|
||||
- iframe element with src containing "monadical.daily.co"
|
||||
- Daily.co pre-call UI visible
|
||||
```
|
||||
|
||||
**Take screenshot:**
|
||||
```
|
||||
Use: mcp__playwright__browser_take_screenshot
|
||||
Input: {"filename": "test2-before-join.png"}
|
||||
|
||||
Expected: Daily.co pre-call UI with "Join" button visible
|
||||
```
|
||||
|
||||
**Join meeting:**
|
||||
```
|
||||
Note: Daily.co iframe interaction requires clicking inside iframe.
|
||||
Use: mcp__playwright__browser_click
|
||||
Input: {"element": "Join button in Daily.co iframe", "ref": "<ref-from-snapshot>"}
|
||||
|
||||
Then wait 5 seconds for call to connect
|
||||
```
|
||||
|
||||
**Verify in-call:**
|
||||
```
|
||||
Use: mcp__playwright__browser_take_screenshot
|
||||
Input: {"filename": "test2-in-call.png"}
|
||||
|
||||
Expected: "Waiting for others to join" or participant video visible
|
||||
```
|
||||
|
||||
**Leave meeting:**
|
||||
```
|
||||
Use: mcp__playwright__browser_click
|
||||
Input: {"element": "Leave button in Daily.co iframe", "ref": "<ref-from-snapshot>"}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Alternative: JavaScript snippets (for manual testing):**
|
||||
|
||||
```javascript
|
||||
await page.goto('http://localhost:3000/test2');
|
||||
await new Promise(f => setTimeout(f, 12000)); // Wait for load
|
||||
|
||||
// Verify iframe
|
||||
const iframes = document.querySelectorAll('iframe');
|
||||
// Expected: 1 iframe with src containing "monadical.daily.co"
|
||||
|
||||
// Screenshot
|
||||
await page.screenshot({ path: 'test2-before-join.png' });
|
||||
|
||||
// Join
|
||||
await page.locator('iframe').contentFrame().getByRole('button', { name: 'Join' }).click();
|
||||
await new Promise(f => setTimeout(f, 5000));
|
||||
|
||||
// In-call screenshot
|
||||
await page.screenshot({ path: 'test2-in-call.png' });
|
||||
|
||||
// Leave
|
||||
await page.locator('iframe').contentFrame().getByRole('button', { name: 'Leave' }).click();
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Test 5: Webhook Verification
|
||||
|
||||
**Check server logs for webhooks:**
|
||||
```bash
|
||||
docker-compose logs --since 15m server 2>&1 | grep -i "participant joined\|recording started"
|
||||
```
|
||||
|
||||
**Expected logs:**
|
||||
```
|
||||
[info] Participant joined | meeting_id=... | num_clients=1 | recording_type=cloud | recording_trigger=automatic-2nd-participant
|
||||
[info] Recording started | meeting_id=... | recording_id=... | platform=daily
|
||||
```
|
||||
|
||||
**Check Daily.co webhook delivery logs:**
|
||||
```bash
|
||||
curl -s -X GET "https://api.daily.co/v1/logs/webhooks?limit=20" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -c "
|
||||
import sys, json
|
||||
logs = json.load(sys.stdin)
|
||||
for log in logs[:10]:
|
||||
req = json.loads(log['request'])
|
||||
room = req.get('payload', {}).get('room') or req.get('payload', {}).get('room_name', 'N/A')
|
||||
print(f\"{req['type']:30s} | room: {room:30s} | status: {log['status']}\")
|
||||
"
|
||||
```
|
||||
|
||||
**Expected output:**
|
||||
```
|
||||
participant.joined | room: test2-YYYYMMDDHHMMSS | status: 200
|
||||
recording.started | room: test2-YYYYMMDDHHMMSS | status: 200
|
||||
participant.left | room: test2-YYYYMMDDHHMMSS | status: 200
|
||||
recording.ready-to-download | room: test2-YYYYMMDDHHMMSS | status: 200
|
||||
```
|
||||
|
||||
**Check database updated:**
|
||||
```bash
|
||||
docker-compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT room_name, num_clients FROM meeting WHERE room_name LIKE 'test2-%' ORDER BY end_date DESC LIMIT 1;"
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```
|
||||
room_name: test2-YYYYMMDDHHMMSS
|
||||
num_clients: 0 // After participant left
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Test 6: Recording in S3
|
||||
|
||||
**List recent recordings:**
|
||||
```bash
|
||||
curl -s -X GET "https://api.daily.co/v1/recordings" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -c "
|
||||
import sys, json
|
||||
data = json.load(sys.stdin)
|
||||
for rec in data.get('data', [])[:5]:
|
||||
if 'test2-' in rec.get('room_name', ''):
|
||||
print(f\"Room: {rec['room_name']}\")
|
||||
print(f\"Status: {rec['status']}\")
|
||||
print(f\"Duration: {rec.get('duration', 0)}s\")
|
||||
print(f\"S3 key: {rec.get('s3key', 'N/A')}\")
|
||||
print(f\"Tracks: {len(rec.get('tracks', []))} files\")
|
||||
for track in rec.get('tracks', []):
|
||||
print(f\" - {track['type']}: {track['s3Key'].split('/')[-1]} ({track['size']} bytes)\")
|
||||
print()
|
||||
"
|
||||
```
|
||||
|
||||
**Expected output:**
|
||||
```
|
||||
Room: test2-20251009192341
|
||||
Status: finished
|
||||
Duration: ~30-120s
|
||||
S3 key: monadical/test2-20251009192341/1760037914930
|
||||
Tracks: 2 files
|
||||
- audio: 1760037914930-<uuid>-cam-audio-1760037915265 (~400 KB)
|
||||
- video: 1760037914930-<uuid>-cam-video-1760037915269 (~10-30 MB)
|
||||
```
|
||||
|
||||
**Verify S3 path structure:**
|
||||
- `monadical/` - Daily.co subdomain
|
||||
- `test2-20251009192341/` - Reflector room name + timestamp
|
||||
- `<timestamp>-<participant-uuid>-<media-type>-<track-start>.webm` - Individual track files
|
||||
|
||||
---
|
||||
|
||||
## Test 7: Database Check - Recording and Transcript
|
||||
|
||||
**Check recording created:**
|
||||
```bash
|
||||
docker-compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT id, bucket_name, object_key, status, meeting_id, recorded_at
|
||||
FROM recording
|
||||
ORDER BY recorded_at DESC LIMIT 1;"
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```
|
||||
id: <recording-id-from-webhook>
|
||||
bucket_name: reflector-dailyco-local
|
||||
object_key: monadical/test2-<timestamp>/<recording-timestamp>-<uuid>-cam-audio-<track-start>.webm
|
||||
status: completed
|
||||
meeting_id: <meeting-id>
|
||||
recorded_at: <recent-timestamp>
|
||||
```
|
||||
|
||||
**Check transcript created:**
|
||||
```bash
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT id, title, status, duration, recording_id, meeting_id, room_id
|
||||
FROM transcript
|
||||
ORDER BY created_at DESC LIMIT 1;"
|
||||
```
|
||||
|
||||
**Expected (REAL transcription):**
|
||||
```
|
||||
id: <transcript-id>
|
||||
title: <AI-generated title based on actual conversation content>
|
||||
status: uploaded (audio file processed and available)
|
||||
duration: <actual meeting duration in seconds>
|
||||
recording_id: <same-as-recording-id-above>
|
||||
meeting_id: <meeting-id>
|
||||
room_id: 552640fd-16f2-4162-9526-8cf40cd2357e
|
||||
```
|
||||
|
||||
**Note:** Title and content will reflect the ACTUAL conversation, not mock data. Processing time depends on recording length and GPU backend availability (Modal).
|
||||
|
||||
**Verify audio file exists:**
|
||||
```bash
|
||||
ls -lh data/<transcript-id>/upload.webm
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```
|
||||
-rw-r--r-- 1 user staff ~100-200K Oct 10 18:48 upload.webm
|
||||
```
|
||||
|
||||
**Check transcript topics (REAL transcription):**
|
||||
```bash
|
||||
TRANSCRIPT_ID=$(docker compose exec -T postgres psql -U reflector -d reflector -t -c \
|
||||
"SELECT id FROM transcript ORDER BY created_at DESC LIMIT 1;")
|
||||
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT
|
||||
jsonb_array_length(topics) as num_topics,
|
||||
jsonb_array_length(participants) as num_participants,
|
||||
short_summary,
|
||||
title
|
||||
FROM transcript
|
||||
WHERE id = '$TRANSCRIPT_ID';"
|
||||
```
|
||||
|
||||
**Expected (REAL data):**
|
||||
```
|
||||
num_topics: <varies based on conversation>
|
||||
num_participants: <actual number of participants who spoke>
|
||||
short_summary: <AI-generated summary of actual conversation>
|
||||
title: <AI-generated title based on content>
|
||||
```
|
||||
|
||||
**Check topics contain actual transcription:**
|
||||
```bash
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT topics->0->'title', topics->0->'summary', topics->0->'transcript'
|
||||
FROM transcript
|
||||
ORDER BY created_at DESC LIMIT 1;" | head -20
|
||||
```
|
||||
|
||||
**Expected output:** Will contain the ACTUAL transcribed conversation from the Daily.co meeting, not mock data.
|
||||
|
||||
**Check participants:**
|
||||
```bash
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT participants FROM transcript ORDER BY created_at DESC LIMIT 1;" \
|
||||
| python3 -c "import sys, json; data=json.loads(sys.stdin.read()); print(json.dumps(data, indent=2))"
|
||||
```
|
||||
|
||||
**Expected (REAL diarization):**
|
||||
```json
|
||||
[
|
||||
{
|
||||
"id": "<uuid>",
|
||||
"speaker": 0,
|
||||
"name": "Speaker 1"
|
||||
},
|
||||
{
|
||||
"id": "<uuid>",
|
||||
"speaker": 1,
|
||||
"name": "Speaker 2"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
**Note:** Speaker names will be generic ("Speaker 1", "Speaker 2", etc.) as determined by the diarization backend. Number of participants depends on how many actually spoke during the meeting.
|
||||
|
||||
**Check word-level data:**
|
||||
```bash
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT jsonb_array_length(topics->0->'words') as num_words_first_topic
|
||||
FROM transcript
|
||||
ORDER BY created_at DESC LIMIT 1;"
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```
|
||||
num_words_first_topic: <varies based on actual conversation length and topic chunking>
|
||||
```
|
||||
|
||||
**Verify speaker diarization in words:**
|
||||
```bash
|
||||
docker compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT
|
||||
topics->0->'words'->0->>'text' as first_word,
|
||||
topics->0->'words'->0->>'speaker' as speaker,
|
||||
topics->0->'words'->0->>'start' as start_time,
|
||||
topics->0->'words'->0->>'end' as end_time
|
||||
FROM transcript
|
||||
ORDER BY created_at DESC LIMIT 1;"
|
||||
```
|
||||
|
||||
**Expected (REAL transcription):**
|
||||
```
|
||||
first_word: <actual first word from transcription>
|
||||
speaker: 0, 1, 2, ... (actual speaker ID from diarization)
|
||||
start_time: <actual timestamp in seconds>
|
||||
end_time: <actual end timestamp>
|
||||
```
|
||||
|
||||
**Note:** All timestamps and speaker IDs are from real transcription/diarization, synchronized across tracks.
|
||||
|
||||
---
|
||||
|
||||
## Test 8: Recording Type Verification
|
||||
|
||||
**Check what Daily.co received:**
|
||||
```bash
|
||||
curl -s -X GET "https://api.daily.co/v1/rooms/test2-<timestamp>" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -m json.tool | grep "enable_recording"
|
||||
```
|
||||
|
||||
**Expected:**
|
||||
```json
|
||||
"enable_recording": "raw-tracks"
|
||||
```
|
||||
|
||||
**NOT:** `"enable_recording": "cloud"` (that would be wrong - we want raw tracks)
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Issue: No webhooks received
|
||||
|
||||
**Check webhook state:**
|
||||
```bash
|
||||
curl -s -X GET "https://api.daily.co/v1/webhooks" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -m json.tool
|
||||
```
|
||||
|
||||
**If state is FAILED:**
|
||||
```bash
|
||||
cd server
|
||||
uv run python scripts/recreate_daily_webhook.py https://<ngrok-url>/v1/daily/webhook
|
||||
```
|
||||
|
||||
### Issue: Webhooks return 422
|
||||
|
||||
**Check server logs:**
|
||||
```bash
|
||||
docker-compose logs --tail=50 server | grep "Failed to parse webhook event"
|
||||
```
|
||||
|
||||
**Common cause:** Event structure mismatch. Daily.co events use:
|
||||
```json
|
||||
{
|
||||
"version": "1.0.0",
|
||||
"type": "participant.joined",
|
||||
"payload": {...}, // NOT "data"
|
||||
"event_ts": 123.456 // NOT "ts"
|
||||
}
|
||||
```
|
||||
|
||||
### Issue: Recording not starting
|
||||
|
||||
1. **Check token has `sr: true`:**
|
||||
- Decode JWT token from room_url query param
|
||||
- Should contain `"sr": true`
|
||||
|
||||
2. **Check Daily.co room config:**
|
||||
- `enable_recording` must be set (not false)
|
||||
- For raw-tracks: must be exactly `"raw-tracks"`
|
||||
|
||||
3. **Check participant actually joined:**
|
||||
- Logs should show "Participant joined"
|
||||
- Must click "Join" button, not just pre-call screen
|
||||
|
||||
### Issue: Recording in S3 but wrong format
|
||||
|
||||
**Daily.co recording types:**
|
||||
- `"cloud"` → Single MP4 file (`download_link` in webhook)
|
||||
- `"raw-tracks"` → Multiple WebM files (`tracks` array in webhook)
|
||||
- `"raw-tracks-audio-only"` → Only audio WebM files
|
||||
|
||||
**Current implementation:** Always uses `"raw-tracks"` (better for transcription)
|
||||
|
||||
---
|
||||
|
||||
## Quick Validation Commands
|
||||
|
||||
**One-liner to verify everything:**
|
||||
```bash
|
||||
# 1. Check room exists
|
||||
docker-compose exec -T postgres psql -U reflector -d reflector -c \
|
||||
"SELECT name, platform FROM room WHERE name = 'test2';" && \
|
||||
|
||||
# 2. Create meeting
|
||||
MEETING=$(curl -s -X POST http://localhost:1250/v1/rooms/test2/meeting \
|
||||
-H "Content-Type: application/json" -d '{"allow_duplicated":false}') && \
|
||||
echo "$MEETING" | python3 -c "import sys,json; m=json.load(sys.stdin); print(f'Room: {m[\"room_name\"]}\nURL: {m[\"room_url\"][:80]}...')" && \
|
||||
|
||||
# 3. Check Daily.co config
|
||||
ROOM_NAME=$(echo "$MEETING" | python3 -c "import sys,json; print(json.load(sys.stdin)['room_name'])") && \
|
||||
curl -s -X GET "https://api.daily.co/v1/rooms/$ROOM_NAME" \
|
||||
-H "Authorization: Bearer $DAILY_API_KEY" | python3 -c "import sys,json; print(f'Recording: {json.load(sys.stdin)[\"config\"][\"enable_recording\"]}')"
|
||||
```
|
||||
|
||||
**Expected output:**
|
||||
```
|
||||
name: test2, platform: whereby
|
||||
Room: test2-20251009192341
|
||||
URL: https://monadical.daily.co/test2-20251009192341?t=eyJhbGc...
|
||||
Recording: raw-tracks
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Success Criteria Checklist
|
||||
|
||||
- [x] Room name includes Reflector room prefix (`test2-...`)
|
||||
- [x] Meeting URL contains JWT token (`?t=...`)
|
||||
- [x] Token has `sr: true` (auto-recording enabled)
|
||||
- [x] Daily.co room config: `enable_recording: "raw-tracks"`
|
||||
- [x] Browser loads Daily.co interface (not Whereby)
|
||||
- [x] Recording auto-starts when participant joins
|
||||
- [x] Webhooks received: participant.joined, recording.started, participant.left, recording.ready-to-download
|
||||
- [x] Recording status: `finished`
|
||||
- [x] S3 contains 2 files: audio (.webm) and video (.webm)
|
||||
- [x] S3 path: `monadical/test2-{timestamp}/{recording-start-ts}-{participant-uuid}-cam-{audio|video}-{track-start-ts}`
|
||||
- [x] Database `num_clients` increments/decrements correctly
|
||||
- [x] **Database recording entry created** with correct S3 path and status `completed`
|
||||
- [ ] **Database transcript entry created** with status `uploaded`
|
||||
- [ ] **Audio file downloaded** to `data/{transcript_id}/upload.webm`
|
||||
- [ ] **Transcript has REAL data**: AI-generated title based on conversation
|
||||
- [ ] **Transcript has topics** generated from actual content
|
||||
- [ ] **Transcript has participants** with proper speaker diarization
|
||||
- [ ] **Topics contain word-level data** with accurate timestamps and speaker IDs
|
||||
- [ ] **Total duration** matches actual meeting length
|
||||
- [ ] **MP3 and waveform files generated** by file processing pipeline
|
||||
- [ ] **Frontend transcript page loads** without "Failed to load audio" error
|
||||
- [ ] **Audio player functional** with working playback and waveform visualization
|
||||
- [ ] **Multitrack processing completed** without errors in worker logs
|
||||
- [ ] **Modal GPU backends accessible** (transcription and diarization)
|
||||
@@ -6,7 +6,7 @@ ENV PYTHONUNBUFFERED=1 \
|
||||
|
||||
# builder install base dependencies
|
||||
WORKDIR /tmp
|
||||
RUN apt-get update && apt-get install -y curl ffmpeg && apt-get clean
|
||||
RUN apt-get update && apt-get install -y curl && 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"
|
||||
|
||||
212
server/contrib/jitsi/README.md
Normal file
212
server/contrib/jitsi/README.md
Normal file
@@ -0,0 +1,212 @@
|
||||
# Event Logger for Docker-Jitsi-Meet
|
||||
|
||||
A Prosody module that logs Jitsi meeting events to JSONL files alongside recordings, enabling complete participant tracking and speaker statistics.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Running docker-jitsi-meet installation
|
||||
- Jibri configured for recording
|
||||
|
||||
## Installation
|
||||
|
||||
### Step 1: Copy the Module
|
||||
|
||||
Copy the Prosody module to your custom plugins directory:
|
||||
|
||||
```bash
|
||||
# Create the directory if it doesn't exist
|
||||
mkdir -p ~/.jitsi-meet-cfg/prosody/prosody-plugins-custom
|
||||
|
||||
# Copy the module
|
||||
cp mod_event_logger.lua ~/.jitsi-meet-cfg/prosody/prosody-plugins-custom/
|
||||
```
|
||||
|
||||
### Step 2: Update Your .env File
|
||||
|
||||
Add or modify these variables in your `.env` file:
|
||||
|
||||
```bash
|
||||
# If XMPP_MUC_MODULES already exists, append event_logger
|
||||
# Example: XMPP_MUC_MODULES=existing_module,event_logger
|
||||
XMPP_MUC_MODULES=event_logger
|
||||
|
||||
# Optional: Configure the module (these are defaults)
|
||||
JIBRI_RECORDINGS_PATH=/config/recordings
|
||||
JIBRI_LOG_SPEAKER_STATS=true
|
||||
JIBRI_SPEAKER_STATS_INTERVAL=10
|
||||
```
|
||||
|
||||
**Important**: If you already have `XMPP_MUC_MODULES` defined, add `event_logger` to the comma-separated list:
|
||||
```bash
|
||||
# Existing modules + our module
|
||||
XMPP_MUC_MODULES=mod_info,mod_alert,event_logger
|
||||
```
|
||||
|
||||
### Step 3: Modify docker-compose.yml
|
||||
|
||||
Add a shared recordings volume so Prosody can write events alongside Jibri recordings:
|
||||
|
||||
```yaml
|
||||
services:
|
||||
prosody:
|
||||
# ... existing configuration ...
|
||||
volumes:
|
||||
- ${CONFIG}/prosody/config:/config:Z
|
||||
- ${CONFIG}/prosody/prosody-plugins-custom:/prosody-plugins-custom:Z
|
||||
- ${CONFIG}/recordings:/config/recordings:Z # Add this line
|
||||
environment:
|
||||
# Add if not using .env file
|
||||
- XMPP_MUC_MODULES=${XMPP_MUC_MODULES:-event_logger}
|
||||
- JIBRI_RECORDINGS_PATH=/config/recordings
|
||||
|
||||
jibri:
|
||||
# ... existing configuration ...
|
||||
volumes:
|
||||
- ${CONFIG}/jibri:/config:Z
|
||||
- ${CONFIG}/recordings:/config/recordings:Z # Add this line
|
||||
environment:
|
||||
# For Reflector webhook integration (optional)
|
||||
- REFLECTOR_WEBHOOK_URL=${REFLECTOR_WEBHOOK_URL:-}
|
||||
- JIBRI_FINALIZE_RECORDING_SCRIPT_PATH=/config/finalize.sh
|
||||
```
|
||||
|
||||
### Step 4: Add Finalize Script (Optional - For Reflector Integration)
|
||||
|
||||
If you want to notify Reflector when recordings complete:
|
||||
|
||||
```bash
|
||||
# Copy the finalize script
|
||||
cp finalize.sh ~/.jitsi-meet-cfg/jibri/finalize.sh
|
||||
chmod +x ~/.jitsi-meet-cfg/jibri/finalize.sh
|
||||
|
||||
# Add to .env
|
||||
REFLECTOR_WEBHOOK_URL=http://your-reflector-api:8000
|
||||
```
|
||||
|
||||
### Step 5: Restart Services
|
||||
|
||||
```bash
|
||||
docker-compose down
|
||||
docker-compose up -d
|
||||
```
|
||||
|
||||
## What Gets Created
|
||||
|
||||
After a recording, you'll find in `~/.jitsi-meet-cfg/recordings/{session-id}/`:
|
||||
- `recording.mp4` - The video recording (created by Jibri)
|
||||
- `metadata.json` - Basic metadata (created by Jibri)
|
||||
- `events.jsonl` - Complete participant timeline (created by this module)
|
||||
|
||||
## Event Format
|
||||
|
||||
Each line in `events.jsonl` is a JSON object:
|
||||
|
||||
```json
|
||||
{"type":"room_created","timestamp":1234567890,"room_name":"TestRoom","room_jid":"testroom@conference.meet.jitsi","meeting_url":"https://meet.jitsi/TestRoom"}
|
||||
{"type":"recording_started","timestamp":1234567891,"room_name":"TestRoom","session_id":"20240115120000_TestRoom","jibri_jid":"jibri@recorder.meet.jitsi"}
|
||||
{"type":"participant_joined","timestamp":1234567892,"room_name":"TestRoom","participant":{"jid":"user1@meet.jitsi/web","nick":"John Doe","id":"user1@meet.jitsi","is_moderator":false}}
|
||||
{"type":"speaker_active","timestamp":1234567895,"room_name":"TestRoom","speaker_jid":"user1@meet.jitsi","speaker_nick":"John Doe","duration":10}
|
||||
{"type":"participant_left","timestamp":1234567920,"room_name":"TestRoom","participant":{"jid":"user1@meet.jitsi/web","nick":"John Doe","duration_seconds":28}}
|
||||
{"type":"recording_stopped","timestamp":1234567950,"room_name":"TestRoom","session_id":"20240115120000_TestRoom","meeting_url":"https://meet.jitsi/TestRoom"}
|
||||
```
|
||||
|
||||
## Configuration Options
|
||||
|
||||
All configuration can be done via environment variables:
|
||||
|
||||
| Environment Variable | Default | Description |
|
||||
|---------------------|---------|-------------|
|
||||
| `JIBRI_RECORDINGS_PATH` | `/config/recordings` | Path where recordings are stored |
|
||||
| `JIBRI_LOG_SPEAKER_STATS` | `true` | Enable speaker statistics logging |
|
||||
| `JIBRI_SPEAKER_STATS_INTERVAL` | `10` | Seconds between speaker stats updates |
|
||||
|
||||
## Verifying Installation
|
||||
|
||||
Check that the module is loaded:
|
||||
```bash
|
||||
docker-compose logs prosody | grep "Event Logger"
|
||||
# Should see: "Event Logger loaded - writing to /config/recordings"
|
||||
```
|
||||
|
||||
Check for events after a recording:
|
||||
```bash
|
||||
ls -la ~/.jitsi-meet-cfg/recordings/*/events.jsonl
|
||||
cat ~/.jitsi-meet-cfg/recordings/*/events.jsonl | jq .
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### No events.jsonl file created
|
||||
|
||||
1. **Check module is enabled**:
|
||||
```bash
|
||||
docker-compose exec prosody grep -r "event_logger" /config
|
||||
```
|
||||
|
||||
2. **Verify volume permissions**:
|
||||
```bash
|
||||
docker-compose exec prosody ls -la /config/recordings
|
||||
```
|
||||
|
||||
3. **Check Prosody logs for errors**:
|
||||
```bash
|
||||
docker-compose logs prosody | grep -i error
|
||||
```
|
||||
|
||||
### Module not loading
|
||||
|
||||
1. **Verify file exists in container**:
|
||||
```bash
|
||||
docker-compose exec prosody ls -la /prosody-plugins-custom/
|
||||
```
|
||||
|
||||
2. **Check XMPP_MUC_MODULES format** (must be comma-separated, no spaces):
|
||||
- ✅ Correct: `XMPP_MUC_MODULES=mod1,mod2,event_logger`
|
||||
- ❌ Wrong: `XMPP_MUC_MODULES=mod1, mod2, event_logger`
|
||||
|
||||
## Common docker-compose.yml Patterns
|
||||
|
||||
### Minimal Addition (if you trust defaults)
|
||||
```yaml
|
||||
services:
|
||||
prosody:
|
||||
volumes:
|
||||
- ${CONFIG}/recordings:/config/recordings:Z # Just add this
|
||||
```
|
||||
|
||||
### Full Configuration
|
||||
```yaml
|
||||
services:
|
||||
prosody:
|
||||
volumes:
|
||||
- ${CONFIG}/prosody/config:/config:Z
|
||||
- ${CONFIG}/prosody/prosody-plugins-custom:/prosody-plugins-custom:Z
|
||||
- ${CONFIG}/recordings:/config/recordings:Z
|
||||
environment:
|
||||
- XMPP_MUC_MODULES=event_logger
|
||||
- JIBRI_RECORDINGS_PATH=/config/recordings
|
||||
- JIBRI_LOG_SPEAKER_STATS=true
|
||||
- JIBRI_SPEAKER_STATS_INTERVAL=10
|
||||
|
||||
jibri:
|
||||
volumes:
|
||||
- ${CONFIG}/jibri:/config:Z
|
||||
- ${CONFIG}/recordings:/config/recordings:Z
|
||||
environment:
|
||||
- JIBRI_RECORDING_DIR=/config/recordings
|
||||
- JIBRI_FINALIZE_RECORDING_SCRIPT_PATH=/config/finalize.sh
|
||||
```
|
||||
|
||||
## Integration with Reflector
|
||||
|
||||
The finalize.sh script will automatically notify Reflector when a recording completes if `REFLECTOR_WEBHOOK_URL` is set. Reflector will receive:
|
||||
|
||||
```json
|
||||
{
|
||||
"session_id": "20240115120000_TestRoom",
|
||||
"path": "20240115120000_TestRoom",
|
||||
"meeting_url": "https://meet.jitsi/TestRoom"
|
||||
}
|
||||
```
|
||||
|
||||
Reflector then processes the recording along with the complete participant timeline from `events.jsonl`.
|
||||
49
server/contrib/jitsi/finalize.sh
Executable file
49
server/contrib/jitsi/finalize.sh
Executable file
@@ -0,0 +1,49 @@
|
||||
#!/bin/bash
|
||||
# Jibri finalize script to notify Reflector when recording is complete
|
||||
# This script is called by Jibri with the recording directory as argument
|
||||
|
||||
RECORDING_PATH="$1"
|
||||
SESSION_ID=$(basename "$RECORDING_PATH")
|
||||
METADATA_FILE="$RECORDING_PATH/metadata.json"
|
||||
|
||||
# Extract meeting URL from Jibri's metadata
|
||||
MEETING_URL=""
|
||||
if [ -f "$METADATA_FILE" ]; then
|
||||
MEETING_URL=$(jq -r '.meeting_url' "$METADATA_FILE" 2>/dev/null || echo "")
|
||||
fi
|
||||
|
||||
echo "[$(date)] Recording finalized: $RECORDING_PATH"
|
||||
echo "[$(date)] Session ID: $SESSION_ID"
|
||||
echo "[$(date)] Meeting URL: $MEETING_URL"
|
||||
|
||||
# Check if events.jsonl was created by our Prosody module
|
||||
if [ -f "$RECORDING_PATH/events.jsonl" ]; then
|
||||
EVENT_COUNT=$(wc -l < "$RECORDING_PATH/events.jsonl")
|
||||
echo "[$(date)] Found events.jsonl with $EVENT_COUNT events"
|
||||
else
|
||||
echo "[$(date)] Warning: No events.jsonl found"
|
||||
fi
|
||||
|
||||
# Notify Reflector if webhook URL is configured
|
||||
if [ -n "$REFLECTOR_WEBHOOK_URL" ]; then
|
||||
echo "[$(date)] Notifying Reflector at: $REFLECTOR_WEBHOOK_URL"
|
||||
|
||||
RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "$REFLECTOR_WEBHOOK_URL/api/v1/jibri/recording-ready" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"session_id\":\"$SESSION_ID\",\"path\":\"$SESSION_ID\",\"meeting_url\":\"$MEETING_URL\"}")
|
||||
|
||||
HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
|
||||
BODY=$(echo "$RESPONSE" | sed '$d')
|
||||
|
||||
if [ "$HTTP_CODE" = "200" ]; then
|
||||
echo "[$(date)] Reflector notified successfully"
|
||||
echo "[$(date)] Response: $BODY"
|
||||
else
|
||||
echo "[$(date)] Failed to notify Reflector. HTTP code: $HTTP_CODE"
|
||||
echo "[$(date)] Response: $BODY"
|
||||
fi
|
||||
else
|
||||
echo "[$(date)] No REFLECTOR_WEBHOOK_URL configured, skipping notification"
|
||||
fi
|
||||
|
||||
echo "[$(date)] Finalize script completed"
|
||||
372
server/contrib/jitsi/mod_event_logger.lua
Normal file
372
server/contrib/jitsi/mod_event_logger.lua
Normal file
@@ -0,0 +1,372 @@
|
||||
local json = require "util.json"
|
||||
local st = require "util.stanza"
|
||||
local jid_bare = require "util.jid".bare
|
||||
|
||||
local recordings_path = os.getenv("JIBRI_RECORDINGS_PATH") or
|
||||
module:get_option_string("jibri_recordings_path", "/recordings")
|
||||
|
||||
-- room_jid -> { session_id, participants = {jid -> info} }
|
||||
local active_recordings = {}
|
||||
-- room_jid -> { participants = {jid -> info}, created_at }
|
||||
local room_states = {}
|
||||
|
||||
local function get_timestamp()
|
||||
return os.time()
|
||||
end
|
||||
|
||||
local function write_event(session_id, event)
|
||||
if not session_id then
|
||||
module:log("warn", "No session_id for event: %s", event.type)
|
||||
return
|
||||
end
|
||||
|
||||
local session_dir = string.format("%s/%s", recordings_path, session_id)
|
||||
local event_file = string.format("%s/events.jsonl", session_dir)
|
||||
|
||||
module:log("info", "Writing event %s to %s", event.type, event_file)
|
||||
|
||||
-- Create directory
|
||||
local mkdir_cmd = string.format("mkdir -p '%s' 2>&1", session_dir)
|
||||
local mkdir_result = os.execute(mkdir_cmd)
|
||||
module:log("debug", "mkdir result: %s", tostring(mkdir_result))
|
||||
|
||||
local file, err = io.open(event_file, "a")
|
||||
if file then
|
||||
local json_str = json.encode(event)
|
||||
file:write(json_str .. "\n")
|
||||
file:close()
|
||||
module:log("info", "Successfully wrote event %s", event.type)
|
||||
else
|
||||
module:log("error", "Failed to write event to %s: %s", event_file, err)
|
||||
end
|
||||
end
|
||||
|
||||
local function extract_participant_info(occupant)
|
||||
local info = {
|
||||
jid = occupant.jid,
|
||||
bare_jid = occupant.bare_jid,
|
||||
nick = occupant.nick,
|
||||
display_name = nil,
|
||||
role = occupant.role
|
||||
}
|
||||
|
||||
local presence = occupant:get_presence()
|
||||
if presence then
|
||||
local nick_element = presence:get_child("nick", "http://jabber.org/protocol/nick")
|
||||
if nick_element then
|
||||
info.display_name = nick_element:get_text()
|
||||
end
|
||||
|
||||
local identity = presence:get_child("identity")
|
||||
if identity then
|
||||
local user = identity:get_child("user")
|
||||
if user then
|
||||
local name = user:get_child("name")
|
||||
if name then
|
||||
info.display_name = name:get_text()
|
||||
end
|
||||
|
||||
local id_element = user:get_child("id")
|
||||
if id_element then
|
||||
info.id = id_element:get_text()
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
if not info.display_name and occupant.nick then
|
||||
local _, _, resource = occupant.nick:match("([^@]+)@([^/]+)/(.+)")
|
||||
if resource then
|
||||
info.display_name = resource
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
return info
|
||||
end
|
||||
|
||||
local function get_room_participant_count(room)
|
||||
local count = 0
|
||||
for _ in room:each_occupant() do
|
||||
count = count + 1
|
||||
end
|
||||
return count
|
||||
end
|
||||
|
||||
local function snapshot_room_participants(room)
|
||||
local participants = {}
|
||||
local total = 0
|
||||
local skipped = 0
|
||||
|
||||
module:log("info", "Snapshotting room participants")
|
||||
|
||||
for _, occupant in room:each_occupant() do
|
||||
total = total + 1
|
||||
-- Skip recorders (Jibri)
|
||||
if occupant.bare_jid and (occupant.bare_jid:match("^recorder@") or
|
||||
occupant.bare_jid:match("^jibri@")) then
|
||||
skipped = skipped + 1
|
||||
else
|
||||
local info = extract_participant_info(occupant)
|
||||
participants[occupant.jid] = info
|
||||
module:log("debug", "Added participant: %s", info.display_name or info.bare_jid)
|
||||
end
|
||||
end
|
||||
|
||||
module:log("info", "Snapshot: %d total, %d participants", total, total - skipped)
|
||||
return participants
|
||||
end
|
||||
|
||||
-- Import utility functions if available
|
||||
local util = module:require "util";
|
||||
local get_room_from_jid = util.get_room_from_jid;
|
||||
local room_jid_match_rewrite = util.room_jid_match_rewrite;
|
||||
|
||||
-- Main IQ handler for Jibri stanzas
|
||||
module:hook("pre-iq/full", function(event)
|
||||
local stanza = event.stanza
|
||||
if stanza.name ~= "iq" then
|
||||
return
|
||||
end
|
||||
|
||||
local jibri = stanza:get_child('jibri', 'http://jitsi.org/protocol/jibri')
|
||||
if not jibri then
|
||||
return
|
||||
end
|
||||
|
||||
module:log("info", "=== Jibri IQ intercepted ===")
|
||||
|
||||
local action = jibri.attr.action
|
||||
local session_id = jibri.attr.session_id
|
||||
local room_jid = jibri.attr.room
|
||||
local recording_mode = jibri.attr.recording_mode
|
||||
local app_data = jibri.attr.app_data
|
||||
|
||||
module:log("info", "Jibri %s - session: %s, room: %s, mode: %s",
|
||||
action or "?", session_id or "?", room_jid or "?", recording_mode or "?")
