mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2025-12-20 20:29:06 +00:00
Compare commits
1 Commits
main
...
fix/zombie
| Author | SHA1 | Date | |
|---|---|---|---|
|
02b269ad6d |
90
.github/workflows/deploy.yml
vendored
Normal file
90
.github/workflows/deploy.yml
vendored
Normal file
@@ -0,0 +1,90 @@
|
||||
name: Build container/push to container registry
|
||||
|
||||
on: [workflow_dispatch]
|
||||
|
||||
env:
|
||||
# 950402358378.dkr.ecr.us-east-1.amazonaws.com/reflector
|
||||
AWS_REGION: us-east-1
|
||||
ECR_REPOSITORY: reflector
|
||||
|
||||
jobs:
|
||||
build:
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- platform: linux/amd64
|
||||
runner: linux-amd64
|
||||
arch: amd64
|
||||
- platform: linux/arm64
|
||||
runner: linux-arm64
|
||||
arch: arm64
|
||||
|
||||
runs-on: ${{ matrix.runner }}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
outputs:
|
||||
registry: ${{ steps.login-ecr.outputs.registry }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Configure AWS credentials
|
||||
uses: aws-actions/configure-aws-credentials@v4
|
||||
with:
|
||||
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
|
||||
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
|
||||
aws-region: ${{ env.AWS_REGION }}
|
||||
|
||||
- name: Login to Amazon ECR
|
||||
id: login-ecr
|
||||
uses: aws-actions/amazon-ecr-login@v2
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Build and push ${{ matrix.arch }}
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: server
|
||||
platforms: ${{ matrix.platform }}
|
||||
push: true
|
||||
tags: ${{ steps.login-ecr.outputs.registry }}/${{ env.ECR_REPOSITORY }}:latest-${{ matrix.arch }}
|
||||
cache-from: type=gha,scope=${{ matrix.arch }}
|
||||
cache-to: type=gha,mode=max,scope=${{ matrix.arch }}
|
||||
github-token: ${{ secrets.GHA_CACHE_TOKEN }}
|
||||
provenance: false
|
||||
|
||||
create-manifest:
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
|
||||
permissions:
|
||||
deployments: write
|
||||
contents: read
|
||||
|
||||
steps:
|
||||
- name: Configure AWS credentials
|
||||
uses: aws-actions/configure-aws-credentials@v4
|
||||
with:
|
||||
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
|
||||
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
|
||||
aws-region: ${{ env.AWS_REGION }}
|
||||
|
||||
- name: Login to Amazon ECR
|
||||
uses: aws-actions/amazon-ecr-login@v2
|
||||
|
||||
- name: Create and push multi-arch manifest
|
||||
run: |
|
||||
# Get the registry URL (since we can't easily access job outputs in matrix)
|
||||
ECR_REGISTRY=$(aws ecr describe-registry --query 'registryId' --output text).dkr.ecr.${{ env.AWS_REGION }}.amazonaws.com
|
||||
|
||||
docker manifest create \
|
||||
$ECR_REGISTRY/${{ env.ECR_REPOSITORY }}:latest \
|
||||
$ECR_REGISTRY/${{ env.ECR_REPOSITORY }}:latest-amd64 \
|
||||
$ECR_REGISTRY/${{ env.ECR_REPOSITORY }}:latest-arm64
|
||||
|
||||
docker manifest push $ECR_REGISTRY/${{ env.ECR_REPOSITORY }}:latest
|
||||
|
||||
echo "✅ Multi-arch manifest pushed: $ECR_REGISTRY/${{ env.ECR_REPOSITORY }}:latest"
|
||||
@@ -1,31 +1,35 @@
|
||||
name: Build and Push Backend Docker Image (Docker Hub)
|
||||
name: Build and Push Frontend Docker Image
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "v*"
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- 'www/**'
|
||||
- '.github/workflows/docker-frontend.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
REGISTRY: docker.io
|
||||
IMAGE_NAME: monadicalsas/reflector-backend
|
||||
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 Docker Hub
|
||||
- name: Log in to GitHub Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: monadicalsas
|
||||
password: ${{ secrets.DOCKERHUB_TOKEN }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
@@ -34,7 +38,7 @@ jobs:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=ref,event=tag
|
||||
type=sha,prefix={{branch}}-
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
@@ -43,11 +47,11 @@ jobs:
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: ./server
|
||||
file: ./server/Dockerfile
|
||||
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
|
||||
platforms: linux/amd64,linux/arm64
|
||||
70
.github/workflows/dockerhub-frontend.yml
vendored
70
.github/workflows/dockerhub-frontend.yml
vendored
@@ -1,70 +0,0 @@
|
||||
name: Build and Push Frontend Docker Image
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- "v*"
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
REGISTRY: docker.io
|
||||
IMAGE_NAME: monadicalsas/reflector-frontend
|
||||
|
||||
jobs:
|
||||
build-and-push:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Log in to Docker Hub
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: monadicalsas
|
||||
password: ${{ secrets.DOCKERHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=ref,event=tag
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
github-token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- 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
|
||||
|
||||
deploy:
|
||||
needs: build-and-push
|
||||
runs-on: ubuntu-latest
|
||||
if: success()
|
||||
strategy:
|
||||
matrix:
|
||||
environment: [reflector-monadical, reflector-media]
|
||||
environment: ${{ matrix.environment }}
|
||||
steps:
|
||||
- name: Trigger Coolify deployment
|
||||
run: |
|
||||
curl -X POST "${{ secrets.COOLIFY_WEBHOOK_URL }}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "Authorization: Bearer ${{ secrets.COOLIFY_WEBHOOK_TOKEN }}" \
|
||||
-f || (echo "Failed to trigger Coolify deployment for ${{ matrix.environment }}" && exit 1)
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -18,4 +18,3 @@ CLAUDE.local.md
|
||||
www/.env.development
|
||||
www/.env.production
|
||||
.playwright-mcp
|
||||
.secrets
|
||||
|
||||
@@ -1,24 +0,0 @@
|
||||
# Example secrets file for GitHub Actions workflows
|
||||
# Copy this to .secrets and fill in your values
|
||||
# These secrets should be configured in GitHub repository settings:
|
||||
# Settings > Secrets and variables > Actions
|
||||
|
||||
# DockerHub Configuration (required for frontend and backend deployment)
|
||||
# Create a Docker Hub access token at https://hub.docker.com/settings/security
|
||||
# Username: monadicalsas
|
||||
DOCKERHUB_TOKEN=your-dockerhub-access-token
|
||||
|
||||
# GitHub Token (required for frontend and backend deployment)
|
||||
# Used by docker/metadata-action for extracting image metadata
|
||||
# Can use the default GITHUB_TOKEN or create a personal access token
|
||||
GITHUB_TOKEN=your-github-token-or-use-default-GITHUB_TOKEN
|
||||
|
||||
# Coolify Deployment Webhook (required for frontend deployment)
|
||||
# Used to trigger automatic deployment after image push
|
||||
# Configure these secrets in GitHub Environments:
|
||||
# Each environment should have:
|
||||
# - COOLIFY_WEBHOOK_URL: The webhook URL for that specific deployment
|
||||
# - COOLIFY_WEBHOOK_TOKEN: The webhook token (can be the same for both if using same token)
|
||||
|
||||
# Optional: GitHub Actions Cache Token (for local testing with act)
|
||||
GHA_CACHE_TOKEN=your-github-token-or-empty
|
||||
88
CHANGELOG.md
88
CHANGELOG.md
@@ -1,93 +1,5 @@
|
||||
# Changelog
|
||||
|
||||
## [0.24.0](https://github.com/Monadical-SAS/reflector/compare/v0.23.2...v0.24.0) (2025-12-18)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* identify action items ([#790](https://github.com/Monadical-SAS/reflector/issues/790)) ([964cd78](https://github.com/Monadical-SAS/reflector/commit/964cd78bb699d83d012ae4b8c96565df25b90a5d))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* automatically reprocess daily recordings ([#797](https://github.com/Monadical-SAS/reflector/issues/797)) ([5f458aa](https://github.com/Monadical-SAS/reflector/commit/5f458aa4a7ec3d00ca5ec49d62fcc8ad232b138e))
|
||||
* daily video optimisation ([#789](https://github.com/Monadical-SAS/reflector/issues/789)) ([16284e1](https://github.com/Monadical-SAS/reflector/commit/16284e1ac3faede2b74f0d91b50c0b5612af2c35))
|
||||
* main menu login ([#800](https://github.com/Monadical-SAS/reflector/issues/800)) ([0bc971b](https://github.com/Monadical-SAS/reflector/commit/0bc971ba966a52d719c8c240b47dc7b3bdea4391))
|
||||
* retry on workflow timeout ([#798](https://github.com/Monadical-SAS/reflector/issues/798)) ([5f7dfad](https://github.com/Monadical-SAS/reflector/commit/5f7dfadabd3e8017406ad3720ba495a59963ee34))
|
||||
|
||||
## [0.23.2](https://github.com/Monadical-SAS/reflector/compare/v0.23.1...v0.23.2) (2025-12-11)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* build on push tags ([#785](https://github.com/Monadical-SAS/reflector/issues/785)) ([d7f140b](https://github.com/Monadical-SAS/reflector/commit/d7f140b7d1f4660d5da7a0da1357f68869e0b5cd))
|
||||
|
||||
## [0.23.1](https://github.com/Monadical-SAS/reflector/compare/v0.23.0...v0.23.1) (2025-12-11)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* populate room_name in transcript GET endpoint ([#783](https://github.com/Monadical-SAS/reflector/issues/783)) ([0eba147](https://github.com/Monadical-SAS/reflector/commit/0eba1470181c7b9e0a79964a1ef28c09bcbdd9d7))
|
||||
|
||||
## [0.23.0](https://github.com/Monadical-SAS/reflector/compare/v0.22.4...v0.23.0) (2025-12-10)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* dockerhub ci ([#772](https://github.com/Monadical-SAS/reflector/issues/772)) ([00549f1](https://github.com/Monadical-SAS/reflector/commit/00549f153ade922cf4cb6c5358a7d11a39c426d2))
|
||||
* llm retries ([#739](https://github.com/Monadical-SAS/reflector/issues/739)) ([61f0e29](https://github.com/Monadical-SAS/reflector/commit/61f0e29d4c51eab54ee67af92141fbb171e8ccaa))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* celery inspect bug sidestep in restart script ([#766](https://github.com/Monadical-SAS/reflector/issues/766)) ([ec17ed7](https://github.com/Monadical-SAS/reflector/commit/ec17ed7b587cf6ee143646baaee67a7c017044d4))
|
||||
* deploy frontend to coolify ([#779](https://github.com/Monadical-SAS/reflector/issues/779)) ([91650ec](https://github.com/Monadical-SAS/reflector/commit/91650ec65f65713faa7ee0dcfb75af427b7c4ba0))
|
||||
* hide rooms settings instead of disabling ([#763](https://github.com/Monadical-SAS/reflector/issues/763)) ([3ad78be](https://github.com/Monadical-SAS/reflector/commit/3ad78be7628c0d029296b301a0e87236c76b7598))
|
||||
* return participant emails from transcript endpoint ([#769](https://github.com/Monadical-SAS/reflector/issues/769)) ([d3a5cd1](https://github.com/Monadical-SAS/reflector/commit/d3a5cd12d2d0d9c32af2d5bd9322e030ef69b85d))
|
||||
|
||||
## [0.22.4](https://github.com/Monadical-SAS/reflector/compare/v0.22.3...v0.22.4) (2025-12-02)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* Multitrack mixdown optimisation 2 ([#764](https://github.com/Monadical-SAS/reflector/issues/764)) ([bd5df1c](https://github.com/Monadical-SAS/reflector/commit/bd5df1ce2ebf35d7f3413b295e56937a9a28ef7b))
|
||||
|
||||
## [0.22.3](https://github.com/Monadical-SAS/reflector/compare/v0.22.2...v0.22.3) (2025-12-02)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* align daily room settings ([#759](https://github.com/Monadical-SAS/reflector/issues/759)) ([28f87c0](https://github.com/Monadical-SAS/reflector/commit/28f87c09dc459846873d0dde65b03e3d7b2b9399))
|
||||
|
||||
## [0.22.2](https://github.com/Monadical-SAS/reflector/compare/v0.22.1...v0.22.2) (2025-12-02)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* daily auto refresh fix ([#755](https://github.com/Monadical-SAS/reflector/issues/755)) ([fe47c46](https://github.com/Monadical-SAS/reflector/commit/fe47c46489c5aa0cc538109f7559cc9accb35c01))
|
||||
* Skip mixdown for multitrack ([#760](https://github.com/Monadical-SAS/reflector/issues/760)) ([b51b7aa](https://github.com/Monadical-SAS/reflector/commit/b51b7aa9176c1a53ba57ad99f5e976c804a1e80c))
|
||||
|
||||
## [0.22.1](https://github.com/Monadical-SAS/reflector/compare/v0.22.0...v0.22.1) (2025-11-27)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* participants update from daily ([#749](https://github.com/Monadical-SAS/reflector/issues/749)) ([7f0b728](https://github.com/Monadical-SAS/reflector/commit/7f0b728991c1b9f9aae702c96297eae63b561ef5))
|
||||
|
||||
## [0.22.0](https://github.com/Monadical-SAS/reflector/compare/v0.21.0...v0.22.0) (2025-11-26)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* Multitrack segmentation ([#747](https://github.com/Monadical-SAS/reflector/issues/747)) ([d63040e](https://github.com/Monadical-SAS/reflector/commit/d63040e2fdc07e7b272e85a39eb2411cd6a14798))
|
||||
|
||||
## [0.21.0](https://github.com/Monadical-SAS/reflector/compare/v0.20.0...v0.21.0) (2025-11-26)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* add transcript format parameter to GET endpoint ([#709](https://github.com/Monadical-SAS/reflector/issues/709)) ([f6ca075](https://github.com/Monadical-SAS/reflector/commit/f6ca07505f34483b02270a2ef3bd809e9d2e1045))
|
||||
|
||||
## [0.20.0](https://github.com/Monadical-SAS/reflector/compare/v0.19.0...v0.20.0) (2025-11-25)
|
||||
|
||||
|
||||
|
||||
@@ -3,8 +3,10 @@
|
||||
|
||||
services:
|
||||
web:
|
||||
image: monadicalsas/reflector-frontend:latest
|
||||
pull_policy: always
|
||||
build:
|
||||
context: ./www
|
||||
dockerfile: Dockerfile
|
||||
image: reflector-frontend:latest
|
||||
environment:
|
||||
- KV_URL=${KV_URL:-redis://redis:6379}
|
||||
- SITE_URL=${SITE_URL}
|
||||
@@ -34,4 +36,4 @@ services:
|
||||
- redis_data:/data
|
||||
|
||||
volumes:
|
||||
redis_data:
|
||||
redis_data:
|
||||
@@ -1,241 +0,0 @@
|
||||
# Transcript Formats
|
||||
|
||||
The Reflector API provides multiple output formats for transcript data through the `transcript_format` query parameter on the GET `/v1/transcripts/{id}` endpoint.
|
||||
|
||||
## Overview
|
||||
|
||||
When retrieving a transcript, you can specify the desired format using the `transcript_format` query parameter. The API supports four formats optimized for different use cases:
|
||||
|
||||
- **text** - Plain text with speaker names (default)
|
||||
- **text-timestamped** - Timestamped text with speaker names
|
||||
- **webvtt-named** - WebVTT subtitle format with participant names
|
||||
- **json** - Structured JSON segments with full metadata
|
||||
|
||||
All formats include participant information when available, resolving speaker IDs to actual names.
|
||||
|
||||
## Query Parameter Usage
|
||||
|
||||
```
|
||||
GET /v1/transcripts/{id}?transcript_format={format}
|
||||
```
|
||||
|
||||
### Parameters
|
||||
|
||||
- `transcript_format` (optional): The desired output format
|
||||
- Type: `"text" | "text-timestamped" | "webvtt-named" | "json"`
|
||||
- Default: `"text"`
|
||||
|
||||
## Format Descriptions
|
||||
|
||||
### Text Format (`text`)
|
||||
|
||||
**Use case:** Simple, human-readable transcript for display or export.
|
||||
|
||||
**Format:** Speaker names followed by their dialogue, one line per segment.
|
||||
|
||||
**Example:**
|
||||
```
|
||||
John Smith: Hello everyone
|
||||
Jane Doe: Hi there
|
||||
John Smith: How are you today?
|
||||
```
|
||||
|
||||
**Request:**
|
||||
```bash
|
||||
GET /v1/transcripts/{id}?transcript_format=text
|
||||
```
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"id": "transcript_123",
|
||||
"name": "Meeting Recording",
|
||||
"transcript_format": "text",
|
||||
"transcript": "John Smith: Hello everyone\nJane Doe: Hi there\nJohn Smith: How are you today?",
|
||||
"participants": [
|
||||
{"id": "p1", "speaker": 0, "name": "John Smith"},
|
||||
{"id": "p2", "speaker": 1, "name": "Jane Doe"}
|
||||
],
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
### Text Timestamped Format (`text-timestamped`)
|
||||
|
||||
**Use case:** Transcript with timing information for navigation or reference.
|
||||
|
||||
**Format:** `[MM:SS]` timestamp prefix before each speaker and dialogue.
|
||||
|
||||
**Example:**
|
||||
```
|
||||
[00:00] John Smith: Hello everyone
|
||||
[00:05] Jane Doe: Hi there
|
||||
[00:12] John Smith: How are you today?
|
||||
```
|
||||
|
||||
**Request:**
|
||||
```bash
|
||||
GET /v1/transcripts/{id}?transcript_format=text-timestamped
|
||||
```
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"id": "transcript_123",
|
||||
"name": "Meeting Recording",
|
||||
"transcript_format": "text-timestamped",
|
||||
"transcript": "[00:00] John Smith: Hello everyone\n[00:05] Jane Doe: Hi there\n[00:12] John Smith: How are you today?",
|
||||
"participants": [
|
||||
{"id": "p1", "speaker": 0, "name": "John Smith"},
|
||||
{"id": "p2", "speaker": 1, "name": "Jane Doe"}
|
||||
],
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
### WebVTT Named Format (`webvtt-named`)
|
||||
|
||||
**Use case:** Subtitle files for video players, accessibility tools, or video editing.
|
||||
|
||||
**Format:** Standard WebVTT subtitle format with voice tags using participant names.
|
||||
|
||||
**Example:**
|
||||
```
|
||||
WEBVTT
|
||||
|
||||
00:00:00.000 --> 00:00:05.000
|
||||
<v John Smith>Hello everyone
|
||||
|
||||
00:00:05.000 --> 00:00:12.000
|
||||
<v Jane Doe>Hi there
|
||||
|
||||
00:00:12.000 --> 00:00:18.000
|
||||
<v John Smith>How are you today?
|
||||
```
|
||||
|
||||
**Request:**
|
||||
```bash
|
||||
GET /v1/transcripts/{id}?transcript_format=webvtt-named
|
||||
```
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"id": "transcript_123",
|
||||
"name": "Meeting Recording",
|
||||
"transcript_format": "webvtt-named",
|
||||
"transcript": "WEBVTT\n\n00:00:00.000 --> 00:00:05.000\n<v John Smith>Hello everyone\n\n...",
|
||||
"participants": [
|
||||
{"id": "p1", "speaker": 0, "name": "John Smith"},
|
||||
{"id": "p2", "speaker": 1, "name": "Jane Doe"}
|
||||
],
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
### JSON Format (`json`)
|
||||
|
||||
**Use case:** Programmatic access with full timing and speaker metadata.
|
||||
|
||||
**Format:** Array of segment objects with speaker information, text content, and precise timing.
|
||||
|
||||
**Example:**
|
||||
```json
|
||||
[
|
||||
{
|
||||
"speaker": 0,
|
||||
"speaker_name": "John Smith",
|
||||
"text": "Hello everyone",
|
||||
"start": 0.0,
|
||||
"end": 5.0
|
||||
},
|
||||
{
|
||||
"speaker": 1,
|
||||
"speaker_name": "Jane Doe",
|
||||
"text": "Hi there",
|
||||
"start": 5.0,
|
||||
"end": 12.0
|
||||
},
|
||||
{
|
||||
"speaker": 0,
|
||||
"speaker_name": "John Smith",
|
||||
"text": "How are you today?",
|
||||
"start": 12.0,
|
||||
"end": 18.0
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
**Request:**
|
||||
```bash
|
||||
GET /v1/transcripts/{id}?transcript_format=json
|
||||
```
|
||||
|
||||
**Response:**
|
||||
```json
|
||||
{
|
||||
"id": "transcript_123",
|
||||
"name": "Meeting Recording",
|
||||
"transcript_format": "json",
|
||||
"transcript": [
|
||||
{
|
||||
"speaker": 0,
|
||||
"speaker_name": "John Smith",
|
||||
"text": "Hello everyone",
|
||||
"start": 0.0,
|
||||
"end": 5.0
|
||||
},
|
||||
{
|
||||
"speaker": 1,
|
||||
"speaker_name": "Jane Doe",
|
||||
"text": "Hi there",
|
||||
"start": 5.0,
|
||||
"end": 12.0
|
||||
}
|
||||
],
|
||||
"participants": [
|
||||
{"id": "p1", "speaker": 0, "name": "John Smith"},
|
||||
{"id": "p2", "speaker": 1, "name": "Jane Doe"}
|
||||
],
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
## Response Structure
|
||||
|
||||
All formats return the same base transcript metadata with an additional `transcript_format` field and format-specific `transcript` field:
|
||||
|
||||
### Common Fields
|
||||
|
||||
- `id`: Transcript identifier
|
||||
- `user_id`: Owner user ID (if authenticated)
|
||||
- `name`: Transcript name
|
||||
- `status`: Processing status
|
||||
- `locked`: Whether transcript is locked for editing
|
||||
- `duration`: Total duration in seconds
|
||||
- `title`: Auto-generated or custom title
|
||||
- `short_summary`: Brief summary
|
||||
- `long_summary`: Detailed summary
|
||||
- `created_at`: Creation timestamp
|
||||
- `share_mode`: Access control setting
|
||||
- `source_language`: Original audio language
|
||||
- `target_language`: Translation target language
|
||||
- `reviewed`: Whether transcript has been reviewed
|
||||
- `meeting_id`: Associated meeting ID (if applicable)
|
||||
- `source_kind`: Source type (live, file, room)
|
||||
- `room_id`: Associated room ID (if applicable)
|
||||
- `audio_deleted`: Whether audio has been deleted
|
||||
- `participants`: Array of participant objects with speaker mappings
|
||||
|
||||
### Format-Specific Fields
|
||||
|
||||
- `transcript_format`: The format identifier (discriminator field)
|
||||
- `transcript`: The formatted transcript content (string for text/webvtt formats, array for json format)
|
||||
|
||||
## Speaker Name Resolution
|
||||
|
||||
All formats resolve speaker IDs to participant names when available:
|
||||
|
||||
- If a participant exists for the speaker ID, their name is used
|
||||
- If no participant exists, a default name like "Speaker 0" is generated
|
||||
- Speaker IDs are integers (0, 1, 2, etc.) assigned during diarization
|
||||
@@ -1,26 +0,0 @@
|
||||
"""add_action_items
|
||||
|
||||
Revision ID: 05f8688d6895
|
||||
Revises: bbafedfa510c
|
||||
Create Date: 2025-12-12 11:57:50.209658
|
||||
|
||||
"""
|
||||
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "05f8688d6895"
|
||||
down_revision: Union[str, None] = "bbafedfa510c"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
op.add_column("transcript", sa.Column("action_items", sa.JSON(), nullable=True))
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.drop_column("transcript", "action_items")
|
||||
@@ -126,7 +126,6 @@ markers = [
|
||||
select = [
|
||||
"I", # isort - import sorting
|
||||
"F401", # unused imports
|
||||
"E402", # module level import not at top of file
|
||||
"PLC0415", # import-outside-top-level - detect inline imports
|
||||
]
|
||||
|
||||
|
||||
@@ -1,19 +1,13 @@
|
||||
import asyncio
|
||||
import functools
|
||||
from uuid import uuid4
|
||||
|
||||
from celery import current_task
|
||||
|
||||
from reflector.db import get_database
|
||||
from reflector.llm import llm_session_id
|
||||
|
||||
|
||||
def asynctask(f):
|
||||
@functools.wraps(f)
|
||||
def wrapper(*args, **kwargs):
|
||||
async def run_with_db():
|
||||
task_id = current_task.request.id if current_task else None
|
||||
llm_session_id.set(task_id or f"random-{uuid4().hex}")
|
||||
database = get_database()
|
||||
await database.connect()
|
||||
try:
|
||||
|
||||
@@ -18,7 +18,6 @@ from .requests import (
|
||||
|
||||
# Response models
|
||||
from .responses import (
|
||||
FinishedRecordingResponse,
|
||||
MeetingParticipant,
|
||||
MeetingParticipantsResponse,
|
||||
MeetingResponse,
|
||||
@@ -80,7 +79,6 @@ __all__ = [
|
||||
"MeetingParticipant",
|
||||
"MeetingResponse",
|
||||
"RecordingResponse",
|
||||
"FinishedRecordingResponse",
|
||||
"RecordingS3Info",
|
||||
"MeetingTokenResponse",
|
||||
"WebhookResponse",
|
||||
|
||||
@@ -40,10 +40,6 @@ class RoomProperties(BaseModel):
|
||||
)
|
||||
enable_chat: bool = Field(default=True, description="Enable in-meeting chat")
|
||||
enable_screenshare: bool = Field(default=True, description="Enable screen sharing")
|
||||
enable_knocking: bool = Field(
|
||||
default=False,
|
||||
description="Enable knocking for private rooms (allows participants to request access)",
|
||||
)
|
||||
start_video_off: bool = Field(
|
||||
default=False, description="Start with video off for all participants"
|
||||
)
|
||||
|
||||
@@ -68,7 +68,7 @@ class MeetingParticipant(BaseModel):
|
||||
Reference: https://docs.daily.co/reference/rest-api/meetings/get-meeting-participants
|
||||
"""
|
||||
|
||||
user_id: NonEmptyString | None = Field(None, description="User identifier")
|
||||
user_id: NonEmptyString = Field(description="User identifier")
|
||||
participant_id: NonEmptyString = Field(description="Participant session identifier")
|
||||
user_name: NonEmptyString | None = Field(None, description="User display name")
|
||||
join_time: int = Field(description="Join timestamp (Unix epoch seconds)")
|
||||
@@ -121,10 +121,7 @@ class RecordingS3Info(BaseModel):
|
||||
|
||||
class RecordingResponse(BaseModel):
|
||||
"""
|
||||
Response from recording retrieval endpoint (network layer).