|
||||
|
||||
if not room_jid or not session_id then
|
||||
module:log("warn", "Missing room_jid or session_id")
|
||||
return
|
||||
end
|
||||
|
||||
-- Get the room using util function
|
||||
local room = get_room_from_jid(room_jid_match_rewrite(jid_bare(stanza.attr.to)))
|
||||
if not room then
|
||||
-- Try with the room_jid directly
|
||||
room = get_room_from_jid(room_jid)
|
||||
end
|
||||
|
||||
if not room then
|
||||
module:log("error", "Room not found for jid: %s", room_jid)
|
||||
return
|
||||
end
|
||||
|
||||
module:log("info", "Room found: %s", room:get_name() or room_jid)
|
||||
|
||||
if action == "start" then
|
||||
module:log("info", "Recording START for session %s", session_id)
|
||||
|
||||
-- Count and snapshot participants
|
||||
local participant_count = 0
|
||||
for _ in room:each_occupant() do
|
||||
participant_count = participant_count + 1
|
||||
end
|
||||
|
||||
local participants = snapshot_room_participants(room)
|
||||
local participant_list = {}
|
||||
for jid, info in pairs(participants) do
|
||||
table.insert(participant_list, info)
|
||||
end
|
||||
|
||||
active_recordings[room_jid] = {
|
||||
session_id = session_id,
|
||||
participants = participants,
|
||||
started_at = get_timestamp()
|
||||
}
|
||||
|
||||
write_event(session_id, {
|
||||
type = "recording_started",
|
||||
timestamp = get_timestamp(),
|
||||
room_jid = room_jid,
|
||||
room_name = room:get_name(),
|
||||
session_id = session_id,
|
||||
recording_mode = recording_mode,
|
||||
app_data = app_data,
|
||||
participant_count = participant_count,
|
||||
participants_at_start = participant_list
|
||||
})
|
||||
|
||||
elseif action == "stop" then
|
||||
module:log("info", "Recording STOP for session %s", session_id)
|
||||
|
||||
local recording = active_recordings[room_jid]
|
||||
if recording and recording.session_id == session_id then
|
||||
write_event(session_id, {
|
||||
type = "recording_stopped",
|
||||
timestamp = get_timestamp(),
|
||||
room_jid = room_jid,
|
||||
room_name = room:get_name(),
|
||||
session_id = session_id,
|
||||
duration = get_timestamp() - recording.started_at,
|
||||
participant_count = get_room_participant_count(room)
|
||||
})
|
||||
|
||||
active_recordings[room_jid] = nil
|
||||
else
|
||||
module:log("warn", "No active recording found for room %s", room_jid)
|
||||
end
|
||||
end
|
||||
end);
|
||||
|
||||
-- Room and participant event hooks
|
||||
local function setup_room_hooks(host_module)
|
||||
module:log("info", "Setting up room hooks on %s", host_module.host or "unknown")
|
||||
|
||||
-- Room created
|
||||
host_module:hook("muc-room-created", function(event)
|
||||
local room = event.room
|
||||
local room_jid = room.jid
|
||||
|
||||
room_states[room_jid] = {
|
||||
participants = {},
|
||||
created_at = get_timestamp()
|
||||
}
|
||||
|
||||
module:log("info", "Room created: %s", room_jid)
|
||||
end)
|
||||
|
||||
-- Room destroyed
|
||||
host_module:hook("muc-room-destroyed", function(event)
|
||||
local room = event.room
|
||||
local room_jid = room.jid
|
||||
|
||||
room_states[room_jid] = nil
|
||||
active_recordings[room_jid] = nil
|
||||
|
||||
module:log("info", "Room destroyed: %s", room_jid)
|
||||
end)
|
||||
|
||||
-- Occupant joined
|
||||
host_module:hook("muc-occupant-joined", function(event)
|
||||
local room = event.room
|
||||
local occupant = event.occupant
|
||||
local room_jid = room.jid
|
||||
|
||||
-- Skip recorders
|
||||
if occupant.bare_jid and (occupant.bare_jid:match("^recorder@") or
|
||||
occupant.bare_jid:match("^jibri@")) then
|
||||
return
|
||||
end
|
||||
|
||||
local participant_info = extract_participant_info(occupant)
|
||||
|
||||
-- Update room state
|
||||
if room_states[room_jid] then
|
||||
room_states[room_jid].participants[occupant.jid] = participant_info
|
||||
end
|
||||
|
||||
-- Log to active recording if exists
|
||||
local recording = active_recordings[room_jid]
|
||||
if recording then
|
||||
recording.participants[occupant.jid] = participant_info
|
||||
|
||||
write_event(recording.session_id, {
|
||||
type = "participant_joined",
|
||||
timestamp = get_timestamp(),
|
||||
room_jid = room_jid,
|
||||
room_name = room:get_name(),
|
||||
participant = participant_info,
|
||||
participant_count = get_room_participant_count(room)
|
||||
})
|
||||
end
|
||||
|
||||
module:log("info", "Participant joined %s: %s (%d total)",
|
||||
room:get_name() or room_jid,
|
||||
participant_info.display_name or participant_info.bare_jid,
|
||||
get_room_participant_count(room))
|
||||
end)
|
||||
|
||||
-- Occupant left
|
||||
host_module:hook("muc-occupant-left", function(event)
|
||||
local room = event.room
|
||||
local occupant = event.occupant
|
||||
local room_jid = room.jid
|
||||
|
||||
-- Skip recorders
|
||||
if occupant.bare_jid and (occupant.bare_jid:match("^recorder@") or
|
||||
occupant.bare_jid:match("^jibri@")) then
|
||||
return
|
||||
end
|
||||
|
||||
local participant_info = extract_participant_info(occupant)
|
||||
|
||||
-- Update room state
|
||||
if room_states[room_jid] then
|
||||
room_states[room_jid].participants[occupant.jid] = nil
|
||||
end
|
||||
|
||||
-- Log to active recording if exists
|
||||
local recording = active_recordings[room_jid]
|
||||
if recording then
|
||||
if recording.participants[occupant.jid] then
|
||||
recording.participants[occupant.jid] = nil
|
||||
end
|
||||
|
||||
write_event(recording.session_id, {
|
||||
type = "participant_left",
|
||||
timestamp = get_timestamp(),
|
||||
room_jid = room_jid,
|
||||
room_name = room:get_name(),
|
||||
participant = participant_info,
|
||||
participant_count = get_room_participant_count(room)
|
||||
})
|
||||
end
|
||||
|
||||
module:log("info", "Participant left %s: %s (%d remaining)",
|
||||
room:get_name() or room_jid,
|
||||
participant_info.display_name or participant_info.bare_jid,
|
||||
get_room_participant_count(room))
|
||||
end)
|
||||
end
|
||||
|
||||
-- Module initialization
|
||||
local current_host = module:get_host()
|
||||
local host_type = module:get_host_type()
|
||||
|
||||
module:log("info", "Event Logger loading on %s (type: %s)", current_host, host_type or "unknown")
|
||||
module:log("info", "Recording path: %s", recordings_path)
|
||||
|
||||
-- Setup room hooks based on host type
|
||||
if host_type == "component" and current_host:match("^[^.]+%.") then
|
||||
setup_room_hooks(module)
|
||||
else
|
||||
-- Try to find and hook to MUC component
|
||||
local process_host_module = util.process_host_module
|
||||
local muc_component_host = module:get_option_string("muc_component") or
|
||||
module:get_option_string("main_muc")
|
||||
|
||||
if not muc_component_host then
|
||||
local possible_hosts = {
|
||||
"muc." .. current_host,
|
||||
"conference." .. current_host,
|
||||
"rooms." .. current_host
|
||||
}
|
||||
|
||||
for _, host in ipairs(possible_hosts) do
|
||||
if prosody.hosts[host] then
|
||||
muc_component_host = host
|
||||
module:log("info", "Auto-detected MUC component: %s", muc_component_host)
|
||||
break
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
if muc_component_host then
|
||||
process_host_module(muc_component_host, function(host_module, host)
|
||||
module:log("info", "Hooking to MUC events on %s", host)
|
||||
setup_room_hooks(host_module)
|
||||
end)
|
||||
else
|
||||
module:log("error", "Could not find MUC component")
|
||||
end
|
||||
end
|
||||
@@ -190,5 +190,5 @@ Use the pytest-based conformance tests to validate any new implementation (inclu
|
||||
```
|
||||
TRANSCRIPT_URL=https://<your-deployment-base> \
|
||||
TRANSCRIPT_MODAL_API_KEY=your-api-key \
|
||||
uv run -m pytest -m model_api --no-cov server/tests/test_model_api_transcript.py
|
||||
uv run -m pytest -m gpu_modal --no-cov server/tests/test_gpu_modal_transcript.py
|
||||
```
|
||||
|
||||
493
server/docs/platform-jitsi.md
Normal file
493
server/docs/platform-jitsi.md
Normal file
@@ -0,0 +1,493 @@
|
||||
# Jitsi Integration Configuration Guide
|
||||
|
||||
This guide provides step-by-step instructions for configuring Reflector to work with a self-hosted Jitsi Meet installation for video meetings and recording.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before configuring Jitsi integration, ensure you have:
|
||||
|
||||
- **Self-hosted Jitsi Meet installation** (version 2.0.8922 or later recommended)
|
||||
- **Jibri recording service** configured and running
|
||||
- **Prosody XMPP server** with mod_event_sync module installed
|
||||
- **Docker or system deployment** of Reflector with access to environment variables
|
||||
- **SSL certificates** for secure communication between services
|
||||
|
||||
## Environment Configuration
|
||||
|
||||
Add the following environment variables to your Reflector deployment:
|
||||
|
||||
### Required Settings
|
||||
|
||||
```bash
|
||||
# Jitsi Meet domain (without https://)
|
||||
JITSI_DOMAIN=meet.example.com
|
||||
|
||||
# JWT secret for room authentication (generate with: openssl rand -hex 32)
|
||||
JITSI_JWT_SECRET=your-64-character-hex-secret-here
|
||||
|
||||
# Webhook secret for secure event handling (generate with: openssl rand -hex 16)
|
||||
JITSI_WEBHOOK_SECRET=your-32-character-hex-secret-here
|
||||
|
||||
# Application identifier (should match Jitsi configuration)
|
||||
JITSI_APP_ID=reflector
|
||||
|
||||
# JWT issuer and audience (should match Jitsi configuration)
|
||||
JITSI_JWT_ISSUER=reflector
|
||||
JITSI_JWT_AUDIENCE=jitsi
|
||||
```
|
||||
|
||||
### Example .env Configuration
|
||||
|
||||
```bash
|
||||
# Add to your server/.env file
|
||||
JITSI_DOMAIN=meet.mycompany.com
|
||||
JITSI_JWT_SECRET=$(openssl rand -hex 32)
|
||||
JITSI_WEBHOOK_SECRET=$(openssl rand -hex 16)
|
||||
JITSI_APP_ID=reflector
|
||||
JITSI_JWT_ISSUER=reflector
|
||||
JITSI_JWT_AUDIENCE=jitsi
|
||||
```
|
||||
|
||||
## Jitsi Meet Server Configuration
|
||||
|
||||
### 1. JWT Authentication Setup
|
||||
|
||||
Edit `/etc/prosody/conf.d/[YOUR_DOMAIN].cfg.lua`:
|
||||
|
||||
```lua
|
||||
VirtualHost "meet.example.com"
|
||||
authentication = "token"
|
||||
app_id = "reflector"
|
||||
app_secret = "your-jwt-secret-here"
|
||||
|
||||
-- Allow anonymous access for non-authenticated users
|
||||
c2s_require_encryption = false
|
||||
admins = { "focusUser@auth.meet.example.com" }
|
||||
|
||||
modules_enabled = {
|
||||
"bosh";
|
||||
"pubsub";
|
||||
"ping";
|
||||
"roster";
|
||||
"saslauth";
|
||||
"tls";
|
||||
"dialback";
|
||||
"disco";
|
||||
"carbons";
|
||||
"pep";
|
||||
"private";
|
||||
"blocklist";
|
||||
"vcard";
|
||||
"version";
|
||||
"uptime";
|
||||
"time";
|
||||
"ping";
|
||||
"register";
|
||||
"admin_adhoc";
|
||||
"token_verification";
|
||||
"event_sync"; -- Required for webhook events
|
||||
}
|
||||
```
|
||||
|
||||
### 2. Room Access Control
|
||||
|
||||
Edit `/etc/jitsi/meet/meet.example.com-config.js`:
|
||||
|
||||
```javascript
|
||||
var config = {
|
||||
hosts: {
|
||||
domain: 'meet.example.com',
|
||||
muc: 'conference.meet.example.com'
|
||||
},
|
||||
|
||||
// Enable JWT authentication
|
||||
enableUserRolesBasedOnToken: true,
|
||||
|
||||
// Recording configuration
|
||||
fileRecordingsEnabled: true,
|
||||
liveStreamingEnabled: false,
|
||||
|
||||
// Reflector-specific settings
|
||||
prejoinPageEnabled: true,
|
||||
requireDisplayName: true,
|
||||
};
|
||||
```
|
||||
|
||||
### 3. Interface Configuration
|
||||
|
||||
Edit `/usr/share/jitsi-meet/interface_config.js`:
|
||||
|
||||
```javascript
|
||||
var interfaceConfig = {
|
||||
// Customize for Reflector branding
|
||||
APP_NAME: 'Reflector Meeting',
|
||||
DEFAULT_WELCOME_PAGE_LOGO_URL: 'https://your-domain.com/logo.png',
|
||||
|
||||
// Hide unnecessary buttons
|
||||
TOOLBAR_BUTTONS: [
|
||||
'microphone', 'camera', 'closedcaptions', 'desktop',
|
||||
'fullscreen', 'fodeviceselection', 'hangup',
|
||||
'chat', 'recording', 'livestreaming', 'etherpad',
|
||||
'sharedvideo', 'settings', 'raisehand', 'videoquality',
|
||||
'filmstrip', 'invite', 'feedback', 'stats', 'shortcuts',
|
||||
'tileview', 'videobackgroundblur', 'download', 'help',
|
||||
'mute-everyone'
|
||||
]
|
||||
};
|
||||
```
|
||||
|
||||
## Jibri Configuration
|
||||
|
||||
### 1. Recording Service Setup
|
||||
|
||||
Edit `/etc/jitsi/jibri/jibri.conf`:
|
||||
|
||||
```hocon
|
||||
jibri {
|
||||
recording {
|
||||
recordings-directory = "/var/recordings"
|
||||
finalize-script = "/opt/jitsi/jibri/finalize.sh"
|
||||
}
|
||||
|
||||
api {
|
||||
xmpp {
|
||||
environments = [{
|
||||
name = "prod environment"
|
||||
xmpp-server-hosts = ["meet.example.com"]
|
||||
xmpp-domain = "meet.example.com"
|
||||
|
||||
control-muc {
|
||||
domain = "internal.auth.meet.example.com"
|
||||
room-name = "JibriBrewery"
|
||||
nickname = "jibri-nickname"
|
||||
}
|
||||
|
||||
control-login {
|
||||
domain = "auth.meet.example.com"
|
||||
username = "jibri"
|
||||
password = "jibri-password"
|
||||
}
|
||||
}]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 2. Finalize Script Setup
|
||||
|
||||
Create `/opt/jitsi/jibri/finalize.sh`:
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# Jibri finalize script for Reflector integration
|
||||
|
||||
RECORDING_FILE="$1"
|
||||
ROOM_NAME="$2"
|
||||
REFLECTOR_API_URL="${REFLECTOR_API_URL:-http://localhost:1250}"
|
||||
WEBHOOK_SECRET="${JITSI_WEBHOOK_SECRET}"
|
||||
|
||||
# Generate webhook signature
|
||||
generate_signature() {
|
||||
local payload="$1"
|
||||
echo -n "$payload" | openssl dgst -sha256 -hmac "$WEBHOOK_SECRET" | cut -d' ' -f2
|
||||
}
|
||||
|
||||
# Prepare webhook payload
|
||||
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)
|
||||
PAYLOAD=$(cat <<EOF
|
||||
{
|
||||
"room_name": "$ROOM_NAME",
|
||||
"recording_file": "$RECORDING_FILE",
|
||||
"recording_status": "completed",
|
||||
"timestamp": "$TIMESTAMP"
|
||||
}
|
||||
EOF
|
||||
)
|
||||
|
||||
# Generate signature
|
||||
SIGNATURE=$(generate_signature "$PAYLOAD")
|
||||
|
||||
# Send webhook to Reflector
|
||||
curl -X POST "$REFLECTOR_API_URL/v1/jibri/recording-complete" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: $SIGNATURE" \
|
||||
-d "$PAYLOAD" \
|
||||
--max-time 30
|
||||
|
||||
echo "Recording finalization webhook sent for room: $ROOM_NAME"
|
||||
```
|
||||
|
||||
Make the script executable:
|
||||
|
||||
```bash
|
||||
chmod +x /opt/jitsi/jibri/finalize.sh
|
||||
```
|
||||
|
||||
## Prosody Event Configuration
|
||||
|
||||
### 1. Event-Sync Module Installation
|
||||
|
||||
Install the mod_event_sync module:
|
||||
|
||||
```bash
|
||||
# Download the module
|
||||
cd /usr/share/jitsi-meet/prosody-plugins/
|
||||
wget https://raw.githubusercontent.com/jitsi-contrib/prosody-plugins/main/mod_event_sync.lua
|
||||
|
||||
# Or if using git
|
||||
git clone https://github.com/jitsi-contrib/prosody-plugins.git
|
||||
cp prosody-plugins/mod_event_sync.lua /usr/share/jitsi-meet/prosody-plugins/
|
||||
```
|
||||
|
||||
### 2. Webhook Configuration
|
||||
|
||||
Add to `/etc/prosody/conf.d/[YOUR_DOMAIN].cfg.lua`:
|
||||
|
||||
```lua
|
||||
Component "conference.meet.example.com" "muc"
|
||||
storage = "memory"
|
||||
modules_enabled = {
|
||||
"muc_meeting_id";
|
||||
"muc_domain_mapper";
|
||||
"polls";
|
||||
"event_sync"; -- Enable event sync
|
||||
}
|
||||
|
||||
-- Event sync webhook configuration
|
||||
event_sync_url = "https://your-reflector-domain.com/v1/jitsi/events"
|
||||
event_sync_secret = "your-webhook-secret-here"
|
||||
|
||||
-- Events to track
|
||||
event_sync_events = {
|
||||
"muc-occupant-joined",
|
||||
"muc-occupant-left",
|
||||
"jibri-recording-on",
|
||||
"jibri-recording-off"
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Restart Services
|
||||
|
||||
After configuration changes, restart all services:
|
||||
|
||||
```bash
|
||||
systemctl restart prosody
|
||||
systemctl restart jicofo
|
||||
systemctl restart jitsi-videobridge2
|
||||
systemctl restart jibri
|
||||
systemctl restart nginx
|
||||
```
|
||||
|
||||
## Reflector Room Configuration
|
||||
|
||||
### 1. Create Jitsi Room
|
||||
|
||||
When creating rooms in Reflector, set the platform field:
|
||||
|
||||
```bash
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"name": "my-jitsi-room",
|
||||
"platform": "jitsi",
|
||||
"recording_type": "cloud",
|
||||
"recording_trigger": "automatic-2nd-participant",
|
||||
"is_locked": false,
|
||||
"room_mode": "normal"
|
||||
}'
|
||||
```
|
||||
|
||||
### 2. Meeting Creation
|
||||
|
||||
Meetings will automatically use Jitsi when the room platform is set to "jitsi":
|
||||
|
||||
```bash
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms/my-jitsi-room/meeting" \
|
||||
-H "Authorization: Bearer $AUTH_TOKEN"
|
||||
```
|
||||
|
||||
## Testing the Integration
|
||||
|
||||
### 1. Health Check
|
||||
|
||||
Verify Jitsi webhook configuration:
|
||||
|
||||
```bash
|
||||
curl "https://your-reflector-domain.com/v1/jitsi/health"
|
||||
```
|
||||
|
||||
Expected response:
|
||||
```json
|
||||
{
|
||||
"status": "ok",
|
||||
"service": "jitsi-webhooks",
|
||||
"timestamp": "2025-01-15T10:30:00.000Z",
|
||||
"webhook_secret_configured": true
|
||||
}
|
||||
```
|
||||
|
||||
### 2. Room Creation Test
|
||||
|
||||
1. Create a Jitsi room via Reflector API
|
||||
2. Start a meeting - should generate Jitsi Meet URL with JWT token
|
||||
3. Join with multiple participants - should trigger participant events
|
||||
4. Start recording - should trigger Jibri recording workflow
|
||||
|
||||
### 3. Webhook Event Test
|
||||
|
||||
Monitor Reflector logs for incoming webhook events:
|
||||
|
||||
```bash
|
||||
# Check for participant events
|
||||
curl -X POST "https://your-reflector-domain.com/v1/jitsi/events" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Jitsi-Signature: test-signature" \
|
||||
-d '{
|
||||
"event": "muc-occupant-joined",
|
||||
"room": "test-room-name",
|
||||
"timestamp": "2025-01-15T10:30:00.000Z",
|
||||
"data": {}
|
||||
}'
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
#### JWT Authentication Failures
|
||||
|
||||
**Symptoms:** Users can't join rooms, "Authentication failed" errors
|
||||
|
||||
**Solutions:**
|
||||
1. Verify JWT secret matches between Jitsi and Reflector
|
||||
2. Check JWT token expiration (default 8 hours)
|
||||
3. Ensure system clocks are synchronized
|
||||
4. Validate JWT issuer/audience configuration
|
||||
|
||||
```bash
|
||||
# Debug JWT tokens
|
||||
echo "JWT_TOKEN_HERE" | cut -d'.' -f2 | base64 -d | jq
|
||||
```
|
||||
|
||||
#### Webhook Events Not Received
|
||||
|
||||
**Symptoms:** Participant counts not updating, recording events missing
|
||||
|
||||
**Solutions:**
|
||||
1. Verify event_sync module is loaded in Prosody
|
||||
2. Check webhook URL accessibility from Jitsi server
|
||||
3. Validate webhook signature generation
|
||||
4. Review Prosody and Reflector logs
|
||||
|
||||
```bash
|
||||
# Test webhook connectivity
|
||||
curl -v "https://your-reflector-domain.com/v1/jitsi/health"
|
||||
|
||||
# Check Prosody logs
|
||||
tail -f /var/log/prosody/prosody.log
|
||||
|
||||
# Check Reflector logs
|
||||
docker logs your-reflector-container
|
||||
```
|
||||
|
||||
#### Recording Issues
|
||||
|
||||
**Symptoms:** Recordings not starting, finalize script errors
|
||||
|
||||
**Solutions:**
|
||||
1. Verify Jibri service status and configuration
|
||||
2. Check recording directory permissions
|
||||
3. Validate finalize script execution permissions
|
||||
4. Monitor Jibri logs for errors
|
||||
|
||||
```bash
|
||||
# Check Jibri status
|
||||
systemctl status jibri
|
||||
|
||||
# Test finalize script
|
||||
sudo -u jibri /opt/jitsi/jibri/finalize.sh "/test/recording.mp4" "test-room"
|
||||
|
||||
# Check Jibri logs
|
||||
journalctl -u jibri -f
|
||||
```
|
||||
|
||||
### Debug Commands
|
||||
|
||||
```bash
|
||||
# Verify Jitsi configuration
|
||||
prosodyctl check config
|
||||
|
||||
# Test JWT generation
|
||||
curl -X POST "https://your-reflector-domain.com/v1/rooms/test/meeting" \
|
||||
-H "Authorization: Bearer $TOKEN" -v
|
||||
|
||||
# Monitor webhook events
|
||||
tail -f /var/log/reflector/app.log | grep jitsi
|
||||
|
||||
# Check room participant counts
|
||||
curl "https://your-reflector-domain.com/v1/rooms" \
|
||||
-H "Authorization: Bearer $TOKEN" | jq '.data[].num_clients'
|
||||
```
|
||||
|
||||
### Performance Optimization
|
||||
|
||||
#### For High-Concurrent Usage
|
||||
|
||||
1. **Jitsi Videobridge Tuning:**
|
||||
```bash
|
||||
# /etc/jitsi/videobridge/sip-communicator.properties
|
||||
org.jitsi.videobridge.STATISTICS_INTERVAL=5000
|
||||
org.jitsi.videobridge.load.INITIAL_STREAM_LIMIT=50
|
||||
```
|
||||
|
||||
2. **Database Connection Pooling:**
|
||||
```python
|
||||
# In your Reflector settings
|
||||
DATABASE_POOL_SIZE=20
|
||||
DATABASE_MAX_OVERFLOW=30
|
||||
```
|
||||
|
||||
3. **Redis Configuration:**
|
||||
```bash
|
||||
# For webhook event caching
|
||||
REDIS_URL=redis://localhost:6379/1
|
||||
WEBHOOK_EVENT_TTL=3600
|
||||
```
|
||||
|
||||
## Security Considerations
|
||||
|
||||
### Network Security
|
||||
- Use HTTPS/WSS for all communications
|
||||
- Implement proper firewall rules
|
||||
- Consider VPN for server-to-server communication
|
||||
|
||||
### Authentication Security
|
||||
- Rotate JWT secrets regularly
|
||||
- Use strong webhook secrets (32+ characters)
|
||||
- Implement rate limiting on webhook endpoints
|
||||
|
||||
### Recording Security
|
||||
- Encrypt recordings at rest
|
||||
- Implement access controls for recording files
|
||||
- Regular security audits of file permissions
|
||||
|
||||
## Support
|
||||
|
||||
For additional support:
|
||||
|
||||
1. **Reflector Issues:** Check GitHub issues or create new ones
|
||||
2. **Jitsi Community:** [Community Forum](https://community.jitsi.org/)
|
||||
3. **Documentation:** [Jitsi Developer Guide](https://jitsi.github.io/handbook/)
|
||||
|
||||
## Migration from Whereby
|
||||
|
||||
If migrating from Whereby integration:
|
||||
|
||||
1. Update existing rooms to use "jitsi" platform
|
||||
2. Verify webhook configurations are updated
|
||||
3. Test recording workflows thoroughly
|
||||
4. Monitor participant event accuracy
|
||||
5. Update any custom integrations using meeting APIs
|
||||
|
||||
The platform abstraction layer ensures smooth migration with minimal API changes.
|
||||
@@ -14,7 +14,7 @@ Webhooks are configured at the room level with two fields:
|
||||
|
||||
### `transcript.completed`
|
||||
|
||||
Triggered when a transcript has been fully processed, including transcription, diarization, summarization, topic detection and calendar event integration.
|
||||
Triggered when a transcript has been fully processed, including transcription, diarization, summarization, and topic detection.
|
||||
|
||||
### `test`
|
||||
|
||||
@@ -128,27 +128,6 @@ This event includes a convenient URL for accessing the transcript:
|
||||
"room": {
|
||||
"id": "room-789",
|
||||
"name": "Product Team Room"
|
||||
},
|
||||
"calendar_event": {
|
||||
"id": "calendar-event-123",
|
||||
"ics_uid": "event-123",
|
||||
"title": "Q3 Product Planning Meeting",
|
||||
"start_time": "2025-08-27T12:00:00Z",
|
||||
"end_time": "2025-08-27T12:30:00Z",
|
||||
"description": "Team discussed Q3 product roadmap, prioritizing mobile app features and API improvements.",
|
||||
"location": "Conference Room 1",
|
||||
"attendees": [
|
||||
{
|
||||
"id": "participant-1",
|
||||
"name": "John Doe",
|
||||
"speaker": "Speaker 1"
|
||||
},
|
||||
{
|
||||
"id": "participant-2",
|
||||
"name": "Jane Smith",
|
||||
"speaker": "Speaker 2"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -27,7 +27,7 @@ AUTH_JWT_AUDIENCE=
|
||||
#TRANSCRIPT_MODAL_API_KEY=xxxxx
|
||||
|
||||
TRANSCRIPT_BACKEND=modal
|
||||
TRANSCRIPT_URL=https://monadical-sas--reflector-transcriber-parakeet-web.modal.run
|
||||
TRANSCRIPT_URL=https://monadical-sas--reflector-transcriber-web.modal.run
|
||||
TRANSCRIPT_MODAL_API_KEY=
|
||||
|
||||
## =======================================================
|
||||
@@ -71,27 +71,3 @@ DIARIZATION_URL=https://monadical-sas--reflector-diarizer-web.modal.run
|
||||
|
||||
## Sentry DSN configuration
|
||||
#SENTRY_DSN=
|
||||
|
||||
## =======================================================
|
||||
## Video Platform Configuration
|
||||
## =======================================================
|
||||
|
||||
## Whereby
|
||||
#WHEREBY_API_KEY=your-whereby-api-key
|
||||
#WHEREBY_WEBHOOK_SECRET=your-whereby-webhook-secret
|
||||
#AWS_WHEREBY_ACCESS_KEY_ID=your-aws-key
|
||||
#AWS_WHEREBY_ACCESS_KEY_SECRET=your-aws-secret
|
||||
#AWS_PROCESS_RECORDING_QUEUE_URL=https://sqs.us-west-2.amazonaws.com/...
|
||||
|
||||
## Daily.co
|
||||
#DAILY_API_KEY=your-daily-api-key
|
||||
#DAILY_WEBHOOK_SECRET=your-daily-webhook-secret
|
||||
#DAILY_SUBDOMAIN=your-subdomain
|
||||
#AWS_DAILY_S3_BUCKET=your-daily-bucket
|
||||
#AWS_DAILY_S3_REGION=us-west-2
|
||||
#AWS_DAILY_ROLE_ARN=arn:aws:iam::ACCOUNT:role/DailyRecording
|
||||
|
||||
## Platform Selection
|
||||
#DAILY_MIGRATION_ENABLED=false # Enable Daily.co support
|
||||
#DAILY_MIGRATION_ROOM_IDS=[] # Specific rooms to use Daily
|
||||
#DEFAULT_VIDEO_PLATFORM=whereby # Default platform for new rooms
|
||||
|
||||
@@ -77,7 +77,7 @@ image = (
|
||||
.pip_install(
|
||||
"hf_transfer==0.1.9",
|
||||
"huggingface_hub[hf-xet]==0.31.2",
|
||||
"nemo_toolkit[asr]==2.5.0",
|
||||
"nemo_toolkit[asr]==2.3.0",
|
||||
"cuda-python==12.8.0",
|
||||
"fastapi==0.115.12",
|
||||
"numpy<2",
|
||||
@@ -0,0 +1,38 @@
|
||||
"""Add events column to meetings table
|
||||
|
||||
Revision ID: 2890b5104577
|
||||
Revises: 6e6ea8e607c5
|
||||
Create Date: 2025-09-02 17:51:41.620777
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "2890b5104577"
|
||||
down_revision: Union[str, None] = "6e6ea8e607c5"
|
||||
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(
|
||||
"events", sa.JSON(), server_default=sa.text("'[]'"), nullable=False
|
||||
)
|
||||
)
|
||||
|
||||
# ### 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("events")
|
||||
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,53 +0,0 @@
|
||||
"""remove_one_active_meeting_per_room_constraint
|
||||
|
||||
Revision ID: 6025e9b2bef2
|
||||
Revises: 2ae3db106d4e
|
||||
Create Date: 2025-08-18 18:45:44.418392
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "6025e9b2bef2"
|
||||
down_revision: Union[str, None] = "2ae3db106d4e"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# Remove the unique constraint that prevents multiple active meetings per room
|
||||
# This is needed to support calendar integration with overlapping meetings
|
||||
# Check if index exists before trying to drop it
|
||||
from alembic import context
|
||||
|
||||
if context.get_context().dialect.name == "postgresql":
|
||||
conn = op.get_bind()
|
||||
result = conn.execute(
|
||||
sa.text(
|
||||
"SELECT 1 FROM pg_indexes WHERE indexname = 'idx_one_active_meeting_per_room'"
|
||||
)
|
||||
)
|
||||
if result.fetchone():
|
||||
op.drop_index("idx_one_active_meeting_per_room", table_name="meeting")
|
||||
else:
|
||||
# For SQLite, just try to drop it
|
||||
try:
|
||||
op.drop_index("idx_one_active_meeting_per_room", table_name="meeting")
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# Restore the unique constraint
|
||||
op.create_index(
|
||||
"idx_one_active_meeting_per_room",
|
||||
"meeting",
|
||||
["room_id"],
|
||||
unique=True,
|
||||
postgresql_where=sa.text("is_active = true"),
|
||||
sqlite_where=sa.text("is_active = 1"),
|
||||
)
|
||||
@@ -8,6 +8,7 @@ Create Date: 2025-09-10 10:47:06.006819
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
@@ -20,6 +21,7 @@ depends_on: Union[str, Sequence[str], None] = None
|
||||
def upgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.alter_column("room_id", existing_type=sa.VARCHAR(), nullable=False)
|
||||
batch_op.create_foreign_key(
|
||||
None, "room", ["room_id"], ["id"], ondelete="CASCADE"
|
||||
)
|
||||
@@ -31,5 +33,6 @@ def downgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.drop_constraint("meeting_room_id_fkey", type_="foreignkey")
|
||||
batch_op.alter_column("room_id", existing_type=sa.VARCHAR(), nullable=True)
|
||||
|
||||
# ### end Alembic commands ###
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
"""add_platform_support
|
||||
"""Add VideoPlatform enum for rooms and meetings
|
||||
|
||||
Revision ID: 1e49625677e4
|
||||
Revises: dc035ff72fd5
|
||||
Create Date: 2025-10-08 13:17:29.943612
|
||||
Revision ID: 6e6ea8e607c5
|
||||
Revises: 61882a919591
|
||||
Create Date: 2025-09-02 17:33:21.022214
|
||||
|
||||
"""
|
||||
|
||||
@@ -12,39 +12,33 @@ import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "1e49625677e4"
|
||||
down_revision: Union[str, None] = "dc035ff72fd5"
|
||||
revision: str = "6e6ea8e607c5"
|
||||
down_revision: Union[str, None] = "61882a919591"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Add platform field with default 'whereby' for backward compatibility."""
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.add_column(
|
||||
sa.Column(
|
||||
"platform",
|
||||
sa.String(),
|
||||
nullable=False,
|
||||
server_default="whereby",
|
||||
)
|
||||
)
|
||||
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.add_column(
|
||||
sa.Column(
|
||||
"platform",
|
||||
sa.String(),
|
||||
nullable=False,
|
||||
server_default="whereby",
|
||||
)
|
||||
sa.Column("platform", sa.String(), server_default="whereby", nullable=False)
|
||||
)
|
||||
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.add_column(
|
||||
sa.Column("platform", sa.String(), server_default="whereby", nullable=False)
|
||||
)
|
||||
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Remove platform field."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.drop_column("platform")
|
||||
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.drop_column("platform")
|
||||
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.drop_column("platform")
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,34 +0,0 @@
|
||||
"""add_grace_period_fields_to_meeting
|
||||
|
||||
Revision ID: d4a1c446458c
|
||||
Revises: 6025e9b2bef2
|
||||
Create Date: 2025-08-18 18:50:37.768052
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "d4a1c446458c"
|
||||
down_revision: Union[str, None] = "6025e9b2bef2"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# Add fields to track when participants left for grace period logic
|
||||
op.add_column(
|
||||
"meeting", sa.Column("last_participant_left_at", sa.DateTime(timezone=True))
|
||||
)
|
||||
op.add_column(
|
||||
"meeting",
|
||||
sa.Column("grace_period_minutes", sa.Integer, server_default=sa.text("15")),
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.drop_column("meeting", "grace_period_minutes")
|
||||
op.drop_column("meeting", "last_participant_left_at")
|
||||
@@ -1,129 +0,0 @@
|
||||
"""add calendar
|
||||
|
||||
Revision ID: d8e204bbf615
|
||||
Revises: d4a1c446458c
|
||||
Create Date: 2025-09-10 19:56:22.295756
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "d8e204bbf615"
|
||||
down_revision: Union[str, None] = "d4a1c446458c"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"calendar_event",
|
||||
sa.Column("id", sa.String(), nullable=False),
|
||||
sa.Column("room_id", sa.String(), nullable=False),
|
||||
sa.Column("ics_uid", sa.Text(), nullable=False),
|
||||
sa.Column("title", sa.Text(), nullable=True),
|
||||
sa.Column("description", sa.Text(), nullable=True),
|
||||
sa.Column("start_time", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("end_time", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("attendees", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
|
||||
sa.Column("location", sa.Text(), nullable=True),
|
||||
sa.Column("ics_raw_data", sa.Text(), nullable=True),
|
||||
sa.Column("last_synced", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column(
|
||||
"is_deleted", sa.Boolean(), server_default=sa.text("false"), nullable=False
|
||||
),
|
||||
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["room_id"],
|
||||
["room.id"],
|
||||
name="fk_calendar_event_room_id",
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id"),
|
||||
sa.UniqueConstraint("room_id", "ics_uid", name="uq_room_calendar_event"),
|
||||
)
|
||||
with op.batch_alter_table("calendar_event", schema=None) as batch_op:
|
||||
batch_op.create_index(
|
||||
"idx_calendar_event_deleted",
|
||||
["is_deleted"],
|
||||
unique=False,
|
||||
postgresql_where=sa.text("NOT is_deleted"),
|
||||
)
|
||||
batch_op.create_index(
|
||||
"idx_calendar_event_room_start", ["room_id", "start_time"], unique=False
|
||||
)
|
||||
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.add_column(sa.Column("calendar_event_id", sa.String(), nullable=True))
|
||||
batch_op.add_column(
|
||||
sa.Column(
|
||||
"calendar_metadata",
|
||||
postgresql.JSONB(astext_type=sa.Text()),
|
||||
nullable=True,
|
||||
)
|
||||
)
|
||||
batch_op.create_index(
|
||||
"idx_meeting_calendar_event", ["calendar_event_id"], unique=False
|
||||
)
|
||||
batch_op.create_foreign_key(
|
||||
"fk_meeting_calendar_event_id",
|
||||
"calendar_event",
|
||||
["calendar_event_id"],
|
||||
["id"],
|
||||
ondelete="SET NULL",
|
||||
)
|
||||
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.add_column(sa.Column("ics_url", sa.Text(), nullable=True))
|
||||
batch_op.add_column(
|
||||
sa.Column(
|
||||
"ics_fetch_interval", sa.Integer(), server_default="300", nullable=True
|
||||
)
|
||||
)
|
||||
batch_op.add_column(
|
||||
sa.Column(
|
||||
"ics_enabled",
|
||||
sa.Boolean(),
|
||||
server_default=sa.text("false"),
|
||||
nullable=False,
|
||||
)
|
||||
)
|
||||
batch_op.add_column(
|
||||
sa.Column("ics_last_sync", sa.DateTime(timezone=True), nullable=True)
|
||||
)
|
||||
batch_op.add_column(sa.Column("ics_last_etag", sa.Text(), nullable=True))
|
||||
batch_op.create_index("idx_room_ics_enabled", ["ics_enabled"], unique=False)
|
||||
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
with op.batch_alter_table("room", schema=None) as batch_op:
|
||||
batch_op.drop_index("idx_room_ics_enabled")
|
||||
batch_op.drop_column("ics_last_etag")
|
||||
batch_op.drop_column("ics_last_sync")
|
||||
batch_op.drop_column("ics_enabled")
|
||||
batch_op.drop_column("ics_fetch_interval")
|
||||
batch_op.drop_column("ics_url")
|
||||
|
||||
with op.batch_alter_table("meeting", schema=None) as batch_op:
|
||||
batch_op.drop_constraint("fk_meeting_calendar_event_id", type_="foreignkey")
|
||||
batch_op.drop_index("idx_meeting_calendar_event")
|
||||
batch_op.drop_column("calendar_metadata")
|
||||
batch_op.drop_column("calendar_event_id")
|
||||
|
||||
with op.batch_alter_table("calendar_event", schema=None) as batch_op:
|
||||
batch_op.drop_index("idx_calendar_event_room_start")
|
||||
batch_op.drop_index(
|
||||
"idx_calendar_event_deleted", postgresql_where=sa.text("NOT is_deleted")
|
||||
)
|
||||
|
||||
op.drop_table("calendar_event")
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,43 +0,0 @@
|
||||
"""remove_grace_period_fields
|
||||
|
||||
Revision ID: dc035ff72fd5
|
||||
Revises: d8e204bbf615
|
||||
Create Date: 2025-09-11 10:36:45.197588
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "dc035ff72fd5"
|
||||
down_revision: Union[str, None] = "d8e204bbf615"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# Remove grace period columns from meeting table
|
||||
op.drop_column("meeting", "last_participant_left_at")
|
||||
op.drop_column("meeting", "grace_period_minutes")
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# Add back grace period columns to meeting table
|
||||
op.add_column(
|
||||
"meeting",
|
||||
sa.Column(
|
||||
"last_participant_left_at", sa.DateTime(timezone=True), nullable=True
|
||||
),
|
||||
)
|
||||
op.add_column(
|
||||
"meeting",
|
||||
sa.Column(
|
||||
"grace_period_minutes",
|
||||
sa.Integer(),
|
||||
server_default=sa.text("15"),
|
||||
nullable=True,
|
||||
),
|
||||
)
|
||||
@@ -12,6 +12,7 @@ dependencies = [
|
||||
"requests>=2.31.0",
|
||||
"aiortc>=1.5.0",
|
||||
"sortedcontainers>=2.4.0",
|
||||
"loguru>=0.7.0",
|
||||
"pydantic-settings>=2.0.2",
|
||||
"structlog>=23.1.0",
|
||||
"uvicorn[standard]>=0.23.1",
|
||||
@@ -26,6 +27,7 @@ dependencies = [
|
||||
"prometheus-fastapi-instrumentator>=6.1.0",
|
||||
"sentencepiece>=0.1.99",
|
||||
"protobuf>=4.24.3",
|
||||
"profanityfilter>=2.0.6",
|
||||
"celery>=5.3.4",
|
||||
"redis>=5.0.1",
|
||||
"python-jose[cryptography]>=3.3.0",
|
||||
@@ -38,7 +40,7 @@ dependencies = [
|
||||
"llama-index-llms-openai-like>=0.4.0",
|
||||
"pytest-env>=1.1.5",
|
||||
"webvtt-py>=0.5.0",
|
||||
"icalendar>=6.0.0",
|
||||
"PyJWT>=2.8.0",
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
@@ -112,14 +114,13 @@ source = ["reflector"]
|
||||
[tool.pytest_env]
|
||||
ENVIRONMENT = "pytest"
|
||||
DATABASE_URL = "postgresql://test_user:test_password@localhost:15432/reflector_test"
|
||||
AUTH_BACKEND = "jwt"
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v"
|
||||
testpaths = ["tests"]
|
||||
asyncio_mode = "auto"
|
||||
markers = [
|
||||
"model_api: tests for the unified model-serving HTTP API (backend- and hardware-agnostic)",
|
||||
"gpu_modal: mark test to run only with GPU Modal endpoints (deselect with '-m \"not gpu_modal\"')",
|
||||
]
|
||||
|
||||
[tool.ruff.lint]
|
||||
@@ -131,7 +132,7 @@ select = [
|
||||
|
||||
[tool.ruff.lint.per-file-ignores]
|
||||
"reflector/processors/summary/summary_builder.py" = ["E501"]
|
||||
"gpu/modal_deployments/**.py" = ["PLC0415"]
|
||||
"gpu/**.py" = ["PLC0415"]
|
||||
"reflector/tools/**.py" = ["PLC0415"]
|
||||
"migrations/versions/**.py" = ["PLC0415"]
|
||||
"tests/**.py" = ["PLC0415"]
|
||||
|
||||
@@ -12,7 +12,9 @@ from reflector.events import subscribers_shutdown, subscribers_startup
|
||||
from reflector.logger import logger
|
||||
from reflector.metrics import metrics_init
|
||||
from reflector.settings import settings
|
||||
from reflector.views.daily import router as daily_router
|
||||
from reflector.video_platforms.jitsi import router as jitsi_router
|
||||
from reflector.video_platforms.whereby import router as whereby_router
|
||||
from reflector.views.jibri_webhook import router as jibri_webhook_router
|
||||
from reflector.views.meetings import router as meetings_router
|
||||
from reflector.views.rooms import router as rooms_router
|
||||
from reflector.views.rtc_offer import router as rtc_offer_router
|
||||
@@ -27,8 +29,6 @@ from reflector.views.transcripts_upload import router as transcripts_upload_rout
|
||||
from reflector.views.transcripts_webrtc import router as transcripts_webrtc_router
|
||||
from reflector.views.transcripts_websocket import router as transcripts_websocket_router
|
||||
from reflector.views.user import router as user_router
|
||||
from reflector.views.user_websocket import router as user_ws_router
|
||||
from reflector.views.whereby import router as whereby_router
|
||||
from reflector.views.zulip import router as zulip_router
|
||||
|
||||
try:
|
||||
@@ -67,12 +67,6 @@ app.add_middleware(
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
|
||||
@app.get("/health")
|
||||
async def health():
|
||||
return {"status": "healthy"}
|
||||
|
||||
|
||||
# metrics
|
||||
instrumentator = Instrumentator(
|
||||
excluded_handlers=["/docs", "/metrics"],
|
||||
@@ -92,10 +86,10 @@ app.include_router(transcripts_websocket_router, prefix="/v1")
|
||||
app.include_router(transcripts_webrtc_router, prefix="/v1")
|
||||
app.include_router(transcripts_process_router, prefix="/v1")
|
||||
app.include_router(user_router, prefix="/v1")
|
||||
app.include_router(user_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")
|
||||
app.include_router(jitsi_router, prefix="/v1")
|
||||
app.include_router(jibri_webhook_router) # No /v1 prefix, uses /api/v1/jibri
|
||||
add_pagination(app)
|
||||
|
||||
# prepare celery
|
||||
|
||||
@@ -67,8 +67,7 @@ def current_user(
|
||||
try:
|
||||
payload = jwtauth.verify_token(token)
|
||||
sub = payload["sub"]
|
||||
email = payload["email"]
|
||||
return UserInfo(sub=sub, email=email)
|
||||
return UserInfo(sub=sub)
|
||||
except JWTError as e:
|
||||
logger.error(f"JWT error: {e}")
|
||||
raise HTTPException(status_code=401, detail="Invalid authentication")
|
||||
|
||||
@@ -24,7 +24,6 @@ def get_database() -> databases.Database:
|
||||
|
||||
|
||||
# import models
|
||||
import reflector.db.calendar_events # noqa
|
||||
import reflector.db.meetings # noqa
|
||||
import reflector.db.recordings # noqa
|
||||
import reflector.db.rooms # noqa
|
||||
|
||||
@@ -1,187 +0,0 @@
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import Any
|
||||
|
||||
import sqlalchemy as sa
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy.dialects.postgresql import JSONB
|
||||
|
||||
from reflector.db import get_database, metadata
|
||||
from reflector.utils import generate_uuid4
|
||||
|
||||
calendar_events = sa.Table(
|
||||
"calendar_event",
|
||||
metadata,
|
||||
sa.Column("id", sa.String, primary_key=True),
|
||||
sa.Column(
|
||||
"room_id",
|
||||
sa.String,
|
||||
sa.ForeignKey("room.id", ondelete="CASCADE", name="fk_calendar_event_room_id"),
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column("ics_uid", sa.Text, nullable=False),
|
||||
sa.Column("title", sa.Text),
|
||||
sa.Column("description", sa.Text),
|
||||
sa.Column("start_time", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("end_time", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("attendees", JSONB),
|
||||
sa.Column("location", sa.Text),
|
||||
sa.Column("ics_raw_data", sa.Text),
|
||||
sa.Column("last_synced", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("is_deleted", sa.Boolean, nullable=False, server_default=sa.false()),
|
||||
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.UniqueConstraint("room_id", "ics_uid", name="uq_room_calendar_event"),
|
||||
sa.Index("idx_calendar_event_room_start", "room_id", "start_time"),
|
||||
sa.Index(
|
||||
"idx_calendar_event_deleted",
|
||||
"is_deleted",
|
||||
postgresql_where=sa.text("NOT is_deleted"),
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
class CalendarEvent(BaseModel):
|
||||
id: str = Field(default_factory=generate_uuid4)
|
||||
room_id: str
|
||||
ics_uid: str
|
||||
title: str | None = None
|
||||
description: str | None = None
|
||||
start_time: datetime
|
||||
end_time: datetime
|
||||
attendees: list[dict[str, Any]] | None = None
|
||||
location: str | None = None
|
||||
ics_raw_data: str | None = None
|
||||
last_synced: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
|
||||
is_deleted: bool = False
|
||||
created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
|
||||
updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
|
||||
|
||||
|
||||
class CalendarEventController:
|
||||
async def get_by_room(
|
||||
self,
|
||||
room_id: str,
|
||||
include_deleted: bool = False,
|
||||
start_after: datetime | None = None,
|
||||
end_before: datetime | None = None,
|
||||
) -> list[CalendarEvent]:
|
||||
query = calendar_events.select().where(calendar_events.c.room_id == room_id)
|
||||
|
||||
if not include_deleted:
|
||||
query = query.where(calendar_events.c.is_deleted == False)
|
||||
|
||||
if start_after:
|
||||
query = query.where(calendar_events.c.start_time >= start_after)
|
||||
|
||||
if end_before:
|
||||
query = query.where(calendar_events.c.end_time <= end_before)
|
||||
|
||||
query = query.order_by(calendar_events.c.start_time.asc())
|
||||
|
||||
results = await get_database().fetch_all(query)
|
||||
return [CalendarEvent(**result) for result in results]
|
||||
|
||||
async def get_upcoming(
|
||||
self, room_id: str, minutes_ahead: int = 120
|
||||
) -> list[CalendarEvent]:
|
||||
"""Get upcoming events for a room within the specified minutes, including currently happening events."""
|
||||
now = datetime.now(timezone.utc)
|
||||
future_time = now + timedelta(minutes=minutes_ahead)
|
||||
|
||||
query = (
|
||||
calendar_events.select()
|
||||
.where(
|
||||
sa.and_(
|
||||
calendar_events.c.room_id == room_id,
|
||||
calendar_events.c.is_deleted == False,
|
||||
calendar_events.c.start_time <= future_time,
|
||||
calendar_events.c.end_time >= now,
|
||||
)
|
||||
)
|
||||
.order_by(calendar_events.c.start_time.asc())
|
||||
)
|
||||
|
||||
results = await get_database().fetch_all(query)
|
||||
return [CalendarEvent(**result) for result in results]
|
||||
|
||||
async def get_by_id(self, event_id: str) -> CalendarEvent | None:
|
||||
query = calendar_events.select().where(calendar_events.c.id == event_id)
|
||||
result = await get_database().fetch_one(query)
|
||||
return CalendarEvent(**result) if result else None
|
||||
|
||||
async def get_by_ics_uid(self, room_id: str, ics_uid: str) -> CalendarEvent | None:
|
||||
query = calendar_events.select().where(
|
||||
sa.and_(
|
||||
calendar_events.c.room_id == room_id,
|
||||
calendar_events.c.ics_uid == ics_uid,
|
||||
)
|
||||
)
|
||||
result = await get_database().fetch_one(query)
|
||||
return CalendarEvent(**result) if result else None
|
||||
|
||||
async def upsert(self, event: CalendarEvent) -> CalendarEvent:
|
||||
existing = await self.get_by_ics_uid(event.room_id, event.ics_uid)
|
||||
|
||||
if existing:
|
||||
event.id = existing.id
|
||||
event.created_at = existing.created_at
|
||||
event.updated_at = datetime.now(timezone.utc)
|
||||
|
||||
query = (
|
||||
calendar_events.update()
|
||||
.where(calendar_events.c.id == existing.id)
|
||||
.values(**event.model_dump())
|
||||
)
|
||||
else:
|
||||
query = calendar_events.insert().values(**event.model_dump())
|
||||
|
||||
await get_database().execute(query)
|
||||
return event
|
||||
|
||||
async def soft_delete_missing(
|
||||
self, room_id: str, current_ics_uids: list[str]
|
||||
) -> int:
|
||||
"""Soft delete future events that are no longer in the calendar."""
|
||||
now = datetime.now(timezone.utc)
|
||||
|
||||
select_query = calendar_events.select().where(
|
||||
sa.and_(
|
||||
calendar_events.c.room_id == room_id,
|
||||
calendar_events.c.start_time > now,
|
||||
calendar_events.c.is_deleted == False,
|
||||
calendar_events.c.ics_uid.notin_(current_ics_uids)
|
||||
if current_ics_uids
|
||||
else True,
|
||||
)
|
||||
)
|
||||
|
||||
to_delete = await get_database().fetch_all(select_query)
|
||||
delete_count = len(to_delete)
|
||||
|
||||
if delete_count > 0:
|
||||
update_query = (
|
||||
calendar_events.update()
|
||||
.where(
|
||||
sa.and_(
|
||||
calendar_events.c.room_id == room_id,
|
||||
calendar_events.c.start_time > now,
|
||||
calendar_events.c.is_deleted == False,
|
||||
calendar_events.c.ics_uid.notin_(current_ics_uids)
|
||||
if current_ics_uids
|
||||
else True,
|
||||
)
|
||||
)
|
||||
.values(is_deleted=True, updated_at=now)
|
||||
)
|
||||
|
||||
await get_database().execute(update_query)
|
||||
|
||||
return delete_count
|
||||
|
||||
async def delete_by_room(self, room_id: str) -> int:
|
||||
query = calendar_events.delete().where(calendar_events.c.room_id == room_id)
|
||||
result = await get_database().execute(query)
|
||||
return result.rowcount
|
||||
|
||||
|
||||
calendar_events_controller = CalendarEventController()
|
||||
@@ -1,13 +1,11 @@
|
||||
from datetime import datetime
|
||||
from typing import Any, Literal
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any, Dict, List, Literal
|
||||
|
||||
import sqlalchemy as sa
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy.dialects.postgresql import JSONB
|
||||
|
||||
from reflector.db import get_database, metadata
|
||||
from reflector.db.rooms import Room
|
||||
from reflector.platform_types import Platform
|
||||
from reflector.db.rooms import Room, VideoPlatform
|
||||
from reflector.utils import generate_uuid4
|
||||
|
||||
meetings = sa.Table(
|
||||
@@ -46,24 +44,15 @@ meetings = sa.Table(
|
||||
nullable=False,
|
||||
server_default=sa.true(),
|
||||
),
|
||||
sa.Column(
|
||||
"calendar_event_id",
|
||||
sa.String,
|
||||
sa.ForeignKey(
|
||||
"calendar_event.id",
|
||||
ondelete="SET NULL",
|
||||
name="fk_meeting_calendar_event_id",
|
||||
),
|
||||
),
|
||||
sa.Column("calendar_metadata", JSONB),
|
||||
sa.Column(
|
||||
"platform",
|
||||
sa.String,
|
||||
nullable=False,
|
||||
server_default="whereby",
|
||||
),
|
||||
sa.Column("platform", sa.String, nullable=False, server_default="whereby"),
|
||||
sa.Column("events", sa.JSON, nullable=False, server_default=sa.text("'[]'")),
|
||||
sa.Index("idx_meeting_room_id", "room_id"),
|
||||
sa.Index("idx_meeting_calendar_event", "calendar_event_id"),
|
||||
sa.Index(
|
||||
"idx_one_active_meeting_per_room",
|
||||
"room_id",
|
||||
unique=True,
|
||||
postgresql_where=sa.text("is_active = true"),
|
||||
),
|
||||
)
|
||||
|
||||
meeting_consent = sa.Table(
|
||||
@@ -101,14 +90,12 @@ class Meeting(BaseModel):
|
||||
is_locked: bool = False
|
||||
room_mode: Literal["normal", "group"] = "normal"
|
||||
recording_type: Literal["none", "local", "cloud"] = "cloud"
|
||||
recording_trigger: Literal[ # whereby-specific
|
||||
recording_trigger: Literal[
|
||||
"none", "prompt", "automatic", "automatic-2nd-participant"
|
||||
] = "automatic-2nd-participant"
|
||||
num_clients: int = 0
|
||||
is_active: bool = True
|
||||
calendar_event_id: str | None = None
|
||||
calendar_metadata: dict[str, Any] | None = None
|
||||
platform: Platform = "whereby"
|
||||
platform: VideoPlatform = VideoPlatform.WHEREBY
|
||||
events: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
|
||||
|
||||
class MeetingController:
|
||||
@@ -121,9 +108,6 @@ class MeetingController:
|
||||
start_date: datetime,
|
||||
end_date: datetime,
|
||||
room: Room,
|
||||
calendar_event_id: str | None = None,
|
||||
calendar_metadata: dict[str, Any] | None = None,
|
||||
platform: Platform = "whereby",
|
||||
):
|
||||
meeting = Meeting(
|
||||
id=id,
|
||||
@@ -137,9 +121,7 @@ class MeetingController:
|
||||
room_mode=room.room_mode,
|
||||
recording_type=room.recording_type,
|
||||
recording_trigger=room.recording_trigger,
|
||||
calendar_event_id=calendar_event_id,
|
||||
calendar_metadata=calendar_metadata,
|
||||
platform=platform,
|
||||
platform=room.platform,
|
||||
)
|
||||
query = meetings.insert().values(**meeting.model_dump())
|
||||
await get_database().execute(query)
|
||||
@@ -153,16 +135,7 @@ class MeetingController:
|
||||
self,
|
||||
room_name: str,
|
||||
) -> Meeting | None:
|
||||
"""
|
||||
Get a meeting by room name.
|
||||
For backward compatibility, returns the most recent meeting.
|
||||
"""
|
||||
end_date = getattr(meetings.c, "end_date")
|
||||
query = (
|
||||
meetings.select()
|
||||
.where(meetings.c.room_name == room_name)
|
||||
.order_by(end_date.desc())
|
||||
)
|
||||
query = meetings.select().where(meetings.c.room_name == room_name)
|
||||
result = await get_database().fetch_one(query)
|
||||
if not result:
|
||||
return None
|
||||
@@ -170,10 +143,6 @@ class MeetingController:
|
||||
return Meeting(**result)
|
||||
|
||||
async def get_active(self, room: Room, current_time: datetime) -> Meeting | None:
|
||||
"""
|
||||
Get latest active meeting for a room.
|
||||
For backward compatibility, returns the most recent active meeting.
|
||||
"""
|
||||
end_date = getattr(meetings.c, "end_date")
|
||||
query = (
|
||||
meetings.select()
|
||||
@@ -192,43 +161,6 @@ class MeetingController:
|
||||
|
||||
return Meeting(**result)
|
||||
|
||||
async def get_all_active_for_room(
|
||||
self, room: Room, current_time: datetime
|
||||
) -> list[Meeting]:
|
||||
end_date = getattr(meetings.c, "end_date")
|
||||
query = (
|
||||
meetings.select()
|
||||
.where(
|
||||
sa.and_(
|
||||
meetings.c.room_id == room.id,
|
||||
meetings.c.end_date > current_time,
|
||||
meetings.c.is_active,
|
||||
)
|
||||
)
|
||||
.order_by(end_date.desc())
|
||||
)
|
||||
results = await get_database().fetch_all(query)
|
||||
return [Meeting(**result) for result in results]
|
||||
|
||||
async def get_active_by_calendar_event(
|
||||
self, room: Room, calendar_event_id: str, current_time: datetime
|
||||
) -> Meeting | None:
|
||||
"""
|
||||
Get active meeting for a specific calendar event.
|
||||
"""
|
||||
query = meetings.select().where(
|
||||
sa.and_(
|
||||
meetings.c.room_id == room.id,
|
||||
meetings.c.calendar_event_id == calendar_event_id,
|
||||
meetings.c.end_date > current_time,
|
||||
meetings.c.is_active,
|
||||
)
|
||||
)
|
||||
result = await get_database().fetch_one(query)
|
||||
if not result:
|
||||
return None
|
||||
return Meeting(**result)
|
||||
|
||||
async def get_by_id(self, meeting_id: str, **kwargs) -> Meeting | None:
|
||||
query = meetings.select().where(meetings.c.id == meeting_id)
|
||||
result = await get_database().fetch_one(query)
|
||||
@@ -236,40 +168,71 @@ class MeetingController:
|
||||
return None
|
||||
return Meeting(**result)
|
||||
|
||||
async def get_by_calendar_event(self, calendar_event_id: str) -> Meeting | None:
|
||||
query = meetings.select().where(
|
||||
meetings.c.calendar_event_id == calendar_event_id
|
||||
)
|
||||
result = await get_database().fetch_one(query)
|
||||
if not result:
|
||||
return None
|
||||
return Meeting(**result)
|
||||
|
||||
async def update_meeting(self, meeting_id: str, **kwargs):
|
||||
query = meetings.update().where(meetings.c.id == meeting_id).values(**kwargs)
|
||||
await get_database().execute(query)
|
||||
|
||||
async def increment_num_clients(self, meeting_id: str):
|
||||
"""Atomically increment participant count."""
|
||||
query = (
|
||||
meetings.update()
|
||||
.where(meetings.c.id == meeting_id)
|
||||
.values(num_clients=meetings.c.num_clients + 1)
|
||||
)
|
||||
await get_database().execute(query)
|
||||
async def add_event(
|
||||
self, meeting_id: str, event_type: str, event_data: Dict[str, Any] = None
|
||||
):
|
||||
"""Add an event to a meeting's events list."""
|
||||
if event_data is None:
|
||||
event_data = {}
|
||||
|
||||
async def decrement_num_clients(self, meeting_id: str):
|
||||
"""Atomically decrement participant count (min 0)."""
|
||||
query = (
|
||||
event = {
|
||||
"type": event_type,
|
||||
"timestamp": datetime.now(tz=timezone.utc).isoformat(),
|
||||
"data": event_data,
|
||||
}
|
||||
|
||||
# Get current events
|
||||
query = meetings.select().where(meetings.c.id == meeting_id)
|
||||
result = await get_database().fetch_one(query)
|
||||
if not result:
|
||||
return
|
||||
|
||||
current_events = result["events"] or []
|
||||
current_events.append(event)
|
||||
|
||||
# Update with new events list
|
||||
update_query = (
|
||||
meetings.update()
|
||||
.where(meetings.c.id == meeting_id)
|
||||
.values(
|
||||
num_clients=sa.case(
|
||||
(meetings.c.num_clients > 0, meetings.c.num_clients - 1), else_=0
|
||||
)
|
||||
)
|
||||
.values(events=current_events)
|
||||
)
|
||||
await get_database().execute(query)
|
||||
await get_database().execute(update_query)
|
||||
|
||||
async def participant_joined(
|
||||
self, meeting_id: str, participant_data: Dict[str, Any] = None
|
||||
):
|
||||
"""Record a participant joined event."""
|
||||
await self.add_event(meeting_id, "participant_joined", participant_data)
|
||||
|
||||
async def participant_left(
|
||||
self, meeting_id: str, participant_data: Dict[str, Any] = None
|
||||
):
|
||||
"""Record a participant left event."""
|
||||
await self.add_event(meeting_id, "participant_left", participant_data)
|
||||
|
||||
async def recording_started(
|
||||
self, meeting_id: str, recording_data: Dict[str, Any] = None
|
||||
):
|
||||
"""Record a recording started event."""
|
||||
await self.add_event(meeting_id, "recording_started", recording_data)
|
||||
|
||||
async def recording_stopped(
|
||||
self, meeting_id: str, recording_data: Dict[str, Any] = None
|
||||
):
|
||||
"""Record a recording stopped event."""
|
||||
await self.add_event(meeting_id, "recording_stopped", recording_data)
|
||||
|
||||
async def get_events(self, meeting_id: str) -> List[Dict[str, Any]]:
|
||||
"""Get all events for a meeting."""
|
||||
query = meetings.select().where(meetings.c.id == meeting_id)
|
||||
result = await get_database().fetch_one(query)
|
||||
if not result:
|
||||
return []
|
||||
return result["events"] or []
|
||||
|
||||
|
||||
class MeetingConsentController:
|
||||
@@ -294,6 +257,7 @@ class MeetingConsentController:
|
||||
return MeetingConsent(**result)
|
||||
|
||||
async def upsert(self, consent: MeetingConsent) -> MeetingConsent:
|
||||
"""Create new consent or update existing one for authenticated users"""
|
||||
if consent.user_id:
|
||||
# For authenticated users, check if consent already exists
|
||||
# not transactional but we're ok with that; the consents ain't deleted anyways
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
import secrets
|
||||
from datetime import datetime, timezone
|
||||
from enum import StrEnum
|
||||
from sqlite3 import IntegrityError
|
||||
from typing import Literal, Optional
|
||||
from typing import Literal
|
||||
|
||||
import sqlalchemy
|
||||
from fastapi import HTTPException
|
||||
@@ -9,9 +10,14 @@ from pydantic import BaseModel, Field
|
||||
from sqlalchemy.sql import false, or_
|
||||
|
||||
from reflector.db import get_database, metadata
|
||||
from reflector.platform_types import Platform
|
||||
from reflector.utils import generate_uuid4
|
||||
|
||||
|
||||
class VideoPlatform(StrEnum):
|
||||
WHEREBY = "whereby"
|
||||
JITSI = "jitsi"
|
||||
|
||||
|
||||
rooms = sqlalchemy.Table(
|
||||
"room",
|
||||
metadata,
|
||||
@@ -44,21 +50,10 @@ rooms = sqlalchemy.Table(
|
||||
),
|
||||
sqlalchemy.Column("webhook_url", sqlalchemy.String, nullable=True),
|
||||
sqlalchemy.Column("webhook_secret", sqlalchemy.String, nullable=True),
|
||||
sqlalchemy.Column("ics_url", sqlalchemy.Text),
|
||||
sqlalchemy.Column("ics_fetch_interval", sqlalchemy.Integer, server_default="300"),
|
||||
sqlalchemy.Column(
|
||||
"ics_enabled", sqlalchemy.Boolean, nullable=False, server_default=false()
|
||||
),
|
||||
sqlalchemy.Column("ics_last_sync", sqlalchemy.DateTime(timezone=True)),
|
||||
sqlalchemy.Column("ics_last_etag", sqlalchemy.Text),
|
||||
sqlalchemy.Column(
|
||||
"platform",
|
||||
sqlalchemy.String,
|
||||
nullable=False,
|
||||
server_default="whereby",
|
||||
"platform", sqlalchemy.String, nullable=False, server_default="whereby"
|
||||
),
|
||||
sqlalchemy.Index("idx_room_is_shared", "is_shared"),
|
||||
sqlalchemy.Index("idx_room_ics_enabled", "ics_enabled"),
|
||||
)
|
||||
|
||||
|
||||
@@ -73,18 +68,13 @@ class Room(BaseModel):
|
||||
is_locked: bool = False
|
||||
room_mode: Literal["normal", "group"] = "normal"
|
||||
recording_type: Literal["none", "local", "cloud"] = "cloud"
|
||||
recording_trigger: Literal[ # whereby-specific
|
||||
recording_trigger: Literal[
|
||||
"none", "prompt", "automatic", "automatic-2nd-participant"
|
||||
] = "automatic-2nd-participant"
|
||||
is_shared: bool = False
|
||||
webhook_url: str | None = None
|
||||
webhook_secret: str | None = None
|
||||
ics_url: str | None = None
|
||||
ics_fetch_interval: int = 300
|
||||
ics_enabled: bool = False
|
||||
ics_last_sync: datetime | None = None
|
||||
ics_last_etag: str | None = None
|
||||
platform: Platform = "whereby"
|
||||
platform: VideoPlatform = VideoPlatform.WHEREBY
|
||||
|
||||
|
||||
class RoomController:
|
||||
@@ -135,10 +125,7 @@ class RoomController:
|
||||
is_shared: bool,
|
||||
webhook_url: str = "",
|
||||
webhook_secret: str = "",
|
||||
ics_url: str | None = None,
|
||||
ics_fetch_interval: int = 300,
|
||||
ics_enabled: bool = False,
|
||||
platform: Optional[Platform] = None,
|
||||
platform: str = "whereby",
|
||||
):
|
||||
"""
|
||||
Add a new room
|
||||
@@ -159,10 +146,7 @@ class RoomController:
|
||||
is_shared=is_shared,
|
||||
webhook_url=webhook_url,
|
||||
webhook_secret=webhook_secret,
|
||||
ics_url=ics_url,
|
||||
ics_fetch_interval=ics_fetch_interval,
|
||||
ics_enabled=ics_enabled,
|
||||
platform=platform or "whereby",
|
||||
platform=platform,
|
||||
)
|
||||
query = rooms.insert().values(**room.model_dump())
|
||||
try:
|
||||
@@ -227,13 +211,6 @@ class RoomController:
|
||||
|
||||
return room
|
||||
|
||||
async def get_ics_enabled(self) -> list[Room]:
|
||||
query = rooms.select().where(
|
||||
rooms.c.ics_enabled == True, rooms.c.ics_url != None
|
||||
)
|
||||
results = await get_database().fetch_all(query)
|
||||
return [Room(**result) for result in results]
|
||||
|
||||
async def remove_by_id(
|
||||
self,
|
||||
room_id: str,
|
||||
|
||||
@@ -647,19 +647,6 @@ class TranscriptController:
|
||||
query = transcripts.delete().where(transcripts.c.recording_id == recording_id)
|
||||
await get_database().execute(query)
|
||||
|
||||
@staticmethod
|
||||
def user_can_mutate(transcript: Transcript, user_id: str | None) -> bool:
|
||||
"""
|
||||
Returns True if the given user is allowed to modify the transcript.