|
||||
|
||||
Duration may be None for recordings still being processed by Daily.
|
||||
Use FinishedRecordingResponse for recordings ready for processing.
|
||||
Response from recording retrieval endpoint.
|
||||
|
||||
Reference: https://docs.daily.co/reference/rest-api/recordings
|
||||
"""
|
||||
@@ -138,9 +135,7 @@ class RecordingResponse(BaseModel):
|
||||
max_participants: int | None = Field(
|
||||
None, description="Maximum participants during recording (may be missing)"
|
||||
)
|
||||
duration: int | None = Field(
|
||||
None, description="Recording duration in seconds (None if still processing)"
|
||||
)
|
||||
duration: int = Field(description="Recording duration in seconds")
|
||||
share_token: NonEmptyString | None = Field(
|
||||
None, description="Token for sharing recording"
|
||||
)
|
||||
@@ -154,25 +149,6 @@ class RecordingResponse(BaseModel):
|
||||
None, description="Meeting session identifier (may be missing)"
|
||||
)
|
||||
|
||||
def to_finished(self) -> "FinishedRecordingResponse | None":
|
||||
"""Convert to FinishedRecordingResponse if duration is available and status is finished."""
|
||||
if self.duration is None or self.status != "finished":
|
||||
return None
|
||||
return FinishedRecordingResponse(**self.model_dump())
|
||||
|
||||
|
||||
class FinishedRecordingResponse(RecordingResponse):
|
||||
"""
|
||||
Recording with confirmed duration - ready for processing.
|
||||
|
||||
This model guarantees duration is present and status is finished.
|
||||
"""
|
||||
|
||||
status: Literal["finished"] = Field(
|
||||
description="Recording status (always 'finished')"
|
||||
)
|
||||
duration: int = Field(description="Recording duration in seconds")
|
||||
|
||||
|
||||
class MeetingTokenResponse(BaseModel):
|
||||
"""
|
||||
|
||||
@@ -3,7 +3,6 @@ from typing import Literal
|
||||
|
||||
import sqlalchemy as sa
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy import or_
|
||||
|
||||
from reflector.db import get_database, metadata
|
||||
from reflector.utils import generate_uuid4
|
||||
@@ -36,15 +35,8 @@ class Recording(BaseModel):
|
||||
status: Literal["pending", "processing", "completed", "failed"] = "pending"
|
||||
meeting_id: str | None = None
|
||||
# for multitrack reprocessing
|
||||
# track_keys can be empty list [] if recording finished but no audio was captured (silence/muted)
|
||||
# None means not a multitrack recording, [] means multitrack with no tracks
|
||||
track_keys: list[str] | None = None
|
||||
|
||||
@property
|
||||
def is_multitrack(self) -> bool:
|
||||
"""True if recording has separate audio tracks (1+ tracks counts as multitrack)."""
|
||||
return self.track_keys is not None and len(self.track_keys) > 0
|
||||
|
||||
|
||||
class RecordingController:
|
||||
async def create(self, recording: Recording):
|
||||
@@ -80,35 +72,5 @@ class RecordingController:
|
||||
results = await get_database().fetch_all(query)
|
||||
return [Recording(**row) for row in results]
|
||||
|
||||
async def get_multitrack_needing_reprocessing(
|
||||
self, bucket_name: str
|
||||
) -> list[Recording]:
|
||||
"""
|
||||
Get multitrack recordings that need reprocessing:
|
||||
- Have track_keys (multitrack)
|
||||
- Either have no transcript OR transcript has error status
|
||||
|
||||
This is more efficient than fetching all recordings and filtering in Python.
|
||||
"""
|
||||
from reflector.db.transcripts import (
|
||||
transcripts, # noqa: PLC0415 cyclic import
|
||||
)
|
||||
|
||||
query = (
|
||||
recordings.select()
|
||||
.outerjoin(transcripts, recordings.c.id == transcripts.c.recording_id)
|
||||
.where(
|
||||
recordings.c.bucket_name == bucket_name,
|
||||
recordings.c.track_keys.isnot(None),
|
||||
or_(
|
||||
transcripts.c.id.is_(None),
|
||||
transcripts.c.status == "error",
|
||||
),
|
||||
)
|
||||
)
|
||||
results = await get_database().fetch_all(query)
|
||||
recordings_list = [Recording(**row) for row in results]
|
||||
return [r for r in recordings_list if r.is_multitrack]
|
||||
|
||||
|
||||
recordings_controller = RecordingController()
|
||||
|
||||
@@ -44,7 +44,6 @@ transcripts = sqlalchemy.Table(
|
||||
sqlalchemy.Column("title", sqlalchemy.String),
|
||||
sqlalchemy.Column("short_summary", sqlalchemy.String),
|
||||
sqlalchemy.Column("long_summary", sqlalchemy.String),
|
||||
sqlalchemy.Column("action_items", sqlalchemy.JSON),
|
||||
sqlalchemy.Column("topics", sqlalchemy.JSON),
|
||||
sqlalchemy.Column("events", sqlalchemy.JSON),
|
||||
sqlalchemy.Column("participants", sqlalchemy.JSON),
|
||||
@@ -165,10 +164,6 @@ class TranscriptFinalLongSummary(BaseModel):
|
||||
long_summary: str
|
||||
|
||||
|
||||
class TranscriptActionItems(BaseModel):
|
||||
action_items: dict
|
||||
|
||||
|
||||
class TranscriptFinalTitle(BaseModel):
|
||||
title: str
|
||||
|
||||
@@ -209,7 +204,6 @@ class Transcript(BaseModel):
|
||||
locked: bool = False
|
||||
short_summary: str | None = None
|
||||
long_summary: str | None = None
|
||||
action_items: dict | None = None
|
||||
topics: list[TranscriptTopic] = []
|
||||
events: list[TranscriptEvent] = []
|
||||
participants: list[TranscriptParticipant] | None = []
|
||||
@@ -374,12 +368,7 @@ class TranscriptController:
|
||||
room_id: str | None = None,
|
||||
search_term: str | None = None,
|
||||
return_query: bool = False,
|
||||
exclude_columns: list[str] = [
|
||||
"topics",
|
||||
"events",
|
||||
"participants",
|
||||
"action_items",
|
||||
],
|
||||
exclude_columns: list[str] = ["topics", "events", "participants"],
|
||||
) -> list[Transcript]:
|
||||
"""
|
||||
Get all transcripts
|
||||
|
||||
@@ -88,11 +88,5 @@ class UserController:
|
||||
results = await get_database().fetch_all(query)
|
||||
return [User(**r) for r in results]
|
||||
|
||||
@staticmethod
|
||||
async def get_by_ids(user_ids: list[NonEmptyString]) -> dict[str, User]:
|
||||
query = users.select().where(users.c.id.in_(user_ids))
|
||||
results = await get_database().fetch_all(query)
|
||||
return {user.id: User(**user) for user in results}
|
||||
|
||||
|
||||
user_controller = UserController()
|
||||
|
||||
@@ -1,32 +1,14 @@
|
||||
import logging
|
||||
from contextvars import ContextVar
|
||||
from typing import Generic, Type, TypeVar
|
||||
from uuid import uuid4
|
||||
from typing import Type, TypeVar
|
||||
|
||||
from llama_index.core import Settings
|
||||
from llama_index.core.output_parsers import PydanticOutputParser
|
||||
from llama_index.core.program import LLMTextCompletionProgram
|
||||
from llama_index.core.response_synthesizers import TreeSummarize
|
||||
from llama_index.core.workflow import (
|
||||
Context,
|
||||
Event,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
step,
|
||||
)
|
||||
from llama_index.llms.openai_like import OpenAILike
|
||||
from pydantic import BaseModel, ValidationError
|
||||
from workflows.errors import WorkflowTimeoutError
|
||||
|
||||
from reflector.utils.retry import retry
|
||||
|
||||
T = TypeVar("T", bound=BaseModel)
|
||||
OutputT = TypeVar("OutputT", bound=BaseModel)
|
||||
|
||||
# Session ID for LiteLLM request grouping - set per processing run
|
||||
llm_session_id: ContextVar[str | None] = ContextVar("llm_session_id", default=None)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
STRUCTURED_RESPONSE_PROMPT_TEMPLATE = """
|
||||
Based on the following analysis, provide the information in the requested JSON format:
|
||||
@@ -38,158 +20,6 @@ Analysis:
|
||||
"""
|
||||
|
||||
|
||||
class LLMParseError(Exception):
|
||||
"""Raised when LLM output cannot be parsed after retries."""
|
||||
|
||||
def __init__(self, output_cls: Type[BaseModel], error_msg: str, attempts: int):
|
||||
self.output_cls = output_cls
|
||||
self.error_msg = error_msg
|
||||
self.attempts = attempts
|
||||
super().__init__(
|
||||
f"Failed to parse {output_cls.__name__} after {attempts} attempts: {error_msg}"
|
||||
)
|
||||
|
||||
|
||||
class ExtractionDone(Event):
|
||||
"""Event emitted when LLM JSON formatting completes."""
|
||||
|
||||
output: str
|
||||
|
||||
|
||||
class ValidationErrorEvent(Event):
|
||||
"""Event emitted when validation fails."""
|
||||
|
||||
error: str
|
||||
wrong_output: str
|
||||
|
||||
|
||||
class StructuredOutputWorkflow(Workflow, Generic[OutputT]):
|
||||
"""Workflow for structured output extraction with validation retry.
|
||||
|
||||
This workflow handles parse/validation retries only. Network error retries
|
||||
are handled internally by Settings.llm (OpenAILike max_retries=3).
|
||||
The caller should NOT wrap this workflow in additional retry logic.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
output_cls: Type[OutputT],
|
||||
max_retries: int = 3,
|
||||
**kwargs,
|
||||
):
|
||||
super().__init__(**kwargs)
|
||||
self.output_cls: Type[OutputT] = output_cls
|
||||
self.max_retries = max_retries
|
||||
self.output_parser = PydanticOutputParser(output_cls)
|
||||
|
||||
@step
|
||||
async def extract(
|
||||
self, ctx: Context, ev: StartEvent | ValidationErrorEvent
|
||||
) -> StopEvent | ExtractionDone:
|
||||
"""Extract structured data from text using two-step LLM process.
|
||||
|
||||
Step 1 (first call only): TreeSummarize generates text analysis
|
||||
Step 2 (every call): Settings.llm.acomplete formats analysis as JSON
|
||||
"""
|
||||
current_retries = await ctx.store.get("retries", default=0)
|
||||
await ctx.store.set("retries", current_retries + 1)
|
||||
|
||||
if current_retries >= self.max_retries:
|
||||
last_error = await ctx.store.get("last_error", default=None)
|
||||
logger.error(
|
||||
f"Max retries ({self.max_retries}) reached for {self.output_cls.__name__}"
|
||||
)
|
||||
return StopEvent(result={"error": last_error, "attempts": current_retries})
|
||||
|
||||
if isinstance(ev, StartEvent):
|
||||
# First call: run TreeSummarize to get analysis, store in context
|
||||
prompt = ev.get("prompt")
|
||||
texts = ev.get("texts")
|
||||
tone_name = ev.get("tone_name")
|
||||
if not prompt or not isinstance(texts, list):
|
||||
raise ValueError(
|
||||
"StartEvent must contain 'prompt' (str) and 'texts' (list)"
|
||||
)
|
||||
|
||||
summarizer = TreeSummarize(verbose=False)
|
||||
analysis = await summarizer.aget_response(
|
||||
prompt, texts, tone_name=tone_name
|
||||
)
|
||||
await ctx.store.set("analysis", str(analysis))
|
||||
reflection = ""
|
||||
else:
|
||||
# Retry: reuse analysis from context
|
||||
analysis = await ctx.store.get("analysis")
|
||||
if not analysis:
|
||||
raise RuntimeError("Internal error: analysis not found in context")
|
||||
|
||||
wrong_output = ev.wrong_output
|
||||
if len(wrong_output) > 2000:
|
||||
wrong_output = wrong_output[:2000] + "... [truncated]"
|
||||
reflection = (
|
||||
f"\n\nYour previous response could not be parsed:\n{wrong_output}\n\n"
|
||||
f"Error:\n{ev.error}\n\n"
|
||||
"Please try again. Return ONLY valid JSON matching the schema above, "
|
||||
"with no markdown formatting or extra text."
|
||||
)
|
||||
|
||||
# Step 2: Format analysis as JSON using LLM completion
|
||||
format_instructions = self.output_parser.format(
|
||||
"Please structure the above information in the following JSON format:"
|
||||
)
|
||||
|
||||
json_prompt = STRUCTURED_RESPONSE_PROMPT_TEMPLATE.format(
|
||||
analysis=analysis,
|
||||
format_instructions=format_instructions + reflection,
|
||||
)
|
||||
|
||||
# Network retries handled by OpenAILike (max_retries=3)
|
||||
response = await Settings.llm.acomplete(json_prompt)
|
||||
return ExtractionDone(output=response.text)
|
||||
|
||||
@step
|
||||
async def validate(
|
||||
self, ctx: Context, ev: ExtractionDone
|
||||
) -> StopEvent | ValidationErrorEvent:
|
||||
"""Validate extracted output against Pydantic schema."""
|
||||
raw_output = ev.output
|
||||
retries = await ctx.store.get("retries", default=0)
|
||||
|
||||
try:
|
||||
parsed = self.output_parser.parse(raw_output)
|
||||
if retries > 1:
|
||||
logger.info(
|
||||
f"LLM parse succeeded on attempt {retries}/{self.max_retries} "
|
||||
f"for {self.output_cls.__name__}"
|
||||
)
|
||||
return StopEvent(result={"success": parsed})
|
||||
|
||||
except (ValidationError, ValueError) as e:
|
||||
error_msg = self._format_error(e, raw_output)
|
||||
await ctx.store.set("last_error", error_msg)
|
||||
|
||||
logger.error(
|
||||
f"LLM parse error (attempt {retries}/{self.max_retries}): "
|
||||
f"{type(e).__name__}: {e}\nRaw response: {raw_output[:500]}"
|
||||
)
|
||||
|
||||
return ValidationErrorEvent(
|
||||
error=error_msg,
|
||||
wrong_output=raw_output,
|
||||
)
|
||||
|
||||
def _format_error(self, error: Exception, raw_output: str) -> str:
|
||||
"""Format error for LLM feedback."""
|
||||
if isinstance(error, ValidationError):
|
||||
error_messages = []
|
||||
for err in error.errors():
|
||||
field = ".".join(str(loc) for loc in err["loc"])
|
||||
error_messages.append(f"- {err['msg']} in field '{field}'")
|
||||
return "Schema validation errors:\n" + "\n".join(error_messages)
|
||||
else:
|
||||
return f"Parse error: {str(error)}"
|
||||
|
||||
|
||||
class LLM:
|
||||
def __init__(self, settings, temperature: float = 0.4, max_tokens: int = 2048):
|
||||
self.settings_obj = settings
|
||||
@@ -200,12 +30,11 @@ class LLM:
|
||||
self.temperature = temperature
|
||||
self.max_tokens = max_tokens
|
||||
|
||||
# Configure llamaindex Settings
|
||||
self._configure_llamaindex()
|
||||
|
||||
def _configure_llamaindex(self):
|
||||
"""Configure llamaindex Settings with OpenAILike LLM"""
|
||||
session_id = llm_session_id.get() or f"fallback-{uuid4().hex}"
|
||||
|
||||
Settings.llm = OpenAILike(
|
||||
model=self.model_name,
|
||||
api_base=self.url,
|
||||
@@ -215,7 +44,6 @@ class LLM:
|
||||
is_function_calling_model=False,
|
||||
temperature=self.temperature,
|
||||
max_tokens=self.max_tokens,
|
||||
additional_kwargs={"extra_body": {"litellm_session_id": session_id}},
|
||||
)
|
||||
|
||||
async def get_response(
|
||||
@@ -232,38 +60,44 @@ class LLM:
|
||||
texts: list[str],
|
||||
output_cls: Type[T],
|
||||
tone_name: str | None = None,
|
||||
timeout: int | None = None,
|
||||
) -> T:
|
||||
"""Get structured output from LLM with validation retry via Workflow."""
|
||||
if timeout is None:
|
||||
timeout = self.settings_obj.LLM_STRUCTURED_RESPONSE_TIMEOUT
|
||||
"""Get structured output from LLM for non-function-calling models"""
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
async def run_workflow():
|
||||
workflow = StructuredOutputWorkflow(
|
||||
output_cls=output_cls,
|
||||
max_retries=self.settings_obj.LLM_PARSE_MAX_RETRIES + 1,
|
||||
timeout=timeout,
|
||||
)
|
||||
summarizer = TreeSummarize(verbose=True)
|
||||
response = await summarizer.aget_response(prompt, texts, tone_name=tone_name)
|
||||
|
||||
result = await workflow.run(
|
||||
prompt=prompt,
|
||||
texts=texts,
|
||||
tone_name=tone_name,
|
||||
)
|
||||
output_parser = PydanticOutputParser(output_cls)
|
||||
|
||||
if "error" in result:
|
||||
error_msg = result["error"] or "Max retries exceeded"
|
||||
raise LLMParseError(
|
||||
output_cls=output_cls,
|
||||
error_msg=error_msg,
|
||||
attempts=result.get("attempts", 0),
|
||||
)
|
||||
|
||||
return result["success"]
|
||||
|
||||
return await retry(run_workflow)(
|
||||
retry_attempts=3,
|
||||
retry_backoff_interval=1.0,
|
||||
retry_backoff_max=30.0,
|
||||
retry_ignore_exc_types=(WorkflowTimeoutError,),
|
||||
program = LLMTextCompletionProgram.from_defaults(
|
||||
output_parser=output_parser,
|
||||
prompt_template_str=STRUCTURED_RESPONSE_PROMPT_TEMPLATE,
|
||||
verbose=False,
|
||||
)
|
||||
|
||||
format_instructions = output_parser.format(
|
||||
"Please structure the above information in the following JSON format:"
|
||||
)
|
||||
|
||||
try:
|
||||
output = await program.acall(
|
||||
analysis=str(response), format_instructions=format_instructions
|
||||
)
|
||||
except ValidationError as e:
|
||||
# Extract the raw JSON from the error details
|
||||
errors = e.errors()
|
||||
if errors and "input" in errors[0]:
|
||||
raw_json = errors[0]["input"]
|
||||
logger.error(
|
||||
f"JSON validation failed for {output_cls.__name__}. "
|
||||
f"Full raw JSON output:\n{raw_json}\n"
|
||||
f"Validation errors: {errors}"
|
||||
)
|
||||
else:
|
||||
logger.error(
|
||||
f"JSON validation failed for {output_cls.__name__}. "
|
||||
f"Validation errors: {errors}"
|
||||
)
|
||||
raise
|
||||
|
||||
return output
|
||||
|
||||
@@ -309,7 +309,6 @@ class PipelineMainFile(PipelineMainBase):
|
||||
transcript,
|
||||
on_long_summary_callback=self.on_long_summary,
|
||||
on_short_summary_callback=self.on_short_summary,
|
||||
on_action_items_callback=self.on_action_items,
|
||||
empty_pipeline=self.empty_pipeline,
|
||||
logger=self.logger,
|
||||
)
|
||||
@@ -341,6 +340,7 @@ async def task_send_webhook_if_needed(*, transcript_id: str):
|
||||
@asynctask
|
||||
async def task_pipeline_file_process(*, transcript_id: str):
|
||||
"""Celery task for file pipeline processing"""
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(transcript_id)
|
||||
if not transcript:
|
||||
raise Exception(f"Transcript {transcript_id} not found")
|
||||
|
||||
@@ -27,7 +27,6 @@ from reflector.db.recordings import recordings_controller
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.db.transcripts import (
|
||||
Transcript,
|
||||
TranscriptActionItems,
|
||||
TranscriptDuration,
|
||||
TranscriptFinalLongSummary,
|
||||
TranscriptFinalShortSummary,
|
||||
@@ -307,23 +306,6 @@ class PipelineMainBase(PipelineRunner[PipelineMessage], Generic[PipelineMessage]
|
||||
data=final_short_summary,
|
||||
)
|
||||
|
||||
@broadcast_to_sockets
|
||||
async def on_action_items(self, data):
|
||||
action_items = TranscriptActionItems(action_items=data.action_items)
|
||||
async with self.transaction():
|
||||
transcript = await self.get_transcript()
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"action_items": action_items.action_items,
|
||||
},
|
||||
)
|
||||
return await transcripts_controller.append_event(
|
||||
transcript=transcript,
|
||||
event="ACTION_ITEMS",
|
||||
data=action_items,
|
||||
)
|
||||
|
||||
@broadcast_to_sockets
|
||||
async def on_duration(self, data):
|
||||
async with self.transaction():
|
||||
@@ -483,7 +465,6 @@ class PipelineMainFinalSummaries(PipelineMainFromTopics):
|
||||
transcript=self._transcript,
|
||||
callback=self.on_long_summary,
|
||||
on_short_summary=self.on_short_summary,
|
||||
on_action_items=self.on_action_items,
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
@@ -9,10 +9,7 @@ from av.audio.resampler import AudioResampler
|
||||
from celery import chain, shared_task
|
||||
|
||||
from reflector.asynctask import asynctask
|
||||
from reflector.dailyco_api import MeetingParticipantsResponse
|
||||
from reflector.db.transcripts import (
|
||||
Transcript,
|
||||
TranscriptParticipant,
|
||||
TranscriptStatus,
|
||||
TranscriptWaveform,
|
||||
transcripts_controller,
|
||||
@@ -32,12 +29,7 @@ from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
|
||||
from reflector.processors.types import TitleSummary
|
||||
from reflector.processors.types import Transcript as TranscriptType
|
||||
from reflector.storage import Storage, get_transcripts_storage
|
||||
from reflector.utils.daily import (
|
||||
filter_cam_audio_tracks,
|
||||
parse_daily_recording_filename,
|
||||
)
|
||||
from reflector.utils.string import NonEmptyString
|
||||
from reflector.video_platforms.factory import create_platform_client
|
||||
|
||||
# Audio encoding constants
|
||||
OPUS_STANDARD_SAMPLE_RATE = 48000
|
||||
@@ -422,15 +414,7 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
# Open all containers with cleanup guaranteed
|
||||
for i, url in enumerate(valid_track_urls):
|
||||
try:
|
||||
c = av.open(
|
||||
url,
|
||||
options={
|
||||
# it's trying to stream from s3 by default
|
||||
"reconnect": "1",
|
||||
"reconnect_streamed": "1",
|
||||
"reconnect_delay_max": "5",
|
||||
},
|
||||
)
|
||||
c = av.open(url)
|
||||
containers.append(c)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
@@ -459,8 +443,6 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
# causes stream to move on / unclogs memory
|
||||
inputs[i].push(None)
|
||||
continue
|
||||
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
@@ -480,6 +462,8 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
await writer.push(mixed)
|
||||
|
||||
for in_ctx in inputs:
|
||||
in_ctx.push(None)
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
@@ -510,90 +494,6 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
transcript=transcript, event="WAVEFORM", data=waveform
|
||||
)
|
||||
|
||||
async def update_participants_from_daily(
|
||||
self, transcript: Transcript, track_keys: list[str]
|
||||
) -> None:
|
||||
"""Update transcript participants with user_id and names from Daily.co API."""