|
||||
|
||||
Policy:
|
||||
- Anonymous transcripts (user_id is None) cannot be modified via API
|
||||
- Only the owner (matching user_id) can modify their transcript
|
||||
"""
|
||||
if transcript.user_id is None:
|
||||
return False
|
||||
return user_id and transcript.user_id == user_id
|
||||
|
||||
@asynccontextmanager
|
||||
async def transaction(self):
|
||||
"""
|
||||
|
||||
227
server/reflector/jibri_events.py
Normal file
227
server/reflector/jibri_events.py
Normal file
@@ -0,0 +1,227 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Literal, Optional, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
|
||||
class ParticipantInfo(BaseModel):
|
||||
jid: str
|
||||
nick: str
|
||||
id: str
|
||||
is_moderator: bool = False
|
||||
|
||||
|
||||
class ParticipantLeftInfo(BaseModel):
|
||||
jid: str
|
||||
nick: Optional[str] = None
|
||||
duration_seconds: Optional[int] = None
|
||||
|
||||
|
||||
class RoomCreatedEvent(BaseModel):
|
||||
type: Literal["room_created"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
room_jid: str
|
||||
meeting_url: str
|
||||
|
||||
|
||||
class RecordingStartedEvent(BaseModel):
|
||||
type: Literal["recording_started"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
session_id: str
|
||||
jibri_jid: str
|
||||
|
||||
|
||||
class RecordingStoppedEvent(BaseModel):
|
||||
type: Literal["recording_stopped"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
session_id: str
|
||||
meeting_url: str
|
||||
|
||||
|
||||
class ParticipantJoinedEvent(BaseModel):
|
||||
type: Literal["participant_joined"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
participant: ParticipantInfo
|
||||
|
||||
|
||||
class ParticipantLeftEvent(BaseModel):
|
||||
type: Literal["participant_left"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
participant: ParticipantLeftInfo
|
||||
|
||||
|
||||
class SpeakerActiveEvent(BaseModel):
|
||||
type: Literal["speaker_active"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
speaker_jid: str
|
||||
speaker_nick: str
|
||||
duration: int
|
||||
|
||||
|
||||
class DominantSpeakerChangedEvent(BaseModel):
|
||||
type: Literal["dominant_speaker_changed"]
|
||||
timestamp: int
|
||||
room_name: str
|
||||
previous: str
|
||||
current: str
|
||||
|
||||
|
||||
JitsiEvent = Union[
|
||||
RoomCreatedEvent,
|
||||
RecordingStartedEvent,
|
||||
RecordingStoppedEvent,
|
||||
ParticipantJoinedEvent,
|
||||
ParticipantLeftEvent,
|
||||
SpeakerActiveEvent,
|
||||
DominantSpeakerChangedEvent,
|
||||
]
|
||||
|
||||
|
||||
class RoomInfo(TypedDict):
|
||||
name: str
|
||||
jid: str
|
||||
created_at: int
|
||||
meeting_url: str
|
||||
recording_stopped_at: Optional[int]
|
||||
|
||||
|
||||
class ParticipantData(TypedDict):
|
||||
jid: str
|
||||
nick: str
|
||||
id: str
|
||||
is_moderator: bool
|
||||
joined_at: int
|
||||
left_at: Optional[int]
|
||||
duration: Optional[int]
|
||||
events: List[str]
|
||||
|
||||
|
||||
class SpeakerStats(TypedDict):
|
||||
total_time: int
|
||||
nick: str
|
||||
|
||||
|
||||
class ParsedMetadata(TypedDict):
|
||||
room: RoomInfo
|
||||
participants: List[ParticipantData]
|
||||
speaker_stats: Dict[str, SpeakerStats]
|
||||
event_count: int
|
||||
|
||||
|
||||
class JitsiEventParser:
|
||||
def parse_event(self, event_data: Dict[str, Any]) -> Optional[JitsiEvent]:
|
||||
event_type = event_data.get("type")
|
||||
|
||||
try:
|
||||
if event_type == "room_created":
|
||||
return RoomCreatedEvent(**event_data)
|
||||
elif event_type == "recording_started":
|
||||
return RecordingStartedEvent(**event_data)
|
||||
elif event_type == "recording_stopped":
|
||||
return RecordingStoppedEvent(**event_data)
|
||||
elif event_type == "participant_joined":
|
||||
return ParticipantJoinedEvent(**event_data)
|
||||
elif event_type == "participant_left":
|
||||
return ParticipantLeftEvent(**event_data)
|
||||
elif event_type == "speaker_active":
|
||||
return SpeakerActiveEvent(**event_data)
|
||||
elif event_type == "dominant_speaker_changed":
|
||||
return DominantSpeakerChangedEvent(**event_data)
|
||||
else:
|
||||
return None
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def parse_events_file(self, recording_path: str) -> ParsedMetadata:
|
||||
events_file = Path(recording_path) / "events.jsonl"
|
||||
|
||||
room_info: RoomInfo = {
|
||||
"name": "",
|
||||
"jid": "",
|
||||
"created_at": 0,
|
||||
"meeting_url": "",
|
||||
"recording_stopped_at": None,
|
||||
}
|
||||
|
||||
if not events_file.exists():
|
||||
return ParsedMetadata(
|
||||
room=room_info, participants=[], speaker_stats={}, event_count=0
|
||||
)
|
||||
|
||||
events: List[JitsiEvent] = []
|
||||
participants: Dict[str, ParticipantData] = {}
|
||||
speaker_stats: Dict[str, SpeakerStats] = {}
|
||||
|
||||
with open(events_file, "r") as f:
|
||||
for line in f:
|
||||
if not line.strip():
|
||||
continue
|
||||
|
||||
try:
|
||||
event_data = json.loads(line)
|
||||
event = self.parse_event(event_data)
|
||||
|
||||
if event is None:
|
||||
continue
|
||||
|
||||
events.append(event)
|
||||
|
||||
if isinstance(event, RoomCreatedEvent):
|
||||
room_info = {
|
||||
"name": event.room_name,
|
||||
"jid": event.room_jid,
|
||||
"created_at": event.timestamp,
|
||||
"meeting_url": event.meeting_url,
|
||||
"recording_stopped_at": None,
|
||||
}
|
||||
|
||||
elif isinstance(event, ParticipantJoinedEvent):
|
||||
participants[event.participant.id] = {
|
||||
"jid": event.participant.jid,
|
||||
"nick": event.participant.nick,
|
||||
"id": event.participant.id,
|
||||
"is_moderator": event.participant.is_moderator,
|
||||
"joined_at": event.timestamp,
|
||||
"left_at": None,
|
||||
"duration": None,
|
||||
"events": ["joined"],
|
||||
}
|
||||
|
||||
elif isinstance(event, ParticipantLeftEvent):
|
||||
participant_id = event.participant.jid.split("/")[0]
|
||||
if participant_id in participants:
|
||||
participants[participant_id]["left_at"] = event.timestamp
|
||||
participants[participant_id]["duration"] = (
|
||||
event.participant.duration_seconds
|
||||
)
|
||||
participants[participant_id]["events"].append("left")
|
||||
|
||||
elif isinstance(event, SpeakerActiveEvent):
|
||||
if event.speaker_jid not in speaker_stats:
|
||||
speaker_stats[event.speaker_jid] = {
|
||||
"total_time": 0,
|
||||
"nick": event.speaker_nick,
|
||||
}
|
||||
speaker_stats[event.speaker_jid]["total_time"] += event.duration
|
||||
|
||||
elif isinstance(event, RecordingStoppedEvent):
|
||||
room_info["recording_stopped_at"] = event.timestamp
|
||||
room_info["meeting_url"] = event.meeting_url
|
||||
|
||||
except (json.JSONDecodeError, Exception):
|
||||
continue
|
||||
|
||||
return ParsedMetadata(
|
||||
room=room_info,
|
||||
participants=list(participants.values()),
|
||||
speaker_stats=speaker_stats,
|
||||
event_count=len(events),
|
||||
)
|
||||
@@ -1,84 +0,0 @@
|
||||
# Multitrack Pipeline Fix Summary
|
||||
|
||||
## Problem
|
||||
Whisper timestamps were incorrect because it ignores leading silence in audio files. Daily.co tracks can have arbitrary amounts of silence before speech starts.
|
||||
|
||||
## Solution
|
||||
**Pad tracks BEFORE transcription using stream metadata `start_time`**
|
||||
|
||||
This makes Whisper timestamps automatically correct relative to recording start.
|
||||
|
||||
## Key Changes in `main_multitrack_pipeline_fixed.py`
|
||||
|
||||
### 1. Added `pad_track_for_transcription()` method (lines 55-172)
|
||||
|
||||
```python
|
||||
async def pad_track_for_transcription(
|
||||
self,
|
||||
track_data: bytes,
|
||||
track_idx: int,
|
||||
storage,
|
||||
) -> tuple[bytes, str]:
|
||||
```
|
||||
|
||||
- Extracts stream metadata `start_time` using PyAV
|
||||
- Creates PyAV filter graph with `adelay` filter to add padding
|
||||
- Stores padded track to S3 and returns URL
|
||||
- Uses same audio processing library (PyAV) already in the pipeline
|
||||
|
||||
### 2. Modified `process()` method
|
||||
|
||||
#### REMOVED (lines 255-302):
|
||||
- Entire filename parsing for offsets - NOT NEEDED ANYMORE
|
||||
- The complex regex parsing of Daily.co filenames
|
||||
- Offset adjustment after transcription
|
||||
|
||||
#### ADDED (lines 371-382):
|
||||
- Padding step BEFORE transcription:
|
||||
```python
|
||||
# PAD TRACKS BEFORE TRANSCRIPTION - THIS IS THE KEY FIX!
|
||||
padded_track_urls: list[str] = []
|
||||
for idx, data in enumerate(track_datas):
|
||||
if not data:
|
||||
padded_track_urls.append("")
|
||||
continue
|
||||
|
||||
_, padded_url = await self.pad_track_for_transcription(
|
||||
data, idx, storage
|
||||
)
|
||||
padded_track_urls.append(padded_url)
|
||||
```
|
||||
|
||||
#### MODIFIED (lines 385-435):
|
||||
- Transcribe PADDED tracks instead of raw tracks
|
||||
- Removed all timestamp offset adjustment code
|
||||
- Just set speaker ID - timestamps already correct!
|
||||
|
||||
```python
|
||||
# NO OFFSET ADJUSTMENT NEEDED!
|
||||
# Timestamps are already correct because we transcribed padded tracks
|
||||
# Just set speaker ID
|
||||
for w in t.words:
|
||||
w.speaker = idx
|
||||
```
|
||||
|
||||
## Why This Works
|
||||
|
||||
1. **Stream metadata is authoritative**: Daily.co sets `start_time` in the WebM container
|
||||
2. **PyAV respects metadata**: `audio_stream.start_time * audio_stream.time_base` gives seconds
|
||||
3. **Padding before transcription**: Whisper sees continuous audio from time 0
|
||||
4. **Automatic alignment**: Word at 51s in padded track = 51s in recording
|
||||
|
||||
## Testing
|
||||
|
||||
Process the test recording (daily-20251020193458) and verify:
|
||||
- Participant 0 words appear at ~2s
|
||||
- Participant 1 words appear at ~51s
|
||||
- No word interleaving
|
||||
- Correct chronological order
|
||||
|
||||
## Files
|
||||
|
||||
- **Original**: `main_multitrack_pipeline.py`
|
||||
- **Fixed**: `main_multitrack_pipeline_fixed.py`
|
||||
- **Test data**: `/Users/firfi/work/clients/monadical/reflector/1760988935484-*.webm`
|
||||
@@ -131,7 +131,7 @@ class PipelineMainFile(PipelineMainBase):
|
||||
|
||||
self.logger.info("File pipeline complete")
|
||||
|
||||
await self.set_status(transcript.id, "ended")
|
||||
await transcripts_controller.set_status(transcript.id, "ended")
|
||||
|
||||
async def extract_and_write_audio(
|
||||
self, file_path: Path, transcript: Transcript
|
||||
|
||||
@@ -85,20 +85,6 @@ def broadcast_to_sockets(func):
|
||||
message=resp.model_dump(mode="json"),
|
||||
)
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(self.transcript_id)
|
||||
if transcript and transcript.user_id:
|
||||
# Emit only relevant events to the user room to avoid noisy updates.
|
||||
# Allowed: STATUS, FINAL_TITLE, DURATION. All are prefixed with TRANSCRIPT_
|
||||
allowed_user_events = {"STATUS", "FINAL_TITLE", "DURATION"}
|
||||
if resp.event in allowed_user_events:
|
||||
await self.ws_manager.send_json(
|
||||
room_id=f"user:{transcript.user_id}",
|
||||
message={
|
||||
"event": f"TRANSCRIPT_{resp.event}",
|
||||
"data": {"id": self.transcript_id, **resp.data},
|
||||
},
|
||||
)
|
||||
|
||||
return wrapper
|
||||
|
||||
|
||||
|
||||
@@ -1,510 +0,0 @@
|
||||
import asyncio
|
||||
import io
|
||||
from fractions import Fraction
|
||||
|
||||
import av
|
||||
import boto3
|
||||
import structlog
|
||||
from av.audio.resampler import AudioResampler
|
||||
from celery import chain, shared_task
|
||||
|
||||
from reflector.asynctask import asynctask
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptStatus,
|
||||
TranscriptText,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.logger import logger
|
||||
from reflector.pipelines.main_file_pipeline import task_send_webhook_if_needed
|
||||
from reflector.pipelines.main_live_pipeline import (
|
||||
PipelineMainBase,
|
||||
task_cleanup_consent,
|
||||
task_pipeline_post_to_zulip,
|
||||
)
|
||||
from reflector.processors import (
|
||||
AudioFileWriterProcessor,
|
||||
TranscriptFinalSummaryProcessor,
|
||||
TranscriptFinalTitleProcessor,
|
||||
TranscriptTopicDetectorProcessor,
|
||||
)
|
||||
from reflector.processors.file_transcript import FileTranscriptInput
|
||||
from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
|
||||
from reflector.processors.types import TitleSummary
|
||||
from reflector.processors.types import (
|
||||
Transcript as TranscriptType,
|
||||
)
|
||||
from reflector.settings import settings
|
||||
from reflector.storage import get_transcripts_storage
|
||||
|
||||
|
||||
class EmptyPipeline:
|
||||
def __init__(self, logger: structlog.BoundLogger):
|
||||
self.logger = logger
|
||||
|
||||
def get_pref(self, k, d=None):
|
||||
return d
|
||||
|
||||
async def emit(self, event):
|
||||
pass
|
||||
|
||||
|
||||
class PipelineMainMultitrack(PipelineMainBase):
|
||||
"""Process multiple participant tracks for a transcript without mixing audio."""
|
||||
|
||||
def __init__(self, transcript_id: str):
|
||||
super().__init__(transcript_id=transcript_id)
|
||||
self.logger = logger.bind(transcript_id=self.transcript_id)
|
||||
self.empty_pipeline = EmptyPipeline(logger=self.logger)
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_datas: list[bytes],
|
||||
writer: AudioFileWriterProcessor,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> None:
|
||||
"""
|
||||
Minimal multi-track mixdown using a PyAV filter graph (amix), no resampling.
|
||||
"""
|
||||
|
||||
# Discover target sample rate from first decodable frame
|
||||
target_sample_rate: int | None = None
|
||||
for data in track_datas:
|
||||
if not data:
|
||||
continue
|
||||
try:
|
||||
container = av.open(io.BytesIO(data))
|
||||
try:
|
||||
for frame in container.decode(audio=0):
|
||||
target_sample_rate = frame.sample_rate
|
||||
break
|
||||
finally:
|
||||
container.close()
|
||||
except Exception:
|
||||
continue
|
||||
if target_sample_rate:
|
||||
break
|
||||
|
||||
if not target_sample_rate:
|
||||
self.logger.warning("Mixdown skipped - no decodable audio frames found")
|
||||
return
|
||||
|
||||
# Build PyAV filter graph:
|
||||
# N abuffer (s32/stereo)
|
||||
# -> optional adelay per input (for alignment)
|
||||
# -> amix (s32)
|
||||
# -> aformat(s16)
|
||||
# -> sink
|
||||
graph = av.filter.Graph()
|
||||
inputs = []
|
||||
valid_track_datas = [d for d in track_datas if d]
|
||||
# Align offsets list with the filtered inputs (skip empties)
|
||||
input_offsets_seconds = None
|
||||
if offsets_seconds is not None:
|
||||
input_offsets_seconds = [
|
||||
offsets_seconds[i] for i, d in enumerate(track_datas) if d
|
||||
]
|
||||
for idx, data in enumerate(valid_track_datas):
|
||||
args = (
|
||||
f"time_base=1/{target_sample_rate}:"
|
||||
f"sample_rate={target_sample_rate}:"
|
||||
f"sample_fmt=s32:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
|
||||
inputs.append(in_ctx)
|
||||
|
||||
if not inputs:
|
||||
self.logger.warning("Mixdown skipped - no valid inputs for graph")
|
||||
return
|
||||
|
||||
mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
|
||||
|
||||
fmt = graph.add(
|
||||
"aformat",
|
||||
args=(
|
||||
f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}"
|
||||
),
|
||||
name="fmt",
|
||||
)
|
||||
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
# Optional per-input delay before mixing
|
||||
delays_ms: list[int] = []
|
||||
if input_offsets_seconds is not None:
|
||||
base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
|
||||
delays_ms = [
|
||||
max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds
|
||||
]
|
||||
else:
|
||||
delays_ms = [0 for _ in inputs]
|
||||
|
||||
for idx, in_ctx in enumerate(inputs):
|
||||
delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
|
||||
if delay_ms > 0:
|
||||
# adelay requires one value per channel; use same for stereo
|
||||
adelay = graph.add(
|
||||
"adelay",
|
||||
args=f"delays={delay_ms}|{delay_ms}:all=1",
|
||||
name=f"delay{idx}",
|
||||
)
|
||||
in_ctx.link_to(adelay)
|
||||
adelay.link_to(mixer, 0, idx)
|
||||
else:
|
||||
in_ctx.link_to(mixer, 0, idx)
|
||||
mixer.link_to(fmt)
|
||||
fmt.link_to(sink)
|
||||
graph.configure()
|
||||
|
||||
# Open containers for decoding
|
||||
containers = []
|
||||
for i, d in enumerate(valid_track_datas):
|
||||
try:
|
||||
c = av.open(io.BytesIO(d))
|
||||
containers.append(c)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Mixdown: failed to open container", input=i, error=str(e)
|
||||
)
|
||||
containers.append(None)
|
||||
# Filter out Nones for decoders
|
||||
containers = [c for c in containers if c is not None]
|
||||
decoders = [c.decode(audio=0) for c in containers]
|
||||
active = [True] * len(decoders)
|
||||
# Per-input resamplers to enforce s32/stereo at the same rate (no resample of rate)
|
||||
resamplers = [
|
||||
AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
|
||||
for _ in decoders
|
||||
]
|
||||
|
||||
try:
|
||||
# Round-robin feed frames into graph, pull mixed frames as they become available
|
||||
while any(active):
|
||||
for i, (dec, is_active) in enumerate(zip(decoders, active)):
|
||||
if not is_active:
|
||||
continue
|
||||
try:
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
continue
|
||||
|
||||
# Enforce same sample rate; convert format/layout to s16/stereo (no resample)
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
# Skip frames with differing rate
|
||||
continue
|
||||
out_frames = resamplers[i].resample(frame) or []
|
||||
for rf in out_frames:
|
||||
rf.sample_rate = target_sample_rate
|
||||
rf.time_base = Fraction(1, target_sample_rate)
|
||||
inputs[i].push(rf)
|
||||
|
||||
# Drain available mixed frames
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
|
||||
# Signal EOF to inputs and drain remaining
|
||||
for in_ctx in inputs:
|
||||
in_ctx.push(None)
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
finally:
|
||||
for c in containers:
|
||||
c.close()
|
||||
|
||||
async def set_status(self, transcript_id: str, status: TranscriptStatus):
|
||||
async with self.lock_transaction():
|
||||
return await transcripts_controller.set_status(transcript_id, status)
|
||||
|
||||
async def process(self, bucket_name: str, track_keys: list[str]):
|
||||
transcript = await self.get_transcript()
|
||||
|
||||
s3 = boto3.client(
|
||||
"s3",
|
||||
region_name=settings.RECORDING_STORAGE_AWS_REGION,
|
||||
aws_access_key_id=settings.RECORDING_STORAGE_AWS_ACCESS_KEY_ID,
|
||||
aws_secret_access_key=settings.RECORDING_STORAGE_AWS_SECRET_ACCESS_KEY,
|
||||
)
|
||||
|
||||
storage = get_transcripts_storage()
|
||||
|
||||
# Pre-download bytes for all tracks for mixing and transcription
|
||||
track_datas: list[bytes] = []
|
||||
for key in track_keys:
|
||||
try:
|
||||
obj = s3.get_object(Bucket=bucket_name, Key=key)
|
||||
track_datas.append(obj["Body"].read())
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Skipping track - cannot read S3 object", key=key, error=str(e)
|
||||
)
|
||||
track_datas.append(b"")
|
||||
|
||||
# Extract offsets from Daily.co filename timestamps
|
||||
# Format: {rec_start_ts}-{uuid}-{media_type}-{track_start_ts}.{ext}
|
||||
# Example: 1760988935484-uuid-cam-audio-1760988935922
|
||||
import re
|
||||
|
||||
offsets_seconds: list[float] = []
|
||||
recording_start_ts: int | None = None
|
||||
|
||||
for key in track_keys:
|
||||
# Parse Daily.co raw-tracks filename pattern
|
||||
match = re.search(r"(\d+)-([0-9a-f-]{36})-(cam-audio)-(\d+)", key)
|
||||
if not match:
|
||||
self.logger.warning(
|
||||
"Track key doesn't match Daily.co pattern, using 0.0 offset",
|
||||
key=key,
|
||||
)
|
||||
offsets_seconds.append(0.0)
|
||||
continue
|
||||
|
||||
rec_start_ts = int(match.group(1))
|
||||
track_start_ts = int(match.group(4))
|
||||
|
||||
# Validate all tracks belong to same recording
|
||||
if recording_start_ts is None:
|
||||
recording_start_ts = rec_start_ts
|
||||
elif rec_start_ts != recording_start_ts:
|
||||
self.logger.error(
|
||||
"Track belongs to different recording",
|
||||
key=key,
|
||||
expected_start=recording_start_ts,
|
||||
got_start=rec_start_ts,
|
||||
)
|
||||
offsets_seconds.append(0.0)
|
||||
continue
|
||||
|
||||
# Calculate offset in seconds
|
||||
offset_ms = track_start_ts - rec_start_ts
|
||||
offset_s = offset_ms / 1000.0
|
||||
|
||||
self.logger.info(
|
||||
"Parsed track offset from filename",
|
||||
key=key,
|
||||
recording_start=rec_start_ts,
|
||||
track_start=track_start_ts,
|
||||
offset_seconds=offset_s,
|
||||
)
|
||||
|
||||
offsets_seconds.append(max(0.0, offset_s))
|
||||
|
||||
# Mixdown all available tracks into transcript.audio_mp3_filename, preserving sample rate
|
||||
try:
|
||||
mp3_writer = AudioFileWriterProcessor(
|
||||
path=str(transcript.audio_mp3_filename)
|
||||
)
|
||||
await self.mixdown_tracks(track_datas, mp3_writer, offsets_seconds)
|
||||
await mp3_writer.flush()
|
||||
except Exception as e:
|
||||
self.logger.error("Mixdown failed", error=str(e))
|
||||
|
||||
speaker_transcripts: list[TranscriptType] = []
|
||||
for idx, key in enumerate(track_keys):
|
||||
ext = ".mp4"
|
||||
|
||||
try:
|
||||
obj = s3.get_object(Bucket=bucket_name, Key=key)
|
||||
data = obj["Body"].read()
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Skipping track - cannot read S3 object", key=key, error=str(e)
|
||||
)
|
||||
continue
|
||||
|
||||
storage_path = f"file_pipeline/{transcript.id}/tracks/track_{idx}{ext}"
|
||||
try:
|
||||
await storage.put_file(storage_path, data)
|
||||
audio_url = await storage.get_file_url(storage_path)
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Skipping track - cannot upload to storage", key=key, error=str(e)
|
||||
)
|
||||
continue
|
||||
|
||||
try:
|
||||
t = await self.transcribe_file(audio_url, transcript.source_language)
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Transcription via default backend failed, trying local whisper",
|
||||
key=key,
|
||||
url=audio_url,
|
||||
error=str(e),
|
||||
)
|
||||
try:
|
||||
fallback = FileTranscriptAutoProcessor(name="whisper")
|
||||
result = None
|
||||
|
||||
async def capture_result(r):
|
||||
nonlocal result
|
||||
result = r
|
||||
|
||||
fallback.on(capture_result)
|
||||
await fallback.push(
|
||||
FileTranscriptInput(
|
||||
audio_url=audio_url, language=transcript.source_language
|
||||
)
|
||||
)
|
||||
await fallback.flush()
|
||||
if not result:
|
||||
raise Exception("No transcript captured in fallback")
|
||||
t = result
|
||||
except Exception as e2:
|
||||
self.logger.error(
|
||||
"Skipping track - transcription failed after fallback",
|
||||
key=key,
|
||||
url=audio_url,
|
||||
error=str(e2),
|
||||
)
|
||||
continue
|
||||
|
||||
if not t.words:
|
||||
continue
|
||||
# Shift word timestamps by the track's offset so all are relative to 00:00
|
||||
track_offset = offsets_seconds[idx] if idx < len(offsets_seconds) else 0.0
|
||||
for w in t.words:
|
||||
try:
|
||||
if hasattr(w, "start") and w.start is not None:
|
||||
w.start = float(w.start) + track_offset
|
||||
if hasattr(w, "end") and w.end is not None:
|
||||
w.end = float(w.end) + track_offset
|
||||
except Exception:
|
||||
pass
|
||||
w.speaker = idx
|
||||
speaker_transcripts.append(t)
|
||||
|
||||
if not speaker_transcripts:
|
||||
raise Exception("No valid track transcriptions")
|
||||
|
||||
merged_words = []
|
||||
for t in speaker_transcripts:
|
||||
merged_words.extend(t.words)
|
||||
merged_words.sort(key=lambda w: w.start)
|
||||
|
||||
merged_transcript = TranscriptType(words=merged_words, translation=None)
|
||||
|
||||
await transcripts_controller.append_event(
|
||||
transcript,
|
||||
event="TRANSCRIPT",
|
||||
data=TranscriptText(
|
||||
text=merged_transcript.text, translation=merged_transcript.translation
|
||||
),
|
||||
)
|
||||
|
||||
topics = await self.detect_topics(merged_transcript, transcript.target_language)
|
||||
await asyncio.gather(
|
||||
self.generate_title(topics),
|
||||
self.generate_summaries(topics),
|
||||
return_exceptions=False,
|
||||
)
|
||||
|
||||
await self.set_status(transcript.id, "ended")
|
||||
|
||||
async def transcribe_file(self, audio_url: str, language: str) -> TranscriptType:
|
||||
processor = FileTranscriptAutoProcessor()
|
||||
input_data = FileTranscriptInput(audio_url=audio_url, language=language)
|
||||
|
||||
result: TranscriptType | None = None
|
||||
|
||||
async def capture_result(transcript):
|
||||
nonlocal result
|
||||
result = transcript
|
||||
|
||||
processor.on(capture_result)
|
||||
await processor.push(input_data)
|
||||
await processor.flush()
|
||||
|
||||
if not result:
|
||||
raise ValueError("No transcript captured")
|
||||
|
||||
return result
|
||||
|
||||
async def detect_topics(
|
||||
self, transcript: TranscriptType, target_language: str
|
||||
) -> list[TitleSummary]:
|
||||
chunk_size = 300
|
||||
topics: list[TitleSummary] = []
|
||||
|
||||
async def on_topic(topic: TitleSummary):
|
||||
topics.append(topic)
|
||||
return await self.on_topic(topic)
|
||||
|
||||
topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
|
||||
topic_detector.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for i in range(0, len(transcript.words), chunk_size):
|
||||
chunk_words = transcript.words[i : i + chunk_size]
|
||||
if not chunk_words:
|
||||
continue
|
||||
|
||||
chunk_transcript = TranscriptType(
|
||||
words=chunk_words, translation=transcript.translation
|
||||
)
|
||||
await topic_detector.push(chunk_transcript)
|
||||
|
||||
await topic_detector.flush()
|
||||
return topics
|
||||
|
||||
async def generate_title(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for title generation")
|
||||
return
|
||||
|
||||
processor = TranscriptFinalTitleProcessor(callback=self.on_title)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
async def generate_summaries(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for summary generation")
|
||||
return
|
||||
|
||||
transcript = await self.get_transcript()
|
||||
processor = TranscriptFinalSummaryProcessor(
|
||||
transcript=transcript,
|
||||
callback=self.on_long_summary,
|
||||
on_short_summary=self.on_short_summary,
|
||||
)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def task_pipeline_multitrack_process(
|
||||
*, transcript_id: str, bucket_name: str, track_keys: list[str]
|
||||
):
|
||||
pipeline = PipelineMainMultitrack(transcript_id=transcript_id)
|
||||
try:
|
||||
await pipeline.set_status(transcript_id, "processing")
|
||||
await pipeline.process(bucket_name, track_keys)
|
||||
except Exception:
|
||||
await pipeline.set_status(transcript_id, "error")
|
||||
raise
|
||||
|
||||
post_chain = chain(
|
||||
task_cleanup_consent.si(transcript_id=transcript_id),
|
||||
task_pipeline_post_to_zulip.si(transcript_id=transcript_id),
|
||||
task_send_webhook_if_needed.si(transcript_id=transcript_id),
|
||||
)
|
||||
post_chain.delay()
|
||||
@@ -1,654 +0,0 @@
|
||||
import asyncio
|
||||
import io
|
||||
from fractions import Fraction
|
||||
|
||||
import av
|
||||
import boto3
|
||||
import structlog
|
||||
from av.audio.resampler import AudioResampler
|
||||
from celery import chain, shared_task
|
||||
|
||||
from reflector.asynctask import asynctask
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptStatus,
|
||||
TranscriptWaveform,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.logger import logger
|
||||
from reflector.pipelines.main_file_pipeline import task_send_webhook_if_needed
|
||||
from reflector.pipelines.main_live_pipeline import (
|
||||
PipelineMainBase,
|
||||
broadcast_to_sockets,
|
||||
task_cleanup_consent,
|
||||
task_pipeline_post_to_zulip,
|
||||
)
|
||||
from reflector.processors import (
|
||||
AudioFileWriterProcessor,
|
||||
TranscriptFinalSummaryProcessor,
|
||||
TranscriptFinalTitleProcessor,
|
||||
TranscriptTopicDetectorProcessor,
|
||||
)
|
||||
from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
|
||||
from reflector.processors.file_transcript import FileTranscriptInput
|
||||
from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
|
||||
from reflector.processors.types import TitleSummary
|
||||
from reflector.processors.types import (
|
||||
Transcript as TranscriptType,
|
||||
)
|
||||
from reflector.settings import settings
|
||||
from reflector.storage import get_transcripts_storage
|
||||
|
||||
|
||||
class EmptyPipeline:
|
||||
def __init__(self, logger: structlog.BoundLogger):
|
||||
self.logger = logger
|
||||
|
||||
def get_pref(self, k, d=None):
|
||||
return d
|
||||
|
||||
async def emit(self, event):
|
||||
pass
|
||||
|
||||
|
||||
class PipelineMainMultitrack(PipelineMainBase):
|
||||
"""Process multiple participant tracks for a transcript without mixing audio."""
|
||||
|
||||
def __init__(self, transcript_id: str):
|
||||
super().__init__(transcript_id=transcript_id)
|
||||
self.logger = logger.bind(transcript_id=self.transcript_id)
|
||||
self.empty_pipeline = EmptyPipeline(logger=self.logger)
|
||||
|
||||
async def pad_track_for_transcription(
|
||||
self,
|
||||
track_data: bytes,
|
||||
track_idx: int,
|
||||
storage,
|
||||
) -> tuple[bytes, str]:
|
||||
"""
|
||||
Pad a single track with silence based on stream metadata start_time.
|
||||
This ensures Whisper timestamps will be relative to recording start.
|
||||
Uses ffmpeg subprocess approach proven to work with python-raw-tracks-align.
|
||||
|
||||
Returns: (padded_data, storage_url)
|
||||
"""
|
||||
import json
|
||||
import math
|
||||
import subprocess
|
||||
import tempfile
|
||||
|
||||
if not track_data:
|
||||
return b"", ""
|
||||
|
||||
transcript = await self.get_transcript()
|
||||
|
||||
# Create temp files for ffmpeg processing
|
||||
with tempfile.NamedTemporaryFile(suffix=".webm", delete=False) as input_file:
|
||||
input_file.write(track_data)
|
||||
input_file_path = input_file.name
|
||||
|
||||
output_file_path = input_file_path.replace(".webm", "_padded.webm")
|
||||
|
||||
try:
|
||||
# Get stream metadata using ffprobe
|
||||
ffprobe_cmd = [
|
||||
"ffprobe",
|
||||
"-v",
|
||||
"error",
|
||||
"-show_entries",
|
||||
"stream=start_time",
|
||||
"-of",
|
||||
"json",
|
||||
input_file_path,
|
||||
]
|
||||
|
||||
result = subprocess.run(
|
||||
ffprobe_cmd, capture_output=True, text=True, check=True
|
||||
)
|
||||
metadata = json.loads(result.stdout)
|
||||
|
||||
# Extract start_time from stream metadata
|
||||
start_time_seconds = 0.0
|
||||
if metadata.get("streams") and len(metadata["streams"]) > 0:
|
||||
start_time_str = metadata["streams"][0].get("start_time", "0")
|
||||
start_time_seconds = float(start_time_str)
|
||||
|
||||
self.logger.info(
|
||||
f"Track {track_idx} stream metadata: start_time={start_time_seconds:.3f}s",
|
||||
track_idx=track_idx,
|
||||
)
|
||||
|
||||
# If no padding needed, use original
|
||||
if start_time_seconds <= 0:
|
||||
storage_path = f"file_pipeline/{transcript.id}/tracks/original_track_{track_idx}.webm"
|
||||
await storage.put_file(storage_path, track_data)
|
||||
url = await storage.get_file_url(storage_path)
|
||||
return track_data, url
|
||||
|
||||
# Calculate delay in milliseconds
|
||||
delay_ms = math.floor(start_time_seconds * 1000)
|
||||
|
||||
# Run ffmpeg to pad the audio while maintaining WebM/Opus format for Modal compatibility
|
||||
# ffmpeg quirk: aresample needs to come before adelay in the filter chain
|
||||
ffmpeg_cmd = [
|
||||
"ffmpeg",
|
||||
"-hide_banner",
|
||||
"-loglevel",
|
||||
"error",
|
||||
"-y", # overwrite output
|
||||
"-i",
|
||||
input_file_path,
|
||||
"-af",
|
||||
f"aresample=async=1,adelay={delay_ms}:all=true",
|
||||
"-c:a",
|
||||
"libopus", # Keep Opus codec for Modal compatibility
|
||||
"-b:a",
|
||||
"128k", # Standard bitrate for Opus
|
||||
output_file_path,
|
||||
]
|
||||
|
||||
self.logger.info(
|
||||
f"Padding track {track_idx} with {delay_ms}ms delay using ffmpeg",
|
||||
track_idx=track_idx,
|
||||
delay_ms=delay_ms,
|
||||
command=" ".join(ffmpeg_cmd),
|
||||
)
|
||||
|
||||
result = subprocess.run(ffmpeg_cmd, capture_output=True, text=True)
|
||||
if result.returncode != 0:
|
||||
self.logger.error(
|
||||
f"ffmpeg padding failed for track {track_idx}",
|
||||
track_idx=track_idx,
|
||||
stderr=result.stderr,
|
||||
returncode=result.returncode,
|
||||
)
|
||||
raise Exception(f"ffmpeg padding failed: {result.stderr}")
|
||||
|
||||
# Read the padded output
|
||||
with open(output_file_path, "rb") as f:
|
||||
padded_data = f.read()
|
||||
|
||||
# Store padded track
|
||||
storage_path = (
|
||||
f"file_pipeline/{transcript.id}/tracks/padded_track_{track_idx}.webm"
|
||||
)
|
||||
await storage.put_file(storage_path, padded_data)
|
||||
padded_url = await storage.get_file_url(storage_path)
|
||||
|
||||
self.logger.info(
|
||||
f"Successfully padded track {track_idx} with {start_time_seconds:.3f}s offset, stored at {storage_path}",
|
||||
track_idx=track_idx,
|
||||
delay_ms=delay_ms,
|
||||
padded_url=padded_url,
|
||||
padded_size=len(padded_data),
|
||||
)
|
||||
|
||||
return padded_data, padded_url
|
||||
|
||||
finally:
|
||||
# Clean up temp files
|
||||
import os
|
||||
|
||||
try:
|
||||
os.unlink(input_file_path)
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
os.unlink(output_file_path)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_datas: list[bytes],
|
||||
writer: AudioFileWriterProcessor,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> None:
|
||||
"""
|
||||
Minimal multi-track mixdown using a PyAV filter graph (amix), no resampling.
|
||||
"""
|
||||
|
||||
# Discover target sample rate from first decodable frame
|
||||
target_sample_rate: int | None = None
|
||||
for data in track_datas:
|
||||
if not data:
|
||||
continue
|
||||
try:
|
||||
container = av.open(io.BytesIO(data))
|
||||
try:
|
||||
for frame in container.decode(audio=0):
|
||||
target_sample_rate = frame.sample_rate
|
||||
break
|
||||
finally:
|
||||
container.close()
|
||||
except Exception:
|
||||
continue
|
||||
if target_sample_rate:
|
||||
break
|
||||
|
||||
if not target_sample_rate:
|
||||
self.logger.warning("Mixdown skipped - no decodable audio frames found")
|
||||
return
|
||||
|
||||
# Build PyAV filter graph:
|
||||
# N abuffer (s32/stereo)
|
||||
# -> optional adelay per input (for alignment)
|
||||
# -> amix (s32)
|
||||
# -> aformat(s16)
|
||||
# -> sink
|
||||
graph = av.filter.Graph()
|
||||
inputs = []
|
||||
valid_track_datas = [d for d in track_datas if d]
|
||||
# Align offsets list with the filtered inputs (skip empties)
|
||||
input_offsets_seconds = None
|
||||
if offsets_seconds is not None:
|
||||
input_offsets_seconds = [
|
||||
offsets_seconds[i] for i, d in enumerate(track_datas) if d
|
||||
]
|
||||
for idx, data in enumerate(valid_track_datas):
|
||||
args = (
|
||||
f"time_base=1/{target_sample_rate}:"
|
||||
f"sample_rate={target_sample_rate}:"
|
||||
f"sample_fmt=s32:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
|
||||
inputs.append(in_ctx)
|
||||
|
||||
if not inputs:
|
||||
self.logger.warning("Mixdown skipped - no valid inputs for graph")
|
||||
return
|
||||
|
||||
mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
|
||||
|
||||
fmt = graph.add(
|
||||
"aformat",
|
||||
args=(
|
||||
f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}"
|
||||
),
|
||||
name="fmt",
|
||||
)
|
||||
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
# Optional per-input delay before mixing
|
||||
delays_ms: list[int] = []
|
||||
if input_offsets_seconds is not None:
|
||||
base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
|
||||
delays_ms = [
|
||||
max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds
|
||||
]
|
||||
else:
|
||||
delays_ms = [0 for _ in inputs]
|
||||
|
||||
for idx, in_ctx in enumerate(inputs):
|
||||
delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
|
||||
if delay_ms > 0:
|
||||
# adelay requires one value per channel; use same for stereo
|
||||
adelay = graph.add(
|
||||
"adelay",
|
||||
args=f"delays={delay_ms}|{delay_ms}:all=1",
|
||||
name=f"delay{idx}",
|
||||
)
|
||||
in_ctx.link_to(adelay)
|
||||
adelay.link_to(mixer, 0, idx)
|
||||
else:
|
||||
in_ctx.link_to(mixer, 0, idx)
|
||||
mixer.link_to(fmt)
|
||||
fmt.link_to(sink)
|
||||
graph.configure()
|
||||
|
||||
# Open containers for decoding
|
||||
containers = []
|
||||
for i, d in enumerate(valid_track_datas):
|
||||
try:
|
||||
c = av.open(io.BytesIO(d))
|
||||
containers.append(c)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Mixdown: failed to open container", input=i, error=str(e)
|
||||
)
|
||||
containers.append(None)
|
||||
# Filter out Nones for decoders
|
||||
containers = [c for c in containers if c is not None]
|
||||
decoders = [c.decode(audio=0) for c in containers]
|
||||
active = [True] * len(decoders)
|
||||
# Per-input resamplers to enforce s32/stereo at the same rate (no resample of rate)
|
||||
resamplers = [
|
||||
AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
|
||||
for _ in decoders
|
||||
]
|
||||
|
||||
try:
|
||||
# Round-robin feed frames into graph, pull mixed frames as they become available
|
||||
while any(active):
|
||||
for i, (dec, is_active) in enumerate(zip(decoders, active)):
|
||||
if not is_active:
|
||||
continue
|
||||
try:
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
continue
|
||||
|
||||
# Enforce same sample rate; convert format/layout to s16/stereo (no resample)
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
# Skip frames with differing rate
|
||||
continue
|
||||
out_frames = resamplers[i].resample(frame) or []
|
||||
for rf in out_frames:
|
||||
rf.sample_rate = target_sample_rate
|
||||
rf.time_base = Fraction(1, target_sample_rate)
|
||||
inputs[i].push(rf)
|
||||
|
||||
# Drain available mixed frames
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
|
||||
# Signal EOF to inputs and drain remaining
|
||||
for in_ctx in inputs:
|
||||
in_ctx.push(None)
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
finally:
|
||||
for c in containers:
|
||||
c.close()
|
||||
|
||||
@broadcast_to_sockets
|
||||
async def set_status(self, transcript_id: str, status: TranscriptStatus):
|
||||
async with self.lock_transaction():
|
||||
return await transcripts_controller.set_status(transcript_id, status)
|
||||
|
||||
async def on_waveform(self, data):
|
||||
async with self.transaction():
|
||||
waveform = TranscriptWaveform(waveform=data)
|
||||
transcript = await self.get_transcript()
|
||||
return await transcripts_controller.append_event(
|
||||
transcript=transcript, event="WAVEFORM", data=waveform
|
||||
)
|
||||
|
||||
async def process(self, bucket_name: str, track_keys: list[str]):
|
||||
transcript = await self.get_transcript()
|
||||
|
||||
s3 = boto3.client(
|
||||
"s3",
|
||||
region_name=settings.RECORDING_STORAGE_AWS_REGION,
|
||||
aws_access_key_id=settings.RECORDING_STORAGE_AWS_ACCESS_KEY_ID,
|
||||
aws_secret_access_key=settings.RECORDING_STORAGE_AWS_SECRET_ACCESS_KEY,
|
||||
)
|
||||
|
||||
storage = get_transcripts_storage()
|
||||
|
||||
# Pre-download bytes for all tracks for mixing and transcription
|
||||
track_datas: list[bytes] = []
|
||||
for key in track_keys:
|
||||
try:
|
||||
obj = s3.get_object(Bucket=bucket_name, Key=key)
|
||||
track_datas.append(obj["Body"].read())
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Skipping track - cannot read S3 object", key=key, error=str(e)
|
||||
)
|
||||
track_datas.append(b"")
|
||||
|
||||
# PAD TRACKS FIRST - this creates full-length tracks with correct timeline
|
||||
padded_track_datas: list[bytes] = []
|
||||
padded_track_urls: list[str] = []
|
||||
for idx, data in enumerate(track_datas):
|
||||
if not data:
|
||||
padded_track_datas.append(b"")
|
||||
padded_track_urls.append("")
|
||||
continue
|
||||
|
||||
padded_data, padded_url = await self.pad_track_for_transcription(
|
||||
data, idx, storage
|
||||
)
|
||||
padded_track_datas.append(padded_data)
|
||||
padded_track_urls.append(padded_url)
|
||||
self.logger.info(f"Padded track {idx} for transcription: {padded_url}")
|
||||
|
||||
# Mixdown PADDED tracks (already aligned with timeline) into transcript.audio_mp3_filename
|
||||
try:
|
||||
# Ensure data directory exists
|
||||
transcript.data_path.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
mp3_writer = AudioFileWriterProcessor(
|
||||
path=str(transcript.audio_mp3_filename),
|
||||
on_duration=self.on_duration,
|
||||
)
|
||||
# Use PADDED tracks with NO additional offsets (already aligned by padding)
|
||||
await self.mixdown_tracks(
|
||||
padded_track_datas, mp3_writer, offsets_seconds=None
|
||||
)
|
||||
await mp3_writer.flush()
|
||||
|
||||
# Upload the mixed audio to S3 for web playback
|
||||
if transcript.audio_mp3_filename.exists():
|
||||
mp3_data = transcript.audio_mp3_filename.read_bytes()
|
||||
storage_path = f"{transcript.id}/audio.mp3"
|
||||
await storage.put_file(storage_path, mp3_data)
|
||||
mp3_url = await storage.get_file_url(storage_path)
|
||||
|
||||
# Update transcript to indicate audio is in storage
|
||||
await transcripts_controller.update(
|
||||
transcript, {"audio_location": "storage"}
|
||||
)
|
||||
|
||||
self.logger.info(
|
||||
f"Uploaded mixed audio to storage",
|
||||
storage_path=storage_path,
|
||||
size=len(mp3_data),
|
||||
url=mp3_url,
|
||||
)
|
||||
else:
|
||||
self.logger.warning("Mixdown file does not exist after processing")
|
||||
except Exception as e:
|
||||
self.logger.error("Mixdown failed", error=str(e), exc_info=True)
|
||||
|
||||
# Generate waveform from the mixed audio file
|
||||
if transcript.audio_mp3_filename.exists():
|
||||
try:
|
||||
self.logger.info("Generating waveform from mixed audio")
|
||||
waveform_processor = AudioWaveformProcessor(
|
||||
audio_path=transcript.audio_mp3_filename,
|
||||
waveform_path=transcript.audio_waveform_filename,
|
||||
on_waveform=self.on_waveform,
|
||||
)
|
||||
waveform_processor.set_pipeline(self.empty_pipeline)
|
||||
await waveform_processor.flush()
|
||||
self.logger.info("Waveform generated successfully")
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Waveform generation failed", error=str(e), exc_info=True
|
||||
)
|
||||
|
||||
# Transcribe PADDED tracks - timestamps will be automatically correct!
|
||||
speaker_transcripts: list[TranscriptType] = []
|
||||
for idx, padded_url in enumerate(padded_track_urls):
|
||||
if not padded_url:
|
||||
continue
|
||||
|
||||
try:
|
||||
# Transcribe the PADDED track
|
||||
t = await self.transcribe_file(padded_url, transcript.source_language)
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Transcription via default backend failed, trying local whisper",
|
||||
track_idx=idx,
|
||||
url=padded_url,
|
||||
error=str(e),
|
||||
)
|
||||
try:
|
||||
fallback = FileTranscriptAutoProcessor(name="whisper")
|
||||
result = None
|
||||
|
||||
async def capture_result(r):
|
||||
nonlocal result
|
||||
result = r
|
||||
|
||||
fallback.on(capture_result)
|
||||
await fallback.push(
|
||||
FileTranscriptInput(
|
||||
audio_url=padded_url, language=transcript.source_language
|
||||
)
|
||||
)
|
||||
await fallback.flush()
|
||||
if not result:
|
||||
raise Exception("No transcript captured in fallback")
|
||||
t = result
|
||||
except Exception as e2:
|
||||
self.logger.error(
|
||||
"Skipping track - transcription failed after fallback",
|
||||
track_idx=idx,
|
||||
url=padded_url,
|
||||
error=str(e2),
|
||||
)
|
||||
continue
|
||||
|
||||
if not t.words:
|
||||
continue
|
||||
|
||||
# NO OFFSET ADJUSTMENT NEEDED!
|
||||
# Timestamps are already correct because we transcribed padded tracks
|
||||
# Just set speaker ID
|
||||
for w in t.words:
|
||||
w.speaker = idx
|
||||
|
||||
speaker_transcripts.append(t)
|
||||
self.logger.info(
|
||||
f"Track {idx} transcribed successfully with {len(t.words)} words",
|
||||
track_idx=idx,
|
||||
)
|
||||
|
||||
if not speaker_transcripts:
|
||||
raise Exception("No valid track transcriptions")
|
||||
|
||||
# Merge all words and sort by timestamp
|
||||
merged_words = []
|
||||
for t in speaker_transcripts:
|
||||
merged_words.extend(t.words)
|
||||
merged_words.sort(
|
||||
key=lambda w: w.start if hasattr(w, "start") and w.start is not None else 0
|
||||
)
|
||||
|
||||
merged_transcript = TranscriptType(words=merged_words, translation=None)
|
||||
|
||||
# Emit TRANSCRIPT event through the shared handler (persists and broadcasts)
|
||||
await self.on_transcript(merged_transcript)
|
||||
|
||||
topics = await self.detect_topics(merged_transcript, transcript.target_language)
|
||||
await asyncio.gather(
|
||||
self.generate_title(topics),
|
||||
self.generate_summaries(topics),
|
||||
return_exceptions=False,
|
||||
)
|
||||
|
||||
await self.set_status(transcript.id, "ended")
|
||||
|
||||
async def transcribe_file(self, audio_url: str, language: str) -> TranscriptType:
|
||||
processor = FileTranscriptAutoProcessor()
|
||||
input_data = FileTranscriptInput(audio_url=audio_url, language=language)
|
||||
|
||||
result: TranscriptType | None = None
|
||||
|
||||
async def capture_result(transcript):
|
||||
nonlocal result
|
||||
result = transcript
|
||||
|
||||
processor.on(capture_result)
|
||||
await processor.push(input_data)
|
||||
await processor.flush()
|
||||
|
||||
if not result:
|
||||
raise ValueError("No transcript captured")
|
||||
|
||||
return result
|
||||
|
||||
async def detect_topics(
|
||||
self, transcript: TranscriptType, target_language: str
|
||||
) -> list[TitleSummary]:
|
||||
chunk_size = 300
|
||||
topics: list[TitleSummary] = []
|
||||
|
||||
async def on_topic(topic: TitleSummary):
|
||||
topics.append(topic)
|
||||
return await self.on_topic(topic)
|
||||
|
||||
topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
|
||||
topic_detector.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for i in range(0, len(transcript.words), chunk_size):
|
||||
chunk_words = transcript.words[i : i + chunk_size]
|
||||
if not chunk_words:
|
||||
continue
|
||||
|
||||
chunk_transcript = TranscriptType(
|
||||
words=chunk_words, translation=transcript.translation
|
||||
)
|
||||
await topic_detector.push(chunk_transcript)
|
||||
|
||||
await topic_detector.flush()
|
||||
return topics
|
||||
|
||||
async def generate_title(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for title generation")
|
||||
return
|
||||
|
||||
processor = TranscriptFinalTitleProcessor(callback=self.on_title)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
async def generate_summaries(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for summary generation")
|
||||
return
|
||||
|
||||
transcript = await self.get_transcript()
|
||||
processor = TranscriptFinalSummaryProcessor(
|
||||
transcript=transcript,
|
||||
callback=self.on_long_summary,
|
||||
on_short_summary=self.on_short_summary,
|
||||
)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def task_pipeline_multitrack_process(
|
||||
*, transcript_id: str, bucket_name: str, track_keys: list[str]
|
||||
):
|
||||
pipeline = PipelineMainMultitrack(transcript_id=transcript_id)
|
||||
try:
|
||||
await pipeline.set_status(transcript_id, "processing")
|
||||
await pipeline.process(bucket_name, track_keys)
|
||||
except Exception:
|
||||
await pipeline.set_status(transcript_id, "error")
|
||||
raise
|
||||
|
||||
post_chain = chain(
|
||||
task_cleanup_consent.si(transcript_id=transcript_id),
|
||||
task_pipeline_post_to_zulip.si(transcript_id=transcript_id),
|
||||
task_send_webhook_if_needed.si(transcript_id=transcript_id),
|
||||
)
|
||||
post_chain.delay()
|
||||
@@ -1,629 +0,0 @@
|
||||
import asyncio
|
||||
import io
|
||||
from fractions import Fraction
|
||||
|
||||
import av
|
||||
import boto3
|
||||
import structlog
|
||||
from av.audio.resampler import AudioResampler
|
||||
from celery import chain, shared_task
|
||||
|
||||
from reflector.asynctask import asynctask
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptStatus,
|
||||
TranscriptText,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.logger import logger
|
||||
from reflector.pipelines.main_file_pipeline import task_send_webhook_if_needed
|
||||
from reflector.pipelines.main_live_pipeline import (
|
||||
PipelineMainBase,
|
||||
task_cleanup_consent,
|
||||
task_pipeline_post_to_zulip,
|
||||
)
|
||||
from reflector.processors import (
|
||||
AudioFileWriterProcessor,
|
||||
TranscriptFinalSummaryProcessor,
|
||||
TranscriptFinalTitleProcessor,
|
||||
TranscriptTopicDetectorProcessor,
|
||||
)
|
||||
from reflector.processors.file_transcript import FileTranscriptInput
|
||||
from reflector.processors.file_transcript_auto import FileTranscriptAutoProcessor
|
||||
from reflector.processors.types import TitleSummary
|
||||
from reflector.processors.types import (
|
||||
Transcript as TranscriptType,
|
||||
)
|
||||
from reflector.settings import settings
|
||||
from reflector.storage import get_transcripts_storage
|
||||
|
||||
|
||||
class EmptyPipeline:
|
||||
def __init__(self, logger: structlog.BoundLogger):
|
||||
self.logger = logger
|
||||
|
||||
def get_pref(self, k, d=None):
|
||||
return d
|
||||
|
||||
async def emit(self, event):
|
||||
pass
|
||||
|
||||
|
||||
class PipelineMainMultitrack(PipelineMainBase):
|
||||
"""Process multiple participant tracks for a transcript without mixing audio."""
|
||||
|
||||
def __init__(self, transcript_id: str):
|
||||
super().__init__(transcript_id=transcript_id)
|
||||
self.logger = logger.bind(transcript_id=self.transcript_id)
|
||||
self.empty_pipeline = EmptyPipeline(logger=self.logger)
|
||||
|
||||
async def pad_track_for_transcription(
|
||||
self,
|
||||
track_data: bytes,
|
||||
track_idx: int,
|
||||
storage,
|
||||
) -> tuple[bytes, str]:
|
||||
"""
|
||||
Pad a single track with silence based on stream metadata start_time.
|
||||
This ensures Whisper timestamps will be relative to recording start.
|
||||
|
||||
Returns: (padded_data, storage_url)
|
||||
"""
|
||||
if not track_data:
|
||||
return b"", ""
|
||||
|
||||
transcript = await self.get_transcript()
|
||||
|
||||
# Get stream metadata start_time using PyAV
|
||||
container = av.open(io.BytesIO(track_data))
|
||||
try:
|
||||
audio_stream = container.streams.audio[0]
|
||||
|
||||
# Extract start_time from stream metadata
|
||||
if (
|
||||
audio_stream.start_time is not None
|
||||
and audio_stream.time_base is not None
|
||||
):
|
||||
start_time_seconds = float(
|
||||
audio_stream.start_time * audio_stream.time_base
|
||||
)
|
||||
else:
|
||||
start_time_seconds = 0.0
|
||||
|
||||
sample_rate = audio_stream.sample_rate
|
||||
codec_name = audio_stream.codec.name
|
||||
finally:
|
||||
container.close()
|
||||
|
||||
self.logger.info(
|
||||
f"Track {track_idx} stream metadata: start_time={start_time_seconds:.3f}s, sample_rate={sample_rate}",
|
||||
track_idx=track_idx,
|
||||
)
|
||||
|
||||
# If no padding needed, use original
|
||||
if start_time_seconds <= 0:
|
||||
storage_path = (
|
||||
f"file_pipeline/{transcript.id}/tracks/original_track_{track_idx}.webm"
|
||||
)
|
||||
await storage.put_file(storage_path, track_data)
|
||||
url = await storage.get_file_url(storage_path)
|
||||
return track_data, url
|
||||
|
||||
# Create PyAV filter graph for padding
|
||||
graph = av.filter.Graph()
|
||||
|
||||
# Input buffer
|
||||
in_args = (
|
||||
f"time_base=1/{sample_rate}:"
|
||||
f"sample_rate={sample_rate}:"
|
||||
f"sample_fmt=s16:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
input_buffer = graph.add("abuffer", args=in_args, name="in")
|
||||
|
||||
# Add delay filter for padding
|
||||
delay_ms = int(start_time_seconds * 1000)
|
||||
delay_filter = graph.add(
|
||||
"adelay", args=f"delays={delay_ms}|{delay_ms}:all=1", name="delay"
|
||||
)
|
||||
|
||||
# Output sink
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
# Link filters
|
||||
input_buffer.link_to(delay_filter)
|
||||
delay_filter.link_to(sink)
|
||||
|
||||
graph.configure()
|
||||
|
||||
# Process audio through filter
|
||||
output_bytes = io.BytesIO()
|
||||
output_container = av.open(output_bytes, "w", format="webm")
|
||||
output_stream = output_container.add_stream("libopus", rate=sample_rate)
|
||||
output_stream.channels = 2
|
||||
|
||||
# Reopen input for processing
|
||||
input_container = av.open(io.BytesIO(track_data))
|
||||
resampler = AudioResampler(format="s16", layout="stereo", rate=sample_rate)
|
||||
|
||||
try:
|
||||
# Process frames
|
||||
for frame in input_container.decode(audio=0):
|
||||
# Resample to match filter requirements
|
||||
resampled_frames = resampler.resample(frame)
|
||||
for resampled_frame in resampled_frames:
|
||||
resampled_frame.pts = frame.pts
|
||||
resampled_frame.time_base = Fraction(1, sample_rate)
|
||||
input_buffer.push(resampled_frame)
|
||||
|
||||
# Pull from filter and encode
|
||||
while True:
|
||||
try:
|
||||
out_frame = sink.pull()
|
||||
out_frame.pts = out_frame.pts if out_frame.pts else 0
|
||||
out_frame.time_base = Fraction(1, sample_rate)
|
||||
for packet in output_stream.encode(out_frame):
|
||||
output_container.mux(packet)
|
||||
except av.BlockingIOError:
|
||||
break
|
||||
|
||||
# Flush
|
||||
input_buffer.push(None)
|
||||
while True:
|
||||
try:
|
||||
out_frame = sink.pull()
|
||||
for packet in output_stream.encode(out_frame):
|
||||
output_container.mux(packet)
|
||||
except (av.BlockingIOError, av.EOFError):
|
||||
break
|
||||
|
||||
# Flush encoder
|
||||
for packet in output_stream.encode(None):
|
||||
output_container.mux(packet)
|
||||
|
||||
finally:
|
||||
input_container.close()
|
||||
output_container.close()
|
||||
|
||||
padded_data = output_bytes.getvalue()
|
||||
|
||||
# Store padded track
|
||||
storage_path = (
|
||||
f"file_pipeline/{transcript.id}/tracks/padded_track_{track_idx}.webm"
|
||||
)
|
||||
await storage.put_file(storage_path, padded_data)
|
||||
padded_url = await storage.get_file_url(storage_path)
|
||||
|
||||
self.logger.info(
|
||||
f"Padded track {track_idx} with {start_time_seconds:.3f}s offset, stored at {storage_path}",
|
||||
track_idx=track_idx,
|
||||
delay_ms=delay_ms,
|
||||
padded_url=padded_url,
|
||||
)
|
||||
|
||||
return padded_data, padded_url
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_datas: list[bytes],
|
||||
writer: AudioFileWriterProcessor,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> None:
|
||||
"""
|
||||
Minimal multi-track mixdown using a PyAV filter graph (amix), no resampling.
|
||||
"""
|
||||
|
||||
# Discover target sample rate from first decodable frame
|
||||
target_sample_rate: int | None = None
|
||||
for data in track_datas:
|
||||
if not data:
|
||||
continue
|
||||
try:
|
||||
container = av.open(io.BytesIO(data))
|
||||
try:
|
||||
for frame in container.decode(audio=0):
|
||||
target_sample_rate = frame.sample_rate
|
||||
break
|
||||
finally:
|
||||
container.close()
|
||||
except Exception:
|
||||
continue
|
||||
if target_sample_rate:
|
||||
break
|
||||
|
||||
if not target_sample_rate:
|
||||
self.logger.warning("Mixdown skipped - no decodable audio frames found")
|
||||
return
|
||||
|
||||
# Build PyAV filter graph:
|
||||
# N abuffer (s32/stereo)
|
||||
# -> optional adelay per input (for alignment)
|
||||
# -> amix (s32)
|
||||
# -> aformat(s16)
|
||||
# -> sink
|
||||
graph = av.filter.Graph()
|
||||
inputs = []
|
||||
valid_track_datas = [d for d in track_datas if d]
|
||||
# Align offsets list with the filtered inputs (skip empties)
|
||||
input_offsets_seconds = None
|
||||
if offsets_seconds is not None:
|
||||
input_offsets_seconds = [
|
||||
offsets_seconds[i] for i, d in enumerate(track_datas) if d
|
||||
]
|
||||
for idx, data in enumerate(valid_track_datas):
|
||||
args = (
|
||||
f"time_base=1/{target_sample_rate}:"
|
||||
f"sample_rate={target_sample_rate}:"
|
||||
f"sample_fmt=s32:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
|
||||
inputs.append(in_ctx)
|
||||
|
||||
if not inputs:
|
||||
self.logger.warning("Mixdown skipped - no valid inputs for graph")
|
||||
return
|
||||
|
||||
mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
|
||||
|
||||
fmt = graph.add(
|
||||
"aformat",
|
||||
args=(
|
||||
f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}"
|
||||
),
|
||||
name="fmt",
|
||||
)
|
||||
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
# Optional per-input delay before mixing
|
||||
delays_ms: list[int] = []
|
||||
if input_offsets_seconds is not None:
|
||||
base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
|
||||
delays_ms = [
|
||||
max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds
|
||||
]
|
||||
else:
|
||||
delays_ms = [0 for _ in inputs]
|
||||
|
||||
for idx, in_ctx in enumerate(inputs):
|
||||
delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
|
||||
if delay_ms > 0:
|
||||
# adelay requires one value per channel; use same for stereo
|
||||
adelay = graph.add(
|
||||
"adelay",
|
||||
args=f"delays={delay_ms}|{delay_ms}:all=1",
|
||||
name=f"delay{idx}",
|
||||
)
|
||||
in_ctx.link_to(adelay)
|
||||
adelay.link_to(mixer, 0, idx)
|
||||
else:
|
||||
in_ctx.link_to(mixer, 0, idx)
|
||||
mixer.link_to(fmt)
|
||||
fmt.link_to(sink)
|
||||
graph.configure()
|
||||
|
||||
# Open containers for decoding
|
||||
containers = []
|
||||
for i, d in enumerate(valid_track_datas):
|
||||
try:
|
||||
c = av.open(io.BytesIO(d))
|
||||
containers.append(c)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Mixdown: failed to open container", input=i, error=str(e)
|
||||
)
|
||||
containers.append(None)
|
||||
# Filter out Nones for decoders
|
||||
containers = [c for c in containers if c is not None]
|
||||
decoders = [c.decode(audio=0) for c in containers]
|
||||
active = [True] * len(decoders)
|
||||
# Per-input resamplers to enforce s32/stereo at the same rate (no resample of rate)
|
||||
resamplers = [
|
||||
AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
|
||||
for _ in decoders
|
||||
]
|
||||
|
||||
try:
|
||||
# Round-robin feed frames into graph, pull mixed frames as they become available
|
||||
while any(active):
|
||||
for i, (dec, is_active) in enumerate(zip(decoders, active)):
|
||||
if not is_active:
|
||||
continue
|
||||
try:
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
continue
|
||||
|
||||
# Enforce same sample rate; convert format/layout to s16/stereo (no resample)
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
# Skip frames with differing rate
|
||||
continue
|
||||
out_frames = resamplers[i].resample(frame) or []
|
||||
for rf in out_frames:
|
||||
rf.sample_rate = target_sample_rate
|
||||
rf.time_base = Fraction(1, target_sample_rate)
|
||||
inputs[i].push(rf)
|
||||
|
||||
# Drain available mixed frames
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
|
||||
# Signal EOF to inputs and drain remaining
|
||||
for in_ctx in inputs:
|
||||
in_ctx.push(None)
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
finally:
|
||||
for c in containers:
|
||||
c.close()
|
||||
|
||||
async def set_status(self, transcript_id: str, status: TranscriptStatus):
|
||||
async with self.lock_transaction():
|
||||
return await transcripts_controller.set_status(transcript_id, status)
|
||||
|
||||
async def process(self, bucket_name: str, track_keys: list[str]):
|
||||
transcript = await self.get_transcript()
|
||||
|
||||
s3 = boto3.client(
|
||||
"s3",
|
||||
region_name=settings.RECORDING_STORAGE_AWS_REGION,
|
||||
aws_access_key_id=settings.RECORDING_STORAGE_AWS_ACCESS_KEY_ID,
|
||||
aws_secret_access_key=settings.RECORDING_STORAGE_AWS_SECRET_ACCESS_KEY,
|
||||
)
|
||||
|
||||
storage = get_transcripts_storage()
|
||||
|
||||
# Pre-download bytes for all tracks for mixing and transcription
|
||||
track_datas: list[bytes] = []
|
||||
for key in track_keys:
|
||||
try:
|
||||
obj = s3.get_object(Bucket=bucket_name, Key=key)
|
||||
track_datas.append(obj["Body"].read())
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Skipping track - cannot read S3 object", key=key, error=str(e)
|
||||
)
|
||||
track_datas.append(b"")
|
||||
|
||||
# REMOVED: Filename offset extraction - not needed anymore!
|
||||
# We use stream metadata start_time for padding instead
|
||||
|
||||
# Get stream metadata start_times for mixing (still useful for mixdown)
|
||||
stream_start_times: list[float] = []
|
||||
for data in track_datas:
|
||||
if not data:
|
||||
stream_start_times.append(0.0)
|
||||
continue
|
||||
|
||||
container = av.open(io.BytesIO(data))
|
||||
try:
|
||||
audio_stream = container.streams.audio[0]
|
||||
if (
|
||||
audio_stream.start_time is not None
|
||||
and audio_stream.time_base is not None
|
||||
):
|
||||
start_time = float(audio_stream.start_time * audio_stream.time_base)
|
||||
else:
|
||||
start_time = 0.0
|
||||
stream_start_times.append(start_time)
|
||||
finally:
|
||||
container.close()
|
||||
|
||||
# Mixdown all available tracks into transcript.audio_mp3_filename, using stream metadata offsets
|
||||
try:
|
||||
mp3_writer = AudioFileWriterProcessor(
|
||||
path=str(transcript.audio_mp3_filename)
|
||||
)
|
||||
await self.mixdown_tracks(track_datas, mp3_writer, stream_start_times)
|
||||
await mp3_writer.flush()
|
||||
except Exception as e:
|
||||
self.logger.error("Mixdown failed", error=str(e))
|
||||
|
||||
# PAD TRACKS BEFORE TRANSCRIPTION - THIS IS THE KEY FIX!
|
||||
padded_track_urls: list[str] = []
|
||||
for idx, data in enumerate(track_datas):
|
||||
if not data:
|
||||
padded_track_urls.append("")
|
||||
continue
|
||||
|
||||
_, padded_url = await self.pad_track_for_transcription(data, idx, storage)
|
||||
padded_track_urls.append(padded_url)
|
||||
self.logger.info(f"Padded track {idx} for transcription: {padded_url}")
|
||||
|
||||
# Transcribe PADDED tracks - timestamps will be automatically correct!
|
||||
speaker_transcripts: list[TranscriptType] = []
|
||||
for idx, padded_url in enumerate(padded_track_urls):
|
||||
if not padded_url:
|
||||
continue
|
||||
|
||||
try:
|
||||
# Transcribe the PADDED track
|
||||
t = await self.transcribe_file(padded_url, transcript.source_language)
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
"Transcription via default backend failed, trying local whisper",
|
||||
track_idx=idx,
|
||||
url=padded_url,
|
||||
error=str(e),
|
||||
)
|
||||
try:
|
||||
fallback = FileTranscriptAutoProcessor(name="whisper")
|
||||
result = None
|
||||
|
||||
async def capture_result(r):
|
||||
nonlocal result
|
||||
result = r
|
||||
|
||||
fallback.on(capture_result)
|
||||
await fallback.push(
|
||||
FileTranscriptInput(
|
||||
audio_url=padded_url, language=transcript.source_language
|
||||
)
|
||||
)
|
||||
await fallback.flush()
|
||||
if not result:
|
||||
raise Exception("No transcript captured in fallback")
|
||||
t = result
|
||||
except Exception as e2:
|
||||
self.logger.error(
|
||||
"Skipping track - transcription failed after fallback",
|
||||
track_idx=idx,
|
||||
url=padded_url,
|
||||
error=str(e2),
|
||||
)
|
||||
continue
|
||||
|
||||
if not t.words:
|
||||
continue
|
||||
|
||||
# NO OFFSET ADJUSTMENT NEEDED!
|
||||
# Timestamps are already correct because we transcribed padded tracks
|
||||
# Just set speaker ID
|
||||
for w in t.words:
|
||||
w.speaker = idx
|
||||
|
||||
speaker_transcripts.append(t)
|
||||
self.logger.info(
|
||||
f"Track {idx} transcribed successfully with {len(t.words)} words",
|
||||
track_idx=idx,
|
||||
)
|
||||
|
||||
if not speaker_transcripts:
|
||||
raise Exception("No valid track transcriptions")
|
||||
|
||||
# Merge all words and sort by timestamp
|
||||
merged_words = []
|
||||
for t in speaker_transcripts:
|
||||
merged_words.extend(t.words)
|
||||
merged_words.sort(
|
||||
key=lambda w: w.start if hasattr(w, "start") and w.start is not None else 0
|
||||
)
|
||||
|
||||
merged_transcript = TranscriptType(words=merged_words, translation=None)
|
||||
|
||||
await transcripts_controller.append_event(
|
||||
transcript,
|
||||
event="TRANSCRIPT",
|
||||
data=TranscriptText(
|
||||
text=merged_transcript.text, translation=merged_transcript.translation
|
||||
),
|
||||
)
|
||||
|
||||
topics = await self.detect_topics(merged_transcript, transcript.target_language)
|
||||
await asyncio.gather(
|
||||
self.generate_title(topics),
|
||||
self.generate_summaries(topics),
|
||||
return_exceptions=False,
|
||||
)
|
||||
|
||||
await self.set_status(transcript.id, "ended")
|
||||
|
||||
async def transcribe_file(self, audio_url: str, language: str) -> TranscriptType:
|
||||
processor = FileTranscriptAutoProcessor()
|
||||
input_data = FileTranscriptInput(audio_url=audio_url, language=language)
|
||||
|
||||
result: TranscriptType | None = None
|
||||
|
||||
async def capture_result(transcript):
|
||||
nonlocal result
|
||||
result = transcript
|
||||
|
||||
processor.on(capture_result)
|
||||
await processor.push(input_data)
|
||||
await processor.flush()
|
||||
|
||||
if not result:
|
||||
raise ValueError("No transcript captured")
|
||||
|
||||
return result
|
||||
|
||||
async def detect_topics(
|
||||
self, transcript: TranscriptType, target_language: str
|
||||
) -> list[TitleSummary]:
|
||||
chunk_size = 300
|
||||
topics: list[TitleSummary] = []
|
||||
|
||||
async def on_topic(topic: TitleSummary):
|
||||
topics.append(topic)
|
||||
return await self.on_topic(topic)
|
||||
|
||||
topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
|
||||
topic_detector.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for i in range(0, len(transcript.words), chunk_size):
|
||||
chunk_words = transcript.words[i : i + chunk_size]
|
||||
if not chunk_words:
|
||||
continue
|
||||
|
||||
chunk_transcript = TranscriptType(
|
||||
words=chunk_words, translation=transcript.translation
|
||||
)
|
||||
await topic_detector.push(chunk_transcript)
|
||||
|
||||
await topic_detector.flush()
|
||||
return topics
|
||||
|
||||
async def generate_title(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for title generation")
|
||||
return
|
||||
|
||||
processor = TranscriptFinalTitleProcessor(callback=self.on_title)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
async def generate_summaries(self, topics: list[TitleSummary]):
|
||||
if not topics:
|
||||
self.logger.warning("No topics for summary generation")
|
||||
return
|
||||
|
||||
transcript = await self.get_transcript()
|
||||
processor = TranscriptFinalSummaryProcessor(
|
||||
transcript=transcript,
|
||||
callback=self.on_long_summary,
|
||||
on_short_summary=self.on_short_summary,
|
||||
)
|
||||
processor.set_pipeline(self.empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
await processor.push(topic)
|
||||
|
||||
await processor.flush()
|
||||
|
||||
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def task_pipeline_multitrack_process(
|
||||
*, transcript_id: str, bucket_name: str, track_keys: list[str]
|
||||
):
|
||||
pipeline = PipelineMainMultitrack(transcript_id=transcript_id)
|
||||
try:
|
||||
await pipeline.set_status(transcript_id, "processing")
|
||||
await pipeline.process(bucket_name, track_keys)
|
||||
except Exception:
|
||||
await pipeline.set_status(transcript_id, "error")
|
||||
raise
|
||||
|
||||
post_chain = chain(
|
||||
task_cleanup_consent.si(transcript_id=transcript_id),
|
||||
task_pipeline_post_to_zulip.si(transcript_id=transcript_id),
|
||||
task_send_webhook_if_needed.si(transcript_id=transcript_id),
|
||||
)
|
||||
post_chain.delay()
|
||||
@@ -1,9 +0,0 @@
|
||||
"""Platform type definitions.
|
||||
|
||||
This module exists solely to define the Platform literal type without any imports,
|
||||
preventing circular import issues when used across the codebase.