|
||||
if not transcript.recording_id:
|
||||
return
|
||||
|
||||
try:
|
||||
async with create_platform_client("daily") as daily_client:
|
||||
id_to_name = {}
|
||||
id_to_user_id = {}
|
||||
|
||||
try:
|
||||
rec_details = await daily_client.get_recording(
|
||||
transcript.recording_id
|
||||
)
|
||||
mtg_session_id = rec_details.mtgSessionId
|
||||
if mtg_session_id:
|
||||
try:
|
||||
payload: MeetingParticipantsResponse = (
|
||||
await daily_client.get_meeting_participants(
|
||||
mtg_session_id
|
||||
)
|
||||
)
|
||||
for p in payload.data:
|
||||
pid = p.participant_id
|
||||
name = p.user_name
|
||||
user_id = p.user_id
|
||||
if name:
|
||||
id_to_name[pid] = name
|
||||
if user_id:
|
||||
id_to_user_id[pid] = user_id
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Failed to fetch Daily meeting participants",
|
||||
error=str(e),
|
||||
mtg_session_id=mtg_session_id,
|
||||
exc_info=True,
|
||||
)
|
||||
else:
|
||||
self.logger.warning(
|
||||
"No mtgSessionId found for recording; participant names may be generic",
|
||||
recording_id=transcript.recording_id,
|
||||
)
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Failed to fetch Daily recording details",
|
||||
error=str(e),
|
||||
recording_id=transcript.recording_id,
|
||||
exc_info=True,
|
||||
)
|
||||
return
|
||||
|
||||
cam_audio_keys = filter_cam_audio_tracks(track_keys)
|
||||
|
||||
for idx, key in enumerate(cam_audio_keys):
|
||||
try:
|
||||
parsed = parse_daily_recording_filename(key)
|
||||
participant_id = parsed.participant_id
|
||||
except ValueError as e:
|
||||
self.logger.error(
|
||||
"Failed to parse Daily recording filename",
|
||||
error=str(e),
|
||||
key=key,
|
||||
exc_info=True,
|
||||
)
|
||||
continue
|
||||
|
||||
default_name = f"Speaker {idx}"
|
||||
name = id_to_name.get(participant_id, default_name)
|
||||
user_id = id_to_user_id.get(participant_id)
|
||||
|
||||
participant = TranscriptParticipant(
|
||||
id=participant_id, speaker=idx, name=name, user_id=user_id
|
||||
)
|
||||
await transcripts_controller.upsert_participant(
|
||||
transcript, participant
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
self.logger.warning(
|
||||
"Failed to map participant names", error=str(e), exc_info=True
|
||||
)
|
||||
|
||||
async def process(self, bucket_name: str, track_keys: list[str]):
|
||||
transcript = await self.get_transcript()
|
||||
async with self.transaction():
|
||||
@@ -602,12 +502,9 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
{
|
||||
"events": [],
|
||||
"topics": [],
|
||||
"participants": [],
|
||||
},
|
||||
)
|
||||
|
||||
await self.update_participants_from_daily(transcript, track_keys)
|
||||
|
||||
source_storage = get_transcripts_storage()
|
||||
transcript_storage = source_storage
|
||||
|
||||
@@ -772,7 +669,6 @@ class PipelineMainMultitrack(PipelineMainBase):
|
||||
transcript,
|
||||
on_long_summary_callback=self.on_long_summary,
|
||||
on_short_summary_callback=self.on_short_summary,
|
||||
on_action_items_callback=self.on_action_items,
|
||||
empty_pipeline=self.empty_pipeline,
|
||||
logger=self.logger,
|
||||
)
|
||||
|
||||
@@ -89,7 +89,6 @@ async def generate_summaries(
|
||||
*,
|
||||
on_long_summary_callback: Callable,
|
||||
on_short_summary_callback: Callable,
|
||||
on_action_items_callback: Callable,
|
||||
empty_pipeline: EmptyPipeline,
|
||||
logger: structlog.BoundLogger,
|
||||
):
|
||||
@@ -97,14 +96,11 @@ async def generate_summaries(
|
||||
logger.warning("No topics for summary generation")
|
||||
return
|
||||
|
||||
processor_kwargs = {
|
||||
"transcript": transcript,
|
||||
"callback": on_long_summary_callback,
|
||||
"on_short_summary": on_short_summary_callback,
|
||||
"on_action_items": on_action_items_callback,
|
||||
}
|
||||
|
||||
processor = TranscriptFinalSummaryProcessor(**processor_kwargs)
|
||||
processor = TranscriptFinalSummaryProcessor(
|
||||
transcript=transcript,
|
||||
callback=on_long_summary_callback,
|
||||
on_short_summary=on_short_summary_callback,
|
||||
)
|
||||
processor.set_pipeline(empty_pipeline)
|
||||
|
||||
for topic in topics:
|
||||
|
||||
@@ -96,36 +96,6 @@ RECAP_PROMPT = dedent(
|
||||
"""
|
||||
).strip()
|
||||
|
||||
ACTION_ITEMS_PROMPT = dedent(
|
||||
"""
|
||||
Identify action items from this meeting transcript. Your goal is to identify what was decided and what needs to happen next.
|
||||
|
||||
Look for:
|
||||
|
||||
1. **Decisions Made**: Any decisions, choices, or conclusions reached during the meeting. For each decision:
|
||||
- What was decided? (be specific)
|
||||
- Who made the decision or was involved? (use actual participant names)
|
||||
- Why was this decision made? (key factors, reasoning, or rationale)
|
||||
|
||||
2. **Next Steps / Action Items**: Any tasks, follow-ups, or actions that were mentioned or assigned. For each action item:
|
||||
- What specific task needs to be done? (be concrete and actionable)
|
||||
- Who is responsible? (use actual participant names if mentioned, or "team" if unclear)
|
||||
- When is it due? (any deadlines, timeframes, or "by next meeting" type commitments)
|
||||
- What context is needed? (any additional details that help understand the task)
|
||||
|
||||
Guidelines:
|
||||
- Be thorough and identify all action items, even if they seem minor
|
||||
- Include items that were agreed upon, assigned, or committed to
|
||||
- Include decisions even if they seem obvious or implicit
|
||||
- If someone says "I'll do X" or "We should do Y", that's an action item
|
||||
- If someone says "Let's go with option A", that's a decision
|
||||
- Use the exact participant names from the transcript
|
||||
- If no participant name is mentioned, you can leave assigned_to/decided_by as null
|
||||
|
||||
Only return empty lists if the transcript contains NO decisions and NO action items whatsoever.
|
||||
"""
|
||||
).strip()
|
||||
|
||||
STRUCTURED_RESPONSE_PROMPT_TEMPLATE = dedent(
|
||||
"""
|
||||
Based on the following analysis, provide the information in the requested JSON format:
|
||||
@@ -185,53 +155,6 @@ class SubjectsResponse(BaseModel):
|
||||
)
|
||||
|
||||
|
||||
class ActionItem(BaseModel):
|
||||
"""A single action item from the meeting"""
|
||||
|
||||
task: str = Field(description="The task or action item to be completed")
|
||||
assigned_to: str | None = Field(
|
||||
default=None, description="Person or team assigned to this task (name)"
|
||||
)
|
||||
assigned_to_participant_id: str | None = Field(
|
||||
default=None, description="Participant ID if assigned_to matches a participant"
|
||||
)
|
||||
deadline: str | None = Field(
|
||||
default=None, description="Deadline or timeframe mentioned for this task"
|
||||
)
|
||||
context: str | None = Field(
|
||||
default=None, description="Additional context or notes about this task"
|
||||
)
|
||||
|
||||
|
||||
class Decision(BaseModel):
|
||||
"""A decision made during the meeting"""
|
||||
|
||||
decision: str = Field(description="What was decided")
|
||||
rationale: str | None = Field(
|
||||
default=None,
|
||||
description="Reasoning or key factors that influenced this decision",
|
||||
)
|
||||
decided_by: str | None = Field(
|
||||
default=None, description="Person or group who made the decision (name)"
|
||||
)
|
||||
decided_by_participant_id: str | None = Field(
|
||||
default=None, description="Participant ID if decided_by matches a participant"
|
||||
)
|
||||
|
||||
|
||||
class ActionItemsResponse(BaseModel):
|
||||
"""Pydantic model for identified action items"""
|
||||
|
||||
decisions: list[Decision] = Field(
|
||||
default_factory=list,
|
||||
description="List of decisions made during the meeting",
|
||||
)
|
||||
next_steps: list[ActionItem] = Field(
|
||||
default_factory=list,
|
||||
description="List of action items and next steps to be taken",
|
||||
)
|
||||
|
||||
|
||||
class SummaryBuilder:
|
||||
def __init__(self, llm: LLM, filename: str | None = None, logger=None) -> None:
|
||||
self.transcript: str | None = None
|
||||
@@ -243,8 +166,6 @@ class SummaryBuilder:
|
||||
self.model_name: str = llm.model_name
|
||||
self.logger = logger or structlog.get_logger()
|
||||
self.participant_instructions: str | None = None
|
||||
self.action_items: ActionItemsResponse | None = None
|
||||
self.participant_name_to_id: dict[str, str] = {}
|
||||
if filename:
|
||||
self.read_transcript_from_file(filename)
|
||||
|
||||
@@ -268,20 +189,13 @@ class SummaryBuilder:
|
||||
self.llm = llm
|
||||
|
||||
async def _get_structured_response(
|
||||
self,
|
||||
prompt: str,
|
||||
output_cls: Type[T],
|
||||
tone_name: str | None = None,
|
||||
timeout: int | None = None,
|
||||
self, prompt: str, output_cls: Type[T], tone_name: str | None = None
|
||||
) -> T:
|
||||
"""Generic function to get structured output from LLM for non-function-calling models."""
|
||||
# Add participant instructions to the prompt if available
|
||||
enhanced_prompt = self._enhance_prompt_with_participants(prompt)
|
||||
return await self.llm.get_structured_response(
|
||||
enhanced_prompt,
|
||||
[self.transcript],
|
||||
output_cls,
|
||||
tone_name=tone_name,
|
||||
timeout=timeout,
|
||||
enhanced_prompt, [self.transcript], output_cls, tone_name=tone_name
|
||||
)
|
||||
|
||||
async def _get_response(
|
||||
@@ -302,19 +216,11 @@ class SummaryBuilder:
|
||||
# Participants
|
||||
# ----------------------------------------------------------------------------
|
||||
|
||||
def set_known_participants(
|
||||
self,
|
||||
participants: list[str],
|
||||
participant_name_to_id: dict[str, str] | None = None,
|
||||
) -> None:
|
||||
def set_known_participants(self, participants: list[str]) -> None:
|
||||
"""
|
||||
Set known participants directly without LLM identification.
|
||||
This is used when participants are already identified and stored.
|
||||
They are appended at the end of the transcript, providing more context for the assistant.
|
||||
|
||||
Args:
|
||||
participants: List of participant names
|
||||
participant_name_to_id: Optional mapping of participant names to their IDs
|
||||
"""
|
||||
if not participants:
|
||||
self.logger.warning("No participants provided")
|
||||
@@ -325,12 +231,10 @@ class SummaryBuilder:
|
||||
participants=participants,
|
||||
)
|
||||
|
||||
if participant_name_to_id:
|
||||
self.participant_name_to_id = participant_name_to_id
|
||||
|
||||
participants_md = self.format_list_md(participants)
|
||||
self.transcript += f"\n\n# Participants\n\n{participants_md}"
|
||||
|
||||
# Set instructions that will be automatically added to all prompts
|
||||
participants_list = ", ".join(participants)
|
||||
self.participant_instructions = dedent(
|
||||
f"""
|
||||
@@ -509,92 +413,6 @@ class SummaryBuilder:
|
||||
self.recap = str(recap_response)
|
||||
self.logger.info(f"Quick recap: {self.recap}")
|
||||
|
||||
def _map_participant_names_to_ids(
|
||||
self, response: ActionItemsResponse
|
||||
) -> ActionItemsResponse:
|
||||
"""Map participant names in action items to participant IDs."""
|
||||
if not self.participant_name_to_id:
|
||||
return response
|
||||
|
||||
decisions = []
|
||||
for decision in response.decisions:
|
||||
new_decision = decision.model_copy()
|
||||
if (
|
||||
decision.decided_by
|
||||
and decision.decided_by in self.participant_name_to_id
|
||||
):
|
||||
new_decision.decided_by_participant_id = self.participant_name_to_id[
|
||||
decision.decided_by
|
||||
]
|
||||
decisions.append(new_decision)
|
||||
|
||||
next_steps = []
|
||||
for item in response.next_steps:
|
||||
new_item = item.model_copy()
|
||||
if item.assigned_to and item.assigned_to in self.participant_name_to_id:
|
||||
new_item.assigned_to_participant_id = self.participant_name_to_id[
|
||||
item.assigned_to
|
||||
]
|
||||
next_steps.append(new_item)
|
||||
|
||||
return ActionItemsResponse(decisions=decisions, next_steps=next_steps)
|
||||
|
||||
async def identify_action_items(self) -> ActionItemsResponse | None:
|
||||
"""Identify action items (decisions and next steps) from the transcript."""
|
||||
self.logger.info("--- identify action items using TreeSummarize")
|
||||
|
||||
if not self.transcript:
|
||||
self.logger.warning(
|
||||
"No transcript available for action items identification"
|
||||
)
|
||||
self.action_items = None
|
||||
return None
|
||||
|
||||
action_items_prompt = ACTION_ITEMS_PROMPT
|
||||
|
||||
try:
|
||||
response = await self._get_structured_response(
|
||||
action_items_prompt,
|
||||
ActionItemsResponse,
|
||||
tone_name="Action item identifier",
|
||||
timeout=settings.LLM_STRUCTURED_RESPONSE_TIMEOUT,
|
||||
)
|
||||
|
||||
response = self._map_participant_names_to_ids(response)
|
||||
|
||||
self.action_items = response
|
||||
self.logger.info(
|
||||
f"Identified {len(response.decisions)} decisions and {len(response.next_steps)} action items",
|
||||
decisions_count=len(response.decisions),
|
||||
next_steps_count=len(response.next_steps),
|
||||
)
|
||||
|
||||
if response.decisions:
|
||||
self.logger.debug(
|
||||
"Decisions identified",
|
||||
decisions=[d.decision for d in response.decisions],
|
||||
)
|
||||
if response.next_steps:
|
||||
self.logger.debug(
|
||||
"Action items identified",
|
||||
tasks=[item.task for item in response.next_steps],
|
||||
)
|
||||
if not response.decisions and not response.next_steps:
|
||||
self.logger.warning(
|
||||
"No action items identified from transcript",
|
||||
transcript_length=len(self.transcript),
|
||||
)
|
||||
|
||||
return response
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
f"Error identifying action items: {e}",
|
||||
exc_info=True,
|
||||
)
|
||||
self.action_items = None
|
||||
return None
|
||||
|
||||
async def generate_summary(self, only_subjects: bool = False) -> None:
|
||||
"""
|
||||
Generate summary by extracting subjects, creating summaries for each, and generating a recap.
|
||||
@@ -606,7 +424,6 @@ class SummaryBuilder:
|
||||
|
||||
await self.generate_subject_summaries()
|
||||
await self.generate_recap()
|
||||
await self.identify_action_items()
|
||||
|
||||
# ----------------------------------------------------------------------------
|
||||
# Markdown
|
||||
@@ -709,6 +526,8 @@ if __name__ == "__main__":
|
||||
if args.summary:
|
||||
await sm.generate_summary()
|
||||
|
||||
# Note: action items generation has been removed
|
||||
|
||||
print("")
|
||||
print("-" * 80)
|
||||
print("")
|
||||
|
||||
@@ -1,12 +1,7 @@
|
||||
from reflector.llm import LLM
|
||||
from reflector.processors.base import Processor
|
||||
from reflector.processors.summary.summary_builder import SummaryBuilder
|
||||
from reflector.processors.types import (
|
||||
ActionItems,
|
||||
FinalLongSummary,
|
||||
FinalShortSummary,
|
||||
TitleSummary,
|
||||
)
|
||||
from reflector.processors.types import FinalLongSummary, FinalShortSummary, TitleSummary
|
||||
from reflector.settings import settings
|
||||
|
||||
|
||||
@@ -32,20 +27,15 @@ class TranscriptFinalSummaryProcessor(Processor):
|
||||
builder = SummaryBuilder(self.llm, logger=self.logger)
|
||||
builder.set_transcript(text)
|
||||
|
||||
# Use known participants if available, otherwise identify them
|
||||
if self.transcript and self.transcript.participants:
|
||||
# Extract participant names from the stored participants
|
||||
participant_names = [p.name for p in self.transcript.participants if p.name]
|
||||
if participant_names:
|
||||
self.logger.info(
|
||||
f"Using {len(participant_names)} known participants from transcript"
|
||||
)
|
||||
participant_name_to_id = {
|
||||
p.name: p.id
|
||||
for p in self.transcript.participants
|
||||
if p.name and p.id
|
||||
}
|
||||
builder.set_known_participants(
|
||||
participant_names, participant_name_to_id=participant_name_to_id
|
||||
)
|
||||
builder.set_known_participants(participant_names)
|
||||
else:
|
||||
self.logger.info(
|
||||
"Participants field exists but is empty, identifying participants"
|
||||
@@ -73,6 +63,7 @@ class TranscriptFinalSummaryProcessor(Processor):
|
||||
self.logger.warning("No summary to output")
|
||||
return
|
||||
|
||||
# build the speakermap from the transcript
|
||||
speakermap = {}
|
||||
if self.transcript:
|
||||
speakermap = {
|
||||
@@ -85,6 +76,8 @@ class TranscriptFinalSummaryProcessor(Processor):
|
||||
speakermap=speakermap,
|
||||
)
|
||||
|
||||
# build the transcript as a single string
|
||||
# Replace speaker IDs with actual participant names if available
|
||||
text_transcript = []
|
||||
unique_speakers = set()
|
||||
for topic in self.chunks:
|
||||
@@ -118,9 +111,4 @@ class TranscriptFinalSummaryProcessor(Processor):
|
||||
)
|
||||
await self.emit(final_short_summary, name="short_summary")
|
||||
|
||||
if self.builder and self.builder.action_items:
|
||||
action_items = self.builder.action_items.model_dump()
|
||||
action_items = ActionItems(action_items=action_items)
|
||||
await self.emit(action_items, name="action_items")
|
||||
|
||||
await self.emit(final_long_summary)
|
||||
|
||||
@@ -78,11 +78,7 @@ class TranscriptTopicDetectorProcessor(Processor):
|
||||
"""
|
||||
prompt = TOPIC_PROMPT.format(text=text)
|
||||
response = await self.llm.get_structured_response(
|
||||
prompt,
|
||||
[text],
|
||||
TopicResponse,
|
||||
tone_name="Topic analyzer",
|
||||
timeout=settings.LLM_STRUCTURED_RESPONSE_TIMEOUT,
|
||||
prompt, [text], TopicResponse, tone_name="Topic analyzer"
|
||||
)
|
||||
return response
|
||||
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
import io
|
||||
import re
|
||||
import tempfile
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
from typing import Annotated, TypedDict
|
||||
|
||||
@@ -17,17 +16,6 @@ class DiarizationSegment(TypedDict):
|
||||
|
||||
|
||||
PUNC_RE = re.compile(r"[.;:?!…]")
|
||||
SENTENCE_END_RE = re.compile(r"[.?!…]$")
|
||||
|
||||
# Max segment length for words_to_segments() - breaks on any punctuation (. ; : ? ! …)
|
||||
# when segment exceeds this limit. Used for non-multitrack recordings.
|
||||
MAX_SEGMENT_CHARS = 120
|
||||
|
||||
# Max segment length for words_to_segments_by_sentence() - only breaks on sentence-ending
|
||||
# punctuation (. ? ! …) when segment exceeds this limit. Higher threshold allows complete
|
||||
# sentences in multitrack recordings where speakers overlap.
|
||||
# similar number to server/reflector/processors/transcript_liner.py
|
||||
MAX_SENTENCE_SEGMENT_CHARS = 1000
|
||||
|
||||
|
||||
class AudioFile(BaseModel):
|
||||
@@ -88,6 +76,7 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
|
||||
# but separate if the speaker changes, or if the punctuation is a . , ; : ? !
|
||||
segments = []
|
||||
current_segment = None
|
||||
MAX_SEGMENT_LENGTH = 120
|
||||
|
||||
for word in words:
|
||||
if current_segment is None:
|
||||
@@ -117,7 +106,7 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
|
||||
current_segment.end = word.end
|
||||
|
||||
have_punc = PUNC_RE.search(word.text)
|
||||
if have_punc and (len(current_segment.text) > MAX_SEGMENT_CHARS):
|
||||
if have_punc and (len(current_segment.text) > MAX_SEGMENT_LENGTH):
|
||||
segments.append(current_segment)
|
||||
current_segment = None
|
||||
|
||||
@@ -127,70 +116,6 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
|
||||
return segments
|
||||
|
||||
|
||||
def words_to_segments_by_sentence(words: list[Word]) -> list[TranscriptSegment]:
|
||||
"""Group words by speaker, then split into sentences.
|
||||
|
||||
For multitrack recordings where words from different speakers are interleaved
|
||||
by timestamp, this function first groups all words by speaker, then creates
|
||||
segments based on sentence boundaries within each speaker's words.
|
||||
|
||||
This produces cleaner output than words_to_segments() which breaks on every
|
||||
speaker change, resulting in many tiny segments when speakers overlap.
|
||||
"""
|
||||
if not words:
|
||||
return []
|
||||
|
||||
# Group words by speaker, preserving order within each speaker
|
||||
by_speaker: dict[int, list[Word]] = defaultdict(list)
|
||||
for w in words:
|
||||
by_speaker[w.speaker].append(w)
|
||||
|
||||
segments: list[TranscriptSegment] = []
|
||||
|
||||
for speaker, speaker_words in by_speaker.items():
|
||||
current_text = ""
|
||||
current_start: float | None = None
|
||||
current_end: float = 0.0
|
||||
|
||||
for word in speaker_words:
|
||||
if current_start is None:
|
||||
current_start = word.start
|
||||
|
||||
current_text += word.text
|
||||
current_end = word.end
|
||||
|
||||
# Check for sentence end or max length
|
||||
is_sentence_end = SENTENCE_END_RE.search(word.text.strip())
|
||||
is_too_long = len(current_text) >= MAX_SENTENCE_SEGMENT_CHARS
|
||||
|
||||
if is_sentence_end or is_too_long:
|
||||
segments.append(
|
||||
TranscriptSegment(
|
||||
text=current_text,
|
||||
start=current_start,
|
||||
end=current_end,
|
||||
speaker=speaker,
|
||||
)
|
||||
)
|
||||
current_text = ""
|
||||
current_start = None
|
||||
|
||||
# Flush remaining words for this speaker
|
||||
if current_text and current_start is not None:
|
||||
segments.append(
|
||||
TranscriptSegment(
|
||||
text=current_text,
|
||||
start=current_start,
|
||||
end=current_end,
|
||||
speaker=speaker,
|
||||
)
|
||||
)
|
||||
|
||||
# Sort segments by start time
|
||||
segments.sort(key=lambda s: s.start)
|
||||
return segments
|
||||
|
||||
|
||||
class Transcript(BaseModel):
|
||||
translation: str | None = None
|
||||
words: list[Word] = []
|
||||
@@ -229,9 +154,7 @@ class Transcript(BaseModel):
|
||||
word.start += offset
|
||||
word.end += offset
|
||||
|
||||
def as_segments(self, is_multitrack: bool = False) -> list[TranscriptSegment]:
|
||||
if is_multitrack:
|
||||
return words_to_segments_by_sentence(self.words)
|
||||
def as_segments(self) -> list[TranscriptSegment]:
|
||||
return words_to_segments(self.words)
|
||||
|
||||
|
||||
@@ -264,10 +187,6 @@ class FinalShortSummary(BaseModel):
|
||||
duration: float
|
||||
|
||||
|
||||
class ActionItems(BaseModel):
|
||||
action_items: dict # JSON-serializable dict from ActionItemsResponse
|
||||
|
||||
|
||||
class FinalTitle(BaseModel):
|
||||
title: str
|
||||
|
||||
|
||||
@@ -1,17 +0,0 @@
|
||||
"""Schema definitions for transcript format types and segments."""
|
||||
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
TranscriptFormat = Literal["text", "text-timestamped", "webvtt-named", "json"]
|
||||
|
||||
|
||||
class TranscriptSegment(BaseModel):
|
||||
"""A single transcript segment with speaker and timing information."""
|
||||
|
||||
speaker: int
|
||||
speaker_name: str
|
||||
text: str
|
||||
start: float
|
||||
end: float
|
||||
@@ -7,7 +7,7 @@ This module provides result-based error handling that works in both contexts:
|
||||
"""
|
||||
|
||||
from dataclasses import dataclass
|
||||
from typing import Literal, Union, assert_never
|
||||
from typing import Literal, Union
|
||||
|
||||
import celery
|
||||
from celery.result import AsyncResult
|
||||
@@ -18,6 +18,7 @@ from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
|
||||
from reflector.pipelines.main_multitrack_pipeline import (
|
||||
task_pipeline_multitrack_process,
|
||||
)
|
||||
from reflector.utils.match import absurd
|
||||
from reflector.utils.string import NonEmptyString
|
||||
|
||||
|
||||
@@ -154,16 +155,13 @@ def dispatch_transcript_processing(config: ProcessingConfig) -> AsyncResult:
|
||||
elif isinstance(config, FileProcessingConfig):
|
||||
return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
|
||||
else:
|
||||
assert_never(config)
|
||||
absurd(config)
|
||||
|
||||
|
||||
def task_is_scheduled_or_active(task_name: str, **kwargs):
|
||||
inspect = celery.current_app.control.inspect()
|
||||
|
||||
scheduled = inspect.scheduled() or {}
|
||||
active = inspect.active() or {}
|
||||
all = scheduled | active
|
||||
for worker, tasks in all.items():
|
||||
for worker, tasks in (inspect.scheduled() | inspect.active()).items():
|
||||
for task in tasks:
|
||||
if task["name"] == task_name and task["kwargs"] == kwargs:
|
||||
return True
|
||||
|
||||
@@ -74,13 +74,6 @@ class Settings(BaseSettings):
|
||||
LLM_API_KEY: str | None = None
|
||||
LLM_CONTEXT_WINDOW: int = 16000
|
||||
|
||||
LLM_PARSE_MAX_RETRIES: int = (
|
||||
3 # Max retries for JSON/validation errors (total attempts = retries + 1)
|
||||
)
|
||||
LLM_STRUCTURED_RESPONSE_TIMEOUT: int = (
|
||||
300 # Timeout in seconds for structured responses (5 minutes)
|
||||
)
|
||||
|
||||
# Diarization
|
||||
DIARIZATION_ENABLED: bool = True
|
||||
DIARIZATION_BACKEND: str = "modal"
|
||||
|
||||
@@ -64,11 +64,6 @@ def recording_lock_key(recording_id: NonEmptyString) -> NonEmptyString:
|
||||
return f"recording:{recording_id}"
|
||||
|
||||
|
||||
def filter_cam_audio_tracks(track_keys: list[str]) -> list[str]:
|
||||
"""Filter track keys to cam-audio tracks only (skip screen-audio, etc.)."""
|
||||
return [k for k in track_keys if "cam-audio" in k]
|
||||
|
||||
|
||||
def extract_base_room_name(daily_room_name: DailyRoomName) -> NonEmptyString:
|
||||
"""
|
||||
Extract base room name from Daily.co timestamped room name.
|
||||
|
||||
10
server/reflector/utils/match.py
Normal file
10
server/reflector/utils/match.py
Normal file
@@ -0,0 +1,10 @@
|
||||
from typing import NoReturn
|
||||
|
||||
|
||||
def assert_exhaustiveness(x: NoReturn) -> NoReturn:
|
||||
"""Provide an assertion at type-check time that this function is never called."""
|
||||
raise AssertionError(f"Invalid value: {x!r}")
|
||||
|
||||
|
||||
def absurd(x: NoReturn) -> NoReturn:
|
||||
return assert_exhaustiveness(x)
|
||||
@@ -1,133 +0,0 @@
|
||||
"""Utilities for converting transcript data to various output formats."""