|
||||
"""
|
||||
|
||||
from typing import Literal
|
||||
|
||||
Platform = Literal["whereby", "daily"]
|
||||
@@ -1,6 +1,6 @@
|
||||
from textwrap import dedent
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Field
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from reflector.llm import LLM
|
||||
from reflector.processors.base import Processor
|
||||
@@ -34,14 +34,8 @@ TOPIC_PROMPT = dedent(
|
||||
class TopicResponse(BaseModel):
|
||||
"""Structured response for topic detection"""
|
||||
|
||||
model_config = ConfigDict(populate_by_name=True)
|
||||
|
||||
title: str = Field(
|
||||
description="A descriptive title for the topic being discussed", alias="Title"
|
||||
)
|
||||
summary: str = Field(
|
||||
description="A concise 1-2 sentence summary of the discussion", alias="Summary"
|
||||
)
|
||||
title: str = Field(description="A descriptive title for the topic being discussed")
|
||||
summary: str = Field(description="A concise 1-2 sentence summary of the discussion")
|
||||
|
||||
|
||||
class TranscriptTopicDetectorProcessor(Processor):
|
||||
|
||||
@@ -4,8 +4,11 @@ import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Annotated, TypedDict
|
||||
|
||||
from profanityfilter import ProfanityFilter
|
||||
from pydantic import BaseModel, Field, PrivateAttr
|
||||
|
||||
from reflector.redis_cache import redis_cache
|
||||
|
||||
|
||||
class DiarizationSegment(TypedDict):
|
||||
"""Type definition for diarization segment containing speaker information"""
|
||||
@@ -17,6 +20,9 @@ class DiarizationSegment(TypedDict):
|
||||
|
||||
PUNC_RE = re.compile(r"[.;:?!…]")
|
||||
|
||||
profanity_filter = ProfanityFilter()
|
||||
profanity_filter.set_censor("*")
|
||||
|
||||
|
||||
class AudioFile(BaseModel):
|
||||
name: str
|
||||
@@ -118,11 +124,21 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
|
||||
|
||||
class Transcript(BaseModel):
|
||||
translation: str | None = None
|
||||
words: list[Word] = []
|
||||
words: list[Word] = None
|
||||
|
||||
@property
|
||||
def raw_text(self):
|
||||
# Uncensored text
|
||||
return "".join([word.text for word in self.words])
|
||||
|
||||
@redis_cache(prefix="profanity", duration=3600 * 24 * 7)
|
||||
def _get_censored_text(self, text: str):
|
||||
return profanity_filter.censor(text).strip()
|
||||
|
||||
@property
|
||||
def text(self):
|
||||
return "".join([word.text for word in self.words])
|
||||
# Censored text
|
||||
return self._get_censored_text(self.raw_text)
|
||||
|
||||
@property
|
||||
def human_timestamp(self):
|
||||
@@ -154,6 +170,12 @@ class Transcript(BaseModel):
|
||||
word.start += offset
|
||||
word.end += offset
|
||||
|
||||
def clone(self):
|
||||
words = [
|
||||
Word(text=word.text, start=word.start, end=word.end) for word in self.words
|
||||
]
|
||||
return Transcript(text=self.text, translation=self.translation, words=words)
|
||||
|
||||
def as_segments(self) -> list[TranscriptSegment]:
|
||||
return words_to_segments(self.words)
|
||||
|
||||
|
||||
@@ -1,17 +1,10 @@
|
||||
import asyncio
|
||||
import functools
|
||||
import json
|
||||
from typing import Optional
|
||||
|
||||
import redis
|
||||
import redis.asyncio as redis_async
|
||||
import structlog
|
||||
from redis.exceptions import LockError
|
||||
|
||||
from reflector.settings import settings
|
||||
|
||||
logger = structlog.get_logger(__name__)
|
||||
|
||||
redis_clients = {}
|
||||
|
||||
|
||||
@@ -28,12 +21,6 @@ def get_redis_client(db=0):
|
||||
return redis_clients[db]
|
||||
|
||||
|
||||
async def get_async_redis_client(db: int = 0):
|
||||
return await redis_async.from_url(
|
||||
f"redis://{settings.REDIS_HOST}:{settings.REDIS_PORT}/{db}"
|
||||
)
|
||||
|
||||
|
||||
def redis_cache(prefix="cache", duration=3600, db=settings.REDIS_CACHE_DB, argidx=1):
|
||||
"""
|
||||
Cache the result of a function in Redis.
|
||||
@@ -62,87 +49,3 @@ def redis_cache(prefix="cache", duration=3600, db=settings.REDIS_CACHE_DB, argid
|
||||
return wrapper
|
||||
|
||||
return decorator
|
||||
|
||||
|
||||
class RedisAsyncLock:
|
||||
def __init__(
|
||||
self,
|
||||
key: str,
|
||||
timeout: int = 120,
|
||||
extend_interval: int = 30,
|
||||
skip_if_locked: bool = False,
|
||||
blocking: bool = True,
|
||||
blocking_timeout: Optional[float] = None,
|
||||
):
|
||||
self.key = f"async_lock:{key}"
|
||||
self.timeout = timeout
|
||||
self.extend_interval = extend_interval
|
||||
self.skip_if_locked = skip_if_locked
|
||||
self.blocking = blocking
|
||||
self.blocking_timeout = blocking_timeout
|
||||
self._lock = None
|
||||
self._redis = None
|
||||
self._extend_task = None
|
||||
self._acquired = False
|
||||
|
||||
async def _extend_lock_periodically(self):
|
||||
while True:
|
||||
try:
|
||||
await asyncio.sleep(self.extend_interval)
|
||||
if self._lock:
|
||||
await self._lock.extend(self.timeout, replace_ttl=True)
|
||||
logger.debug("Extended lock", key=self.key)
|
||||
except LockError:
|
||||
logger.warning("Failed to extend lock", key=self.key)
|
||||
break
|
||||
except asyncio.CancelledError:
|
||||
break
|
||||
except Exception as e:
|
||||
logger.error("Error extending lock", key=self.key, error=str(e))
|
||||
break
|
||||
|
||||
async def __aenter__(self):
|
||||
self._redis = await get_async_redis_client()
|
||||
self._lock = self._redis.lock(
|
||||
self.key,
|
||||
timeout=self.timeout,
|
||||
blocking=self.blocking,
|
||||
blocking_timeout=self.blocking_timeout,
|
||||
)
|
||||
|
||||
self._acquired = await self._lock.acquire()
|
||||
|
||||
if not self._acquired:
|
||||
if self.skip_if_locked:
|
||||
logger.warning(
|
||||
"Lock already acquired by another process, skipping", key=self.key
|
||||
)
|
||||
return self
|
||||
else:
|
||||
raise LockError(f"Failed to acquire lock: {self.key}")
|
||||
|
||||
self._extend_task = asyncio.create_task(self._extend_lock_periodically())
|
||||
logger.info("Acquired lock", key=self.key)
|
||||
return self
|
||||
|
||||
async def __aexit__(self, exc_type, exc_val, exc_tb):
|
||||
if self._extend_task:
|
||||
self._extend_task.cancel()
|
||||
try:
|
||||
await self._extend_task
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
|
||||
if self._acquired and self._lock:
|
||||
try:
|
||||
await self._lock.release()
|
||||
logger.info("Released lock", key=self.key)
|
||||
except LockError:
|
||||
logger.debug("Lock already released or expired", key=self.key)
|
||||
|
||||
if self._redis:
|
||||
await self._redis.aclose()
|
||||
|
||||
@property
|
||||
def acquired(self) -> bool:
|
||||
return self._acquired
|
||||
|
||||
@@ -1,408 +0,0 @@
|
||||
"""
|
||||
ICS Calendar Synchronization Service
|
||||
|
||||
This module provides services for fetching, parsing, and synchronizing ICS (iCalendar)
|
||||
calendar feeds with room booking data in the database.
|
||||
|
||||
Key Components:
|
||||
- ICSFetchService: Handles HTTP fetching and parsing of ICS calendar data
|
||||
- ICSSyncService: Manages the synchronization process between ICS feeds and database
|
||||
|
||||
Example Usage:
|
||||
# Sync a room's calendar
|
||||
room = Room(id="room1", name="conference-room", ics_url="https://cal.example.com/room.ics")
|
||||
result = await ics_sync_service.sync_room_calendar(room)
|
||||
|
||||
# Result structure:
|
||||
{
|
||||
"status": "success", # success|unchanged|error|skipped
|
||||
"hash": "abc123...", # MD5 hash of ICS content
|
||||
"events_found": 5, # Events matching this room
|
||||
"total_events": 12, # Total events in calendar within time window
|
||||
"events_created": 2, # New events added to database
|
||||
"events_updated": 3, # Existing events modified
|
||||
"events_deleted": 1 # Events soft-deleted (no longer in calendar)
|
||||
}
|
||||
|
||||
Event Matching:
|
||||
Events are matched to rooms by checking if the room's full URL appears in the
|
||||
event's LOCATION or DESCRIPTION fields. Only events within a 25-hour window
|
||||
(1 hour ago to 24 hours from now) are processed.
|
||||
|
||||
Input: ICS calendar URL (e.g., "https://calendar.google.com/calendar/ical/...")
|
||||
Output: EventData objects with structured calendar information:
|
||||
{
|
||||
"ics_uid": "event123@google.com",
|
||||
"title": "Team Meeting",
|
||||
"description": "Weekly sync meeting",
|
||||
"location": "https://meet.company.com/conference-room",
|
||||
"start_time": datetime(2024, 1, 15, 14, 0, tzinfo=UTC),
|
||||
"end_time": datetime(2024, 1, 15, 15, 0, tzinfo=UTC),
|
||||
"attendees": [
|
||||
{"email": "user@company.com", "name": "John Doe", "role": "ORGANIZER"},
|
||||
{"email": "attendee@company.com", "name": "Jane Smith", "status": "ACCEPTED"}
|
||||
],
|
||||
"ics_raw_data": "BEGIN:VEVENT\nUID:event123@google.com\n..."
|
||||
}
|
||||
"""
|
||||
|
||||
import hashlib
|
||||
from datetime import date, datetime, timedelta, timezone
|
||||
from enum import Enum
|
||||
from typing import TypedDict
|
||||
|
||||
import httpx
|
||||
import pytz
|
||||
import structlog
|
||||
from icalendar import Calendar, Event
|
||||
|
||||
from reflector.db.calendar_events import CalendarEvent, calendar_events_controller
|
||||
from reflector.db.rooms import Room, rooms_controller
|
||||
from reflector.redis_cache import RedisAsyncLock
|
||||
from reflector.settings import settings
|
||||
|
||||
logger = structlog.get_logger()
|
||||
|
||||
EVENT_WINDOW_DELTA_START = timedelta(hours=-1)
|
||||
EVENT_WINDOW_DELTA_END = timedelta(hours=24)
|
||||
|
||||
|
||||
class SyncStatus(str, Enum):
|
||||
SUCCESS = "success"
|
||||
UNCHANGED = "unchanged"
|
||||
ERROR = "error"
|
||||
SKIPPED = "skipped"
|
||||
|
||||
|
||||
class AttendeeData(TypedDict, total=False):
|
||||
email: str | None
|
||||
name: str | None
|
||||
status: str | None
|
||||
role: str | None
|
||||
|
||||
|
||||
class EventData(TypedDict):
|
||||
ics_uid: str
|
||||
title: str | None
|
||||
description: str | None
|
||||
location: str | None
|
||||
start_time: datetime
|
||||
end_time: datetime
|
||||
attendees: list[AttendeeData]
|
||||
ics_raw_data: str
|
||||
|
||||
|
||||
class SyncStats(TypedDict):
|
||||
events_created: int
|
||||
events_updated: int
|
||||
events_deleted: int
|
||||
|
||||
|
||||
class SyncResultBase(TypedDict):
|
||||
status: SyncStatus
|
||||
|
||||
|
||||
class SyncResult(SyncResultBase, total=False):
|
||||
hash: str | None
|
||||
events_found: int
|
||||
total_events: int
|
||||
events_created: int
|
||||
events_updated: int
|
||||
events_deleted: int
|
||||
error: str | None
|
||||
reason: str | None
|
||||
|
||||
|
||||
class ICSFetchService:
|
||||
def __init__(self):
|
||||
self.client = httpx.AsyncClient(
|
||||
timeout=30.0, headers={"User-Agent": "Reflector/1.0"}
|
||||
)
|
||||
|
||||
async def fetch_ics(self, url: str) -> str:
|
||||
response = await self.client.get(url)
|
||||
response.raise_for_status()
|
||||
|
||||
return response.text
|
||||
|
||||
def parse_ics(self, ics_content: str) -> Calendar:
|
||||
return Calendar.from_ical(ics_content)
|
||||
|
||||
def extract_room_events(
|
||||
self, calendar: Calendar, room_name: str, room_url: str
|
||||
) -> tuple[list[EventData], int]:
|
||||
events = []
|
||||
total_events = 0
|
||||
now = datetime.now(timezone.utc)
|
||||
window_start = now + EVENT_WINDOW_DELTA_START
|
||||
window_end = now + EVENT_WINDOW_DELTA_END
|
||||
|
||||
for component in calendar.walk():
|
||||
if component.name != "VEVENT":
|
||||
continue
|
||||
|
||||
status = component.get("STATUS", "").upper()
|
||||
if status == "CANCELLED":
|
||||
continue
|
||||
|
||||
# Count total non-cancelled events in the time window
|
||||
event_data = self._parse_event(component)
|
||||
if event_data and window_start <= event_data["start_time"] <= window_end:
|
||||
total_events += 1
|
||||
|
||||
# Check if event matches this room
|
||||
if self._event_matches_room(component, room_name, room_url):
|
||||
events.append(event_data)
|
||||
|
||||
return events, total_events
|
||||
|
||||
def _event_matches_room(self, event: Event, room_name: str, room_url: str) -> bool:
|
||||
location = str(event.get("LOCATION", ""))
|
||||
description = str(event.get("DESCRIPTION", ""))
|
||||
|
||||
# Only match full room URL
|
||||
# XXX leaved here as a patterns, to later be extended with tinyurl or such too
|
||||
patterns = [
|
||||
room_url,
|
||||
]
|
||||
|
||||
# Check location and description for patterns
|
||||
text_to_check = f"{location} {description}".lower()
|
||||
for pattern in patterns:
|
||||
if pattern.lower() in text_to_check:
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def _parse_event(self, event: Event) -> EventData | None:
|
||||
uid = str(event.get("UID", ""))
|
||||
summary = str(event.get("SUMMARY", ""))
|
||||
description = str(event.get("DESCRIPTION", ""))
|
||||
location = str(event.get("LOCATION", ""))
|
||||
dtstart = event.get("DTSTART")
|
||||
dtend = event.get("DTEND")
|
||||
|
||||
if not dtstart:
|
||||
return None
|
||||
|
||||
# Convert fields
|
||||
start_time = self._normalize_datetime(
|
||||
dtstart.dt if hasattr(dtstart, "dt") else dtstart
|
||||
)
|
||||
end_time = (
|
||||
self._normalize_datetime(dtend.dt if hasattr(dtend, "dt") else dtend)
|
||||
if dtend
|
||||
else start_time + timedelta(hours=1)
|
||||
)
|
||||
attendees = self._parse_attendees(event)
|
||||
|
||||
# Get raw event data for storage
|
||||
raw_data = event.to_ical().decode("utf-8")
|
||||
|
||||
return {
|
||||
"ics_uid": uid,
|
||||
"title": summary,
|
||||
"description": description,
|
||||
"location": location,
|
||||
"start_time": start_time,
|
||||
"end_time": end_time,
|
||||
"attendees": attendees,
|
||||
"ics_raw_data": raw_data,
|
||||
}
|
||||
|
||||
def _normalize_datetime(self, dt) -> datetime:
|
||||
# Ensure datetime is with timezone, if not, assume UTC
|
||||
if isinstance(dt, date) and not isinstance(dt, datetime):
|
||||
dt = datetime.combine(dt, datetime.min.time())
|
||||
dt = pytz.UTC.localize(dt)
|
||||
elif isinstance(dt, datetime):
|
||||
if dt.tzinfo is None:
|
||||
dt = pytz.UTC.localize(dt)
|
||||
else:
|
||||
dt = dt.astimezone(pytz.UTC)
|
||||
|
||||
return dt
|
||||
|
||||
def _parse_attendees(self, event: Event) -> list[AttendeeData]:
|
||||
# Extracts attendee information from both ATTENDEE and ORGANIZER properties.
|
||||
# Handles malformed comma-separated email addresses in single ATTENDEE fields
|
||||
# by splitting them into separate attendee entries. Returns a list of attendee
|
||||
# data including email, name, status, and role information.
|
||||
final_attendees = []
|
||||
|
||||
attendees = event.get("ATTENDEE", [])
|
||||
if not isinstance(attendees, list):
|
||||
attendees = [attendees]
|
||||
for att in attendees:
|
||||
email_str = str(att).replace("mailto:", "") if att else None
|
||||
|
||||
# Handle malformed comma-separated email addresses in a single ATTENDEE field
|
||||
if email_str and "," in email_str:
|
||||
# Split comma-separated emails and create separate attendee entries
|
||||
email_parts = [email.strip() for email in email_str.split(",")]
|
||||
for email in email_parts:
|
||||
if email and "@" in email:
|
||||
clean_email = email.replace("MAILTO:", "").replace(
|
||||
"mailto:", ""
|
||||
)
|
||||
att_data: AttendeeData = {
|
||||
"email": clean_email,
|
||||
"name": att.params.get("CN")
|
||||
if hasattr(att, "params") and email == email_parts[0]
|
||||
else None,
|
||||
"status": att.params.get("PARTSTAT")
|
||||
if hasattr(att, "params") and email == email_parts[0]
|
||||
else None,
|
||||
"role": att.params.get("ROLE")
|
||||
if hasattr(att, "params") and email == email_parts[0]
|
||||
else None,
|
||||
}
|
||||
final_attendees.append(att_data)
|
||||
else:
|
||||
# Normal single attendee
|
||||
att_data: AttendeeData = {
|
||||
"email": email_str,
|
||||
"name": att.params.get("CN") if hasattr(att, "params") else None,
|
||||
"status": att.params.get("PARTSTAT")
|
||||
if hasattr(att, "params")
|
||||
else None,
|
||||
"role": att.params.get("ROLE") if hasattr(att, "params") else None,
|
||||
}
|
||||
final_attendees.append(att_data)
|
||||
|
||||
# Add organizer
|
||||
organizer = event.get("ORGANIZER")
|
||||
if organizer:
|
||||
org_email = (
|
||||
str(organizer).replace("mailto:", "").replace("MAILTO:", "")
|
||||
if organizer
|
||||
else None
|
||||
)
|
||||
org_data: AttendeeData = {
|
||||
"email": org_email,
|
||||
"name": organizer.params.get("CN")
|
||||
if hasattr(organizer, "params")
|
||||
else None,
|
||||
"role": "ORGANIZER",
|
||||
}
|
||||
final_attendees.append(org_data)
|
||||
|
||||
return final_attendees
|
||||
|
||||
|
||||
class ICSSyncService:
|
||||
def __init__(self):
|
||||
self.fetch_service = ICSFetchService()
|
||||
|
||||
async def sync_room_calendar(self, room: Room) -> SyncResult:
|
||||
async with RedisAsyncLock(
|
||||
f"ics_sync_room:{room.id}", skip_if_locked=True
|
||||
) as lock:
|
||||
if not lock.acquired:
|
||||
logger.warning("ICS sync already in progress for room", room_id=room.id)
|
||||
return {
|
||||
"status": SyncStatus.SKIPPED,
|
||||
"reason": "Sync already in progress",
|
||||
}
|
||||
|
||||
return await self._sync_room_calendar(room)
|
||||
|
||||
async def _sync_room_calendar(self, room: Room) -> SyncResult:
|
||||
if not room.ics_enabled or not room.ics_url:
|
||||
return {"status": SyncStatus.SKIPPED, "reason": "ICS not configured"}
|
||||
|
||||
try:
|
||||
if not self._should_sync(room):
|
||||
return {"status": SyncStatus.SKIPPED, "reason": "Not time to sync yet"}
|
||||
|
||||
ics_content = await self.fetch_service.fetch_ics(room.ics_url)
|
||||
calendar = self.fetch_service.parse_ics(ics_content)
|
||||
|
||||
content_hash = hashlib.md5(ics_content.encode()).hexdigest()
|
||||
if room.ics_last_etag == content_hash:
|
||||
logger.info("No changes in ICS for room", room_id=room.id)
|
||||
room_url = f"{settings.UI_BASE_URL}/{room.name}"
|
||||
events, total_events = self.fetch_service.extract_room_events(
|
||||
calendar, room.name, room_url
|
||||
)
|
||||
return {
|
||||
"status": SyncStatus.UNCHANGED,
|
||||
"hash": content_hash,
|
||||
"events_found": len(events),
|
||||
"total_events": total_events,
|
||||
"events_created": 0,
|
||||
"events_updated": 0,
|
||||
"events_deleted": 0,
|
||||
}
|
||||
|
||||
# Extract matching events
|
||||
room_url = f"{settings.UI_BASE_URL}/{room.name}"
|
||||
events, total_events = self.fetch_service.extract_room_events(
|
||||
calendar, room.name, room_url
|
||||
)
|
||||
sync_result = await self._sync_events_to_database(room.id, events)
|
||||
|
||||
# Update room sync metadata
|
||||
await rooms_controller.update(
|
||||
room,
|
||||
{
|
||||
"ics_last_sync": datetime.now(timezone.utc),
|
||||
"ics_last_etag": content_hash,
|
||||
},
|
||||
mutate=False,
|
||||
)
|
||||
|
||||
return {
|
||||
"status": SyncStatus.SUCCESS,
|
||||
"hash": content_hash,
|
||||
"events_found": len(events),
|
||||
"total_events": total_events,
|
||||
**sync_result,
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error("Failed to sync ICS for room", room_id=room.id, error=str(e))
|
||||
return {"status": SyncStatus.ERROR, "error": str(e)}
|
||||
|
||||
def _should_sync(self, room: Room) -> bool:
|
||||
if not room.ics_last_sync:
|
||||
return True
|
||||
|
||||
time_since_sync = datetime.now(timezone.utc) - room.ics_last_sync
|
||||
return time_since_sync.total_seconds() >= room.ics_fetch_interval
|
||||
|
||||
async def _sync_events_to_database(
|
||||
self, room_id: str, events: list[EventData]
|
||||
) -> SyncStats:
|
||||
created = 0
|
||||
updated = 0
|
||||
|
||||
current_ics_uids = []
|
||||
|
||||
for event_data in events:
|
||||
calendar_event = CalendarEvent(room_id=room_id, **event_data)
|
||||
existing = await calendar_events_controller.get_by_ics_uid(
|
||||
room_id, event_data["ics_uid"]
|
||||
)
|
||||
|
||||
if existing:
|
||||
updated += 1
|
||||
else:
|
||||
created += 1
|
||||
|
||||
await calendar_events_controller.upsert(calendar_event)
|
||||
current_ics_uids.append(event_data["ics_uid"])
|
||||
|
||||
# Soft delete events that are no longer in calendar
|
||||
deleted = await calendar_events_controller.soft_delete_missing(
|
||||
room_id, current_ics_uids
|
||||
)
|
||||
|
||||
return {
|
||||
"events_created": created,
|
||||
"events_updated": updated,
|
||||
"events_deleted": deleted,
|
||||
}
|
||||
|
||||
|
||||
ics_sync_service = ICSSyncService()
|
||||
@@ -1,7 +1,6 @@
|
||||
from pydantic.types import PositiveInt
|
||||
from pydantic_settings import BaseSettings, SettingsConfigDict
|
||||
|
||||
from reflector.platform_types import Platform
|
||||
from reflector.utils.string import NonEmptyString
|
||||
|
||||
|
||||
@@ -124,24 +123,22 @@ class Settings(BaseSettings):
|
||||
# Whereby integration
|
||||
WHEREBY_API_URL: str = "https://api.whereby.dev/v1"
|
||||
WHEREBY_API_KEY: NonEmptyString | None = None
|
||||
|
||||
# Jibri integration
|
||||
JIBRI_RECORDINGS_PATH: str = "/recordings"
|
||||
WHEREBY_WEBHOOK_SECRET: str | None = None
|
||||
AWS_WHEREBY_ACCESS_KEY_ID: str | None = None
|
||||
AWS_WHEREBY_ACCESS_KEY_SECRET: str | None = None
|
||||
AWS_PROCESS_RECORDING_QUEUE_URL: str | None = None
|
||||
SQS_POLLING_TIMEOUT_SECONDS: int = 60
|
||||
|
||||
# Daily.co integration
|
||||
DAILY_API_KEY: str | None = None
|
||||
DAILY_WEBHOOK_SECRET: str | None = None
|
||||
DAILY_SUBDOMAIN: str | None = None
|
||||
AWS_DAILY_S3_BUCKET: str | None = None
|
||||
AWS_DAILY_S3_REGION: str = "us-west-2"
|
||||
AWS_DAILY_ROLE_ARN: str | None = None
|
||||
|
||||
# Platform Migration Feature Flags
|
||||
DAILY_MIGRATION_ENABLED: bool = False
|
||||
DAILY_MIGRATION_ROOM_IDS: list[str] = []
|
||||
DEFAULT_VIDEO_PLATFORM: Platform = "whereby"
|
||||
# Jitsi Meet
|
||||
JITSI_DOMAIN: str = "meet.jit.si"
|
||||
JITSI_JWT_SECRET: str | None = None
|
||||
JITSI_WEBHOOK_SECRET: str | None = None
|
||||
JITSI_APP_ID: str = "reflector"
|
||||
JITSI_JWT_ISSUER: str = "reflector"
|
||||
JITSI_JWT_AUDIENCE: str = "jitsi"
|
||||
|
||||
# Zulip integration
|
||||
ZULIP_REALM: str | None = None
|
||||
|
||||
@@ -5,8 +5,7 @@ It allows seamless switching between providers (Whereby, Daily.co, etc.) without
|
||||
changing the core application logic.
|
||||
"""
|
||||
|
||||
from .base import VideoPlatformClient
|
||||
from .models import MeetingData, VideoPlatformConfig
|
||||
from .base import MeetingData, VideoPlatformClient, VideoPlatformConfig
|
||||
from .registry import get_platform_client, register_platform
|
||||
|
||||
__all__ = [
|
||||
|
||||
@@ -1,26 +1,48 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from datetime import datetime
|
||||
from typing import TYPE_CHECKING, Any, Dict, Optional
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from reflector.platform_types import Platform
|
||||
from pydantic import BaseModel
|
||||
|
||||
from .models import MeetingData, VideoPlatformConfig
|
||||
from reflector.db.rooms import Room
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from reflector.db.rooms import Room
|
||||
|
||||
class MeetingData(BaseModel):
|
||||
"""Standardized meeting data returned by all platforms."""
|
||||
|
||||
meeting_id: str
|
||||
room_name: str
|
||||
room_url: str
|
||||
host_room_url: str
|
||||
platform: str
|
||||
extra_data: Dict[str, Any] = {} # Platform-specific data
|
||||
|
||||
|
||||
class VideoPlatformConfig(BaseModel):
|
||||
"""Configuration for a video platform."""
|
||||
|
||||
api_key: str
|
||||
webhook_secret: str
|
||||
api_url: Optional[str] = None
|
||||
subdomain: Optional[str] = None
|
||||
s3_bucket: Optional[str] = None
|
||||
s3_region: Optional[str] = None
|
||||
aws_role_arn: Optional[str] = None
|
||||
aws_access_key_id: Optional[str] = None
|
||||
aws_access_key_secret: Optional[str] = None
|
||||
|
||||
|
||||
class VideoPlatformClient(ABC):
|
||||
"""Abstract base class for video platform integrations."""
|
||||
|
||||
PLATFORM_NAME: Platform
|
||||
PLATFORM_NAME: str = ""
|
||||
|
||||
def __init__(self, config: VideoPlatformConfig):
|
||||
self.config = config
|
||||
|
||||
@abstractmethod
|
||||
async def create_meeting(
|
||||
self, room_name_prefix: str, end_date: datetime, room: "Room"
|
||||
self, room_name_prefix: str, end_date: datetime, room: Room
|
||||
) -> MeetingData:
|
||||
"""Create a new meeting room."""
|
||||
pass
|
||||
@@ -47,7 +69,7 @@ class VideoPlatformClient(ABC):
|
||||
"""Verify webhook signature for security."""
|
||||
pass
|
||||
|
||||
def format_recording_config(self, room: "Room") -> Dict[str, Any]:
|
||||
def format_recording_config(self, room: Room) -> Dict[str, Any]:
|
||||
"""Format recording configuration for the platform.
|
||||
Can be overridden by specific implementations."""
|
||||
if room.recording_type == "cloud" and self.config.s3_bucket:
|
||||
|
||||
@@ -1,178 +0,0 @@
|
||||
import hmac
|
||||
from datetime import datetime
|
||||
from hashlib import sha256
|
||||
from http import HTTPStatus
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from reflector.db.rooms import Room
|
||||
from reflector.platform_types import Platform
|
||||
|
||||
from .base import VideoPlatformClient
|
||||
from .models import MeetingData, RecordingType, VideoPlatformConfig
|
||||
|
||||
|
||||
class DailyClient(VideoPlatformClient):
|
||||
PLATFORM_NAME: Platform = "daily"
|
||||
TIMEOUT = 10
|
||||
BASE_URL = "https://api.daily.co/v1"
|
||||
TIMESTAMP_FORMAT = "%Y%m%d%H%M%S"
|
||||
RECORDING_NONE: RecordingType = "none"
|
||||
RECORDING_CLOUD: RecordingType = "cloud"
|
||||
|
||||
def __init__(self, config: VideoPlatformConfig):
|
||||
super().__init__(config)
|
||||
self.headers = {
|
||||
"Authorization": f"Bearer {config.api_key}",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
async def create_meeting(
|
||||
self, room_name_prefix: str, end_date: datetime, room: Room
|
||||
) -> MeetingData:
|
||||
"""Create a Daily.co room."""
|
||||
timestamp = datetime.now().strftime(self.TIMESTAMP_FORMAT)
|
||||
if room_name_prefix:
|
||||
room_name = f"{room_name_prefix}-{timestamp}"
|
||||
else:
|
||||
room_name = f"room-{timestamp}"
|
||||
|
||||
data = {
|
||||
"name": room_name,
|
||||
"privacy": "private" if room.is_locked else "public",
|
||||
"properties": {
|
||||
"enable_recording": "raw-tracks"
|
||||
if room.recording_type != self.RECORDING_NONE
|
||||
else False,
|
||||
"enable_chat": True,
|
||||
"enable_screenshare": True,
|
||||
"start_video_off": False,
|
||||
"start_audio_off": False,
|
||||
"exp": int(end_date.timestamp()),
|
||||
},
|
||||
}
|
||||
|
||||
# Configure S3 bucket for recordings
|
||||
# NOTE: Not checking room.recording_type - figure out later if conditional needed
|
||||
assert self.config.s3_bucket, "S3 bucket must be configured"
|
||||
data["properties"]["recordings_bucket"] = {
|
||||
"bucket_name": self.config.s3_bucket,
|
||||
"bucket_region": self.config.s3_region,
|
||||
"assume_role_arn": self.config.aws_role_arn,
|
||||
"allow_api_access": True,
|
||||
}
|
||||
|
||||
from reflector.logger import logger
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.post(
|
||||
f"{self.BASE_URL}/rooms",
|
||||
headers=self.headers,
|
||||
json=data,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
if response.status_code >= 400:
|
||||
logger.error(
|
||||
"Daily.co API error",
|
||||
status_code=response.status_code,
|
||||
response_body=response.text,
|
||||
request_data=data,
|
||||
)
|
||||
response.raise_for_status()
|
||||
result = response.json()
|
||||
|
||||
# Format response to match our standard
|
||||
room_url = result["url"]
|
||||
|
||||
return MeetingData(
|
||||
meeting_id=result["id"],
|
||||
room_name=result["name"],
|
||||
room_url=room_url,
|
||||
host_room_url=room_url,
|
||||
platform=self.PLATFORM_NAME,
|
||||
extra_data=result,
|
||||
)
|
||||
|
||||
async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
|
||||
"""Get Daily.co room information."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(
|
||||
f"{self.BASE_URL}/rooms/{room_name}",
|
||||
headers=self.headers,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
async def get_room_presence(self, room_name: str) -> Dict[str, Any]:
|
||||
"""Get real-time participant data - Daily.co specific feature."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(
|
||||
f"{self.BASE_URL}/rooms/{room_name}/presence",
|
||||
headers=self.headers,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
async def delete_room(self, room_name: str) -> bool:
|
||||
"""Delete a Daily.co room."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.delete(
|
||||
f"{self.BASE_URL}/rooms/{room_name}",
|
||||
headers=self.headers,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
# Daily.co returns 200 for success, 404 if room doesn't exist
|
||||
return response.status_code in (HTTPStatus.OK, HTTPStatus.NOT_FOUND)
|
||||
|
||||
async def upload_logo(self, room_name: str, logo_path: str) -> bool:
|
||||
"""Daily.co doesn't support custom logos per room - this is a no-op."""
|
||||
return True
|
||||
|
||||
def verify_webhook_signature(
|
||||
self, body: bytes, signature: str, timestamp: Optional[str] = None
|
||||
) -> bool:
|
||||
"""Verify Daily.co webhook signature.
|
||||
|
||||
Daily.co uses:
|
||||
- X-Webhook-Signature header
|
||||
- X-Webhook-Timestamp header
|
||||
- Signature format: HMAC-SHA256(base64_decode(secret), timestamp + '.' + body)
|
||||
- Result is base64 encoded
|
||||
"""
|
||||
if not signature or not timestamp:
|
||||
return False
|
||||
|
||||
try:
|
||||
import base64
|
||||
|
||||
secret_bytes = base64.b64decode(self.config.webhook_secret)
|
||||
|
||||
signed_content = timestamp.encode() + b"." + body
|
||||
|
||||
expected = hmac.new(secret_bytes, signed_content, sha256).digest()
|
||||
expected_b64 = base64.b64encode(expected).decode()
|
||||
|
||||
return hmac.compare_digest(expected_b64, signature)
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
async def create_meeting_token(self, room_name: str, enable_recording: bool) -> str:
|
||||
"""Create meeting token for auto-recording."""
|
||||
data = {"properties": {"room_name": room_name}}
|
||||
|
||||
if enable_recording:
|
||||
data["properties"]["start_cloud_recording"] = True
|
||||
data["properties"]["enable_recording_ui"] = False
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.post(
|
||||
f"{self.BASE_URL}/meeting-tokens",
|
||||
headers=self.headers,
|
||||
json=data,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()["token"]
|
||||
@@ -1,80 +1,54 @@
|
||||
"""Factory for creating video platform clients based on configuration."""
|
||||
|
||||
from typing import Optional
|
||||
from typing import TYPE_CHECKING, Literal, Optional, overload
|
||||
|
||||
from reflector.db.rooms import VideoPlatform
|
||||
from reflector.settings import settings
|
||||
|
||||
from .base import Platform, VideoPlatformClient, VideoPlatformConfig
|
||||
from .base import VideoPlatformClient, VideoPlatformConfig
|
||||
from .registry import get_platform_client
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .jitsi import JitsiClient
|
||||
from .whereby import WherebyClient
|
||||
|
||||
def get_platform_config(platform: Platform) -> VideoPlatformConfig:
|
||||
|
||||
def get_platform_config(platform: str) -> VideoPlatformConfig:
|
||||
"""Get configuration for a specific platform."""
|
||||
if platform == "whereby":
|
||||
if not settings.WHEREBY_API_KEY:
|
||||
raise ValueError(
|
||||
"WHEREBY_API_KEY is required when platform='whereby'. "
|
||||
"Set WHEREBY_API_KEY environment variable."
|
||||
)
|
||||
if platform == VideoPlatform.WHEREBY:
|
||||
return VideoPlatformConfig(
|
||||
api_key=settings.WHEREBY_API_KEY,
|
||||
api_key=settings.WHEREBY_API_KEY or "",
|
||||
webhook_secret=settings.WHEREBY_WEBHOOK_SECRET or "",
|
||||
api_url=settings.WHEREBY_API_URL,
|
||||
s3_bucket=settings.RECORDING_STORAGE_AWS_BUCKET_NAME,
|
||||
s3_region=settings.RECORDING_STORAGE_AWS_REGION,
|
||||
aws_access_key_id=settings.AWS_WHEREBY_ACCESS_KEY_ID,
|
||||
aws_access_key_secret=settings.AWS_WHEREBY_ACCESS_KEY_SECRET,
|
||||
)
|
||||
elif platform == "daily":
|
||||
if not settings.DAILY_API_KEY:
|
||||
raise ValueError(
|
||||
"DAILY_API_KEY is required when platform='daily'. "
|
||||
"Set DAILY_API_KEY environment variable."
|
||||
)
|
||||
if not settings.DAILY_SUBDOMAIN:
|
||||
raise ValueError(
|
||||
"DAILY_SUBDOMAIN is required when platform='daily'. "
|
||||
"Set DAILY_SUBDOMAIN environment variable."
|
||||
)
|
||||
elif platform == VideoPlatform.JITSI:
|
||||
return VideoPlatformConfig(
|
||||
api_key=settings.DAILY_API_KEY,
|
||||
webhook_secret=settings.DAILY_WEBHOOK_SECRET or "",
|
||||
subdomain=settings.DAILY_SUBDOMAIN,
|
||||
s3_bucket=settings.AWS_DAILY_S3_BUCKET,
|
||||
s3_region=settings.AWS_DAILY_S3_REGION,
|
||||
aws_role_arn=settings.AWS_DAILY_ROLE_ARN,
|
||||
api_key="", # Jitsi uses JWT, no API key
|
||||
webhook_secret=settings.JITSI_WEBHOOK_SECRET or "",
|
||||
api_url=f"https://{settings.JITSI_DOMAIN}",
|
||||
)
|
||||
else:
|
||||
raise ValueError(f"Unknown platform: {platform}")
|
||||
|
||||
|
||||
def create_platform_client(platform: Platform) -> VideoPlatformClient:
|
||||
@overload
|
||||
def create_platform_client(platform: Literal["jitsi"]) -> "JitsiClient": ...