|
||||
|
||||
import webvtt
|
||||
|
||||
from reflector.db.transcripts import TranscriptParticipant, TranscriptTopic
|
||||
from reflector.processors.types import (
|
||||
Transcript as ProcessorTranscript,
|
||||
)
|
||||
from reflector.schemas.transcript_formats import TranscriptSegment
|
||||
from reflector.utils.webvtt import seconds_to_timestamp
|
||||
|
||||
|
||||
def get_speaker_name(
|
||||
speaker: int, participants: list[TranscriptParticipant] | None
|
||||
) -> str:
|
||||
"""Get participant name for speaker or default to 'Speaker N'."""
|
||||
if participants:
|
||||
for participant in participants:
|
||||
if participant.speaker == speaker:
|
||||
return participant.name
|
||||
return f"Speaker {speaker}"
|
||||
|
||||
|
||||
def format_timestamp_mmss(seconds: float | int) -> str:
|
||||
"""Format seconds as MM:SS timestamp."""
|
||||
minutes = int(seconds // 60)
|
||||
secs = int(seconds % 60)
|
||||
return f"{minutes:02d}:{secs:02d}"
|
||||
|
||||
|
||||
def transcript_to_text(
|
||||
topics: list[TranscriptTopic],
|
||||
participants: list[TranscriptParticipant] | None,
|
||||
is_multitrack: bool = False,
|
||||
) -> str:
|
||||
"""Convert transcript topics to plain text with speaker names."""
|
||||
lines = []
|
||||
for topic in topics:
|
||||
if not topic.words:
|
||||
continue
|
||||
|
||||
transcript = ProcessorTranscript(words=topic.words)
|
||||
segments = transcript.as_segments(is_multitrack)
|
||||
|
||||
for segment in segments:
|
||||
speaker_name = get_speaker_name(segment.speaker, participants)
|
||||
text = segment.text.strip()
|
||||
lines.append(f"{speaker_name}: {text}")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def transcript_to_text_timestamped(
|
||||
topics: list[TranscriptTopic],
|
||||
participants: list[TranscriptParticipant] | None,
|
||||
is_multitrack: bool = False,
|
||||
) -> str:
|
||||
"""Convert transcript topics to timestamped text with speaker names."""
|
||||
lines = []
|
||||
for topic in topics:
|
||||
if not topic.words:
|
||||
continue
|
||||
|
||||
transcript = ProcessorTranscript(words=topic.words)
|
||||
segments = transcript.as_segments(is_multitrack)
|
||||
|
||||
for segment in segments:
|
||||
speaker_name = get_speaker_name(segment.speaker, participants)
|
||||
timestamp = format_timestamp_mmss(segment.start)
|
||||
text = segment.text.strip()
|
||||
lines.append(f"[{timestamp}] {speaker_name}: {text}")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def topics_to_webvtt_named(
|
||||
topics: list[TranscriptTopic],
|
||||
participants: list[TranscriptParticipant] | None,
|
||||
is_multitrack: bool = False,
|
||||
) -> str:
|
||||
"""Convert transcript topics to WebVTT format with participant names."""
|
||||
vtt = webvtt.WebVTT()
|
||||
|
||||
for topic in topics:
|
||||
if not topic.words:
|
||||
continue
|
||||
|
||||
transcript = ProcessorTranscript(words=topic.words)
|
||||
segments = transcript.as_segments(is_multitrack)
|
||||
|
||||
for segment in segments:
|
||||
speaker_name = get_speaker_name(segment.speaker, participants)
|
||||
text = segment.text.strip()
|
||||
text = f"<v {speaker_name}>{text}"
|
||||
|
||||
caption = webvtt.Caption(
|
||||
start=seconds_to_timestamp(segment.start),
|
||||
end=seconds_to_timestamp(segment.end),
|
||||
text=text,
|
||||
)
|
||||
vtt.captions.append(caption)
|
||||
|
||||
return vtt.content
|
||||
|
||||
|
||||
def transcript_to_json_segments(
|
||||
topics: list[TranscriptTopic],
|
||||
participants: list[TranscriptParticipant] | None,
|
||||
is_multitrack: bool = False,
|
||||
) -> list[TranscriptSegment]:
|
||||
"""Convert transcript topics to a flat list of JSON segments."""
|
||||
result = []
|
||||
|
||||
for topic in topics:
|
||||
if not topic.words:
|
||||
continue
|
||||
|
||||
transcript = ProcessorTranscript(words=topic.words)
|
||||
segments = transcript.as_segments(is_multitrack)
|
||||
|
||||
for segment in segments:
|
||||
speaker_name = get_speaker_name(segment.speaker, participants)
|
||||
result.append(
|
||||
TranscriptSegment(
|
||||
speaker=segment.speaker,
|
||||
speaker_name=speaker_name,
|
||||
text=segment.text.strip(),
|
||||
start=segment.start,
|
||||
end=segment.end,
|
||||
)
|
||||
)
|
||||
|
||||
return result
|
||||
@@ -13,7 +13,7 @@ VttTimestamp = Annotated[str, "vtt_timestamp"]
|
||||
WebVTTStr = Annotated[str, "webvtt_str"]
|
||||
|
||||
|
||||
def seconds_to_timestamp(seconds: Seconds) -> VttTimestamp:
|
||||
def _seconds_to_timestamp(seconds: Seconds) -> VttTimestamp:
|
||||
# lib doesn't do that
|
||||
hours = int(seconds // 3600)
|
||||
minutes = int((seconds % 3600) // 60)
|
||||
@@ -37,8 +37,8 @@ def words_to_webvtt(words: list[Word]) -> WebVTTStr:
|
||||
text = f"<v Speaker{segment.speaker}>{text}"
|
||||
|
||||
caption = webvtt.Caption(
|
||||
start=seconds_to_timestamp(segment.start),
|
||||
end=seconds_to_timestamp(segment.end),
|
||||
start=_seconds_to_timestamp(segment.start),
|
||||
end=_seconds_to_timestamp(segment.end),
|
||||
text=text,
|
||||
)
|
||||
vtt.captions.append(caption)
|
||||
|
||||
@@ -31,7 +31,6 @@ class DailyClient(VideoPlatformClient):
|
||||
PLATFORM_NAME: Platform = "daily"
|
||||
TIMESTAMP_FORMAT = "%Y%m%d%H%M%S"
|
||||
RECORDING_NONE: RecordingType = "none"
|
||||
RECORDING_LOCAL: RecordingType = "local"
|
||||
RECORDING_CLOUD: RecordingType = "cloud"
|
||||
|
||||
def __init__(self, config: VideoPlatformConfig):
|
||||
@@ -55,23 +54,19 @@ class DailyClient(VideoPlatformClient):
|
||||
timestamp = datetime.now().strftime(self.TIMESTAMP_FORMAT)
|
||||
room_name = f"{room_name_prefix}{ROOM_PREFIX_SEPARATOR}{timestamp}"
|
||||
|
||||
enable_recording = None
|
||||
if room.recording_type == self.RECORDING_LOCAL:
|
||||
enable_recording = "local"
|
||||
elif room.recording_type == self.RECORDING_CLOUD:
|
||||
enable_recording = "raw-tracks"
|
||||
|
||||
properties = RoomProperties(
|
||||
enable_recording=enable_recording,
|
||||
enable_recording="raw-tracks"
|
||||
if room.recording_type != self.RECORDING_NONE
|
||||
else False,
|
||||
enable_chat=True,
|
||||
enable_screenshare=True,
|
||||
enable_knocking=room.is_locked,
|
||||
start_video_off=False,
|
||||
start_audio_off=False,
|
||||
exp=int(end_date.timestamp()),
|
||||
)
|
||||
|
||||
if room.recording_type == self.RECORDING_CLOUD:
|
||||
# Only configure recordings_bucket if recording is enabled
|
||||
if room.recording_type != self.RECORDING_NONE:
|
||||
daily_storage = get_dailyco_storage()
|
||||
assert daily_storage.bucket_name, "S3 bucket must be configured"
|
||||
properties.recordings_bucket = RecordingsBucketConfig(
|
||||
@@ -177,18 +172,16 @@ class DailyClient(VideoPlatformClient):
|
||||
async def create_meeting_token(
|
||||
self,
|
||||
room_name: DailyRoomName,
|
||||
start_cloud_recording: bool,
|
||||
enable_recording_ui: bool,
|
||||
user_id: NonEmptyString | None = None,
|
||||
is_owner: bool = False,
|
||||
) -> NonEmptyString:
|
||||
enable_recording: bool,
|
||||
user_id: str | None = None,
|
||||
) -> str:
|
||||
properties = MeetingTokenProperties(
|
||||
room_name=room_name,
|
||||
user_id=user_id,
|
||||
start_cloud_recording=start_cloud_recording,
|
||||
enable_recording_ui=enable_recording_ui,
|
||||
is_owner=is_owner,
|
||||
start_cloud_recording=enable_recording,
|
||||
enable_recording_ui=not enable_recording,
|
||||
)
|
||||
|
||||
request = CreateMeetingTokenRequest(properties=properties)
|
||||
result = await self._api_client.create_meeting_token(request)
|
||||
return result.token
|
||||
|
||||
@@ -89,7 +89,7 @@ class CreateRoom(BaseModel):
|
||||
ics_url: Optional[str] = None
|
||||
ics_fetch_interval: int = 300
|
||||
ics_enabled: bool = False
|
||||
platform: Platform
|
||||
platform: Optional[Platform] = None
|
||||
|
||||
|
||||
class UpdateRoom(BaseModel):
|
||||
@@ -310,22 +310,6 @@ async def rooms_create_meeting(
|
||||
room=room, current_time=current_time
|
||||
)
|
||||
|
||||
if meeting is not None:
|
||||
settings_match = (
|
||||
meeting.is_locked == room.is_locked
|
||||
and meeting.room_mode == room.room_mode
|
||||
and meeting.recording_type == room.recording_type
|
||||
and meeting.recording_trigger == room.recording_trigger
|
||||
and meeting.platform == room.platform
|
||||
)
|
||||
if not settings_match:
|
||||
logger.info(
|
||||
f"Room settings changed for {room_name}, creating new meeting",
|
||||
room_id=room.id,
|
||||
old_meeting_id=meeting.id,
|
||||
)
|
||||
meeting = None
|
||||
|
||||
if meeting is None:
|
||||
end_date = current_time + timedelta(hours=8)
|
||||
|
||||
@@ -565,16 +549,20 @@ async def rooms_join_meeting(
|
||||
if meeting.end_date <= current_time:
|
||||
raise HTTPException(status_code=400, detail="Meeting has ended")
|
||||
|
||||
if meeting.platform == "daily" and user_id is not None:
|
||||
if meeting.platform == "daily":
|
||||
client = create_platform_client(meeting.platform)
|
||||
enable_recording = room.recording_trigger != "none"
|
||||
token = await client.create_meeting_token(
|
||||
meeting.room_name,
|
||||
start_cloud_recording=meeting.recording_type == "cloud",
|
||||
enable_recording_ui=meeting.recording_type == "local",
|
||||
enable_recording=enable_recording,
|
||||
user_id=user_id,
|
||||
is_owner=user_id == room.user_id,
|
||||
)
|
||||
meeting = meeting.model_copy()
|
||||
meeting.room_url = add_query_param(meeting.room_url, "t", token)
|
||||
if meeting.host_room_url:
|
||||
meeting.host_room_url = add_query_param(meeting.host_room_url, "t", token)
|
||||
|
||||
if user_id != room.user_id and meeting.platform == "whereby":
|
||||
meeting.host_room_url = ""
|
||||
|
||||
return meeting
|
||||
|
||||
@@ -1,23 +1,14 @@
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import Annotated, Literal, Optional, assert_never
|
||||
from typing import Annotated, Literal, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query
|
||||
from fastapi_pagination import Page
|
||||
from fastapi_pagination.ext.databases import apaginate
|
||||
from jose import jwt
|
||||
from pydantic import (
|
||||
AwareDatetime,
|
||||
BaseModel,
|
||||
Discriminator,
|
||||
Field,
|
||||
constr,
|
||||
field_serializer,
|
||||
)
|
||||
from pydantic import AwareDatetime, BaseModel, Field, constr, field_serializer
|
||||
|
||||
import reflector.auth as auth
|
||||
from reflector.db import get_database
|
||||
from reflector.db.recordings import recordings_controller
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.db.search import (
|
||||
DEFAULT_SEARCH_LIMIT,
|
||||
SearchLimit,
|
||||
@@ -38,17 +29,9 @@ from reflector.db.transcripts import (
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.db.users import user_controller
|
||||
from reflector.processors.types import Transcript as ProcessorTranscript
|
||||
from reflector.processors.types import Word
|
||||
from reflector.schemas.transcript_formats import TranscriptFormat, TranscriptSegment
|
||||
from reflector.settings import settings
|
||||
from reflector.utils.transcript_formats import (
|
||||
topics_to_webvtt_named,
|
||||
transcript_to_json_segments,
|
||||
transcript_to_text,
|
||||
transcript_to_text_timestamped,
|
||||
)
|
||||
from reflector.ws_manager import get_ws_manager
|
||||
from reflector.zulip import (
|
||||
InvalidMessageError,
|
||||
@@ -63,14 +46,6 @@ ALGORITHM = "HS256"
|
||||
DOWNLOAD_EXPIRE_MINUTES = 60
|
||||
|
||||
|
||||
async def _get_is_multitrack(transcript) -> bool:
|
||||
"""Detect if transcript is from multitrack recording."""
|
||||
if not transcript.recording_id:
|
||||
return False
|
||||
recording = await recordings_controller.get_by_id(transcript.recording_id)
|
||||
return recording is not None and recording.is_multitrack
|
||||
|
||||
|
||||
def create_access_token(data: dict, expires_delta: timedelta):
|
||||
to_encode = data.copy()
|
||||
expire = datetime.now(timezone.utc) + expires_delta
|
||||
@@ -113,86 +88,8 @@ class GetTranscriptMinimal(BaseModel):
|
||||
audio_deleted: bool | None = None
|
||||
|
||||
|
||||
class TranscriptParticipantWithEmail(TranscriptParticipant):
|
||||
email: str | None = None
|
||||
|
||||
|
||||
class GetTranscriptWithParticipants(GetTranscriptMinimal):
|
||||
participants: list[TranscriptParticipantWithEmail] | None
|
||||
|
||||
|
||||
class GetTranscriptWithText(GetTranscriptWithParticipants):
|
||||
"""
|
||||
Transcript response with plain text format.
|
||||
|
||||
Format: Speaker names followed by their dialogue, one line per segment.
|
||||
Example:
|
||||
John Smith: Hello everyone
|
||||
Jane Doe: Hi there
|
||||
"""
|
||||
|
||||
transcript_format: Literal["text"] = "text"
|
||||
transcript: str
|
||||
|
||||
|
||||
class GetTranscriptWithTextTimestamped(GetTranscriptWithParticipants):
|
||||
"""
|
||||
Transcript response with timestamped text format.
|
||||
|
||||
Format: [MM:SS] timestamp prefix before each speaker and dialogue.
|
||||
Example:
|
||||
[00:00] John Smith: Hello everyone
|
||||
[00:05] Jane Doe: Hi there
|
||||
"""
|
||||
|
||||
transcript_format: Literal["text-timestamped"] = "text-timestamped"
|
||||
transcript: str
|
||||
|
||||
|
||||
class GetTranscriptWithWebVTTNamed(GetTranscriptWithParticipants):
|
||||
"""
|
||||
Transcript response in WebVTT subtitle format with participant names.
|
||||
|
||||
Format: Standard WebVTT with voice tags using participant names.
|
||||
Example:
|
||||
WEBVTT
|
||||
|
||||
00:00:00.000 --> 00:00:05.000
|
||||
<v John Smith>Hello everyone
|
||||
"""
|
||||
|
||||
transcript_format: Literal["webvtt-named"] = "webvtt-named"
|
||||
transcript: str
|
||||
|
||||
|
||||
class GetTranscriptWithJSON(GetTranscriptWithParticipants):
|
||||
"""
|
||||
Transcript response as structured JSON segments.
|
||||
|
||||
Format: Array of segment objects with speaker info, text, and timing.
|
||||
Example:
|
||||
[
|
||||
{
|
||||
"speaker": 0,
|
||||
"speaker_name": "John Smith",
|
||||
"text": "Hello everyone",
|
||||
"start": 0.0,
|
||||
"end": 5.0
|
||||
}
|
||||
]
|
||||
"""
|
||||
|
||||
transcript_format: Literal["json"] = "json"
|
||||
transcript: list[TranscriptSegment]
|
||||
|
||||
|
||||
GetTranscript = Annotated[
|
||||
GetTranscriptWithText
|
||||
| GetTranscriptWithTextTimestamped
|
||||
| GetTranscriptWithWebVTTNamed
|
||||
| GetTranscriptWithJSON,
|
||||
Discriminator("transcript_format"),
|
||||
]
|
||||
class GetTranscript(GetTranscriptMinimal):
|
||||
participants: list[TranscriptParticipant] | None
|
||||
|
||||
|
||||
class CreateTranscript(BaseModel):
|
||||
@@ -331,7 +228,7 @@ async def transcripts_search(
|
||||
)
|
||||
|
||||
|
||||
@router.post("/transcripts", response_model=GetTranscriptWithParticipants)
|
||||
@router.post("/transcripts", response_model=GetTranscript)
|
||||
async def transcripts_create(
|
||||
info: CreateTranscript,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
@@ -375,7 +272,7 @@ class GetTranscriptTopic(BaseModel):
|
||||
segments: list[GetTranscriptSegmentTopic] = []
|
||||
|
||||
@classmethod
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic):
|
||||
if not topic.words:
|
||||
# In previous version, words were missing
|
||||
# Just output a segment with speaker 0
|
||||
@@ -399,7 +296,7 @@ class GetTranscriptTopic(BaseModel):
|
||||
start=segment.start,
|
||||
speaker=segment.speaker,
|
||||
)
|
||||
for segment in transcript.as_segments(is_multitrack)
|
||||
for segment in transcript.as_segments()
|
||||
]
|
||||
return cls(
|
||||
id=topic.id,
|
||||
@@ -416,8 +313,8 @@ class GetTranscriptTopicWithWords(GetTranscriptTopic):
|
||||
words: list[Word] = []
|
||||
|
||||
@classmethod
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
|
||||
instance = super().from_transcript_topic(topic, is_multitrack)
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic):
|
||||
instance = super().from_transcript_topic(topic)
|
||||
if topic.words:
|
||||
instance.words = topic.words
|
||||
return instance
|
||||
@@ -432,8 +329,8 @@ class GetTranscriptTopicWithWordsPerSpeaker(GetTranscriptTopic):
|
||||
words_per_speaker: list[SpeakerWords] = []
|
||||
|
||||
@classmethod
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
|
||||
instance = super().from_transcript_topic(topic, is_multitrack)
|
||||
def from_transcript_topic(cls, topic: TranscriptTopic):
|
||||
instance = super().from_transcript_topic(topic)
|
||||
if topic.words:
|
||||
words_per_speakers = []
|
||||
# group words by speaker
|
||||
@@ -465,95 +362,14 @@ class GetTranscriptTopicWithWordsPerSpeaker(GetTranscriptTopic):
|
||||
async def transcript_get(
|
||||
transcript_id: str,
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
transcript_format: TranscriptFormat = "text",
|
||||
):
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
return await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
|
||||
is_multitrack = await _get_is_multitrack(transcript)
|
||||
|
||||
room_name = None
|
||||
if transcript.room_id:
|
||||
room = await rooms_controller.get_by_id(transcript.room_id)
|
||||
room_name = room.name if room else None
|
||||
|
||||
participants = []
|
||||
if transcript.participants:
|
||||
user_ids = [p.user_id for p in transcript.participants if p.user_id is not None]
|
||||
users_dict = await user_controller.get_by_ids(user_ids) if user_ids else {}
|
||||
for p in transcript.participants:
|
||||
user = users_dict.get(p.user_id) if p.user_id else None
|
||||
participants.append(
|
||||
TranscriptParticipantWithEmail(
|
||||
**p.model_dump(), email=user.email if user else None
|
||||
)
|
||||
)
|
||||
|
||||
base_data = {
|
||||
"id": transcript.id,
|
||||
"user_id": transcript.user_id,
|
||||
"name": transcript.name,
|
||||
"status": transcript.status,
|
||||
"locked": transcript.locked,
|
||||
"duration": transcript.duration,
|
||||
"title": transcript.title,
|
||||
"short_summary": transcript.short_summary,
|
||||
"long_summary": transcript.long_summary,
|
||||
"action_items": transcript.action_items,
|
||||
"created_at": transcript.created_at,
|
||||
"share_mode": transcript.share_mode,
|
||||
"source_language": transcript.source_language,
|
||||
"target_language": transcript.target_language,
|
||||
"reviewed": transcript.reviewed,
|
||||
"meeting_id": transcript.meeting_id,
|
||||
"source_kind": transcript.source_kind,
|
||||
"room_id": transcript.room_id,
|
||||
"room_name": room_name,
|
||||
"audio_deleted": transcript.audio_deleted,
|
||||
"participants": participants,
|
||||
}
|
||||
|
||||
if transcript_format == "text":
|
||||
return GetTranscriptWithText(
|
||||
**base_data,
|
||||
transcript_format="text",
|
||||
transcript=transcript_to_text(
|
||||
transcript.topics, transcript.participants, is_multitrack
|
||||
),
|
||||
)
|
||||
elif transcript_format == "text-timestamped":
|
||||
return GetTranscriptWithTextTimestamped(
|
||||
**base_data,
|
||||
transcript_format="text-timestamped",
|
||||
transcript=transcript_to_text_timestamped(
|
||||
transcript.topics, transcript.participants, is_multitrack
|
||||
),
|
||||
)
|
||||
elif transcript_format == "webvtt-named":
|
||||
return GetTranscriptWithWebVTTNamed(
|
||||
**base_data,
|
||||
transcript_format="webvtt-named",
|
||||
transcript=topics_to_webvtt_named(
|
||||
transcript.topics, transcript.participants, is_multitrack
|
||||
),
|
||||
)
|
||||
elif transcript_format == "json":
|
||||
return GetTranscriptWithJSON(
|
||||
**base_data,
|
||||
transcript_format="json",
|
||||
transcript=transcript_to_json_segments(
|
||||
transcript.topics, transcript.participants, is_multitrack
|
||||
),
|
||||
)
|
||||
else:
|
||||
assert_never(transcript_format)
|
||||
|
||||
|
||||
@router.patch(
|
||||
"/transcripts/{transcript_id}", response_model=GetTranscriptWithParticipants
|
||||
)
|
||||
@router.patch("/transcripts/{transcript_id}", response_model=GetTranscript)
|
||||
async def transcript_update(
|
||||
transcript_id: str,
|
||||
info: UpdateTranscript,
|
||||
@@ -603,12 +419,9 @@ async def transcript_get_topics(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
|
||||
is_multitrack = await _get_is_multitrack(transcript)
|
||||
|
||||
# convert to GetTranscriptTopic
|
||||
return [
|
||||
GetTranscriptTopic.from_transcript_topic(topic, is_multitrack)
|
||||
for topic in transcript.topics
|
||||
GetTranscriptTopic.from_transcript_topic(topic) for topic in transcript.topics
|
||||
]
|
||||
|
||||
|
||||
@@ -625,11 +438,9 @@ async def transcript_get_topics_with_words(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
|
||||
is_multitrack = await _get_is_multitrack(transcript)
|
||||
|
||||
# convert to GetTranscriptTopicWithWords
|
||||
return [
|
||||
GetTranscriptTopicWithWords.from_transcript_topic(topic, is_multitrack)
|
||||
GetTranscriptTopicWithWords.from_transcript_topic(topic)
|
||||
for topic in transcript.topics
|
||||
]
|
||||
|
||||
@@ -648,17 +459,13 @@ async def transcript_get_topics_with_words_per_speaker(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
|
||||
is_multitrack = await _get_is_multitrack(transcript)
|
||||
|
||||
# get the topic from the transcript
|
||||
topic = next((t for t in transcript.topics if t.id == topic_id), None)
|
||||
if not topic:
|
||||
raise HTTPException(status_code=404, detail="Topic not found")
|
||||
|
||||
# convert to GetTranscriptTopicWithWordsPerSpeaker
|
||||
return GetTranscriptTopicWithWordsPerSpeaker.from_transcript_topic(
|
||||
topic, is_multitrack
|
||||
)
|
||||
return GetTranscriptTopicWithWordsPerSpeaker.from_transcript_topic(topic)
|
||||
|
||||
|
||||
@router.post("/transcripts/{transcript_id}/zulip")
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from typing import Annotated, Optional, assert_never
|
||||
from typing import Annotated, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from pydantic import BaseModel
|
||||
@@ -15,6 +15,7 @@ from reflector.services.transcript_process import (
|
||||
prepare_transcript_processing,
|
||||
validate_transcript_for_processing,
|
||||
)
|
||||
from reflector.utils.match import absurd
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@@ -43,7 +44,7 @@ async def transcript_process(
|
||||
elif isinstance(validation, ValidationOk):
|
||||
pass
|
||||
else:
|
||||
assert_never(validation)
|
||||
absurd(validation)
|
||||
|
||||
config = await prepare_transcript_processing(validation)
|
||||
|
||||
|
||||
@@ -38,10 +38,6 @@ else:
|
||||
"task": "reflector.worker.process.reprocess_failed_recordings",
|
||||
"schedule": crontab(hour=5, minute=0), # Midnight EST
|
||||
},
|
||||
"reprocess_failed_daily_recordings": {
|
||||
"task": "reflector.worker.process.reprocess_failed_daily_recordings",
|
||||
"schedule": crontab(hour=5, minute=0), # Midnight EST
|
||||
},
|
||||
"poll_daily_recordings": {
|
||||
"task": "reflector.worker.process.poll_daily_recordings",
|
||||
"schedule": 180.0, # Every 3 minutes (configurable lookback window)
|
||||
|
||||
@@ -2,7 +2,6 @@ import json
|
||||
import os
|
||||
import re
|
||||
from datetime import datetime, timezone
|
||||
from typing import List
|
||||
from urllib.parse import unquote
|
||||
|
||||
import av
|
||||
@@ -12,7 +11,7 @@ from celery import shared_task
|
||||
from celery.utils.log import get_task_logger
|
||||
from pydantic import ValidationError
|
||||
|
||||
from reflector.dailyco_api import FinishedRecordingResponse, RecordingResponse
|
||||
from reflector.dailyco_api import MeetingParticipantsResponse
|
||||
from reflector.db.daily_participant_sessions import (
|
||||
DailyParticipantSession,
|
||||
daily_participant_sessions_controller,
|
||||
@@ -22,6 +21,7 @@ from reflector.db.recordings import Recording, recordings_controller
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.db.transcripts import (
|
||||
SourceKind,
|
||||
TranscriptParticipant,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
|
||||
@@ -38,7 +38,7 @@ from reflector.storage import get_transcripts_storage
|
||||
from reflector.utils.daily import (
|
||||
DailyRoomName,
|
||||
extract_base_room_name,
|
||||
filter_cam_audio_tracks,
|
||||
parse_daily_recording_filename,
|
||||
recording_lock_key,
|
||||
)
|
||||
from reflector.video_platforms.factory import create_platform_client
|
||||
@@ -240,6 +240,8 @@ async def _process_multitrack_recording_inner(
|
||||
)
|
||||
|
||||
meeting = await meetings_controller.get_by_room_name(daily_room_name)
|
||||
if not meeting:
|
||||
raise Exception(f"Meeting not found: {daily_room_name}")
|
||||
|
||||
room_name_base = extract_base_room_name(daily_room_name)
|
||||
|
||||
@@ -247,9 +249,6 @@ async def _process_multitrack_recording_inner(
|
||||
if not room:
|
||||
raise Exception(f"Room not found: {room_name_base}")
|
||||
|
||||
if not meeting:
|
||||
raise Exception(f"Meeting not found: {room_name_base}")
|
||||
|
||||
logger.info(
|
||||
"Found existing Meeting for recording",
|
||||
meeting_id=meeting.id,
|
||||
@@ -273,7 +272,15 @@ async def _process_multitrack_recording_inner(
|
||||
# else: Recording already exists; metadata set at creation time
|
||||
|
||||
transcript = await transcripts_controller.get_by_recording_id(recording.id)
|
||||
if not transcript:
|
||||
if transcript:
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"topics": [],
|
||||
"participants": [],
|
||||
},
|
||||
)
|
||||
else:
|
||||
transcript = await transcripts_controller.add(
|
||||
"",
|
||||
source_kind=SourceKind.ROOM,
|
||||