|
||||
|
||||
|
||||
@overload
|
||||
def create_platform_client(platform: Literal["whereby"]) -> "WherebyClient": ...
|
||||
|
||||
|
||||
def create_platform_client(platform: str) -> VideoPlatformClient:
|
||||
"""Create a video platform client instance."""
|
||||
config = get_platform_config(platform)
|
||||
return get_platform_client(platform, config)
|
||||
|
||||
|
||||
def get_platform_for_room(
|
||||
room_id: Optional[str] = None, room_platform: Optional[Platform] = None
|
||||
) -> Platform:
|
||||
"""Determine which platform to use for a room.
|
||||
|
||||
Priority order (highest to lowest):
|
||||
1. DAILY_MIGRATION_ROOM_IDS - env var override for testing/migration
|
||||
2. room_platform - database persisted platform choice
|
||||
3. DEFAULT_VIDEO_PLATFORM - env var fallback
|
||||
"""
|
||||
# If Daily migration is disabled, always use Whereby
|
||||
if not settings.DAILY_MIGRATION_ENABLED:
|
||||
return "whereby"
|
||||
|
||||
# Highest priority: If room is in migration list, use Daily (env var override)
|
||||
if room_id and room_id in settings.DAILY_MIGRATION_ROOM_IDS:
|
||||
return "daily"
|
||||
|
||||
# Second priority: Use room's persisted platform from database
|
||||
if room_platform:
|
||||
return room_platform
|
||||
|
||||
# Fallback: Use default platform from env var
|
||||
return settings.DEFAULT_VIDEO_PLATFORM
|
||||
def get_platform_for_room(room_id: Optional[str] = None) -> str:
|
||||
"""Determine which platform to use for a room based on feature flags."""
|
||||
# For now, default to whereby since we don't have feature flags yet
|
||||
return VideoPlatform.WHEREBY
|
||||
|
||||
4
server/reflector/video_platforms/jitsi/__init__.py
Normal file
4
server/reflector/video_platforms/jitsi/__init__.py
Normal file
@@ -0,0 +1,4 @@
|
||||
from .client import JitsiClient, JitsiMeetingData
|
||||
from .router import router
|
||||
|
||||
__all__ = ["JitsiClient", "JitsiMeetingData", "router"]
|
||||
111
server/reflector/video_platforms/jitsi/client.py
Normal file
111
server/reflector/video_platforms/jitsi/client.py
Normal file
@@ -0,0 +1,111 @@
|
||||
import hmac
|
||||
from datetime import datetime, timezone
|
||||
from hashlib import sha256
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import jwt
|
||||
|
||||
from reflector.db.rooms import Room, VideoPlatform
|
||||
from reflector.settings import settings
|
||||
from reflector.utils import generate_uuid4
|
||||
|
||||
from ..base import MeetingData, VideoPlatformClient
|
||||
|
||||
|
||||
class JitsiMeetingData(MeetingData):
|
||||
@property
|
||||
def user_jwt(self) -> str:
|
||||
return self.extra_data.get("user_jwt", "")
|
||||
|
||||
@property
|
||||
def host_jwt(self) -> str:
|
||||
return self.extra_data.get("host_jwt", "")
|
||||
|
||||
@property
|
||||
def domain(self) -> str:
|
||||
return self.extra_data.get("domain", "")
|
||||
|
||||
|
||||
class JitsiClient(VideoPlatformClient):
|
||||
PLATFORM_NAME = VideoPlatform.JITSI
|
||||
|
||||
def _generate_jwt(self, room: str, moderator: bool, exp: datetime) -> str:
|
||||
if not settings.JITSI_JWT_SECRET:
|
||||
raise ValueError("JITSI_JWT_SECRET is required for JWT generation")
|
||||
|
||||
payload = {
|
||||
"aud": settings.JITSI_JWT_AUDIENCE,
|
||||
"iss": settings.JITSI_JWT_ISSUER,
|
||||
"sub": settings.JITSI_DOMAIN,
|
||||
"room": room,
|
||||
"exp": int(exp.timestamp()),
|
||||
"context": {
|
||||
"user": {
|
||||
"name": "Reflector User",
|
||||
"moderator": moderator,
|
||||
},
|
||||
"features": {
|
||||
"recording": True,
|
||||
"livestreaming": False,
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
return jwt.encode(payload, settings.JITSI_JWT_SECRET, algorithm="HS256")
|
||||
|
||||
async def create_meeting(
|
||||
self, room_name_prefix: str, end_date: datetime, room: Room
|
||||
) -> JitsiMeetingData:
|
||||
jitsi_room = f"reflector-{room.name}-{generate_uuid4()}"
|
||||
|
||||
user_jwt = self._generate_jwt(room=jitsi_room, moderator=False, exp=end_date)
|
||||
host_jwt = self._generate_jwt(room=jitsi_room, moderator=True, exp=end_date)
|
||||
|
||||
room_url = f"https://{settings.JITSI_DOMAIN}/{jitsi_room}?jwt={user_jwt}"
|
||||
host_room_url = f"https://{settings.JITSI_DOMAIN}/{jitsi_room}?jwt={host_jwt}"
|
||||
|
||||
return JitsiMeetingData(
|
||||
meeting_id=generate_uuid4(),
|
||||
room_name=jitsi_room,
|
||||
room_url=room_url,
|
||||
host_room_url=host_room_url,
|
||||
platform=self.PLATFORM_NAME,
|
||||
extra_data={
|
||||
"user_jwt": user_jwt,
|
||||
"host_jwt": host_jwt,
|
||||
"domain": settings.JITSI_DOMAIN,
|
||||
},
|
||||
)
|
||||
|
||||
async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
|
||||
return {
|
||||
"roomName": room_name,
|
||||
"sessions": [
|
||||
{
|
||||
"sessionId": generate_uuid4(),
|
||||
"startTime": datetime.now(tz=timezone.utc).isoformat(),
|
||||
"participants": [],
|
||||
"isActive": True,
|
||||
}
|
||||
],
|
||||
}
|
||||
|
||||
async def delete_room(self, room_name: str) -> bool:
|
||||
return True
|
||||
|
||||
async def upload_logo(self, room_name: str, logo_path: str) -> bool:
|
||||
return True
|
||||
|
||||
def verify_webhook_signature(
|
||||
self, body: bytes, signature: str, timestamp: Optional[str] = None
|
||||
) -> bool:
|
||||
if not signature or not self.config.webhook_secret:
|
||||
return False
|
||||
|
||||
try:
|
||||
expected = hmac.new(
|
||||
self.config.webhook_secret.encode(), body, sha256
|
||||
).hexdigest()
|
||||
return hmac.compare_digest(expected, signature)
|
||||
except Exception:
|
||||
return False
|
||||
165
server/reflector/video_platforms/jitsi/router.py
Normal file
165
server/reflector/video_platforms/jitsi/router.py
Normal file
@@ -0,0 +1,165 @@
|
||||
import hmac
|
||||
from datetime import datetime
|
||||
from hashlib import sha256
|
||||
from typing import Any, Dict
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from reflector.db.meetings import meetings_controller
|
||||
from reflector.settings import settings
|
||||
|
||||
try:
|
||||
from reflector.video_platforms import create_platform_client
|
||||
except ImportError:
|
||||
# PyJWT not yet installed, will be added in final task
|
||||
def create_platform_client(platform: str):
|
||||
return None
|
||||
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
class JitsiWebhookEvent(BaseModel):
|
||||
event: str
|
||||
room: str
|
||||
timestamp: datetime
|
||||
data: Dict[str, Any] = {}
|
||||
|
||||
|
||||
class JibriRecordingEvent(BaseModel):
|
||||
room_name: str
|
||||
recording_file: str
|
||||
recording_status: str
|
||||
timestamp: datetime
|
||||
|
||||
|
||||
def verify_jitsi_webhook_signature(body: bytes, signature: str) -> bool:
|
||||
"""Verify Jitsi webhook signature using HMAC-SHA256."""
|
||||
if not signature or not settings.JITSI_WEBHOOK_SECRET:
|
||||
return False
|
||||
|
||||
try:
|
||||
client = create_platform_client("jitsi")
|
||||
if client is None:
|
||||
# Fallback verification when platform client not available
|
||||
expected = hmac.new(
|
||||
settings.JITSI_WEBHOOK_SECRET.encode(), body, sha256
|
||||
).hexdigest()
|
||||
return hmac.compare_digest(expected, signature)
|
||||
return client.verify_webhook_signature(body, signature)
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
@router.post("/jitsi/events")
|
||||
async def jitsi_events_webhook(event: JitsiWebhookEvent, request: Request):
|
||||
"""
|
||||
Handle Prosody event-sync webhooks from Jitsi Meet.
|
||||
|
||||
Expected event types:
|
||||
- muc-occupant-joined: participant joined the room
|
||||
- muc-occupant-left: participant left the room
|
||||
- jibri-recording-on: recording started
|
||||
- jibri-recording-off: recording stopped
|
||||
"""
|
||||
# Verify webhook signature
|
||||
body = await request.body()
|
||||
signature = request.headers.get("x-jitsi-signature", "")
|
||||
|
||||
if not verify_jitsi_webhook_signature(body, signature):
|
||||
raise HTTPException(status_code=401, detail="Invalid webhook signature")
|
||||
|
||||
# Find meeting by room name
|
||||
meeting = await meetings_controller.get_by_room_name(event.room)
|
||||
if not meeting:
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
# Handle participant events
|
||||
if event.event == "muc-occupant-joined":
|
||||
# Store event and update participant count
|
||||
await meetings_controller.participant_joined(
|
||||
meeting.id, {"timestamp": event.timestamp, "data": event.data}
|
||||
)
|
||||
current_count = getattr(meeting, "num_clients", 0)
|
||||
await meetings_controller.update_meeting(
|
||||
meeting.id, num_clients=current_count + 1
|
||||
)
|
||||
elif event.event == "muc-occupant-left":
|
||||
# Store event and update participant count
|
||||
await meetings_controller.participant_left(
|
||||
meeting.id, {"timestamp": event.timestamp, "data": event.data}
|
||||
)
|
||||
current_count = getattr(meeting, "num_clients", 0)
|
||||
await meetings_controller.update_meeting(
|
||||
meeting.id, num_clients=max(0, current_count - 1)
|
||||
)
|
||||
elif event.event == "jibri-recording-on":
|
||||
# Store recording started event
|
||||
await meetings_controller.recording_started(
|
||||
meeting.id, {"timestamp": event.timestamp, "data": event.data}
|
||||
)
|
||||
elif event.event == "jibri-recording-off":
|
||||
# Store recording stopped event
|
||||
await meetings_controller.recording_stopped(
|
||||
meeting.id, {"timestamp": event.timestamp, "data": event.data}
|
||||
)
|
||||
|
||||
return {"status": "ok", "event": event.event, "room": event.room}
|
||||
|
||||
|
||||
@router.post("/jibri/recording-complete")
|
||||
async def jibri_recording_complete(event: JibriRecordingEvent, request: Request):
|
||||
"""
|
||||
Handle Jibri recording completion webhook.
|
||||
|
||||
This endpoint is called by the Jibri finalize script when a recording
|
||||
is completed and uploaded to storage.
|
||||
"""
|
||||
# Verify webhook signature
|
||||
body = await request.body()
|
||||
signature = request.headers.get("x-jitsi-signature", "")
|
||||
|
||||
if not verify_jitsi_webhook_signature(body, signature):
|
||||
raise HTTPException(status_code=401, detail="Invalid webhook signature")
|
||||
|
||||
# Find meeting by room name
|
||||
meeting = await meetings_controller.get_by_room_name(event.room_name)
|
||||
if not meeting:
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
# Store recording completion event
|
||||
await meetings_controller.add_event(
|
||||
meeting.id,
|
||||
"recording_completed",
|
||||
{
|
||||
"recording_file": event.recording_file,
|
||||
"recording_status": event.recording_status,
|
||||
"timestamp": event.timestamp,
|
||||
},
|
||||
)
|
||||
|
||||
# TODO: Trigger recording processing pipeline
|
||||
# This is where we would:
|
||||
# 1. Download the recording file from Jibri storage
|
||||
# 2. Create a transcript record in the database
|
||||
# 3. Queue the audio processing tasks (chunking, transcription, etc.)
|
||||
# 4. Update meeting status to indicate recording is being processed
|
||||
|
||||
return {
|
||||
"status": "ok",
|
||||
"room_name": event.room_name,
|
||||
"recording_file": event.recording_file,
|
||||
"message": "Recording processing queued",
|
||||
}
|
||||
|
||||
|
||||
@router.get("/jitsi/health")
|
||||
async def jitsi_health_check():
|
||||
"""Simple health check endpoint for Jitsi webhook configuration."""
|
||||
return {
|
||||
"status": "ok",
|
||||
"service": "jitsi-webhooks",
|
||||
"timestamp": datetime.now(tz=timezone.utc).isoformat(),
|
||||
"webhook_secret_configured": bool(settings.JITSI_WEBHOOK_SECRET),
|
||||
}
|
||||
3
server/reflector/video_platforms/jitsi/tasks.py
Normal file
3
server/reflector/video_platforms/jitsi/tasks.py
Normal file
@@ -0,0 +1,3 @@
|
||||
"""Jitsi-specific worker tasks."""
|
||||
|
||||
# Placeholder for Jitsi recording tasks
|
||||
@@ -1,49 +0,0 @@
|
||||
"""Video platform data models.
|
||||
|
||||
Standard data models used across all video platform implementations.
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, Literal, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from reflector.platform_types import Platform
|
||||
|
||||
RecordingType = Literal["none", "local", "cloud"]
|
||||
|
||||
|
||||
class MeetingData(BaseModel):
|
||||
"""Standardized meeting data returned by all providers."""
|
||||
|
||||
platform: Platform
|
||||
meeting_id: str = Field(description="Platform-specific meeting identifier")
|
||||
room_url: str = Field(description="URL for participants to join")
|
||||
host_room_url: str = Field(description="URL for hosts (may be same as room_url)")
|
||||
room_name: str = Field(description="Human-readable room name")
|
||||
extra_data: Dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
class Config:
|
||||
json_schema_extra = {
|
||||
"example": {
|
||||
"platform": "whereby",
|
||||
"meeting_id": "12345678",
|
||||
"room_url": "https://subdomain.whereby.com/room-20251008120000",
|
||||
"host_room_url": "https://subdomain.whereby.com/room-20251008120000?roomKey=abc123",
|
||||
"room_name": "room-20251008120000",
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class VideoPlatformConfig(BaseModel):
|
||||
"""Platform-agnostic configuration model."""
|
||||
|
||||
api_key: str
|
||||
webhook_secret: str
|
||||
api_url: Optional[str] = None
|
||||
subdomain: Optional[str] = None # Whereby/Daily subdomain
|
||||
s3_bucket: Optional[str] = None
|
||||
s3_region: Optional[str] = None
|
||||
# Whereby uses access keys, Daily uses IAM role
|
||||
aws_access_key_id: Optional[str] = None
|
||||
aws_access_key_secret: Optional[str] = None
|
||||
aws_role_arn: Optional[str] = None
|
||||
@@ -1,39 +1,56 @@
|
||||
from typing import Dict, Type
|
||||
from typing import TYPE_CHECKING, Dict, Literal, Type, overload
|
||||
|
||||
from .base import Platform, VideoPlatformClient, VideoPlatformConfig
|
||||
from .base import VideoPlatformClient, VideoPlatformConfig
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from .jitsi import JitsiClient
|
||||
from .whereby import WherebyClient
|
||||
|
||||
# Registry of available video platforms
|
||||
_PLATFORMS: Dict[Platform, Type[VideoPlatformClient]] = {}
|
||||
_PLATFORMS: Dict[str, Type[VideoPlatformClient]] = {}
|
||||
|
||||
|
||||
def register_platform(name: Platform, client_class: Type[VideoPlatformClient]):
|
||||
def register_platform(name: str, client_class: Type[VideoPlatformClient]):
|
||||
"""Register a video platform implementation."""
|
||||
_PLATFORMS[name] = client_class
|
||||
_PLATFORMS[name.lower()] = client_class
|
||||
|
||||
|
||||
@overload
|
||||
def get_platform_client(
|
||||
platform: Literal["jitsi"], config: VideoPlatformConfig
|
||||
) -> "JitsiClient": ...
|
||||
|
||||
|
||||
@overload
|
||||
def get_platform_client(
|
||||
platform: Literal["whereby"], config: VideoPlatformConfig
|
||||
) -> "WherebyClient": ...
|
||||
|
||||
|
||||
def get_platform_client(
|
||||
platform: Platform, config: VideoPlatformConfig
|
||||
platform: str, config: VideoPlatformConfig
|
||||
) -> VideoPlatformClient:
|
||||
"""Get a video platform client instance."""
|
||||
if platform not in _PLATFORMS:
|
||||
platform_lower = platform.lower()
|
||||
if platform_lower not in _PLATFORMS:
|
||||
raise ValueError(f"Unknown video platform: {platform}")
|
||||
|
||||
client_class = _PLATFORMS[platform]
|
||||
client_class = _PLATFORMS[platform_lower]
|
||||
return client_class(config)
|
||||
|
||||
|
||||
def get_available_platforms() -> list[Platform]:
|
||||
def get_available_platforms() -> list[str]:
|
||||
"""Get list of available platform names."""
|
||||
return list(_PLATFORMS.keys())
|
||||
|
||||
|
||||
# Auto-register built-in platforms
|
||||
def _register_builtin_platforms():
|
||||
from .daily import DailyClient # noqa: PLC0415
|
||||
from .whereby import WherebyClient # noqa: PLC0415
|
||||
from .jitsi import JitsiClient
|
||||
from .whereby import WherebyClient
|
||||
|
||||
register_platform("jitsi", JitsiClient)
|
||||
register_platform("whereby", WherebyClient)
|
||||
register_platform("daily", DailyClient)
|
||||
|
||||
|
||||
_register_builtin_platforms()
|
||||
|
||||
@@ -1,140 +0,0 @@
|
||||
import hmac
|
||||
import json
|
||||
import re
|
||||
import time
|
||||
from datetime import datetime
|
||||
from hashlib import sha256
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from reflector.db.rooms import Room
|
||||
|
||||
from .base import MeetingData, Platform, VideoPlatformClient, VideoPlatformConfig
|
||||
|
||||
|
||||
class WherebyClient(VideoPlatformClient):
|
||||
"""Whereby video platform implementation."""
|
||||
|
||||
PLATFORM_NAME: Platform = "whereby"
|
||||
TIMEOUT = 10 # seconds
|
||||
MAX_ELAPSED_TIME = 60 * 1000 # 1 minute in milliseconds
|
||||
|
||||
def __init__(self, config: VideoPlatformConfig):
|
||||
super().__init__(config)
|
||||
self.headers = {
|
||||
"Content-Type": "application/json; charset=utf-8",
|
||||
"Authorization": f"Bearer {config.api_key}",
|
||||
}
|
||||
|
||||
async def create_meeting(
|
||||
self, room_name_prefix: str, end_date: datetime, room: Room
|
||||
) -> MeetingData:
|
||||
"""Create a Whereby meeting."""
|
||||
data = {
|
||||
"isLocked": room.is_locked,
|
||||
"roomNamePrefix": room_name_prefix,
|
||||
"roomNamePattern": "uuid",
|
||||
"roomMode": room.room_mode,
|
||||
"endDate": end_date.isoformat(),
|
||||
"fields": ["hostRoomUrl"],
|
||||
}
|
||||
|
||||
# Add recording configuration if cloud recording is enabled
|
||||
if room.recording_type == "cloud":
|
||||
data["recording"] = {
|
||||
"type": room.recording_type,
|
||||
"destination": {
|
||||
"provider": "s3",
|
||||
"bucket": self.config.s3_bucket,
|
||||
"accessKeyId": self.config.aws_access_key_id,
|
||||
"accessKeySecret": self.config.aws_access_key_secret,
|
||||
"fileFormat": "mp4",
|
||||
},
|
||||
"startTrigger": room.recording_trigger,
|
||||
}
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.post(
|
||||
f"{self.config.api_url}/meetings",
|
||||
headers=self.headers,
|
||||
json=data,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
result = response.json()
|
||||
|
||||
return MeetingData(
|
||||
meeting_id=result["meetingId"],
|
||||
room_name=result["roomName"],
|
||||
room_url=result["roomUrl"],
|
||||
host_room_url=result["hostRoomUrl"],
|
||||
platform=self.PLATFORM_NAME,
|
||||
extra_data=result,
|
||||
)
|
||||
|
||||
async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
|
||||
"""Get Whereby room session information."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(
|
||||
f"{self.config.api_url}/insights/room-sessions?roomName={room_name}",
|
||||
headers=self.headers,
|
||||
timeout=self.TIMEOUT,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
async def delete_room(self, room_name: str) -> bool:
|
||||
"""Whereby doesn't support room deletion - meetings expire automatically."""
|
||||
return True
|
||||
|
||||
async def upload_logo(self, room_name: str, logo_path: str) -> bool:
|
||||
"""Upload logo to Whereby room."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
with open(logo_path, "rb") as f:
|
||||
response = await client.put(
|
||||
f"{self.config.api_url}/rooms/{room_name}/theme/logo",
|
||||
headers={
|
||||
"Authorization": f"Bearer {self.config.api_key}",
|
||||
},
|
||||
timeout=self.TIMEOUT,
|
||||
files={"image": f},
|
||||
)
|
||||
response.raise_for_status()
|
||||
return True
|
||||
|
||||
def verify_webhook_signature(
|
||||
self, body: bytes, signature: str, timestamp: Optional[str] = None
|
||||
) -> bool:
|
||||
"""Verify Whereby webhook signature."""
|
||||
if not signature:
|
||||
return False
|
||||
|
||||
matches = re.match(r"t=(.*),v1=(.*)", signature)
|
||||
if not matches:
|
||||
return False
|
||||
|
||||
ts, sig = matches.groups()
|
||||
|
||||
# Check timestamp to prevent replay attacks
|
||||
current_time = int(time.time() * 1000)
|
||||
diff_time = current_time - int(ts) * 1000
|
||||
if diff_time >= self.MAX_ELAPSED_TIME:
|
||||
return False
|
||||
|
||||
# Verify signature
|
||||
body_dict = json.loads(body)
|
||||
signed_payload = f"{ts}.{json.dumps(body_dict, separators=(',', ':'))}"
|
||||
hmac_obj = hmac.new(
|
||||
self.config.webhook_secret.encode("utf-8"),
|
||||
signed_payload.encode("utf-8"),
|
||||
sha256,
|
||||
)
|
||||
expected_signature = hmac_obj.hexdigest()
|
||||
|
||||
try:
|
||||
return hmac.compare_digest(
|
||||
expected_signature.encode("utf-8"), sig.encode("utf-8")
|
||||
)
|
||||
except Exception:
|
||||
return False
|
||||
6
server/reflector/video_platforms/whereby/__init__.py
Normal file
6
server/reflector/video_platforms/whereby/__init__.py
Normal file
@@ -0,0 +1,6 @@
|
||||
"""Whereby video platform integration."""
|
||||
|
||||
from .client import WherebyClient
|
||||
from .router import router
|
||||
|
||||
__all__ = ["WherebyClient", "router"]
|
||||
113
server/reflector/video_platforms/whereby/client.py
Normal file
113
server/reflector/video_platforms/whereby/client.py
Normal file
@@ -0,0 +1,113 @@
|
||||
import hmac
|
||||
from datetime import datetime
|
||||
from hashlib import sha256
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from reflector.db.rooms import Room, VideoPlatform
|
||||
from reflector.settings import settings
|
||||
|
||||
from ..base import MeetingData, VideoPlatformClient
|
||||
|
||||
|
||||
class WherebyClient(VideoPlatformClient):
|
||||
PLATFORM_NAME = VideoPlatform.WHEREBY
|
||||
|
||||
def __init__(self, config):
|
||||
super().__init__(config)
|
||||
self.headers = {
|
||||
"Content-Type": "application/json; charset=utf-8",
|
||||
"Authorization": f"Bearer {self.config.api_key}",
|
||||
}
|
||||
self.timeout = 10
|
||||
|
||||
async def create_meeting(
|
||||
self, room_name_prefix: str, end_date: datetime, room: Room
|
||||
) -> MeetingData:
|
||||
data = {
|
||||
"isLocked": room.is_locked,
|
||||
"roomNamePrefix": room_name_prefix,
|
||||
"roomNamePattern": "uuid",
|
||||
"roomMode": room.room_mode,
|
||||
"endDate": end_date.isoformat(),
|
||||
"recording": {
|
||||
"type": room.recording_type,
|
||||
"destination": {
|
||||
"provider": "s3",
|
||||
"bucket": settings.RECORDING_STORAGE_AWS_BUCKET_NAME,
|
||||
"accessKeyId": self.config.aws_access_key_id,
|
||||
"accessKeySecret": self.config.aws_access_key_secret,
|
||||
"fileFormat": "mp4",
|
||||
},
|
||||
"startTrigger": room.recording_trigger,
|
||||
},
|
||||
"fields": ["hostRoomUrl"],
|
||||
}
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.post(
|
||||
f"{self.config.api_url}/meetings",
|
||||
headers=self.headers,
|
||||
json=data,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
response.raise_for_status()
|
||||
meeting_data = response.json()
|
||||
|
||||
return MeetingData(
|
||||
meeting_id=meeting_data["meetingId"],
|
||||
room_name=meeting_data["roomName"],
|
||||
room_url=meeting_data["roomUrl"],
|
||||
host_room_url=meeting_data["hostRoomUrl"],
|
||||
platform=self.PLATFORM_NAME,
|
||||
extra_data={
|
||||
"startDate": meeting_data["startDate"],
|
||||
"endDate": meeting_data["endDate"],
|
||||
"recording": meeting_data.get("recording", {}),
|
||||
},
|
||||
)
|
||||
|
||||
async def get_room_sessions(self, room_name: str) -> Dict[str, Any]:
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(
|
||||
f"{self.config.api_url}/insights/room-sessions?roomName={room_name}",
|
||||
headers=self.headers,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
async def delete_room(self, room_name: str) -> bool:
|
||||
return True
|
||||
|
||||
async def upload_logo(self, room_name: str, logo_path: str) -> bool:
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
with open(logo_path, "rb") as f:
|
||||
response = await client.put(
|
||||
f"{self.config.api_url}/rooms{room_name}/theme/logo",
|
||||
headers={
|
||||
"Authorization": f"Bearer {self.config.api_key}",
|
||||
},
|
||||
timeout=self.timeout,
|
||||
files={"image": f},
|
||||
)
|
||||
response.raise_for_status()
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def verify_webhook_signature(
|
||||
self, body: bytes, signature: str, timestamp: Optional[str] = None
|
||||
) -> bool:
|
||||
if not signature or not self.config.webhook_secret:
|
||||
return False
|
||||
|
||||
try:
|
||||
expected = hmac.new(
|
||||
self.config.webhook_secret.encode(), body, sha256
|
||||
).hexdigest()
|
||||
return hmac.compare_digest(expected, signature)
|
||||
except Exception:
|
||||
return False
|
||||
@@ -68,7 +68,8 @@ async def whereby_webhook(event: WherebyWebhookEvent, request: Request):
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
if event.type in ["room.client.joined", "room.client.left"]:
|
||||
update_data = {"num_clients": event.data["numClients"]}
|
||||
await meetings_controller.update_meeting(meeting.id, **update_data)
|
||||
await meetings_controller.update_meeting(
|
||||
meeting.id, num_clients=event.data["numClients"]
|
||||
)
|
||||
|
||||
return {"status": "ok"}
|
||||
4
server/reflector/video_platforms/whereby/tasks.py
Normal file
4
server/reflector/video_platforms/whereby/tasks.py
Normal file
@@ -0,0 +1,4 @@
|
||||
"""Whereby-specific worker tasks."""
|
||||
|
||||
# Placeholder for Whereby-specific background tasks
|
||||
# This can be extended with Whereby-specific processing tasks in the future
|
||||
@@ -1,235 +0,0 @@
|
||||
"""Daily.co webhook handler endpoint."""
|
||||
|
||||
import json
|
||||
from typing import Any, Dict, Literal
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from reflector.db.meetings import meetings_controller
|
||||
from reflector.logger import logger
|
||||
from reflector.settings import settings
|
||||
from reflector.video_platforms.factory import create_platform_client
|
||||
from reflector.worker.process import process_multitrack_recording
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
class DailyTrack(BaseModel):
|
||||
"""Daily.co recording track (audio or video file)."""
|
||||
|
||||
type: Literal["audio", "video"]
|
||||
s3Key: str
|
||||
size: int
|
||||
|
||||
|
||||
class DailyWebhookEvent(BaseModel):
|
||||
"""Daily webhook event structure."""
|
||||
|
||||
version: str
|
||||
type: str
|
||||
id: str
|
||||
payload: Dict[str, Any]
|
||||
event_ts: float
|
||||
|
||||
|
||||
def _extract_room_name(event: DailyWebhookEvent) -> str | None:
|
||||
"""Extract room name from Daily event payload.
|
||||
|
||||
Daily.co API inconsistency:
|
||||
- participant.* events use "room" field
|
||||
- recording.* events use "room_name" field
|
||||
"""
|
||||
return event.payload.get("room_name") or event.payload.get("room")
|
||||
|
||||
|
||||
@router.post("/webhook")
|
||||
async def webhook(request: Request):
|
||||
"""Handle Daily webhook events.
|
||||
|
||||
Daily.co circuit-breaker: After 3+ failed responses (4xx/5xx), webhook
|
||||
state→FAILED, stops sending events. Reset: scripts/recreate_daily_webhook.py
|
||||
"""
|
||||
body = await request.body()
|
||||
signature = request.headers.get("X-Webhook-Signature", "")
|
||||
timestamp = request.headers.get("X-Webhook-Timestamp", "")
|
||||
|
||||
client = create_platform_client("daily")
|
||||
|
||||
# TEMPORARY: Bypass signature check for testing
|
||||
# TODO: Remove this after testing is complete
|
||||
BYPASS_FOR_TESTING = True
|
||||
if not BYPASS_FOR_TESTING:
|
||||
if not client.verify_webhook_signature(body, signature, timestamp):
|
||||
logger.warning(
|
||||
"Invalid webhook signature",
|
||||
signature=signature,
|
||||
timestamp=timestamp,
|
||||
has_body=bool(body),
|
||||
)
|
||||
raise HTTPException(status_code=401, detail="Invalid webhook signature")
|
||||
|
||||
# Parse the JSON body
|
||||
try:
|
||||
body_json = json.loads(body)
|
||||
except json.JSONDecodeError:
|
||||
raise HTTPException(status_code=422, detail="Invalid JSON")
|
||||
|
||||
# Handle Daily's test event during webhook creation
|
||||
if body_json.get("test") == "test":
|
||||
logger.info("Received Daily webhook test event")
|
||||
return {"status": "ok"}
|
||||
|
||||
# Parse as actual event
|
||||
try:
|
||||
event = DailyWebhookEvent(**body_json)
|
||||
except Exception as e:
|
||||
logger.error("Failed to parse webhook event", error=str(e), body=body.decode())
|
||||
raise HTTPException(status_code=422, detail="Invalid event format")
|
||||
|
||||
# Handle participant events
|
||||
if event.type == "participant.joined":
|
||||
await _handle_participant_joined(event)
|
||||
elif event.type == "participant.left":
|
||||
await _handle_participant_left(event)
|
||||
elif event.type == "recording.started":
|
||||
await _handle_recording_started(event)
|
||||
elif event.type == "recording.ready-to-download":
|
||||
await _handle_recording_ready(event)
|
||||
elif event.type == "recording.error":
|
||||
await _handle_recording_error(event)
|
||||
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
async def _handle_participant_joined(event: DailyWebhookEvent):
|
||||
"""Handle participant joined event."""
|
||||
room_name = _extract_room_name(event)
|
||||
if not room_name:
|
||||
logger.warning("participant.joined: no room in payload", payload=event.payload)
|
||||
return
|
||||
|
||||
meeting = await meetings_controller.get_by_room_name(room_name)
|
||||
if meeting:
|
||||
await meetings_controller.increment_num_clients(meeting.id)
|
||||
logger.info(
|
||||
"Participant joined",
|
||||
meeting_id=meeting.id,
|
||||
room_name=room_name,
|
||||
recording_type=meeting.recording_type,
|
||||
recording_trigger=meeting.recording_trigger,
|
||||
)
|
||||
else:
|
||||
logger.warning("participant.joined: meeting not found", room_name=room_name)
|
||||
|
||||
|
||||
async def _handle_participant_left(event: DailyWebhookEvent):
|
||||
"""Handle participant left event."""
|
||||
room_name = _extract_room_name(event)
|
||||
if not room_name:
|
||||
return
|
||||
|
||||
meeting = await meetings_controller.get_by_room_name(room_name)
|
||||
if meeting:
|
||||
await meetings_controller.decrement_num_clients(meeting.id)
|
||||
|
||||
|
||||
async def _handle_recording_started(event: DailyWebhookEvent):
|
||||
"""Handle recording started event."""
|
||||
room_name = _extract_room_name(event)
|
||||
if not room_name:
|
||||
logger.warning(
|
||||
"recording.started: no room_name in payload", payload=event.payload
|
||||
)
|
||||
return
|
||||
|
||||
meeting = await meetings_controller.get_by_room_name(room_name)
|
||||
if meeting:
|
||||
logger.info(
|
||||
"Recording started",
|
||||
meeting_id=meeting.id,
|
||||
room_name=room_name,
|
||||
recording_id=event.payload.get("recording_id"),
|
||||
platform="daily",
|
||||
)
|
||||
else:
|
||||
logger.warning("recording.started: meeting not found", room_name=room_name)
|
||||
|
||||
|
||||
async def _handle_recording_ready(event: DailyWebhookEvent):
|
||||
"""Handle recording ready for download event.
|
||||
|
||||
Daily.co webhook payload for raw-tracks recordings:
|
||||
{
|
||||
"recording_id": "...",
|
||||
"room_name": "test2-20251009192341",
|
||||
"tracks": [
|
||||
{"type": "audio", "s3Key": "monadical/test2-.../uuid-cam-audio-123.webm", "size": 400000},
|
||||
{"type": "video", "s3Key": "monadical/test2-.../uuid-cam-video-456.webm", "size": 30000000}
|
||||
]
|
||||
}
|
||||
"""
|
||||
room_name = _extract_room_name(event)
|
||||
recording_id = event.payload.get("recording_id")
|
||||
tracks_raw = event.payload.get("tracks", [])
|
||||
|
||||
if not room_name or not tracks_raw:
|
||||
logger.warning(
|
||||
"recording.ready-to-download: missing room_name or tracks",
|
||||
room_name=room_name,
|
||||
has_tracks=bool(tracks_raw),
|
||||
payload=event.payload,
|
||||
)
|
||||
return
|
||||
|
||||
# Validate tracks structure
|
||||
try:
|
||||
tracks = [DailyTrack(**t) for t in tracks_raw]
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"recording.ready-to-download: invalid tracks structure",
|
||||
error=str(e),
|
||||
tracks=tracks_raw,
|
||||
)
|
||||
return
|
||||
|
||||
logger.info(
|
||||
"Recording ready for download",
|
||||
room_name=room_name,
|
||||
recording_id=recording_id,
|
||||
num_tracks=len(tracks),
|
||||
platform="daily",
|
||||
)
|
||||
|
||||
bucket_name = settings.AWS_DAILY_S3_BUCKET
|
||||
if not bucket_name:
|
||||
logger.error(
|
||||
"AWS_DAILY_S3_BUCKET not configured; cannot process Daily recording"
|
||||
)
|
||||
return
|
||||
|
||||
track_keys = [t.s3Key for t in tracks if t.type == "audio"]
|
||||
|
||||
process_multitrack_recording.delay(
|
||||
bucket_name=bucket_name,
|
||||
room_name=room_name,
|
||||
recording_id=recording_id,
|
||||
track_keys=track_keys,
|
||||
)
|
||||
|
||||
|
||||
async def _handle_recording_error(event: DailyWebhookEvent):
|
||||
"""Handle recording error event."""