@@ -286,10 +293,79 @@ async def _process_multitrack_recording_inner(
|
||||
room_id=room.id,
|
||||
)
|
||||
|
||||
try:
|
||||
async with create_platform_client("daily") as daily_client:
|
||||
id_to_name = {}
|
||||
id_to_user_id = {}
|
||||
|
||||
try:
|
||||
rec_details = await daily_client.get_recording(recording_id)
|
||||
mtg_session_id = rec_details.mtgSessionId
|
||||
if mtg_session_id:
|
||||
try:
|
||||
payload: MeetingParticipantsResponse = (
|
||||
await daily_client.get_meeting_participants(mtg_session_id)
|
||||
)
|
||||
for p in payload.data:
|
||||
pid = p.participant_id
|
||||
assert (
|
||||
pid is not None
|
||||
), "panic! participant id cannot be None"
|
||||
name = p.user_name
|
||||
user_id = p.user_id
|
||||
if name:
|
||||
id_to_name[pid] = name
|
||||
if user_id:
|
||||
id_to_user_id[pid] = user_id
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Failed to fetch Daily meeting participants",
|
||||
error=str(e),
|
||||
mtg_session_id=mtg_session_id,
|
||||
exc_info=True,
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
"No mtgSessionId found for recording; participant names may be generic",
|
||||
recording_id=recording_id,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Failed to fetch Daily recording details",
|
||||
error=str(e),
|
||||
recording_id=recording_id,
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
for idx, key in enumerate(track_keys):
|
||||
try:
|
||||
parsed = parse_daily_recording_filename(key)
|
||||
participant_id = parsed.participant_id
|
||||
except ValueError as e:
|
||||
logger.error(
|
||||
"Failed to parse Daily recording filename",
|
||||
error=str(e),
|
||||
key=key,
|
||||
exc_info=True,
|
||||
)
|
||||
continue
|
||||
|
||||
default_name = f"Speaker {idx}"
|
||||
name = id_to_name.get(participant_id, default_name)
|
||||
user_id = id_to_user_id.get(participant_id)
|
||||
|
||||
participant = TranscriptParticipant(
|
||||
id=participant_id, speaker=idx, name=name, user_id=user_id
|
||||
)
|
||||
await transcripts_controller.upsert_participant(transcript, participant)
|
||||
|
||||
except Exception as e:
|
||||
logger.warning("Failed to map participant names", error=str(e), exc_info=True)
|
||||
|
||||
task_pipeline_multitrack_process.delay(
|
||||
transcript_id=transcript.id,
|
||||
bucket_name=bucket_name,
|
||||
track_keys=filter_cam_audio_tracks(track_keys),
|
||||
track_keys=track_keys,
|
||||
)
|
||||
|
||||
|
||||
@@ -314,7 +390,7 @@ async def poll_daily_recordings():
|
||||
|
||||
async with create_platform_client("daily") as daily_client:
|
||||
# latest 100. TODO cursor-based state
|
||||
api_recordings: List[RecordingResponse] = await daily_client.list_recordings()
|
||||
api_recordings = await daily_client.list_recordings()
|
||||
|
||||
if not api_recordings:
|
||||
logger.debug(
|
||||
@@ -322,38 +398,16 @@ async def poll_daily_recordings():
|
||||
)
|
||||
return
|
||||
|
||||
finished_recordings: List[FinishedRecordingResponse] = []
|
||||
for rec in api_recordings:
|
||||
finished = rec.to_finished()
|
||||
if finished is None:
|
||||
logger.debug(
|
||||
"Skipping unfinished recording",
|
||||
recording_id=rec.id,
|
||||
room_name=rec.room_name,
|
||||
status=rec.status,
|
||||
)
|
||||
continue
|
||||
finished_recordings.append(finished)
|
||||
|
||||
if not finished_recordings:
|
||||
logger.debug(
|
||||
"No finished recordings found from Daily.co API",
|
||||
total_api_count=len(api_recordings),
|
||||
)
|
||||
return
|
||||
|
||||
recording_ids = [rec.id for rec in finished_recordings]
|
||||
recording_ids = [rec.id for rec in api_recordings]
|
||||
existing_recordings = await recordings_controller.get_by_ids(recording_ids)
|
||||
existing_ids = {rec.id for rec in existing_recordings}
|
||||
|
||||
missing_recordings = [
|
||||
rec for rec in finished_recordings if rec.id not in existing_ids
|
||||
]
|
||||
missing_recordings = [rec for rec in api_recordings if rec.id not in existing_ids]
|
||||
|
||||
if not missing_recordings:
|
||||
logger.debug(
|
||||
"All recordings already in DB",
|
||||
api_count=len(finished_recordings),
|
||||
api_count=len(api_recordings),
|
||||
existing_count=len(existing_recordings),
|
||||
)
|
||||
return
|
||||
@@ -361,25 +415,23 @@ async def poll_daily_recordings():
|
||||
logger.info(
|
||||
"Found recordings missing from DB",
|
||||
missing_count=len(missing_recordings),
|
||||
total_api_count=len(finished_recordings),
|
||||
total_api_count=len(api_recordings),
|
||||
existing_count=len(existing_recordings),
|
||||
)
|
||||
|
||||
for recording in missing_recordings:
|
||||
if not recording.tracks:
|
||||
if recording.status == "finished":
|
||||
logger.warning(
|
||||
"Finished recording has no tracks (no audio captured)",
|
||||
recording_id=recording.id,
|
||||
room_name=recording.room_name,
|
||||
)
|
||||
else:
|
||||
logger.debug(
|
||||
"No tracks in recording yet",
|
||||
recording_id=recording.id,
|
||||
room_name=recording.room_name,
|
||||
status=recording.status,
|
||||
)
|
||||
assert recording.status != "finished", (
|
||||
f"Recording {recording.id} has status='finished' but no tracks. "
|
||||
f"Daily.co API guarantees finished recordings have tracks available. "
|
||||
f"room_name={recording.room_name}"
|
||||
)
|
||||
logger.debug(
|
||||
"No tracks in recording yet",
|
||||
recording_id=recording.id,
|
||||
room_name=recording.room_name,
|
||||
status=recording.status,
|
||||
)
|
||||
continue
|
||||
|
||||
track_keys = [t.s3Key for t in recording.tracks if t.type == "audio"]
|
||||
@@ -393,6 +445,15 @@ async def poll_daily_recordings():
|
||||
)
|
||||
continue
|
||||
|
||||
meeting = await meetings_controller.get_by_room_name(recording.room_name)
|
||||
if not meeting:
|
||||
logger.warning(
|
||||
"Skipping recording - no matching meeting",
|
||||
recording_id=recording.id,
|
||||
room_name=recording.room_name,
|
||||
)
|
||||
continue
|
||||
|
||||
logger.info(
|
||||
"Queueing missing recording for processing",
|
||||
recording_id=recording.id,
|
||||
@@ -671,7 +732,7 @@ async def reprocess_failed_recordings():
|
||||
Find recordings in Whereby S3 bucket and check if they have proper transcriptions.
|
||||
If not, requeue them for processing.
|
||||
|
||||
Note: Daily.co multitrack recordings are handled by reprocess_failed_daily_recordings.
|
||||
Note: Daily.co recordings are processed via webhooks, not this cron job.
|
||||
"""
|
||||
logger.info("Checking Whereby recordings that need processing or reprocessing")
|
||||
|
||||
@@ -724,103 +785,6 @@ async def reprocess_failed_recordings():
|
||||
return reprocessed_count
|
||||
|
||||
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def reprocess_failed_daily_recordings():
|
||||
"""
|
||||
Find Daily.co multitrack recordings in the database and check if they have proper transcriptions.
|
||||
If not, requeue them for processing.
|
||||
"""
|
||||
logger.info(
|
||||
"Checking Daily.co multitrack recordings that need processing or reprocessing"
|
||||
)
|
||||
|
||||
if not settings.DAILYCO_STORAGE_AWS_BUCKET_NAME:
|
||||
logger.debug(
|
||||
"DAILYCO_STORAGE_AWS_BUCKET_NAME not configured; skipping Daily recording reprocessing"
|
||||
)
|
||||
return 0
|
||||
|
||||
bucket_name = settings.DAILYCO_STORAGE_AWS_BUCKET_NAME
|
||||
reprocessed_count = 0
|
||||
|
||||
try:
|
||||
multitrack_recordings = (
|
||||
await recordings_controller.get_multitrack_needing_reprocessing(bucket_name)
|
||||
)
|
||||
|
||||
logger.info(
|
||||
"Found multitrack recordings needing reprocessing",
|
||||
count=len(multitrack_recordings),
|
||||
bucket=bucket_name,
|
||||
)
|
||||
|
||||
for recording in multitrack_recordings:
|
||||
if not recording.meeting_id:
|
||||
logger.debug(
|
||||
"Skipping recording without meeting_id",
|
||||
recording_id=recording.id,
|
||||
)
|
||||
continue
|
||||
|
||||
meeting = await meetings_controller.get_by_id(recording.meeting_id)
|
||||
if not meeting:
|
||||
logger.warning(
|
||||
"Meeting not found for recording",
|
||||
recording_id=recording.id,
|
||||
meeting_id=recording.meeting_id,
|
||||
)
|
||||
continue
|
||||
|
||||
transcript = None
|
||||
try:
|
||||
transcript = await transcripts_controller.get_by_recording_id(
|
||||
recording.id
|
||||
)
|
||||
except ValidationError:
|
||||
await transcripts_controller.remove_by_recording_id(recording.id)
|
||||
logger.warning(
|
||||
"Removed invalid transcript for recording",
|
||||
recording_id=recording.id,
|
||||
)
|
||||
|
||||
if not recording.track_keys:
|
||||
logger.warning(
|
||||
"Recording has no track_keys, cannot reprocess",
|
||||
recording_id=recording.id,
|
||||
)
|
||||
continue
|
||||
|
||||
logger.info(
|
||||
"Queueing Daily recording for reprocessing",
|
||||
recording_id=recording.id,
|
||||
room_name=meeting.room_name,
|
||||
track_count=len(recording.track_keys),
|
||||
transcript_status=transcript.status if transcript else None,
|
||||
)
|
||||
|
||||
process_multitrack_recording.delay(
|
||||
bucket_name=bucket_name,
|
||||
daily_room_name=meeting.room_name,
|
||||
recording_id=recording.id,
|
||||
track_keys=recording.track_keys,
|
||||
)
|
||||
reprocessed_count += 1
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"Error checking Daily multitrack recordings",
|
||||
error=str(e),
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
logger.info(
|
||||
"Daily reprocessing complete",
|
||||
requeued_count=reprocessed_count,
|
||||
)
|
||||
return reprocessed_count
|
||||
|
||||
|
||||
@shared_task
|
||||
@asynctask
|
||||
async def trigger_daily_reconciliation() -> None:
|
||||
|
||||
@@ -123,7 +123,6 @@ async def send_transcript_webhook(
|
||||
"target_language": transcript.target_language,
|
||||
"status": transcript.status,
|
||||
"frontend_url": frontend_url,
|
||||
"action_items": transcript.action_items,
|
||||
},
|
||||
"room": {
|
||||
"id": room.id,
|
||||
|
||||
@@ -318,14 +318,6 @@ async def dummy_storage():
|
||||
yield
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def test_settings():
|
||||
"""Provide isolated settings for tests to avoid modifying global settings"""
|
||||
from reflector.settings import Settings
|
||||
|
||||
return Settings()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def celery_enable_logging():
|
||||
return True
|
||||
|
||||
@@ -1,488 +0,0 @@
|
||||
"""Tests for LLM parse error recovery using llama-index Workflow"""
|
||||
|
||||
from time import monotonic
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel, Field
|
||||
from workflows.errors import WorkflowRuntimeError, WorkflowTimeoutError
|
||||
|
||||
from reflector.llm import LLM, LLMParseError, StructuredOutputWorkflow
|
||||
from reflector.utils.retry import RetryException
|
||||
|
||||
|
||||
class TestResponse(BaseModel):
|
||||
"""Test response model for structured output"""
|
||||
|
||||
title: str = Field(description="A title")
|
||||
summary: str = Field(description="A summary")
|
||||
confidence: float = Field(description="Confidence score", ge=0, le=1)
|
||||
|
||||
|
||||
def make_completion_response(text: str):
|
||||
"""Create a mock CompletionResponse with .text attribute"""
|
||||
response = MagicMock()
|
||||
response.text = text
|
||||
return response
|
||||
|
||||
|
||||
class TestLLMParseErrorRecovery:
|
||||
"""Test parse error recovery with Workflow feedback loop"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_parse_error_recovery_with_feedback(self, test_settings):
|
||||
"""Test that parse errors trigger retry with error feedback"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
# TreeSummarize returns plain text analysis (step 1)
|
||||
mock_summarizer.aget_response = AsyncMock(
|
||||
return_value="The analysis shows a test with summary and high confidence."
|
||||
)
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def acomplete_handler(prompt, *args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
if call_count["count"] == 1:
|
||||
# First JSON formatting call returns invalid JSON
|
||||
return make_completion_response('{"title": "Test"}')
|
||||
else:
|
||||
# Second call should have error feedback in prompt
|
||||
assert "Your previous response could not be parsed:" in prompt
|
||||
assert '{"title": "Test"}' in prompt
|
||||
assert "Error:" in prompt
|
||||
assert "Please try again" in prompt
|
||||
return make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
|
||||
mock_settings.llm.acomplete = AsyncMock(side_effect=acomplete_handler)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
assert result.summary == "Summary"
|
||||
assert result.confidence == 0.95
|
||||
# TreeSummarize called once, Settings.llm.acomplete called twice
|
||||
assert mock_summarizer.aget_response.call_count == 1
|
||||
assert call_count["count"] == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_max_parse_retry_attempts(self, test_settings):
|
||||
"""Test that parse error retry stops after max attempts"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
# Always return invalid JSON from acomplete
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response(
|
||||
'{"invalid": "missing required fields"}'
|
||||
)
|
||||
)
|
||||
|
||||
with pytest.raises(LLMParseError, match="Failed to parse"):
|
||||
await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
expected_attempts = test_settings.LLM_PARSE_MAX_RETRIES + 1
|
||||
# TreeSummarize called once, acomplete called max_retries times
|
||||
assert mock_summarizer.aget_response.call_count == 1
|
||||
assert mock_settings.llm.acomplete.call_count == expected_attempts
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_raw_response_logging_on_parse_error(self, test_settings, caplog):
|
||||
"""Test that raw response is logged when parse error occurs"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
caplog.at_level("ERROR"),
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def acomplete_handler(*args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
if call_count["count"] == 1:
|
||||
return make_completion_response('{"title": "Test"}') # Invalid
|
||||
return make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
|
||||
mock_settings.llm.acomplete = AsyncMock(side_effect=acomplete_handler)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
|
||||
error_logs = [r for r in caplog.records if r.levelname == "ERROR"]
|
||||
raw_response_logged = any("Raw response:" in r.message for r in error_logs)
|
||||
assert raw_response_logged, "Raw response should be logged on parse error"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_multiple_validation_errors_in_feedback(self, test_settings):
|
||||
"""Test that validation errors are included in feedback"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def acomplete_handler(prompt, *args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
if call_count["count"] == 1:
|
||||
# Missing title and summary
|
||||
return make_completion_response('{"confidence": 0.5}')
|
||||
else:
|
||||
# Should have schema validation errors in prompt
|
||||
assert (
|
||||
"Schema validation errors" in prompt
|
||||
or "error" in prompt.lower()
|
||||
)
|
||||
return make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
|
||||
mock_settings.llm.acomplete = AsyncMock(side_effect=acomplete_handler)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
assert call_count["count"] == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_success_on_first_attempt(self, test_settings):
|
||||
"""Test that no retry happens when first attempt succeeds"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
assert result.summary == "Summary"
|
||||
assert result.confidence == 0.95
|
||||
assert mock_summarizer.aget_response.call_count == 1
|
||||
assert mock_settings.llm.acomplete.call_count == 1
|
||||
|
||||
|
||||
class TestStructuredOutputWorkflow:
|
||||
"""Direct tests for the StructuredOutputWorkflow"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_workflow_retries_on_validation_error(self):
|
||||
"""Test workflow retries when validation fails"""
|
||||
workflow = StructuredOutputWorkflow(
|
||||
output_cls=TestResponse,
|
||||
max_retries=3,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def acomplete_handler(*args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
if call_count["count"] < 2:
|
||||
return make_completion_response('{"title": "Only title"}')
|
||||
return make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.9}'
|
||||
)
|
||||
|
||||
mock_settings.llm.acomplete = AsyncMock(side_effect=acomplete_handler)
|
||||
|
||||
result = await workflow.run(
|
||||
prompt="Extract data",
|
||||
texts=["Some text"],
|
||||
tone_name=None,
|
||||
)
|
||||
|
||||
assert "success" in result
|
||||
assert result["success"].title == "Test"
|
||||
assert call_count["count"] == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_workflow_returns_error_after_max_retries(self):
|
||||
"""Test workflow returns error after exhausting retries"""
|
||||
workflow = StructuredOutputWorkflow(
|
||||
output_cls=TestResponse,
|
||||
max_retries=2,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
# Always return invalid JSON
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response('{"invalid": true}')
|
||||
)
|
||||
|
||||
result = await workflow.run(
|
||||
prompt="Extract data",
|
||||
texts=["Some text"],
|
||||
tone_name=None,
|
||||
)
|
||||
|
||||
assert "error" in result
|
||||
# TreeSummarize called once, acomplete called max_retries times
|
||||
assert mock_summarizer.aget_response.call_count == 1
|
||||
assert mock_settings.llm.acomplete.call_count == 2
|
||||
|
||||
|
||||
class TestNetworkErrorRetries:
|
||||
"""Test that network error retries are handled by OpenAILike, not Workflow"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_network_error_propagates_after_openai_retries(self, test_settings):
|
||||
"""Test that network errors are retried by OpenAILike and then propagate.
|
||||
|
||||
Network retries are handled by OpenAILike (max_retries=3), not by our
|
||||
StructuredOutputWorkflow. This test verifies that network errors propagate
|
||||
up after OpenAILike exhausts its retries.
|
||||
"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
# Simulate network error from acomplete (after OpenAILike retries exhausted)
|
||||
network_error = ConnectionError("Connection refused")
|
||||
mock_settings.llm.acomplete = AsyncMock(side_effect=network_error)
|
||||
|
||||
# Network error wrapped in WorkflowRuntimeError
|
||||
with pytest.raises(WorkflowRuntimeError, match="Connection refused"):
|
||||
await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
# acomplete called only once - network error propagates, not retried by Workflow
|
||||
assert mock_settings.llm.acomplete.call_count == 1
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_network_error_not_retried_by_workflow(self, test_settings):
|
||||
"""Test that Workflow does NOT retry network errors (OpenAILike handles those).
|
||||
|
||||
This verifies the separation of concerns:
|
||||
- StructuredOutputWorkflow: retries parse/validation errors
|
||||
- OpenAILike: retries network errors (internally, max_retries=3)
|
||||
"""
|
||||
workflow = StructuredOutputWorkflow(
|
||||
output_cls=TestResponse,
|
||||
max_retries=3,
|
||||
timeout=30,
|
||||
)
|
||||
|
||||
with (
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
|
||||
# Network error should propagate immediately, not trigger Workflow retry
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
side_effect=TimeoutError("Request timed out")
|
||||
)
|
||||
|
||||
# Network error wrapped in WorkflowRuntimeError
|
||||
with pytest.raises(WorkflowRuntimeError, match="Request timed out"):
|
||||
await workflow.run(
|
||||
prompt="Extract data",
|
||||
texts=["Some text"],
|
||||
tone_name=None,
|
||||
)
|
||||
|
||||
# Only called once - Workflow doesn't retry network errors
|
||||
assert mock_settings.llm.acomplete.call_count == 1
|
||||
|
||||
|
||||
class TestWorkflowTimeoutRetry:
|
||||
"""Test timeout retry mechanism in get_structured_response"""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_timeout_retry_succeeds_on_retry(self, test_settings):
|
||||
"""Test that WorkflowTimeoutError triggers retry and succeeds"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def workflow_run_side_effect(*args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
if call_count["count"] == 1:
|
||||
raise WorkflowTimeoutError("Operation timed out after 120 seconds")
|
||||
return {
|
||||
"success": TestResponse(
|
||||
title="Test", summary="Summary", confidence=0.95
|
||||
)
|
||||
}
|
||||
|
||||
with (
|
||||
patch("reflector.llm.StructuredOutputWorkflow") as mock_workflow_class,
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_workflow = MagicMock()
|
||||
mock_workflow.run = AsyncMock(side_effect=workflow_run_side_effect)
|
||||
mock_workflow_class.return_value = mock_workflow
|
||||
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
assert result.summary == "Summary"
|
||||
assert call_count["count"] == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_timeout_retry_exhausts_after_max_attempts(self, test_settings):
|
||||
"""Test that timeout retry stops after max attempts"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
call_count = {"count": 0}
|
||||
|
||||
async def workflow_run_side_effect(*args, **kwargs):
|
||||
call_count["count"] += 1
|
||||
raise WorkflowTimeoutError("Operation timed out after 120 seconds")
|
||||
|
||||
with (
|
||||
patch("reflector.llm.StructuredOutputWorkflow") as mock_workflow_class,
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_workflow = MagicMock()
|
||||
mock_workflow.run = AsyncMock(side_effect=workflow_run_side_effect)
|
||||
mock_workflow_class.return_value = mock_workflow
|
||||
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
)
|
||||
|
||||
with pytest.raises(RetryException, match="Retry attempts exceeded"):
|
||||
await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert call_count["count"] == 3
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_timeout_retry_with_backoff(self, test_settings):
|
||||
"""Test that exponential backoff is applied between retries"""
|
||||
llm = LLM(settings=test_settings, temperature=0.4, max_tokens=100)
|
||||
|
||||
call_times = []
|
||||
|
||||
async def workflow_run_side_effect(*args, **kwargs):
|
||||
call_times.append(monotonic())
|
||||
if len(call_times) < 3:
|
||||
raise WorkflowTimeoutError("Operation timed out after 120 seconds")
|
||||
return {
|
||||
"success": TestResponse(
|
||||
title="Test", summary="Summary", confidence=0.95
|
||||
)
|
||||
}
|
||||
|
||||
with (
|
||||
patch("reflector.llm.StructuredOutputWorkflow") as mock_workflow_class,
|
||||
patch("reflector.llm.TreeSummarize") as mock_summarize,
|
||||
patch("reflector.llm.Settings") as mock_settings,
|
||||
):
|
||||
mock_workflow = MagicMock()
|
||||
mock_workflow.run = AsyncMock(side_effect=workflow_run_side_effect)
|
||||
mock_workflow_class.return_value = mock_workflow
|
||||
|
||||
mock_summarizer = MagicMock()
|
||||
mock_summarize.return_value = mock_summarizer
|
||||
mock_summarizer.aget_response = AsyncMock(return_value="Some analysis")
|
||||
mock_settings.llm.acomplete = AsyncMock(
|
||||
return_value=make_completion_response(
|
||||
'{"title": "Test", "summary": "Summary", "confidence": 0.95}'
|
||||
)
|
||||
)
|
||||
|
||||
result = await llm.get_structured_response(
|
||||
prompt="Test prompt", texts=["Test text"], output_cls=TestResponse
|
||||
)
|
||||
|
||||
assert result.title == "Test"
|
||||
if len(call_times) >= 2:
|
||||
time_between_calls = call_times[1] - call_times[0]
|
||||
assert (
|
||||
time_between_calls >= 1.5
|
||||
), f"Expected ~2s backoff, got {time_between_calls}s"
|
||||
@@ -266,11 +266,7 @@ async def mock_summary_processor():
|
||||
# When flush is called, simulate summary generation by calling the callbacks
|
||||
async def flush_with_callback():
|
||||
mock_summary.flush_called = True
|
||||
from reflector.processors.types import (
|
||||
ActionItems,
|
||||
FinalLongSummary,
|
||||
FinalShortSummary,
|
||||
)
|
||||
from reflector.processors.types import FinalLongSummary, FinalShortSummary
|
||||
|
||||
if hasattr(mock_summary, "_callback"):
|
||||
await mock_summary._callback(
|
||||
@@ -280,19 +276,12 @@ async def mock_summary_processor():
|
||||
await mock_summary._on_short_summary(
|
||||
FinalShortSummary(short_summary="Test short summary", duration=10.0)
|
||||
)
|
||||
if hasattr(mock_summary, "_on_action_items"):
|
||||
await mock_summary._on_action_items(
|
||||
ActionItems(action_items={"test": "action item"})
|
||||
)
|
||||
|
||||
mock_summary.flush = flush_with_callback
|
||||
|
||||
def init_with_callback(
|
||||
transcript=None, callback=None, on_short_summary=None, on_action_items=None
|
||||
):
|
||||
def init_with_callback(transcript=None, callback=None, on_short_summary=None):
|
||||
mock_summary._callback = callback
|
||||
mock_summary._on_short_summary = on_short_summary
|
||||
mock_summary._on_action_items = on_action_items
|
||||
return mock_summary
|
||||
|
||||
mock_summary_class.side_effect = init_with_callback
|
||||
|
||||
@@ -59,17 +59,37 @@ def mock_recording_response():
|
||||
]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_meeting():
|
||||
"""Mock meeting object."""