|
||||
room_name = _extract_room_name(event)
|
||||
error = event.payload.get("error", "Unknown error")
|
||||
|
||||
if room_name:
|
||||
meeting = await meetings_controller.get_by_room_name(room_name)
|
||||
if meeting:
|
||||
logger.error(
|
||||
"Recording error",
|
||||
meeting_id=meeting.id,
|
||||
room_name=room_name,
|
||||
error=error,
|
||||
platform="daily",
|
||||
)
|
||||
126
server/reflector/views/jibri_webhook.py
Normal file
126
server/reflector/views/jibri_webhook.py
Normal file
@@ -0,0 +1,126 @@
|
||||
from pathlib import Path
|
||||
from typing import Annotated, Any, Dict, Optional
|
||||
|
||||
import structlog
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from pydantic import BaseModel
|
||||
|
||||
import reflector.auth as auth
|
||||
from reflector.db.transcripts import SourceKind, transcripts_controller
|
||||
from reflector.jibri_events import JitsiEventParser
|
||||
from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
|
||||
from reflector.settings import settings
|
||||
|
||||
logger = structlog.get_logger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api/v1/jibri", tags=["jibri"])
|
||||
|
||||
|
||||
class RecordingReadyRequest(BaseModel):
|
||||
session_id: str
|
||||
path: str # Relative path from recordings directory
|
||||
meeting_url: str
|
||||
|
||||
|
||||
@router.post("/recording-ready")
|
||||
async def handle_recording_ready(
|
||||
request: RecordingReadyRequest,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> Dict[str, Any]:
|
||||
user_id = user["sub"] if user else None
|
||||
|
||||
recordings_base = Path(settings.JIBRI_RECORDINGS_PATH or "/recordings")
|
||||
recording_path = recordings_base / request.path
|
||||
|
||||
if not recording_path.exists():
|
||||
raise HTTPException(
|
||||
status_code=404, detail=f"Recording path not found: {request.path}"
|
||||
)
|
||||
|
||||
recording_file = recording_path / "recording.mp4"
|
||||
events_file = recording_path / "events.jsonl"
|
||||
|
||||
if not recording_file.exists():
|
||||
raise HTTPException(status_code=404, detail="Recording file not found")
|
||||
|
||||
# Parse events if available
|
||||
metadata = {}
|
||||
participant_count = 0
|
||||
|
||||
if events_file.exists():
|
||||
parser = JitsiEventParser()
|
||||
metadata = parser.parse_events_file(str(recording_path))
|
||||
participant_count = len(metadata.get("participants", []))
|
||||
logger.info(
|
||||
"Parsed Jibri events",
|
||||
session_id=request.session_id,
|
||||
event_count=metadata.get("event_count", 0),
|
||||
participant_count=participant_count,
|
||||
)
|
||||
else:
|
||||
logger.warning("No events file found", session_id=request.session_id)
|
||||
metadata = {
|
||||
"room": {"meeting_url": request.meeting_url, "name": request.session_id},
|
||||
"participants": [],
|
||||
"speaker_stats": {},
|
||||
"event_count": 0,
|
||||
}
|
||||
|
||||
# Create transcript using controller
|
||||
title = f"Meeting: {metadata.get('room', {}).get('name', request.session_id)}"
|
||||
transcript = await transcripts_controller.add(
|
||||
name=title,
|
||||
source_kind=SourceKind.FILE,
|
||||
source_language="en",
|
||||
target_language="en",
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
# Store Jitsi data in appropriate fields
|
||||
update_data = {}
|
||||
|
||||
# Store participants if available
|
||||
if metadata.get("participants"):
|
||||
update_data["participants"] = metadata["participants"]
|
||||
|
||||
# Store events data (room info, speaker stats, etc.)
|
||||
update_data["events"] = {
|
||||
"jitsi_metadata": metadata,
|
||||
"session_id": request.session_id,
|
||||
"recording_path": str(recording_path),
|
||||
"meeting_url": request.meeting_url,
|
||||
}
|
||||
|
||||
if update_data:
|
||||
await transcripts_controller.update(transcript, update_data)
|
||||
|
||||
# Copy recording file to transcript data path
|
||||
# The pipeline expects the file to be in the transcript's data path
|
||||
upload_file = transcript.data_path / "upload.mp4"
|
||||
upload_file.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Create symlink or copy the file
|
||||
import shutil
|
||||
|
||||
shutil.copy2(recording_file, upload_file)
|
||||
|
||||
# Update status to uploaded
|
||||
await transcripts_controller.update(transcript, {"status": "uploaded"})
|
||||
|
||||
# Trigger processing pipeline
|
||||
task_pipeline_file_process.delay(transcript_id=transcript.id)
|
||||
|
||||
logger.info(
|
||||
"Jibri recording ready for processing",
|
||||
transcript_id=transcript.id,
|
||||
session_id=request.session_id,
|
||||
participant_count=participant_count,
|
||||
)
|
||||
|
||||
return {
|
||||
"status": "accepted",
|
||||
"transcript_id": transcript.id,
|
||||
"session_id": request.session_id,
|
||||
"events_found": events_file.exists(),
|
||||
"participant_count": participant_count,
|
||||
}
|
||||
@@ -10,7 +10,6 @@ from reflector.db.meetings import (
|
||||
meeting_consent_controller,
|
||||
meetings_controller,
|
||||
)
|
||||
from reflector.db.rooms import rooms_controller
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@@ -42,34 +41,3 @@ async def meeting_audio_consent(
|
||||
updated_consent = await meeting_consent_controller.upsert(consent)
|
||||
|
||||
return {"status": "success", "consent_id": updated_consent.id}
|
||||
|
||||
|
||||
@router.patch("/meetings/{meeting_id}/deactivate")
|
||||
async def meeting_deactivate(
|
||||
meeting_id: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
meeting = await meetings_controller.get_by_id(meeting_id)
|
||||
if not meeting:
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
if not meeting.is_active:
|
||||
return {"status": "success", "meeting_id": meeting_id}
|
||||
|
||||
# Only room owner or meeting creator can deactivate
|
||||
room = await rooms_controller.get_by_id(meeting.room_id)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
if user_id != room.user_id and user_id != meeting.user_id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Only the room owner can deactivate meetings"
|
||||
)
|
||||
|
||||
await meetings_controller.update_meeting(meeting_id, is_active=False)
|
||||
|
||||
return {"status": "success", "meeting_id": meeting_id}
|
||||
|
||||
@@ -1,31 +1,35 @@
|
||||
import logging
|
||||
import sqlite3
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from enum import Enum
|
||||
from typing import Annotated, Any, Literal, Optional
|
||||
from typing import Annotated, Literal, Optional
|
||||
|
||||
import asyncpg.exceptions
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi_pagination import Page
|
||||
from fastapi_pagination.ext.databases import apaginate
|
||||
from pydantic import BaseModel
|
||||
from redis.exceptions import LockError
|
||||
|
||||
import reflector.auth as auth
|
||||
from reflector.db import get_database
|
||||
from reflector.db.calendar_events import calendar_events_controller
|
||||
from reflector.db.meetings import meetings_controller
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.redis_cache import RedisAsyncLock
|
||||
from reflector.services.ics_sync import ics_sync_service
|
||||
from reflector.db.rooms import VideoPlatform, rooms_controller
|
||||
from reflector.settings import settings
|
||||
from reflector.video_platforms.base import Platform
|
||||
from reflector.video_platforms.factory import (
|
||||
create_platform_client,
|
||||
get_platform_for_room,
|
||||
)
|
||||
from reflector.worker.webhook import test_webhook
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def parse_datetime_with_timezone(iso_string: str) -> datetime:
|
||||
dt = datetime.fromisoformat(iso_string)
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return dt
|
||||
|
||||
|
||||
class Room(BaseModel):
|
||||
id: str
|
||||
@@ -40,12 +44,7 @@ class Room(BaseModel):
|
||||
recording_type: str
|
||||
recording_trigger: str
|
||||
is_shared: bool
|
||||
ics_url: Optional[str] = None
|
||||
ics_fetch_interval: int = 300
|
||||
ics_enabled: bool = False
|
||||
ics_last_sync: Optional[datetime] = None
|
||||
ics_last_etag: Optional[str] = None
|
||||
platform: Platform = "whereby"
|
||||
platform: VideoPlatform = VideoPlatform.WHEREBY
|
||||
|
||||
|
||||
class RoomDetails(Room):
|
||||
@@ -57,23 +56,10 @@ class Meeting(BaseModel):
|
||||
id: str
|
||||
room_name: str
|
||||
room_url: str
|
||||
# TODO it's not always present, | None
|
||||
host_room_url: str
|
||||
start_date: datetime
|
||||
end_date: datetime
|
||||
user_id: str | None = None
|
||||
room_id: str | None = None
|
||||
is_locked: bool = False
|
||||
room_mode: Literal["normal", "group"] = "normal"
|
||||
recording_type: Literal["none", "local", "cloud"] = "cloud"
|
||||
recording_trigger: Literal[
|
||||
"none", "prompt", "automatic", "automatic-2nd-participant"
|
||||
] = "automatic-2nd-participant"
|
||||
num_clients: int = 0
|
||||
is_active: bool = True
|
||||
calendar_event_id: str | None = None
|
||||
calendar_metadata: dict[str, Any] | None = None
|
||||
platform: Platform = "whereby"
|
||||
|
||||
|
||||
class CreateRoom(BaseModel):
|
||||
@@ -88,32 +74,22 @@ class CreateRoom(BaseModel):
|
||||
is_shared: bool
|
||||
webhook_url: str
|
||||
webhook_secret: str
|
||||
ics_url: Optional[str] = None
|
||||
ics_fetch_interval: int = 300
|
||||
ics_enabled: bool = False
|
||||
platform: Optional[Platform] = None
|
||||
platform: VideoPlatform
|
||||
|
||||
|
||||
class UpdateRoom(BaseModel):
|
||||
name: Optional[str] = None
|
||||
zulip_auto_post: Optional[bool] = None
|
||||
zulip_stream: Optional[str] = None
|
||||
zulip_topic: Optional[str] = None
|
||||
is_locked: Optional[bool] = None
|
||||
room_mode: Optional[str] = None
|
||||
recording_type: Optional[str] = None
|
||||
recording_trigger: Optional[str] = None
|
||||
is_shared: Optional[bool] = None
|
||||
webhook_url: Optional[str] = None
|
||||
webhook_secret: Optional[str] = None
|
||||
ics_url: Optional[str] = None
|
||||
ics_fetch_interval: Optional[int] = None
|
||||
ics_enabled: Optional[bool] = None
|
||||
platform: Optional[Platform] = None
|
||||
|
||||
|
||||
class CreateRoomMeeting(BaseModel):
|
||||
allow_duplicated: Optional[bool] = False
|
||||
name: str
|
||||
zulip_auto_post: bool
|
||||
zulip_stream: str
|
||||
zulip_topic: str
|
||||
is_locked: bool
|
||||
room_mode: str
|
||||
recording_type: str
|
||||
recording_trigger: str
|
||||
is_shared: bool
|
||||
webhook_url: str
|
||||
webhook_secret: str
|
||||
platform: VideoPlatform
|
||||
|
||||
|
||||
class DeletionStatus(BaseModel):
|
||||
@@ -128,59 +104,6 @@ class WebhookTestResult(BaseModel):
|
||||
response_preview: str | None = None
|
||||
|
||||
|
||||
class ICSStatus(BaseModel):
|
||||
status: Literal["enabled", "disabled"]
|
||||
last_sync: Optional[datetime] = None
|
||||
next_sync: Optional[datetime] = None
|
||||
last_etag: Optional[str] = None
|
||||
events_count: int = 0
|
||||
|
||||
|
||||
class SyncStatus(str, Enum):
|
||||
success = "success"
|
||||
unchanged = "unchanged"
|
||||
error = "error"
|
||||
skipped = "skipped"
|
||||
|
||||
|
||||
class ICSSyncResult(BaseModel):
|
||||
status: SyncStatus
|
||||
hash: Optional[str] = None
|
||||
events_found: int = 0
|
||||
total_events: int = 0
|
||||
events_created: int = 0
|
||||
events_updated: int = 0
|
||||
events_deleted: int = 0
|
||||
error: Optional[str] = None
|
||||
reason: Optional[str] = None
|
||||
|
||||
|
||||
class CalendarEventResponse(BaseModel):
|
||||
id: str
|
||||
room_id: str
|
||||
ics_uid: str
|
||||
title: Optional[str] = None
|
||||
description: Optional[str] = None
|
||||
start_time: datetime
|
||||
end_time: datetime
|
||||
attendees: Optional[list[dict]] = None
|
||||
location: Optional[str] = None
|
||||
last_synced: datetime
|
||||
created_at: datetime
|
||||
updated_at: datetime
|
||||
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def parse_datetime_with_timezone(iso_string: str) -> datetime:
|
||||
"""Parse ISO datetime string and ensure timezone awareness (defaults to UTC if naive)."""
|
||||
dt = datetime.fromisoformat(iso_string)
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return dt
|
||||
|
||||
|
||||
@router.get("/rooms", response_model=Page[RoomDetails])
|
||||
async def rooms_list(
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
@@ -190,18 +113,13 @@ async def rooms_list(
|
||||
|
||||
user_id = user["sub"] if user else None
|
||||
|
||||
paginated = await apaginate(
|
||||
return await apaginate(
|
||||
get_database(),
|
||||
await rooms_controller.get_all(
|
||||
user_id=user_id, order_by="-created_at", return_query=True
|
||||
),
|
||||
)
|
||||
|
||||
for room in paginated.items:
|
||||
room.platform = get_platform_for_room(room.id, room.platform)
|
||||
|
||||
return paginated
|
||||
|
||||
|
||||
@router.get("/rooms/{room_id}", response_model=RoomDetails)
|
||||
async def rooms_get(
|
||||
@@ -212,41 +130,15 @@ async def rooms_get(
|
||||
room = await rooms_controller.get_by_id_for_http(room_id, user_id=user_id)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
if not room.is_shared and (user_id is None or room.user_id != user_id):
|
||||
raise HTTPException(status_code=403, detail="Room access denied")
|
||||
room.platform = get_platform_for_room(room.id, room.platform)
|
||||
return room
|
||||
|
||||
|
||||
@router.get("/rooms/name/{room_name}", response_model=RoomDetails)
|
||||
async def rooms_get_by_name(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
room_dict = room.__dict__.copy()
|
||||
if user_id == room.user_id:
|
||||
room_dict["webhook_url"] = getattr(room, "webhook_url", None)
|
||||
room_dict["webhook_secret"] = getattr(room, "webhook_secret", None)
|
||||
else:
|
||||
room_dict["webhook_url"] = None
|
||||
room_dict["webhook_secret"] = None
|
||||
|
||||
room_dict["platform"] = get_platform_for_room(room.id, room.platform)
|
||||
|
||||
return RoomDetails(**room_dict)
|
||||
|
||||
|
||||
@router.post("/rooms", response_model=Room)
|
||||
async def rooms_create(
|
||||
room: CreateRoom,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
|
||||
return await rooms_controller.add(
|
||||
name=room.name,
|
||||
@@ -261,9 +153,6 @@ async def rooms_create(
|
||||
is_shared=room.is_shared,
|
||||
webhook_url=room.webhook_url,
|
||||
webhook_secret=room.webhook_secret,
|
||||
ics_url=room.ics_url,
|
||||
ics_fetch_interval=room.ics_fetch_interval,
|
||||
ics_enabled=room.ics_enabled,
|
||||
platform=room.platform,
|
||||
)
|
||||
|
||||
@@ -272,31 +161,26 @@ async def rooms_create(
|
||||
async def rooms_update(
|
||||
room_id: str,
|
||||
info: UpdateRoom,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_id_for_http(room_id, user_id=user_id)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
if room.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
values = info.dict(exclude_unset=True)
|
||||
await rooms_controller.update(room, values)
|
||||
room.platform = get_platform_for_room(room.id, room.platform)
|
||||
return room
|
||||
|
||||
|
||||
@router.delete("/rooms/{room_id}", response_model=DeletionStatus)
|
||||
async def rooms_delete(
|
||||
room_id: str,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
room = await rooms_controller.get_by_id(room_id)
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_id(room_id, user_id=user_id)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
if room.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
await rooms_controller.remove_by_id(room.id, user_id=user_id)
|
||||
return DeletionStatus(status="ok")
|
||||
|
||||
@@ -304,7 +188,6 @@ async def rooms_delete(
|
||||
@router.post("/rooms/{room_name}/meeting", response_model=Meeting)
|
||||
async def rooms_create_meeting(
|
||||
room_name: str,
|
||||
info: CreateRoomMeeting,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
@@ -312,63 +195,59 @@ async def rooms_create_meeting(
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
try:
|
||||
async with RedisAsyncLock(
|
||||
f"create_meeting:{room_name}",
|
||||
timeout=30,
|
||||
extend_interval=10,
|
||||
blocking_timeout=5.0,
|
||||
) as lock:
|
||||
current_time = datetime.now(timezone.utc)
|
||||
current_time = datetime.now(timezone.utc)
|
||||
meeting = await meetings_controller.get_active(room=room, current_time=current_time)
|
||||
|
||||
meeting = None
|
||||
if not info.allow_duplicated:
|
||||
meeting = await meetings_controller.get_active(
|
||||
room=room, current_time=current_time
|
||||
)
|
||||
if meeting is None:
|
||||
end_date = current_time + timedelta(hours=8)
|
||||
|
||||
platform = room.platform
|
||||
client = create_platform_client(platform)
|
||||
|
||||
platform_meeting = await client.create_meeting("", end_date=end_date, room=room)
|
||||
await client.upload_logo(platform_meeting.room_name, "./images/logo.png")
|
||||
|
||||
meeting_data = {
|
||||
"meeting_id": platform_meeting.meeting_id,
|
||||
"room_name": platform_meeting.room_name,
|
||||
"room_url": platform_meeting.room_url,
|
||||
"host_room_url": platform_meeting.host_room_url,
|
||||
"start_date": current_time,
|
||||
"end_date": end_date,
|
||||
}
|
||||
try:
|
||||
meeting = await meetings_controller.create(
|
||||
id=meeting_data["meeting_id"],
|
||||
room_name=meeting_data["room_name"],
|
||||
room_url=meeting_data["room_url"],
|
||||
host_room_url=meeting_data["host_room_url"],
|
||||
start_date=meeting_data["start_date"],
|
||||
end_date=meeting_data["end_date"],
|
||||
user_id=user_id,
|
||||
room=room,
|
||||
)
|
||||
except (asyncpg.exceptions.UniqueViolationError, sqlite3.IntegrityError):
|
||||
logger.info(
|
||||
"Race condition detected for room %s - fetching existing meeting",
|
||||
room.name,
|
||||
)
|
||||
logger.warning(
|
||||
"Platform meeting %s was created but not used (resource leak) for room %s",
|
||||
meeting_data["meeting_id"],
|
||||
room.name,
|
||||
)
|
||||
meeting = await meetings_controller.get_active(
|
||||
room=room, current_time=current_time
|
||||
)
|
||||
if meeting is None:
|
||||
end_date = current_time + timedelta(hours=8)
|
||||
|
||||
# Determine which platform to use
|
||||
platform = get_platform_for_room(room.id, room.platform)
|
||||
client = create_platform_client(platform)
|
||||
|
||||
# Create meeting via platform abstraction
|
||||
meeting_data = await client.create_meeting(
|
||||
room.name, end_date=end_date, room=room
|
||||
logger.error(
|
||||
"Meeting disappeared after race condition for room %s",
|
||||
room.name,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
# Upload logo if supported by platform
|
||||
await client.upload_logo(meeting_data.room_name, "./images/logo.png")
|
||||
|
||||
meeting = await meetings_controller.create(
|
||||
id=meeting_data.meeting_id,
|
||||
room_name=meeting_data.room_name,
|
||||
room_url=meeting_data.room_url,
|
||||
host_room_url=meeting_data.host_room_url,
|
||||
start_date=current_time,
|
||||
end_date=end_date,
|
||||
room=room,
|
||||
platform=platform,
|
||||
raise HTTPException(
|
||||
status_code=503, detail="Unable to join meeting - please try again"
|
||||
)
|
||||
except LockError:
|
||||
logger.warning("Failed to acquire lock for room %s within timeout", room_name)
|
||||
raise HTTPException(
|
||||
status_code=503, detail="Meeting creation in progress, please try again"
|
||||
)
|
||||
|
||||
meeting.platform = get_platform_for_room(room.id, room.platform)
|
||||
|
||||
if meeting.platform == "daily" and room.recording_trigger != "none":
|
||||
client = create_platform_client(meeting.platform)
|
||||
token = await client.create_meeting_token(
|
||||
meeting.room_name, enable_recording=True
|
||||
)
|
||||
meeting = meeting.model_copy()
|
||||
meeting.room_url += f"?t={token}"
|
||||
if meeting.host_room_url:
|
||||
meeting.host_room_url += f"?t={token}"
|
||||
|
||||
if user_id != room.user_id:
|
||||
meeting.host_room_url = ""
|
||||
@@ -379,224 +258,18 @@ async def rooms_create_meeting(
|
||||
@router.post("/rooms/{room_id}/webhook/test", response_model=WebhookTestResult)
|
||||
async def rooms_test_webhook(
|
||||
room_id: str,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
"""Test webhook configuration by sending a sample payload."""
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
|
||||
room = await rooms_controller.get_by_id(room_id)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
if room.user_id != user_id:
|
||||
if user_id and room.user_id != user_id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Not authorized to test this room's webhook"
|
||||
)
|
||||
|
||||
result = await test_webhook(room_id)
|
||||
return WebhookTestResult(**result)
|
||||
|
||||
|
||||
@router.post("/rooms/{room_name}/ics/sync", response_model=ICSSyncResult)
|
||||
async def rooms_sync_ics(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
if user_id != room.user_id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Only room owner can trigger ICS sync"
|
||||
)
|
||||
|
||||
if not room.ics_enabled or not room.ics_url:
|
||||
raise HTTPException(status_code=400, detail="ICS not configured for this room")
|
||||
|
||||
result = await ics_sync_service.sync_room_calendar(room)
|
||||
|
||||
if result["status"] == "error":
|
||||
raise HTTPException(
|
||||
status_code=500, detail=result.get("error", "Unknown error")
|
||||
)
|
||||
|
||||
return ICSSyncResult(**result)
|
||||
|
||||
|
||||
@router.get("/rooms/{room_name}/ics/status", response_model=ICSStatus)
|
||||
async def rooms_ics_status(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
if user_id != room.user_id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Only room owner can view ICS status"
|
||||
)
|
||||
|
||||
next_sync = None
|
||||
if room.ics_enabled and room.ics_last_sync:
|
||||
next_sync = room.ics_last_sync + timedelta(seconds=room.ics_fetch_interval)
|
||||
|
||||
events = await calendar_events_controller.get_by_room(
|
||||
room.id, include_deleted=False
|
||||
)
|
||||
|
||||
return ICSStatus(
|
||||
status="enabled" if room.ics_enabled else "disabled",
|
||||
last_sync=room.ics_last_sync,
|
||||
next_sync=next_sync,
|
||||
last_etag=room.ics_last_etag,
|
||||
events_count=len(events),
|
||||
)
|
||||
|
||||
|
||||
@router.get("/rooms/{room_name}/meetings", response_model=list[CalendarEventResponse])
|
||||
async def rooms_list_meetings(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
events = await calendar_events_controller.get_by_room(
|
||||
room.id, include_deleted=False
|
||||
)
|
||||
|
||||
if user_id != room.user_id:
|
||||
for event in events:
|
||||
event.description = None
|
||||
event.attendees = None
|
||||
|
||||
return events
|
||||
|
||||
|
||||
@router.get(
|
||||
"/rooms/{room_name}/meetings/upcoming", response_model=list[CalendarEventResponse]
|
||||
)
|
||||
async def rooms_list_upcoming_meetings(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
minutes_ahead: int = 120,
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
events = await calendar_events_controller.get_upcoming(
|
||||
room.id, minutes_ahead=minutes_ahead
|
||||
)
|
||||
|
||||
if user_id != room.user_id:
|
||||
for event in events:
|
||||
event.description = None
|
||||
event.attendees = None
|
||||
|
||||
return events
|
||||
|
||||
|
||||
@router.get("/rooms/{room_name}/meetings/active", response_model=list[Meeting])
|
||||
async def rooms_list_active_meetings(
|
||||
room_name: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
current_time = datetime.now(timezone.utc)
|
||||
meetings = await meetings_controller.get_all_active_for_room(
|
||||
room=room, current_time=current_time
|
||||
)
|
||||
|
||||
effective_platform = get_platform_for_room(room.id, room.platform)
|
||||
for meeting in meetings:
|
||||
meeting.platform = effective_platform
|
||||
|
||||
if user_id != room.user_id:
|
||||
for meeting in meetings:
|
||||
meeting.host_room_url = ""
|
||||
|
||||
return meetings
|
||||
|
||||
|
||||
@router.get("/rooms/{room_name}/meetings/{meeting_id}", response_model=Meeting)
|
||||
async def rooms_get_meeting(
|
||||
room_name: str,
|
||||
meeting_id: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
"""Get a single meeting by ID within a specific room."""
|
||||
user_id = user["sub"] if user else None
|
||||
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
meeting = await meetings_controller.get_by_id(meeting_id)
|
||||
if not meeting:
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
if meeting.room_id != room.id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Meeting does not belong to this room"
|
||||
)
|
||||
|
||||
meeting.platform = get_platform_for_room(room.id, room.platform)
|
||||
|
||||
if user_id != room.user_id and not room.is_shared:
|
||||
meeting.host_room_url = ""
|
||||
|
||||
return meeting
|
||||
|
||||
|
||||
@router.post("/rooms/{room_name}/meetings/{meeting_id}/join", response_model=Meeting)
|
||||
async def rooms_join_meeting(
|
||||
room_name: str,
|
||||
meeting_id: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
room = await rooms_controller.get_by_name(room_name)
|
||||
|
||||
if not room:
|
||||
raise HTTPException(status_code=404, detail="Room not found")
|
||||
|
||||
meeting = await meetings_controller.get_by_id(meeting_id)
|
||||
|
||||
if not meeting:
|
||||
raise HTTPException(status_code=404, detail="Meeting not found")
|
||||
|
||||
if meeting.room_id != room.id:
|
||||
raise HTTPException(
|
||||
status_code=403, detail="Meeting does not belong to this room"
|
||||
)
|
||||
|
||||
if not meeting.is_active:
|
||||
raise HTTPException(status_code=400, detail="Meeting is not active")
|
||||
|
||||
current_time = datetime.now(timezone.utc)
|
||||
if meeting.end_date <= current_time:
|
||||
raise HTTPException(status_code=400, detail="Meeting has ended")
|
||||
|
||||
meeting.platform = get_platform_for_room(room.id, room.platform)
|
||||
|
||||
if user_id != room.user_id:
|
||||
meeting.host_room_url = ""
|
||||
|
||||
return meeting
|
||||
|
||||
@@ -9,6 +9,8 @@ from pydantic import BaseModel, Field, constr, field_serializer
|
||||
|
||||
import reflector.auth as auth
|
||||
from reflector.db import get_database
|
||||
from reflector.db.meetings import meetings_controller
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.db.search import (
|
||||
DEFAULT_SEARCH_LIMIT,
|
||||
SearchLimit,
|
||||
@@ -32,7 +34,6 @@ from reflector.db.transcripts import (
|
||||
from reflector.processors.types import Transcript as ProcessorTranscript
|
||||
from reflector.processors.types import Word
|
||||
from reflector.settings import settings
|
||||
from reflector.ws_manager import get_ws_manager
|
||||
from reflector.zulip import (
|
||||
InvalidMessageError,
|
||||
get_zulip_message,
|
||||
@@ -212,7 +213,7 @@ async def transcripts_create(
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.add(
|
||||
return await transcripts_controller.add(
|
||||
info.name,
|
||||
source_kind=info.source_kind or SourceKind.LIVE,
|
||||
source_language=info.source_language,
|
||||
@@ -220,14 +221,6 @@ async def transcripts_create(
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
if user_id:
|
||||
await get_ws_manager().send_json(
|
||||
room_id=f"user:{user_id}",
|
||||
message={"event": "TRANSCRIPT_CREATED", "data": {"id": transcript.id}},
|
||||
)
|
||||
|
||||
return transcript
|
||||
|
||||
|
||||
# ==============================================================
|
||||
# Single transcript
|
||||
@@ -351,14 +344,12 @@ async def transcript_get(
|
||||
async def transcript_update(
|
||||
transcript_id: str,
|
||||
info: UpdateTranscript,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if not transcripts_controller.user_can_mutate(transcript, user_id):
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
values = info.dict(exclude_unset=True)
|
||||
updated_transcript = await transcripts_controller.update(transcript, values)
|
||||
return updated_transcript
|
||||
@@ -367,20 +358,20 @@ async def transcript_update(
|
||||
@router.delete("/transcripts/{transcript_id}", response_model=DeletionStatus)
|
||||
async def transcript_delete(
|
||||
transcript_id: str,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id(transcript_id)
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
if not transcripts_controller.user_can_mutate(transcript, user_id):
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
if transcript.meeting_id:
|
||||
meeting = await meetings_controller.get_by_id(transcript.meeting_id)
|
||||
room = await rooms_controller.get_by_id(meeting.room_id)
|
||||
if room.is_shared:
|
||||
user_id = None
|
||||
|
||||
await transcripts_controller.remove_by_id(transcript.id, user_id=user_id)
|
||||
await get_ws_manager().send_json(
|
||||
room_id=f"user:{user_id}",
|
||||
message={"event": "TRANSCRIPT_DELETED", "data": {"id": transcript.id}},
|
||||
)
|
||||
return DeletionStatus(status="ok")
|
||||
|
||||
|
||||
@@ -452,16 +443,15 @@ async def transcript_post_to_zulip(
|
||||
stream: str,
|
||||
topic: str,
|
||||
include_topics: bool,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
if not transcripts_controller.user_can_mutate(transcript, user_id):
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
content = get_zulip_message(transcript, include_topics)
|
||||
|
||||
message_updated = False
|
||||
|
||||
@@ -56,14 +56,12 @@ async def transcript_get_participants(
|
||||
async def transcript_add_participant(
|
||||
transcript_id: str,
|
||||
participant: CreateParticipant,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> Participant:
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if transcript.user_id is not None and transcript.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
# ensure the speaker is unique
|
||||
if participant.speaker is not None and transcript.participants is not None:
|
||||
@@ -103,14 +101,12 @@ async def transcript_update_participant(
|
||||
transcript_id: str,
|
||||
participant_id: str,
|
||||
participant: UpdateParticipant,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> Participant:
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if transcript.user_id is not None and transcript.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
# ensure the speaker is unique
|
||||
for p in transcript.participants:
|
||||
@@ -142,13 +138,11 @@ async def transcript_update_participant(
|
||||
async def transcript_delete_participant(
|
||||
transcript_id: str,
|
||||
participant_id: str,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> DeletionStatus:
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if transcript.user_id is not None and transcript.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
await transcripts_controller.delete_participant(transcript, participant_id)
|
||||
return DeletionStatus(status="ok")
|
||||
|
||||
@@ -35,14 +35,12 @@ class SpeakerMerge(BaseModel):
|
||||
async def transcript_assign_speaker(
|
||||
transcript_id: str,
|
||||
assignment: SpeakerAssignment,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> SpeakerAssignmentStatus:
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if transcript.user_id is not None and transcript.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
@@ -115,14 +113,12 @@ async def transcript_assign_speaker(
|
||||
async def transcript_merge_speaker(
|
||||
transcript_id: str,
|
||||
merge: SpeakerMerge,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
) -> SpeakerAssignmentStatus:
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if transcript.user_id is not None and transcript.user_id != user_id:
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
|
||||
@@ -4,11 +4,8 @@ Transcripts websocket API
|
||||
|
||||
"""
|
||||
|
||||
from typing import Optional
|
||||
from fastapi import APIRouter, HTTPException, WebSocket, WebSocketDisconnect
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, WebSocket, WebSocketDisconnect
|
||||
|
||||
import reflector.auth as auth
|
||||
from reflector.db.transcripts import transcripts_controller
|
||||
from reflector.ws_manager import get_ws_manager
|
||||
|
||||
@@ -24,12 +21,10 @@ async def transcript_get_websocket_events(transcript_id: str):
|
||||
async def transcript_events_websocket(
|
||||
transcript_id: str,
|
||||
websocket: WebSocket,
|
||||
user: Optional[auth.UserInfo] = Depends(auth.current_user_optional),
|
||||
# user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
# user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id(transcript_id)
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, WebSocket
|
||||
|
||||
from reflector.auth.auth_jwt import JWTAuth # type: ignore
|
||||
from reflector.ws_manager import get_ws_manager
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# Close code for unauthorized WebSocket connections
|
||||
UNAUTHORISED = 4401
|
||||
|
||||
|
||||
@router.websocket("/events")
|
||||
async def user_events_websocket(websocket: WebSocket):
|
||||
# Browser can't send Authorization header for WS; use subprotocol: ["bearer", token]
|
||||
raw_subprotocol = websocket.headers.get("sec-websocket-protocol") or ""
|
||||
parts = [p.strip() for p in raw_subprotocol.split(",") if p.strip()]
|
||||
token: Optional[str] = None
|
||||
negotiated_subprotocol: Optional[str] = None
|
||||
if len(parts) >= 2 and parts[0].lower() == "bearer":
|
||||
negotiated_subprotocol = "bearer"
|
||||
token = parts[1]
|
||||
|
||||
user_id: Optional[str] = None
|
||||
if not token:
|
||||
await websocket.close(code=UNAUTHORISED)
|
||||
return
|
||||
|
||||
try:
|
||||
payload = JWTAuth().verify_token(token)
|
||||
user_id = payload.get("sub")
|
||||
except Exception:
|
||||
await websocket.close(code=UNAUTHORISED)
|
||||
return
|
||||
|
||||
if not user_id:
|
||||
await websocket.close(code=UNAUTHORISED)
|
||||
return
|
||||
|
||||
room_id = f"user:{user_id}"
|
||||
ws_manager = get_ws_manager()
|
||||
|
||||
await ws_manager.add_user_to_room(
|
||||
room_id, websocket, subprotocol=negotiated_subprotocol
|
||||
)
|
||||
|
||||
try:
|
||||
while True:
|
||||
await websocket.receive()
|
||||
finally:
|
||||
if room_id:
|
||||
await ws_manager.remove_user_from_room(room_id, websocket)
|
||||
@@ -20,7 +20,7 @@ else:
|
||||
"reflector.worker.healthcheck",
|
||||
"reflector.worker.process",
|
||||
"reflector.worker.cleanup",
|
||||
"reflector.worker.ics_sync",
|
||||
"reflector.worker.jitsi_events",
|
||||
]
|
||||
)
|
||||
|
||||
@@ -34,18 +34,14 @@ else:
|
||||
"task": "reflector.worker.process.process_meetings",
|
||||
"schedule": float(settings.SQS_POLLING_TIMEOUT_SECONDS),
|
||||
},
|
||||
"process_jitsi_events": {
|
||||
"task": "reflector.worker.jitsi_events.process_jitsi_events",
|
||||
"schedule": 5.0, # Process every 5 seconds
|
||||
},
|
||||
"reprocess_failed_recordings": {
|
||||
"task": "reflector.worker.process.reprocess_failed_recordings",
|
||||
"schedule": crontab(hour=5, minute=0), # Midnight EST
|
||||
},
|
||||
"sync_all_ics_calendars": {
|
||||
"task": "reflector.worker.ics_sync.sync_all_ics_calendars",
|
||||
"schedule": 60.0, # Run every minute to check which rooms need sync
|
||||
},
|
||||
"create_upcoming_meetings": {
|
||||
"task": "reflector.worker.ics_sync.create_upcoming_meetings",
|
||||
"schedule": 30.0, # Run every 30 seconds to create upcoming meetings
|
||||
},
|
||||
}
|
||||
|
||||
if settings.PUBLIC_MODE:
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user