|
||||
from reflector.db.meetings import Meeting
|
||||
|
||||
return Meeting(
|
||||
id="meeting-123",
|
||||
room_name="test-room-20251118120000",
|
||||
room_url="https://daily.co/test-room",
|
||||
host_room_url="https://daily.co/test-room",
|
||||
start_date=datetime.now(timezone.utc),
|
||||
end_date=datetime.now(timezone.utc) + timedelta(hours=1),
|
||||
room_id="room-123",
|
||||
platform="daily",
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("reflector.worker.process.settings")
|
||||
@patch("reflector.worker.process.create_platform_client")
|
||||
@patch("reflector.worker.process.recordings_controller.get_by_ids")
|
||||
@patch("reflector.worker.process.meetings_controller.get_by_room_name")
|
||||
@patch("reflector.worker.process.process_multitrack_recording.delay")
|
||||
async def test_poll_daily_recordings_processes_missing_recordings(
|
||||
mock_process_delay,
|
||||
mock_get_meeting,
|
||||
mock_get_recordings,
|
||||
mock_create_client,
|
||||
mock_settings,
|
||||
mock_recording_response,
|
||||
mock_meeting,
|
||||
):
|
||||
"""Test that poll_daily_recordings queues processing for recordings not in DB."""
|
||||
mock_settings.DAILYCO_STORAGE_AWS_BUCKET_NAME = "test-bucket"
|
||||
@@ -85,6 +105,9 @@ async def test_poll_daily_recordings_processes_missing_recordings(
|
||||
# Mock DB controller - no existing recordings
|
||||
mock_get_recordings.return_value = []
|
||||
|
||||
# Mock meeting exists for all recordings
|
||||
mock_get_meeting.return_value = mock_meeting
|
||||
|
||||
# Execute - call the unwrapped async function
|
||||
poll_fn = _get_poll_daily_recordings_fn()
|
||||
await poll_fn()
|
||||
@@ -113,6 +136,48 @@ async def test_poll_daily_recordings_processes_missing_recordings(
|
||||
assert calls[1].kwargs["track_keys"] == ["track1.webm"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("reflector.worker.process.settings")
|
||||
@patch("reflector.worker.process.create_platform_client")
|
||||
@patch("reflector.worker.process.recordings_controller.get_by_ids")
|
||||
@patch("reflector.worker.process.meetings_controller.get_by_room_name")
|
||||
@patch("reflector.worker.process.process_multitrack_recording.delay")
|
||||
async def test_poll_daily_recordings_skips_recordings_without_meeting(
|
||||
mock_process_delay,
|
||||
mock_get_meeting,
|
||||
mock_get_recordings,
|
||||
mock_create_client,
|
||||
mock_settings,
|
||||
mock_recording_response,
|
||||
):
|
||||
"""Test that poll_daily_recordings skips recordings without matching meeting."""
|
||||
mock_settings.DAILYCO_STORAGE_AWS_BUCKET_NAME = "test-bucket"
|
||||
|
||||
# Mock Daily.co API client
|
||||
mock_daily_client = AsyncMock()
|
||||
mock_daily_client.list_recordings = AsyncMock(return_value=mock_recording_response)
|
||||
mock_create_client.return_value.__aenter__ = AsyncMock(
|
||||
return_value=mock_daily_client
|
||||
)
|
||||
mock_create_client.return_value.__aexit__ = AsyncMock()
|
||||
|
||||
# Mock DB controller - no existing recordings
|
||||
mock_get_recordings.return_value = []
|
||||
|
||||
# Mock no meeting found
|
||||
mock_get_meeting.return_value = None
|
||||
|
||||
# Execute - call the unwrapped async function
|
||||
poll_fn = _get_poll_daily_recordings_fn()
|
||||
await poll_fn()
|
||||
|
||||
# Verify Daily.co API was called
|
||||
assert mock_daily_client.list_recordings.call_count == 1
|
||||
|
||||
# Verify NO processing was queued (no matching meetings)
|
||||
assert mock_process_delay.call_count == 0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("reflector.worker.process.settings")
|
||||
@patch("reflector.worker.process.create_platform_client")
|
||||
|
||||
@@ -159,78 +159,3 @@ def test_processor_transcript_segment():
|
||||
assert segments[3].start == 30.72
|
||||
assert segments[4].start == 31.56
|
||||
assert segments[5].start == 32.38
|
||||
|
||||
|
||||
def test_processor_transcript_segment_multitrack_interleaved():
|
||||
"""Test as_segments(is_multitrack=True) with interleaved speakers.
|
||||
|
||||
Multitrack recordings have words from different speakers sorted by start time,
|
||||
causing frequent speaker alternation. The multitrack mode should group by
|
||||
speaker first, then split into sentences.
|
||||
"""
|
||||
from reflector.processors.types import Transcript, Word
|
||||
|
||||
# Simulate real multitrack data: words sorted by start time, speakers interleave
|
||||
# Speaker 0 says: "Hello there."
|
||||
# Speaker 1 says: "I'm good."
|
||||
# When sorted by time, words interleave
|
||||
transcript = Transcript(
|
||||
words=[
|
||||
Word(text="Hello ", start=0.0, end=0.5, speaker=0),
|
||||
Word(text="I'm ", start=0.5, end=0.8, speaker=1),
|
||||
Word(text="there.", start=0.5, end=1.0, speaker=0),
|
||||
Word(text="good.", start=1.0, end=1.5, speaker=1),
|
||||
]
|
||||
)
|
||||
|
||||
# Default behavior (is_multitrack=False): breaks on every speaker change = 4 segments
|
||||
segments_default = transcript.as_segments(is_multitrack=False)
|
||||
assert len(segments_default) == 4
|
||||
|
||||
# Multitrack behavior: groups by speaker, then sentences = 2 segments
|
||||
segments_multitrack = transcript.as_segments(is_multitrack=True)
|
||||
assert len(segments_multitrack) == 2
|
||||
|
||||
# Check content - sorted by start time
|
||||
assert segments_multitrack[0].speaker == 0
|
||||
assert segments_multitrack[0].text == "Hello there."
|
||||
assert segments_multitrack[0].start == 0.0
|
||||
assert segments_multitrack[0].end == 1.0
|
||||
|
||||
assert segments_multitrack[1].speaker == 1
|
||||
assert segments_multitrack[1].text == "I'm good."
|
||||
assert segments_multitrack[1].start == 0.5
|
||||
assert segments_multitrack[1].end == 1.5
|
||||
|
||||
|
||||
def test_processor_transcript_segment_multitrack_overlapping_timestamps():
|
||||
"""Test multitrack with exactly overlapping timestamps (real Daily.co data pattern)."""
|
||||
from reflector.processors.types import Transcript, Word
|
||||
|
||||
# Real pattern from transcript 38d84d57: words with identical timestamps
|
||||
transcript = Transcript(
|
||||
words=[
|
||||
Word(text="speaking ", start=6.71, end=7.11, speaker=0),
|
||||
Word(text="Speaking ", start=6.71, end=7.11, speaker=1),
|
||||
Word(text="at ", start=7.11, end=7.27, speaker=0),
|
||||
Word(text="at ", start=7.11, end=7.27, speaker=1),
|
||||
Word(text="the ", start=7.27, end=7.43, speaker=0),
|
||||
Word(text="the ", start=7.27, end=7.43, speaker=1),
|
||||
Word(text="same ", start=7.43, end=7.59, speaker=0),
|
||||
Word(text="same ", start=7.43, end=7.59, speaker=1),
|
||||
Word(text="time.", start=7.59, end=8.0, speaker=0),
|
||||
Word(text="time.", start=7.59, end=8.0, speaker=1),
|
||||
]
|
||||
)
|
||||
|
||||
# Default: 10 segments (one per speaker change)
|
||||
segments_default = transcript.as_segments(is_multitrack=False)
|
||||
assert len(segments_default) == 10
|
||||
|
||||
# Multitrack: 2 segments (one per speaker sentence)
|
||||
segments_multitrack = transcript.as_segments(is_multitrack=True)
|
||||
assert len(segments_multitrack) == 2
|
||||
|
||||
# Both should have complete sentences
|
||||
assert "speaking at the same time." in segments_multitrack[0].text
|
||||
assert "Speaking at the same time." in segments_multitrack[1].text
|
||||
|
||||
@@ -1,779 +0,0 @@
|
||||
"""Tests for transcript format conversion functionality."""
|
||||
|
||||
import pytest
|
||||
|
||||
from reflector.db.transcripts import TranscriptParticipant, TranscriptTopic
|
||||
from reflector.processors.types import Word
|
||||
from reflector.utils.transcript_formats import (
|
||||
format_timestamp_mmss,
|
||||
get_speaker_name,
|
||||
topics_to_webvtt_named,
|
||||
transcript_to_json_segments,
|
||||
transcript_to_text,
|
||||
transcript_to_text_timestamped,
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_speaker_name_with_participants():
|
||||
"""Test speaker name resolution with participants list."""
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="John Smith"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
|
||||
]
|
||||
|
||||
assert get_speaker_name(0, participants) == "John Smith"
|
||||
assert get_speaker_name(1, participants) == "Jane Doe"
|
||||
assert get_speaker_name(2, participants) == "Speaker 2"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_speaker_name_without_participants():
|
||||
"""Test speaker name resolution without participants list."""
|
||||
assert get_speaker_name(0, None) == "Speaker 0"
|
||||
assert get_speaker_name(1, None) == "Speaker 1"
|
||||
assert get_speaker_name(5, []) == "Speaker 5"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_format_timestamp_mmss():
|
||||
"""Test timestamp formatting to MM:SS."""
|
||||
assert format_timestamp_mmss(0) == "00:00"
|
||||
assert format_timestamp_mmss(5) == "00:05"
|
||||
assert format_timestamp_mmss(65) == "01:05"
|
||||
assert format_timestamp_mmss(125.7) == "02:05"
|
||||
assert format_timestamp_mmss(3661) == "61:01"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_to_text():
|
||||
"""Test plain text format conversion."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello", start=0.0, end=1.0, speaker=0),
|
||||
Word(text=" world.", start=1.0, end=2.0, speaker=0),
|
||||
],
|
||||
),
|
||||
TranscriptTopic(
|
||||
id="2",
|
||||
title="Topic 2",
|
||||
summary="Summary 2",
|
||||
timestamp=2.0,
|
||||
words=[
|
||||
Word(text="How", start=2.0, end=3.0, speaker=1),
|
||||
Word(text=" are", start=3.0, end=4.0, speaker=1),
|
||||
Word(text=" you?", start=4.0, end=5.0, speaker=1),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="John Smith"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
|
||||
]
|
||||
|
||||
result = transcript_to_text(topics, participants)
|
||||
lines = result.split("\n")
|
||||
|
||||
assert len(lines) == 2
|
||||
assert lines[0] == "John Smith: Hello world."
|
||||
assert lines[1] == "Jane Doe: How are you?"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_to_text_timestamped():
|
||||
"""Test timestamped text format conversion."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello", start=0.0, end=1.0, speaker=0),
|
||||
Word(text=" world.", start=1.0, end=2.0, speaker=0),
|
||||
],
|
||||
),
|
||||
TranscriptTopic(
|
||||
id="2",
|
||||
title="Topic 2",
|
||||
summary="Summary 2",
|
||||
timestamp=65.0,
|
||||
words=[
|
||||
Word(text="How", start=65.0, end=66.0, speaker=1),
|
||||
Word(text=" are", start=66.0, end=67.0, speaker=1),
|
||||
Word(text=" you?", start=67.0, end=68.0, speaker=1),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="John Smith"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
|
||||
]
|
||||
|
||||
result = transcript_to_text_timestamped(topics, participants)
|
||||
lines = result.split("\n")
|
||||
|
||||
assert len(lines) == 2
|
||||
assert lines[0] == "[00:00] John Smith: Hello world."
|
||||
assert lines[1] == "[01:05] Jane Doe: How are you?"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_topics_to_webvtt_named():
|
||||
"""Test WebVTT format conversion with participant names."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello", start=0.0, end=1.0, speaker=0),
|
||||
Word(text=" world.", start=1.0, end=2.0, speaker=0),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="John Smith"),
|
||||
]
|
||||
|
||||
result = topics_to_webvtt_named(topics, participants)
|
||||
|
||||
assert result.startswith("WEBVTT")
|
||||
assert "<v John Smith>" in result
|
||||
assert "00:00:00.000 --> 00:00:02.000" in result
|
||||
assert "Hello world." in result
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_to_json_segments():
|
||||
"""Test JSON segments format conversion."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello", start=0.0, end=1.0, speaker=0),
|
||||
Word(text=" world.", start=1.0, end=2.0, speaker=0),
|
||||
],
|
||||
),
|
||||
TranscriptTopic(
|
||||
id="2",
|
||||
title="Topic 2",
|
||||
summary="Summary 2",
|
||||
timestamp=2.0,
|
||||
words=[
|
||||
Word(text="How", start=2.0, end=3.0, speaker=1),
|
||||
Word(text=" are", start=3.0, end=4.0, speaker=1),
|
||||
Word(text=" you?", start=4.0, end=5.0, speaker=1),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="John Smith"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
|
||||
]
|
||||
|
||||
result = transcript_to_json_segments(topics, participants)
|
||||
|
||||
assert len(result) == 2
|
||||
assert result[0].speaker == 0
|
||||
assert result[0].speaker_name == "John Smith"
|
||||
assert result[0].text == "Hello world."
|
||||
assert result[0].start == 0.0
|
||||
assert result[0].end == 2.0
|
||||
|
||||
assert result[1].speaker == 1
|
||||
assert result[1].speaker_name == "Jane Doe"
|
||||
assert result[1].text == "How are you?"
|
||||
assert result[1].start == 2.0
|
||||
assert result[1].end == 5.0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_formats_with_empty_topics():
|
||||
"""Test format conversion with empty topics list."""
|
||||
topics = []
|
||||
participants = []
|
||||
|
||||
assert transcript_to_text(topics, participants) == ""
|
||||
assert transcript_to_text_timestamped(topics, participants) == ""
|
||||
assert "WEBVTT" in topics_to_webvtt_named(topics, participants)
|
||||
assert transcript_to_json_segments(topics, participants) == []
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_formats_with_empty_words():
|
||||
"""Test format conversion with topics containing no words."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[],
|
||||
),
|
||||
]
|
||||
participants = []
|
||||
|
||||
assert transcript_to_text(topics, participants) == ""
|
||||
assert transcript_to_text_timestamped(topics, participants) == ""
|
||||
assert "WEBVTT" in topics_to_webvtt_named(topics, participants)
|
||||
assert transcript_to_json_segments(topics, participants) == []
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_formats_with_multiple_speakers():
|
||||
"""Test format conversion with multiple speaker changes."""
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello", start=0.0, end=1.0, speaker=0),
|
||||
Word(text=" there.", start=1.0, end=2.0, speaker=0),
|
||||
Word(text="Hi", start=2.0, end=3.0, speaker=1),
|
||||
Word(text=" back.", start=3.0, end=4.0, speaker=1),
|
||||
Word(text="Good", start=4.0, end=5.0, speaker=0),
|
||||
Word(text=" morning.", start=5.0, end=6.0, speaker=0),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="Alice"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Bob"),
|
||||
]
|
||||
|
||||
text_result = transcript_to_text(topics, participants)
|
||||
lines = text_result.split("\n")
|
||||
assert len(lines) == 3
|
||||
assert "Alice: Hello there." in lines[0]
|
||||
assert "Bob: Hi back." in lines[1]
|
||||
assert "Alice: Good morning." in lines[2]
|
||||
|
||||
json_result = transcript_to_json_segments(topics, participants)
|
||||
assert len(json_result) == 3
|
||||
assert json_result[0].speaker_name == "Alice"
|
||||
assert json_result[1].speaker_name == "Bob"
|
||||
assert json_result[2].speaker_name == "Alice"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_formats_with_overlapping_speakers_multitrack():
|
||||
"""Test format conversion for multitrack recordings with truly interleaved words.
|
||||
|
||||
Multitrack recordings have words from different speakers sorted by start time,
|
||||
causing frequent speaker alternation. This tests the sentence-based segmentation
|
||||
that groups each speaker's words into complete sentences.
|
||||
"""
|
||||
# Real multitrack data: words sorted by start time, speakers interleave
|
||||
# Alice says: "Hello there." (0.0-1.0)
|
||||
# Bob says: "I'm good." (0.5-1.5)
|
||||
# When sorted by time, words interleave: Hello, I'm, there., good.
|
||||
topics = [
|
||||
TranscriptTopic(
|
||||
id="1",
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0.0,
|
||||
words=[
|
||||
Word(text="Hello ", start=0.0, end=0.5, speaker=0),
|
||||
Word(text="I'm ", start=0.5, end=0.8, speaker=1),
|
||||
Word(text="there.", start=0.5, end=1.0, speaker=0),
|
||||
Word(text="good.", start=1.0, end=1.5, speaker=1),
|
||||
],
|
||||
),
|
||||
]
|
||||
|
||||
participants = [
|
||||
TranscriptParticipant(id="1", speaker=0, name="Alice"),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Bob"),
|
||||
]
|
||||
|
||||
# With is_multitrack=True, should produce 2 segments (one per speaker sentence)
|
||||
# not 4 segments (one per speaker change)
|
||||
webvtt_result = topics_to_webvtt_named(topics, participants, is_multitrack=True)
|
||||
expected_webvtt = """WEBVTT
|
||||
|
||||
00:00:00.000 --> 00:00:01.000
|
||||
<v Alice>Hello there.
|
||||
|
||||
00:00:00.500 --> 00:00:01.500
|
||||
<v Bob>I'm good.
|
||||
"""
|
||||
assert webvtt_result == expected_webvtt
|
||||
|
||||
text_result = transcript_to_text(topics, participants, is_multitrack=True)
|
||||
lines = text_result.split("\n")
|
||||
assert len(lines) == 2
|
||||
assert "Alice: Hello there." in lines[0]
|
||||
assert "Bob: I'm good." in lines[1]
|
||||
|
||||
timestamped_result = transcript_to_text_timestamped(
|
||||
topics, participants, is_multitrack=True
|
||||
)
|
||||
timestamped_lines = timestamped_result.split("\n")
|
||||
assert len(timestamped_lines) == 2
|
||||
assert "[00:00] Alice: Hello there." in timestamped_lines[0]
|
||||
assert "[00:00] Bob: I'm good." in timestamped_lines[1]
|
||||
|
||||
segments = transcript_to_json_segments(topics, participants, is_multitrack=True)
|
||||
assert len(segments) == 2
|
||||
assert segments[0].speaker_name == "Alice"
|
||||
assert segments[0].text == "Hello there."
|
||||
assert segments[1].speaker_name == "Bob"
|
||||
assert segments[1].text == "I'm good."
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_transcript_format_text(client):
|
||||
"""Test GET /transcripts/{id} with transcript_format=text."""
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(
|
||||
id="1", speaker=0, name="John Smith"
|
||||
).model_dump(),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Jane Doe").model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello", start=0, end=1, speaker=0),
|
||||
Word(text=" world.", start=1, end=2, speaker=0),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(f"/transcripts/{tid}?transcript_format=text")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert data["transcript_format"] == "text"
|
||||
assert "transcript" in data
|
||||
assert "John Smith: Hello world." in data["transcript"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_transcript_format_text_timestamped(client):
|
||||
"""Test GET /transcripts/{id} with transcript_format=text-timestamped."""
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(
|
||||
id="1", speaker=0, name="John Smith"
|
||||
).model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello", start=65, end=66, speaker=0),
|
||||
Word(text=" world.", start=66, end=67, speaker=0),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(
|
||||
f"/transcripts/{tid}?transcript_format=text-timestamped"
|
||||
)
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert data["transcript_format"] == "text-timestamped"
|
||||
assert "transcript" in data
|
||||
assert "[01:05] John Smith: Hello world." in data["transcript"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_transcript_format_webvtt_named(client):
|
||||
"""Test GET /transcripts/{id} with transcript_format=webvtt-named."""
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(
|
||||
id="1", speaker=0, name="John Smith"
|
||||
).model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello", start=0, end=1, speaker=0),
|
||||
Word(text=" world.", start=1, end=2, speaker=0),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(f"/transcripts/{tid}?transcript_format=webvtt-named")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert data["transcript_format"] == "webvtt-named"
|
||||
assert "transcript" in data
|
||||
assert "WEBVTT" in data["transcript"]
|
||||
assert "<v John Smith>" in data["transcript"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_transcript_format_json(client):
|
||||
"""Test GET /transcripts/{id} with transcript_format=json."""
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(
|
||||
id="1", speaker=0, name="John Smith"
|
||||
).model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello", start=0, end=1, speaker=0),
|
||||
Word(text=" world.", start=1, end=2, speaker=0),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(f"/transcripts/{tid}?transcript_format=json")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert data["transcript_format"] == "json"
|
||||
assert "transcript" in data
|
||||
assert isinstance(data["transcript"], list)
|
||||
assert len(data["transcript"]) == 1
|
||||
assert data["transcript"][0]["speaker"] == 0
|
||||
assert data["transcript"][0]["speaker_name"] == "John Smith"
|
||||
assert data["transcript"][0]["text"] == "Hello world."
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_transcript_format_default_is_text(client):
|
||||
"""Test GET /transcripts/{id} defaults to text format."""
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
from reflector.db.transcripts import TranscriptTopic, transcripts_controller
|
||||
from reflector.processors.types import Word
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello", start=0, end=1, speaker=0),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(f"/transcripts/{tid}")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert data["transcript_format"] == "text"
|
||||
assert "transcript" in data
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_topics_endpoint_multitrack_segmentation(client):
|
||||
"""Test GET /transcripts/{id}/topics uses sentence-based segmentation for multitrack.
|
||||
|
||||
This tests the fix for TASKS2.md - ensuring /topics endpoints correctly detect
|
||||
multitrack recordings and use sentence-based segmentation instead of fragmenting
|
||||
on every speaker change.
|
||||
"""
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from reflector.db.recordings import Recording, recordings_controller
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
# Create a multitrack recording (has track_keys)
|
||||
recording = Recording(
|
||||
bucket_name="test-bucket",
|
||||
object_key="test-key",
|
||||
recorded_at=datetime.now(timezone.utc),
|
||||
track_keys=["track1.webm", "track2.webm"], # This makes it multitrack
|
||||
)
|
||||
await recordings_controller.create(recording)
|
||||
|
||||
# Create transcript linked to the recording
|
||||
transcript = await transcripts_controller.add(
|
||||
name="Multitrack Test",
|
||||
source_kind="file",
|
||||
recording_id=recording.id,
|
||||
)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
# Add interleaved words (as they appear in real multitrack data)
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello ", start=0.0, end=0.5, speaker=0),
|
||||
Word(text="I'm ", start=0.5, end=0.8, speaker=1),
|
||||
Word(text="there.", start=0.5, end=1.0, speaker=0),
|
||||
Word(text="good.", start=1.0, end=1.5, speaker=1),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
# Test /topics endpoint
|
||||
response = await client.get(f"/transcripts/{transcript.id}/topics")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert len(data) == 1
|
||||
topic = data[0]
|
||||
|
||||
# Key assertion: multitrack should produce 2 segments (one per speaker sentence)
|
||||
# Not 4 segments (one per speaker change)
|
||||
assert len(topic["segments"]) == 2
|
||||
|
||||
# Check content
|
||||
segment_texts = [s["text"] for s in topic["segments"]]
|
||||
assert "Hello there." in segment_texts
|
||||
assert "I'm good." in segment_texts
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_topics_endpoint_non_multitrack_segmentation(client):
|
||||
"""Test GET /transcripts/{id}/topics uses default segmentation for non-multitrack.
|
||||
|
||||
Ensures backward compatibility - transcripts without multitrack recordings
|
||||
should continue using the default speaker-change-based segmentation.
|
||||
"""
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
# Create transcript WITHOUT recording (defaulted as not multitrack) TODO better heuristic
|
||||
response = await client.post("/transcripts", json={"name": "Test transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
transcript = await transcripts_controller.get_by_id(tid)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
# Add interleaved words
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello ", start=0.0, end=0.5, speaker=0),
|
||||
Word(text="I'm ", start=0.5, end=0.8, speaker=1),
|
||||
Word(text="there.", start=0.5, end=1.0, speaker=0),
|
||||
Word(text="good.", start=1.0, end=1.5, speaker=1),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
# Test /topics endpoint
|
||||
response = await client.get(f"/transcripts/{tid}/topics")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert len(data) == 1
|
||||
topic = data[0]
|
||||
|
||||
# Non-multitrack: should produce 4 segments (one per speaker change)
|
||||
assert len(topic["segments"]) == 4
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_api_topics_with_words_endpoint_multitrack(client):
|
||||
"""Test GET /transcripts/{id}/topics/with-words uses multitrack segmentation."""
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from reflector.db.recordings import Recording, recordings_controller
|
||||
from reflector.db.transcripts import (
|
||||
TranscriptParticipant,
|
||||
TranscriptTopic,
|
||||
transcripts_controller,
|
||||
)
|
||||
from reflector.processors.types import Word
|
||||
|
||||
# Create multitrack recording
|
||||
recording = Recording(
|
||||
bucket_name="test-bucket",
|
||||
object_key="test-key-2",
|
||||
recorded_at=datetime.now(timezone.utc),
|
||||
track_keys=["track1.webm", "track2.webm"],
|
||||
)
|
||||
await recordings_controller.create(recording)
|
||||
|
||||
transcript = await transcripts_controller.add(
|
||||
name="Multitrack Test 2",
|
||||
source_kind="file",
|
||||
recording_id=recording.id,
|
||||
)
|
||||
|
||||
await transcripts_controller.update(
|
||||
transcript,
|
||||
{
|
||||
"participants": [
|
||||
TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
|
||||
TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
await transcripts_controller.upsert_topic(
|
||||
transcript,
|
||||
TranscriptTopic(
|
||||
title="Topic 1",
|
||||
summary="Summary 1",
|
||||
timestamp=0,
|
||||
words=[
|
||||
Word(text="Hello ", start=0.0, end=0.5, speaker=0),
|
||||
Word(text="I'm ", start=0.5, end=0.8, speaker=1),
|
||||
Word(text="there.", start=0.5, end=1.0, speaker=0),
|
||||
Word(text="good.", start=1.0, end=1.5, speaker=1),
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
response = await client.get(f"/transcripts/{transcript.id}/topics/with-words")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
|
||||
assert len(data) == 1
|
||||
topic = data[0]
|
||||
|
||||
# Should have 2 segments (multitrack sentence-based)
|
||||
assert len(topic["segments"]) == 2
|
||||
# Should also have words field
|
||||
assert "words" in topic
|
||||
assert len(topic["words"]) == 4
|
||||
@@ -1,8 +1,5 @@
|
||||
import pytest
|
||||
|
||||
from reflector.db.rooms import rooms_controller
|
||||
from reflector.db.transcripts import transcripts_controller
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_create(client):
|
||||
@@ -185,51 +182,3 @@ async def test_transcript_mark_reviewed(authenticated_client, client):
|
||||
response = await client.get(f"/transcripts/{tid}")
|
||||
assert response.status_code == 200
|
||||
assert response.json()["reviewed"] is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_get_returns_room_name(authenticated_client, client):
|
||||
"""Test that getting a transcript returns its room_name when linked to a room."""
|
||||
# Create a room
|
||||
room = await rooms_controller.add(
|
||||
name="test-room-for-transcript",
|
||||
user_id="test-user",
|
||||
zulip_auto_post=False,
|
||||
zulip_stream="",
|
||||
zulip_topic="",
|
||||
is_locked=False,
|
||||
room_mode="normal",
|
||||
recording_type="cloud",
|
||||
recording_trigger="automatic-2nd-participant",
|
||||
is_shared=False,
|
||||
webhook_url="",
|
||||
webhook_secret="",
|
||||
)
|
||||
|
||||
# Create a transcript linked to the room
|
||||
transcript = await transcripts_controller.add(
|
||||
name="transcript-with-room",
|
||||
source_kind="file",
|
||||
room_id=room.id,
|
||||
)
|
||||
|
||||
# Get the transcript and verify room_name is returned
|
||||
response = await client.get(f"/transcripts/{transcript.id}")
|
||||
assert response.status_code == 200
|
||||
assert response.json()["room_id"] == room.id
|
||||
assert response.json()["room_name"] == "test-room-for-transcript"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_transcript_get_returns_null_room_name_when_no_room(
|
||||
authenticated_client, client
|
||||
):
|
||||
"""Test that room_name is null when transcript has no room."""
|
||||
response = await client.post("/transcripts", json={"name": "no-room-transcript"})
|
||||
assert response.status_code == 200
|
||||
tid = response.json()["id"]
|
||||
|
||||
response = await client.get(f"/transcripts/{tid}")
|
||||
assert response.status_code == 200
|
||||
assert response.json()["room_id"] is None
|
||||
assert response.json()["room_name"] is None
|
||||
|
||||
@@ -15,12 +15,9 @@ import {
|
||||
createListCollection,
|
||||
useDisclosure,
|
||||
Tabs,
|
||||
Popover,
|
||||
Text,
|
||||
HStack,
|
||||
} from "@chakra-ui/react";
|
||||
import { useEffect, useMemo, useState } from "react";
|
||||
import { LuEye, LuEyeOff, LuInfo } from "react-icons/lu";
|
||||
import { LuEye, LuEyeOff } from "react-icons/lu";
|
||||
import useRoomList from "./useRoomList";
|
||||
import type { components } from "../../reflector-api";
|
||||
import {
|
||||
@@ -70,11 +67,6 @@ const recordingTypeOptions: SelectOption[] = [
|
||||
{ label: "Cloud", value: "cloud" },
|
||||
];
|
||||
|
||||
const platformOptions: SelectOption[] = [
|
||||
{ label: "Whereby", value: "whereby" },
|
||||
{ label: "Daily", value: "daily" },
|
||||
];
|
||||
|
||||
const roomInitialState = {
|
||||
name: "",
|
||||
zulipAutoPost: false,
|
||||
@@ -90,7 +82,6 @@ const roomInitialState = {
|
||||
icsUrl: "",
|
||||
icsEnabled: false,
|
||||
icsFetchInterval: 5,
|
||||
platform: "whereby",
|
||||
};
|
||||
|
||||
export default function RoomsList() {
|
||||
@@ -108,11 +99,6 @@ export default function RoomsList() {
|
||||
const recordingTypeCollection = createListCollection({
|
||||
items: recordingTypeOptions,
|
||||
});
|
||||
|
||||
const platformCollection = createListCollection({
|
||||
items: platformOptions,
|
||||
});
|
||||
|
||||
const [roomInput, setRoomInput] = useState<null | typeof roomInitialState>(
|
||||
null,
|
||||
);
|
||||
@@ -157,24 +143,15 @@ export default function RoomsList() {
|
||||
zulipStream: detailedEditedRoom.zulip_stream,
|
||||
zulipTopic: detailedEditedRoom.zulip_topic,
|
||||
isLocked: detailedEditedRoom.is_locked,
|
||||
roomMode:
|
||||
detailedEditedRoom.platform === "daily"
|
||||
? "group"
|
||||
: detailedEditedRoom.room_mode,
|
||||
roomMode: detailedEditedRoom.room_mode,
|
||||
recordingType: detailedEditedRoom.recording_type,
|
||||
recordingTrigger:
|
||||
detailedEditedRoom.platform === "daily"
|
||||
? detailedEditedRoom.recording_type === "cloud"
|
||||
? "automatic-2nd-participant"
|
||||
: "none"
|
||||
: detailedEditedRoom.recording_trigger,
|
||||
recordingTrigger: detailedEditedRoom.recording_trigger,
|
||||
isShared: detailedEditedRoom.is_shared,
|
||||
webhookUrl: detailedEditedRoom.webhook_url || "",
|
||||
webhookSecret: detailedEditedRoom.webhook_secret || "",
|
||||
icsUrl: detailedEditedRoom.ics_url || "",
|
||||
icsEnabled: detailedEditedRoom.ics_enabled || false,
|
||||
icsFetchInterval: detailedEditedRoom.ics_fetch_interval || 5,
|
||||
platform: detailedEditedRoom.platform,
|
||||
}
|
||||
: null,
|
||||
[detailedEditedRoom],
|
||||
@@ -300,32 +277,21 @@ export default function RoomsList() {
|
||||
return;
|
||||
}
|
||||
|
||||
const platform: "whereby" | "daily" | null =
|
||||
room.platform === "whereby" || room.platform === "daily"
|
||||
? room.platform
|
||||
: null;
|
||||
|
||||
const roomData = {
|
||||
name: room.name,
|
||||
zulip_auto_post: room.zulipAutoPost,
|
||||
zulip_stream: room.zulipStream,
|
||||
zulip_topic: room.zulipTopic,
|
||||
is_locked: room.isLocked,
|
||||
room_mode: platform === "daily" ? "group" : room.roomMode,
|
||||
room_mode: room.roomMode,
|
||||
recording_type: room.recordingType,
|
||||
recording_trigger:
|
||||
platform === "daily"
|
||||
? room.recordingType === "cloud"
|
||||
? "automatic-2nd-participant"
|
||||
: "none"
|
||||
: room.recordingTrigger,
|
||||
recording_trigger: room.recordingTrigger,
|
||||
is_shared: room.isShared,
|
||||
webhook_url: room.webhookUrl,
|
||||
webhook_secret: room.webhookSecret,
|
||||
ics_url: room.icsUrl,
|
||||
ics_enabled: room.icsEnabled,
|
||||
ics_fetch_interval: room.icsFetchInterval,
|
||||
platform,
|
||||
};
|
||||
|
||||
if (isEditing) {
|
||||
@@ -373,21 +339,15 @@ export default function RoomsList() {
|
||||
zulipStream: roomData.zulip_stream,
|
||||
zulipTopic: roomData.zulip_topic,
|
||||
isLocked: roomData.is_locked,
|
||||
roomMode: roomData.platform === "daily" ? "group" : roomData.room_mode, // Daily always uses 2-200
|
||||
roomMode: roomData.room_mode,
|
||||
recordingType: roomData.recording_type,
|
||||
recordingTrigger:
|
||||
roomData.platform === "daily"
|
||||
? roomData.recording_type === "cloud"
|
||||
? "automatic-2nd-participant"
|
||||
: "none"
|
||||
: roomData.recording_trigger,
|
||||
recordingTrigger: roomData.recording_trigger,
|
||||
isShared: roomData.is_shared,
|
||||
webhookUrl: roomData.webhook_url || "",
|
||||
webhookSecret: roomData.webhook_secret || "",
|
||||
icsUrl: roomData.ics_url || "",
|
||||
icsEnabled: roomData.ics_enabled || false,
|
||||
icsFetchInterval: roomData.ics_fetch_interval || 5,
|
||||
platform: roomData.platform,
|
||||
});
|
||||
setEditRoomId(roomId);
|
||||
setIsEditing(true);
|
||||
@@ -522,52 +482,6 @@ export default function RoomsList() {
|
||||
)}
|
||||
</Field.Root>
|
||||
|
||||
<Field.Root mt={4}>
|
||||
<Field.Label>Platform</Field.Label>
|
||||
<Select.Root
|
||||
value={[room.platform]}
|
||||
onValueChange={(e) => {
|
||||
const newPlatform = e.value[0] as "whereby" | "daily";
|
||||
const updates: Partial<typeof room> = {
|
||||
platform: newPlatform,
|
||||
};
|
||||
if (newPlatform === "daily") {
|
||||
updates.roomMode = "group";
|
||||
updates.recordingTrigger =
|
||||
room.recordingType === "cloud"
|
||||
? "automatic-2nd-participant"
|
||||
: "none";
|
||||
} else {
|
||||
if (room.recordingType !== "cloud") {
|
||||
updates.recordingTrigger = "none";
|
||||
}
|
||||
}
|
||||
setRoomInput({ ...room, ...updates });
|
||||
}}
|
||||
collection={platformCollection}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
<Select.Control>
|
||||
<Select.Trigger>
|
||||
<Select.ValueText placeholder="Select platform" />
|
||||
</Select.Trigger>
|
||||
<Select.IndicatorGroup>
|
||||
<Select.Indicator />
|
||||
</Select.IndicatorGroup>
|
||||
</Select.Control>
|
||||
<Select.Positioner>
|
||||
<Select.Content>
|
||||
{platformOptions.map((option) => (
|
||||
<Select.Item key={option.value} item={option}>
|
||||
{option.label}
|
||||
<Select.ItemIndicator />
|
||||
</Select.Item>
|
||||
))}
|
||||
</Select.Content>
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
|
||||
<Field.Root mt={4}>
|
||||
<Checkbox.Root
|
||||
name="isLocked"
|
||||
@@ -590,95 +504,50 @@ export default function RoomsList() {
|
||||
<Checkbox.Label>Locked room</Checkbox.Label>
|
||||
</Checkbox.Root>
|
||||
</Field.Root>
|
||||
{room.platform !== "daily" && (
|
||||
<Field.Root mt={4}>
|
||||
<Field.Label>Room size</Field.Label>
|
||||
<Select.Root
|
||||
value={[room.roomMode]}
|
||||
onValueChange={(e) =>
|
||||
setRoomInput({ ...room, roomMode: e.value[0] })
|
||||
}
|
||||
collection={roomModeCollection}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
<Select.Control>
|
||||
<Select.Trigger>
|
||||
<Select.ValueText placeholder="Select room size" />
|
||||
</Select.Trigger>
|
||||
<Select.IndicatorGroup>
|
||||
<Select.Indicator />
|
||||
</Select.IndicatorGroup>
|
||||
</Select.Control>
|
||||
<Select.Positioner>
|
||||
<Select.Content>
|
||||
{roomModeOptions.map((option) => (
|
||||
<Select.Item key={option.value} item={option}>
|
||||
{option.label}
|
||||
<Select.ItemIndicator />
|
||||
</Select.Item>
|
||||
))}
|
||||
</Select.Content>
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
)}
|
||||
<Field.Root mt={4}>
|
||||
<HStack gap={2} alignItems="center">
|
||||
<Field.Label>Recording type</Field.Label>
|
||||
<Popover.Root>
|
||||
<Popover.Trigger asChild>
|
||||
<IconButton
|
||||
aria-label="Recording type help"
|
||||
variant="ghost"
|
||||
size="xs"
|
||||
colorPalette="gray"
|
||||
>
|
||||
<LuInfo />
|
||||
</IconButton>
|
||||
</Popover.Trigger>
|
||||
<Popover.Positioner>
|
||||
<Popover.Content>
|
||||
<Popover.Arrow />
|
||||
<Popover.Body>
|
||||
<Text fontSize="sm" lineHeight="1.6">
|
||||
<strong>None:</strong> No recording will be
|
||||
created.
|
||||
<br />
|
||||
<br />
|
||||
<strong>Local:</strong> Recording happens on
|
||||
each participant's device. Files are saved
|
||||
locally.
|
||||
<br />
|
||||
<br />
|
||||
<strong>Cloud:</strong> Recording happens on
|
||||
the platform's servers and is available after
|
||||
the meeting ends.
|
||||
</Text>
|
||||
</Popover.Body>
|
||||
</Popover.Content>
|
||||
</Popover.Positioner>
|
||||
</Popover.Root>
|
||||
</HStack>
|
||||
<Field.Label>Room size</Field.Label>
|
||||
<Select.Root
|
||||
value={[room.roomMode]}
|
||||
onValueChange={(e) =>
|
||||
setRoomInput({ ...room, roomMode: e.value[0] })
|
||||
}
|
||||
collection={roomModeCollection}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
<Select.Control>
|
||||
<Select.Trigger>
|
||||
<Select.ValueText placeholder="Select room size" />
|
||||
</Select.Trigger>
|
||||
<Select.IndicatorGroup>
|
||||
<Select.Indicator />
|
||||
</Select.IndicatorGroup>
|
||||
</Select.Control>
|
||||
<Select.Positioner>
|
||||
<Select.Content>
|
||||
{roomModeOptions.map((option) => (
|
||||
<Select.Item key={option.value} item={option}>
|
||||
{option.label}
|
||||
<Select.ItemIndicator />
|
||||
</Select.Item>
|
||||
))}
|
||||
</Select.Content>
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
<Field.Root mt={4}>
|
||||
<Field.Label>Recording type</Field.Label>
|
||||
<Select.Root
|
||||
value={[room.recordingType]}
|
||||
onValueChange={(e) => {
|
||||
const newRecordingType = e.value[0];
|
||||
const updates: Partial<typeof room> = {
|
||||
recordingType: newRecordingType,
|
||||
};
|
||||
if (room.platform === "daily") {
|
||||
updates.recordingTrigger =
|
||||
newRecordingType === "cloud"
|
||||
? "automatic-2nd-participant"
|
||||
: "none";
|
||||
} else {
|
||||
updates.recordingTrigger =
|
||||
newRecordingType !== "cloud"
|
||||
onValueChange={(e) =>
|
||||
setRoomInput({
|
||||
...room,
|
||||
recordingType: e.value[0],
|
||||
recordingTrigger:
|
||||
e.value[0] !== "cloud"
|
||||
? "none"
|
||||
: room.recordingTrigger;
|
||||
}
|
||||
setRoomInput({ ...room, ...updates });
|
||||
}}
|
||||
: room.recordingTrigger,
|
||||
})
|
||||
}
|
||||
collection={recordingTypeCollection}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
@@ -702,77 +571,40 @@ export default function RoomsList() {
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
{room.recordingType === "cloud" &&
|
||||
room.platform !== "daily" && (
|
||||
<Field.Root mt={4}>
|
||||
<HStack gap={2} alignItems="center">
|
||||
<Field.Label>Recording start trigger</Field.Label>
|
||||
<Popover.Root>
|
||||
<Popover.Trigger asChild>
|
||||
<IconButton
|
||||
aria-label="Recording start trigger help"
|
||||
variant="ghost"
|
||||
size="xs"
|
||||
colorPalette="gray"
|
||||
>
|
||||
<LuInfo />
|
||||
</IconButton>
|
||||
</Popover.Trigger>
|
||||
<Popover.Positioner>
|
||||
<Popover.Content>
|
||||
<Popover.Arrow />
|
||||
<Popover.Body>
|
||||
<Text fontSize="sm" lineHeight="1.6">
|
||||
<strong>None:</strong> Recording must be
|
||||
started manually by a participant.
|
||||
<br />
|
||||
<br />
|
||||
<strong>Prompt:</strong> Participants will
|
||||
be prompted to start recording when they
|
||||
join.
|
||||
<br />
|
||||
<br />
|
||||
<strong>Automatic:</strong> Recording
|
||||
starts automatically when a second
|
||||
participant joins.
|
||||
</Text>
|
||||
</Popover.Body>
|
||||
</Popover.Content>
|
||||
</Popover.Positioner>
|
||||
</Popover.Root>
|
||||
</HStack>
|
||||
<Select.Root
|
||||
value={[room.recordingTrigger]}
|
||||
onValueChange={(e) =>
|
||||
setRoomInput({
|
||||
...room,
|
||||
recordingTrigger: e.value[0],
|
||||
})
|
||||
}
|
||||
collection={recordingTriggerCollection}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
<Select.Control>
|
||||
<Select.Trigger>
|
||||
<Select.ValueText placeholder="Select trigger" />
|
||||
</Select.Trigger>
|
||||
<Select.IndicatorGroup>
|
||||
<Select.Indicator />
|
||||
</Select.IndicatorGroup>
|
||||
</Select.Control>
|
||||
<Select.Positioner>
|
||||
<Select.Content>
|
||||
{recordingTriggerOptions.map((option) => (
|
||||
<Select.Item key={option.value} item={option}>
|
||||
{option.label}
|
||||
<Select.ItemIndicator />
|
||||
</Select.Item>
|
||||
))}
|
||||
</Select.Content>
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
)}
|
||||
<Field.Root mt={4}>
|
||||
<Field.Label>Cloud recording start trigger</Field.Label>
|
||||
<Select.Root
|
||||
value={[room.recordingTrigger]}
|
||||
onValueChange={(e) =>
|
||||
setRoomInput({
|
||||
...room,
|
||||
recordingTrigger: e.value[0],
|
||||
})
|
||||
}
|
||||
collection={recordingTriggerCollection}
|
||||
disabled={room.recordingType !== "cloud"}
|
||||
>
|
||||
<Select.HiddenSelect />
|
||||
<Select.Control>
|
||||
<Select.Trigger>
|
||||
<Select.ValueText placeholder="Select trigger" />
|
||||
</Select.Trigger>
|
||||
<Select.IndicatorGroup>
|
||||
<Select.Indicator />
|
||||
</Select.IndicatorGroup>
|
||||
</Select.Control>
|
||||
<Select.Positioner>
|
||||
<Select.Content>
|
||||
{recordingTriggerOptions.map((option) => (
|
||||
<Select.Item key={option.value} item={option}>
|
||||
{option.label}
|
||||
<Select.ItemIndicator />
|
||||
</Select.Item>
|
||||
))}
|
||||
</Select.Content>
|
||||
</Select.Positioner>
|
||||
</Select.Root>
|
||||
</Field.Root>
|
||||
|
||||
<Field.Root mt={4}>
|
||||
<Checkbox.Root
|
||||
|
||||
@@ -117,6 +117,15 @@ export default function TranscriptDetails(details: TranscriptDetails) {
|
||||
return <Modal title="Loading" text={"Loading transcript..."} />;
|
||||
}
|
||||
|
||||
if (mp3.error) {
|
||||
return (
|
||||
<Modal
|
||||
title="Transcription error"
|
||||
text={`There was an error loading the recording. Error: ${mp3.error}`}
|
||||
/>
|
||||
);
|
||||
}
|
||||
|
||||
return (
|
||||
<>
|
||||
<Grid
|
||||
@@ -138,12 +147,7 @@ export default function TranscriptDetails(details: TranscriptDetails) {
|
||||
/>
|
||||
) : !mp3.loading && (waveform.error || mp3.error) ? (
|
||||
<Box p={4} bg="red.100" borderRadius="md">
|
||||
<Text>
|
||||
Error loading{" "}
|
||||
{[waveform.error && "waveform", mp3.error && "mp3"]
|
||||
.filter(Boolean)
|
||||
.join(" and ")}
|
||||
</Text>
|
||||
<Text>Error loading this recording</Text>
|
||||
</Box>
|
||||
) : (
|
||||
<Skeleton h={14} />
|
||||
|
||||
@@ -1,16 +1,14 @@
|
||||
import { useState } from "react";
|
||||
import type { components, operations } from "../../reflector-api";
|
||||
type GetTranscriptWithParticipants =
|
||||
components["schemas"]["GetTranscriptWithParticipants"];
|
||||
import type { components } from "../../reflector-api";
|
||||
type GetTranscript = components["schemas"]["GetTranscript"];
|
||||
type GetTranscriptTopic = components["schemas"]["GetTranscriptTopic"];
|
||||
import { Button, BoxProps, Box, Menu, Text } from "@chakra-ui/react";
|
||||
import { LuChevronDown } from "react-icons/lu";
|
||||
import { client } from "../../lib/apiClient";
|
||||
import { toaster } from "../../components/ui/toaster";
|
||||
import { Button, BoxProps, Box } from "@chakra-ui/react";
|
||||
import { buildTranscriptWithTopics } from "./buildTranscriptWithTopics";
|
||||
import { useTranscriptParticipants } from "../../lib/apiHooks";
|
||||
|
||||
type ShareCopyProps = {
|
||||
finalSummaryElement: HTMLDivElement | null;
|
||||
transcript: GetTranscriptWithParticipants;
|
||||
transcript: GetTranscript;
|
||||
topics: GetTranscriptTopic[];
|
||||
};
|
||||
|
||||
@@ -22,33 +20,11 @@ export default function ShareCopy({
|
||||
}: ShareCopyProps & BoxProps) {
|
||||
const [isCopiedSummary, setIsCopiedSummary] = useState(false);
|
||||
const [isCopiedTranscript, setIsCopiedTranscript] = useState(false);
|
||||
const [isCopying, setIsCopying] = useState(false);
|
||||
|
||||
type ApiTranscriptFormat = NonNullable<
|
||||
operations["v1_transcript_get"]["parameters"]["query"]
|
||||
>["transcript_format"];
|
||||
const TRANSCRIPT_FORMATS = [
|
||||
"text",
|
||||
"text-timestamped",
|
||||
"webvtt-named",
|
||||
"json",
|
||||
] as const satisfies ApiTranscriptFormat[];
|
||||
type TranscriptFormat = (typeof TRANSCRIPT_FORMATS)[number];
|
||||
|
||||
const TRANSCRIPT_FORMAT_LABELS: { [k in TranscriptFormat]: string } = {
|
||||
text: "Plain text",
|
||||
"text-timestamped": "Text + timestamps",
|
||||
"webvtt-named": "WebVTT (named)",
|
||||
json: "JSON",
|
||||
};
|
||||
|
||||
const formatOptions = TRANSCRIPT_FORMATS.map((f) => ({
|
||||
value: f,
|
||||
label: TRANSCRIPT_FORMAT_LABELS[f],
|
||||
}));
|
||||
const participantsQuery = useTranscriptParticipants(transcript?.id || null);
|
||||
|
||||
const onCopySummaryClick = () => {
|
||||
const text_to_copy = finalSummaryElement?.innerText;
|
||||
|
||||
if (text_to_copy) {
|
||||
navigator.clipboard.writeText(text_to_copy).then(() => {
|
||||
setIsCopiedSummary(true);
|
||||
@@ -58,91 +34,27 @@ export default function ShareCopy({
|
||||
}
|
||||
};
|
||||
|
||||
const onCopyTranscriptFormatClick = async (format: TranscriptFormat) => {
|
||||
try {
|
||||
setIsCopying(true);
|
||||
const { data, error } = await client.GET(
|
||||
"/v1/transcripts/{transcript_id}",
|
||||
{
|
||||
params: {
|
||||
path: { transcript_id: transcript.id },
|
||||
query: { transcript_format: format },
|
||||
},
|
||||
},
|
||||
);
|
||||
if (error) {
|
||||
console.error("Failed to copy transcript:", error);
|
||||
toaster.create({
|
||||
duration: 3000,
|
||||
render: () => (
|
||||
<Box bg="red.500" color="white" px={4} py={3} borderRadius="md">
|
||||
<Text fontWeight="bold">Error</Text>
|
||||
<Text fontSize="sm">Failed to fetch transcript</Text>
|
||||
</Box>
|
||||
),
|
||||
});
|
||||
return;
|
||||
}
|
||||
const onCopyTranscriptClick = () => {
|
||||
const text_to_copy =
|
||||
buildTranscriptWithTopics(
|
||||
topics || [],
|
||||
participantsQuery?.data || null,
|
||||
transcript?.title || null,
|
||||
) || "";
|
||||
|
||||
const copiedText =
|
||||
format === "json"
|
||||
? JSON.stringify(data?.transcript ?? {}, null, 2)
|
||||
: String(data?.transcript ?? "");
|
||||
|
||||
if (copiedText) {
|
||||
await navigator.clipboard.writeText(copiedText);
|
||||
text_to_copy &&
|
||||
navigator.clipboard.writeText(text_to_copy).then(() => {
|
||||
setIsCopiedTranscript(true);
|
||||
// Reset the copied state after 2 seconds
|
||||
setTimeout(() => setIsCopiedTranscript(false), 2000);
|
||||
}
|
||||
} catch (e) {
|
||||
console.error("Failed to copy transcript:", e);
|
||||
toaster.create({
|
||||
duration: 3000,
|
||||
render: () => (
|
||||
<Box bg="red.500" color="white" px={4} py={3} borderRadius="md">
|
||||
<Text fontWeight="bold">Error</Text>
|
||||
<Text fontSize="sm">Failed to copy transcript</Text>
|
||||
</Box>
|
||||
),
|
||||
});
|
||||
} finally {
|
||||
setIsCopying(false);
|
||||
}
|
||||
};
|
||||
|
||||
return (
|
||||
<Box {...boxProps}>
|
||||
<Menu.Root
|
||||
closeOnSelect={true}
|
||||
lazyMount={true}
|
||||
positioning={{ gutter: 4 }}
|
||||
>
|
||||
<Menu.Trigger asChild>
|
||||
<Button
|
||||
mr={2}
|
||||
variant="subtle"
|
||||
loading={isCopying}
|
||||
loadingText="Copying..."
|
||||
>
|
||||
{isCopiedTranscript ? "Copied!" : "Copy Transcript"}
|
||||
<LuChevronDown style={{ marginLeft: 6 }} />
|
||||
</Button>
|
||||
</Menu.Trigger>
|
||||
<Menu.Positioner>
|
||||
<Menu.Content>
|
||||
{formatOptions.map((opt) => (
|
||||
<Menu.Item
|
||||
key={opt.value}
|
||||
value={opt.value}
|
||||
_hover={{ backgroundColor: "gray.100" }}
|
||||
onClick={() => onCopyTranscriptFormatClick(opt.value)}
|
||||
>
|
||||
{opt.label}
|
||||
</Menu.Item>
|
||||
))}
|
||||
</Menu.Content>
|
||||
</Menu.Positioner>
|
||||
</Menu.Root>
|
||||
<Button onClick={onCopyTranscriptClick} mr={2} variant="subtle">
|
||||
{isCopiedTranscript ? "Copied!" : "Copy Transcript"}
|
||||
</Button>
|
||||
<Button onClick={onCopySummaryClick} variant="subtle">
|
||||
{isCopiedSummary ? "Copied!" : "Copy Summary"}
|
||||
</Button>
|
||||
|
||||
@@ -2,29 +2,20 @@
|
||||
|
||||
import { Spinner, Link } from "@chakra-ui/react";
|
||||
import { useAuth } from "../lib/AuthProvider";
|
||||
import { usePathname } from "next/navigation";
|
||||
import { getLogoutRedirectUrl } from "../lib/auth";
|
||||
|
||||
export default function UserInfo() {
|
||||
const auth = useAuth();
|
||||
const pathname = usePathname();
|
||||
const status = auth.status;
|
||||
const isLoading = status === "loading";
|
||||
const isAuthenticated = status === "authenticated";
|
||||
const isRefreshing = status === "refreshing";
|
||||
|
||||
const callbackUrl = getLogoutRedirectUrl(pathname);
|
||||
|
||||
return isLoading ? (
|
||||
<Spinner size="xs" className="mx-3" />
|
||||
) : !isAuthenticated && !isRefreshing ? (
|
||||
<Link
|
||||
href="#"
|
||||
href="/"
|
||||
className="font-light px-2"
|
||||
onClick={(e) => {
|
||||
e.preventDefault();
|
||||
auth.signIn("authentik");
|
||||
}}
|
||||
onClick={() => auth.signIn("authentik")}
|
||||
>
|
||||
Log in
|
||||
</Link>
|
||||
@@ -32,7 +23,7 @@ export default function UserInfo() {
|
||||
<Link
|
||||
href="#"
|
||||
className="font-light px-2"
|
||||
onClick={() => auth.signOut({ callbackUrl })}
|
||||
onClick={() => auth.signOut({ callbackUrl: "/" })}
|
||||
>
|
||||
Log out
|
||||
</Link>
|
||||
|
||||
@@ -11,7 +11,6 @@ import {
|
||||
recordingTypeRequiresConsent,
|
||||
} from "../../lib/consent";
|
||||
import { useRoomJoinMeeting } from "../../lib/apiHooks";
|
||||
import { assertExists } from "../../lib/utils";
|
||||
|
||||
type Meeting = components["schemas"]["Meeting"];
|
||||
|
||||
@@ -23,15 +22,16 @@ export default function DailyRoom({ meeting }: DailyRoomProps) {
|
||||
const router = useRouter();
|
||||
const params = useParams();
|
||||
const auth = useAuth();
|
||||
const authLastUserId = auth.lastUserId;
|
||||
const status = auth.status;
|
||||
const containerRef = useRef<HTMLDivElement>(null);
|
||||
const joinMutation = useRoomJoinMeeting();
|
||||
const [joinedMeeting, setJoinedMeeting] = useState<Meeting | null>(null);
|
||||
|
||||
const roomName = params?.roomName as string;
|
||||
|
||||
// Always call /join to get a fresh token with user_id
|
||||
useEffect(() => {
|
||||
if (authLastUserId === undefined || !meeting?.id || !roomName) return;
|
||||
if (status === "loading" || !meeting?.id || !roomName) return;
|
||||
|
||||
const join = async () => {
|
||||
try {
|
||||
@@ -50,17 +50,18 @@ export default function DailyRoom({ meeting }: DailyRoomProps) {
|
||||
};
|
||||
|
||||
join();
|
||||
}, [meeting?.id, roomName, authLastUserId]);
|
||||
}, [meeting?.id, roomName, status]);
|
||||
|
||||
const roomUrl = joinedMeeting?.room_url;
|
||||
const roomUrl = joinedMeeting?.host_room_url || joinedMeeting?.room_url;
|
||||
const isLoading =
|
||||
status === "loading" || joinMutation.isPending || !joinedMeeting;
|
||||
|
||||
const handleLeave = useCallback(() => {
|
||||
router.push("/browse");
|
||||
}, [router]);
|
||||
|
||||
useEffect(() => {
|
||||
if (authLastUserId === undefined || !roomUrl || !containerRef.current)
|
||||
return;
|
||||
if (isLoading || !roomUrl || !containerRef.current) return;
|
||||
|
||||
let frame: DailyCall | null = null;
|
||||
let destroyed = false;
|
||||
@@ -91,41 +92,19 @@ export default function DailyRoom({ meeting }: DailyRoomProps) {
|
||||
|
||||
frame.on("joined-meeting", async () => {
|
||||
try {
|
||||
const frameInstance = assertExists(
|
||||
frame,
|
||||
"frame object got lost somewhere after frame.on was called",
|
||||
);
|
||||
|
||||
if (meeting.recording_type === "cloud") {
|
||||
console.log("Starting cloud recording");
|
||||
await frameInstance.startRecording({ type: "raw-tracks" });
|
||||
}
|
||||
await frame.startRecording({ type: "raw-tracks" });
|
||||
} catch (error) {
|
||||
console.error("Failed to start recording:", error);
|
||||
}
|
||||
});
|
||||
|
||||
await frame.join({
|
||||
url: roomUrl,
|
||||
sendSettings: {
|
||||
video: {
|
||||
// Optimize bandwidth for camera video
|
||||
// allowAdaptiveLayers automatically adjusts quality based on network conditions
|
||||
allowAdaptiveLayers: true,
|
||||
// Use bandwidth-optimized preset as fallback for browsers without adaptive support
|
||||
maxQuality: "medium",
|
||||
},
|
||||
// Note: screenVideo intentionally not configured to preserve full quality for screen shares
|
||||
},
|
||||
});
|
||||
await frame.join({ url: roomUrl });
|
||||
} catch (error) {
|
||||
console.error("Error creating Daily frame:", error);
|
||||
}
|
||||
};
|
||||
|
||||
createAndJoin().catch((error) => {
|
||||
console.error("Failed to create and join meeting:", error);
|
||||
});
|
||||
createAndJoin();
|
||||
|
||||
return () => {
|
||||
destroyed = true;
|
||||
@@ -135,9 +114,9 @@ export default function DailyRoom({ meeting }: DailyRoomProps) {
|
||||
});
|
||||
}
|
||||
};
|
||||
}, [roomUrl, authLastUserId, handleLeave]);
|
||||
}, [roomUrl, isLoading, handleLeave]);
|
||||
|
||||
if (authLastUserId === undefined) {
|
||||
if (isLoading) {
|
||||
return (
|
||||
<Center width="100vw" height="100vh">
|
||||
<Spinner size="xl" />
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
"use client";
|
||||
|
||||
import { createContext, useContext, useRef } from "react";
|
||||
import { createContext, useContext } from "react";
|
||||
import { useSession as useNextAuthSession } from "next-auth/react";
|
||||
import { signOut, signIn } from "next-auth/react";
|
||||
import { configureApiAuth } from "./apiClient";
|
||||
@@ -25,9 +25,6 @@ type AuthContextType = (
|
||||
update: () => Promise<Session | null>;
|
||||
signIn: typeof signIn;
|
||||
signOut: typeof signOut;
|
||||
// TODO probably rename isLoading to isReloading and make THIS field "isLoading"
|
||||
// undefined is "not known", null is "is certainly logged out"
|
||||
lastUserId: CustomSession["user"]["id"] | null | undefined;
|
||||
};
|
||||
|
||||
const AuthContext = createContext<AuthContextType | undefined>(undefined);
|
||||
@@ -44,15 +41,10 @@ const noopAuthContext: AuthContextType = {
|
||||
signOut: async () => {
|
||||
throw new Error("signOut not supposed to be called");
|
||||
},
|
||||
lastUserId: undefined,
|
||||
};
|
||||
|
||||
export function AuthProvider({ children }: { children: React.ReactNode }) {
|
||||
const { data: session, status, update } = useNextAuthSession();
|
||||
// referential comparison done in component, must be primitive /or cached
|
||||
const lastUserId = useRef<CustomSession["user"]["id"] | null | undefined>(
|
||||
null,
|
||||
);
|
||||
|
||||
const contextValue: AuthContextType = isAuthEnabled
|
||||
? {
|
||||
@@ -81,16 +73,11 @@ export function AuthProvider({ children }: { children: React.ReactNode }) {
|
||||
case "authenticated": {
|
||||
const customSession = assertCustomSession(session);
|
||||
if (customSession?.error === REFRESH_ACCESS_TOKEN_ERROR) {
|
||||
// warning: call order-dependent
|
||||
lastUserId.current = null;
|
||||
// token had expired but next auth still returns "authenticated" so show user unauthenticated state
|
||||
return {
|
||||
status: "unauthenticated" as const,
|
||||
};
|
||||
} else if (customSession?.accessToken) {
|
||||
// updates anyways with updated properties below
|
||||
// warning! execution order conscience, must be ran before reading lastUserId.current below
|
||||
lastUserId.current = customSession.user.id;
|
||||
return {
|
||||
status,
|
||||
accessToken: customSession.accessToken,
|
||||
@@ -105,8 +92,6 @@ export function AuthProvider({ children }: { children: React.ReactNode }) {
|
||||
}
|
||||
}
|
||||
case "unauthenticated": {
|
||||
// warning: call order-dependent
|
||||
lastUserId.current = null;
|
||||
return { status: "unauthenticated" as const };
|
||||
}
|
||||
default: {
|
||||
@@ -118,8 +103,6 @@ export function AuthProvider({ children }: { children: React.ReactNode }) {
|
||||
update,
|
||||
signIn,
|
||||
signOut,
|
||||
// for optimistic cases when we assume "loading" doesn't immediately invalidate the user
|
||||
lastUserId: lastUserId.current,
|
||||
}
|
||||
: noopAuthContext;
|
||||
|
||||
|
||||
@@ -18,8 +18,3 @@ export const LOGIN_REQUIRED_PAGES = [
|
||||
export const PROTECTED_PAGES = new RegExp(
|
||||
LOGIN_REQUIRED_PAGES.map((page) => `^${page}$`).join("|"),
|
||||
);
|
||||
|
||||
export function getLogoutRedirectUrl(pathname: string): string {
|
||||
const transcriptPagePattern = /^\/transcripts\/[^/]+$/;
|
||||
return transcriptPagePattern.test(pathname) ? pathname : "/";
|
||||
}
|
||||
|
||||
@@ -32,11 +32,6 @@ async function getUserId(accessToken: string): Promise<string | null> {
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
try {
|
||||
console.error(await response.text());
|
||||
} catch (e) {
|
||||
console.error("Failed to parse error response", e);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
@@ -148,7 +143,7 @@ export const authOptions = (): AuthOptions =>
|
||||
},
|
||||
async session({ session, token }) {
|
||||
const extendedToken = token as JWTWithAccessToken;
|
||||
console.log("extendedToken", extendedToken);
|
||||
|
||||
const userId = await getUserId(extendedToken.accessToken);
|
||||
|
||||
return {
|
||||
|
||||
486
www/app/reflector-api.d.ts
vendored
486
www/app/reflector-api.d.ts
vendored
@@ -696,7 +696,7 @@ export interface paths {
|
||||
patch?: never;
|
||||
trace?: never;
|
||||
};
|
||||
"/v1/daily/webhook": {
|
||||
"/v1/webhook": {
|
||||
parameters: {
|
||||
query?: never;
|
||||
header?: never;
|
||||
@@ -708,27 +708,6 @@ export interface paths {
|
||||
/**
|
||||
* Webhook
|
||||
* @description Handle Daily webhook events.
|
||||
*
|
||||
* Example webhook payload:
|
||||
* {
|
||||
* "version": "1.0.0",
|
||||
* "type": "recording.ready-to-download",
|
||||
* "id": "rec-rtd-c3df927c-f738-4471-a2b7-066fa7e95a6b-1692124192",
|
||||
* "payload": {
|
||||
* "recording_id": "08fa0b24-9220-44c5-846c-3f116cf8e738",
|
||||
* "room_name": "Xcm97xRZ08b2dePKb78g",
|
||||
* "start_ts": 1692124183,
|
||||
* "status": "finished",
|
||||
* "max_participants": 1,
|
||||
* "duration": 9,
|
||||
* "share_token": "ntDCL5k98Ulq", #gitleaks:allow
|
||||
* "s3_key": "api-test-1j8fizhzd30c/Xcm97xRZ08b2dePKb78g/1692124183028"
|
||||
* },
|
||||
* "event_ts": 1692124192
|
||||
* }
|
||||
*
|
||||
* Daily.co circuit-breaker: After 3+ failed responses (4xx/5xx), webhook
|
||||
* state→FAILED, stops sending events. Reset: scripts/recreate_daily_webhook.py
|
||||
*/
|
||||
post: operations["v1_webhook"];
|
||||
delete?: never;
|
||||
@@ -920,11 +899,81 @@ export interface components {
|
||||
target_language: string;
|
||||
source_kind?: components["schemas"]["SourceKind"] | null;
|
||||
};
|
||||
/**
|
||||
* DailyWebhookEvent
|
||||
* @description Daily webhook event structure.
|
||||
*/
|
||||
DailyWebhookEvent: {
|
||||
/** Type */
|
||||
type: string;
|
||||
/** Id */
|
||||
id: string;
|
||||
/** Ts */
|
||||
ts: number;
|
||||
/** Data */
|
||||
data: {
|
||||
[key: string]: unknown;
|
||||
};
|
||||
};
|
||||
/** DeletionStatus */
|
||||
DeletionStatus: {
|
||||
/** Status */
|
||||
status: string;
|
||||
};
|
||||
/** GetTranscript */
|
||||
GetTranscript: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
};
|
||||
/** GetTranscriptMinimal */
|
||||
GetTranscriptMinimal: {
|
||||
/** Id */
|
||||
@@ -1056,345 +1105,6 @@ export interface components {
|
||||
*/
|
||||
words_per_speaker: components["schemas"]["SpeakerWords"][];
|
||||
};
|
||||
/**
|
||||
* GetTranscriptWithJSON
|
||||
* @description Transcript response as structured JSON segments.
|
||||
*
|
||||
* Format: Array of segment objects with speaker info, text, and timing.
|
||||
* Example:
|
||||
* [
|
||||
* {
|
||||
* "speaker": 0,
|
||||
* "speaker_name": "John Smith",
|
||||
* "text": "Hello everyone",
|
||||
* "start": 0.0,
|
||||
* "end": 5.0
|
||||
* }
|
||||
* ]
|
||||
*/
|
||||
GetTranscriptWithJSON: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
/**
|
||||
* @description discriminator enum property added by openapi-typescript
|
||||
* @enum {string}
|
||||
*/
|
||||
transcript_format: "json";
|
||||
/** Transcript */
|
||||
transcript: components["schemas"]["TranscriptSegment"][];
|
||||
};
|
||||
/** GetTranscriptWithParticipants */
|
||||
GetTranscriptWithParticipants: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
};
|
||||
/**
|
||||
* GetTranscriptWithText
|
||||
* @description Transcript response with plain text format.
|
||||
*
|
||||
* Format: Speaker names followed by their dialogue, one line per segment.
|
||||
* Example:
|
||||
* John Smith: Hello everyone
|
||||
* Jane Doe: Hi there
|
||||
*/
|
||||
GetTranscriptWithText: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
/**
|
||||
* @description discriminator enum property added by openapi-typescript
|
||||
* @enum {string}
|
||||
*/
|
||||
transcript_format: "text";
|
||||
/** Transcript */
|
||||
transcript: string;
|
||||
};
|
||||
/**
|
||||
* GetTranscriptWithTextTimestamped
|
||||
* @description Transcript response with timestamped text format.
|
||||
*
|
||||
* Format: [MM:SS] timestamp prefix before each speaker and dialogue.
|
||||
* Example:
|
||||
* [00:00] John Smith: Hello everyone
|
||||
* [00:05] Jane Doe: Hi there
|
||||
*/
|
||||
GetTranscriptWithTextTimestamped: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
/**
|
||||
* @description discriminator enum property added by openapi-typescript
|
||||
* @enum {string}
|
||||
*/
|
||||
transcript_format: "text-timestamped";
|
||||
/** Transcript */
|
||||
transcript: string;
|
||||
};
|
||||
/**
|
||||
* GetTranscriptWithWebVTTNamed
|
||||
* @description Transcript response in WebVTT subtitle format with participant names.
|
||||
*
|
||||
* Format: Standard WebVTT with voice tags using participant names.
|
||||
* Example:
|
||||
* WEBVTT
|
||||
*
|
||||
* 00:00:00.000 --> 00:00:05.000
|
||||
* <v John Smith>Hello everyone
|
||||
*/
|
||||
GetTranscriptWithWebVTTNamed: {
|
||||
/** Id */
|
||||
id: string;
|
||||
/** User Id */
|
||||
user_id: string | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/**
|
||||
* Status
|
||||
* @enum {string}
|
||||
*/
|
||||
status:
|
||||
| "idle"
|
||||
| "uploaded"
|
||||
| "recording"
|
||||
| "processing"
|
||||
| "error"
|
||||
| "ended";
|
||||
/** Locked */
|
||||
locked: boolean;
|
||||
/** Duration */
|
||||
duration: number;
|
||||
/** Title */
|
||||
title: string | null;
|
||||
/** Short Summary */
|
||||
short_summary: string | null;
|
||||
/** Long Summary */
|
||||
long_summary: string | null;
|
||||
/** Created At */
|
||||
created_at: string;
|
||||
/**
|
||||
* Share Mode
|
||||
* @default private
|
||||
*/
|
||||
share_mode: string;
|
||||
/** Source Language */
|
||||
source_language: string | null;
|
||||
/** Target Language */
|
||||
target_language: string | null;
|
||||
/** Reviewed */
|
||||
reviewed: boolean;
|
||||
/** Meeting Id */
|
||||
meeting_id: string | null;
|
||||
source_kind: components["schemas"]["SourceKind"];
|
||||
/** Room Id */
|
||||
room_id?: string | null;
|
||||
/** Room Name */
|
||||
room_name?: string | null;
|
||||
/** Audio Deleted */
|
||||
audio_deleted?: boolean | null;
|
||||
/** Participants */
|
||||
participants: components["schemas"]["TranscriptParticipant"][] | null;
|
||||
/**
|
||||
* @description discriminator enum property added by openapi-typescript
|
||||
* @enum {string}
|
||||
*/
|
||||
transcript_format: "webvtt-named";
|
||||
/** Transcript */
|
||||
transcript: string;
|
||||
};
|
||||
/** HTTPValidationError */
|
||||
HTTPValidationError: {
|
||||
/** Detail */
|
||||
@@ -1523,6 +1233,7 @@ export interface components {
|
||||
} | null;
|
||||
/**
|
||||
* Platform
|
||||
* @default whereby
|
||||
* @enum {string}
|
||||
*/
|
||||
platform: "whereby" | "daily";
|
||||
@@ -1614,6 +1325,7 @@ export interface components {
|
||||
ics_last_etag?: string | null;
|
||||
/**
|
||||
* Platform
|
||||
* @default whereby
|
||||
* @enum {string}
|
||||
*/
|
||||
platform: "whereby" | "daily";
|
||||
@@ -1665,6 +1377,7 @@ export interface components {
|
||||
ics_last_etag?: string | null;
|
||||
/**
|
||||
* Platform
|
||||
* @default whereby
|
||||
* @enum {string}
|
||||
*/
|
||||
platform: "whereby" | "daily";
|
||||
@@ -1810,24 +1523,6 @@ export interface components {
|
||||
speaker: number | null;
|
||||
/** Name */
|
||||
name: string;
|
||||
/** User Id */
|
||||
user_id?: string | null;
|
||||
};
|
||||
/**
|
||||
* TranscriptSegment
|
||||
* @description A single transcript segment with speaker and timing information.
|
||||
*/
|
||||
TranscriptSegment: {
|
||||
/** Speaker */
|
||||
speaker: number;
|
||||
/** Speaker Name */
|
||||
speaker_name: string;
|
||||
/** Text */
|
||||
text: string;
|
||||
/** Start */
|
||||
start: number;
|
||||
/** End */
|
||||
end: number;
|
||||
};
|
||||
/** UpdateParticipant */
|
||||
UpdateParticipant: {
|
||||
@@ -2616,7 +2311,7 @@ export interface operations {
|
||||
[name: string]: unknown;
|
||||
};
|
||||
content: {
|
||||
"application/json": components["schemas"]["GetTranscriptWithParticipants"];
|
||||
"application/json": components["schemas"]["GetTranscript"];
|
||||
};
|
||||
};
|
||||
/** @description Validation Error */
|
||||
@@ -2674,13 +2369,7 @@ export interface operations {
|
||||
};
|
||||
v1_transcript_get: {
|
||||
parameters: {
|
||||
query?: {
|
||||
transcript_format?:
|
||||
| "text"
|
||||
| "text-timestamped"
|
||||
| "webvtt-named"
|
||||
| "json";
|
||||
};
|
||||
query?: never;
|
||||
header?: never;
|
||||
path: {
|
||||
transcript_id: string;
|
||||
@@ -2695,11 +2384,7 @@ export interface operations {
|
||||
[name: string]: unknown;
|
||||
};
|
||||
content: {
|
||||
"application/json":
|
||||
| components["schemas"]["GetTranscriptWithText"]
|
||||
| components["schemas"]["GetTranscriptWithTextTimestamped"]
|
||||
| components["schemas"]["GetTranscriptWithWebVTTNamed"]
|
||||
| components["schemas"]["GetTranscriptWithJSON"];
|
||||
"application/json": components["schemas"]["GetTranscript"];
|
||||
};
|
||||
};
|
||||
/** @description Validation Error */
|
||||
@@ -2765,7 +2450,7 @@ export interface operations {
|
||||
[name: string]: unknown;
|
||||
};
|
||||
content: {
|
||||
"application/json": components["schemas"]["GetTranscriptWithParticipants"];
|
||||
"application/json": components["schemas"]["GetTranscript"];
|
||||
};
|
||||
};
|
||||
/** @description Validation Error */
|
||||
@@ -3571,7 +3256,11 @@ export interface operations {
|
||||
path?: never;
|
||||
cookie?: never;
|
||||
};
|
||||
requestBody?: never;
|
||||
requestBody: {
|
||||
content: {
|
||||
"application/json": components["schemas"]["DailyWebhookEvent"];
|
||||
};
|
||||
};
|
||||
responses: {
|
||||
/** @description Successful Response */
|
||||
200: {
|
||||
@@ -3582,6 +3271,15 @@ export interface operations {
|
||||
"application/json": unknown;
|
||||
};
|
||||
};
|
||||
/** @description Validation Error */
|
||||
422: {
|
||||
headers: {
|
||||
[name: string]: unknown;
|
||||
};
|
||||
content: {
|
||||
"application/json": components["schemas"]["HTTPValidationError"];
|
||||
};
|
||||
};
|
||||
};
|
||||
};
|
||||
}
|
||||
|
||||
@@ -31,7 +31,7 @@
|
||||
"ioredis": "^5.7.0",
|
||||
"jest-worker": "^29.6.2",
|
||||
"lucide-react": "^0.525.0",
|
||||
"next": "^15.5.9",
|
||||
"next": "^15.5.3",
|
||||
"next-auth": "^4.24.7",
|
||||
"next-themes": "^0.4.6",
|
||||
"nuqs": "^2.4.3",
|
||||
|
||||
508
www/pnpm-lock.yaml
generated
508
www/pnpm-lock.yaml
generated
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user